Merge branch 'x86/for-kvm' into x86/apic

Pull in the apic change which is provided for kvm folks to pull into
their tree.

10 files changed, 118 insertions, 68 deletions

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d3033183ed70..055a01de7c8d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1128,7 +1128,18 @@ END(error_exit)
 
 /* Runs on exception stack */
 ENTRY(nmi)
+	/*
+	 * Fix up the exception frame if we're on Xen.
+	 * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
+	 * one value to the stack on native, so it may clobber the rdx
+	 * scratch slot, but it won't clobber any of the important
+	 * slots past it.
+	 *
+	 * Xen is a different story, because the Xen frame itself overlaps
+	 * the "NMI executing" variable.
+	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+
 	/*
 	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
 	 * the iretq it performs will take us out of NMI context.
@@ -1179,9 +1190,12 @@ ENTRY(nmi)
 	 * we don't want to enable interrupts, because then we'll end
 	 * up in an awkward situation in which IRQs are on but NMIs
 	 * are off.
+	 *
+	 * We also must not push anything to the stack before switching
+	 * stacks lest we corrupt the "NMI executing" variable.
 	 */
 
-	SWAPGS
+	SWAPGS_UNSAFE_STACK
 	cld
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index ebf6d5e5668c..a30316bf801a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -115,6 +115,59 @@ static inline bool apic_is_x2apic_enabled(void)
 	return msr & X2APIC_ENABLE;
 }
 
+extern void enable_IR_x2apic(void);
+
+extern int get_physical_broadcast(void);
+
+extern int lapic_get_maxlvt(void);
+extern void clear_local_APIC(void);
+extern void disconnect_bsp_APIC(int virt_wire_setup);
+extern void disable_local_APIC(void);
+extern void lapic_shutdown(void);
+extern void sync_Arb_IDs(void);
+extern void init_bsp_APIC(void);
+extern void setup_local_APIC(void);
+extern void init_apic_mappings(void);
+void register_lapic_address(unsigned long address);
+extern void setup_boot_APIC_clock(void);
+extern void setup_secondary_APIC_clock(void);
+extern int APIC_init_uniprocessor(void);
+
+#ifdef CONFIG_X86_64
+static inline int apic_force_enable(unsigned long addr)
+{
+	return -1;
+}
+#else
+extern int apic_force_enable(unsigned long addr);
+#endif
+
+extern int apic_bsp_setup(bool upmode);
+extern void apic_ap_setup(void);
+
+/*
+ * On 32bit this is mach-xxx local
+ */
+#ifdef CONFIG_X86_64
+extern int apic_is_clustered_box(void);
+#else
+static inline int apic_is_clustered_box(void)
+{
+	return 0;
+}
+#endif
+
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
+
+#else /* !CONFIG_X86_LOCAL_APIC */
+static inline void lapic_shutdown(void) { }
+#define local_apic_timer_c2_ok		1
+static inline void init_apic_mappings(void) { }
+static inline void disable_local_APIC(void) { }
+# define setup_boot_APIC_clock x86_init_noop
+# define setup_secondary_APIC_clock x86_init_noop
+#endif /* !CONFIG_X86_LOCAL_APIC */
+
 #ifdef CONFIG_X86_X2APIC
 /*
  * Make previous memory operations globally visible before
@@ -186,67 +239,14 @@ static inline int x2apic_enabled(void)
 }
 
 #define x2apic_supported()	(cpu_has_x2apic)
-#else
+#else /* !CONFIG_X86_X2APIC */
 static inline void check_x2apic(void) { }
 static inline void x2apic_setup(void) { }
 static inline int x2apic_enabled(void) { return 0; }
 
 #define x2apic_mode		(0)
 #define	x2apic_supported()	(0)
-#endif
-
-extern void enable_IR_x2apic(void);
-
-extern int get_physical_broadcast(void);
-
-extern int lapic_get_maxlvt(void);
-extern void clear_local_APIC(void);
-extern void disconnect_bsp_APIC(int virt_wire_setup);
-extern void disable_local_APIC(void);
-extern void lapic_shutdown(void);
-extern void sync_Arb_IDs(void);
-extern void init_bsp_APIC(void);
-extern void setup_local_APIC(void);
-extern void init_apic_mappings(void);
-void register_lapic_address(unsigned long address);
-extern void setup_boot_APIC_clock(void);
-extern void setup_secondary_APIC_clock(void);
-extern int APIC_init_uniprocessor(void);
-
-#ifdef CONFIG_X86_64
-static inline int apic_force_enable(unsigned long addr)
-{
-	return -1;
-}
-#else
-extern int apic_force_enable(unsigned long addr);
-#endif
-
-extern int apic_bsp_setup(bool upmode);
-extern void apic_ap_setup(void);
-
-/*
- * On 32bit this is mach-xxx local
- */
-#ifdef CONFIG_X86_64
-extern int apic_is_clustered_box(void);
-#else
-static inline int apic_is_clustered_box(void)
-{
-	return 0;
-}
-#endif
-
-extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
-
-#else /* !CONFIG_X86_LOCAL_APIC */
-static inline void lapic_shutdown(void) { }
-#define local_apic_timer_c2_ok		1
-static inline void init_apic_mappings(void) { }
-static inline void disable_local_APIC(void) { }
-# define setup_boot_APIC_clock x86_init_noop
-# define setup_secondary_APIC_clock x86_init_noop
-#endif /* !CONFIG_X86_LOCAL_APIC */
+#endif /* !CONFIG_X86_X2APIC */
 
 #ifdef CONFIG_X86_64
 #define	SET_APIC_ID(x)		(apic->set_apic_id(x))
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 155162ea0e00..ab5f1d447ef9 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -86,6 +86,16 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 					u32 type, u64 attribute);
 
+/*
+ * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
+ * only in kernel binary.  Since the EFI stub linked into a separate binary it
+ * doesn't have __memset().  So we should use standard memset from
+ * arch/x86/boot/compressed/string.c.  The same applies to memcpy and memmove.
+ */
+#undef memcpy
+#undef memset
+#undef memmove
+
 #endif /* CONFIG_X86_32 */
 
 extern struct efi_scratch efi_scratch;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 349f80a82b82..2beee0382088 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -40,6 +40,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_HALT_POLL_NS_DEFAULT 500000
 
 #define KVM_IRQCHIP_NUM_PINS  KVM_IOAPIC_NUM_PINS
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c1c0a1c14344..b98b471a3b7e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -331,6 +331,7 @@
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
 #define MSR_K8_TSEG_ADDR		0xc0010112
+#define MSR_K8_TSEG_MASK		0xc0010113
 #define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
 #define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f68e48f5f6c2..c2130aef3f9d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -41,10 +41,18 @@
 #include <asm/timer.h>
 #include <asm/special_insns.h>
 
-/* nop stub */
-void _paravirt_nop(void)
-{
-}
+/*
+ * nop stub, which must not clobber anything *including the stack* to
+ * avoid confusing the entry prologues.
+ */
+extern void _paravirt_nop(void);
+asm (".pushsection .entry.text, \"ax\"\n"
+     ".global _paravirt_nop\n"
+     "_paravirt_nop:\n\t"
+     "ret\n\t"
+     ".size _paravirt_nop, . - _paravirt_nop\n\t"
+     ".type _paravirt_nop, @function\n\t"
+     ".popsection");
 
 /* identity function, which can be inlined */
 u32 _paravirt_ident_32(u32 x)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 69088a1ba509..ff606f507913 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3322,7 +3322,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 			break;
 
 		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
-						    leaf);
+						    iterator.level);
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3614,7 +3614,7 @@ static void
 __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			struct rsvd_bits_validate *rsvd_check,
 			int maxphyaddr, int level, bool nx, bool gbpages,
-			bool pse)
+			bool pse, bool amd)
 {
 	u64 exb_bit_rsvd = 0;
 	u64 gbpages_bit_rsvd = 0;
@@ -3631,7 +3631,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	 * Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
 	 * leaf entries) on AMD CPUs only.
 	 */
-	if (guest_cpuid_is_amd(vcpu))
+	if (amd)
 		nonleaf_bit8_rsvd = rsvd_bits(8, 8);
 
 	switch (level) {
@@ -3699,7 +3699,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
 				cpuid_maxphyaddr(vcpu), context->root_level,
 				context->nx, guest_cpuid_has_gbpages(vcpu),
-				is_pse(vcpu));
+				is_pse(vcpu), guest_cpuid_is_amd(vcpu));
 }
 
 static void
@@ -3749,13 +3749,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 void
 reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
 {
+	/*
+	 * 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,
 				boot_cpu_data.x86_phys_bits,
 				context->shadow_root_level, context->nx,
-				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+				guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
+				true);
 }
 EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
 
+static inline bool boot_cpu_is_amd(void)
+{
+	WARN_ON_ONCE(!tdp_enabled);
+	return shadow_x_mask == 0;
+}
+
 /*
  * the direct page table on host, use as much mmu features as
  * possible, however, kvm currently does not do execution-protection.
@@ -3764,11 +3775,11 @@ static void
 reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
 				struct kvm_mmu *context)
 {
-	if (guest_cpuid_is_amd(vcpu))
+	if (boot_cpu_is_amd())
 		__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
 					boot_cpu_data.x86_phys_bits,
 					context->shadow_root_level, false,
-					cpu_has_gbpages, true);
+					cpu_has_gbpages, true, true);
 	else
 		__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
 					    boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fdb8cb63a6c0..94b7d15db3fc 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -202,6 +202,7 @@ module_param(npt, int, S_IRUGO);
 static int nested = true;
 module_param(nested, int, S_IRUGO);
 
+static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 static void svm_flush_tlb(struct kvm_vcpu *vcpu);
 static void svm_complete_interrupts(struct vcpu_svm *svm);
 
@@ -1263,7 +1264,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
 	 * It also updates the guest-visible cr0 value.
 	 */
-	(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	kvm_mmu_reset_context(&svm->vcpu);
 
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6bbb0dfb99d0..991466bf8dee 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2190,6 +2190,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
 	case MSR_K8_SYSCFG:
+	case MSR_K8_TSEG_ADDR:
+	case MSR_K8_TSEG_MASK:
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K8_INT_PENDING_MSG:
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 09d3afc0a181..dc78a4a9a466 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -166,6 +166,7 @@ void pcibios_fixup_bus(struct pci_bus *b)
 {
 	struct pci_dev *dev;
 
+	pci_read_bridge_bases(b);
 	list_for_each_entry(dev, &b->devices, bus_list)
 		pcibios_fixup_device_resources(dev);
 }