Merge branch 'dev-5.10' into dev-5.10-inteldev-5.10-intel

Pull 5.10.67 stable from OpenBMC upstream.

Signed-off-by: Jae Hyun Yoo <jae.hyun.yoo@linux.intel.com>

16 files changed, 115 insertions, 64 deletions

diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 40669eac9d6d..ccc9ee1971e8 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -90,6 +90,7 @@ struct perf_ibs {
 	unsigned long			offset_mask[1];
 	int				offset_max;
 	unsigned int			fetch_count_reset_broken : 1;
+	unsigned int			fetch_ignore_if_zero_rip : 1;
 	struct cpu_perf_ibs __percpu	*pcpu;
 
 	struct attribute		**format_attrs;
@@ -570,6 +571,7 @@ static struct perf_ibs perf_ibs_op = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
 	.config_mask		= IBS_OP_CONFIG_MASK,
@@ -672,6 +674,10 @@ fail:
 	if (check_rip && (ibs_data.regs[2] & IBS_RIP_INVALID)) {
 		regs.flags &= ~PERF_EFLAGS_EXACT;
 	} else {
+		/* Workaround for erratum #1197 */
+		if (perf_ibs->fetch_ignore_if_zero_rip && !(ibs_data.regs[1]))
+			goto out;
+
 		set_linear_ip(&regs, ibs_data.regs[1]);
 		regs.flags |= PERF_EFLAGS_EXACT;
 	}
@@ -769,6 +775,9 @@ static __init void perf_event_ibs_init(void)
 	if (boot_cpu_data.x86 >= 0x16 && boot_cpu_data.x86 <= 0x18)
 		perf_ibs_fetch.fetch_count_reset_broken = 1;
 
+	if (boot_cpu_data.x86 == 0x19 && boot_cpu_data.x86_model < 0x10)
+		perf_ibs_fetch.fetch_ignore_if_zero_rip = 1;
+
 	perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
 
 	if (ibs_caps & IBS_CAPS_OPCNT) {
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index 6a98a7651621..2da6139b0977 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -18,8 +18,6 @@
 #include "../perf_event.h"
 #include "iommu.h"
 
-#define COUNTER_SHIFT		16
-
 /* iommu pmu conf masks */
 #define GET_CSOURCE(x)     ((x)->conf & 0xFFULL)
 #define GET_DEVID(x)       (((x)->conf >> 8)  & 0xFFFFULL)
@@ -285,22 +283,31 @@ static void perf_iommu_start(struct perf_event *event, int flags)
 	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
 	hwc->state = 0;
 
+	/*
+	 * To account for power-gating, which prevents write to
+	 * the counter, we need to enable the counter
+	 * before setting up counter register.
+	 */
+	perf_iommu_enable_event(event);
+
 	if (flags & PERF_EF_RELOAD) {
-		u64 prev_raw_count = local64_read(&hwc->prev_count);
+		u64 count = 0;
 		struct amd_iommu *iommu = perf_event_2_iommu(event);
 
+		/*
+		 * Since the IOMMU PMU only support counting mode,
+		 * the counter always start with value zero.
+		 */
 		amd_iommu_pc_set_reg(iommu, hwc->iommu_bank, hwc->iommu_cntr,
-				     IOMMU_PC_COUNTER_REG, &prev_raw_count);
+				     IOMMU_PC_COUNTER_REG, &count);
 	}
 
-	perf_iommu_enable_event(event);
 	perf_event_update_userpage(event);
-
 }
 
 static void perf_iommu_read(struct perf_event *event)
 {
-	u64 count, prev, delta;
+	u64 count;
 	struct hw_perf_event *hwc = &event->hw;
 	struct amd_iommu *iommu = perf_event_2_iommu(event);
 
@@ -311,14 +318,11 @@ static void perf_iommu_read(struct perf_event *event)
 	/* IOMMU pc counter register is only 48 bits */
 	count &= GENMASK_ULL(47, 0);
 
-	prev = local64_read(&hwc->prev_count);
-	if (local64_cmpxchg(&hwc->prev_count, prev, count) != prev)
-		return;
-
-	/* Handle 48-bit counter overflow */
-	delta = (count << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
-	delta >>= COUNTER_SHIFT;
-	local64_add(delta, &event->count);
+	/*
+	 * Since the counter always start with value zero,
+	 * simply just accumulate the count for the event.
+	 */
+	local64_add(count, &event->count);
 }
 
 static void perf_iommu_stop(struct perf_event *event, int flags)
@@ -328,15 +332,16 @@ static void perf_iommu_stop(struct perf_event *event, int flags)
 	if (hwc->state & PERF_HES_UPTODATE)
 		return;
 
+	/*
+	 * To account for power-gating, in which reading the counter would
+	 * return zero, we need to read the register before disabling.
+	 */
+	perf_iommu_read(event);
+	hwc->state |= PERF_HES_UPTODATE;
+
 	perf_iommu_disable_event(event);
 	WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
 	hwc->state |= PERF_HES_STOPPED;
-
-	if (hwc->state & PERF_HES_UPTODATE)
-		return;
-
-	perf_iommu_read(event);
-	hwc->state |= PERF_HES_UPTODATE;
 }
 
 static int perf_iommu_add(struct perf_event *event, int flags)
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 16a2369c586e..37d5b380516e 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -213,6 +213,7 @@ static struct pmu pmu_class = {
 	.stop		= pmu_event_stop,
 	.read		= pmu_event_read,
 	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE,
+	.module		= THIS_MODULE,
 };
 
 static int power_cpu_exit(unsigned int cpu)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index e94af4a54d0d..37129b76135a 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -62,7 +62,7 @@ static struct pt_cap_desc {
 	PT_CAP(single_range_output,	0, CPUID_ECX, BIT(2)),
 	PT_CAP(output_subsys,		0, CPUID_ECX, BIT(3)),
 	PT_CAP(payloads_lip,		0, CPUID_ECX, BIT(31)),
-	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x3),
+	PT_CAP(num_address_ranges,	1, CPUID_EAX, 0x7),
 	PT_CAP(mtc_periods,		1, CPUID_EAX, 0xffff0000),
 	PT_CAP(cycle_thresholds,	1, CPUID_EBX, 0xffff),
 	PT_CAP(psb_periods,		1, CPUID_EBX, 0xffff0000),
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 9c936d06fb61..2701f87a9a7c 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -4669,7 +4669,7 @@ static void __snr_uncore_mmio_init_box(struct intel_uncore_box *box,
 		return;
 
 	pci_read_config_dword(pdev, SNR_IMC_MMIO_BASE_OFFSET, &pci_dword);
-	addr = (pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
+	addr = ((resource_size_t)pci_dword & SNR_IMC_MMIO_BASE_MASK) << 23;
 
 	pci_read_config_dword(pdev, mem_offset, &pci_dword);
 	addr |= (pci_dword & SNR_IMC_MMIO_MEM0_MASK) << 12;
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index fc25c88c7ff2..9b5ff423e939 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -259,6 +259,7 @@ enum mcp_flags {
 	MCP_TIMESTAMP	= BIT(0),	/* log time stamp */
 	MCP_UC		= BIT(1),	/* log uncorrected errors */
 	MCP_DONTLOG	= BIT(2),	/* only clear, don't log */
+	MCP_QUEUE_LOG	= BIT(3),	/* only queue to genpool */
 };
 bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index b7a27589dfa0..056d0367864e 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -817,7 +817,10 @@ log_it:
 		if (mca_cfg.dont_log_ce && !mce_usable_address(&m))
 			goto clear_it;
 
-		mce_log(&m);
+		if (flags & MCP_QUEUE_LOG)
+			mce_gen_pool_add(&m);
+		else
+			mce_log(&m);
 
 clear_it:
 		/*
@@ -1628,10 +1631,12 @@ static void __mcheck_cpu_init_generic(void)
 		m_fl = MCP_DONTLOG;
 
 	/*
-	 * Log the machine checks left over from the previous reset.
+	 * Log the machine checks left over from the previous reset. Log them
+	 * only, do not start processing them. That will happen in mcheck_late_init()
+	 * when all consumers have been registered on the notifier chain.
 	 */
 	bitmap_fill(all_banks, MAX_NR_BANKS);
-	machine_check_poll(MCP_UC | m_fl, &all_banks);
+	machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks);
 
 	cr4_set_bits(X86_CR4_MCE);
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 6cc50ab07bde..65d11711cd7b 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -322,8 +322,6 @@ static void __init ms_hyperv_init_platform(void)
 	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
 		wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, 0x1);
 		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-	} else {
-		mark_tsc_unstable("running on Hyper-V");
 	}
 
 	/*
@@ -382,6 +380,13 @@ static void __init ms_hyperv_init_platform(void)
 	/* Register Hyper-V specific clocksource */
 	hv_init_clocksource();
 #endif
+	/*
+	 * TSC should be marked as unstable only after Hyper-V
+	 * clocksource has been initialized. This ensures that the
+	 * stability of the sched_clock is not altered.
+	 */
+	if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
+		mark_tsc_unstable("running on Hyper-V");
 }
 
 const __initconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 3075624723b2..576f16a505e3 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -241,6 +241,12 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 	case QOS_L3_MBM_LOCAL_EVENT_ID:
 		m = &rr->d->mbm_local[rmid];
 		break;
+	default:
+		/*
+		 * Code would never reach here because an invalid
+		 * event id would fail the __rmid_read.
+		 */
+		return RMID_VAL_ERROR;
 	}
 
 	if (rr->first) {
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index b29657b76e3f..798a6f73f894 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -388,10 +388,11 @@ static const struct dmi_system_id reboot_dmi_table[] __initconst = {
 	},
 	{	/* Handle problems with rebooting on the OptiPlex 990. */
 		.callback = set_pci_reboot,
-		.ident = "Dell OptiPlex 990",
+		.ident = "Dell OptiPlex 990 BIOS A0x",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 990"),
+			DMI_MATCH(DMI_BIOS_VERSION, "A0"),
 		},
 	},
 	{	/* Handle problems with rebooting on Dell 300's */
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5e25d93ec7d0..060d9a906535 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -267,12 +267,6 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access,
                                   struct x86_exception *exception)
 {
-	/* Check if guest physical address doesn't exceed guest maximum */
-	if (kvm_vcpu_is_illegal_gpa(vcpu, gpa)) {
-		exception->error_code |= PFERR_RSVD_MASK;
-		return UNMAPPED_GVA;
-	}
-
         return gpa;
 }
 
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index e0c7910207c0..d5f24a2f3e91 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2243,12 +2243,11 @@ static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
 			 ~PIN_BASED_VMX_PREEMPTION_TIMER);
 
 	/* Posted interrupts setting is only taken from vmcs12.  */
-	if (nested_cpu_has_posted_intr(vmcs12)) {
+	vmx->nested.pi_pending = false;
+	if (nested_cpu_has_posted_intr(vmcs12))
 		vmx->nested.posted_intr_nv = vmcs12->posted_intr_nv;
-		vmx->nested.pi_pending = false;
-	} else {
+	else
 		exec_control &= ~PIN_BASED_POSTED_INTR;
-	}
 	pin_controls_set(vmx, exec_control);
 
 	/*
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index de24d3826788..fcd8bcb7e0ea 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6396,6 +6396,9 @@ static void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (vmx->emulation_required)
+		return;
+
 	if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT)
 		handle_external_interrupt_irqoff(vcpu);
 	else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6ab42cdcb8a4..75c59ad27e9f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3116,6 +3116,10 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			if (!msr_info->host_initiated) {
 				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
 				adjust_tsc_offset_guest(vcpu, adj);
+				/* Before back to guest, tsc_timestamp must be adjusted
+				 * as well, otherwise guest's percpu pvclock time could jump.
+				 */
+				kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 			}
 			vcpu->arch.ia32_tsc_adjust_msr = data;
 		}
@@ -7023,6 +7027,11 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
 	BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
 
+	ctxt->interruptibility = 0;
+	ctxt->have_exception = false;
+	ctxt->exception.vector = -1;
+	ctxt->perm_ok = false;
+
 	init_decode_cache(ctxt);
 	vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
 }
@@ -7338,6 +7347,37 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt)
 	return false;
 }
 
+/*
+ * Decode to be emulated instruction. Return EMULATION_OK if success.
+ */
+int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
+				    void *insn, int insn_len)
+{
+	int r = EMULATION_OK;
+	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+
+	init_emulate_ctxt(vcpu);
+
+	/*
+	 * We will reenter on the same instruction since we do not set
+	 * complete_userspace_io. This does not handle watchpoints yet,
+	 * those would be handled in the emulate_ops.
+	 */
+	if (!(emulation_type & EMULTYPE_SKIP) &&
+	    kvm_vcpu_check_breakpoint(vcpu, &r))
+		return r;
+
+	ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
+
+	r = x86_decode_insn(ctxt, insn, insn_len);
+
+	trace_kvm_emulate_insn_start(vcpu);
+	++vcpu->stat.insn_emulation;
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(x86_decode_emulated_instruction);
+
 int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    int emulation_type, void *insn, int insn_len)
 {
@@ -7357,32 +7397,12 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	 */
 	write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 	vcpu->arch.write_fault_to_shadow_pgtable = false;
-	kvm_clear_exception_queue(vcpu);
 
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
-		init_emulate_ctxt(vcpu);
-
-		/*
-		 * We will reenter on the same instruction since
-		 * we do not set complete_userspace_io.  This does not
-		 * handle watchpoints yet, those would be handled in
-		 * the emulate_ops.
-		 */
-		if (!(emulation_type & EMULTYPE_SKIP) &&
-		    kvm_vcpu_check_breakpoint(vcpu, &r))
-			return r;
-
-		ctxt->interruptibility = 0;
-		ctxt->have_exception = false;
-		ctxt->exception.vector = -1;
-		ctxt->perm_ok = false;
-
-		ctxt->ud = emulation_type & EMULTYPE_TRAP_UD;
-
-		r = x86_decode_insn(ctxt, insn, insn_len);
+		kvm_clear_exception_queue(vcpu);
 
-		trace_kvm_emulate_insn_start(vcpu);
-		++vcpu->stat.insn_emulation;
+		r = x86_decode_emulated_instruction(vcpu, emulation_type,
+						    insn, insn_len);
 		if (r != EMULATION_OK)  {
 			if ((emulation_type & EMULTYPE_TRAP_UD) ||
 			    (emulation_type & EMULTYPE_TRAP_UD_FORCED)) {
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 2249a7d7ca27..2bff44f1efec 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -272,6 +272,8 @@ bool kvm_mtrr_check_gfn_range_consistency(struct kvm_vcpu *vcpu, gfn_t gfn,
 					  int page_num);
 bool kvm_vector_hashing_enabled(void);
 void kvm_fixup_and_inject_pf_error(struct kvm_vcpu *vcpu, gva_t gva, u16 error_code);
+int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
+				    void *insn, int insn_len);
 int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 			    int emulation_type, void *insn, int insn_len);
 fastpath_t handle_fastpath_set_msr_irqoff(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
index 56e0f290fef6..e809f1446846 100644
--- a/arch/x86/xen/p2m.c
+++ b/arch/x86/xen/p2m.c
@@ -618,8 +618,8 @@ int xen_alloc_p2m_entry(unsigned long pfn)
 	}
 
 	/* Expanded the p2m? */
-	if (pfn > xen_p2m_last_pfn) {
-		xen_p2m_last_pfn = pfn;
+	if (pfn >= xen_p2m_last_pfn) {
+		xen_p2m_last_pfn = ALIGN(pfn + 1, P2M_PER_PAGE);
 		HYPERVISOR_shared_info->arch.max_pfn = xen_p2m_last_pfn;
 	}