From e851265a816f96a86c5a0316d2fc4d45be76d1d4 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <sean.j.christopherson@intel.com>
Date: Wed, 8 Jan 2020 12:24:48 -0800
Subject: [PATCH] KVM: x86/mmu: Use huge pages for DAX-backed files
Walk the host page tables to identify hugepage mappings for ZONE_DEVICE
pfns, i.e. DAX pages. Explicitly query kvm_is_zone_device_pfn() when
deciding whether or not to bother walking the host page tables, as DAX
pages do not set up the head/tail infrastructure, i.e. will return false
for PageCompound() even when using huge pages.
Zap ZONE_DEVICE sptes when disabling dirty logging, e.g. if live
migration fails, to allow KVM to rebuild large pages for DAX-based
mappings. Presumably DAX favors large pages, and worst case scenario is
a minor performance hit as KVM will need to re-fault all DAX-based
pages.
Suggested-by: Barret Rhoden <brho@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Jason Zeng <jason.zeng@intel.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Liran Alon <liran.alon@oracle.com>
Cc: linux-nvdimm <linux-nvdimm@lists.01.org>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
arch/x86/kvm/mmu/mmu.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index a9e6683c802b..febd65a9721a 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -3250,7 +3250,7 @@ static int host_pfn_mapping_level(struct kvm_vcpu *vcpu, gfn_t gfn,
PT_DIRECTORY_LEVEL != (int)PG_LEVEL_2M ||
PT_PDPE_LEVEL != (int)PG_LEVEL_1G);
- if (!PageCompound(pfn_to_page(pfn)))
+ if (!PageCompound(pfn_to_page(pfn)) && !kvm_is_zone_device_pfn(pfn))
return PT_PAGE_TABLE_LEVEL;
/*
@@ -3282,8 +3282,7 @@ static int kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, gfn_t gfn,
if (unlikely(max_level == PT_PAGE_TABLE_LEVEL))
return PT_PAGE_TABLE_LEVEL;
- if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn) ||
- kvm_is_zone_device_pfn(pfn))
+ if (is_error_noslot_pfn(pfn) || kvm_is_reserved_pfn(pfn))
return PT_PAGE_TABLE_LEVEL;
slot = gfn_to_memslot_dirty_bitmap(vcpu, gfn, true);
@@ -5912,8 +5911,8 @@ restart:
* mapping if the indirect sp has level = 1.
*/
if (sp->role.direct && !kvm_is_reserved_pfn(pfn) &&
- !kvm_is_zone_device_pfn(pfn) &&
- PageCompound(pfn_to_page(pfn))) {
+ (kvm_is_zone_device_pfn(pfn) ||
+ PageCompound(pfn_to_page(pfn)))) {
pte_list_remove(rmap_head, sptep);
if (kvm_available_flush_tlb_with_range())