Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Merge the crypto tree to pick up inside-secure fixes.

37 files changed, 317 insertions, 182 deletions

diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index 11b13c4b43d5..f19856d95c60 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -324,5 +324,5 @@ notrace time_t __vdso_time(time_t *t)
 		*t = result;
 	return result;
 }
-int time(time_t *t)
+time_t time(time_t *t)
 	__attribute__((weak, alias("__vdso_time")));
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index c0b0e9e8aa66..800104c8a3ed 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -266,6 +266,7 @@
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
 #define X86_FEATURE_IRPERF		(13*32+ 1) /* Instructions Retired Count */
+#define X86_FEATURE_XSAVEERPTR		(13*32+ 2) /* Always save/restore FP error pointers */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/arch/x86/include/asm/kmemcheck.h b/arch/x86/include/asm/kmemcheck.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/include/asm/kmemcheck.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 034caa1a084e..b24b1c8b3979 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -214,8 +214,6 @@ struct x86_emulate_ops {
 	void (*halt)(struct x86_emulate_ctxt *ctxt);
 	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
 	int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
-	void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
-	void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
 	int (*intercept)(struct x86_emulate_ctxt *ctxt,
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1bfb99770c34..516798431328 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -536,7 +536,20 @@ struct kvm_vcpu_arch {
 	struct kvm_mmu_memory_cache mmu_page_cache;
 	struct kvm_mmu_memory_cache mmu_page_header_cache;
 
+	/*
+	 * QEMU userspace and the guest each have their own FPU state.
+	 * In vcpu_run, we switch between the user and guest FPU contexts.
+	 * While running a VCPU, the VCPU thread will have the guest FPU
+	 * context.
+	 *
+	 * Note that while the PKRU state lives inside the fpu registers,
+	 * it is switched out separately at VMENTER and VMEXIT time. The
+	 * "guest_fpu" state here contains the guest FPU context, with the
+	 * host PRKU bits.
+	 */
+	struct fpu user_fpu;
 	struct fpu guest_fpu;
+
 	u64 xcr0;
 	u64 guest_supported_xcr0;
 	u32 guest_xstate_size;
@@ -1161,7 +1174,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2,
 static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 			int emulation_type)
 {
-	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
+	return x86_emulate_instruction(vcpu, 0,
+			emulation_type | EMULTYPE_NO_REEXECUTE, NULL, 0);
 }
 
 void kvm_enable_efer_bits(u64);
@@ -1434,4 +1448,7 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define put_smstate(type, buf, offset, val)                      \
 	*(type *)((buf) + (offset) - 0x7e00) = val
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end);
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 09f9e1e00e3b..95e2dfd75521 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1061,7 +1061,7 @@ extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
 				  unsigned long address, pmd_t *pmdp);
 
 
-#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write pmd_write
 static inline int pmd_write(pmd_t pmd)
 {
 	return pmd_flags(pmd) & _PAGE_RW;
@@ -1088,6 +1088,12 @@ static inline void pmdp_set_wrprotect(struct mm_struct *mm,
 	clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
 }
 
+#define pud_write pud_write
+static inline int pud_write(pud_t pud)
+{
+	return pud_flags(pud) & _PAGE_RW;
+}
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index b20f9d623f9c..8f09012b92e7 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -236,11 +236,23 @@
  */
 #define EARLY_IDT_HANDLER_SIZE 9
 
+/*
+ * xen_early_idt_handler_array is for Xen pv guests: for each entry in
+ * early_idt_handler_array it contains a prequel in the form of
+ * pop %rcx; pop %r11; jmp early_idt_handler_array[i]; summing up to
+ * max 8 bytes.
+ */
+#define XEN_EARLY_IDT_HANDLER_SIZE 8
+
 #ifndef __ASSEMBLY__
 
 extern const char early_idt_handler_array[NUM_EXCEPTION_VECTORS][EARLY_IDT_HANDLER_SIZE];
 extern void early_ignore_irq(void);
 
+#if defined(CONFIG_X86_64) && defined(CONFIG_XEN_PV)
+extern const char xen_early_idt_handler_array[NUM_EXCEPTION_VECTORS][XEN_EARLY_IDT_HANDLER_SIZE];
+#endif
+
 /*
  * Load a segment. Fall back on loading the zero segment if something goes
  * wrong.  This variant assumes that loading zero fully clears the segment.
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 509046cfa5ce..877b5c1a1b12 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -173,40 +173,43 @@ static inline void cr4_init_shadow(void)
 	this_cpu_write(cpu_tlbstate.cr4, __read_cr4());
 }
 
+static inline void __cr4_set(unsigned long cr4)
+{
+	lockdep_assert_irqs_disabled();
+	this_cpu_write(cpu_tlbstate.cr4, cr4);
+	__write_cr4(cr4);
+}
+
 /* Set in this cpu's CR4. */
 static inline void cr4_set_bits(unsigned long mask)
 {
-	unsigned long cr4;
+	unsigned long cr4, flags;
 
+	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	if ((cr4 | mask) != cr4) {
-		cr4 |= mask;
-		this_cpu_write(cpu_tlbstate.cr4, cr4);
-		__write_cr4(cr4);
-	}
+	if ((cr4 | mask) != cr4)
+		__cr4_set(cr4 | mask);
+	local_irq_restore(flags);
 }
 
 /* Clear in this cpu's CR4. */
 static inline void cr4_clear_bits(unsigned long mask)
 {
-	unsigned long cr4;
+	unsigned long cr4, flags;
 
+	local_irq_save(flags);
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	if ((cr4 & ~mask) != cr4) {
-		cr4 &= ~mask;
-		this_cpu_write(cpu_tlbstate.cr4, cr4);
-		__write_cr4(cr4);
-	}
+	if ((cr4 & ~mask) != cr4)
+		__cr4_set(cr4 & ~mask);
+	local_irq_restore(flags);
 }
 
-static inline void cr4_toggle_bits(unsigned long mask)
+static inline void cr4_toggle_bits_irqsoff(unsigned long mask)
 {
 	unsigned long cr4;
 
 	cr4 = this_cpu_read(cpu_tlbstate.cr4);
-	cr4 ^= mask;
-	this_cpu_write(cpu_tlbstate.cr4, cr4);
-	__write_cr4(cr4);
+	__cr4_set(cr4 ^ mask);
 }
 
 /* Read the CR4 shadow. */
diff --git a/arch/x86/include/uapi/asm/Kbuild b/arch/x86/include/uapi/asm/Kbuild
index da1489cb64dc..1e901e421f2d 100644
--- a/arch/x86/include/uapi/asm/Kbuild
+++ b/arch/x86/include/uapi/asm/Kbuild
@@ -1,6 +1,7 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += bpf_perf_event.h
 generated-y += unistd_32.h
 generated-y += unistd_64.h
 generated-y += unistd_x32.h
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 6a823a25eaff..750449152b04 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -542,8 +542,8 @@ error:
 }
 
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
-void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
-			   struct irq_data *irqd, int ind)
+static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
+				  struct irq_data *irqd, int ind)
 {
 	unsigned int cpu, vector, prev_cpu, prev_vector;
 	struct apic_chip_data *apicd;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d58184b7cd44..bcb75dc97d44 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -804,8 +804,11 @@ static void init_amd(struct cpuinfo_x86 *c)
 	case 0x17: init_amd_zn(c); break;
 	}
 
-	/* Enable workaround for FXSAVE leak */
-	if (c->x86 >= 6)
+	/*
+	 * Enable workaround for FXSAVE leak on CPUs
+	 * without a XSaveErPtr feature
+	 */
+	if ((c->x86 >= 6) && (!cpu_has(c, X86_FEATURE_XSAVEERPTR)))
 		set_cpu_bug(c, X86_BUG_FXSAVE_LEAK);
 
 	cpu_detect_cache_sizes(c);
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index c6daec4bdba5..330b8462d426 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -470,6 +470,7 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 #define F14H_MPB_MAX_SIZE 1824
 #define F15H_MPB_MAX_SIZE 4096
 #define F16H_MPB_MAX_SIZE 3458
+#define F17H_MPB_MAX_SIZE 3200
 
 	switch (family) {
 	case 0x14:
@@ -481,6 +482,9 @@ static unsigned int verify_patch_size(u8 family, u32 patch_size,
 	case 0x16:
 		max_size = F16H_MPB_MAX_SIZE;
 		break;
+	case 0x17:
+		max_size = F17H_MPB_MAX_SIZE;
+		break;
 	default:
 		max_size = F1XH_MPB_MAX_SIZE;
 		break;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 97fb3e5737f5..bb988a24db92 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -299,7 +299,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
 	}
 
 	if ((tifp ^ tifn) & _TIF_NOTSC)
-		cr4_toggle_bits(X86_CR4_TSD);
+		cr4_toggle_bits_irqsoff(X86_CR4_TSD);
 
 	if ((tifp ^ tifn) & _TIF_NOCPUID)
 		set_cpuid_faulting(!!(tifn & _TIF_NOCPUID));
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 3d01df7d7cf6..05a97d5fe298 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -237,7 +237,7 @@ static void notrace start_secondary(void *unused)
 	load_cr3(swapper_pg_dir);
 	__flush_tlb_all();
 #endif
-
+	load_current_idt();
 	cpu_init();
 	x86_cpuinit.early_percpu_clock_init();
 	preempt_disable();
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index cdc70a3a6583..c2cea6651279 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -44,7 +44,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
 	[CPUID_8086_0001_EDX] = {0x80860001, 0, CPUID_EDX},
 	[CPUID_1_ECX]         = {         1, 0, CPUID_ECX},
 	[CPUID_C000_0001_EDX] = {0xc0000001, 0, CPUID_EDX},
-	[CPUID_8000_0001_ECX] = {0xc0000001, 0, CPUID_ECX},
+	[CPUID_8000_0001_ECX] = {0x80000001, 0, CPUID_ECX},
 	[CPUID_7_0_EBX]       = {         7, 0, CPUID_EBX},
 	[CPUID_D_1_EAX]       = {       0xd, 1, CPUID_EAX},
 	[CPUID_F_0_EDX]       = {       0xf, 0, CPUID_EDX},
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 8079d141792a..abe74f779f9d 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -1046,7 +1046,6 @@ static void fetch_register_operand(struct operand *op)
 
 static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %%xmm0, %0" : "=m"(*data)); break;
 	case 1: asm("movdqa %%xmm1, %0" : "=m"(*data)); break;
@@ -1068,13 +1067,11 @@ static void read_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data, int reg)
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 			  int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movdqa %0, %%xmm0" : : "m"(*data)); break;
 	case 1: asm("movdqa %0, %%xmm1" : : "m"(*data)); break;
@@ -1096,12 +1093,10 @@ static void write_sse_reg(struct x86_emulate_ctxt *ctxt, sse128_t *data,
 #endif
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %%mm0, %0" : "=m"(*data)); break;
 	case 1: asm("movq %%mm1, %0" : "=m"(*data)); break;
@@ -1113,12 +1108,10 @@ static void read_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %%mm7, %0" : "=m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 {
-	ctxt->ops->get_fpu(ctxt);
 	switch (reg) {
 	case 0: asm("movq %0, %%mm0" : : "m"(*data)); break;
 	case 1: asm("movq %0, %%mm1" : : "m"(*data)); break;
@@ -1130,7 +1123,6 @@ static void write_mmx_reg(struct x86_emulate_ctxt *ctxt, u64 *data, int reg)
 	case 7: asm("movq %0, %%mm7" : : "m"(*data)); break;
 	default: BUG();
 	}
-	ctxt->ops->put_fpu(ctxt);
 }
 
 static int em_fninit(struct x86_emulate_ctxt *ctxt)
@@ -1138,9 +1130,7 @@ static int em_fninit(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fninit");
-	ctxt->ops->put_fpu(ctxt);
 	return X86EMUL_CONTINUE;
 }
 
@@ -1151,9 +1141,7 @@ static int em_fnstcw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstcw %0": "+m"(fcw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fcw;
 
@@ -1167,9 +1155,7 @@ static int em_fnstsw(struct x86_emulate_ctxt *ctxt)
 	if (ctxt->ops->get_cr(ctxt, 0) & (X86_CR0_TS | X86_CR0_EM))
 		return emulate_nm(ctxt);
 
-	ctxt->ops->get_fpu(ctxt);
 	asm volatile("fnstsw %0": "+m"(fsw));
-	ctxt->ops->put_fpu(ctxt);
 
 	ctxt->dst.val = fsw;
 
@@ -4001,12 +3987,8 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
 
-	ctxt->ops->put_fpu(ctxt);
-
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
@@ -4014,6 +3996,26 @@ static int em_fxsave(struct x86_emulate_ctxt *ctxt)
 		                   fxstate_size(ctxt));
 }
 
+/*
+ * FXRSTOR might restore XMM registers not provided by the guest. Fill
+ * in the host registers (via FXSAVE) instead, so they won't be modified.
+ * (preemption has to stay disabled until FXRSTOR).
+ *
+ * Use noinline to keep the stack for other functions called by callers small.
+ */
+static noinline int fxregs_fixup(struct fxregs_state *fx_state,
+				 const size_t used_size)
+{
+	struct fxregs_state fx_tmp;
+	int rc;
+
+	rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_tmp));
+	memcpy((void *)fx_state + used_size, (void *)&fx_tmp + used_size,
+	       __fxstate_size(16) - used_size);
+
+	return rc;
+}
+
 static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 {
 	struct fxregs_state fx_state;
@@ -4024,19 +4026,17 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 
-	ctxt->ops->get_fpu(ctxt);
-
 	size = fxstate_size(ctxt);
+	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
+	if (rc != X86EMUL_CONTINUE)
+		return rc;
+
 	if (size < __fxstate_size(16)) {
-		rc = asm_safe("fxsave %[fx]", , [fx] "+m"(fx_state));
+		rc = fxregs_fixup(&fx_state, size);
 		if (rc != X86EMUL_CONTINUE)
 			goto out;
 	}
 
-	rc = segmented_read_std(ctxt, ctxt->memop.addr.mem, &fx_state, size);
-	if (rc != X86EMUL_CONTINUE)
-		goto out;
-
 	if (fx_state.mxcsr >> 16) {
 		rc = emulate_gp(ctxt, 0);
 		goto out;
@@ -4046,8 +4046,6 @@ static int em_fxrstor(struct x86_emulate_ctxt *ctxt)
 		rc = asm_safe("fxrstor %[fx]", : [fx] "m"(fx_state));
 
 out:
-	ctxt->ops->put_fpu(ctxt);
-
 	return rc;
 }
 
@@ -5000,6 +4998,8 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	bool op_prefix = false;
 	bool has_seg_override = false;
 	struct opcode opcode;
+	u16 dummy;
+	struct desc_struct desc;
 
 	ctxt->memop.type = OP_NONE;
 	ctxt->memopp = NULL;
@@ -5018,6 +5018,11 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len)
 	switch (mode) {
 	case X86EMUL_MODE_REAL:
 	case X86EMUL_MODE_VM86:
+		def_op_bytes = def_ad_bytes = 2;
+		ctxt->ops->get_segment(ctxt, &dummy, &desc, NULL, VCPU_SREG_CS);
+		if (desc.d)
+			def_op_bytes = def_ad_bytes = 4;
+		break;
 	case X86EMUL_MODE_PROT16:
 		def_op_bytes = def_ad_bytes = 2;
 		break;
@@ -5290,9 +5295,7 @@ static int flush_pending_x87_faults(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 
-	ctxt->ops->get_fpu(ctxt);
 	rc = asm_safe("fwait");
-	ctxt->ops->put_fpu(ctxt);
 
 	if (unlikely(rc != X86EMUL_CONTINUE))
 		return emulate_exception(ctxt, MF_VECTOR, 0, false);
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index bdff437acbcb..4e822ad363f3 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -209,12 +209,12 @@ static int ioapic_set_irq(struct kvm_ioapic *ioapic, unsigned int irq,
 
 	old_irr = ioapic->irr;
 	ioapic->irr |= mask;
-	if (edge)
+	if (edge) {
 		ioapic->irr_delivered &= ~mask;
-	if ((edge && old_irr == ioapic->irr) ||
-	    (!edge && entry.fields.remote_irr)) {
-		ret = 0;
-		goto out;
+		if (old_irr == ioapic->irr) {
+			ret = 0;
+			goto out;
+		}
 	}
 
 	ret = ioapic_service(ioapic, irq, line_status);
@@ -257,8 +257,7 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
 		    index == RTC_GSI) {
 			if (kvm_apic_match_dest(vcpu, NULL, 0,
 			             e->fields.dest_id, e->fields.dest_mode) ||
-			    (e->fields.trig_mode == IOAPIC_EDGE_TRIG &&
-			     kvm_apic_pending_eoi(vcpu, e->fields.vector)))
+			    kvm_apic_pending_eoi(vcpu, e->fields.vector))
 				__set_bit(e->fields.vector,
 					  ioapic_handled_vectors);
 		}
@@ -277,6 +276,7 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 {
 	unsigned index;
 	bool mask_before, mask_after;
+	int old_remote_irr, old_delivery_status;
 	union kvm_ioapic_redirect_entry *e;
 
 	switch (ioapic->ioregsel) {
@@ -299,14 +299,28 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
 			return;
 		e = &ioapic->redirtbl[index];
 		mask_before = e->fields.mask;
+		/* Preserve read-only fields */
+		old_remote_irr = e->fields.remote_irr;
+		old_delivery_status = e->fields.delivery_status;
 		if (ioapic->ioregsel & 1) {
 			e->bits &= 0xffffffff;
 			e->bits |= (u64) val << 32;
 		} else {
 			e->bits &= ~0xffffffffULL;
 			e->bits |= (u32) val;
-			e->fields.remote_irr = 0;
 		}
+		e->fields.remote_irr = old_remote_irr;
+		e->fields.delivery_status = old_delivery_status;
+
+		/*
+		 * Some OSes (Linux, Xen) assume that Remote IRR bit will
+		 * be cleared by IOAPIC hardware when the entry is configured
+		 * as edge-triggered. This behavior is used to simulate an
+		 * explicit EOI on IOAPICs that don't have the EOI register.
+		 */
+		if (e->fields.trig_mode == IOAPIC_EDGE_TRIG)
+			e->fields.remote_irr = 0;
+
 		mask_after = e->fields.mask;
 		if (mask_before != mask_after)
 			kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
@@ -324,7 +338,9 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 	struct kvm_lapic_irq irqe;
 	int ret;
 
-	if (entry->fields.mask)
+	if (entry->fields.mask ||
+	    (entry->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+	    entry->fields.remote_irr))
 		return -1;
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 943acbf00c69..e2c1fb8d35ce 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -266,9 +266,14 @@ static inline void kvm_apic_set_ldr(struct kvm_lapic *apic, u32 id)
 	recalculate_apic_map(apic->vcpu->kvm);
 }
 
+static inline u32 kvm_apic_calc_x2apic_ldr(u32 id)
+{
+	return ((id >> 4) << 16) | (1 << (id & 0xf));
+}
+
 static inline void kvm_apic_set_x2apic_id(struct kvm_lapic *apic, u32 id)
 {
-	u32 ldr = ((id >> 4) << 16) | (1 << (id & 0xf));
+	u32 ldr = kvm_apic_calc_x2apic_ldr(id);
 
 	WARN_ON_ONCE(id != apic->vcpu->vcpu_id);
 
@@ -2245,6 +2250,7 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 {
 	if (apic_x2apic_mode(vcpu->arch.apic)) {
 		u32 *id = (u32 *)(s->regs + APIC_ID);
+		u32 *ldr = (u32 *)(s->regs + APIC_LDR);
 
 		if (vcpu->kvm->arch.x2apic_format) {
 			if (*id != vcpu->vcpu_id)
@@ -2255,6 +2261,10 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
 			else
 				*id <<= 24;
 		}
+
+		/* In x2APIC mode, the LDR is fixed and based on the id */
+		if (set)
+			*ldr = kvm_apic_calc_x2apic_ldr(*id);
 	}
 
 	return 0;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 59e13a79c2e3..eb714f1cdf7e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -361,6 +361,7 @@ static void recalc_intercepts(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *c, *h;
 	struct nested_state *g;
+	u32 h_intercept_exceptions;
 
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 
@@ -371,9 +372,14 @@ static void recalc_intercepts(struct vcpu_svm *svm)
 	h = &svm->nested.hsave->control;
 	g = &svm->nested;
 
+	/* No need to intercept #UD if L1 doesn't intercept it */
+	h_intercept_exceptions =
+		h->intercept_exceptions & ~(1U << UD_VECTOR);
+
 	c->intercept_cr = h->intercept_cr | g->intercept_cr;
 	c->intercept_dr = h->intercept_dr | g->intercept_dr;
-	c->intercept_exceptions = h->intercept_exceptions | g->intercept_exceptions;
+	c->intercept_exceptions =
+		h_intercept_exceptions | g->intercept_exceptions;
 	c->intercept = h->intercept | g->intercept;
 }
 
@@ -2196,7 +2202,10 @@ static int ud_interception(struct vcpu_svm *svm)
 {
 	int er;
 
+	WARN_ON_ONCE(is_guest_mode(&svm->vcpu));
 	er = emulate_instruction(&svm->vcpu, EMULTYPE_TRAP_UD);
+	if (er == EMULATE_USER_EXIT)
+		return 0;
 	if (er != EMULATE_DONE)
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 714a0673ec3c..8eba631c4dbd 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1887,7 +1887,7 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 {
 	u32 eb;
 
-	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR) | (1u << MC_VECTOR) |
+	eb = (1u << PF_VECTOR) | (1u << MC_VECTOR) |
 	     (1u << DB_VECTOR) | (1u << AC_VECTOR);
 	if ((vcpu->guest_debug &
 	     (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)) ==
@@ -1905,6 +1905,8 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	 */
 	if (is_guest_mode(vcpu))
 		eb |= get_vmcs12(vcpu)->exception_bitmap;
+	else
+		eb |= 1u << UD_VECTOR;
 
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
@@ -5600,7 +5602,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 	}
 
-	vmcs_writel(GUEST_RFLAGS, 0x02);
+	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
 	kvm_rip_write(vcpu, 0xfff0);
 
 	vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -5915,11 +5917,10 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		return 1;  /* already handled by vmx_vcpu_run() */
 
 	if (is_invalid_opcode(intr_info)) {
-		if (is_guest_mode(vcpu)) {
-			kvm_queue_exception(vcpu, UD_VECTOR);
-			return 1;
-		}
+		WARN_ON_ONCE(is_guest_mode(vcpu));
 		er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
+		if (er == EMULATE_USER_EXIT)
+			return 0;
 		if (er != EMULATE_DONE)
 			kvm_queue_exception(vcpu, UD_VECTOR);
 		return 1;
@@ -6602,7 +6603,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
 			return 1;
 
-		err = emulate_instruction(vcpu, EMULTYPE_NO_REEXECUTE);
+		err = emulate_instruction(vcpu, 0);
 
 		if (err == EMULATE_USER_EXIT) {
 			++vcpu->stat.mmio_exits;
@@ -6750,16 +6751,10 @@ static __init int hardware_setup(void)
 			goto out;
 	}
 
-	vmx_io_bitmap_b = (unsigned long *)__get_free_page(GFP_KERNEL);
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
 
-	/*
-	 * Allow direct access to the PC debug port (it is often used for I/O
-	 * delays, but the vmexits simply slow things down).
-	 */
 	memset(vmx_io_bitmap_a, 0xff, PAGE_SIZE);
-	clear_bit(0x80, vmx_io_bitmap_a);
 
 	memset(vmx_io_bitmap_b, 0xff, PAGE_SIZE);
 
@@ -7414,10 +7409,11 @@ static inline void nested_release_vmcs12(struct vcpu_vmx *vmx)
  */
 static void free_nested(struct vcpu_vmx *vmx)
 {
-	if (!vmx->nested.vmxon)
+	if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
 		return;
 
 	vmx->nested.vmxon = false;
+	vmx->nested.smm.vmxon = false;
 	free_vpid(vmx->nested.vpid02);
 	vmx->nested.posted_intr_nv = -1;
 	vmx->nested.current_vmptr = -1ull;
@@ -9800,8 +9796,7 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_SMEP,       ebx, bit(X86_FEATURE_SMEP));
 	cr4_fixed1_update(X86_CR4_SMAP,       ebx, bit(X86_FEATURE_SMAP));
 	cr4_fixed1_update(X86_CR4_PKE,        ecx, bit(X86_FEATURE_PKU));
-	/* TODO: Use X86_CR4_UMIP and X86_FEATURE_UMIP macros */
-	cr4_fixed1_update(bit(11),            ecx, bit(2));
+	cr4_fixed1_update(X86_CR4_UMIP,       ecx, bit(X86_FEATURE_UMIP));
 
 #undef cr4_fixed1_update
 }
@@ -10875,6 +10870,11 @@ static int check_vmentry_postreqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 			return 1;
 	}
 
+	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS) &&
+		(is_noncanonical_address(vmcs12->guest_bndcfgs & PAGE_MASK, vcpu) ||
+		(vmcs12->guest_bndcfgs & MSR_IA32_BNDCFGS_RSVD)))
+			return 1;
+
 	return 0;
 }
 
@@ -11099,13 +11099,12 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long exit_qual;
-
-	if (kvm_event_needs_reinjection(vcpu))
-		return -EBUSY;
+	bool block_nested_events =
+	    vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
 
 	if (vcpu->arch.exception.pending &&
 		nested_vmx_check_exception(vcpu, &exit_qual)) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
 		vcpu->arch.exception.pending = false;
@@ -11114,14 +11113,14 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 
 	if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
 	    vmx->nested.preemption_timer_expired) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
 		return 0;
 	}
 
 	if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 				  NMI_VECTOR | INTR_TYPE_NMI_INTR |
@@ -11137,7 +11136,7 @@ static int vmx_check_nested_events(struct kvm_vcpu *vcpu, bool external_intr)
 
 	if ((kvm_cpu_has_interrupt(vcpu) || external_intr) &&
 	    nested_exit_on_intr(vcpu)) {
-		if (vmx->nested.nested_run_pending)
+		if (block_nested_events)
 			return -EBUSY;
 		nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
 		return 0;
@@ -11324,6 +11323,24 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	kvm_clear_interrupt_queue(vcpu);
 }
 
+static void load_vmcs12_mmu_host_state(struct kvm_vcpu *vcpu,
+			struct vmcs12 *vmcs12)
+{
+	u32 entry_failure_code;
+
+	nested_ept_uninit_mmu_context(vcpu);
+
+	/*
+	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
+	 * couldn't have changed.
+	 */
+	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
+
+	if (!enable_ept)
+		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+}
+
 /*
  * A part of what we need to when the nested L2 guest exits and we want to
  * run its L1 parent, is to reset L1's guest state to the host state specified
@@ -11337,7 +11354,6 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 				   struct vmcs12 *vmcs12)
 {
 	struct kvm_segment seg;
-	u32 entry_failure_code;
 
 	if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
 		vcpu->arch.efer = vmcs12->host_ia32_efer;
@@ -11364,17 +11380,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
 	vmx_set_cr4(vcpu, vmcs12->host_cr4);
 
-	nested_ept_uninit_mmu_context(vcpu);
-
-	/*
-	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
-	 * couldn't have changed.
-	 */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
-		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
-
-	if (!enable_ept)
-		vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
+	load_vmcs12_mmu_host_state(vcpu, vmcs12);
 
 	if (enable_vpid) {
 		/*
@@ -11604,6 +11610,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	 * accordingly.
 	 */
 	nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+	load_vmcs12_mmu_host_state(vcpu, vmcs12);
+
 	/*
 	 * The emulated instruction was already skipped in
 	 * nested_vmx_run, but the updated RIP was never
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 34c85aa2e2d1..faf843c9b916 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -107,6 +107,9 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
 static bool __read_mostly ignore_msrs = 0;
 module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
 
+static bool __read_mostly report_ignored_msrs = true;
+module_param(report_ignored_msrs, bool, S_IRUGO | S_IWUSR);
+
 unsigned int min_timer_period_us = 500;
 module_param(min_timer_period_us, uint, S_IRUGO | S_IWUSR);
 
@@ -1795,10 +1798,13 @@ u64 get_kvmclock_ns(struct kvm *kvm)
 	/* both __this_cpu_read() and rdtsc() should be on the same cpu */
 	get_cpu();
 
-	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
-			   &hv_clock.tsc_shift,
-			   &hv_clock.tsc_to_system_mul);
-	ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+	if (__this_cpu_read(cpu_tsc_khz)) {
+		kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+				   &hv_clock.tsc_shift,
+				   &hv_clock.tsc_to_system_mul);
+		ret = __pvclock_read_cycles(&hv_clock, rdtsc());
+	} else
+		ret = ktime_get_boot_ns() + ka->kvmclock_offset;
 
 	put_cpu();
 
@@ -1830,6 +1836,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
 	 */
 	BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
 
+	if (guest_hv_clock.version & 1)
+		++guest_hv_clock.version;  /* first time write, random junk */
+
 	vcpu->hv_clock.version = guest_hv_clock.version + 1;
 	kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
 				&vcpu->hv_clock,
@@ -2322,7 +2331,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Drop writes to this legacy MSR -- see rdmsr
 		 * counterpart for further detail.
 		 */
-		vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n", msr, data);
+		if (report_ignored_msrs)
+			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
+				msr, data);
 		break;
 	case MSR_AMD64_OSVW_ID_LENGTH:
 		if (!guest_cpuid_has(vcpu, X86_FEATURE_OSVW))
@@ -2359,8 +2370,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 				    msr, data);
 			return 1;
 		} else {
-			vcpu_unimpl(vcpu, "ignored wrmsr: 0x%x data 0x%llx\n",
-				    msr, data);
+			if (report_ignored_msrs)
+				vcpu_unimpl(vcpu,
+					"ignored wrmsr: 0x%x data 0x%llx\n",
+					msr, data);
 			break;
 		}
 	}
@@ -2578,7 +2591,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					       msr_info->index);
 			return 1;
 		} else {
-			vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr_info->index);
+			if (report_ignored_msrs)
+				vcpu_unimpl(vcpu, "ignored rdmsr: 0x%x\n",
+					msr_info->index);
 			msr_info->data = 0;
 		}
 		break;
@@ -2922,7 +2937,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	pagefault_enable();
 	kvm_x86_ops->vcpu_put(vcpu);
-	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();
 }
 
@@ -5237,17 +5251,6 @@ static void emulator_halt(struct x86_emulate_ctxt *ctxt)
 	emul_to_vcpu(ctxt)->arch.halt_request = 1;
 }
 
-static void emulator_get_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_disable();
-	kvm_load_guest_fpu(emul_to_vcpu(ctxt));
-}
-
-static void emulator_put_fpu(struct x86_emulate_ctxt *ctxt)
-{
-	preempt_enable();
-}
-
 static int emulator_intercept(struct x86_emulate_ctxt *ctxt,
 			      struct x86_instruction_info *info,
 			      enum x86_intercept_stage stage)
@@ -5325,8 +5328,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.halt                = emulator_halt,
 	.wbinvd              = emulator_wbinvd,
 	.fix_hypercall       = emulator_fix_hypercall,
-	.get_fpu             = emulator_get_fpu,
-	.put_fpu             = emulator_put_fpu,
 	.intercept           = emulator_intercept,
 	.get_cpuid           = emulator_get_cpuid,
 	.set_nmi_mask        = emulator_set_nmi_mask,
@@ -5430,7 +5431,7 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu)
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
 		vcpu->run->internal.ndata = 0;
-		r = EMULATE_FAIL;
+		r = EMULATE_USER_EXIT;
 	}
 	kvm_queue_exception(vcpu, UD_VECTOR);
 
@@ -5722,6 +5723,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 			if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
 						emulation_type))
 				return EMULATE_DONE;
+			if (ctxt->have_exception && inject_emulated_exception(vcpu))
+				return EMULATE_DONE;
 			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
 			return handle_emulation_failure(vcpu);
@@ -6761,6 +6764,20 @@ static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->tlb_flush(vcpu);
 }
 
+void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+		unsigned long start, unsigned long end)
+{
+	unsigned long apic_address;
+
+	/*
+	 * The physical address of apic access page is stored in the VMCS.
+	 * Update it when it becomes invalid.
+	 */
+	apic_address = gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
+	if (start <= apic_address && apic_address < end)
+		kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
 {
 	struct page *page = NULL;
@@ -6935,7 +6952,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	preempt_disable();
 
 	kvm_x86_ops->prepare_guest_switch(vcpu);
-	kvm_load_guest_fpu(vcpu);
 
 	/*
 	 * Disable IRQs before setting IN_GUEST_MODE.  Posted interrupt
@@ -7250,12 +7266,10 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct fpu *fpu = &current->thread.fpu;
 	int r;
-	sigset_t sigsaved;
 
 	fpu__initialize(fpu);
 
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
+	kvm_sigset_activate(vcpu);
 
 	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
 		if (kvm_run->immediate_exit) {
@@ -7282,12 +7296,14 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		}
 	}
 
+	kvm_load_guest_fpu(vcpu);
+
 	if (unlikely(vcpu->arch.complete_userspace_io)) {
 		int (*cui)(struct kvm_vcpu *) = vcpu->arch.complete_userspace_io;
 		vcpu->arch.complete_userspace_io = NULL;
 		r = cui(vcpu);
 		if (r <= 0)
-			goto out;
+			goto out_fpu;
 	} else
 		WARN_ON(vcpu->arch.pio.count || vcpu->mmio_needed);
 
@@ -7296,10 +7312,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	else
 		r = vcpu_run(vcpu);
 
+out_fpu:
+	kvm_put_guest_fpu(vcpu);
 out:
 	post_kvm_run_save(vcpu);
-	if (vcpu->sigset_active)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+	kvm_sigset_deactivate(vcpu);
 
 	return r;
 }
@@ -7690,32 +7707,25 @@ static void fx_init(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr0 |= X86_CR0_ET;
 }
 
+/* Swap (qemu) user FPU context for the guest FPU context. */
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (vcpu->guest_fpu_loaded)
-		return;
-
-	/*
-	 * Restore all possible states in the guest,
-	 * and assume host would use all available bits.
-	 * Guest xcr0 would be loaded later.
-	 */
-	vcpu->guest_fpu_loaded = 1;
-	__kernel_fpu_begin();
+	preempt_disable();
+	copy_fpregs_to_fpstate(&vcpu->arch.user_fpu);
 	/* PKRU is separately restored in kvm_x86_ops->run.  */
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state,
 				~XFEATURE_MASK_PKRU);
+	preempt_enable();
 	trace_kvm_fpu(1);
 }
 
+/* When vcpu_run ends, restore user space FPU context. */
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->guest_fpu_loaded)
-		return;
-
-	vcpu->guest_fpu_loaded = 0;
+	preempt_disable();
 	copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
-	__kernel_fpu_end();
+	copy_kernel_to_fpregs(&vcpu->arch.user_fpu.state);
+	preempt_enable();
 	++vcpu->stat.fpu_reload;
 	trace_kvm_fpu(0);
 }
@@ -7832,7 +7842,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		 * To avoid have the INIT path from kvm_apic_has_events() that be
 		 * called with loaded FPU and does not let userspace fix the state.
 		 */
-		kvm_put_guest_fpu(vcpu);
+		if (init_event)
+			kvm_put_guest_fpu(vcpu);
 		mpx_state_buffer = get_xsave_addr(&vcpu->arch.guest_fpu.state.xsave,
 					XFEATURE_MASK_BNDREGS);
 		if (mpx_state_buffer)
@@ -7841,6 +7852,8 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 					XFEATURE_MASK_BNDCSR);
 		if (mpx_state_buffer)
 			memset(mpx_state_buffer, 0, sizeof(struct mpx_bndcsr));
+		if (init_event)
+			kvm_load_guest_fpu(vcpu);
 	}
 
 	if (!init_event) {
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 3321b446b66c..9fe656c42aa5 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -1,6 +1,7 @@
 #include <linux/extable.h>
 #include <linux/uaccess.h>
 #include <linux/sched/debug.h>
+#include <xen/xen.h>
 
 #include <asm/fpu/internal.h>
 #include <asm/traps.h>
@@ -82,7 +83,7 @@ bool ex_handler_refcount(const struct exception_table_entry *fixup,
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(ex_handler_refcount);
+EXPORT_SYMBOL(ex_handler_refcount);
 
 /*
  * Handler for when we fail to restore a task's FPU state.  We should never get
@@ -212,8 +213,9 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 	 * Old CPUs leave the high bits of CS on the stack
 	 * undefined.  I'm not sure which CPUs do this, but at least
 	 * the 486 DX works this way.
+	 * Xen pv domains are not using the default __KERNEL_CS.
 	 */
-	if (regs->cs != __KERNEL_CS)
+	if (!xen_pv_domain() && regs->cs != __KERNEL_CS)
 		goto fail;
 
 	/*
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 78ca9a8ee454..febf6980e653 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -701,7 +701,7 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 	else
 		printk(KERN_CONT "paging request");
 
-	printk(KERN_CONT " at %p\n", (void *) address);
+	printk(KERN_CONT " at %px\n", (void *) address);
 	printk(KERN_ALERT "IP: %pS\n", (void *)regs->ip);
 
 	dump_pagetable(address);
diff --git a/arch/x86/mm/kmemcheck/error.c b/arch/x86/mm/kmemcheck/error.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/error.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/error.h b/arch/x86/mm/kmemcheck/error.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/error.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/opcode.c b/arch/x86/mm/kmemcheck/opcode.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/opcode.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/opcode.h b/arch/x86/mm/kmemcheck/opcode.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/opcode.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/pte.c b/arch/x86/mm/kmemcheck/pte.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/pte.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/pte.h b/arch/x86/mm/kmemcheck/pte.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/pte.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/selftest.c b/arch/x86/mm/kmemcheck/selftest.c
deleted file mode 100644
index cec594032515..000000000000
--- a/arch/x86/mm/kmemcheck/selftest.c
+++ /dev/null
@@ -1 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
diff --git a/arch/x86/mm/kmemcheck/selftest.h b/arch/x86/mm/kmemcheck/selftest.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/selftest.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/mm/kmemcheck/shadow.h b/arch/x86/mm/kmemcheck/shadow.h
deleted file mode 100644
index ea32a7d3cf1b..000000000000
--- a/arch/x86/mm/kmemcheck/shadow.h
+++ /dev/null
@@ -1 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c
index bb461cfd01ab..526536c81ddc 100644
--- a/arch/x86/pci/broadcom_bus.c
+++ b/arch/x86/pci/broadcom_bus.c
@@ -97,7 +97,7 @@ static int __init broadcom_postcore_init(void)
 	 * We should get host bridge information from ACPI unless the BIOS
 	 * doesn't support it.
 	 */
-	if (acpi_os_get_root_pointer())
+	if (!acpi_disabled && acpi_os_get_root_pointer())
 		return 0;
 #endif
 
diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c
index c34bd8233f7c..5f64f30873e2 100644
--- a/arch/x86/platform/uv/uv_nmi.c
+++ b/arch/x86/platform/uv/uv_nmi.c
@@ -905,7 +905,7 @@ static inline void uv_call_kgdb_kdb(int cpu, struct pt_regs *regs, int master)
 /*
  * UV NMI handler
  */
-int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
+static int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 {
 	struct uv_hub_nmi_s *hub_nmi = uv_hub_nmi;
 	int cpu = smp_processor_id();
@@ -1013,7 +1013,7 @@ void uv_nmi_init(void)
 }
 
 /* Setup HUB NMI info */
-void __init uv_nmi_setup_common(bool hubbed)
+static void __init uv_nmi_setup_common(bool hubbed)
 {
 	int size = sizeof(void *) * (1 << NODES_SHIFT);
 	int cpu;
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 84fcfde53f8f..5191de14f4df 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -226,8 +226,20 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	load_idt((const struct desc_ptr *)&ctxt->idt_limit);
 #endif
 
+#ifdef CONFIG_X86_64
 	/*
-	 * segment registers
+	 * We need GSBASE restored before percpu access can work.
+	 * percpu access can happen in exception handlers or in complicated
+	 * helpers like load_gs_index().
+	 */
+	wrmsrl(MSR_GS_BASE, ctxt->gs_base);
+#endif
+
+	fix_processor_context();
+
+	/*
+	 * Restore segment registers.  This happens after restoring the GDT
+	 * and LDT, which happen in fix_processor_context().
 	 */
 #ifdef CONFIG_X86_32
 	loadsegment(es, ctxt->es);
@@ -248,13 +260,14 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
 	load_gs_index(ctxt->gs);
 	asm volatile ("movw %0, %%ss" :: "r" (ctxt->ss));
 
+	/*
+	 * Restore FSBASE and user GSBASE after reloading the respective
+	 * segment selectors.
+	 */
 	wrmsrl(MSR_FS_BASE, ctxt->fs_base);
-	wrmsrl(MSR_GS_BASE, ctxt->gs_base);
 	wrmsrl(MSR_KERNEL_GS_BASE, ctxt->gs_kernel_base);
 #endif
 
-	fix_processor_context();
-
 	do_fpu_end();
 	tsc_verify_tsc_adjust(true);
 	x86_platform.restore_sched_clock_state();
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 5b2b3f3f6531..f2414c6c5e7c 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -622,7 +622,7 @@ static struct trap_array_entry trap_array[] = {
 	{ simd_coprocessor_error,      xen_simd_coprocessor_error,      false },
 };
 
-static bool get_trap_addr(void **addr, unsigned int ist)
+static bool __ref get_trap_addr(void **addr, unsigned int ist)
 {
 	unsigned int nr;
 	bool ist_okay = false;
@@ -644,6 +644,14 @@ static bool get_trap_addr(void **addr, unsigned int ist)
 		}
 	}
 
+	if (nr == ARRAY_SIZE(trap_array) &&
+	    *addr >= (void *)early_idt_handler_array[0] &&
+	    *addr < (void *)early_idt_handler_array[NUM_EXCEPTION_VECTORS]) {
+		nr = (*addr - (void *)early_idt_handler_array[0]) /
+		     EARLY_IDT_HANDLER_SIZE;
+		*addr = (void *)xen_early_idt_handler_array[nr];
+	}
+
 	if (WARN_ON(ist != 0 && !ist_okay))
 		return false;
 
@@ -1262,6 +1270,21 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	xen_setup_gdt(0);
 
 	xen_init_irq_ops();
+
+	/* Let's presume PV guests always boot on vCPU with id 0. */
+	per_cpu(xen_vcpu_id, 0) = 0;
+
+	/*
+	 * Setup xen_vcpu early because idt_setup_early_handler needs it for
+	 * local_irq_disable(), irqs_disabled().
+	 *
+	 * Don't do the full vcpu_info placement stuff until we have
+	 * the cpu_possible_mask and a non-dummy shared_info.
+	 */
+	xen_vcpu_info_reset(0);
+
+	idt_setup_early_handler();
+
 	xen_init_capabilities();
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -1295,18 +1318,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	 */
 	acpi_numa = -1;
 #endif
-	/* Let's presume PV guests always boot on vCPU with id 0. */
-	per_cpu(xen_vcpu_id, 0) = 0;
-
-	/*
-	 * Setup xen_vcpu early because start_kernel needs it for
-	 * local_irq_disable(), irqs_disabled().
-	 *
-	 * Don't do the full vcpu_info placement stuff until we have
-	 * the cpu_possible_mask and a non-dummy shared_info.
-	 */
-	xen_vcpu_info_reset(0);
-
 	WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
 
 	local_irq_disable();
diff --git a/arch/x86/xen/xen-asm_64.S b/arch/x86/xen/xen-asm_64.S
index 8a10c9a9e2b5..417b339e5c8e 100644
--- a/arch/x86/xen/xen-asm_64.S
+++ b/arch/x86/xen/xen-asm_64.S
@@ -15,6 +15,7 @@
 
 #include <xen/interface/xen.h>
 
+#include <linux/init.h>
 #include <linux/linkage.h>
 
 .macro xen_pv_trap name
@@ -54,6 +55,19 @@ xen_pv_trap entry_INT80_compat
 #endif
 xen_pv_trap hypervisor_callback
 
+	__INIT
+ENTRY(xen_early_idt_handler_array)
+	i = 0
+	.rept NUM_EXCEPTION_VECTORS
+	pop %rcx
+	pop %r11
+	jmp early_idt_handler_array + i*EARLY_IDT_HANDLER_SIZE
+	i = i + 1
+	.fill xen_early_idt_handler_array + i*XEN_EARLY_IDT_HANDLER_SIZE - ., 1, 0xcc
+	.endr
+END(xen_early_idt_handler_array)
+	__FINIT
+
 hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
 /*
  * Xen64 iret frame: