From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sean Christopherson Date: Wed, 08 Jan 2020 20:24:48 +0000 Subject: [PATCH 14/14] KVM: x86/mmu: Use huge pages for DAX-backed files Message-Id: <20200108202448.9669-15-sean.j.christopherson@intel.com> List-Id: References: <20200108202448.9669-1-sean.j.christopherson@intel.com> In-Reply-To: <20200108202448.9669-1-sean.j.christopherson@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Paolo Bonzini Cc: Paul Mackerras , Sean Christopherson , Vitaly Kuznetsov , Wanpeng Li , Jim Mattson , Joerg Roedel , Dave Hansen , Andy Lutomirski , Peter Zijlstra , Andrew Morton , Marc Zyngier , James Morse , Julien Thierry , Suzuki K Poulose , kvm-ppc@vger.kernel.org, kvm@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, kvmarm@lists.cs.columbia.edu, syzbot+c9d1fb51ac9d0d10c39d@syzkaller.appspotmail.com, Andrea Arcangeli , Barret Rhoden , David Hildenbrand , Jason Zeng , Liran Alon , linux-nvdimm 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 Cc: David Hildenbrand Cc: Dan Williams Cc: Jason Zeng Cc: Dave Jiang Cc: Liran Alon Cc: linux-nvdimm Signed-off-by: Sean Christopherson --- 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 1e4e0ac169a7..324e1919722f 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 = kvm_vcpu_gfn_to_memslot(vcpu, gfn); @@ -5910,8 +5909,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm, * 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()) -- 2.24.1