7 files changed, 75 insertions, 244 deletions

diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index 79833170bb9c..b45da40e8d25 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -19,16 +19,6 @@ config PM
           will issue the hlt instruction if nothing is to be done, thereby
           sending the processor to sleep and saving power.
 
-config PM_LEGACY
-        bool "Legacy Power Management API (DEPRECATED)"
-        depends on PM
-        default n
-        ---help---
-           Support for pm_register() and friends.  This old API is obsoleted
-           by the driver model.
-
-           If unsure, say N.
-
 config PM_DEBUG
         bool "Power Management Debug Support"
         depends on PM
@@ -190,7 +180,7 @@ config APM_EMULATION
           notification of APM "events" (e.g. battery status change).
 
           In order to use APM, you will need supporting software. For location
-          and more information, read <file:Documentation/pm.txt> and the
+          and more information, read <file:Documentation/power/pm.txt> and the
           Battery Powered Linux mini-HOWTO, available from
           <http://www.tldp.org/docs.html#howto>.
 
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index f7dfff28ecdb..597823b5b700 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -4,7 +4,6 @@ EXTRA_CFLAGS	+=	-DDEBUG
 endif
 
 obj-y                           := main.o
-obj-$(CONFIG_PM_LEGACY)         += pm.o
 obj-$(CONFIG_PM_SLEEP)          += process.o console.o
 obj-$(CONFIG_HIBERNATION)       += swsusp.o disk.o snapshot.o swap.o user.o
 
diff --git a/kernel/power/console.c b/kernel/power/console.c
index 89bcf4973ee5..b8628be2a465 100644
--- a/kernel/power/console.c
+++ b/kernel/power/console.c
@@ -7,17 +7,39 @@
 #include <linux/vt_kern.h>
 #include <linux/kbd_kern.h>
 #include <linux/console.h>
+#include <linux/module.h>
 #include "power.h"
 
 #if defined(CONFIG_VT) && defined(CONFIG_VT_CONSOLE)
 #define SUSPEND_CONSOLE (MAX_NR_CONSOLES-1)
 
 static int orig_fgconsole, orig_kmsg;
+static int disable_vt_switch;
+
+/*
+ * Normally during a suspend, we allocate a new console and switch to it.
+ * When we resume, we switch back to the original console.  This switch
+ * can be slow, so on systems where the framebuffer can handle restoration
+ * of video registers anyways, there's little point in doing the console
+ * switch.  This function allows you to disable it by passing it '0'.
+ */
+void pm_set_vt_switch(int do_switch)
+{
+        acquire_console_sem();
+        disable_vt_switch = !do_switch;
+        release_console_sem();
+}
+EXPORT_SYMBOL(pm_set_vt_switch);
 
 int pm_prepare_console(void)
 {
         acquire_console_sem();
 
+        if (disable_vt_switch) {
+                release_console_sem();
+                return 0;
+        }
+
         orig_fgconsole = fg_console;
 
         if (vc_allocate(SUSPEND_CONSOLE)) {
@@ -50,9 +72,12 @@ int pm_prepare_console(void)
 void pm_restore_console(void)
 {
         acquire_console_sem();
+        if (disable_vt_switch) {
+                release_console_sem();
+                return;
+        }
         set_console(orig_fgconsole);
         release_console_sem();
         kmsg_redirect = orig_kmsg;
-        return;
 }
 #endif
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index 859a8e59773a..14a656cdc652 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -391,7 +391,7 @@ int hibernation_platform_enter(void)
                 goto Close;
 
         suspend_console();
-        error = device_suspend(PMSG_SUSPEND);
+        error = device_suspend(PMSG_HIBERNATE);
         if (error)
                 goto Resume_console;
 
@@ -404,7 +404,7 @@ int hibernation_platform_enter(void)
                 goto Finish;
 
         local_irq_disable();
-        error = device_power_down(PMSG_SUSPEND);
+        error = device_power_down(PMSG_HIBERNATE);
         if (!error) {
                 hibernation_ops->enter();
                 /* We should never get here */
diff --git a/kernel/power/pm.c b/kernel/power/pm.c
deleted file mode 100644
index 60c73fa670d5..000000000000
--- a/kernel/power/pm.c
+++ /dev/null
@@ -1,205 +0,0 @@
-/*
- *  pm.c - Power management interface
- *
- *  Copyright (C) 2000 Andrew Henroid
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/slab.h>
-#include <linux/pm.h>
-#include <linux/pm_legacy.h>
-#include <linux/interrupt.h>
-#include <linux/mutex.h>
-
-/*
- *      Locking notes:
- *              pm_devs_lock can be a semaphore providing pm ops are not called
- *      from an interrupt handler (already a bad idea so no change here). Each
- *      change must be protected so that an unlink of an entry doesn't clash
- *      with a pm send - which is permitted to sleep in the current architecture
- *
- *      Module unloads clashing with pm events now work out safely, the module 
- *      unload path will block until the event has been sent. It may well block
- *      until a resume but that will be fine.
- */
- 
-static DEFINE_MUTEX(pm_devs_lock);
-static LIST_HEAD(pm_devs);
-
-/**
- *      pm_register - register a device with power management
- *      @type: device type 
- *      @id: device ID
- *      @callback: callback function
- *
- *      Add a device to the list of devices that wish to be notified about
- *      power management events. A &pm_dev structure is returned on success,
- *      on failure the return is %NULL.
- *
- *      The callback function will be called in process context and
- *      it may sleep.
- */
- 
-struct pm_dev *pm_register(pm_dev_t type,
-                           unsigned long id,
-                           pm_callback callback)
-{
-        struct pm_dev *dev = kzalloc(sizeof(struct pm_dev), GFP_KERNEL);
-        if (dev) {
-                dev->type = type;
-                dev->id = id;
-                dev->callback = callback;
-
-                mutex_lock(&pm_devs_lock);
-                list_add(&dev->entry, &pm_devs);
-                mutex_unlock(&pm_devs_lock);
-        }
-        return dev;
-}
-
-/**
- *      pm_send - send request to a single device
- *      @dev: device to send to
- *      @rqst: power management request
- *      @data: data for the callback
- *
- *      Issue a power management request to a given device. The 
- *      %PM_SUSPEND and %PM_RESUME events are handled specially. The
- *      data field must hold the intended next state. No call is made
- *      if the state matches.
- *
- *      BUGS: what stops two power management requests occurring in parallel
- *      and conflicting.
- *
- *      WARNING: Calling pm_send directly is not generally recommended, in
- *      particular there is no locking against the pm_dev going away. The
- *      caller must maintain all needed locking or have 'inside knowledge'
- *      on the safety. Also remember that this function is not locked against
- *      pm_unregister. This means that you must handle SMP races on callback
- *      execution and unload yourself.
- */
- 
-static int pm_send(struct pm_dev *dev, pm_request_t rqst, void *data)
-{
-        int status = 0;
-        unsigned long prev_state, next_state;
-
-        if (in_interrupt())
-                BUG();
-
-        switch (rqst) {
-        case PM_SUSPEND:
-        case PM_RESUME:
-                prev_state = dev->state;
-                next_state = (unsigned long) data;
-                if (prev_state != next_state) {
-                        if (dev->callback)
-                                status = (*dev->callback)(dev, rqst, data);
-                        if (!status) {
-                                dev->state = next_state;
-                                dev->prev_state = prev_state;
-                        }
-                }
-                else {
-                        dev->prev_state = prev_state;
-                }
-                break;
-        default:
-                if (dev->callback)
-                        status = (*dev->callback)(dev, rqst, data);
-                break;
-        }
-        return status;
-}
-
-/*
- * Undo incomplete request
- */
-static void pm_undo_all(struct pm_dev *last)
-{
-        struct list_head *entry = last->entry.prev;
-        while (entry != &pm_devs) {
-                struct pm_dev *dev = list_entry(entry, struct pm_dev, entry);
-                if (dev->state != dev->prev_state) {
-                        /* previous state was zero (running) resume or
-                         * previous state was non-zero (suspended) suspend
-                         */
-                        pm_request_t undo = (dev->prev_state
-                                             ? PM_SUSPEND:PM_RESUME);
-                        pm_send(dev, undo, (void*) dev->prev_state);
-                }
-                entry = entry->prev;
-        }
-}
-
-/**
- *      pm_send_all - send request to all managed devices
- *      @rqst: power management request
- *      @data: data for the callback
- *
- *      Issue a power management request to a all devices. The 
- *      %PM_SUSPEND events are handled specially. Any device is 
- *      permitted to fail a suspend by returning a non zero (error)
- *      value from its callback function. If any device vetoes a 
- *      suspend request then all other devices that have suspended 
- *      during the processing of this request are restored to their
- *      previous state.
- *
- *      WARNING:  This function takes the pm_devs_lock. The lock is not dropped until
- *      the callbacks have completed. This prevents races against pm locking
- *      functions, races against module unload pm_unregister code. It does
- *      mean however that you must not issue pm_ functions within the callback
- *      or you will deadlock and users will hate you.
- *
- *      Zero is returned on success. If a suspend fails then the status
- *      from the device that vetoes the suspend is returned.
- *
- *      BUGS: what stops two power management requests occurring in parallel
- *      and conflicting.
- */
- 
-int pm_send_all(pm_request_t rqst, void *data)
-{
-        struct list_head *entry;
-        
-        mutex_lock(&pm_devs_lock);
-        entry = pm_devs.next;
-        while (entry != &pm_devs) {
-                struct pm_dev *dev = list_entry(entry, struct pm_dev, entry);
-                if (dev->callback) {
-                        int status = pm_send(dev, rqst, data);
-                        if (status) {
-                                /* return devices to previous state on
-                                 * failed suspend request
-                                 */
-                                if (rqst == PM_SUSPEND)
-                                        pm_undo_all(dev);
-                                mutex_unlock(&pm_devs_lock);
-                                return status;
-                        }
-                }
-                entry = entry->next;
-        }
-        mutex_unlock(&pm_devs_lock);
-        return 0;
-}
-
-EXPORT_SYMBOL(pm_register);
-EXPORT_SYMBOL(pm_send_all);
-
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 7c2118f9597f..f1d0b345c9ba 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -75,22 +75,15 @@ void refrigerator(void)
         __set_current_state(save);
 }
 
-static void fake_signal_wake_up(struct task_struct *p, int resume)
+static void fake_signal_wake_up(struct task_struct *p)
 {
         unsigned long flags;
 
         spin_lock_irqsave(&p->sighand->siglock, flags);
-        signal_wake_up(p, resume);
+        signal_wake_up(p, 0);
         spin_unlock_irqrestore(&p->sighand->siglock, flags);
 }
 
-static void send_fake_signal(struct task_struct *p)
-{
-        if (task_is_stopped(p))
-                force_sig_specific(SIGSTOP, p);
-        fake_signal_wake_up(p, task_is_stopped(p));
-}
-
 static int has_mm(struct task_struct *p)
 {
         return (p->mm && !(p->flags & PF_BORROWED_MM));
@@ -121,7 +114,7 @@ static int freeze_task(struct task_struct *p, int with_mm_only)
         if (freezing(p)) {
                 if (has_mm(p)) {
                         if (!signal_pending(p))
-                                fake_signal_wake_up(p, 0);
+                                fake_signal_wake_up(p);
                 } else {
                         if (with_mm_only)
                                 ret = 0;
@@ -135,7 +128,7 @@ static int freeze_task(struct task_struct *p, int with_mm_only)
                 } else {
                         if (has_mm(p)) {
                                 set_freeze_flag(p);
-                                send_fake_signal(p);
+                                fake_signal_wake_up(p);
                         } else {
                                 if (with_mm_only) {
                                         ret = 0;
@@ -182,15 +175,17 @@ static int try_to_freeze_tasks(int freeze_user_space)
                         if (frozen(p) || !freezeable(p))
                                 continue;
 
-                        if (task_is_traced(p) && frozen(p->parent)) {
-                                cancel_freezing(p);
-                                continue;
-                        }
-
                         if (!freeze_task(p, freeze_user_space))
                                 continue;
 
-                        if (!freezer_should_skip(p))
+                        /*
+                         * Now that we've done set_freeze_flag, don't
+                         * perturb a task in TASK_STOPPED or TASK_TRACED.
+                         * It is "frozen enough".  If the task does wake
+                         * up, it will immediately call try_to_freeze.
+                         */
+                        if (!task_is_stopped_or_traced(p) &&
+                            !freezer_should_skip(p))
                                 todo++;
                 } while_each_thread(g, p);
                 read_unlock(&tasklist_lock);
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 72a020cabb4c..5f91a07c4eac 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -447,7 +447,7 @@ static void memory_bm_free(struct memory_bitmap *bm, int clear_nosave_free)
  *      of @bm->cur_zone_bm are updated.
  */
 
-static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
+static int memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
                                 void **addr, unsigned int *bit_nr)
 {
         struct zone_bitmap *zone_bm;
@@ -461,7 +461,8 @@ static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
                 while (pfn < zone_bm->start_pfn || pfn >= zone_bm->end_pfn) {
                         zone_bm = zone_bm->next;
 
-                        BUG_ON(!zone_bm);
+                        if (!zone_bm)
+                                return -EFAULT;
                 }
                 bm->cur.zone_bm = zone_bm;
         }
@@ -479,23 +480,40 @@ static void memory_bm_find_bit(struct memory_bitmap *bm, unsigned long pfn,
         pfn -= bb->start_pfn;
         *bit_nr = pfn % BM_BITS_PER_CHUNK;
         *addr = bb->data + pfn / BM_BITS_PER_CHUNK;
+        return 0;
 }
 
 static void memory_bm_set_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
         void *addr;
         unsigned int bit;
+        int error;
 
-        memory_bm_find_bit(bm, pfn, &addr, &bit);
+        error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+        BUG_ON(error);
         set_bit(bit, addr);
 }
 
+static int mem_bm_set_bit_check(struct memory_bitmap *bm, unsigned long pfn)
+{
+        void *addr;
+        unsigned int bit;
+        int error;
+
+        error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+        if (!error)
+                set_bit(bit, addr);
+        return error;
+}
+
 static void memory_bm_clear_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
         void *addr;
         unsigned int bit;
+        int error;
 
-        memory_bm_find_bit(bm, pfn, &addr, &bit);
+        error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+        BUG_ON(error);
         clear_bit(bit, addr);
 }
 
@@ -503,8 +521,10 @@ static int memory_bm_test_bit(struct memory_bitmap *bm, unsigned long pfn)
 {
         void *addr;
         unsigned int bit;
+        int error;
 
-        memory_bm_find_bit(bm, pfn, &addr, &bit);
+        error = memory_bm_find_bit(bm, pfn, &addr, &bit);
+        BUG_ON(error);
         return test_bit(bit, addr);
 }
 
@@ -709,8 +729,15 @@ static void mark_nosave_pages(struct memory_bitmap *bm)
                                 region->end_pfn << PAGE_SHIFT);
 
                 for (pfn = region->start_pfn; pfn < region->end_pfn; pfn++)
-                        if (pfn_valid(pfn))
-                                memory_bm_set_bit(bm, pfn);
+                        if (pfn_valid(pfn)) {
+                                /*
+                                 * It is safe to ignore the result of
+                                 * mem_bm_set_bit_check() here, since we won't
+                                 * touch the PFNs for which the error is
+                                 * returned anyway.
+                                 */
+                                mem_bm_set_bit_check(bm, pfn);
+                        }
         }
 }