[Devel] [PATCH RHEL7 COMMIT] kvm: mmu: don't set the present bit unconditionally

[Konstantin Khorenko]

The commit is pushed to "branch-rh7-3.10.0-693.21.1.vz7.50.x-ovz" and will appear at https://src.openvz.org/scm/ovz/vzkernel.git
after rh7-3.10.0-693.21.1.vz7.47.6
------>
commit 19e5cd42fd649c10244f18920ea3906c47d99c01
Author: Bandan Das <bsd at redhat.com>
Date:   Wed May 16 12:50:41 2018 +0300

    kvm: mmu: don't set the present bit unconditionally
    
    To support execute only mappings on behalf of L1
    hypervisors, we need to teach set_spte() to honor all three of
    L1's XWR bits.  As a start, add a new variable "shadow_present_mask"
    that will be set for non-EPT shadow paging and clear for EPT.
    
    Signed-off-by: Bandan Das <bsd at redhat.com>
    Signed-off-by: Paolo Bonzini <pbonzini at redhat.com>
    
    (cherry picked from commit ffb128c89b77b44da18ccf51844a8e750e2c427a)
    Signed-off-by: Jan Dakinevich <jan.dakinevich at virtuozzo.com>
    
    =====================
    Patchset description:
    
    EPT fixes and enhancements
    
    Backport of EPT fixes from upstream for
    https://jira.sw.ru/browse/PSBM-84046
    
    Bandan Das (3):
      kvm: mmu: don't set the present bit unconditionally
      kvm: mmu: track read permission explicitly for shadow EPT page tables
      kvm: vmx: advertise support for ept execute only
    
    Junaid Shahid (2):
      kvm: x86: mmu: Use symbolic constants for EPT Violation Exit
        Qualifications
      kvm: x86: mmu: Rename EPT_VIOLATION_READ/WRITE/INSTR constants
    
    KarimAllah Ahmed (2):
      kvm: Map PFN-type memory regions as writable (if possible)
      KVM: x86: Update the exit_qualification access bits while walking an
        address
    
    Paolo Bonzini (5):
      KVM: nVMX: we support 1GB EPT pages
      kvm: x86: MMU support for EPT accessed/dirty bits
      kvm: nVMX: support EPT accessed/dirty bits
      KVM: MMU: return page fault error code from permission_fault
      KVM: nVMX: fix EPT permissions as reported in exit qualification
---
 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kvm/mmu.c              | 13 +++++++------
 arch/x86/kvm/vmx.c              |  1 +
 arch/x86/kvm/x86.c              |  4 ++--
 4 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d8966018ae60..0d77f961eb83 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1008,7 +1008,7 @@ void kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask);
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask);
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d1f5589dce82..7fa10bf2e2b0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -176,6 +176,7 @@ static u64 __read_mostly shadow_user_mask;
 static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mmio_mask;
+static u64 __read_mostly shadow_present_mask;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static void mmu_free_roots(struct kvm_vcpu *vcpu);
@@ -283,13 +284,14 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 }
 
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask)
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask)
 {
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
 	shadow_dirty_mask = dirty_mask;
 	shadow_nx_mask = nx_mask;
 	shadow_x_mask = x_mask;
+	shadow_present_mask = p_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -2233,10 +2235,9 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp)
 {
 	u64 spte;
 
-	BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
-			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+	BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
 
-	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+	spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
 	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
@@ -2506,13 +2507,13 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    gfn_t gfn, kvm_pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
-	u64 spte;
+	u64 spte = 0;
 	int ret = 0;
 
 	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
 		return 0;
 
-	spte = PT_PRESENT_MASK;
+	spte |= shadow_present_mask;
 	if (!speculative)
 		spte |= shadow_accessed_mask;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f4bb98930a1b..9b64a96f401a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6305,6 +6305,7 @@ static __init int hardware_setup(void)
 			(enable_ept_ad_bits) ? VMX_EPT_ACCESS_BIT : 0ull,
 			(enable_ept_ad_bits) ? VMX_EPT_DIRTY_BIT : 0ull,
 			0ull, VMX_EPT_EXECUTABLE_MASK);
+			0ull, VMX_EPT_EXECUTABLE_MASK, VMX_EPT_READABLE_MASK);
 		ept_set_mmio_spte_mask();
 		kvm_enable_tdp();
 	} else
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 14dedc4ec207..3b943c782f60 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5982,8 +5982,8 @@ int kvm_arch_init(void *opaque)
 	kvm_x86_ops = ops;
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
-			PT_DIRTY_MASK, PT64_NX_MASK, 0);
-
+			PT_DIRTY_MASK, PT64_NX_MASK, 0,
+			PT_PRESENT_MASK);
 	kvm_timer_init();
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);