Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

1 files changed, 99 insertions, 12 deletions

diff --git a/mm/memory.c b/mm/memory.c
index bbab1e37..2302d22 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);
@@ -969,7 +986,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		goto no_page_table;
 	
 	pmd = pmd_offset(pud, address);
-	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
+	if (pmd_none(*pmd))
 		goto no_page_table;
 
 	if (pmd_huge(*pmd)) {
@@ -978,18 +995,19 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		goto out;
 	}
 
+	if (unlikely(pmd_bad(*pmd)))
+		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);
@@ -1004,6 +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
@@ -1018,6 +1045,26 @@ no_page_table:
 	return page;
 }
 
+/* Can we do the FOLL_ANON optimization? */
+static inline int use_zero_page(struct vm_area_struct *vma)
+{
+	/*
+	 * We don't want to optimize FOLL_ANON for make_pages_present()
+	 * when it tries to page in a VM_LOCKED region. As to VM_SHARED,
+	 * we want to get the page from the page tables to make sure
+	 * that we serialize and update with any other user of that
+	 * mapping.
+	 */
+	if (vma->vm_flags & (VM_LOCKED | VM_SHARED))
+		return 0;
+	/*
+	 * And if we have a fault or a nopfn routine, it's not an
+	 * anonymous region.
+	 */
+	return !vma->vm_ops ||
+		(!vma->vm_ops->fault && !vma->vm_ops->nopfn);
+}
+
 int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, int len, int write, int force,
 		struct page **pages, struct vm_area_struct **vmas)
@@ -1092,8 +1139,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		foll_flags = FOLL_TOUCH;
 		if (pages)
 			foll_flags |= FOLL_GET;
-		if (!write && !(vma->vm_flags & VM_LOCKED) &&
-		    (!vma->vm_ops || !vma->vm_ops->fault))
+		if (!write && use_zero_page(vma))
 			foll_flags |= FOLL_ANON;
 
 		do {
@@ -1105,7 +1151,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			 * be processed until returning to user space.
 			 */
 			if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE)))
-				return -ENOMEM;
+				return i ? i : -ENOMEM;
 
 			if (write)
 				foll_flags |= FOLL_WRITE;
@@ -1139,6 +1185,8 @@ 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;
 
@@ -1649,8 +1697,19 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *dirty_page = NULL;
 
 	old_page = vm_normal_page(vma, address, orig_pte);
-	if (!old_page)
+	if (!old_page) {
+		/*
+		 * VM_MIXEDMAP !pfn_valid() case
+		 *
+		 * We should not cow pages in a shared writeable mapping.
+		 * Just mark the pages writable as we can't do any dirty
+		 * accounting on raw pfn maps.
+		 */
+		if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
+				     (VM_WRITE|VM_SHARED))
+			goto reuse;
 		goto gotten;
+	}
 
 	/*
 	 * Take out anonymous pages first, anonymous shared vmas are
@@ -1703,6 +1762,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 
 	if (reuse) {
+reuse:
 		flush_cache_page(vma, address, pte_pfn(orig_pte));
 		entry = pte_mkyoung(orig_pte);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
@@ -1737,7 +1797,6 @@ gotten:
 	page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
 	if (likely(pte_same(*page_table, orig_pte))) {
 		if (old_page) {
-			page_remove_rmap(old_page, vma);
 			if (!PageAnon(old_page)) {
 				dec_mm_counter(mm, file_rss);
 				inc_mm_counter(mm, anon_rss);
@@ -1759,6 +1818,32 @@ gotten:
 		lru_cache_add_active(new_page);
 		page_add_new_anon_rmap(new_page, vma, address);
 
+		if (old_page) {
+			/*
+			 * Only after switching the pte to the new page may
+			 * we remove the mapcount here. Otherwise another
+			 * process may come and find the rmap count decremented
+			 * before the pte is switched to the new page, and
+			 * "reuse" the old page writing into it while our pte
+			 * here still points into it and can be read by other
+			 * threads.
+			 *
+			 * The critical issue is to order this
+			 * page_remove_rmap with the ptp_clear_flush above.
+			 * Those stores are ordered by (if nothing else,)
+			 * the barrier present in the atomic_add_negative
+			 * in page_remove_rmap.
+			 *
+			 * Then the TLB flush in ptep_clear_flush ensures that
+			 * no process can access the old page before the
+			 * decremented mapcount is visible. And the old page
+			 * cannot be reused until after the decremented
+			 * mapcount is visible. So transitively, TLBs to
+			 * old page will be flushed before it can be reused.
+			 */
+			page_remove_rmap(old_page, vma);
+		}
+
 		/* Free the old page.. */
 		new_page = old_page;
 		ret |= VM_FAULT_WRITE;
@@ -2275,8 +2360,6 @@ 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;
@@ -2616,6 +2699,8 @@ 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);
@@ -2637,6 +2722,8 @@ 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 */