percpu: __percpu_depopulate_mask can take a const mask

[safe/jmp/linux-2.6] / mm / memory.c

diff --git a/mm/memory.c b/mm/memory.c
index e009ce8..cf6873e 100644 (file)
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1151,6 +1151,11 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
                if ((flags & FOLL_WRITE) &&
                    !pte_dirty(pte) && !PageDirty(page))
                        set_page_dirty(page);
+               /*
+                * pte_mkyoung() would be more correct here, but atomic care
+                * is needed to avoid losing the dirty bit: it is easier to use
+                * mark_page_accessed().
+                */
                mark_page_accessed(page);
        }
 unlock:
@@ -1511,6 +1516,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
                        unsigned long pfn)
 {
        int ret;
+       pgprot_t pgprot = vma->vm_page_prot;
        /*
         * Technically, architectures with pte_special can avoid all these
         * restrictions (same for remap_pfn_range).  However we would like
@@ -1525,10 +1531,10 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 
        if (addr < vma->vm_start || addr >= vma->vm_end)
                return -EFAULT;
-       if (track_pfn_vma_new(vma, vma->vm_page_prot, pfn, PAGE_SIZE))
+       if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
                return -EINVAL;
 
-       ret = insert_pfn(vma, addr, pfn, vma->vm_page_prot);
+       ret = insert_pfn(vma, addr, pfn, pgprot);
 
        if (ret)
                untrack_pfn_vma(vma, pfn, PAGE_SIZE);
@@ -1664,16 +1670,24 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
         * behaviour that some programs depend on. We mark the "original"
         * un-COW'ed pages by matching them up with "vma->vm_pgoff".
         */
-       if (addr == vma->vm_start && end == vma->vm_end)
+       if (addr == vma->vm_start && end == vma->vm_end) {
                vma->vm_pgoff = pfn;
-       else if (is_cow_mapping(vma->vm_flags))
+               vma->vm_flags |= VM_PFN_AT_MMAP;
+       } else if (is_cow_mapping(vma->vm_flags))
                return -EINVAL;
 
        vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
 
-       err = track_pfn_vma_new(vma, prot, pfn, PAGE_ALIGN(size));
-       if (err)
+       err = track_pfn_vma_new(vma, &prot, pfn, PAGE_ALIGN(size));
+       if (err) {
+               /*
+                * To indicate that track_pfn related cleanup is not
+                * needed from higher level routine calling unmap_vmas
+                */
+               vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
+               vma->vm_flags &= ~VM_PFN_AT_MMAP;
                return -EINVAL;
+       }
 
        BUG_ON(addr >= end);
        pfn -= addr >> PAGE_SHIFT;
@@ -1931,6 +1945,15 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                 * get_user_pages(.write=1, .force=1).
                 */
                if (vma->vm_ops && vma->vm_ops->page_mkwrite) {
+                       struct vm_fault vmf;
+                       int tmp;
+
+                       vmf.virtual_address = (void __user *)(address &
+                                                               PAGE_MASK);
+                       vmf.pgoff = old_page->index;
+                       vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+                       vmf.page = old_page;
+
                        /*
                         * Notify the address space that the page is about to
                         * become writable so that it can prohibit this or wait
@@ -1942,8 +1965,12 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
                        page_cache_get(old_page);
                        pte_unmap_unlock(page_table, ptl);
 
-                       if (vma->vm_ops->page_mkwrite(vma, old_page) < 0)
+                       tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
+                       if (unlikely(tmp &
+                                       (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
+                               ret = tmp;
                                goto unwritable_page;
+                       }
 
                        /*
                         * Since we dropped the lock we need to revalidate
@@ -1992,7 +2019,7 @@ gotten:
         * Don't let another task, with possibly unlocked vma,
         * keep the mlocked page.
         */
-       if (vma->vm_flags & VM_LOCKED) {
+       if ((vma->vm_flags & VM_LOCKED) && old_page) {
                lock_page(old_page);    /* for LRU manipulation */
                clear_page_mlock(old_page);
                unlock_page(old_page);
@@ -2092,7 +2119,7 @@ oom:
 
 unwritable_page:
        page_cache_release(old_page);
-       return VM_FAULT_SIGBUS;
+       return ret;
 }
 
 /*
@@ -2426,8 +2453,6 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
                count_vm_event(PGMAJFAULT);
        }
 
-       mark_page_accessed(page);
-
        lock_page(page);
        delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
 
@@ -2636,9 +2661,14 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
                         * to become writable
                         */
                        if (vma->vm_ops->page_mkwrite) {
+                               int tmp;
+
                                unlock_page(page);
-                               if (vma->vm_ops->page_mkwrite(vma, page) < 0) {
-                                       ret = VM_FAULT_SIGBUS;
+                               vmf.flags |= FAULT_FLAG_MKWRITE;
+                               tmp = vma->vm_ops->page_mkwrite(vma, &vmf);
+                               if (unlikely(tmp &
+                                         (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) {
+                                       ret = tmp;
                                        anon = 1; /* no anon but release vmf.page */
                                        goto out_unlocked;
                                }
@@ -3165,6 +3195,15 @@ void print_vma_addr(char *prefix, unsigned long ip)
 #ifdef CONFIG_PROVE_LOCKING
 void might_fault(void)
 {
+       /*
+        * Some code (nfs/sunrpc) uses socket ops on kernel memory while
+        * holding the mmap_sem, this is safe because kernel memory doesn't
+        * get paged out, therefore we'll never actually fault, and the
+        * below annotations will generate false positives.
+        */
+       if (segment_eq(get_fs(), KERNEL_DS))
+               return;
+
        might_sleep();
        /*
         * it would be nicer only to annotate paths which are not under