goto out_enomem_free_avc;
allocated = anon_vma;
}
- spin_lock(&anon_vma->lock);
+ spin_lock(&anon_vma->lock);
/* page_table_lock to protect against threads */
spin_lock(&mm->page_table_lock);
if (likely(!vma->anon_vma)) {
list_add(&avc->same_vma, &vma->anon_vma_chain);
list_add(&avc->same_anon_vma, &anon_vma->head);
allocated = NULL;
+ avc = NULL;
}
spin_unlock(&mm->page_table_lock);
-
spin_unlock(&anon_vma->lock);
- if (unlikely(allocated)) {
+
+ if (unlikely(allocated))
anon_vma_free(allocated);
+ if (unlikely(avc))
anon_vma_chain_free(avc);
- }
}
return 0;
{
struct anon_vma_chain *avc, *pavc;
- list_for_each_entry(pavc, &src->anon_vma_chain, same_vma) {
+ list_for_each_entry_reverse(pavc, &src->anon_vma_chain, same_vma) {
avc = anon_vma_chain_alloc();
if (!avc)
goto enomem_failure;
out_error_free_anon_vma:
anon_vma_free(anon_vma);
out_error:
+ unlink_anon_vmas(vma);
return -ENOMEM;
}
list_del(&anon_vma_chain->same_anon_vma);
/* We must garbage collect the anon_vma if it's empty */
- empty = list_empty(&anon_vma->head) && !ksm_refcount(anon_vma);
+ empty = list_empty(&anon_vma->head) && !anonvma_external_refcount(anon_vma);
spin_unlock(&anon_vma->lock);
if (empty)
struct anon_vma *anon_vma = data;
spin_lock_init(&anon_vma->lock);
- ksm_refcount_init(anon_vma);
+ anonvma_external_refcount_init(anon_vma);
INIT_LIST_HEAD(&anon_vma->head);
}
/* page should be within @vma mapping range */
return -EFAULT;
}
- if (unlikely(vma->vm_flags & VM_LOCK_RMAP)) {
- /*
- * This VMA is being unlinked or is not yet linked into the
- * VMA tree. Do not try to follow this rmap. This race
- * condition can result in page_referenced() ignoring a
- * reference or in try_to_unmap() failing to unmap a page.
- * The VMA cannot be freed under us because we hold the
- * anon_vma->lock, which the munmap code takes while
- * unlinking the anon_vmas from the VMA.
- */
- return -EFAULT;
- }
return address;
}
/*
* At what user virtual address is page expected in vma?
- * checking that the page matches the vma.
+ * Caller should check the page is actually part of the vma.
*/
unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
{
- if (PageAnon(page)) {
- if (vma->anon_vma != page_anon_vma(page))
- return -EFAULT;
- } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
+ if (PageAnon(page))
+ ;
+ else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) {
if (!vma->vm_file ||
vma->vm_file->f_mapping != page->mapping)
return -EFAULT;
int referenced = 0;
int we_locked = 0;
- if (TestClearPageReferenced(page))
- referenced++;
-
*vm_flags = 0;
if (page_mapped(page) && page_rmapping(page)) {
if (!is_locked && (!PageAnon(page) || PageKsm(page))) {
EXPORT_SYMBOL_GPL(page_mkclean);
/**
+ * page_move_anon_rmap - move a page to our anon_vma
+ * @page: the page to move to our anon_vma
+ * @vma: the vma the page belongs to
+ * @address: the user virtual address mapped
+ *
+ * When a page belongs exclusively to one process after a COW event,
+ * that page can be moved into the anon_vma that belongs to just that
+ * process, so the rmap code will not search the parent or sibling
+ * processes.
+ */
+void page_move_anon_rmap(struct page *page,
+ struct vm_area_struct *vma, unsigned long address)
+{
+ struct anon_vma *anon_vma = vma->anon_vma;
+
+ VM_BUG_ON(!PageLocked(page));
+ VM_BUG_ON(!anon_vma);
+ VM_BUG_ON(page->index != linear_page_index(vma, address));
+
+ anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+ page->mapping = (struct address_space *) anon_vma;
+}
+
+/**
* __page_set_anon_rmap - setup new anonymous rmap
* @page: the page to add the mapping to
* @vma: the vm area in which the mapping is added
* @address: the user virtual address mapped
+ * @exclusive: the page is exclusively owned by the current process
*/
static void __page_set_anon_rmap(struct page *page,
- struct vm_area_struct *vma, unsigned long address)
+ struct vm_area_struct *vma, unsigned long address, int exclusive)
{
struct anon_vma *anon_vma = vma->anon_vma;
BUG_ON(!anon_vma);
+
+ /*
+ * If the page isn't exclusively mapped into this vma,
+ * we must use the _oldest_ possible anon_vma for the
+ * page mapping!
+ *
+ * So take the last AVC chain entry in the vma, which is
+ * the deepest ancestor, and use the anon_vma from that.
+ */
+ if (!exclusive) {
+ struct anon_vma_chain *avc;
+ avc = list_entry(vma->anon_vma_chain.prev, struct anon_vma_chain, same_vma);
+ anon_vma = avc->anon_vma;
+ }
+
anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
page->mapping = (struct address_space *) anon_vma;
page->index = linear_page_index(vma, address);
* are initially only visible via the pagetables, and the pte is locked
* over the call to page_add_new_anon_rmap.
*/
- struct anon_vma *anon_vma = vma->anon_vma;
- anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
- BUG_ON(page->mapping != (struct address_space *)anon_vma);
BUG_ON(page->index != linear_page_index(vma, address));
#endif
}
VM_BUG_ON(!PageLocked(page));
VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
if (first)
- __page_set_anon_rmap(page, vma, address);
+ __page_set_anon_rmap(page, vma, address, 0);
else
__page_check_anon_rmap(page, vma, address);
}
SetPageSwapBacked(page);
atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
__inc_zone_page_state(page, NR_ANON_PAGES);
- __page_set_anon_rmap(page, vma, address);
+ __page_set_anon_rmap(page, vma, address, 1);
if (page_evictable(page, vma))
lru_cache_add_lru(page, LRU_ACTIVE_ANON);
else
return ret;
}
+static bool is_vma_temporary_stack(struct vm_area_struct *vma)
+{
+ int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
+
+ if (!maybe_stack)
+ return false;
+
+ if ((vma->vm_flags & VM_STACK_INCOMPLETE_SETUP) ==
+ VM_STACK_INCOMPLETE_SETUP)
+ return true;
+
+ return false;
+}
+
/**
* try_to_unmap_anon - unmap or unlock anonymous page using the object-based
* rmap method
list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
struct vm_area_struct *vma = avc->vma;
- unsigned long address = vma_address(page, vma);
+ unsigned long address;
+
+ /*
+ * During exec, a temporary VMA is setup and later moved.
+ * The VMA is moved under the anon_vma lock but not the
+ * page tables leading to a race where migration cannot
+ * find the migration ptes. Rather than increasing the
+ * locking requirements of exec(), migration skips
+ * temporary VMAs until after exec() completes.
+ */
+ if (PAGE_MIGRATION && (flags & TTU_MIGRATION) &&
+ is_vma_temporary_stack(vma))
+ continue;
+
+ address = vma_address(page, vma);
if (address == -EFAULT)
continue;
ret = try_to_unmap_one(page, vma, address, flags);
/*
* Note: remove_migration_ptes() cannot use page_lock_anon_vma()
* because that depends on page_mapped(); but not all its usages
- * are holding mmap_sem, which also gave the necessary guarantee
- * (that this anon_vma's slab has not already been destroyed).
- * This needs to be reviewed later: avoiding page_lock_anon_vma()
- * is risky, and currently limits the usefulness of rmap_walk().
+ * are holding mmap_sem. Users without mmap_sem are required to
+ * take a reference count to prevent the anon_vma disappearing
*/
anon_vma = page_anon_vma(page);
if (!anon_vma)