[RFC PATCH 01/14] userfaultfd: set dirty and young on writeprotect

[Nadav Amit]

From: Nadav Amit <namit@xxxxxxxxxx>

When userfaultfd makes a PTE writable, it can now change the PTE
directly, in some cases, without going triggering a page-fault first.
Yet, doing so might leave the PTE that was write-unprotected as old and
clean. At least on x86, this would cause a >500 cycles overhead when the
PTE is first accessed.

Use MM_CP_WILL_NEED to set the PTE as young and dirty when userfaultfd
gets a hint that the page is likely to be used. Avoid changing the PTE
to young and dirty in other cases to avoid excessive writeback and
messing with the page reclamation logic.

Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Peter Xu <peterx@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Nick Piggin <npiggin@xxxxxxxxx>
---
 include/linux/mm.h | 2 ++
 mm/mprotect.c      | 9 ++++++++-
 mm/userfaultfd.c   | 8 ++++++--
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 9cc02a7e503b..4afd75ce5875 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1988,6 +1988,8 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 /* Whether this change is for write protecting */
 #define  MM_CP_UFFD_WP                     (1UL << 2) /* do wp */
 #define  MM_CP_UFFD_WP_RESOLVE             (1UL << 3) /* Resolve wp */
+/* Whether to try to mark entries as dirty as they are to be written */
+#define  MM_CP_WILL_NEED		   (1UL << 4)
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 996a97e213ad..34c2dfb68c42 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -82,6 +82,7 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
 	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
 	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
 	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
+	bool will_need = cp_flags & MM_CP_WILL_NEED;
 
 	tlb_change_page_size(tlb, PAGE_SIZE);
 
@@ -172,6 +173,9 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
 				ptent = pte_clear_uffd_wp(ptent);
 			}
 
+			if (will_need)
+				ptent = pte_mkyoung(ptent);
+
 			/*
 			 * In some writable, shared mappings, we might want
 			 * to catch actual write access -- see
@@ -187,8 +191,11 @@ static unsigned long change_pte_range(struct mmu_gather *tlb,
 			 */
 			if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) &&
 			    !pte_write(ptent) &&
-			    can_change_pte_writable(vma, addr, ptent))
+			    can_change_pte_writable(vma, addr, ptent)) {
 				ptent = pte_mkwrite(ptent);
+				if (will_need)
+					ptent = pte_mkdirty(ptent);
+			}
 
 			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
 			if (pte_needs_flush(oldpte, ptent))
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 954c6980b29f..e0492f5f06a0 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -749,6 +749,7 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 	bool enable_wp = uffd_flags & UFFD_FLAGS_WP;
 	struct vm_area_struct *dst_vma;
 	unsigned long page_mask;
+	unsigned long cp_flags;
 	struct mmu_gather tlb;
 	pgprot_t newprot;
 	int err;
@@ -795,9 +796,12 @@ int mwriteprotect_range(struct mm_struct *dst_mm, unsigned long start,
 	else
 		newprot = vm_get_page_prot(dst_vma->vm_flags);
 
+	cp_flags = enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE;
+	if (uffd_flags & (UFFD_FLAGS_ACCESS_LIKELY|UFFD_FLAGS_WRITE_LIKELY))
+		cp_flags |= MM_CP_WILL_NEED;
+
 	tlb_gather_mmu(&tlb, dst_mm);
-	change_protection(&tlb, dst_vma, start, start + len, newprot,
-			  enable_wp ? MM_CP_UFFD_WP : MM_CP_UFFD_WP_RESOLVE);
+	change_protection(&tlb, dst_vma, start, start + len, newprot, cp_flags);
 	tlb_finish_mmu(&tlb);
 
 	err = 0;
-- 
2.25.1