---

yaml
---
r: 96536
b: refs/heads/master
c: 362a61a
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 73f10281ea96d7e8b4fc1c5d755a7c8eb484155b
+refs/heads/master: 362a61ad61199e19a61b8e432015e2586b288f5b

trunk/include/asm-alpha/pgtable.h

@@ -287,17 +287,34 @@ extern inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
 #define pgd_index(address)	(((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
 #define pgd_offset(mm, address)	((mm)->pgd+pgd_index(address))
 
+/*
+ * The smp_read_barrier_depends() in the following functions are required to
+ * order the load of *dir (the pointer in the top level page table) with any
+ * subsequent load of the returned pmd_t *ret (ret is data dependent on *dir).
+ *
+ * If this ordering is not enforced, the CPU might load an older value of
+ * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for
+ * more details.
+ *
+ * Note that we never change the mm->pgd pointer after the task is running, so
+ * pgd_offset does not require such a barrier.
+ */
+
 /* Find an entry in the second-level page table.. */
 extern inline pmd_t * pmd_offset(pgd_t * dir, unsigned long address)
 {
-	return (pmd_t *) pgd_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
+	pmd_t *ret = (pmd_t *) pgd_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1));
+	smp_read_barrier_depends(); /* see above */
+	return ret;
 }
 
 /* Find an entry in the third-level page table.. */
 extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address)
 {
-	return (pte_t *) pmd_page_vaddr(*dir)
+	pte_t *ret = (pte_t *) pmd_page_vaddr(*dir)
 		+ ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1));
+	smp_read_barrier_depends(); /* see above */
+	return ret;
 }
 
 #define pte_offset_map(dir,addr)	pte_offset_kernel((dir),(addr))

trunk/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);
@@ -2619,6 +2636,8 @@ 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 +2659,8 @@ 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 */