[PATCH] serial moxa: fix wrong BUG

[linux-2.6] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index 8461e2dd91d75fecafeffccd461b106d11af5a66..0f60baf6f69b36c0b0a5ddd65021be62c7150690 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -114,6 +114,7 @@ static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
 {
        struct page *page = pmd_page(*pmd);
        pmd_clear(pmd);
+       pte_lock_deinit(page);
        pte_free_tlb(tlb, page);
        dec_page_state(nr_page_table_pages);
        tlb->mm->nr_ptes--;
@@ -294,10 +295,12 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
        if (!new)
                return -ENOMEM;
 
+       pte_lock_init(new);
        spin_lock(&mm->page_table_lock);
-       if (pmd_present(*pmd))          /* Another has populated it */
+       if (pmd_present(*pmd)) {        /* Another has populated it */
+               pte_lock_deinit(new);
                pte_free(new);
-       else {
+       } else {
                mm->nr_ptes++;
                inc_page_state(nr_page_table_pages);
                pmd_populate(mm, pmd, new);
@@ -369,7 +372,9 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
                        /* make sure dst_mm is on swapoff's mmlist. */
                        if (unlikely(list_empty(&dst_mm->mmlist))) {
                                spin_lock(&mmlist_lock);
-                               list_add(&dst_mm->mmlist, &src_mm->mmlist);
+                               if (list_empty(&dst_mm->mmlist))
+                                       list_add(&dst_mm->mmlist,
+                                                &src_mm->mmlist);
                                spin_unlock(&mmlist_lock);
                        }
                }
@@ -432,7 +437,7 @@ again:
        if (!dst_pte)
                return -ENOMEM;
        src_pte = pte_offset_map_nested(src_pmd, addr);
-       src_ptl = &src_mm->page_table_lock;
+       src_ptl = pte_lockptr(src_mm, src_pmd);
        spin_lock(src_ptl);
 
        do {
@@ -1194,15 +1199,16 @@ EXPORT_SYMBOL(remap_pfn_range);
  * (but do_wp_page is only called after already making such a check;
  * and do_anonymous_page and do_no_page can safely check later on).
  */
-static inline int pte_unmap_same(struct mm_struct *mm,
+static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
                                pte_t *page_table, pte_t orig_pte)
 {
        int same = 1;
 #if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
        if (sizeof(pte_t) > sizeof(unsigned long)) {
-               spin_lock(&mm->page_table_lock);
+               spinlock_t *ptl = pte_lockptr(mm, pmd);
+               spin_lock(ptl);
                same = pte_same(*page_table, orig_pte);
-               spin_unlock(&mm->page_table_lock);
+               spin_unlock(ptl);
        }
 #endif
        pte_unmap(page_table);
@@ -1655,7 +1661,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
        pte_t pte;
        int ret = VM_FAULT_MINOR;
 
-       if (!pte_unmap_same(mm, page_table, orig_pte))
+       if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
                goto out;
 
        entry = pte_to_swp_entry(orig_pte);
@@ -1773,7 +1779,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
                page_cache_get(page);
                entry = mk_pte(page, vma->vm_page_prot);
 
-               ptl = &mm->page_table_lock;
+               ptl = pte_lockptr(mm, pmd);
                spin_lock(ptl);
                if (!pte_none(*page_table))
                        goto release;
@@ -1934,7 +1940,7 @@ static int do_file_page(struct mm_struct *mm, struct vm_area_struct *vma,
        pgoff_t pgoff;
        int err;
 
-       if (!pte_unmap_same(mm, page_table, orig_pte))
+       if (!pte_unmap_same(mm, pmd, page_table, orig_pte))
                return VM_FAULT_MINOR;
 
        if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) {
@@ -1974,9 +1980,10 @@ static inline int handle_pte_fault(struct mm_struct *mm,
                pte_t *pte, pmd_t *pmd, int write_access)
 {
        pte_t entry;
+       pte_t old_entry;
        spinlock_t *ptl;
 
-       entry = *pte;
+       old_entry = entry = *pte;
        if (!pte_present(entry)) {
                if (pte_none(entry)) {
                        if (!vma->vm_ops || !vma->vm_ops->nopage)
@@ -1992,7 +1999,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
                                        pte, pmd, write_access, entry);
        }
 
-       ptl = &mm->page_table_lock;
+       ptl = pte_lockptr(mm, pmd);
        spin_lock(ptl);
        if (unlikely(!pte_same(*pte, entry)))
                goto unlock;
@@ -2003,9 +2010,20 @@ static inline int handle_pte_fault(struct mm_struct *mm,
                entry = pte_mkdirty(entry);
        }
        entry = pte_mkyoung(entry);
-       ptep_set_access_flags(vma, address, pte, entry, write_access);
-       update_mmu_cache(vma, address, entry);
-       lazy_mmu_prot_update(entry);
+       if (!pte_same(old_entry, entry)) {
+               ptep_set_access_flags(vma, address, pte, entry, write_access);
+               update_mmu_cache(vma, address, entry);
+               lazy_mmu_prot_update(entry);
+       } else {
+               /*
+                * This is needed only for protection faults but the arch code
+                * is not yet telling us if this is a protection fault or not.
+                * This still avoids useless tlb flushes for .text page faults
+                * with threads.
+                */
+               if (write_access)
+                       flush_tlb_page(vma, address);
+       }
 unlock:
        pte_unmap_unlock(pte, ptl);
        return VM_FAULT_MINOR;