18 files changed, 126 insertions, 36 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 6915ff2bd996..8774cb23064f 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -26,7 +26,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma \
 	vmlinux.bin.xz vmlinux.bin.lzo vmlinux.bin.lz4
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
-KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
+KBUILD_CFLAGS += -fno-strict-aliasing $(call cc-option, -fPIE, -fPIC)
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_32) := -march=i386
 cflags-$(CONFIG_X86_64) := -mcmodel=small
@@ -40,6 +40,18 @@ GCOV_PROFILE := n
 UBSAN_SANITIZE :=n
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
+ifeq ($(CONFIG_RELOCATABLE),y)
+# If kernel is relocatable, build compressed kernel as PIE.
+ifeq ($(CONFIG_X86_32),y)
+LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
+else
+# To build 64-bit compressed kernel as PIE, we disable relocation
+# overflow check to avoid relocation overflow error with a new linker
+# command-line option, -z noreloc-overflow.
+LDFLAGS += $(shell $(LD) --help 2>&1 | grep -q "\-z noreloc-overflow" \
+	&& echo "-z noreloc-overflow -pie --no-dynamic-linker")
+endif
+endif
 LDFLAGS_vmlinux := -T
 
 hostprogs-y	:= mkpiggy
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 8ef964ddc18e..0256064da8da 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -31,6 +31,34 @@
 #include <asm/asm-offsets.h>
 #include <asm/bootparam.h>
 
+/*
+ * The 32-bit x86 assembler in binutils 2.26 will generate R_386_GOT32X
+ * relocation to get the symbol address in PIC.  When the compressed x86
+ * kernel isn't built as PIC, the linker optimizes R_386_GOT32X
+ * relocations to their fixed symbol addresses.  However, when the
+ * compressed x86 kernel is loaded at a different address, it leads
+ * to the following load failure:
+ *
+ *   Failed to allocate space for phdrs
+ *
+ * during the decompression stage.
+ *
+ * If the compressed x86 kernel is relocatable at run-time, it should be
+ * compiled with -fPIE, instead of -fPIC, if possible and should be built as
+ * Position Independent Executable (PIE) so that linker won't optimize
+ * R_386_GOT32X relocation to its fixed symbol address.  Older
+ * linkers generate R_386_32 relocations against locally defined symbols,
+ * _bss, _ebss, _got and _egot, in PIE.  It isn't wrong, just less
+ * optimal than R_386_RELATIVE.  But the x86 kernel fails to properly handle
+ * R_386_32 relocations when relocating the kernel.  To generate
+ * R_386_RELATIVE relocations, we mark _bss, _ebss, _got and _egot as
+ * hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 ENTRY(startup_32)
 #ifdef CONFIG_EFI_STUB
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index b0c0d16ef58d..86558a199139 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -33,6 +33,14 @@
 #include <asm/asm-offsets.h>
 #include <asm/bootparam.h>
 
+/*
+ * Locally defined symbols should be marked hidden:
+ */
+	.hidden _bss
+	.hidden _ebss
+	.hidden _got
+	.hidden _egot
+
 	__HEAD
 	.code32
 ENTRY(startup_32)
diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c
index a8a0224fa0f8..081255cea1ee 100644
--- a/arch/x86/crypto/sha-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha-mb/sha1_mb.c
@@ -453,10 +453,10 @@ static int sha_complete_job(struct mcryptd_hash_request_ctx *rctx,
 
 			req = cast_mcryptd_ctx_to_req(req_ctx);
 			if (irqs_disabled())
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 			else {
 				local_bh_disable();
-				rctx->complete(&req->base, ret);
+				req_ctx->complete(&req->base, ret);
 				local_bh_enable();
 			}
 		}
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index f8a29d2c97b0..e6a8613fbfb0 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -4,6 +4,7 @@
 #include <asm/page.h>
 #include <asm-generic/hugetlb.h>
 
+#define hugepages_supported() cpu_has_pse
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index f62a9f37f79f..b7e394485a5f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
-#define KVM_HALT_POLL_NS_DEFAULT 500000
+#define KVM_HALT_POLL_NS_DEFAULT 400000
 
 #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 426e946ed0c0..5b3c9a55f51c 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -167,6 +167,14 @@
 #define MSR_PKG_C9_RESIDENCY		0x00000631
 #define MSR_PKG_C10_RESIDENCY		0x00000632
 
+/* Interrupt Response Limit */
+#define MSR_PKGC3_IRTL			0x0000060a
+#define MSR_PKGC6_IRTL			0x0000060b
+#define MSR_PKGC7_IRTL			0x0000060c
+#define MSR_PKGC8_IRTL			0x00000633
+#define MSR_PKGC9_IRTL			0x00000634
+#define MSR_PKGC10_IRTL			0x00000635
+
 /* Run Time Average Power Limiting (RAPL) Interface */
 
 #define MSR_RAPL_POWER_UNIT		0x00000606
diff --git a/arch/x86/kernel/cpu/mcheck/mce-genpool.c b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
index 0a850100c594..2658e2af74ec 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-genpool.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-genpool.c
@@ -29,7 +29,7 @@ static char gen_pool_buf[MCE_POOLSZ];
 void mce_gen_pool_process(void)
 {
 	struct llist_node *head;
-	struct mce_evt_llist *node;
+	struct mce_evt_llist *node, *tmp;
 	struct mce *mce;
 
 	head = llist_del_all(&mce_event_llist);
@@ -37,7 +37,7 @@ void mce_gen_pool_process(void)
 		return;
 
 	head = llist_reverse_order(head);
-	llist_for_each_entry(node, head, llnode) {
+	llist_for_each_entry_safe(node, tmp, head, llnode) {
 		mce = &node->mce;
 		atomic_notifier_call_chain(&x86_mce_decoder_chain, 0, mce);
 		gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node));
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 4e7c6933691c..10c11b4da31d 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -152,6 +152,11 @@ static struct clocksource hyperv_cs = {
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+static unsigned char hv_get_nmi_reason(void)
+{
+	return 0;
+}
+
 static void __init ms_hyperv_init_platform(void)
 {
 	/*
@@ -191,6 +196,13 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
 	mark_tsc_unstable("running on Hyper-V");
+
+	/*
+	 * Generation 2 instances don't support reading the NMI status from
+	 * 0x61 port.
+	 */
+	if (efi_enabled(EFI_BOOT))
+		x86_platform.get_nmi_reason = hv_get_nmi_reason;
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 8efb839948e5..bbbaa802d13e 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -534,6 +534,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 			do_cpuid_1_ent(&entry[i], function, idx);
 			if (idx == 1) {
 				entry[i].eax &= kvm_cpuid_D_1_eax_x86_features;
+				cpuid_mask(&entry[i].eax, CPUID_D_1_EAX);
 				entry[i].ebx = 0;
 				if (entry[i].eax & (F(XSAVES)|F(XSAVEC)))
 					entry[i].ebx =
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 5ff3485acb60..01bd7b7a6866 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1116,6 +1116,11 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		break;
 	case HVCALL_POST_MESSAGE:
 	case HVCALL_SIGNAL_EVENT:
+		/* don't bother userspace if it has no way to handle it */
+		if (!vcpu_to_synic(vcpu)->active) {
+			res = HV_STATUS_INVALID_HYPERCALL_CODE;
+			break;
+		}
 		vcpu->run->exit_reason = KVM_EXIT_HYPERV;
 		vcpu->run->hyperv.type = KVM_EXIT_HYPERV_HCALL;
 		vcpu->run->hyperv.u.hcall.input = param;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 443d2a57ad3d..1a2da0e5a373 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1369,7 +1369,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 
 		hrtimer_start(&apic->lapic_timer.timer,
 			      ktime_add_ns(now, apic->lapic_timer.period),
-			      HRTIMER_MODE_ABS);
+			      HRTIMER_MODE_ABS_PINNED);
 
 		apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
 			   PRIx64 ", "
@@ -1402,7 +1402,7 @@ static void start_apic_timer(struct kvm_lapic *apic)
 			expire = ktime_add_ns(now, ns);
 			expire = ktime_sub_ns(expire, lapic_timer_advance_ns);
 			hrtimer_start(&apic->lapic_timer.timer,
-				      expire, HRTIMER_MODE_ABS);
+				      expire, HRTIMER_MODE_ABS_PINNED);
 		} else
 			apic_timer_expired(apic);
 
@@ -1868,7 +1868,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	apic->vcpu = vcpu;
 
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
-		     HRTIMER_MODE_ABS);
+		     HRTIMER_MODE_ABS_PINNED);
 	apic->lapic_timer.timer.function = apic_timer_fn;
 
 	/*
@@ -2003,7 +2003,7 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu)
 
 	timer = &vcpu->arch.apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
-		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+		hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED);
 }
 
 /*
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 70e95d097ef1..1ff4dbb73fb7 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -557,8 +557,15 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte)
 	      !is_writable_pte(new_spte))
 		ret = true;
 
-	if (!shadow_accessed_mask)
+	if (!shadow_accessed_mask) {
+		/*
+		 * We don't set page dirty when dropping non-writable spte.
+		 * So do it now if the new spte is becoming non-writable.
+		 */
+		if (ret)
+			kvm_set_pfn_dirty(spte_to_pfn(old_spte));
 		return ret;
+	}
 
 	/*
 	 * Flush TLB when accessed/dirty bits are changed in the page tables,
@@ -605,7 +612,8 @@ static int mmu_spte_clear_track_bits(u64 *sptep)
 
 	if (!shadow_accessed_mask || old_spte & shadow_accessed_mask)
 		kvm_set_pfn_accessed(pfn);
-	if (!shadow_dirty_mask || (old_spte & shadow_dirty_mask))
+	if (old_spte & (shadow_dirty_mask ? shadow_dirty_mask :
+					    PT_WRITABLE_MASK))
 		kvm_set_pfn_dirty(pfn);
 	return 1;
 }
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index b70df72e2b33..66b33b96a31b 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -173,10 +173,9 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 	int index = (pfec >> 1) +
 		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
 	bool fault = (mmu->permissions[index] >> pte_access) & 1;
+	u32 errcode = PFERR_PRESENT_MASK;
 
 	WARN_ON(pfec & (PFERR_PK_MASK | PFERR_RSVD_MASK));
-	pfec |= PFERR_PRESENT_MASK;
-
 	if (unlikely(mmu->pkru_mask)) {
 		u32 pkru_bits, offset;
 
@@ -189,15 +188,15 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 		pkru_bits = (kvm_read_pkru(vcpu) >> (pte_pkey * 2)) & 3;
 
 		/* clear present bit, replace PFEC.RSVD with ACC_USER_MASK. */
-		offset = pfec - 1 +
+		offset = (pfec & ~1) +
 			((pte_access & PT_USER_MASK) << (PFERR_RSVD_BIT - PT_USER_SHIFT));
 
 		pkru_bits &= mmu->pkru_mask >> offset;
-		pfec |= -pkru_bits & PFERR_PK_MASK;
+		errcode |= -pkru_bits & PFERR_PK_MASK;
 		fault |= (pkru_bits != 0);
 	}
 
-	return -(uint32_t)fault & pfec;
+	return -(u32)fault & errcode;
 }
 
 void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);
diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
index 1d971c7553c3..bc019f70e0b6 100644
--- a/arch/x86/kvm/paging_tmpl.h
+++ b/arch/x86/kvm/paging_tmpl.h
@@ -360,7 +360,7 @@ retry_walk:
 			goto error;
 
 		if (unlikely(is_rsvd_bits_set(mmu, pte, walker->level))) {
-			errcode |= PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
+			errcode = PFERR_RSVD_MASK | PFERR_PRESENT_MASK;
 			goto error;
 		}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 742d0f7d3556..9b7798c7b210 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -700,7 +700,6 @@ static int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 		if ((xcr0 & XFEATURE_MASK_AVX512) != XFEATURE_MASK_AVX512)
 			return 1;
 	}
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->arch.xcr0 = xcr0;
 
 	if ((xcr0 ^ old_xcr0) & XFEATURE_MASK_EXTEND)
@@ -6095,12 +6094,10 @@ static int inject_pending_event(struct kvm_vcpu *vcpu, bool req_int_win)
 	}
 
 	/* try to inject new event if pending */
-	if (vcpu->arch.nmi_pending) {
-		if (kvm_x86_ops->nmi_allowed(vcpu)) {
-			--vcpu->arch.nmi_pending;
-			vcpu->arch.nmi_injected = true;
-			kvm_x86_ops->set_nmi(vcpu);
-		}
+	if (vcpu->arch.nmi_pending && kvm_x86_ops->nmi_allowed(vcpu)) {
+		--vcpu->arch.nmi_pending;
+		vcpu->arch.nmi_injected = true;
+		kvm_x86_ops->set_nmi(vcpu);
 	} else if (kvm_cpu_has_injectable_intr(vcpu)) {
 		/*
 		 * Because interrupts can be injected asynchronously, we are
@@ -6569,10 +6566,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (inject_pending_event(vcpu, req_int_win) != 0)
 			req_immediate_exit = true;
 		/* enable NMI/IRQ window open exits if needed */
-		else if (vcpu->arch.nmi_pending)
-			kvm_x86_ops->enable_nmi_window(vcpu);
-		else if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
-			kvm_x86_ops->enable_irq_window(vcpu);
+		else {
+			if (vcpu->arch.nmi_pending)
+				kvm_x86_ops->enable_nmi_window(vcpu);
+			if (kvm_cpu_has_injectable_intr(vcpu) || req_int_win)
+				kvm_x86_ops->enable_irq_window(vcpu);
+		}
 
 		if (kvm_lapic_enabled(vcpu)) {
 			update_cr8_intercept(vcpu);
@@ -6590,8 +6589,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->prepare_guest_switch(vcpu);
 	if (vcpu->fpu_active)
 		kvm_load_guest_fpu(vcpu);
-	kvm_load_guest_xcr0(vcpu);
-
 	vcpu->mode = IN_GUEST_MODE;
 
 	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
@@ -6618,6 +6615,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		goto cancel_injection;
 	}
 
+	kvm_load_guest_xcr0(vcpu);
+
 	if (req_immediate_exit)
 		smp_send_reschedule(vcpu->cpu);
 
@@ -6667,6 +6666,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	vcpu->mode = OUTSIDE_GUEST_MODE;
 	smp_wmb();
 
+	kvm_put_guest_xcr0(vcpu);
+
 	/* Interrupt is enabled by handle_external_intr() */
 	kvm_x86_ops->handle_external_intr(vcpu);
 
@@ -7314,7 +7315,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 	 * and assume host would use all available bits.
 	 * Guest xcr0 would be loaded later.
 	 */
-	kvm_put_guest_xcr0(vcpu);
 	vcpu->guest_fpu_loaded = 1;
 	__kernel_fpu_begin();
 	__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu.state);
@@ -7323,8 +7323,6 @@ void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
 
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
 {
-	kvm_put_guest_xcr0(vcpu);
-
 	if (!vcpu->guest_fpu_loaded) {
 		vcpu->fpu_counter = 0;
 		return;
diff --git a/arch/x86/xen/apic.c b/arch/x86/xen/apic.c
index abf4901c917b..db52a7fafcc2 100644
--- a/arch/x86/xen/apic.c
+++ b/arch/x86/xen/apic.c
@@ -66,7 +66,7 @@ static u32 xen_apic_read(u32 reg)
 
 	ret = HYPERVISOR_platform_op(&op);
 	if (ret)
-		return 0;
+		op.u.pcpu_info.apic_id = BAD_APICID;
 
 	return op.u.pcpu_info.apic_id << 24;
 }
@@ -142,6 +142,14 @@ static void xen_silent_inquire(int apicid)
 {
 }
 
+static int xen_cpu_present_to_apicid(int cpu)
+{
+	if (cpu_present(cpu))
+		return xen_get_apic_id(xen_apic_read(APIC_ID));
+	else
+		return BAD_APICID;
+}
+
 static struct apic xen_pv_apic = {
 	.name 				= "Xen PV",
 	.probe 				= xen_apic_probe_pv,
@@ -162,7 +170,7 @@ static struct apic xen_pv_apic = {
 
 	.ioapic_phys_id_map		= default_ioapic_phys_id_map, /* Used on 32-bit */
 	.setup_apic_routing		= NULL,
-	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
+	.cpu_present_to_apicid		= xen_cpu_present_to_apicid,
 	.apicid_to_cpu_present		= physid_set_mask_of_physid, /* Used on 32-bit */
 	.check_phys_apicid_present	= default_check_phys_apicid_present, /* smp_sanity_check needs it */
 	.phys_pkg_id			= xen_phys_pkg_id, /* detect_ht */
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 3c6d17fd423a..719cf291dcdf 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -545,6 +545,8 @@ static void xen_play_dead(void) /* used only with HOTPLUG_CPU */
 	 * data back is to call:
 	 */
 	tick_nohz_idle_enter();
+
+	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */