X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=mm%2Fmemory.c;h=9aefaae4685812e12505551ade19ed6183220422;hb=9e6c29768fc05d32ba1342b9348957b24bc476c2;hp=48c122d42ed743dcc90178170b4aff380ec3ad8c;hpb=1da7807842f7ccd9a3962dc276e489b76cd320c7;p=linux-2.6

diff --git a/mm/memory.c b/mm/memory.c
index 48c122d42e..9aefaae468 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -311,6 +311,21 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
 	if (!new)
 		return -ENOMEM;
 
+	/*
+	 * Ensure all pte setup (eg. pte page lock and page clearing) are
+	 * visible before the pte is made visible to other CPUs by being
+	 * put into page tables.
+	 *
+	 * The other side of the story is the pointer chasing in the page
+	 * table walking code (when walking the page table without locking;
+	 * ie. most of the time). Fortunately, these data accesses consist
+	 * of a chain of data-dependent loads, meaning most CPUs (alpha
+	 * being the notable exception) will already guarantee loads are
+	 * seen in-order. See the alpha page table accessors for the
+	 * smp_read_barrier_depends() barriers in page table walking code.
+	 */
+	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
+
 	spin_lock(&mm->page_table_lock);
 	if (!pmd_present(*pmd)) {	/* Has another populated it ? */
 		mm->nr_ptes++;
@@ -329,6 +344,8 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
 	if (!new)
 		return -ENOMEM;
 
+	smp_wmb(); /* See comment in __pte_alloc */
+
 	spin_lock(&init_mm.page_table_lock);
 	if (!pmd_present(*pmd)) {	/* Has another populated it ? */
 		pmd_populate_kernel(&init_mm, pmd, new);
@@ -982,17 +999,15 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		goto no_page_table;
 
 	ptep = pte_offset_map_lock(mm, pmd, address, &ptl);
-	if (!ptep)
-		goto out;
 
 	pte = *ptep;
 	if (!pte_present(pte))
-		goto unlock;
+		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
 	page = vm_normal_page(vma, address, pte);
 	if (unlikely(!page))
-		goto unlock;
+		goto bad_page;
 
 	if (flags & FOLL_GET)
 		get_page(page);
@@ -1007,6 +1022,15 @@ unlock:
 out:
 	return page;
 
+bad_page:
+	pte_unmap_unlock(ptep, ptl);
+	return ERR_PTR(-EFAULT);
+
+no_page:
+	pte_unmap_unlock(ptep, ptl);
+	if (!pte_none(pte))
+		return page;
+	/* Fall through to ZERO_PAGE handling */
 no_page_table:
 	/*
 	 * When core dumping an enormous anonymous area that nobody
@@ -1142,6 +1166,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 				cond_resched();
 			}
+			if (IS_ERR(page))
+				return i ? i : PTR_ERR(page);
 			if (pages) {
 				pages[i] = page;
 
@@ -2278,8 +2304,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	vmf.flags = flags;
 	vmf.page = NULL;
 
-	BUG_ON(vma->vm_flags & VM_PFNMAP);
-
 	ret = vma->vm_ops->fault(vma, &vmf);
 	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
 		return ret;
@@ -2619,6 +2643,8 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 	if (!new)
 		return -ENOMEM;
 
+	smp_wmb(); /* See comment in __pte_alloc */
+
 	spin_lock(&mm->page_table_lock);
 	if (pgd_present(*pgd))		/* Another has populated it */
 		pud_free(mm, new);
@@ -2640,6 +2666,8 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
 	if (!new)
 		return -ENOMEM;
 
+	smp_wmb(); /* See comment in __pte_alloc */
+
 	spin_lock(&mm->page_table_lock);
 #ifndef __ARCH_HAS_4LEVEL_HACK
 	if (pud_present(*pud))		/* Another has populated it */