From: Jérôme Glisse <jgli...@redhat.com>

When notifying change for a range use MMU_NOTIFIER_USE_CHANGE_PTE flag
for page table update that use set_pte_at_notify() and where the we are
going either from read and write to read only with same pfn or read only
to read and write with new pfn.

Note that set_pte_at_notify() itself should only be use in rare cases
ie we do not want to use it when we are updating a significant range of
virtual addresses and thus a significant number of pte. Instead for
those cases the event provided to mmu notifer invalidate_range_start()
callback should be use for optimization.

Signed-off-by: Jérôme Glisse <jgli...@redhat.com>
Cc: Andrea Arcangeli <aarca...@redhat.com>
Cc: Peter Xu <pet...@redhat.com>
Cc: Andrew Morton <a...@linux-foundation.org>
Cc: Paolo Bonzini <pbonz...@redhat.com>
Cc: Radim Krčmář <rkrc...@redhat.com>
Cc: k...@vger.kernel.org
---
 include/linux/mmu_notifier.h | 13 +++++++++++++
 mm/ksm.c                     |  6 ++++--
 mm/memory.c                  |  3 ++-
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index d7a35975c2bd..0885bf33dc9c 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -43,6 +43,19 @@ enum mmu_notifier_event {
 };
 
 #define MMU_NOTIFIER_EVENT_BITS order_base_2(MMU_NOTIFY_EVENT_MAX)
+/*
+ * Set MMU_NOTIFIER_USE_CHANGE_PTE only when the page table it updated with the
+ * set_pte_at_notify() and when pte is updated from read and write to read only
+ * with same pfn or from read only to read and write with different pfn. It is
+ * illegal to set in any other circumstances.
+ *
+ * Note that set_pte_at_notify() should not be use outside of the above cases.
+ * When updating a range in batch (like write protecting a range) it is better
+ * to rely on invalidate_range_start() and struct mmu_notifier_range to infer
+ * the kind of update that is happening (as an example you can look at the
+ * mmu_notifier_range_update_to_read_only() function).
+ */
+#define MMU_NOTIFIER_USE_CHANGE_PTE (1 << MMU_NOTIFIER_EVENT_BITS)
 
 #ifdef CONFIG_MMU_NOTIFIER
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 97757c5fa15f..b7fb7b560cc0 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1051,7 +1051,8 @@ static int write_protect_page(struct vm_area_struct *vma, 
struct page *page,
 
        BUG_ON(PageTransCompound(page));
 
-       mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, vma, mm,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR |
+                               MMU_NOTIFIER_USE_CHANGE_PTE, vma, mm,
                                pvmw.address,
                                pvmw.address + PAGE_SIZE);
        mmu_notifier_invalidate_range_start(&range);
@@ -1140,7 +1141,8 @@ static int replace_page(struct vm_area_struct *vma, 
struct page *page,
        if (!pmd)
                goto out;
 
-       mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, vma, mm, addr,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR |
+                               MMU_NOTIFIER_USE_CHANGE_PTE, vma, mm, addr,
                                addr + PAGE_SIZE);
        mmu_notifier_invalidate_range_start(&range);
 
diff --git a/mm/memory.c b/mm/memory.c
index a8c6922526f6..daf4b0f92af8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2275,7 +2275,8 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 
        __SetPageUptodate(new_page);
 
-       mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, vma, mm,
+       mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR |
+                               MMU_NOTIFIER_USE_CHANGE_PTE, vma, mm,
                                vmf->address & PAGE_MASK,
                                (vmf->address & PAGE_MASK) + PAGE_SIZE);
        mmu_notifier_invalidate_range_start(&range);
-- 
2.17.1

Reply via email to