10 files changed, 65 insertions, 196 deletions

diff --git a/arch/i386/boot/Makefile b/arch/i386/boot/Makefile
index aa7064a75e..43cd6220ee 100644
--- a/arch/i386/boot/Makefile
+++ b/arch/i386/boot/Makefile
@@ -48,7 +48,7 @@ cmd_image = $(obj)/tools/build $(BUILDFLAGS) $(obj)/bootsect $(obj)/setup \
 $(obj)/zImage $(obj)/bzImage: $(obj)/bootsect $(obj)/setup \
                               $(obj)/vmlinux.bin $(obj)/tools/build FORCE
         $(call if_changed,image)
-        @echo 'Kernel: $@ is ready'
+        @echo 'Kernel: $@ is ready' ' (#'`cat .version`')'
 
 $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
         $(call if_changed,objcopy)
diff --git a/arch/i386/kernel/Makefile b/arch/i386/kernel/Makefile
index 0fbcfe00dd..51ecd51260 100644
--- a/arch/i386/kernel/Makefile
+++ b/arch/i386/kernel/Makefile
@@ -43,7 +43,7 @@ obj-$(CONFIG_SCx200)		+= scx200.o
 # Note: kbuild does not track this dependency due to usage of .incbin
 $(obj)/vsyscall.o: $(obj)/vsyscall-int80.so $(obj)/vsyscall-sysenter.so
 targets += $(foreach F,int80 sysenter,vsyscall-$F.o vsyscall-$F.so)
-targets += vsyscall.lds
+targets += vsyscall-note.o vsyscall.lds
 
 # The DSO images are built using a special linker script.
 quiet_cmd_syscall = SYSCALL $@
diff --git a/arch/i386/kernel/apm.c b/arch/i386/kernel/apm.c
index 45641a8725..0ff65abcd5 100644
--- a/arch/i386/kernel/apm.c
+++ b/arch/i386/kernel/apm.c
@@ -1222,6 +1222,7 @@ static int suspend(int vetoable)
 
         save_processor_state();
         err = set_system_power_state(APM_STATE_SUSPEND);
+        ignore_normal_resume = 1;
         restore_processor_state();
 
         local_irq_disable();
@@ -1229,7 +1230,6 @@ static int suspend(int vetoable)
         spin_lock(&i8253_lock);
         reinit_timer();
         set_time();
-        ignore_normal_resume = 1;
 
         spin_unlock(&i8253_lock);
         write_sequnlock(&xtime_lock);
diff --git a/arch/i386/kernel/cpuid.c b/arch/i386/kernel/cpuid.c
index 2e2756345b..4647db4ad6 100644
--- a/arch/i386/kernel/cpuid.c
+++ b/arch/i386/kernel/cpuid.c
@@ -45,7 +45,7 @@
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
-static struct class_simple *cpuid_class;
+static struct class *cpuid_class;
 
 #ifdef CONFIG_SMP
 
@@ -158,12 +158,12 @@ static struct file_operations cpuid_fops = {
         .open = cpuid_open,
 };
 
-static int cpuid_class_simple_device_add(int i) 
+static int cpuid_class_device_create(int i)
 {
         int err = 0;
         struct class_device *class_err;
 
-        class_err = class_simple_device_add(cpuid_class, MKDEV(CPUID_MAJOR, i), NULL, "cpu%d",i);
+        class_err = class_device_create(cpuid_class, MKDEV(CPUID_MAJOR, i), NULL, "cpu%d",i);
         if (IS_ERR(class_err))
                 err = PTR_ERR(class_err);
         return err;
@@ -175,10 +175,10 @@ static int __devinit cpuid_class_cpu_callback(struct notifier_block *nfb, unsign
 
         switch (action) {
         case CPU_ONLINE:
-                cpuid_class_simple_device_add(cpu);
+                cpuid_class_device_create(cpu);
                 break;
         case CPU_DEAD:
-                class_simple_device_remove(MKDEV(CPUID_MAJOR, cpu));
+                class_device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu));
                 break;
         }
         return NOTIFY_OK;
@@ -200,13 +200,13 @@ static int __init cpuid_init(void)
                 err = -EBUSY;
                 goto out;
         }
-        cpuid_class = class_simple_create(THIS_MODULE, "cpuid");
+        cpuid_class = class_create(THIS_MODULE, "cpuid");
         if (IS_ERR(cpuid_class)) {
                 err = PTR_ERR(cpuid_class);
                 goto out_chrdev;
         }
         for_each_online_cpu(i) {
-                err = cpuid_class_simple_device_add(i);
+                err = cpuid_class_device_create(i);
                 if (err != 0) 
                         goto out_class;
         }
@@ -218,9 +218,9 @@ static int __init cpuid_init(void)
 out_class:
         i = 0;
         for_each_online_cpu(i) {
-                class_simple_device_remove(MKDEV(CPUID_MAJOR, i));
+                class_device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, i));
         }
-        class_simple_destroy(cpuid_class);
+        class_destroy(cpuid_class);
 out_chrdev:
         unregister_chrdev(CPUID_MAJOR, "cpu/cpuid");    
 out:
@@ -232,8 +232,8 @@ static void __exit cpuid_exit(void)
         int cpu = 0;
 
         for_each_online_cpu(cpu)
-                class_simple_device_remove(MKDEV(CPUID_MAJOR, cpu));
-        class_simple_destroy(cpuid_class);
+                class_device_destroy(cpuid_class, MKDEV(CPUID_MAJOR, cpu));
+        class_destroy(cpuid_class);
         unregister_chrdev(CPUID_MAJOR, "cpu/cpuid");
         unregister_cpu_notifier(&cpuid_class_cpu_notifier);
 }
diff --git a/arch/i386/kernel/msr.c b/arch/i386/kernel/msr.c
index 05d9f8f363..b2f03c39a6 100644
--- a/arch/i386/kernel/msr.c
+++ b/arch/i386/kernel/msr.c
@@ -44,7 +44,7 @@
 #include <asm/uaccess.h>
 #include <asm/system.h>
 
-static struct class_simple *msr_class;
+static struct class *msr_class;
 
 /* Note: "err" is handled in a funny way below.  Otherwise one version
    of gcc or another breaks. */
@@ -260,12 +260,12 @@ static struct file_operations msr_fops = {
         .open = msr_open,
 };
 
-static int msr_class_simple_device_add(int i)
+static int msr_class_device_create(int i)
 {
         int err = 0;
         struct class_device *class_err;
 
-        class_err = class_simple_device_add(msr_class, MKDEV(MSR_MAJOR, i), NULL, "msr%d",i);
+        class_err = class_device_create(msr_class, MKDEV(MSR_MAJOR, i), NULL, "msr%d",i);
         if (IS_ERR(class_err)) 
                 err = PTR_ERR(class_err);
         return err;
@@ -277,10 +277,10 @@ static int __devinit msr_class_cpu_callback(struct notifier_block *nfb, unsigned
 
         switch (action) {
         case CPU_ONLINE:
-                msr_class_simple_device_add(cpu);
+                msr_class_device_create(cpu);
                 break;
         case CPU_DEAD:
-                class_simple_device_remove(MKDEV(MSR_MAJOR, cpu));      
+                class_device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu));
                 break;
         }
         return NOTIFY_OK;
@@ -302,13 +302,13 @@ static int __init msr_init(void)
                 err = -EBUSY;
                 goto out;
         }
-        msr_class = class_simple_create(THIS_MODULE, "msr");
+        msr_class = class_create(THIS_MODULE, "msr");
         if (IS_ERR(msr_class)) {
                 err = PTR_ERR(msr_class);
                 goto out_chrdev;
         }
         for_each_online_cpu(i) {
-                err = msr_class_simple_device_add(i);
+                err = msr_class_device_create(i);
                 if (err != 0)
                         goto out_class;
         }
@@ -320,8 +320,8 @@ static int __init msr_init(void)
 out_class:
         i = 0;
         for_each_online_cpu(i)
-                class_simple_device_remove(MKDEV(MSR_MAJOR, i));
-        class_simple_destroy(msr_class);
+                class_device_destroy(msr_class, MKDEV(MSR_MAJOR, i));
+        class_destroy(msr_class);
 out_chrdev:
         unregister_chrdev(MSR_MAJOR, "cpu/msr");
 out:
@@ -332,8 +332,8 @@ static void __exit msr_exit(void)
 {
         int cpu = 0;
         for_each_online_cpu(cpu)
-                class_simple_device_remove(MKDEV(MSR_MAJOR, cpu));
-        class_simple_destroy(msr_class);
+                class_device_destroy(msr_class, MKDEV(MSR_MAJOR, cpu));
+        class_destroy(msr_class);
         unregister_chrdev(MSR_MAJOR, "cpu/msr");
         unregister_cpu_notifier(&msr_class_cpu_notifier);
 }
diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index 6cd1ed311f..d408afaf64 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -251,7 +251,7 @@ ENTRY(sys_call_table)
         .long sys_io_submit
         .long sys_io_cancel
         .long sys_fadvise64     /* 250 */
-        .long sys_ni_syscall
+        .long sys_set_zone_reclaim
         .long sys_exit_group
         .long sys_lookup_dcookie
         .long sys_epoll_create
diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 00c63419c0..83c579e82a 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -306,7 +306,7 @@ void die(const char * str, struct pt_regs * regs, long err)
         };
         static int die_counter;
 
-        if (die.lock_owner != _smp_processor_id()) {
+        if (die.lock_owner != raw_smp_processor_id()) {
                 console_verbose();
                 spin_lock_irq(&die.lock);
                 die.lock_owner = smp_processor_id();
diff --git a/arch/i386/lib/delay.c b/arch/i386/lib/delay.c
index 080639f262..eb0cdfe928 100644
--- a/arch/i386/lib/delay.c
+++ b/arch/i386/lib/delay.c
@@ -34,7 +34,7 @@ inline void __const_udelay(unsigned long xloops)
         xloops *= 4;
         __asm__("mull %0"
                 :"=d" (xloops), "=&a" (d0)
-                :"1" (xloops),"0" (cpu_data[_smp_processor_id()].loops_per_jiffy * (HZ/4)));
+                :"1" (xloops),"0" (cpu_data[raw_smp_processor_id()].loops_per_jiffy * (HZ/4)));
         __delay(++xloops);
 }
 
diff --git a/arch/i386/mm/hugetlbpage.c b/arch/i386/mm/hugetlbpage.c
index 171fc925e1..3b099f32b9 100644
--- a/arch/i386/mm/hugetlbpage.c
+++ b/arch/i386/mm/hugetlbpage.c
@@ -18,7 +18,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 {
         pgd_t *pgd;
         pud_t *pud;
@@ -30,7 +30,7 @@ static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
         return (pte_t *) pmd;
 }
 
-static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 {
         pgd_t *pgd;
         pud_t *pud;
@@ -42,21 +42,6 @@ static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
         return (pte_t *) pmd;
 }
 
-static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, pte_t * page_table, int write_access)
-{
-        pte_t entry;
-
-        add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
-        if (write_access) {
-                entry =
-                    pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot)));
-        } else
-                entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
-        entry = pte_mkyoung(entry);
-        mk_pte_huge(entry);
-        set_pte(page_table, entry);
-}
-
 /*
  * This function checks for proper alignment of input addr and len parameters.
  */
@@ -69,77 +54,6 @@ int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
         return 0;
 }
 
-int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
-                        struct vm_area_struct *vma)
-{
-        pte_t *src_pte, *dst_pte, entry;
-        struct page *ptepage;
-        unsigned long addr = vma->vm_start;
-        unsigned long end = vma->vm_end;
-
-        while (addr < end) {
-                dst_pte = huge_pte_alloc(dst, addr);
-                if (!dst_pte)
-                        goto nomem;
-                src_pte = huge_pte_offset(src, addr);
-                entry = *src_pte;
-                ptepage = pte_page(entry);
-                get_page(ptepage);
-                set_pte(dst_pte, entry);
-                add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_SIZE);
-                addr += HPAGE_SIZE;
-        }
-        return 0;
-
-nomem:
-        return -ENOMEM;
-}
-
-int
-follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
-                    struct page **pages, struct vm_area_struct **vmas,
-                    unsigned long *position, int *length, int i)
-{
-        unsigned long vpfn, vaddr = *position;
-        int remainder = *length;
-
-        WARN_ON(!is_vm_hugetlb_page(vma));
-
-        vpfn = vaddr/PAGE_SIZE;
-        while (vaddr < vma->vm_end && remainder) {
-
-                if (pages) {
-                        pte_t *pte;
-                        struct page *page;
-
-                        pte = huge_pte_offset(mm, vaddr);
-
-                        /* hugetlb should be locked, and hence, prefaulted */
-                        WARN_ON(!pte || pte_none(*pte));
-
-                        page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
-
-                        WARN_ON(!PageCompound(page));
-
-                        get_page(page);
-                        pages[i] = page;
-                }
-
-                if (vmas)
-                        vmas[i] = vma;
-
-                vaddr += PAGE_SIZE;
-                ++vpfn;
-                --remainder;
-                ++i;
-        }
-
-        *length = remainder;
-        *position = vaddr;
-
-        return i;
-}
-
 #if 0   /* This is just for testing */
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
@@ -204,83 +118,15 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 }
 #endif
 
-void unmap_hugepage_range(struct vm_area_struct *vma,
-                unsigned long start, unsigned long end)
+void hugetlb_clean_stale_pgtable(pte_t *pte)
 {
-        struct mm_struct *mm = vma->vm_mm;
-        unsigned long address;
-        pte_t pte, *ptep;
+        pmd_t *pmd = (pmd_t *) pte;
         struct page *page;
 
-        BUG_ON(start & (HPAGE_SIZE - 1));
-        BUG_ON(end & (HPAGE_SIZE - 1));
-
-        for (address = start; address < end; address += HPAGE_SIZE) {
-                ptep = huge_pte_offset(mm, address);
-                if (!ptep)
-                        continue;
-                pte = ptep_get_and_clear(mm, address, ptep);
-                if (pte_none(pte))
-                        continue;
-                page = pte_page(pte);
-                put_page(page);
-        }
-        add_mm_counter(mm ,rss, -((end - start) >> PAGE_SHIFT));
-        flush_tlb_range(vma, start, end);
-}
-
-int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
-{
-        struct mm_struct *mm = current->mm;
-        unsigned long addr;
-        int ret = 0;
-
-        BUG_ON(vma->vm_start & ~HPAGE_MASK);
-        BUG_ON(vma->vm_end & ~HPAGE_MASK);
-
-        spin_lock(&mm->page_table_lock);
-        for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
-                unsigned long idx;
-                pte_t *pte = huge_pte_alloc(mm, addr);
-                struct page *page;
-
-                if (!pte) {
-                        ret = -ENOMEM;
-                        goto out;
-                }
-
-                if (!pte_none(*pte))
-                        continue;
-
-                idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
-                        + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
-                page = find_get_page(mapping, idx);
-                if (!page) {
-                        /* charge the fs quota first */
-                        if (hugetlb_get_quota(mapping)) {
-                                ret = -ENOMEM;
-                                goto out;
-                        }
-                        page = alloc_huge_page();
-                        if (!page) {
-                                hugetlb_put_quota(mapping);
-                                ret = -ENOMEM;
-                                goto out;
-                        }
-                        ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
-                        if (! ret) {
-                                unlock_page(page);
-                        } else {
-                                hugetlb_put_quota(mapping);
-                                free_huge_page(page);
-                                goto out;
-                        }
-                }
-                set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
-        }
-out:
-        spin_unlock(&mm->page_table_lock);
-        return ret;
+        page = pmd_page(*pmd);
+        pmd_clear(pmd);
+        dec_page_state(nr_page_table_pages);
+        page_cache_release(page);
 }
 
 /* x86_64 also uses this file */
@@ -294,7 +140,12 @@ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file,
         struct vm_area_struct *vma;
         unsigned long start_addr;
 
-        start_addr = mm->free_area_cache;
+        if (len > mm->cached_hole_size) {
+                start_addr = mm->free_area_cache;
+        } else {
+                start_addr = TASK_UNMAPPED_BASE;
+                mm->cached_hole_size = 0;
+        }
 
 full_search:
         addr = ALIGN(start_addr, HPAGE_SIZE);
@@ -308,6 +159,7 @@ full_search:
                          */
                         if (start_addr != TASK_UNMAPPED_BASE) {
                                 start_addr = TASK_UNMAPPED_BASE;
+                                mm->cached_hole_size = 0;
                                 goto full_search;
                         }
                         return -ENOMEM;
@@ -316,6 +168,8 @@ full_search:
                         mm->free_area_cache = addr + len;
                         return addr;
                 }
+                if (addr + mm->cached_hole_size < vma->vm_start)
+                        mm->cached_hole_size = vma->vm_start - addr;
                 addr = ALIGN(vma->vm_end, HPAGE_SIZE);
         }
 }
@@ -327,12 +181,17 @@ static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file,
         struct mm_struct *mm = current->mm;
         struct vm_area_struct *vma, *prev_vma;
         unsigned long base = mm->mmap_base, addr = addr0;
+        unsigned long largest_hole = mm->cached_hole_size;
         int first_time = 1;
 
         /* don't allow allocations above current base */
         if (mm->free_area_cache > base)
                 mm->free_area_cache = base;
 
+        if (len <= largest_hole) {
+                largest_hole = 0;
+                mm->free_area_cache  = base;
+        }
 try_again:
         /* make sure it can fit in the remaining address space */
         if (mm->free_area_cache < len)
@@ -353,13 +212,21 @@ try_again:
                  * vma->vm_start, use it:
                  */
                 if (addr + len <= vma->vm_start &&
-                                (!prev_vma || (addr >= prev_vma->vm_end)))
+                            (!prev_vma || (addr >= prev_vma->vm_end))) {
                         /* remember the address as a hint for next time */
-                        return (mm->free_area_cache = addr);
-                else
+                        mm->cached_hole_size = largest_hole;
+                        return (mm->free_area_cache = addr);
+                } else {
                         /* pull free_area_cache down to the first hole */
-                        if (mm->free_area_cache == vma->vm_end)
+                        if (mm->free_area_cache == vma->vm_end) {
                                 mm->free_area_cache = vma->vm_start;
+                                mm->cached_hole_size = largest_hole;
+                        }
+                }
+
+                /* remember the largest hole we saw so far */
+                if (addr + largest_hole < vma->vm_start)
+                        largest_hole = vma->vm_start - addr;
 
                 /* try just below the current vma->vm_start */
                 addr = (vma->vm_start - len) & HPAGE_MASK;
@@ -372,6 +239,7 @@ fail:
          */
         if (first_time) {
                 mm->free_area_cache = base;
+                largest_hole = 0;
                 first_time = 0;
                 goto try_again;
         }
@@ -382,6 +250,7 @@ fail:
          * allocations.
          */
         mm->free_area_cache = TASK_UNMAPPED_BASE;
+        mm->cached_hole_size = ~0UL;
         addr = hugetlb_get_unmapped_area_bottomup(file, addr0,
                         len, pgoff, flags);
 
@@ -389,6 +258,7 @@ fail:
          * Restore the topdown base:
          */
         mm->free_area_cache = base;
+        mm->cached_hole_size = ~0UL;
 
         return addr;
 }
diff --git a/arch/i386/mm/init.c b/arch/i386/mm/init.c
index 7a7ea37372..8766c771bb 100644
--- a/arch/i386/mm/init.c
+++ b/arch/i386/mm/init.c
@@ -269,7 +269,6 @@ void __init one_highpage_init(struct page *page, int pfn, int bad_ppro)
 {
         if (page_is_ram(pfn) && !(bad_ppro && page_kills_ppro(pfn))) {
                 ClearPageReserved(page);
-                set_bit(PG_highmem, &page->flags);
                 set_page_count(page, 1);
                 __free_page(page);
                 totalhigh_pages++;