From 379e0be812ab8a2a351e784b0c987788f5123090 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Fri, 3 Feb 2012 22:22:41 +0100 Subject: PM / Freezer: Thaw only kernel threads if freezing of kernel threads fails If freezing of kernel threads fails, we are expected to automatically thaw tasks in the error recovery path. However, at times, we encounter situations in which we would like the automatic error recovery path to thaw only the kernel threads, because we want to be able to do some more cleanup before we thaw userspace. Something like: error = freeze_kernel_threads(); if (error) { /* Do some cleanup */ /* Only then thaw userspace tasks*/ thaw_processes(); } An example of such a situation is where we freeze/thaw filesystems during suspend/hibernation. There, if freezing of kernel threads fails, we would like to thaw the frozen filesystems before thawing the userspace tasks. So, modify freeze_kernel_threads() to thaw only kernel threads in case of freezing failure. And change suspend_freeze_processes() accordingly. (At the same time, let us also get rid of the rather cryptic usage of the conditional operator (:?) in that function.) [rjw: In fact, this patch fixes a regression introduced during the 3.3 merge window, because without it thaw_processes() may be called before swsusp_free() in some situations and that may lead to massive memory allocation failures.] Signed-off-by: Srivatsa S. Bhat Acked-by: Tejun Heo Acked-by: Nigel Cunningham Signed-off-by: Rafael J. Wysocki --- kernel/power/process.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'kernel/power/process.c') diff --git a/kernel/power/process.c b/kernel/power/process.c index eeca00311f39..7e426459e60a 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -143,7 +143,10 @@ int freeze_processes(void) /** * freeze_kernel_threads - Make freezable kernel threads go to the refrigerator. * - * On success, returns 0. On failure, -errno and system is fully thawed. + * On success, returns 0. On failure, -errno and only the kernel threads are + * thawed, so as to give a chance to the caller to do additional cleanups + * (if any) before thawing the userspace tasks. So, it is the responsibility + * of the caller to thaw the userspace tasks, when the time is right. */ int freeze_kernel_threads(void) { @@ -159,7 +162,7 @@ int freeze_kernel_threads(void) BUG_ON(in_atomic()); if (error) - thaw_processes(); + thaw_kernel_threads(); return error; } -- cgit v1.2.3 From 6c83b4818dd65eb17e633b6b629a81da7bed90b3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sat, 11 Feb 2012 00:00:34 +0100 Subject: PM / Sleep: Do not check wakeup too often in try_to_freeze_tasks() Use the observation that it is more efficient to check the wakeup variable once before the loop reporting tasks that were not frozen in try_to_freeze_tasks() than to do that in every step of that loop. Signed-off-by: Rafael J. Wysocki --- kernel/power/process.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'kernel/power/process.c') diff --git a/kernel/power/process.c b/kernel/power/process.c index 7e426459e60a..6aeb5efe00eb 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -98,13 +98,15 @@ static int try_to_freeze_tasks(bool user_only) elapsed_csecs / 100, elapsed_csecs % 100, todo - wq_busy, wq_busy); - read_lock(&tasklist_lock); - do_each_thread(g, p) { - if (!wakeup && !freezer_should_skip(p) && - p != current && freezing(p) && !frozen(p)) - sched_show_task(p); - } while_each_thread(g, p); - read_unlock(&tasklist_lock); + if (!wakeup) { + read_lock(&tasklist_lock); + do_each_thread(g, p) { + if (p != current && !freezer_should_skip(p) + && freezing(p) && !frozen(p)) + sched_show_task(p); + } while_each_thread(g, p); + read_unlock(&tasklist_lock); + } } else { printk("(elapsed %d.%02d seconds) ", elapsed_csecs / 100, elapsed_csecs % 100); -- cgit v1.2.3 From 37f08be11be9a7d9351fb1b9b408259519a126f3 Mon Sep 17 00:00:00 2001 From: Marcos Paulo de Souza Date: Tue, 21 Feb 2012 23:57:47 +0100 Subject: PM / Freezer: Remove references to TIF_FREEZE in comments This patch removes all the references in the code about the TIF_FREEZE flag removed by commit a3201227f803ad7fd43180c5195dbe5a2bf998aa freezer: make freezing() test freeze conditions in effect instead of TIF_FREEZE There still are some references to TIF_FREEZE in Documentation/power/freezing-of-tasks.txt, but it looks like that documentation needs more thorough work to reflect how the new freezer works, and hence merely removing the references to TIF_FREEZE won't really help. So I have not touched that part in this patch. Suggested-by: Srivatsa S. Bhat Signed-off-by: Marcos Paulo de Souza Signed-off-by: Rafael J. Wysocki --- kernel/exit.c | 2 +- kernel/freezer.c | 6 +++--- kernel/power/process.c | 8 +++----- 3 files changed, 7 insertions(+), 9 deletions(-) (limited to 'kernel/power/process.c') diff --git a/kernel/exit.c b/kernel/exit.c index 294b1709170d..fd0af05e0639 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -424,7 +424,7 @@ void daemonize(const char *name, ...) */ exit_mm(current); /* - * We don't want to have TIF_FREEZE set if the system-wide hibernation + * We don't want to get frozen, in case system-wide hibernation * or suspend transition begins right now. */ current->flags |= (PF_NOFREEZE | PF_KTHREAD); diff --git a/kernel/freezer.c b/kernel/freezer.c index 9815b8d1eed5..11f82a4d4eae 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -99,9 +99,9 @@ static void fake_signal_wake_up(struct task_struct *p) * freeze_task - send a freeze request to given task * @p: task to send the request to * - * If @p is freezing, the freeze request is sent by setting %TIF_FREEZE - * flag and either sending a fake signal to it or waking it up, depending - * on whether it has %PF_FREEZER_NOSIG set. + * If @p is freezing, the freeze request is sent either by sending a fake + * signal (if it's not a kernel thread) or waking it up (if it's a kernel + * thread). * * RETURNS: * %false, if @p is not freezing or already frozen; %true, otherwise diff --git a/kernel/power/process.c b/kernel/power/process.c index 6aeb5efe00eb..0d2aeb226108 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -53,11 +53,9 @@ static int try_to_freeze_tasks(bool user_only) * It is "frozen enough". If the task does wake * up, it will immediately call try_to_freeze. * - * Because freeze_task() goes through p's - * scheduler lock after setting TIF_FREEZE, it's - * guaranteed that either we see TASK_RUNNING or - * try_to_stop() after schedule() in ptrace/signal - * stop sees TIF_FREEZE. + * Because freeze_task() goes through p's scheduler lock, it's + * guaranteed that TASK_STOPPED/TRACED -> TASK_RUNNING + * transition can't race with task state testing here. */ if (!task_is_stopped_or_traced(p) && !freezer_should_skip(p)) -- cgit v1.2.3 From 1e73203cd1157a03facc41ffb54050f5b28e55bd Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 28 Mar 2012 23:30:21 +0200 Subject: PM / Sleep: Move disabling of usermode helpers to the freezer The core suspend/hibernation code calls usermodehelper_disable() to avoid race conditions between the freezer and the starting of usermode helpers and each code path has to do that on its own. However, it is always called right before freeze_processes() and usermodehelper_enable() is always called right after thaw_processes(). For this reason, to avoid code duplication and to make the connection between usermodehelper_disable() and the freezer more visible, make freeze_processes() call it and remove the direct usermodehelper_disable() and usermodehelper_enable() calls from all suspend/hibernation code paths. Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Cc: stable@vger.kernel.org --- kernel/power/hibernate.c | 11 ----------- kernel/power/process.c | 7 +++++++ kernel/power/suspend.c | 7 ------- kernel/power/user.c | 10 +--------- 4 files changed, 8 insertions(+), 27 deletions(-) (limited to 'kernel/power/process.c') diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index 639ff6e4ae9e..e09dfbfeecee 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -620,10 +619,6 @@ int hibernate(void) sys_sync(); printk("done.\n"); - error = usermodehelper_disable(); - if (error) - goto Exit; - error = freeze_processes(); if (error) goto Free_bitmaps; @@ -660,7 +655,6 @@ int hibernate(void) freezer_test_done = false; Free_bitmaps: - usermodehelper_enable(); free_basic_memory_bitmaps(); Exit: pm_notifier_call_chain(PM_POST_HIBERNATION); @@ -780,10 +774,6 @@ static int software_resume(void) if (error) goto close_finish; - error = usermodehelper_disable(); - if (error) - goto close_finish; - pr_debug("PM: Preparing processes for restore.\n"); error = freeze_processes(); if (error) { @@ -802,7 +792,6 @@ static int software_resume(void) swsusp_free(); thaw_processes(); Done: - usermodehelper_enable(); free_basic_memory_bitmaps(); Finish: pm_notifier_call_chain(PM_POST_RESTORE); diff --git a/kernel/power/process.c b/kernel/power/process.c index 0d2aeb226108..56eaac7e88ab 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -16,6 +16,7 @@ #include #include #include +#include /* * Timeout for stopping processes @@ -122,6 +123,10 @@ int freeze_processes(void) { int error; + error = usermodehelper_disable(); + if (error) + return error; + if (!pm_freezing) atomic_inc(&system_freezing_cnt); @@ -187,6 +192,8 @@ void thaw_processes(void) } while_each_thread(g, p); read_unlock(&tasklist_lock); + usermodehelper_enable(); + schedule(); printk("done.\n"); } diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index 88e5c967370d..396d262b8fd0 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -102,17 +101,12 @@ static int suspend_prepare(void) if (error) goto Finish; - error = usermodehelper_disable(); - if (error) - goto Finish; - error = suspend_freeze_processes(); if (!error) return 0; suspend_stats.failed_freeze++; dpm_save_failed_step(SUSPEND_FREEZE); - usermodehelper_enable(); Finish: pm_notifier_call_chain(PM_POST_SUSPEND); pm_restore_console(); @@ -259,7 +253,6 @@ int suspend_devices_and_enter(suspend_state_t state) static void suspend_finish(void) { suspend_thaw_processes(); - usermodehelper_enable(); pm_notifier_call_chain(PM_POST_SUSPEND); pm_restore_console(); } diff --git a/kernel/power/user.c b/kernel/power/user.c index 33c4329205af..91b0fd021a95 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include @@ -222,14 +221,8 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, sys_sync(); printk("done.\n"); - error = usermodehelper_disable(); - if (error) - break; - error = freeze_processes(); - if (error) - usermodehelper_enable(); - else + if (!error) data->frozen = 1; break; @@ -238,7 +231,6 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd, break; pm_restore_gfp_mask(); thaw_processes(); - usermodehelper_enable(); data->frozen = 0; break; -- cgit v1.2.3 From 247bc03742545fec2f79939a3b9f738392a0f7b4 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 28 Mar 2012 23:30:28 +0200 Subject: PM / Sleep: Mitigate race between the freezer and request_firmware() There is a race condition between the freezer and request_firmware() such that if request_firmware() is run on one CPU and freeze_processes() is run on another CPU and usermodehelper_disable() called by it succeeds to grab umhelper_sem for writing before usermodehelper_read_trylock() called from request_firmware() acquires it for reading, the request_firmware() will fail and trigger a WARN_ON() complaining that it was called at a wrong time. However, in fact, it wasn't called at a wrong time and freeze_processes() simply happened to be executed simultaneously. To avoid this race, at least in some cases, modify usermodehelper_read_trylock() so that it doesn't fail if the freezing of tasks has just started and hasn't been completed yet. Instead, during the freezing of tasks, it will try to freeze the task that has called it so that it can wait until user space is thawed without triggering the scary warning. For this purpose, change usermodehelper_disabled so that it can take three different values, UMH_ENABLED (0), UMH_FREEZING and UMH_DISABLED. The first one means that usermode helpers are enabled, the last one means "hard disable" (i.e. the system is not ready for usermode helpers to be used) and the second one is reserved for the freezer. Namely, when freeze_processes() is started, it sets usermodehelper_disabled to UMH_FREEZING which tells usermodehelper_read_trylock() that it shouldn't fail just yet and should call try_to_freeze() if woken up and cannot return immediately. This way all freezable tasks that happen to call request_firmware() right before freeze_processes() is started and lose the race for umhelper_sem with it will be frozen and will sleep until thaw_processes() unsets usermodehelper_disabled. [For the non-freezable callers of request_firmware() the race for umhelper_sem against freeze_processes() is unfortunately unavoidable.] Reported-by: Stephen Boyd Signed-off-by: Rafael J. Wysocki Acked-by: Greg Kroah-Hartman Cc: stable@vger.kernel.org --- include/linux/kmod.h | 21 +++++++++++++++++++-- kernel/kmod.c | 47 +++++++++++++++++++++++++++++++++++++---------- kernel/power/process.c | 3 ++- 3 files changed, 58 insertions(+), 13 deletions(-) (limited to 'kernel/power/process.c') diff --git a/include/linux/kmod.h b/include/linux/kmod.h index b087377ae2c4..dd99c329e161 100644 --- a/include/linux/kmod.h +++ b/include/linux/kmod.h @@ -110,10 +110,27 @@ call_usermodehelper(char *path, char **argv, char **envp, int wait) extern struct ctl_table usermodehelper_table[]; +enum umh_disable_depth { + UMH_ENABLED = 0, + UMH_FREEZING, + UMH_DISABLED, +}; + extern void usermodehelper_init(void); -extern int usermodehelper_disable(void); -extern void usermodehelper_enable(void); +extern int __usermodehelper_disable(enum umh_disable_depth depth); +extern void __usermodehelper_set_disable_depth(enum umh_disable_depth depth); + +static inline int usermodehelper_disable(void) +{ + return __usermodehelper_disable(UMH_DISABLED); +} + +static inline void usermodehelper_enable(void) +{ + __usermodehelper_set_disable_depth(UMH_ENABLED); +} + extern int usermodehelper_read_trylock(void); extern long usermodehelper_read_lock_wait(long timeout); extern void usermodehelper_read_unlock(void); diff --git a/kernel/kmod.c b/kernel/kmod.c index da7fcca279f9..05698a7415fe 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -322,7 +322,7 @@ static void __call_usermodehelper(struct work_struct *work) * land has been frozen during a system-wide hibernation or suspend operation). * Should always be manipulated under umhelper_sem acquired for write. */ -static int usermodehelper_disabled = 1; +static enum umh_disable_depth usermodehelper_disabled = UMH_DISABLED; /* Number of helpers running */ static atomic_t running_helpers = ATOMIC_INIT(0); @@ -347,13 +347,30 @@ static DECLARE_WAIT_QUEUE_HEAD(usermodehelper_disabled_waitq); int usermodehelper_read_trylock(void) { + DEFINE_WAIT(wait); int ret = 0; down_read(&umhelper_sem); - if (usermodehelper_disabled) { + for (;;) { + prepare_to_wait(&usermodehelper_disabled_waitq, &wait, + TASK_INTERRUPTIBLE); + if (!usermodehelper_disabled) + break; + + if (usermodehelper_disabled == UMH_DISABLED) + ret = -EAGAIN; + up_read(&umhelper_sem); - ret = -EAGAIN; + + if (ret) + break; + + schedule(); + try_to_freeze(); + + down_read(&umhelper_sem); } + finish_wait(&usermodehelper_disabled_waitq, &wait); return ret; } EXPORT_SYMBOL_GPL(usermodehelper_read_trylock); @@ -392,25 +409,35 @@ void usermodehelper_read_unlock(void) EXPORT_SYMBOL_GPL(usermodehelper_read_unlock); /** - * usermodehelper_enable - allow new helpers to be started again + * __usermodehelper_set_disable_depth - Modify usermodehelper_disabled. + * depth: New value to assign to usermodehelper_disabled. + * + * Change the value of usermodehelper_disabled (under umhelper_sem locked for + * writing) and wakeup tasks waiting for it to change. */ -void usermodehelper_enable(void) +void __usermodehelper_set_disable_depth(enum umh_disable_depth depth) { down_write(&umhelper_sem); - usermodehelper_disabled = 0; + usermodehelper_disabled = depth; wake_up(&usermodehelper_disabled_waitq); up_write(&umhelper_sem); } /** - * usermodehelper_disable - prevent new helpers from being started + * __usermodehelper_disable - Prevent new helpers from being started. + * @depth: New value to assign to usermodehelper_disabled. + * + * Set usermodehelper_disabled to @depth and wait for running helpers to exit. */ -int usermodehelper_disable(void) +int __usermodehelper_disable(enum umh_disable_depth depth) { long retval; + if (!depth) + return -EINVAL; + down_write(&umhelper_sem); - usermodehelper_disabled = 1; + usermodehelper_disabled = depth; up_write(&umhelper_sem); /* @@ -425,7 +452,7 @@ int usermodehelper_disable(void) if (retval) return 0; - usermodehelper_enable(); + __usermodehelper_set_disable_depth(UMH_ENABLED); return -EAGAIN; } diff --git a/kernel/power/process.c b/kernel/power/process.c index 56eaac7e88ab..19db29f67558 100644 --- a/kernel/power/process.c +++ b/kernel/power/process.c @@ -123,7 +123,7 @@ int freeze_processes(void) { int error; - error = usermodehelper_disable(); + error = __usermodehelper_disable(UMH_FREEZING); if (error) return error; @@ -135,6 +135,7 @@ int freeze_processes(void) error = try_to_freeze_tasks(true); if (!error) { printk("done."); + __usermodehelper_set_disable_depth(UMH_DISABLED); oom_killer_disable(); } printk("\n"); -- cgit v1.2.3