From c751085943362143f84346d274e0011419c84202 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 12 Apr 2009 20:06:56 +0200 Subject: PM/Hibernate: Wait for SCSI devices scan to complete during resume There is a race between resume from hibernation and the asynchronous scanning of SCSI devices and to prevent it from happening we need to call scsi_complete_async_scans() during resume from hibernation. In addition, if the resume from hibernation is userland-driven, it's better to wait for all device probes in the kernel to complete before attempting to open the resume device. Signed-off-by: Rafael J. Wysocki Acked-by: Arjan van de Ven Signed-off-by: Linus Torvalds --- kernel/power/disk.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel/power/disk.c') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 5f21ab2bbcd..0854770b63b 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -22,6 +22,7 @@ #include #include #include +#include #include #include "power.h" @@ -644,6 +645,13 @@ static int software_resume(void) if (noresume) return 0; + /* + * We can't depend on SCSI devices being available after loading one of + * their modules if scsi_complete_async_scans() is not called and the + * resume device usually is a SCSI one. + */ + scsi_complete_async_scans(); + /* * name_to_dev_t() below takes a sysfs buffer mutex when sysfs * is configured into the kernel. Since the regular hibernate -- cgit v1.2.3 From 0c8454f56623505a99463405fd7d5664adfbb094 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 25 Apr 2009 00:16:06 +0200 Subject: PM/Hibernate: Fix waiting for image device to appear on resume Commit c751085943362143f84346d274e0011419c84202 ("PM/Hibernate: Wait for SCSI devices scan to complete during resume") added a call to scsi_complete_async_scans() to software_resume(), so that it waited for the SCSI scanning to complete, but the call was added at a wrong place. Namely, it should have been added after wait_for_device_probe(), which is called only if the image partition hasn't been specified yet. Also, it's reasonable to check if the image partition is present and only wait for the device probing and SCSI scanning to complete if it is not the case. Additionally, since noresume is checked right at the beginning of software_resume() and the function returns immediately if it's set, it doesn't make sense to check it once again later. Signed-off-by: Rafael J. Wysocki Signed-off-by: Linus Torvalds --- kernel/power/disk.c | 51 +++++++++++++++++++++++++++------------------------ 1 file changed, 27 insertions(+), 24 deletions(-) (limited to 'kernel/power/disk.c') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index 0854770b63b..e71ca9cd81b 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -645,13 +645,6 @@ static int software_resume(void) if (noresume) return 0; - /* - * We can't depend on SCSI devices being available after loading one of - * their modules if scsi_complete_async_scans() is not called and the - * resume device usually is a SCSI one. - */ - scsi_complete_async_scans(); - /* * name_to_dev_t() below takes a sysfs buffer mutex when sysfs * is configured into the kernel. Since the regular hibernate @@ -663,32 +656,42 @@ static int software_resume(void) * here to avoid lockdep complaining. */ mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING); + + if (swsusp_resume_device) + goto Check_image; + + if (!strlen(resume_file)) { + error = -ENOENT; + goto Unlock; + } + + pr_debug("PM: Checking image partition %s\n", resume_file); + + /* Check if the device is there */ + swsusp_resume_device = name_to_dev_t(resume_file); if (!swsusp_resume_device) { - if (!strlen(resume_file)) { - mutex_unlock(&pm_mutex); - return -ENOENT; - } /* * Some device discovery might still be in progress; we need * to wait for this to finish. */ wait_for_device_probe(); + /* + * We can't depend on SCSI devices being available after loading + * one of their modules until scsi_complete_async_scans() is + * called and the resume device usually is a SCSI one. + */ + scsi_complete_async_scans(); + swsusp_resume_device = name_to_dev_t(resume_file); - pr_debug("PM: Resume from partition %s\n", resume_file); - } else { - pr_debug("PM: Resume from partition %d:%d\n", - MAJOR(swsusp_resume_device), - MINOR(swsusp_resume_device)); + if (!swsusp_resume_device) { + error = -ENODEV; + goto Unlock; + } } - if (noresume) { - /** - * FIXME: If noresume is specified, we need to find the - * partition and reset it back to normal swap space. - */ - mutex_unlock(&pm_mutex); - return 0; - } + Check_image: + pr_debug("PM: Resume from partition %d:%d\n", + MAJOR(swsusp_resume_device), MINOR(swsusp_resume_device)); pr_debug("PM: Checking hibernation image.\n"); error = swsusp_check(); -- cgit v1.2.3 From 4484079d517c2b6521621be0b1ea246ccc55c7d7 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Fri, 15 May 2009 23:30:50 +0200 Subject: PM: check sysdev_suspend(PMSG_FREEZE) return value Check the return value of sysdev_suspend(). I think this was a typo. Without this change, the following "if" check is always false. I also changed the error message so it's distinguishable from the similar message a few lines above. Signed-off-by: Bjorn Helgaas Acked-by: Pavel Machek Signed-off-by: Rafael J. Wysocki --- kernel/power/disk.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/power/disk.c') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index e71ca9cd81b..b0dc9e7a0d1 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -241,9 +241,9 @@ static int create_image(int platform_mode) local_irq_disable(); - sysdev_suspend(PMSG_FREEZE); + error = sysdev_suspend(PMSG_FREEZE); if (error) { - printk(KERN_ERR "PM: Some devices failed to power down, " + printk(KERN_ERR "PM: Some system devices failed to power down, " "aborting hibernation\n"); goto Enable_irqs; } -- cgit v1.2.3 From 32bdfac5462d777f35b00838893c4f87baf23efe Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 24 May 2009 21:15:07 +0200 Subject: PM: Do not hold dpm_list_mtx while disabling/enabling nonboot CPUs We shouldn't hold dpm_list_mtx while executing [disable|enable]_nonboot_cpus(), because theoretically this may lead to a deadlock as shown by the following example (provided by Johannes Berg): CPU 3 CPU 2 CPU 1 suspend/hibernate something: rtnl_lock() device_pm_lock() -> mutex_lock(&dpm_list_mtx) mutex_lock(&dpm_list_mtx) linkwatch_work -> rtnl_lock() disable_nonboot_cpus() -> flush CPU 3 workqueue Fortunately, device drivers are supposed to stop any activities that might lead to the registration of new device objects way before disable_nonboot_cpus() is called, so it shouldn't be necessary to hold dpm_list_mtx over the entire late part of device suspend and early part of device resume. Thus, during the late suspend and the early resume of devices acquire dpm_list_mtx only when dpm_list is going to be traversed and release it right after that. This patch is reported to fix the regressions tracked as http://bugzilla.kernel.org/show_bug.cgi?id=13245. Signed-off-by: Rafael J. Wysocki Acked-by: Alan Stern Reported-by: Miles Lane Tested-by: Ming Lei --- kernel/power/disk.c | 21 +++------------------ 1 file changed, 3 insertions(+), 18 deletions(-) (limited to 'kernel/power/disk.c') diff --git a/kernel/power/disk.c b/kernel/power/disk.c index b0dc9e7a0d1..5cb080e7eeb 100644 --- a/kernel/power/disk.c +++ b/kernel/power/disk.c @@ -215,8 +215,6 @@ static int create_image(int platform_mode) if (error) return error; - device_pm_lock(); - /* At this point, device_suspend() has been called, but *not* * device_power_down(). We *must* call device_power_down() now. * Otherwise, drivers for some devices (e.g. interrupt controllers) @@ -227,7 +225,7 @@ static int create_image(int platform_mode) if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting hibernation\n"); - goto Unlock; + return error; } error = platform_pre_snapshot(platform_mode); @@ -280,9 +278,6 @@ static int create_image(int platform_mode) device_power_up(in_suspend ? (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE); - Unlock: - device_pm_unlock(); - return error; } @@ -344,13 +339,11 @@ static int resume_target_kernel(bool platform_mode) { int error; - device_pm_lock(); - error = device_power_down(PMSG_QUIESCE); if (error) { printk(KERN_ERR "PM: Some devices failed to power down, " "aborting resume\n"); - goto Unlock; + return error; } error = platform_pre_restore(platform_mode); @@ -403,9 +396,6 @@ static int resume_target_kernel(bool platform_mode) device_power_up(PMSG_RECOVER); - Unlock: - device_pm_unlock(); - return error; } @@ -464,11 +454,9 @@ int hibernation_platform_enter(void) goto Resume_devices; } - device_pm_lock(); - error = device_power_down(PMSG_HIBERNATE); if (error) - goto Unlock; + goto Resume_devices; error = hibernation_ops->prepare(); if (error) @@ -493,9 +481,6 @@ int hibernation_platform_enter(void) device_power_up(PMSG_RESTORE); - Unlock: - device_pm_unlock(); - Resume_devices: entering_platform_hibernation = false; device_resume(PMSG_RESTORE); -- cgit v1.2.3