PM: Rework handling of interrupts during suspend-resume

Use the functions introduced in by the previous patch,
suspend_device_irqs(), resume_device_irqs() and check_wakeup_irqs(),
to rework the handling of interrupts during suspend (hibernation) and
resume.  Namely, interrupts will only be disabled on the CPU right
before suspending sysdevs, while device drivers will be prevented
from receiving interrupts, with the help of the new helper function,
before their "late" suspend callbacks run (and analogously during
resume).

In addition, since the device interrups are now disabled before the
CPU has turned all interrupts off and the CPU will ACK the interrupts
setting the IRQ_PENDING bit for them, check in sysdev_suspend() if
any wake-up interrupts are pending and abort suspend if that's the
case.

Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Ingo Molnar <mingo@elte.hu>

7 files changed, 83 insertions, 40 deletions

diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 10033fe718e0..ac7783a67432 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1190,8 +1190,10 @@ static int suspend(int vetoable)
         struct apm_user *as;
 
         device_suspend(PMSG_SUSPEND);
-        local_irq_disable();
+
         device_power_down(PMSG_SUSPEND);
+
+        local_irq_disable();
         sysdev_suspend(PMSG_SUSPEND);
 
         local_irq_enable();
@@ -1209,9 +1211,12 @@ static int suspend(int vetoable)
         if (err != APM_SUCCESS)
                 apm_error("suspend", err);
         err = (err == APM_SUCCESS) ? 0 : -EIO;
+
         sysdev_resume();
-        device_power_up(PMSG_RESUME);
         local_irq_enable();
+
+        device_power_up(PMSG_RESUME);
+
         device_resume(PMSG_RESUME);
         queue_event(APM_NORMAL_RESUME, NULL);
         spin_lock(&user_list_lock);
@@ -1228,8 +1233,9 @@ static void standby(void)
 {
         int err;
 
-        local_irq_disable();
         device_power_down(PMSG_SUSPEND);
+
+        local_irq_disable();
         sysdev_suspend(PMSG_SUSPEND);
         local_irq_enable();
 
@@ -1239,8 +1245,9 @@ static void standby(void)
 
         local_irq_disable();
         sysdev_resume();
-        device_power_up(PMSG_RESUME);
         local_irq_enable();
+
+        device_power_up(PMSG_RESUME);
 }
 
 static apm_event_t get_event(void)
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index e255341682c8..69b4ddb7de3b 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -23,6 +23,7 @@
 #include <linux/pm.h>
 #include <linux/resume-trace.h>
 #include <linux/rwsem.h>
+#include <linux/interrupt.h>
 
 #include "../base.h"
 #include "power.h"
@@ -349,7 +350,8 @@ static int resume_device_noirq(struct device *dev, pm_message_t state)
  *      Execute the appropriate "noirq resume" callback for all devices marked
  *      as DPM_OFF_IRQ.
  *
- *      Must be called with interrupts disabled and only one CPU running.
+ *      Must be called under dpm_list_mtx.  Device drivers should not receive
+ *      interrupts while it's being executed.
  */
 static void dpm_power_up(pm_message_t state)
 {
@@ -370,14 +372,13 @@ static void dpm_power_up(pm_message_t state)
  *      device_power_up - Turn on all devices that need special attention.
  *      @state: PM transition of the system being carried out.
  *
- *      Power on system devices, then devices that required we shut them down
- *      with interrupts disabled.
- *
- *      Must be called with interrupts disabled.
+ *      Call the "early" resume handlers and enable device drivers to receive
+ *      interrupts.
  */
 void device_power_up(pm_message_t state)
 {
         dpm_power_up(state);
+        resume_device_irqs();
 }
 EXPORT_SYMBOL_GPL(device_power_up);
 
@@ -602,16 +603,17 @@ static int suspend_device_noirq(struct device *dev, pm_message_t state)
  *      device_power_down - Shut down special devices.
  *      @state: PM transition of the system being carried out.
  *
- *      Power down devices that require interrupts to be disabled.
- *      Then power down system devices.
+ *      Prevent device drivers from receiving interrupts and call the "late"
+ *      suspend handlers.
  *
- *      Must be called with interrupts disabled and only one CPU running.
+ *      Must be called under dpm_list_mtx.
  */
 int device_power_down(pm_message_t state)
 {
         struct device *dev;
         int error = 0;
 
+        suspend_device_irqs();
         list_for_each_entry_reverse(dev, &dpm_list, power.entry) {
                 error = suspend_device_noirq(dev, state);
                 if (error) {
@@ -621,7 +623,7 @@ int device_power_down(pm_message_t state)
                 dev->power.status = DPM_OFF_IRQ;
         }
         if (error)
-                dpm_power_up(resume_event(state));
+                device_power_up(resume_event(state));
         return error;
 }
 EXPORT_SYMBOL_GPL(device_power_down);
diff --git a/drivers/base/sys.c b/drivers/base/sys.c
index cbd36cf59a0f..76ce75bad91e 100644
--- a/drivers/base/sys.c
+++ b/drivers/base/sys.c
@@ -22,6 +22,7 @@
 #include <linux/pm.h>
 #include <linux/device.h>
 #include <linux/mutex.h>
+#include <linux/interrupt.h>
 
 #include "base.h"
 
@@ -369,6 +370,13 @@ int sysdev_suspend(pm_message_t state)
         struct sysdev_driver *drv, *err_drv;
         int ret;
 
+        pr_debug("Checking wake-up interrupts\n");
+
+        /* Return error code if there are any wake-up interrupts pending */
+        ret = check_wakeup_irqs();
+        if (ret)
+                return ret;
+
         pr_debug("Suspending System Devices\n");
 
         list_for_each_entry_reverse(cls, &system_kset->list, kset.kobj.entry) {
diff --git a/drivers/xen/manage.c b/drivers/xen/manage.c
index 3ccd348d112d..0d61db1e7b49 100644
--- a/drivers/xen/manage.c
+++ b/drivers/xen/manage.c
@@ -39,12 +39,6 @@ static int xen_suspend(void *data)
 
         BUG_ON(!irqs_disabled());
 
-        err = device_power_down(PMSG_SUSPEND);
-        if (err) {
-                printk(KERN_ERR "xen_suspend: device_power_down failed: %d\n",
-                       err);
-                return err;
-        }
         err = sysdev_suspend(PMSG_SUSPEND);
         if (err) {
                 printk(KERN_ERR "xen_suspend: sysdev_suspend failed: %d\n",
@@ -69,7 +63,6 @@ static int xen_suspend(void *data)
         xen_mm_unpin_all();
 
         sysdev_resume();
-        device_power_up(PMSG_RESUME);
 
         if (!*cancelled) {
                 xen_irq_resume();
@@ -108,6 +101,12 @@ static void do_suspend(void)
         /* XXX use normal device tree? */
         xenbus_suspend();
 
+        err = device_power_down(PMSG_SUSPEND);
+        if (err) {
+                printk(KERN_ERR "device_power_down failed: %d\n", err);
+                goto resume_devices;
+        }
+
         err = stop_machine(xen_suspend, &cancelled, cpumask_of(0));
         if (err) {
                 printk(KERN_ERR "failed to start xen_suspend: %d\n", err);
@@ -120,6 +119,9 @@ static void do_suspend(void)
         } else
                 xenbus_suspend_cancel();
 
+        device_power_up(PMSG_RESUME);
+
+resume_devices:
         device_resume(PMSG_RESUME);
 
         /* Make sure timer events get retriggered on all CPUs */
diff --git a/kernel/kexec.c b/kernel/kexec.c
index c7fd6692939d..dade9af6bf21 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -1454,7 +1454,6 @@ int kernel_kexec(void)
                 if (error)
                         goto Resume_devices;
                 device_pm_lock();
-                local_irq_disable();
                 /* At this point, device_suspend() has been called,
                  * but *not* device_power_down(). We *must*
                  * device_power_down() now.  Otherwise, drivers for
@@ -1464,8 +1463,9 @@ int kernel_kexec(void)
                  */
                 error = device_power_down(PMSG_FREEZE);
                 if (error)
-                        goto Enable_irqs;
+                        goto Unlock_pm;
 
+                local_irq_disable();
                 /* Suspend system devices */
                 error = sysdev_suspend(PMSG_FREEZE);
                 if (error)
@@ -1484,9 +1484,9 @@ int kernel_kexec(void)
         if (kexec_image->preserve_context) {
                 sysdev_resume();
  Power_up_devices:
-                device_power_up(PMSG_RESTORE);
- Enable_irqs:
                 local_irq_enable();
+                device_power_up(PMSG_RESTORE);
+ Unlock_pm:
                 device_pm_unlock();
                 enable_nonboot_cpus();
  Resume_devices:
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 4a4a206b1979..320bb0949bdf 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -214,7 +214,7 @@ static int create_image(int platform_mode)
                 return error;
 
         device_pm_lock();
-        local_irq_disable();
+
         /* 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)
@@ -225,8 +225,11 @@ static int create_image(int platform_mode)
         if (error) {
                 printk(KERN_ERR "PM: Some devices failed to power down, "
                         "aborting hibernation\n");
-                goto Enable_irqs;
+                goto Unlock;
         }
+
+        local_irq_disable();
+
         sysdev_suspend(PMSG_FREEZE);
         if (error) {
                 printk(KERN_ERR "PM: Some devices failed to power down, "
@@ -252,12 +255,16 @@ static int create_image(int platform_mode)
         /* NOTE:  device_power_up() is just a resume() for devices
          * that suspended with irqs off ... no overall powerup.
          */
+
  Power_up_devices:
+        local_irq_enable();
+
         device_power_up(in_suspend ?
                 (error ? PMSG_RECOVER : PMSG_THAW) : PMSG_RESTORE);
- Enable_irqs:
-        local_irq_enable();
+
+ Unlock:
         device_pm_unlock();
+
         return error;
 }
 
@@ -336,13 +343,16 @@ static int resume_target_kernel(void)
         int error;
 
         device_pm_lock();
-        local_irq_disable();
+
         error = device_power_down(PMSG_QUIESCE);
         if (error) {
                 printk(KERN_ERR "PM: Some devices failed to power down, "
                         "aborting resume\n");
-                goto Enable_irqs;
+                goto Unlock;
         }
+
+        local_irq_disable();
+
         sysdev_suspend(PMSG_QUIESCE);
         /* We'll ignore saved state, but this gets preempt count (etc) right */
         save_processor_state();
@@ -366,11 +376,16 @@ static int resume_target_kernel(void)
         swsusp_free();
         restore_processor_state();
         touch_softlockup_watchdog();
+
         sysdev_resume();
-        device_power_up(PMSG_RECOVER);
- Enable_irqs:
+
         local_irq_enable();
+
+        device_power_up(PMSG_RECOVER);
+
+ Unlock:
         device_pm_unlock();
+
         return error;
 }
 
@@ -447,15 +462,16 @@ int hibernation_platform_enter(void)
                 goto Finish;
 
         device_pm_lock();
-        local_irq_disable();
+
         error = device_power_down(PMSG_HIBERNATE);
         if (!error) {
+                local_irq_disable();
                 sysdev_suspend(PMSG_HIBERNATE);
                 hibernation_ops->enter();
                 /* We should never get here */
                 while (1);
         }
-        local_irq_enable();
+
         device_pm_unlock();
 
         /*
@@ -464,12 +480,15 @@ int hibernation_platform_enter(void)
          */
  Finish:
         hibernation_ops->finish();
+
  Resume_devices:
         entering_platform_hibernation = false;
         device_resume(PMSG_RESTORE);
         resume_console();
+
  Close:
         hibernation_ops->end();
+
         return error;
 }
 
diff --git a/kernel/power/main.c b/kernel/power/main.c
index c9632f841f64..f0a466736c01 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -287,17 +287,19 @@ void __attribute__ ((weak)) arch_suspend_enable_irqs(void)
  */
 static int suspend_enter(suspend_state_t state)
 {
-        int error = 0;
+        int error;
 
         device_pm_lock();
-        arch_suspend_disable_irqs();
-        BUG_ON(!irqs_disabled());
 
-        if ((error = device_power_down(PMSG_SUSPEND))) {
+        error = device_power_down(PMSG_SUSPEND);
+        if (error) {
                 printk(KERN_ERR "PM: Some devices failed to power down\n");
                 goto Done;
         }
 
+        arch_suspend_disable_irqs();
+        BUG_ON(!irqs_disabled());
+
         error = sysdev_suspend(PMSG_SUSPEND);
         if (!error) {
                 if (!suspend_test(TEST_CORE))
@@ -305,11 +307,14 @@ static int suspend_enter(suspend_state_t state)
                 sysdev_resume();
         }
 
-        device_power_up(PMSG_RESUME);
- Done:
         arch_suspend_enable_irqs();
         BUG_ON(irqs_disabled());
+
+        device_power_up(PMSG_RESUME);
+
+ Done:
         device_pm_unlock();
+
         return error;
 }