Merge remote-tracking branch 'stable/linux-3.12.y' into sdk-v1.6.x

Signed-off-by: Scott Wood <scottwood@freescale.com>

Conflicts:
	drivers/mmc/card/block.c

1 files changed, 49 insertions, 17 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cca80d9..389973f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -884,6 +884,10 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		ret = 0;
 		goto out_unlock;
 	}
+
+	/* mmap_sem prevents this happening but warn if that changes */
+	WARN_ON(pmd_trans_migrating(pmd));
+
 	if (unlikely(pmd_trans_splitting(pmd))) {
 		/* split huge page running from under us */
 		spin_unlock(&src_mm->page_table_lock);
@@ -1150,14 +1154,16 @@ alloc:
 		new_page = NULL;
 
 	if (unlikely(!new_page)) {
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			ret = do_huge_pmd_wp_zero_page_fallback(mm, vma,
 					address, pmd, orig_pmd, haddr);
 		} else {
 			ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
 					pmd, orig_pmd, page, haddr);
-			if (ret & VM_FAULT_OOM)
+			if (ret & VM_FAULT_OOM) {
 				split_huge_page(page);
+				ret |= VM_FAULT_FALLBACK;
+			}
 			put_page(page);
 		}
 		count_vm_event(THP_FAULT_FALLBACK);
@@ -1169,15 +1175,16 @@ alloc:
 		if (page) {
 			split_huge_page(page);
 			put_page(page);
-		}
+		} else
+			split_huge_page_pmd(vma, address, pmd);
+		ret |= VM_FAULT_FALLBACK;
 		count_vm_event(THP_FAULT_FALLBACK);
-		ret |= VM_FAULT_OOM;
 		goto out;
 	}
 
 	count_vm_event(THP_FAULT_ALLOC);
 
-	if (is_huge_zero_pmd(orig_pmd))
+	if (!page)
 		clear_huge_page(new_page, haddr, HPAGE_PMD_NR);
 	else
 		copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
@@ -1203,7 +1210,7 @@ alloc:
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
 		update_mmu_cache_pmd(vma, address, pmd);
-		if (is_huge_zero_pmd(orig_pmd)) {
+		if (!page) {
 			add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
 			put_huge_zero_page();
 		} else {
@@ -1240,6 +1247,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
 		return ERR_PTR(-EFAULT);
 
+	/* Full NUMA hinting faults to serialise migration in fault paths */
+	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+		goto out;
+
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
 	if (flags & FOLL_TOUCH) {
@@ -1290,6 +1301,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
+	/*
+	 * If there are potential migrations, wait for completion and retry
+	 * without disrupting NUMA hinting information. Do not relock and
+	 * check_same as the page may no longer be mapped.
+	 */
+	if (unlikely(pmd_trans_migrating(*pmdp))) {
+		spin_unlock(&mm->page_table_lock);
+		wait_migrate_huge_page(vma->anon_vma, pmdp);
+		goto out;
+	}
+
 	page = pmd_page(pmd);
 	page_nid = page_to_nid(page);
 	count_vm_numa_event(NUMA_HINT_FAULTS);
@@ -1306,23 +1328,22 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* If the page was locked, there are no parallel migrations */
 		if (page_locked)
 			goto clear_pmdnuma;
+	}
 
-		/*
-		 * Otherwise wait for potential migrations and retry. We do
-		 * relock and check_same as the page may no longer be mapped.
-		 * As the fault is being retried, do not account for it.
-		 */
+	/* Migration could have started since the pmd_trans_migrating check */
+	if (!page_locked) {
 		spin_unlock(&mm->page_table_lock);
 		wait_on_page_locked(page);
 		page_nid = -1;
 		goto out;
 	}
 
-	/* Page is misplaced, serialise migrations and parallel THP splits */
+	/*
+	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+	 * to serialises splits
+	 */
 	get_page(page);
 	spin_unlock(&mm->page_table_lock);
-	if (!page_locked)
-		lock_page(page);
 	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PTE did not while locked */
@@ -1334,6 +1355,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_unlock;
 	}
 
+	/* Bail if we fail to protect against THP splits for any reason */
+	if (unlikely(!anon_vma)) {
+		put_page(page);
+		page_nid = -1;
+		goto clear_pmdnuma;
+	}
+
 	/*
 	 * Migrate the THP to the requested node, returns with page unlocked
 	 * and pmd_numa cleared.
@@ -1466,20 +1494,24 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 
 	if (__pmd_trans_huge_lock(pmd, vma) == 1) {
 		pmd_t entry;
-		entry = pmdp_get_and_clear(mm, addr, pmd);
 		if (!prot_numa) {
+			entry = pmdp_get_and_clear(mm, addr, pmd);
+			if (pmd_numa(entry))
+				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			BUG_ON(pmd_write(entry));
+			set_pmd_at(mm, addr, pmd, entry);
 		} else {
 			struct page *page = pmd_page(*pmd);
+			entry = *pmd;
 
 			/* only check non-shared pages */
 			if (page_mapcount(page) == 1 &&
 			    !pmd_numa(*pmd)) {
 				entry = pmd_mknuma(entry);
+				set_pmd_at(mm, addr, pmd, entry);
 			}
 		}
-		set_pmd_at(mm, addr, pmd, entry);
 		spin_unlock(&vma->vm_mm->page_table_lock);
 		ret = 1;
 	}
@@ -1865,7 +1897,7 @@ out:
 	return ret;
 }
 
-#define VM_NO_THP (VM_SPECIAL|VM_MIXEDMAP|VM_HUGETLB|VM_SHARED|VM_MAYSHARE)
+#define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE)
 
 int hugepage_madvise(struct vm_area_struct *vma,
 		     unsigned long *vm_flags, int advice)