Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 mm changes from Ingo Molnar:
 "PCID support, 5-level paging support, Secure Memory Encryption support

  The main changes in this cycle are support for three new, complex
  hardware features of x86 CPUs:

   - Add 5-level paging support, which is a new hardware feature on
     upcoming Intel CPUs allowing up to 128 PB of virtual address space
     and 4 PB of physical RAM space - a 512-fold increase over the old
     limits. (Supercomputers of the future forecasting hurricanes on an
     ever warming planet can certainly make good use of more RAM.)

     Many of the necessary changes went upstream in previous cycles,
     v4.14 is the first kernel that can enable 5-level paging.

     This feature is activated via CONFIG_X86_5LEVEL=y - disabled by
     default.

     (By Kirill A. Shutemov)

   - Add 'encrypted memory' support, which is a new hardware feature on
     upcoming AMD CPUs ('Secure Memory Encryption', SME) allowing system
     RAM to be encrypted and decrypted (mostly) transparently by the
     CPU, with a little help from the kernel to transition to/from
     encrypted RAM. Such RAM should be more secure against various
     attacks like RAM access via the memory bus and should make the
     radio signature of memory bus traffic harder to intercept (and
     decrypt) as well.

     This feature is activated via CONFIG_AMD_MEM_ENCRYPT=y - disabled
     by default.

     (By Tom Lendacky)

   - Enable PCID optimized TLB flushing on newer Intel CPUs: PCID is a
     hardware feature that attaches an address space tag to TLB entries
     and thus allows to skip TLB flushing in many cases, even if we
     switch mm's.

     (By Andy Lutomirski)

  All three of these features were in the works for a long time, and
  it's coincidence of the three independent development paths that they
  are all enabled in v4.14 at once"

* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (65 commits)
  x86/mm: Enable RCU based page table freeing (CONFIG_HAVE_RCU_TABLE_FREE=y)
  x86/mm: Use pr_cont() in dump_pagetable()
  x86/mm: Fix SME encryption stack ptr handling
  kvm/x86: Avoid clearing the C-bit in rsvd_bits()
  x86/CPU: Align CR3 defines
  x86/mm, mm/hwpoison: Clear PRESENT bit for kernel 1:1 mappings of poison pages
  acpi, x86/mm: Remove encryption mask from ACPI page protection type
  x86/mm, kexec: Fix memory corruption with SME on successive kexecs
  x86/mm/pkeys: Fix typo in Documentation/x86/protection-keys.txt
  x86/mm/dump_pagetables: Speed up page tables dump for CONFIG_KASAN=y
  x86/mm: Implement PCID based optimization: try to preserve old TLB entries using PCID
  x86: Enable 5-level paging support via CONFIG_X86_5LEVEL=y
  x86/mm: Allow userspace have mappings above 47-bit
  x86/mm: Prepare to expose larger address space to userspace
  x86/mpx: Do not allow MPX if we have mappings above 47-bit
  x86/mm: Rename tasksize_32bit/64bit to task_size_32bit/64bit()
  x86/xen: Redefine XEN_ELFNOTE_INIT_P2M using PUD_SIZE * PTRS_PER_PUD
  x86/mm/dump_pagetables: Fix printout of p4d level
  x86/mm/dump_pagetables: Generalize address normalization
  x86/boot: Fix memremap() related build failure
  ...

4 files changed, 55 insertions, 26 deletions

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 9b1dd114956a..04d750813c9d 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -108,7 +108,7 @@ module_param(dbg, bool, 0644);
 	(((address) >> PT32_LEVEL_SHIFT(level)) & ((1 << PT32_LEVEL_BITS) - 1))
 
 
-#define PT64_BASE_ADDR_MASK (((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1))
+#define PT64_BASE_ADDR_MASK __sme_clr((((1ULL << 52) - 1) & ~(u64)(PAGE_SIZE-1)))
 #define PT64_DIR_BASE_ADDR_MASK \
 	(PT64_BASE_ADDR_MASK & ~((1ULL << (PAGE_SHIFT + PT64_LEVEL_BITS)) - 1))
 #define PT64_LVL_ADDR_MASK(level) \
@@ -126,7 +126,7 @@ module_param(dbg, bool, 0644);
 					    * PT32_LEVEL_BITS))) - 1))
 
 #define PT64_PERM_MASK (PT_PRESENT_MASK | PT_WRITABLE_MASK | shadow_user_mask \
-			| shadow_x_mask | shadow_nx_mask)
+			| shadow_x_mask | shadow_nx_mask | shadow_me_mask)
 
 #define ACC_EXEC_MASK    1
 #define ACC_WRITE_MASK   PT_WRITABLE_MASK
@@ -186,6 +186,7 @@ static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mmio_mask;
 static u64 __read_mostly shadow_mmio_value;
 static u64 __read_mostly shadow_present_mask;
+static u64 __read_mostly shadow_me_mask;
 
 /*
  * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value.
@@ -349,7 +350,7 @@ 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 p_mask,
-		u64 acc_track_mask)
+		u64 acc_track_mask, u64 me_mask)
 {
 	BUG_ON(!dirty_mask != !accessed_mask);
 	BUG_ON(!accessed_mask && !acc_track_mask);
@@ -362,6 +363,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 	shadow_x_mask = x_mask;
 	shadow_present_mask = p_mask;
 	shadow_acc_track_mask = acc_track_mask;
+	shadow_me_mask = me_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -2433,7 +2435,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
 	BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
 
 	spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
-	       shadow_user_mask | shadow_x_mask;
+	       shadow_user_mask | shadow_x_mask | shadow_me_mask;
 
 	if (sp_ad_disabled(sp))
 		spte |= shadow_acc_track_value;
@@ -2745,6 +2747,7 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		pte_access &= ~ACC_WRITE_MASK;
 
 	spte |= (u64)pfn << PAGE_SHIFT;
+	spte |= shadow_me_mask;
 
 	if (pte_access & ACC_WRITE_MASK) {
 
@@ -4106,16 +4109,28 @@ void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
 	bool uses_nx = context->nx || context->base_role.smep_andnot_wp;
+	struct rsvd_bits_validate *shadow_zero_check;
+	int i;
 
 	/*
 	 * Passing "true" to the last argument is okay; it adds a check
 	 * on bit 8 of the SPTEs which KVM doesn't use anyway.
 	 */
-	__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+	shadow_zero_check = &context->shadow_zero_check;
+	__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
 				boot_cpu_data.x86_phys_bits,
 				context->shadow_root_level, uses_nx,
 				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
 				true);
+
+	if (!shadow_me_mask)
+		return;
+
+	for (i = context->shadow_root_level; --i >= 0;) {
+		shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask;
+		shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask;
+	}
+
 }
 EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
 
@@ -4133,17 +4148,29 @@ static void
 reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context)
 {
+	struct rsvd_bits_validate *shadow_zero_check;
+	int i;
+
+	shadow_zero_check = &context->shadow_zero_check;
+
 	if (boot_cpu_is_amd())
-		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
+		__reset_rsvds_bits_mask(vcpu, shadow_zero_check,
 					boot_cpu_data.x86_phys_bits,
 					context->shadow_root_level, false,
 					boot_cpu_has(X86_FEATURE_GBPAGES),
 					true, true);
 	else
-		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
+		__reset_rsvds_bits_mask_ept(shadow_zero_check,
 					    boot_cpu_data.x86_phys_bits,
 					    false);
 
+	if (!shadow_me_mask)
+		return;
+
+	for (i = context->shadow_root_level; --i >= 0;) {
+		shadow_zero_check->rsvd_bits_mask[0][i] &= ~shadow_me_mask;
+		shadow_zero_check->rsvd_bits_mask[1][i] &= ~shadow_me_mask;
+	}
 }
 
 /*
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index af256b786a70..8dbd8dbc83eb 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1167,9 +1167,9 @@ static void avic_init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb;
 	struct kvm_arch *vm_data = &svm->vcpu.kvm->arch;
-	phys_addr_t bpa = page_to_phys(svm->avic_backing_page);
-	phys_addr_t lpa = page_to_phys(vm_data->avic_logical_id_table_page);
-	phys_addr_t ppa = page_to_phys(vm_data->avic_physical_id_table_page);
+	phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
+	phys_addr_t lpa = __sme_set(page_to_phys(vm_data->avic_logical_id_table_page));
+	phys_addr_t ppa = __sme_set(page_to_phys(vm_data->avic_physical_id_table_page));
 
 	vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK;
 	vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK;
@@ -1232,8 +1232,8 @@ static void init_vmcb(struct vcpu_svm *svm)
 		set_intercept(svm, INTERCEPT_MWAIT);
 	}
 
-	control->iopm_base_pa = iopm_base;
-	control->msrpm_base_pa = __pa(svm->msrpm);
+	control->iopm_base_pa = __sme_set(iopm_base);
+	control->msrpm_base_pa = __sme_set(__pa(svm->msrpm));
 	control->int_ctl = V_INTR_MASKING_MASK;
 
 	init_seg(&save->es);
@@ -1377,9 +1377,9 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 
 	new_entry = READ_ONCE(*entry);
-	new_entry = (page_to_phys(svm->avic_backing_page) &
-		     AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
-		     AVIC_PHYSICAL_ID_ENTRY_VALID_MASK;
+	new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
+			      AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
+			      AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
 	WRITE_ONCE(*entry, new_entry);
 
 	svm->avic_physical_id_cache = entry;
@@ -1647,7 +1647,7 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 
 	svm->vmcb = page_address(page);
 	clear_page(svm->vmcb);
-	svm->vmcb_pa = page_to_pfn(page) << PAGE_SHIFT;
+	svm->vmcb_pa = __sme_set(page_to_pfn(page) << PAGE_SHIFT);
 	svm->asid_generation = 0;
 	init_vmcb(svm);
 
@@ -1675,7 +1675,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	__free_page(pfn_to_page(svm->vmcb_pa >> PAGE_SHIFT));
+	__free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT));
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
@@ -2330,7 +2330,7 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index)
 	u64 pdpte;
 	int ret;
 
-	ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte,
+	ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(__sme_clr(cr3)), &pdpte,
 				       offset_in_page(cr3) + index * 8, 8);
 	if (ret)
 		return 0;
@@ -2342,7 +2342,7 @@ static void nested_svm_set_tdp_cr3(struct kvm_vcpu *vcpu,
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->control.nested_cr3 = root;
+	svm->vmcb->control.nested_cr3 = __sme_set(root);
 	mark_dirty(svm->vmcb, VMCB_NPT);
 	svm_flush_tlb(vcpu);
 }
@@ -2873,7 +2873,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
 		svm->nested.msrpm[p] = svm->msrpm[p] | value;
 	}
 
-	svm->vmcb->control.msrpm_base_pa = __pa(svm->nested.msrpm);
+	svm->vmcb->control.msrpm_base_pa = __sme_set(__pa(svm->nested.msrpm));
 
 	return true;
 }
@@ -4506,7 +4506,7 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 	pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
 		 irq.vector);
 	*svm = to_svm(vcpu);
-	vcpu_info->pi_desc_addr = page_to_phys((*svm)->avic_backing_page);
+	vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page));
 	vcpu_info->vector = irq.vector;
 
 	return 0;
@@ -4557,7 +4557,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 			struct amd_iommu_pi_data pi;
 
 			/* Try to enable guest_mode in IRTE */
-			pi.base = page_to_phys(svm->avic_backing_page) & AVIC_HPA_MASK;
+			pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
+					    AVIC_HPA_MASK);
 			pi.ga_tag = AVIC_GATAG(kvm->arch.avic_vm_id,
 						     svm->vcpu.vcpu_id);
 			pi.is_guest_mode = true;
@@ -5006,7 +5007,7 @@ static void svm_set_cr3(struct kvm_vcpu *vcpu, unsigned long root)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->save.cr3 = root;
+	svm->vmcb->save.cr3 = __sme_set(root);
 	mark_dirty(svm->vmcb, VMCB_CR);
 	svm_flush_tlb(vcpu);
 }
@@ -5015,7 +5016,7 @@ static void set_tdp_cr3(struct kvm_vcpu *vcpu, unsigned long root)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	svm->vmcb->control.nested_cr3 = root;
+	svm->vmcb->control.nested_cr3 = __sme_set(root);
 	mark_dirty(svm->vmcb, VMCB_NPT);
 
 	/* Also sync guest cr3 here in case we live migrate */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c6ef2940119b..d40900914a72 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6556,7 +6556,7 @@ void vmx_enable_tdp(void)
 		enable_ept_ad_bits ? VMX_EPT_DIRTY_BIT : 0ull,
 		0ull, VMX_EPT_EXECUTABLE_MASK,
 		cpu_has_vmx_ept_execute_only() ? 0ull : VMX_EPT_READABLE_MASK,
-		VMX_EPT_RWX_MASK);
+		VMX_EPT_RWX_MASK, 0ull);
 
 	ept_set_mmio_spte_mask();
 	kvm_enable_tdp();
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 272320eb328c..ef5102f80497 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -54,6 +54,7 @@
 #include <linux/kvm_irqfd.h>
 #include <linux/irqbypass.h>
 #include <linux/sched/stat.h>
+#include <linux/mem_encrypt.h>
 
 #include <trace/events/kvm.h>
 
@@ -6125,7 +6126,7 @@ int kvm_arch_init(void *opaque)
 
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0,
-			PT_PRESENT_MASK, 0);
+			PT_PRESENT_MASK, 0, sme_me_mask);
 	kvm_timer_init();
 
 	perf_register_guest_info_callbacks(&kvm_guest_cbs);