Merge branch 'for-linus' of git://brick.kernel.dk/data/git/linux-2.6-block

[pandora-kernel.git] / mm / msync.c

diff --git a/mm/msync.c b/mm/msync.c
index d0f5a1b..0e040e9 100644 (file)
--- a/mm/msync.c
+++ b/mm/msync.c
@@ -17,40 +17,48 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
-/*
- * Called with mm->page_table_lock held to protect against other
- * threads/the swapper from ripping pte's out from under us.
- */
-
-static void sync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
+static void msync_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
                                unsigned long addr, unsigned long end)
 {
        pte_t *pte;
+       spinlock_t *ptl;
+       int progress = 0;
 
-       pte = pte_offset_map(pmd, addr);
+again:
+       pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
        do {
                unsigned long pfn;
                struct page *page;
 
+               if (progress >= 64) {
+                       progress = 0;
+                       if (need_resched() || need_lockbreak(ptl))
+                               break;
+               }
+               progress++;
                if (!pte_present(*pte))
                        continue;
                if (!pte_maybe_dirty(*pte))
                        continue;
                pfn = pte_pfn(*pte);
-               if (!pfn_valid(pfn))
+               if (unlikely(!pfn_valid(pfn))) {
+                       print_bad_pte(vma, *pte, addr);
                        continue;
+               }
                page = pfn_to_page(pfn);
-               if (PageReserved(page))
-                       continue;
 
                if (ptep_clear_flush_dirty(vma, addr, pte) ||
                    page_test_and_clear_dirty(page))
                        set_page_dirty(page);
+               progress += 3;
        } while (pte++, addr += PAGE_SIZE, addr != end);
-       pte_unmap(pte - 1);
+       pte_unmap_unlock(pte - 1, ptl);
+       cond_resched();
+       if (addr != end)
+               goto again;
 }
 
-static inline void sync_pmd_range(struct vm_area_struct *vma, pud_t *pud,
+static inline void msync_pmd_range(struct vm_area_struct *vma, pud_t *pud,
                                unsigned long addr, unsigned long end)
 {
        pmd_t *pmd;
@@ -61,11 +69,11 @@ static inline void sync_pmd_range(struct vm_area_struct *vma, pud_t *pud,
                next = pmd_addr_end(addr, end);
                if (pmd_none_or_clear_bad(pmd))
                        continue;
-               sync_pte_range(vma, pmd, addr, next);
+               msync_pte_range(vma, pmd, addr, next);
        } while (pmd++, addr = next, addr != end);
 }
 
-static inline void sync_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
+static inline void msync_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
                                unsigned long addr, unsigned long end)
 {
        pud_t *pud;
@@ -76,58 +84,34 @@ static inline void sync_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
                next = pud_addr_end(addr, end);
                if (pud_none_or_clear_bad(pud))
                        continue;
-               sync_pmd_range(vma, pud, addr, next);
+               msync_pmd_range(vma, pud, addr, next);
        } while (pud++, addr = next, addr != end);
 }
 
-static void sync_page_range(struct vm_area_struct *vma,
+static void msync_page_range(struct vm_area_struct *vma,
                                unsigned long addr, unsigned long end)
 {
-       struct mm_struct *mm = vma->vm_mm;
        pgd_t *pgd;
        unsigned long next;
 
        /* For hugepages we can't go walking the page table normally,
         * but that's ok, hugetlbfs is memory based, so we don't need
-        * to do anything more on an msync() */
-       if (is_vm_hugetlb_page(vma))
+        * to do anything more on an msync().
+        * Can't do anything with VM_RESERVED regions either.
+        */
+       if (vma->vm_flags & (VM_HUGETLB|VM_RESERVED))
                return;
 
        BUG_ON(addr >= end);
-       pgd = pgd_offset(mm, addr);
+       pgd = pgd_offset(vma->vm_mm, addr);
        flush_cache_range(vma, addr, end);
-       spin_lock(&mm->page_table_lock);
        do {
                next = pgd_addr_end(addr, end);
                if (pgd_none_or_clear_bad(pgd))
                        continue;
-               sync_pud_range(vma, pgd, addr, next);
+               msync_pud_range(vma, pgd, addr, next);
        } while (pgd++, addr = next, addr != end);
-       spin_unlock(&mm->page_table_lock);
-}
-
-#ifdef CONFIG_PREEMPT
-static inline void filemap_sync(struct vm_area_struct *vma,
-                               unsigned long addr, unsigned long end)
-{
-       const size_t chunk = 64 * 1024; /* bytes */
-       unsigned long next;
-
-       do {
-               next = addr + chunk;
-               if (next > end || next < addr)
-                       next = end;
-               sync_page_range(vma, addr, next);
-               cond_resched();
-       } while (addr = next, addr != end);
-}
-#else
-static inline void filemap_sync(struct vm_area_struct *vma,
-                               unsigned long addr, unsigned long end)
-{
-       sync_page_range(vma, addr, end);
 }
-#endif
 
 /*
  * MS_SYNC syncs the entire file - including mappings.
@@ -150,7 +134,7 @@ static int msync_interval(struct vm_area_struct *vma,
                return -EBUSY;
 
        if (file && (vma->vm_flags & VM_SHARED)) {
-               filemap_sync(vma, addr, end);
+               msync_page_range(vma, addr, end);
 
                if (flags & MS_SYNC) {
                        struct address_space *mapping = file->f_mapping;