8 files changed, 48 insertions, 36 deletions

diff --git a/kernel/acct.c b/kernel/acct.c
index b756f527497e..2e3f4a47e7d0 100644
--- a/kernel/acct.c
+++ b/kernel/acct.c
@@ -553,7 +553,7 @@ void acct_update_integrals(struct task_struct *tsk)
                 if (delta == 0)
                         return;
                 tsk->acct_stimexpd = tsk->stime;
-                tsk->acct_rss_mem1 += delta * get_mm_counter(tsk->mm, rss);
+                tsk->acct_rss_mem1 += delta * get_mm_rss(tsk->mm);
                 tsk->acct_vm_mem1 += delta * tsk->mm->total_vm;
         }
 }
diff --git a/kernel/exit.c b/kernel/exit.c
index 3b25b182d2be..79f52b85d6ed 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -839,7 +839,10 @@ fastcall NORET_TYPE void do_exit(long code)
                                 preempt_count());
 
         acct_update_integrals(tsk);
-        update_mem_hiwater(tsk);
+        if (tsk->mm) {
+                update_hiwater_rss(tsk->mm);
+                update_hiwater_vm(tsk->mm);
+        }
         group_dead = atomic_dec_and_test(&tsk->signal->live);
         if (group_dead) {
                 del_timer_sync(&tsk->signal->real_timer);
diff --git a/kernel/fork.c b/kernel/fork.c
index 280bd44ac441..8a069612eac3 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -182,37 +182,37 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 }
 
 #ifdef CONFIG_MMU
-static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
+static inline int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-        struct vm_area_struct * mpnt, *tmp, **pprev;
+        struct vm_area_struct *mpnt, *tmp, **pprev;
         struct rb_node **rb_link, *rb_parent;
         int retval;
         unsigned long charge;
         struct mempolicy *pol;
 
         down_write(&oldmm->mmap_sem);
-        flush_cache_mm(current->mm);
+        flush_cache_mm(oldmm);
+        down_write(&mm->mmap_sem);
+
         mm->locked_vm = 0;
         mm->mmap = NULL;
         mm->mmap_cache = NULL;
         mm->free_area_cache = oldmm->mmap_base;
         mm->cached_hole_size = ~0UL;
         mm->map_count = 0;
-        set_mm_counter(mm, rss, 0);
-        set_mm_counter(mm, anon_rss, 0);
         cpus_clear(mm->cpu_vm_mask);
         mm->mm_rb = RB_ROOT;
         rb_link = &mm->mm_rb.rb_node;
         rb_parent = NULL;
         pprev = &mm->mmap;
 
-        for (mpnt = current->mm->mmap ; mpnt ; mpnt = mpnt->vm_next) {
+        for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) {
                 struct file *file;
 
                 if (mpnt->vm_flags & VM_DONTCOPY) {
                         long pages = vma_pages(mpnt);
                         mm->total_vm -= pages;
-                        __vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
+                        vm_stat_account(mm, mpnt->vm_flags, mpnt->vm_file,
                                                                 -pages);
                         continue;
                 }
@@ -253,12 +253,8 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
                 }
 
                 /*
-                 * Link in the new vma and copy the page table entries:
-                 * link in first so that swapoff can see swap entries.
-                 * Note that, exceptionally, here the vma is inserted
-                 * without holding mm->mmap_sem.
+                 * Link in the new vma and copy the page table entries.
                  */
-                spin_lock(&mm->page_table_lock);
                 *pprev = tmp;
                 pprev = &tmp->vm_next;
 
@@ -267,8 +263,7 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
                 rb_parent = &tmp->vm_rb;
 
                 mm->map_count++;
-                retval = copy_page_range(mm, current->mm, tmp);
-                spin_unlock(&mm->page_table_lock);
+                retval = copy_page_range(mm, oldmm, tmp);
 
                 if (tmp->vm_ops && tmp->vm_ops->open)
                         tmp->vm_ops->open(tmp);
@@ -277,9 +272,9 @@ static inline int dup_mmap(struct mm_struct * mm, struct mm_struct * oldmm)
                         goto out;
         }
         retval = 0;
-
 out:
-        flush_tlb_mm(current->mm);
+        up_write(&mm->mmap_sem);
+        flush_tlb_mm(oldmm);
         up_write(&oldmm->mmap_sem);
         return retval;
 fail_nomem_policy:
@@ -323,6 +318,8 @@ static struct mm_struct * mm_init(struct mm_struct * mm)
         INIT_LIST_HEAD(&mm->mmlist);
         mm->core_waiters = 0;
         mm->nr_ptes = 0;
+        set_mm_counter(mm, file_rss, 0);
+        set_mm_counter(mm, anon_rss, 0);
         spin_lock_init(&mm->page_table_lock);
         rwlock_init(&mm->ioctx_list_lock);
         mm->ioctx_list = NULL;
@@ -499,7 +496,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct * tsk)
         if (retval)
                 goto free_pt;
 
-        mm->hiwater_rss = get_mm_counter(mm,rss);
+        mm->hiwater_rss = get_mm_rss(mm);
         mm->hiwater_vm = mm->total_vm;
 
 good_mm:
diff --git a/kernel/futex.c b/kernel/futex.c
index ca05fe6a70b2..3b4d5ad44cc6 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -205,15 +205,13 @@ static int get_futex_key(unsigned long uaddr, union futex_key *key)
         /*
          * Do a quick atomic lookup first - this is the fastpath.
          */
-        spin_lock(&current->mm->page_table_lock);
-        page = follow_page(mm, uaddr, 0);
+        page = follow_page(mm, uaddr, FOLL_TOUCH|FOLL_GET);
         if (likely(page != NULL)) {
                 key->shared.pgoff =
                         page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
-                spin_unlock(&current->mm->page_table_lock);
+                put_page(page);
                 return 0;
         }
-        spin_unlock(&current->mm->page_table_lock);
 
         /*
          * Do it the general way.
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 36c5d9cd4cc1..2c95848fbce8 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -334,7 +334,7 @@ static struct page *kimage_alloc_pages(gfp_t gfp_mask, unsigned int order)
         if (pages) {
                 unsigned int count, i;
                 pages->mapping = NULL;
-                pages->private = order;
+                set_page_private(pages, order);
                 count = 1 << order;
                 for (i = 0; i < count; i++)
                         SetPageReserved(pages + i);
@@ -347,7 +347,7 @@ static void kimage_free_pages(struct page *page)
 {
         unsigned int order, count, i;
 
-        order = page->private;
+        order = page_private(page);
         count = 1 << order;
         for (i = 0; i < count; i++)
                 ClearPageReserved(page + i);
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 10bc5ec496d7..016504ccfccf 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -578,15 +578,23 @@ static int save_highmem_zone(struct zone *zone)
                         continue;
                 page = pfn_to_page(pfn);
                 /*
-                 * This condition results from rvmalloc() sans vmalloc_32()
-                 * and architectural memory reservations. This should be
-                 * corrected eventually when the cases giving rise to this
-                 * are better understood.
+                 * PageReserved results from rvmalloc() sans vmalloc_32()
+                 * and architectural memory reservations.
+                 *
+                 * rvmalloc should not cause this, because all implementations
+                 * appear to always be using vmalloc_32 on architectures with
+                 * highmem. This is a good thing, because we would like to save
+                 * rvmalloc pages.
+                 *
+                 * It appears to be triggered by pages which do not point to
+                 * valid memory (see arch/i386/mm/init.c:one_highpage_init(),
+                 * which sets PageReserved if the page does not point to valid
+                 * RAM.
+                 *
+                 * XXX: must remove usage of PageReserved!
                  */
-                if (PageReserved(page)) {
-                        printk("highmem reserved page?!\n");
+                if (PageReserved(page))
                         continue;
-                }
                 BUG_ON(PageNosave(page));
                 if (PageNosaveFree(page))
                         continue;
@@ -672,10 +680,9 @@ static int saveable(struct zone * zone, unsigned long * zone_pfn)
                 return 0;
 
         page = pfn_to_page(pfn);
-        BUG_ON(PageReserved(page) && PageNosave(page));
         if (PageNosave(page))
                 return 0;
-        if (PageReserved(page) && pfn_is_nosave(pfn)) {
+        if (pfn_is_nosave(pfn)) {
                 pr_debug("[nosave pfn 0x%lx]", pfn);
                 return 0;
         }
diff --git a/kernel/sched.c b/kernel/sched.c
index 1e5cafdf4e27..4f26c544d02c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2511,8 +2511,6 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
                 cpustat->idle = cputime64_add(cpustat->idle, tmp);
         /* Account for system time used */
         acct_update_integrals(p);
-        /* Update rss highwater mark */
-        update_mem_hiwater(p);
 }
 
 /*
diff --git a/kernel/timer.c b/kernel/timer.c
index 3ba10fa35b60..6a2e5f8dc725 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -752,6 +752,15 @@ static void second_overflow(void)
     else
         time_adj += (time_adj >> 2) + (time_adj >> 5);
 #endif
+#if HZ == 250
+    /* Compensate for (HZ==250) != (1 << SHIFT_HZ).
+     * Add 1.5625% and 0.78125% to get 255.85938; => only 0.05% error (p. 14)
+     */
+    if (time_adj < 0)
+        time_adj -= (-time_adj >> 6) + (-time_adj >> 7);
+    else
+        time_adj += (time_adj >> 6) + (time_adj >> 7);
+#endif
 #if HZ == 1000
     /* Compensate for (HZ==1000) != (1 << SHIFT_HZ).
      * Add 1.5625% and 0.78125% to get 1023.4375; => only 0.05% error (p. 14)