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 <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 38 insertions, 0 deletions

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index aa75f21a9fba..ffd7f8d29187 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -822,6 +822,7 @@ extern bool kvm_rebooting;
 #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);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 47b2c3288b6b..f02b8edc3d44 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -945,6 +945,35 @@ static int kvm_age_rmapp(struct kvm *kvm, unsigned long *rmapp,
 	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)
@@ -965,6 +994,11 @@ 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
 static int is_empty_shadow_page(u64 *spt)
 {
diff --git a/arch/x86/mm/gup.c b/arch/x86/mm/gup.c
index 269aa53932e0..dbe34b931374 100644
--- a/arch/x86/mm/gup.c
+++ b/arch/x86/mm/gup.c
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/vmstat.h>
 #include <linux/highmem.h>
+#include <linux/swap.h>
 
 #include <asm/pgtable.h>
 
@@ -89,6 +90,7 @@ static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
 		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 		get_page(page);
+		SetPageReferenced(page);
 		pages[*nr] = page;
 		(*nr)++;
 
@@ -103,6 +105,7 @@ static inline void get_head_page_multiple(struct page *page, int 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)