* readonly mappings. The tradeoff is that copy_page_range is more
* efficient than faulting.
*/
- if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) {
+ if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR |
+ VM_PFNMAP | VM_MIXEDMAP))) {
if (!vma->anon_vma)
return 0;
}
if (is_vm_hugetlb_page(vma))
return copy_hugetlb_page_range(dst_mm, src_mm, vma);
- if (unlikely(is_pfn_mapping(vma))) {
+ if (unlikely(vma->vm_flags & VM_PFNMAP)) {
/*
* We do not free on error cases below as remove_vma
* gets called on error from higher level routine
*/
- ret = track_pfn_vma_copy(vma);
+ ret = track_pfn_copy(vma);
if (ret)
return ret;
}
if (vma->vm_file)
uprobe_munmap(vma, start, end);
- if (unlikely(is_pfn_mapping(vma)))
- untrack_pfn_vma(vma, 0, 0);
+ if (unlikely(vma->vm_flags & VM_PFNMAP))
+ untrack_pfn(vma, 0, 0);
if (start != end) {
if (unlikely(is_vm_hugetlb_page(vma))) {
* Since no pte has actually been setup, it is
* safe to do nothing in this case.
*/
- if (vma->vm_file)
- unmap_hugepage_range(vma, start, end, NULL);
+ if (vma->vm_file) {
+ mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
+ __unmap_hugepage_range_final(tlb, vma, start, end, NULL);
+ mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
+ }
} else
unmap_page_range(tlb, vma, start, end, details);
}
if (page->mapping && trylock_page(page)) {
lru_add_drain(); /* push cached pages to LRU */
/*
- * Because we lock page here and migration is
- * blocked by the pte's page reference, we need
- * only check for file-cache page truncation.
+ * Because we lock page here, and migration is
+ * blocked by the pte's page reference, and we
+ * know the page is still mapped, we don't even
+ * need to check for file-cache page truncation.
*/
- if (page->mapping)
- mlock_vma_page(page);
+ mlock_vma_page(page);
unlock_page(page);
}
}
* ask for a shared writable mapping!
*
* The page does not need to be reserved.
+ *
+ * Usually this function is called from f_op->mmap() handler
+ * under mm->mmap_sem write-lock, so it can change vma->vm_flags.
+ * Caller must set VM_MIXEDMAP on vma if it wants to call this
+ * function from other places, for example from page-fault handler.
*/
int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
struct page *page)
return -EFAULT;
if (!page_count(page))
return -EINVAL;
- vma->vm_flags |= VM_INSERTPAGE;
+ if (!(vma->vm_flags & VM_MIXEDMAP)) {
+ BUG_ON(down_read_trylock(&vma->vm_mm->mmap_sem));
+ BUG_ON(vma->vm_flags & VM_PFNMAP);
+ vma->vm_flags |= VM_MIXEDMAP;
+ }
return insert_page(vma, addr, page, vma->vm_page_prot);
}
EXPORT_SYMBOL(vm_insert_page);
if (addr < vma->vm_start || addr >= vma->vm_end)
return -EFAULT;
- if (track_pfn_vma_new(vma, &pgprot, pfn, PAGE_SIZE))
+ if (track_pfn_insert(vma, &pgprot, pfn))
return -EINVAL;
ret = insert_pfn(vma, addr, pfn, pgprot);
- if (ret)
- untrack_pfn_vma(vma, pfn, PAGE_SIZE);
-
return ret;
}
EXPORT_SYMBOL(vm_insert_pfn);
* rest of the world about it:
* VM_IO tells people not to look at these pages
* (accesses can have side effects).
- * VM_RESERVED is specified all over the place, because
- * in 2.4 it kept swapout's vma scan off this vma; but
- * in 2.6 the LRU scan won't even find its pages, so this
- * flag means no more than count its pages in reserved_vm,
- * and omit it from core dump, even when VM_IO turned off.
* VM_PFNMAP tells the core MM that the base pages are just
* raw PFN mappings, and do not have a "struct page" associated
* with them.
+ * VM_DONTEXPAND
+ * Disable vma merging and expanding with mremap().
+ * VM_DONTDUMP
+ * Omit vma from core dump, even when VM_IO turned off.
*
* There's a horrible special case to handle copy-on-write
* behaviour that some programs depend on. We mark the "original"
* un-COW'ed pages by matching them up with "vma->vm_pgoff".
+ * See vm_normal_page() for details.
*/
- if (addr == vma->vm_start && end == vma->vm_end) {
+ if (is_cow_mapping(vma->vm_flags)) {
+ if (addr != vma->vm_start || end != vma->vm_end)
+ return -EINVAL;
vma->vm_pgoff = pfn;
- 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) {
- /*
- * 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;
+ err = track_pfn_remap(vma, &prot, pfn, addr, PAGE_ALIGN(size));
+ if (err)
return -EINVAL;
- }
+
+ vma->vm_flags |= VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
BUG_ON(addr >= end);
pfn -= addr >> PAGE_SHIFT;
} while (pgd++, addr = next, addr != end);
if (err)
- untrack_pfn_vma(vma, pfn, PAGE_ALIGN(size));
+ untrack_pfn(vma, pfn, PAGE_ALIGN(size));
return err;
}
if (!page_mkwrite) {
wait_on_page_locked(dirty_page);
set_page_dirty_balance(dirty_page, page_mkwrite);
+ /* file_update_time outside page_lock */
+ if (vma->vm_file)
+ file_update_time(vma->vm_file);
}
put_page(dirty_page);
if (page_mkwrite) {
}
}
- /* file_update_time outside page_lock */
- if (vma->vm_file)
- file_update_time(vma->vm_file);
-
return ret;
}
zap_page_range_single(vma, start_addr, end_addr - start_addr, details);
}
-static inline void unmap_mapping_range_tree(struct prio_tree_root *root,
+static inline void unmap_mapping_range_tree(struct rb_root *root,
struct zap_details *details)
{
struct vm_area_struct *vma;
- struct prio_tree_iter iter;
pgoff_t vba, vea, zba, zea;
- vma_prio_tree_foreach(vma, &iter, root,
+ vma_interval_tree_foreach(vma, root,
details->first_index, details->last_index) {
vba = vma->vm_pgoff;
* across *all* the pages in each nonlinear VMA, not just the pages
* whose virtual address lies outside the file truncation point.
*/
- list_for_each_entry(vma, head, shared.vm_set.list) {
+ list_for_each_entry(vma, head, shared.nonlinear) {
details->nonlinear_vma = vma;
unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details);
}
mutex_lock(&mapping->i_mmap_mutex);
- if (unlikely(!prio_tree_empty(&mapping->i_mmap)))
+ if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap)))
unmap_mapping_range_tree(&mapping->i_mmap, &details);
if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
if (dirty_page) {
struct address_space *mapping = page->mapping;
+ int dirtied = 0;
if (set_page_dirty(dirty_page))
- page_mkwrite = 1;
+ dirtied = 1;
unlock_page(dirty_page);
put_page(dirty_page);
- if (page_mkwrite && mapping) {
+ if ((dirtied || page_mkwrite) && mapping) {
/*
* Some device drivers do not set page.mapping but still
* dirty their pages
}
/* file_update_time outside page_lock */
- if (vma->vm_file)
+ if (vma->vm_file && !page_mkwrite)
file_update_time(vma->vm_file);
} else {
unlock_page(vmf.page);
free_page((unsigned long)buf);
}
}
- up_read(¤t->mm->mmap_sem);
+ up_read(&mm->mmap_sem);
}
#ifdef CONFIG_PROVE_LOCKING