thp: mmu_notifier_test_young

For GRU and EPT, we need gup-fast to set referenced bit too (this is why
it's correct to return 0 when shadow_access_mask is zero, it requires
gup-fast to set the referenced bit). qemu-kvm access already sets the
young bit in the pte if it isn't zero-copy, if it's zero copy or a shadow
paging EPT minor fault we relay on gup-fast to signal the page is in
use...

We also need to check the young bits on the secondary pagetables for NPT
and not nested shadow mmu as the data may never get accessed again by the
primary pte.

Without this closer accuracy, we'd have to remove the heuristic that
avoids collapsing hugepages in hugepage virtual regions that have not even
a single subpage in use.

->test_young is full backwards compatible with GRU and other usages that
don't have young bits in pagetables set by the hardware and that should
nuke the secondary mmu mappings when ->clear_flush_young runs just like
EPT does.

Removing the heuristic that checks the young bit in
khugepaged/collapse_huge_page completely isn't so bad either probably but
I thought it was worth it and this makes it reliable.

Signed-off-by: Andrea Arcangeli <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

arch/x86/include/asm/kvm_host.h

···
 #define KVM_ARCH_WANT_MMU_NOTIFIER
 int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
 int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
 void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
 int cpuid_maxphyaddr(struct kvm_vcpu *vcpu);
 int kvm_cpu_has_interrupt(struct kvm_vcpu *vcpu);

arch/x86/kvm/mmu.c

···
 	return young;
 }
 
+static int kvm_test_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
+			      unsigned long data)
+{
+	u64 *spte;
+	int young = 0;
+
+	/*
+	 * If there's no access bit in the secondary pte set by the
+	 * hardware it's up to gup-fast/gup to set the access bit in
+	 * the primary pte or in the page structure.
+	 */
+	if (!shadow_accessed_mask)
+		goto out;
+
+	spte = rmap_next(kvm, rmapp, NULL);
+	while (spte) {
+		u64 _spte = *spte;
+		BUG_ON(!(_spte & PT_PRESENT_MASK));
+		young = _spte & PT_ACCESSED_MASK;
+		if (young) {
+			young = 1;
+			break;
+		}
+		spte = rmap_next(kvm, rmapp, spte);
+	}
+out:
+	return young;
+}
+
 #define RMAP_RECYCLE_THRESHOLD 1000
 
 static void rmap_recycle(struct kvm_vcpu *vcpu, u64 *spte, gfn_t gfn)
···
 int kvm_age_hva(struct kvm *kvm, unsigned long hva)
 {
 	return kvm_handle_hva(kvm, hva, 0, kvm_age_rmapp);
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+	return kvm_handle_hva(kvm, hva, 0, kvm_test_age_rmapp);
 }
 
 #ifdef MMU_DEBUG

arch/x86/mm/gup.c

···
 #include <linux/mm.h>
 #include <linux/vmstat.h>
 #include <linux/highmem.h>
+#include <linux/swap.h>
 
 #include <asm/pgtable.h>
 
···
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 		get_page(page);
+		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
 
···
 	VM_BUG_ON(page != compound_head(page));
 	VM_BUG_ON(page_count(page) == 0);
 	atomic_add(nr, &page->_count);
+	SetPageReferenced(page);
 }
 
 static inline void get_huge_page_tail(struct page *page)

include/linux/mmu_notifier.h

···
 				 unsigned long address);
 
 	/*
+	 * test_young is called to check the young/accessed bitflag in
+	 * the secondary pte. This is used to know if the page is
+	 * frequently used without actually clearing the flag or tearing
+	 * down the secondary mapping on the page.
+	 */
+	int (*test_young)(struct mmu_notifier *mn,
+			  struct mm_struct *mm,
+			  unsigned long address);
+
+	/*
 	 * change_pte is called in cases that pte mapping to page is changed:
 	 * for example, when ksm remaps pte to point to a new shared page.
 	 */
···
 extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					  unsigned long address);
+extern int __mmu_notifier_test_young(struct mm_struct *mm,
+				     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,
 				      unsigned long address, pte_t pte);
 extern void __mmu_notifier_invalidate_page(struct mm_struct *mm,
···
 {
 	if (mm_has_notifiers(mm))
 		return __mmu_notifier_clear_flush_young(mm, address);
+	return 0;
+}
+
+static inline int mmu_notifier_test_young(struct mm_struct *mm,
+					  unsigned long address)
+{
+	if (mm_has_notifiers(mm))
+		return __mmu_notifier_test_young(mm, address);
 	return 0;
 }
 
···
 }
 
 static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
+					  unsigned long address)
+{
+	return 0;
+}
+
+static inline int mmu_notifier_test_young(struct mm_struct *mm,
 					  unsigned long address)
 {
 	return 0;

mm/huge_memory.c

···
 		VM_BUG_ON(PageLRU(page));
 
 		/* If there is no mapped pte young don't collapse the page */
-		if (pte_young(pteval))
+		if (pte_young(pteval) || PageReferenced(page) ||
+		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = 1;
 	}
 	if (unlikely(!referenced))
···
 		/* cannot use mapcount: can't collapse if there's a gup pin */
 		if (page_count(page) != 1)
 			goto out_unmap;
-		if (pte_young(pteval))
+		if (pte_young(pteval) || PageReferenced(page) ||
+		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = 1;
 	}
 	if (referenced)

mm/mmu_notifier.c

···
 	return young;
 }
 
+int __mmu_notifier_test_young(struct mm_struct *mm,
+			      unsigned long address)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n;
+	int young = 0;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->test_young) {
+			young = mn->ops->test_young(mn, mm, address);
+			if (young)
+				break;
+		}
+	}
+	rcu_read_unlock();
+
+	return young;
+}
+
 void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 			       pte_t pte)
 {

virt/kvm/kvm_main.c

···
 	return young;
 }
 
+static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
+				       struct mm_struct *mm,
+				       unsigned long address)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	int young, idx;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	spin_lock(&kvm->mmu_lock);
+	young = kvm_test_age_hva(kvm, address);
+	spin_unlock(&kvm->mmu_lock);
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return young;
+}
+
 static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 				     struct mm_struct *mm)
 {
···
 	.invalidate_range_start	= kvm_mmu_notifier_invalidate_range_start,
 	.invalidate_range_end	= kvm_mmu_notifier_invalidate_range_end,
 	.clear_flush_young	= kvm_mmu_notifier_clear_flush_young,
+	.test_young		= kvm_mmu_notifier_test_young,
 	.change_pte		= kvm_mmu_notifier_change_pte,
 	.release		= kvm_mmu_notifier_release,
 };