6 files changed, 237 insertions, 73 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index b45da40e8d25..dcd165f92a88 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -82,7 +82,7 @@ config PM_SLEEP_SMP
 
 config PM_SLEEP
         bool
-        depends on SUSPEND || HIBERNATION
+        depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
         default y
 
 config SUSPEND
@@ -94,6 +94,17 @@ config SUSPEND
           powered and thus its contents are preserved, such as the
           suspend-to-RAM state (e.g. the ACPI S3 state).
 
+config PM_TEST_SUSPEND
+        bool "Test suspend/resume and wakealarm during bootup"
+        depends on SUSPEND && PM_DEBUG && RTC_LIB=y
+        ---help---
+        This option will let you suspend your machine during bootup, and
+        make it wake up a few seconds later using an RTC wakeup alarm.
+        Enable this with a kernel parameter like "test_suspend=mem".
+
+        You probably want to have your system's RTC driver statically
+        linked, ensuring that it's available when this test runs.
+
 config SUSPEND_FREEZER
         bool "Enable freezer for suspend to RAM/standby" \
                 if ARCH_WANTS_FREEZER_CONTROL || BROKEN
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 3398f4651aa1..0b7476f5d2a6 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -132,6 +132,61 @@ static inline int suspend_test(int level) { return 0; }
 
 #ifdef CONFIG_SUSPEND
 
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+/*
+ * We test the system suspend code by setting an RTC wakealarm a short
+ * time in the future, then suspending.  Suspending the devices won't
+ * normally take long ... some systems only need a few milliseconds.
+ *
+ * The time it takes is system-specific though, so when we test this
+ * during system bootup we allow a LOT of time.
+ */
+#define TEST_SUSPEND_SECONDS    5
+
+static unsigned long suspend_test_start_time;
+
+static void suspend_test_start(void)
+{
+        /* FIXME Use better timebase than "jiffies", ideally a clocksource.
+         * What we want is a hardware counter that will work correctly even
+         * during the irqs-are-off stages of the suspend/resume cycle...
+         */
+        suspend_test_start_time = jiffies;
+}
+
+static void suspend_test_finish(const char *label)
+{
+        long nj = jiffies - suspend_test_start_time;
+        unsigned msec;
+
+        msec = jiffies_to_msecs(abs(nj));
+        pr_info("PM: %s took %d.%03d seconds\n", label,
+                        msec / 1000, msec % 1000);
+
+        /* Warning on suspend means the RTC alarm period needs to be
+         * larger -- the system was sooo slooowwww to suspend that the
+         * alarm (should have) fired before the system went to sleep!
+         *
+         * Warning on either suspend or resume also means the system
+         * has some performance issues.  The stack dump of a WARN_ON
+         * is more likely to get the right attention than a printk...
+         */
+        WARN_ON(msec > (TEST_SUSPEND_SECONDS * 1000));
+}
+
+#else
+
+static void suspend_test_start(void)
+{
+}
+
+static void suspend_test_finish(const char *label)
+{
+}
+
+#endif
+
 /* This is just an arbitrary number */
 #define FREE_PAGE_NUMBER (100)
 
@@ -266,12 +321,13 @@ int suspend_devices_and_enter(suspend_state_t state)
                         goto Close;
         }
         suspend_console();
+        suspend_test_start();
         error = device_suspend(PMSG_SUSPEND);
         if (error) {
                 printk(KERN_ERR "PM: Some devices failed to suspend\n");
                 goto Recover_platform;
         }
-
+        suspend_test_finish("suspend devices");
         if (suspend_test(TEST_DEVICES))
                 goto Recover_platform;
 
@@ -293,7 +349,9 @@ int suspend_devices_and_enter(suspend_state_t state)
         if (suspend_ops->finish)
                 suspend_ops->finish();
  Resume_devices:
+        suspend_test_start();
         device_resume(PMSG_RESUME);
+        suspend_test_finish("resume devices");
         resume_console();
  Close:
         if (suspend_ops->end)
@@ -521,3 +579,144 @@ static int __init pm_init(void)
 }
 
 core_initcall(pm_init);
+
+
+#ifdef CONFIG_PM_TEST_SUSPEND
+
+#include <linux/rtc.h>
+
+/*
+ * To test system suspend, we need a hands-off mechanism to resume the
+ * system.  RTCs wake alarms are a common self-contained mechanism.
+ */
+
+static void __init test_wakealarm(struct rtc_device *rtc, suspend_state_t state)
+{
+        static char err_readtime[] __initdata =
+                KERN_ERR "PM: can't read %s time, err %d\n";
+        static char err_wakealarm [] __initdata =
+                KERN_ERR "PM: can't set %s wakealarm, err %d\n";
+        static char err_suspend[] __initdata =
+                KERN_ERR "PM: suspend test failed, error %d\n";
+        static char info_test[] __initdata =
+                KERN_INFO "PM: test RTC wakeup from '%s' suspend\n";
+
+        unsigned long           now;
+        struct rtc_wkalrm       alm;
+        int                     status;
+
+        /* this may fail if the RTC hasn't been initialized */
+        status = rtc_read_time(rtc, &alm.time);
+        if (status < 0) {
+                printk(err_readtime, rtc->dev.bus_id, status);
+                return;
+        }
+        rtc_tm_to_time(&alm.time, &now);
+
+        memset(&alm, 0, sizeof alm);
+        rtc_time_to_tm(now + TEST_SUSPEND_SECONDS, &alm.time);
+        alm.enabled = true;
+
+        status = rtc_set_alarm(rtc, &alm);
+        if (status < 0) {
+                printk(err_wakealarm, rtc->dev.bus_id, status);
+                return;
+        }
+
+        if (state == PM_SUSPEND_MEM) {
+                printk(info_test, pm_states[state]);
+                status = pm_suspend(state);
+                if (status == -ENODEV)
+                        state = PM_SUSPEND_STANDBY;
+        }
+        if (state == PM_SUSPEND_STANDBY) {
+                printk(info_test, pm_states[state]);
+                status = pm_suspend(state);
+        }
+        if (status < 0)
+                printk(err_suspend, status);
+
+        /* Some platforms can't detect that the alarm triggered the
+         * wakeup, or (accordingly) disable it after it afterwards.
+         * It's supposed to give oneshot behavior; cope.
+         */
+        alm.enabled = false;
+        rtc_set_alarm(rtc, &alm);
+}
+
+static int __init has_wakealarm(struct device *dev, void *name_ptr)
+{
+        struct rtc_device *candidate = to_rtc_device(dev);
+
+        if (!candidate->ops->set_alarm)
+                return 0;
+        if (!device_may_wakeup(candidate->dev.parent))
+                return 0;
+
+        *(char **)name_ptr = dev->bus_id;
+        return 1;
+}
+
+/*
+ * Kernel options like "test_suspend=mem" force suspend/resume sanity tests
+ * at startup time.  They're normally disabled, for faster boot and because
+ * we can't know which states really work on this particular system.
+ */
+static suspend_state_t test_state __initdata = PM_SUSPEND_ON;
+
+static char warn_bad_state[] __initdata =
+        KERN_WARNING "PM: can't test '%s' suspend state\n";
+
+static int __init setup_test_suspend(char *value)
+{
+        unsigned i;
+
+        /* "=mem" ==> "mem" */
+        value++;
+        for (i = 0; i < PM_SUSPEND_MAX; i++) {
+                if (!pm_states[i])
+                        continue;
+                if (strcmp(pm_states[i], value) != 0)
+                        continue;
+                test_state = (__force suspend_state_t) i;
+                return 0;
+        }
+        printk(warn_bad_state, value);
+        return 0;
+}
+__setup("test_suspend", setup_test_suspend);
+
+static int __init test_suspend(void)
+{
+        static char             warn_no_rtc[] __initdata =
+                KERN_WARNING "PM: no wakealarm-capable RTC driver is ready\n";
+
+        char                    *pony = NULL;
+        struct rtc_device       *rtc = NULL;
+
+        /* PM is initialized by now; is that state testable? */
+        if (test_state == PM_SUSPEND_ON)
+                goto done;
+        if (!valid_state(test_state)) {
+                printk(warn_bad_state, pm_states[test_state]);
+                goto done;
+        }
+
+        /* RTCs have initialized by now too ... can we use one? */
+        class_find_device(rtc_class, NULL, &pony, has_wakealarm);
+        if (pony)
+                rtc = rtc_class_open(pony);
+        if (!rtc) {
+                printk(warn_no_rtc);
+                goto done;
+        }
+
+        /* go for it */
+        test_wakealarm(rtc, test_state);
+        rtc_class_close(rtc);
+done:
+        return 0;
+}
+late_initcall(test_suspend);
+
+#endif /* CONFIG_PM_TEST_SUSPEND */
diff --git a/kernel/power/power.h b/kernel/power/power.h
index 700f44ec8406..acc0c101dbd5 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -53,8 +53,6 @@ extern int hibernation_platform_enter(void);
 
 extern int pfn_is_nosave(unsigned long);
 
-extern struct mutex pm_mutex;
-
 #define power_attr(_name) \
 static struct kobj_attribute _name##_attr = {   \
         .attr   = {                             \
diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c
index 678ec736076b..72016f051477 100644
--- a/kernel/power/poweroff.c
+++ b/kernel/power/poweroff.c
@@ -10,6 +10,7 @@
 #include <linux/pm.h>
 #include <linux/workqueue.h>
 #include <linux/reboot.h>
+#include <linux/cpumask.h>
 
 /*
  * When the user hits Sys-Rq o to power down the machine this is the
@@ -25,7 +26,8 @@ static DECLARE_WORK(poweroff_work, do_poweroff);
 
 static void handle_poweroff(int key, struct tty_struct *tty)
 {
-        schedule_work(&poweroff_work);
+        /* run sysrq poweroff on boot cpu */
+        schedule_work_on(first_cpu(cpu_online_map), &poweroff_work);
 }
 
 static struct sysrq_key_op      sysrq_poweroff_op = {
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 5fb87652f214..278946aecaf0 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -149,7 +149,7 @@ static int try_to_freeze_tasks(bool sig_only)
         unsigned long end_time;
         unsigned int todo;
         struct timeval start, end;
-        s64 elapsed_csecs64;
+        u64 elapsed_csecs64;
         unsigned int elapsed_csecs;
 
         do_gettimeofday(&start);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 5f91a07c4eac..5d2ab836e998 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -205,8 +205,7 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *      objects.  The main list's elements are of type struct zone_bitmap
  *      and each of them corresonds to one zone.  For each zone bitmap
  *      object there is a list of objects of type struct bm_block that
- *      represent each blocks of bit chunks in which information is
- *      stored.
+ *      represent each blocks of bitmap in which information is stored.
  *
  *      struct memory_bitmap contains a pointer to the main list of zone
  *      bitmap objects, a struct bm_position used for browsing the bitmap,
@@ -224,26 +223,27 @@ static void chain_free(struct chain_allocator *ca, int clear_page_nosave)
  *      pfns that correspond to the start and end of the represented zone.
  *
  *      struct bm_block contains a pointer to the memory page in which
- *      information is stored (in the form of a block of bit chunks
- *      of type unsigned long each).  It also contains the pfns that
- *      correspond to the start and end of the represented memory area and
- *      the number of bit chunks in the block.
+ *      information is stored (in the form of a block of bitmap)
+ *      It also contains the pfns that correspond to the start and end of
+ *      the represented memory area.
  */
 
 #define BM_END_OF_MAP   (~0UL)
 
-#define BM_CHUNKS_PER_BLOCK     (PAGE_SIZE / sizeof(long))
-#define BM_BITS_PER_CHUNK       (sizeof(long) << 3)
 #define BM_BITS_PER_BLOCK       (PAGE_SIZE << 3)
 
 struct bm_block {
         struct bm_block *next;          /* next element of the list */
         unsigned long start_pfn;        /* pfn represented by the first bit */
         unsigned long end_pfn;  /* pfn represented by the last bit plus 1 */
-        unsigned int size;      /* number of bit chunks */
-        unsigned long *data;    /* chunks of bits representing pages */
+        unsigned long *data;    /* bitmap representing pages */
 };
 
+static inline unsigned long bm_block_bits(struct bm_block *bb)
+{
+        return bb->end_pfn - bb->start_pfn;
+}
+
 struct zone_bitmap {
         struct zone_bitmap *next;       /* next element of the list */
         unsigned long start_pfn;        /* minimal pfn in this zone */
@@ -257,7 +257,6 @@ struct zone_bitmap {
 struct bm_position {
         struct zone_bitmap *zone_bm;
         struct bm_block *block;
-        int chunk;
         int bit;
 };
 
@@ -272,12 +271,6 @@ struct memory_bitmap {
 
 /* Functions that operate on memory bitmaps */
 
-static inline void memory_bm_reset_chunk(struct memory_bitmap *bm)
-{
-        bm->cur.chunk = 0;
-        bm->cur.bit = -1;
-}
-
 static void memory_bm_position_reset(struct memory_bitmap *bm)
 {
         struct zone_bitmap *zone_bm;
@@ -285,7 +278,7 @@ static void memory_bm_position_reset(struct memory_bitmap *bm)
         zone_bm = bm->zone_bm_list;
         bm->cur.zone_bm = zone_bm;
         bm->cur.block = zone_bm->bm_blocks;
-        memory_bm_reset_chunk(bm);
+        bm->cur.bit = 0;
 }
 
 static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free);
@@ -394,12 +387,10 @@ memory_bm_create(struct memory_bitmap *bm, gfp_t gfp_mask, int safe_needed)
                         bb->start_pfn = pfn;
                         if (nr >= BM_BITS_PER_BLOCK) {
                                 pfn += BM_BITS_PER_BLOCK;
-                                bb->size = BM_CHUNKS_PER_BLOCK;
                                 nr -= BM_BITS_PER_BLOCK;
                         } else {
                                 /* This is executed only once in the loop */
                                 pfn += nr;
-                                bb->size = DIV_ROUND_UP(nr, BM_BITS_PER_CHUNK);
                         }
                         bb->end_pfn = pfn;
                         bb = bb->next;
@@ -478,8 +469,8 @@ static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
         }
         zone_bm->cur_block = bb;
         pfn -= bb->start_pfn;
-        *bit_nr = pfn % BM_BITS_PER_CHUNK;
-        *addr = bb->data + pfn / BM_BITS_PER_CHUNK;
+        *bit_nr = pfn;
+        *addr = bb->data;
         return 0;
 }
 
@@ -528,36 +519,6 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
         return test_bit(bit, addr);
 }
 
-/* Two auxiliary functions for memory_bm_next_pfn */
-
-/* Find the first set bit in the given chunk, if there is one */
-
-static inline int next_bit_in_chunk(int bit, unsigned long *chunk_p)
-{
-        bit++;
-        while (bit < BM_BITS_PER_CHUNK) {
-                if (test_bit(bit, chunk_p))
-                        return bit;
-
-                bit++;
-        }
-        return -1;
-}
-
-/* Find a chunk containing some bits set in given block of bits */
-
-static inline int next_chunk_in_block(int n, struct bm_block *bb)
-{
-        n++;
-        while (n < bb->size) {
-                if (bb->data[n])
-                        return n;
-
-                n++;
-        }
-        return -1;
-}
-
 /**
  *      memory_bm_next_pfn - find the pfn that corresponds to the next set bit
  *      in the bitmap @bm.  If the pfn cannot be found, BM_END_OF_MAP is
@@ -571,40 +532,33 @@ static unsigned long memory_bm_next_pfn(struct memory_bitmap *bm)
 {
         struct zone_bitmap *zone_bm;
         struct bm_block *bb;
-        int chunk;
         int bit;
 
         do {
                 bb = bm->cur.block;
                 do {
-                        chunk = bm->cur.chunk;
                         bit = bm->cur.bit;
-                        do {
-                                bit = next_bit_in_chunk(bit, bb->data + chunk);
-                                if (bit >= 0)
-                                        goto Return_pfn;
-
-                                chunk = next_chunk_in_block(chunk, bb);
-                                bit = -1;
-                        } while (chunk >= 0);
+                        bit = find_next_bit(bb->data, bm_block_bits(bb), bit);
+                        if (bit < bm_block_bits(bb))
+                                goto Return_pfn;
+
                         bb = bb->next;
                         bm->cur.block = bb;
-                        memory_bm_reset_chunk(bm);
+                        bm->cur.bit = 0;
                 } while (bb);
                 zone_bm = bm->cur.zone_bm->next;
                 if (zone_bm) {
                         bm->cur.zone_bm = zone_bm;
                         bm->cur.block = zone_bm->bm_blocks;
-                        memory_bm_reset_chunk(bm);
+                        bm->cur.bit = 0;
                 }
         } while (zone_bm);
         memory_bm_position_reset(bm);
         return BM_END_OF_MAP;
 
  Return_pfn:
-        bm->cur.chunk = chunk;
-        bm->cur.bit = bit;
-        return bb->start_pfn + chunk * BM_BITS_PER_CHUNK + bit;
+        bm->cur.bit = bit + 1;
+        return bb->start_pfn + bit;
 }
 
 /**