[PATCH] fix get_user_pages bug

[deliverable/linux.git] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index 2405289dfdf88d03fa0113712a37c4bf5444c640..81d7117aa58b65ec7f93cef8e212a337735ba440 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -811,15 +811,18 @@ static struct page *__follow_page(struct mm_struct *mm, unsigned long address,
        pte = *ptep;
        pte_unmap(ptep);
        if (pte_present(pte)) {
-               if (write && !pte_dirty(pte))
+               if (write && !pte_write(pte))
                        goto out;
                if (read && !pte_read(pte))
                        goto out;
                pfn = pte_pfn(pte);
                if (pfn_valid(pfn)) {
                        page = pfn_to_page(pfn);
-                       if (accessed)
+                       if (accessed) {
+                               if (write && !pte_dirty(pte) &&!PageDirty(page))
+                                       set_page_dirty(page);
                                mark_page_accessed(page);
+                       }
                        return page;
                }
        }
@@ -941,10 +944,11 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                }
                spin_lock(&mm->page_table_lock);
                do {
+                       int write_access = write;
                        struct page *page;
 
                        cond_resched_lock(&mm->page_table_lock);
-                       while (!(page = follow_page(mm, start, write))) {
+                       while (!(page = follow_page(mm, start, write_access))) {
                                /*
                                 * Shortcut for anonymous pages. We don't want
                                 * to force the creation of pages tables for
@@ -957,7 +961,16 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
                                        break;
                                }
                                spin_unlock(&mm->page_table_lock);
-                               switch (handle_mm_fault(mm,vma,start,write)) {
+                               switch (__handle_mm_fault(mm, vma, start,
+                                                       write_access)) {
+                               case VM_FAULT_WRITE:
+                                       /*
+                                        * do_wp_page has broken COW when
+                                        * necessary, even if maybe_mkwrite
+                                        * decided not to set pte_write
+                                        */
+                                       write_access = 0;
+                                       /* FALLTHRU */
                                case VM_FAULT_MINOR:
                                        tsk->min_flt++;
                                        break;
@@ -1220,6 +1233,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
        struct page *old_page, *new_page;
        unsigned long pfn = pte_pfn(pte);
        pte_t entry;
+       int ret;
 
        if (unlikely(!pfn_valid(pfn))) {
                /*
@@ -1247,7 +1261,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
                        lazy_mmu_prot_update(entry);
                        pte_unmap(page_table);
                        spin_unlock(&mm->page_table_lock);
-                       return VM_FAULT_MINOR;
+                       return VM_FAULT_MINOR|VM_FAULT_WRITE;
                }
        }
        pte_unmap(page_table);
@@ -1274,6 +1288,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
        /*
         * Re-check the pte - we dropped the lock
         */
+       ret = VM_FAULT_MINOR;
        spin_lock(&mm->page_table_lock);
        page_table = pte_offset_map(pmd, address);
        if (likely(pte_same(*page_table, pte))) {
@@ -1290,12 +1305,13 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct * vma,
 
                /* Free the old page.. */
                new_page = old_page;
+               ret |= VM_FAULT_WRITE;
        }
        pte_unmap(page_table);
        page_cache_release(new_page);
        page_cache_release(old_page);
        spin_unlock(&mm->page_table_lock);
-       return VM_FAULT_MINOR;
+       return ret;
 
 no_new_page:
        page_cache_release(old_page);
@@ -1987,7 +2003,6 @@ static inline int handle_pte_fault(struct mm_struct *mm,
        if (write_access) {
                if (!pte_write(entry))
                        return do_wp_page(mm, vma, address, pte, pmd, entry);
-
                entry = pte_mkdirty(entry);
        }
        entry = pte_mkyoung(entry);
@@ -2002,7 +2017,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 /*
  * By the time we get here, we already hold the mm semaphore
  */
-int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
+int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct * vma,
                unsigned long address, int write_access)
 {
        pgd_t *pgd;