23 files changed, 319 insertions, 116 deletions

diff --git a/arch/i386/kernel/acpi/cstate.c b/arch/i386/kernel/acpi/cstate.c
index 4664b55f623e..12e937c1ce4b 100644
--- a/arch/i386/kernel/acpi/cstate.c
+++ b/arch/i386/kernel/acpi/cstate.c
@@ -156,10 +156,8 @@ static int __init ffh_cstate_init(void)
 
 static void __exit ffh_cstate_exit(void)
 {
-        if (cpu_cstate_entry) {
-                free_percpu(cpu_cstate_entry);
-                cpu_cstate_entry = NULL;
-        }
+        free_percpu(cpu_cstate_entry);
+        cpu_cstate_entry = NULL;
 }
 
 arch_initcall(ffh_cstate_init);
diff --git a/arch/i386/kernel/cpu/mcheck/non-fatal.c b/arch/i386/kernel/cpu/mcheck/non-fatal.c
index 1f9153ae5b03..6b5d3518a1c0 100644
--- a/arch/i386/kernel/cpu/mcheck/non-fatal.c
+++ b/arch/i386/kernel/cpu/mcheck/non-fatal.c
@@ -51,10 +51,10 @@ static void mce_checkregs (void *info)
         }
 }
 
-static void mce_work_fn(void *data);
-static DECLARE_WORK(mce_work, mce_work_fn, NULL);
+static void mce_work_fn(struct work_struct *work);
+static DECLARE_DELAYED_WORK(mce_work, mce_work_fn);
 
-static void mce_work_fn(void *data)
+static void mce_work_fn(struct work_struct *work)
 { 
         on_each_cpu(mce_checkregs, NULL, 1, 1);
         schedule_delayed_work(&mce_work, MCE_RATE);
diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c
index bad8b4420709..065005c3f168 100644
--- a/arch/i386/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c
@@ -116,7 +116,6 @@ static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
         return sysfs_create_group(&sys_dev->kobj, &thermal_throttle_attr_group);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
 {
         return sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
@@ -153,7 +152,6 @@ static struct notifier_block thermal_throttle_cpu_notifier =
 {
         .notifier_call = thermal_throttle_cpu_callback,
 };
-#endif /* CONFIG_HOTPLUG_CPU */
 
 static __init int thermal_throttle_init_device(void)
 {
diff --git a/arch/i386/kernel/cpuid.c b/arch/i386/kernel/cpuid.c
index 5c5d4507ee7d..db6dd20c3589 100644
--- a/arch/i386/kernel/cpuid.c
+++ b/arch/i386/kernel/cpuid.c
@@ -166,7 +166,6 @@ static int cpuid_device_create(int i)
         return err;
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 static int cpuid_class_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
         unsigned int cpu = (unsigned long)hcpu;
@@ -186,7 +185,6 @@ static struct notifier_block __cpuinitdata cpuid_class_cpu_notifier =
 {
         .notifier_call = cpuid_class_cpu_callback,
 };
-#endif /* !CONFIG_HOTPLUG_CPU */
 
 static int __init cpuid_init(void)
 {
diff --git a/arch/i386/kernel/crash.c b/arch/i386/kernel/crash.c
index 144b43288965..a5e0e990ea95 100644
--- a/arch/i386/kernel/crash.c
+++ b/arch/i386/kernel/crash.c
@@ -31,68 +31,6 @@
 /* This keeps a track of which one is crashing cpu. */
 static int crashing_cpu;
 
-static u32 *append_elf_note(u32 *buf, char *name, unsigned type, void *data,
-                                                               size_t data_len)
-{
-        struct elf_note note;
-
-        note.n_namesz = strlen(name) + 1;
-        note.n_descsz = data_len;
-        note.n_type   = type;
-        memcpy(buf, &note, sizeof(note));
-        buf += (sizeof(note) +3)/4;
-        memcpy(buf, name, note.n_namesz);
-        buf += (note.n_namesz + 3)/4;
-        memcpy(buf, data, note.n_descsz);
-        buf += (note.n_descsz + 3)/4;
-
-        return buf;
-}
-
-static void final_note(u32 *buf)
-{
-        struct elf_note note;
-
-        note.n_namesz = 0;
-        note.n_descsz = 0;
-        note.n_type   = 0;
-        memcpy(buf, &note, sizeof(note));
-}
-
-static void crash_save_this_cpu(struct pt_regs *regs, int cpu)
-{
-        struct elf_prstatus prstatus;
-        u32 *buf;
-
-        if ((cpu < 0) || (cpu >= NR_CPUS))
-                return;
-
-        /* Using ELF notes here is opportunistic.
-         * I need a well defined structure format
-         * for the data I pass, and I need tags
-         * on the data to indicate what information I have
-         * squirrelled away.  ELF notes happen to provide
-         * all of that, so there is no need to invent something new.
-         */
-        buf = (u32*)per_cpu_ptr(crash_notes, cpu);
-        if (!buf)
-                return;
-        memset(&prstatus, 0, sizeof(prstatus));
-        prstatus.pr_pid = current->pid;
-        elf_core_copy_regs(&prstatus.pr_reg, regs);
-        buf = append_elf_note(buf, "CORE", NT_PRSTATUS, &prstatus,
-                                sizeof(prstatus));
-        final_note(buf);
-}
-
-static void crash_save_self(struct pt_regs *regs)
-{
-        int cpu;
-
-        cpu = safe_smp_processor_id();
-        crash_save_this_cpu(regs, cpu);
-}
-
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 static atomic_t waiting_for_crash_ipi;
 
@@ -121,7 +59,7 @@ static int crash_nmi_callback(struct notifier_block *self,
                 crash_fixup_ss_esp(&fixed_regs, regs);
                 regs = &fixed_regs;
         }
-        crash_save_this_cpu(regs, cpu);
+        crash_save_cpu(regs, cpu);
         disable_local_APIC();
         atomic_dec(&waiting_for_crash_ipi);
         /* Assume hlt works */
@@ -195,5 +133,5 @@ void machine_crash_shutdown(struct pt_regs *regs)
 #if defined(CONFIG_X86_IO_APIC)
         disable_IO_APIC();
 #endif
-        crash_save_self(regs);
+        crash_save_cpu(regs, safe_smp_processor_id());
 }
diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 7f015a71ab55..e21dcde0790e 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -34,6 +34,7 @@
 #include <linux/pci.h>
 #include <linux/msi.h>
 #include <linux/htirq.h>
+#include <linux/freezer.h>
 
 #include <asm/io.h>
 #include <asm/smp.h>
diff --git a/arch/i386/kernel/kprobes.c b/arch/i386/kernel/kprobes.c
index fc79e1e859c4..af1d53344993 100644
--- a/arch/i386/kernel/kprobes.c
+++ b/arch/i386/kernel/kprobes.c
@@ -184,7 +184,7 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
         mutex_lock(&kprobe_mutex);
-        free_insn_slot(p->ainsn.insn);
+        free_insn_slot(p->ainsn.insn, (p->ainsn.boostable == 1));
         mutex_unlock(&kprobe_mutex);
 }
 
@@ -333,7 +333,7 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
                 return 1;
 
 ss_probe:
-#ifndef CONFIG_PREEMPT
+#if !defined(CONFIG_PREEMPT) || defined(CONFIG_PM)
         if (p->ainsn.boostable == 1 && !p->post_handler){
                 /* Boost up -- we can execute copied instructions directly */
                 reset_current_kprobe();
diff --git a/arch/i386/kernel/microcode.c b/arch/i386/kernel/microcode.c
index 23f5984d0654..972346604f9d 100644
--- a/arch/i386/kernel/microcode.c
+++ b/arch/i386/kernel/microcode.c
@@ -703,7 +703,6 @@ static struct sysdev_driver mc_sysdev_driver = {
         .resume = mc_sysdev_resume,
 };
 
-#ifdef CONFIG_HOTPLUG_CPU
 static __cpuinit int
 mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 {
@@ -726,7 +725,6 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 static struct notifier_block mc_cpu_notifier = {
         .notifier_call = mc_cpu_callback,
 };
-#endif
 
 static int __init microcode_init (void)
 {
diff --git a/arch/i386/kernel/msr.c b/arch/i386/kernel/msr.c
index fd45059c9084..1d1a56cae340 100644
--- a/arch/i386/kernel/msr.c
+++ b/arch/i386/kernel/msr.c
@@ -249,7 +249,6 @@ static int msr_device_create(int i)
         return err;
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
 static int msr_class_cpu_callback(struct notifier_block *nfb,
                                 unsigned long action, void *hcpu)
 {
@@ -270,7 +269,6 @@ static struct notifier_block __cpuinitdata msr_class_cpu_notifier =
 {
         .notifier_call = msr_class_cpu_callback,
 };
-#endif
 
 static int __init msr_init(void)
 {
diff --git a/arch/i386/kernel/reboot.c b/arch/i386/kernel/reboot.c
index 84278e0093a2..3514b4153f7f 100644
--- a/arch/i386/kernel/reboot.c
+++ b/arch/i386/kernel/reboot.c
@@ -12,6 +12,7 @@
 #include <linux/dmi.h>
 #include <linux/ctype.h>
 #include <linux/pm.h>
+#include <linux/reboot.h>
 #include <asm/uaccess.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
diff --git a/arch/i386/kernel/setup.c b/arch/i386/kernel/setup.c
index 695d53fd14de..79df6e612dbd 100644
--- a/arch/i386/kernel/setup.c
+++ b/arch/i386/kernel/setup.c
@@ -448,8 +448,7 @@ void __init setup_bootmem_allocator(void)
         if (LOADER_TYPE && INITRD_START) {
                 if (INITRD_START + INITRD_SIZE <= (max_low_pfn << PAGE_SHIFT)) {
                         reserve_bootmem(INITRD_START, INITRD_SIZE);
-                        initrd_start =
-                                INITRD_START ? INITRD_START + PAGE_OFFSET : 0;
+                        initrd_start = INITRD_START + PAGE_OFFSET;
                         initrd_end = initrd_start+INITRD_SIZE;
                 }
                 else {
diff --git a/arch/i386/kernel/smp.c b/arch/i386/kernel/smp.c
index 1b080ab8a49f..5285aff8367f 100644
--- a/arch/i386/kernel/smp.c
+++ b/arch/i386/kernel/smp.c
@@ -693,6 +693,10 @@ int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
                 put_cpu();
                 return -EBUSY;
         }
+
+        /* Can deadlock when called with interrupts disabled */
+        WARN_ON(irqs_disabled());
+
         spin_lock_bh(&call_lock);
         __smp_call_function_single(cpu, func, info, nonatomic, wait);
         spin_unlock_bh(&call_lock);
diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c
index b4e6f32de453..4bf0e3c83b8b 100644
--- a/arch/i386/kernel/smpboot.c
+++ b/arch/i386/kernel/smpboot.c
@@ -1071,13 +1071,15 @@ void cpu_exit_clear(void)
 
 struct warm_boot_cpu_info {
         struct completion *complete;
+        struct work_struct task;
         int apicid;
         int cpu;
 };
 
-static void __cpuinit do_warm_boot_cpu(void *p)
+static void __cpuinit do_warm_boot_cpu(struct work_struct *work)
 {
-        struct warm_boot_cpu_info *info = p;
+        struct warm_boot_cpu_info *info =
+                container_of(work, struct warm_boot_cpu_info, task);
         do_boot_cpu(info->apicid, info->cpu);
         complete(info->complete);
 }
@@ -1086,7 +1088,6 @@ static int __cpuinit __smp_prepare_cpu(int cpu)
 {
         DECLARE_COMPLETION_ONSTACK(done);
         struct warm_boot_cpu_info info;
-        struct work_struct task;
         int     apicid, ret;
         struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
 
@@ -1111,7 +1112,7 @@ static int __cpuinit __smp_prepare_cpu(int cpu)
         info.complete = &done;
         info.apicid = apicid;
         info.cpu = cpu;
-        INIT_WORK(&task, do_warm_boot_cpu, &info);
+        INIT_WORK(&info.task, do_warm_boot_cpu);
 
         tsc_sync_disabled = 1;
 
@@ -1119,7 +1120,7 @@ static int __cpuinit __smp_prepare_cpu(int cpu)
         clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
                         KERNEL_PGD_PTRS);
         flush_tlb_all();
-        schedule_work(&task);
+        schedule_work(&info.task);
         wait_for_completion(&done);
 
         tsc_sync_disabled = 0;
diff --git a/arch/i386/kernel/sysenter.c b/arch/i386/kernel/sysenter.c
index 92849c7def5a..7de9117b5a3a 100644
--- a/arch/i386/kernel/sysenter.c
+++ b/arch/i386/kernel/sysenter.c
@@ -136,7 +136,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int exstack)
                 goto up_fail;
         }
 
-        vma = kmem_cache_zalloc(vm_area_cachep, SLAB_KERNEL);
+        vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
         if (!vma) {
                 ret = -ENOMEM;
                 goto up_fail;
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index c447807e2a45..68de48e498ca 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -464,7 +464,7 @@ void die(const char * str, struct pt_regs * regs, long err)
                 u32 lock_owner;
                 int lock_owner_depth;
         } die = {
-                .lock =                 SPIN_LOCK_UNLOCKED,
+                .lock =                 __SPIN_LOCK_UNLOCKED(die.lock),
                 .lock_owner =           -1,
                 .lock_owner_depth =     0
         };
diff --git a/arch/i386/kernel/tsc.c b/arch/i386/kernel/tsc.c
index 7f22e03253e2..1bbe45dca7a0 100644
--- a/arch/i386/kernel/tsc.c
+++ b/arch/i386/kernel/tsc.c
@@ -216,7 +216,7 @@ static unsigned int cpufreq_delayed_issched = 0;
 static unsigned int cpufreq_init = 0;
 static struct work_struct cpufreq_delayed_get_work;
 
-static void handle_cpufreq_delayed_get(void *v)
+static void handle_cpufreq_delayed_get(struct work_struct *work)
 {
         unsigned int cpu;
 
@@ -305,7 +305,7 @@ static int __init cpufreq_tsc(void)
 {
         int ret;
 
-        INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get, NULL);
+        INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get);
         ret = cpufreq_register_notifier(&time_cpufreq_notifier_block,
                                         CPUFREQ_TRANSITION_NOTIFIER);
         if (!ret)
diff --git a/arch/i386/mm/highmem.c b/arch/i386/mm/highmem.c
index f9f647cdbc7b..e0fa6cb655a8 100644
--- a/arch/i386/mm/highmem.c
+++ b/arch/i386/mm/highmem.c
@@ -32,7 +32,7 @@ void *kmap_atomic(struct page *page, enum km_type type)
         unsigned long vaddr;
 
         /* even !CONFIG_PREEMPT needs this, for in_atomic in do_page_fault */
-        inc_preempt_count();
+        pagefault_disable();
         if (!PageHighMem(page))
                 return page_address(page);
 
@@ -50,26 +50,22 @@ void kunmap_atomic(void *kvaddr, enum km_type type)
         unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
         enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
 
-#ifdef CONFIG_DEBUG_HIGHMEM
-        if (vaddr >= PAGE_OFFSET && vaddr < (unsigned long)high_memory) {
-                dec_preempt_count();
-                preempt_check_resched();
-                return;
-        }
-
-        if (vaddr != __fix_to_virt(FIX_KMAP_BEGIN+idx))
-                BUG();
-#endif
         /*
          * Force other mappings to Oops if they'll try to access this pte
          * without first remap it.  Keeping stale mappings around is a bad idea
          * also, in case the page changes cacheability attributes or becomes
          * a protected page in a hypervisor.
          */
-        kpte_clear_flush(kmap_pte-idx, vaddr);
+        if (vaddr == __fix_to_virt(FIX_KMAP_BEGIN+idx))
+                kpte_clear_flush(kmap_pte-idx, vaddr);
+        else {
+#ifdef CONFIG_DEBUG_HIGHMEM
+                BUG_ON(vaddr < PAGE_OFFSET);
+                BUG_ON(vaddr >= (unsigned long)high_memory);
+#endif
+        }
 
-        dec_preempt_count();
-        preempt_check_resched();
+        pagefault_enable();
 }
 
 /* This is the same as kmap_atomic() but can map memory that doesn't
@@ -80,7 +76,7 @@ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type)
         enum fixed_addresses idx;
         unsigned long vaddr;
 
-        inc_preempt_count();
+        pagefault_disable();
 
         idx = type + KM_TYPE_NR*smp_processor_id();
         vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
diff --git a/arch/i386/mm/hugetlbpage.c b/arch/i386/mm/hugetlbpage.c
index 1719a8141f81..34728e4afe48 100644
--- a/arch/i386/mm/hugetlbpage.c
+++ b/arch/i386/mm/hugetlbpage.c
@@ -17,6 +17,113 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+static unsigned long page_table_shareable(struct vm_area_struct *svma,
+                                struct vm_area_struct *vma,
+                                unsigned long addr, pgoff_t idx)
+{
+        unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) +
+                                svma->vm_start;
+        unsigned long sbase = saddr & PUD_MASK;
+        unsigned long s_end = sbase + PUD_SIZE;
+
+        /*
+         * match the virtual addresses, permission and the alignment of the
+         * page table page.
+         */
+        if (pmd_index(addr) != pmd_index(saddr) ||
+            vma->vm_flags != svma->vm_flags ||
+            sbase < svma->vm_start || svma->vm_end < s_end)
+                return 0;
+
+        return saddr;
+}
+
+static int vma_shareable(struct vm_area_struct *vma, unsigned long addr)
+{
+        unsigned long base = addr & PUD_MASK;
+        unsigned long end = base + PUD_SIZE;
+
+        /*
+         * check on proper vm_flags and page table alignment
+         */
+        if (vma->vm_flags & VM_MAYSHARE &&
+            vma->vm_start <= base && end <= vma->vm_end)
+                return 1;
+        return 0;
+}
+
+/*
+ * search for a shareable pmd page for hugetlb.
+ */
+static void huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud)
+{
+        struct vm_area_struct *vma = find_vma(mm, addr);
+        struct address_space *mapping = vma->vm_file->f_mapping;
+        pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+                        vma->vm_pgoff;
+        struct prio_tree_iter iter;
+        struct vm_area_struct *svma;
+        unsigned long saddr;
+        pte_t *spte = NULL;
+
+        if (!vma_shareable(vma, addr))
+                return;
+
+        spin_lock(&mapping->i_mmap_lock);
+        vma_prio_tree_foreach(svma, &iter, &mapping->i_mmap, idx, idx) {
+                if (svma == vma)
+                        continue;
+
+                saddr = page_table_shareable(svma, vma, addr, idx);
+                if (saddr) {
+                        spte = huge_pte_offset(svma->vm_mm, saddr);
+                        if (spte) {
+                                get_page(virt_to_page(spte));
+                                break;
+                        }
+                }
+        }
+
+        if (!spte)
+                goto out;
+
+        spin_lock(&mm->page_table_lock);
+        if (pud_none(*pud))
+                pud_populate(mm, pud, (unsigned long) spte & PAGE_MASK);
+        else
+                put_page(virt_to_page(spte));
+        spin_unlock(&mm->page_table_lock);
+out:
+        spin_unlock(&mapping->i_mmap_lock);
+}
+
+/*
+ * unmap huge page backed by shared pte.
+ *
+ * Hugetlb pte page is ref counted at the time of mapping.  If pte is shared
+ * indicated by page_count > 1, unmap is achieved by clearing pud and
+ * decrementing the ref count. If count == 1, the pte page is not shared.
+ *
+ * called with vma->vm_mm->page_table_lock held.
+ *
+ * returns: 1 successfully unmapped a shared pte page
+ *          0 the underlying pte page is not shared, or it is the last user
+ */
+int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
+{
+        pgd_t *pgd = pgd_offset(mm, *addr);
+        pud_t *pud = pud_offset(pgd, *addr);
+
+        BUG_ON(page_count(virt_to_page(ptep)) == 0);
+        if (page_count(virt_to_page(ptep)) == 1)
+                return 0;
+
+        pud_clear(pud);
+        put_page(virt_to_page(ptep));
+        *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE;
+        return 1;
+}
+
 pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 {
         pgd_t *pgd;
@@ -25,8 +132,11 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 
         pgd = pgd_offset(mm, addr);
         pud = pud_alloc(mm, pgd, addr);
-        if (pud)
+        if (pud) {
+                if (pud_none(*pud))
+                        huge_pmd_share(mm, addr, pud);
                 pte = (pte_t *) pmd_alloc(mm, pud, addr);
+        }
         BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
 
         return pte;
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index f4dd048187ff..84697dfc7348 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -697,8 +697,8 @@ int remove_memory(u64 start, u64 size)
 #endif
 #endif
 
-kmem_cache_t *pgd_cache;
-kmem_cache_t *pmd_cache;
+struct kmem_cache *pgd_cache;
+struct kmem_cache *pmd_cache;
 
 void __init pgtable_cache_init(void)
 {
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index 65b5c0959033..f349eaf450b0 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -196,7 +196,7 @@ struct page *pte_alloc_one(struct mm_struct *mm, unsigned long address)
         return pte;
 }
 
-void pmd_ctor(void *pmd, kmem_cache_t *cache, unsigned long flags)
+void pmd_ctor(void *pmd, struct kmem_cache *cache, unsigned long flags)
 {
         memset(pmd, 0, PTRS_PER_PMD*sizeof(pmd_t));
 }
@@ -236,7 +236,7 @@ static inline void pgd_list_del(pgd_t *pgd)
                 set_page_private(next, (unsigned long)pprev);
 }
 
-void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
+void pgd_ctor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 {
         unsigned long flags;
 
@@ -256,7 +256,7 @@ void pgd_ctor(void *pgd, kmem_cache_t *cache, unsigned long unused)
 }
 
 /* never called when PTRS_PER_PMD > 1 */
-void pgd_dtor(void *pgd, kmem_cache_t *cache, unsigned long unused)
+void pgd_dtor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 {
         unsigned long flags; /* can be called from interrupt context */
 
diff --git a/arch/i386/power/Makefile b/arch/i386/power/Makefile
index 8cfa4e8a719d..2de7bbf03cd7 100644
--- a/arch/i386/power/Makefile
+++ b/arch/i386/power/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_PM)                += cpu.o
-obj-$(CONFIG_SOFTWARE_SUSPEND)  += swsusp.o
+obj-$(CONFIG_SOFTWARE_SUSPEND)  += swsusp.o suspend.o
diff --git a/arch/i386/power/suspend.c b/arch/i386/power/suspend.c
new file mode 100644
index 000000000000..db5e98d2eb73
--- /dev/null
+++ b/arch/i386/power/suspend.c
@@ -0,0 +1,158 @@
+/*
+ * Suspend support specific for i386 - temporary page tables
+ *
+ * Distribute under GPLv2
+ *
+ * Copyright (c) 2006 Rafael J. Wysocki <rjw@sisk.pl>
+ */
+
+#include <linux/suspend.h>
+#include <linux/bootmem.h>
+
+#include <asm/system.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+
+/* Defined in arch/i386/power/swsusp.S */
+extern int restore_image(void);
+
+/* Pointer to the temporary resume page tables */
+pgd_t *resume_pg_dir;
+
+/* The following three functions are based on the analogous code in
+ * arch/i386/mm/init.c
+ */
+
+/*
+ * Create a middle page table on a resume-safe page and put a pointer to it in
+ * the given global directory entry.  This only returns the gd entry
+ * in non-PAE compilation mode, since the middle layer is folded.
+ */
+static pmd_t *resume_one_md_table_init(pgd_t *pgd)
+{
+        pud_t *pud;
+        pmd_t *pmd_table;
+
+#ifdef CONFIG_X86_PAE
+        pmd_table = (pmd_t *)get_safe_page(GFP_ATOMIC);
+        if (!pmd_table)
+                return NULL;
+
+        set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
+        pud = pud_offset(pgd, 0);
+
+        BUG_ON(pmd_table != pmd_offset(pud, 0));
+#else
+        pud = pud_offset(pgd, 0);
+        pmd_table = pmd_offset(pud, 0);
+#endif
+
+        return pmd_table;
+}
+
+/*
+ * Create a page table on a resume-safe page and place a pointer to it in
+ * a middle page directory entry.
+ */
+static pte_t *resume_one_page_table_init(pmd_t *pmd)
+{
+        if (pmd_none(*pmd)) {
+                pte_t *page_table = (pte_t *)get_safe_page(GFP_ATOMIC);
+                if (!page_table)
+                        return NULL;
+
+                set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
+
+                BUG_ON(page_table != pte_offset_kernel(pmd, 0));
+
+                return page_table;
+        }
+
+        return pte_offset_kernel(pmd, 0);
+}
+
+/*
+ * This maps the physical memory to kernel virtual address space, a total
+ * of max_low_pfn pages, by creating page tables starting from address
+ * PAGE_OFFSET.  The page tables are allocated out of resume-safe pages.
+ */
+static int resume_physical_mapping_init(pgd_t *pgd_base)
+{
+        unsigned long pfn;
+        pgd_t *pgd;
+        pmd_t *pmd;
+        pte_t *pte;
+        int pgd_idx, pmd_idx;
+
+        pgd_idx = pgd_index(PAGE_OFFSET);
+        pgd = pgd_base + pgd_idx;
+        pfn = 0;
+
+        for (; pgd_idx < PTRS_PER_PGD; pgd++, pgd_idx++) {
+                pmd = resume_one_md_table_init(pgd);
+                if (!pmd)
+                        return -ENOMEM;
+
+                if (pfn >= max_low_pfn)
+                        continue;
+
+                for (pmd_idx = 0; pmd_idx < PTRS_PER_PMD; pmd++, pmd_idx++) {
+                        if (pfn >= max_low_pfn)
+                                break;
+
+                        /* Map with big pages if possible, otherwise create
+                         * normal page tables.
+                         * NOTE: We can mark everything as executable here
+                         */
+                        if (cpu_has_pse) {
+                                set_pmd(pmd, pfn_pmd(pfn, PAGE_KERNEL_LARGE_EXEC));
+                                pfn += PTRS_PER_PTE;
+                        } else {
+                                pte_t *max_pte;
+
+                                pte = resume_one_page_table_init(pmd);
+                                if (!pte)
+                                        return -ENOMEM;
+
+                                max_pte = pte + PTRS_PER_PTE;
+                                for (; pte < max_pte; pte++, pfn++) {
+                                        if (pfn >= max_low_pfn)
+                                                break;
+
+                                        set_pte(pte, pfn_pte(pfn, PAGE_KERNEL_EXEC));
+                                }
+                        }
+                }
+        }
+        return 0;
+}
+
+static inline void resume_init_first_level_page_table(pgd_t *pg_dir)
+{
+#ifdef CONFIG_X86_PAE
+        int i;
+
+        /* Init entries of the first-level page table to the zero page */
+        for (i = 0; i < PTRS_PER_PGD; i++)
+                set_pgd(pg_dir + i,
+                        __pgd(__pa(empty_zero_page) | _PAGE_PRESENT));
+#endif
+}
+
+int swsusp_arch_resume(void)
+{
+        int error;
+
+        resume_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC);
+        if (!resume_pg_dir)
+                return -ENOMEM;
+
+        resume_init_first_level_page_table(resume_pg_dir);
+        error = resume_physical_mapping_init(resume_pg_dir);
+        if (error)
+                return error;
+
+        /* We have got enough memory and from now on we cannot recover */
+        restore_image();
+        return 0;
+}
diff --git a/arch/i386/power/swsusp.S b/arch/i386/power/swsusp.S
index 8a2b50a0aaad..53662e05b393 100644
--- a/arch/i386/power/swsusp.S
+++ b/arch/i386/power/swsusp.S
@@ -28,8 +28,9 @@ ENTRY(swsusp_arch_suspend)
         call swsusp_save
         ret
 
-ENTRY(swsusp_arch_resume)
-        movl    $swsusp_pg_dir-__PAGE_OFFSET, %ecx
+ENTRY(restore_image)
+        movl    resume_pg_dir, %ecx
+        subl    $__PAGE_OFFSET, %ecx
         movl    %ecx, %cr3
 
         movl    restore_pblist, %edx
@@ -51,6 +52,10 @@ copy_loop:
         .p2align 4,,7
 
 done:
+        /* go back to the original page tables */
+        movl    $swapper_pg_dir, %ecx
+        subl    $__PAGE_OFFSET, %ecx
+        movl    %ecx, %cr3
         /* Flush TLB, including "global" things (vmalloc) */
         movl    mmu_cr4_features, %eax
         movl    %eax, %edx