mm: numa: Support NUMA hinting page faults from gup/gup_fast

Introduce FOLL_NUMA to tell follow_page to check pte/pmd_numa. get_user_pages must use FOLL_NUMA, and it's safe to do so because it always invokes handle_mm_fault and retries the follow_page later. KVM secondary MMU page faults will trigger the NUMA hinting page faults through gup_fast -> get_user_pages -> follow_page -> handle_mm_fault. Other follow_page callers like KSM should not use FOLL_NUMA, or they would fail to get the pages if they use follow_page instead of get_user_pages. [ This patch was picked up from the AutoNUMA tree. ] Originally-by: Andrea Arcangeli <[email protected]> Cc: Linus Torvalds <[email protected]> Cc: Andrew Morton <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Andrea Arcangeli <[email protected]> Cc: Rik van Riel <[email protected]> [ ported to this tree. ] Signed-off-by: Ingo Molnar <[email protected]> Reviewed-by: Rik van Riel <[email protected]>
Baughn · Dec 11, 2012 · 0b9d705 · 0b9d705
1 parent be3a728
commit 0b9d705
Show file tree

Hide file tree

Showing 2 changed files with 18 additions and 0 deletions.
diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -1572,6 +1572,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_MLOCK	0x40	/* mark page as mlocked */
 #define FOLL_SPLIT	0x80	/* don't return transhuge pages, split them */
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
+#define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);

diff --git a/mm/memory.c b/mm/memory.c
@@ -1517,6 +1517,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
 		goto out;
 	}
+	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+		goto no_page_table;
 	if (pmd_trans_huge(*pmd)) {
 		if (flags & FOLL_SPLIT) {
 			split_huge_page_pmd(mm, pmd);
@@ -1546,6 +1548,8 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	pte = *ptep;
 	if (!pte_present(pte))
 		goto no_page;
+	if ((flags & FOLL_NUMA) && pte_numa(pte))
+		goto no_page;
 	if ((flags & FOLL_WRITE) && !pte_write(pte))
 		goto unlock;
 
@@ -1697,6 +1701,19 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			(VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
 	vm_flags &= (gup_flags & FOLL_FORCE) ?
 			(VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+
+	/*
+	 * If FOLL_FORCE and FOLL_NUMA are both set, handle_mm_fault
+	 * would be called on PROT_NONE ranges. We must never invoke
+	 * handle_mm_fault on PROT_NONE ranges or the NUMA hinting
+	 * page faults would unprotect the PROT_NONE ranges if
+	 * _PAGE_NUMA and _PAGE_PROTNONE are sharing the same pte/pmd
+	 * bitflag. So to avoid that, don't set FOLL_NUMA if
+	 * FOLL_FORCE is set.
+	 */
+	if (!(gup_flags & FOLL_FORCE))
+		gup_flags |= FOLL_NUMA;
+
 	i = 0;
 
 	do {