Merge branch 'linus' into x86/cpu, to resolve conflicts

Conflicts:
	tools/power/x86/turbostat/turbostat.c

Recent turbostat changes conflicted with a pending rename of x86 model names in tip:x86/cpu,
sort it out.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

arch/x86/Makefile

@@ -38,6 +38,7 @@ REALMODE_CFLAGS	:= $(M16_CFLAGS) -g -Os -DDISABLE_BRANCH_PROFILING \
 
 REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -ffreestanding)
 REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -fno-stack-protector)
+REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), -Wno-address-of-packed-member)
 REALMODE_CFLAGS += $(call __cc-option, $(CC), $(REALMODE_CFLAGS), $(cc_stack_align4))
 export REALMODE_CFLAGS
 

arch/x86/boot/compressed/pgtable_64.c

@@ -72,7 +72,7 @@ static unsigned long find_trampoline_placement(void)
 
 	/* Find the first usable memory region under bios_start. */
 	for (i = boot_params->e820_entries - 1; i >= 0; i--) {
-		unsigned long new;
+		unsigned long new = bios_start;
 
 		entry = &boot_params->e820_table[i];
 

arch/x86/events/amd/ibs.c

@@ -661,10 +661,17 @@ fail:
 
 	throttle = perf_event_overflow(event, &data, &regs);
 out:
-	if (throttle)
+	if (throttle) {
 		perf_ibs_stop(event, 0);
-	else
-		perf_ibs_enable_event(perf_ibs, hwc, period >> 4);
+	} else {
+		period >>= 4;
+
+		if ((ibs_caps & IBS_CAPS_RDWROPCNT) &&
+		    (*config & IBS_OP_CNT_CTL))
+			period |= *config & IBS_OP_CUR_CNT_RAND;
+
+		perf_ibs_enable_event(perf_ibs, hwc, period);
+	}
 
 	perf_event_update_userpage(event);
 

arch/x86/events/intel/core.c

@@ -3572,6 +3572,11 @@ static u64 bdw_limit_period(struct perf_event *event, u64 left)
 	return left;
 }
 
+static u64 nhm_limit_period(struct perf_event *event, u64 left)
+{
+	return max(left, 32ULL);
+}
+
 PMU_FORMAT_ATTR(event,	"config:0-7"	);
 PMU_FORMAT_ATTR(umask,	"config:8-15"	);
 PMU_FORMAT_ATTR(edge,	"config:18"	);
@@ -4606,6 +4611,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_constraints = intel_nehalem_pebs_event_constraints;
 		x86_pmu.enable_all = intel_pmu_nhm_enable_all;
 		x86_pmu.extra_regs = intel_nehalem_extra_regs;
+		x86_pmu.limit_period = nhm_limit_period;
 
 		mem_attr = nhm_mem_events_attrs;
 

arch/x86/include/asm/ftrace.h

@@ -16,7 +16,6 @@
 #define HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 
 #ifndef __ASSEMBLY__
-extern void mcount(void);
 extern atomic_t modifying_ftrace_code;
 extern void __fentry__(void);
 

arch/x86/include/asm/perf_event.h

@@ -252,16 +252,20 @@ struct pebs_lbr {
 #define IBSCTL_LVT_OFFSET_VALID		(1ULL<<8)
 #define IBSCTL_LVT_OFFSET_MASK		0x0F
 
-/* ibs fetch bits/masks */
+/* IBS fetch bits/masks */
 #define IBS_FETCH_RAND_EN	(1ULL<<57)
 #define IBS_FETCH_VAL		(1ULL<<49)
 #define IBS_FETCH_ENABLE	(1ULL<<48)
 #define IBS_FETCH_CNT		0xFFFF0000ULL
 #define IBS_FETCH_MAX_CNT	0x0000FFFFULL
 
-/* ibs op bits/masks */
-/* lower 4 bits of the current count are ignored: */
-#define IBS_OP_CUR_CNT		(0xFFFF0ULL<<32)
+/*
+ * IBS op bits/masks
+ * The lower 7 bits of the current count are random bits
+ * preloaded by hardware and ignored in software
+ */
+#define IBS_OP_CUR_CNT		(0xFFF80ULL<<32)
+#define IBS_OP_CUR_CNT_RAND	(0x0007FULL<<32)
 #define IBS_OP_CNT_CTL		(1ULL<<19)
 #define IBS_OP_VAL		(1ULL<<18)
 #define IBS_OP_ENABLE		(1ULL<<17)

arch/x86/kernel/apic/apic.c

@@ -1179,6 +1179,10 @@ void clear_local_APIC(void)
 	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
 	v = apic_read(APIC_LVT1);
 	apic_write(APIC_LVT1, v | APIC_LVT_MASKED);
+	if (!x2apic_enabled()) {
+		v = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+		apic_write(APIC_LDR, v);
+	}
 	if (maxlvt >= 4) {
 		v = apic_read(APIC_LVTPC);
 		apic_write(APIC_LVTPC, v | APIC_LVT_MASKED);

arch/x86/kernel/apic/bigsmp_32.c

@@ -38,32 +38,12 @@ static int bigsmp_early_logical_apicid(int cpu)
 	return early_per_cpu(x86_cpu_to_apicid, cpu);
 }
 
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long val, id;
-
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	id = per_cpu(x86_bios_cpu_apicid, cpu);
-	val |= SET_APIC_LOGICAL_ID(id);
-
-	return val;
-}
-
 /*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
+ * bigsmp enables physical destination mode
+ * and doesn't use LDR and DFR
  */
 static void bigsmp_init_apic_ldr(void)
 {
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_FLAT);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
 }
 
 static void bigsmp_setup_apic_routing(void)

arch/x86/kernel/apic/io_apic.c

@@ -2438,7 +2438,13 @@ unsigned int arch_dynirq_lower_bound(unsigned int from)
 	 * dmar_alloc_hwirq() may be called before setup_IO_APIC(), so use
 	 * gsi_top if ioapic_dynirq_base hasn't been initialized yet.
 	 */
-	return ioapic_initialized ? ioapic_dynirq_base : gsi_top;
+	if (!ioapic_initialized)
+		return gsi_top;
+	/*
+	 * For DT enabled machines ioapic_dynirq_base is irrelevant and not
+	 * updated. So simply return @from if ioapic_dynirq_base == 0.
+	 */
+	return ioapic_dynirq_base ? : from;
 }
 
 #ifdef CONFIG_X86_32

arch/x86/kernel/uprobes.c

@@ -508,9 +508,12 @@ struct uprobe_xol_ops {
 	void	(*abort)(struct arch_uprobe *, struct pt_regs *);
 };
 
-static inline int sizeof_long(void)
+static inline int sizeof_long(struct pt_regs *regs)
 {
-	return in_ia32_syscall() ? 4 : 8;
+	/*
+	 * Check registers for mode as in_xxx_syscall() does not apply here.
+	 */
+	return user_64bit_mode(regs) ? 8 : 4;
 }
 
 static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
@@ -521,9 +524,9 @@ static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 
 static int emulate_push_stack(struct pt_regs *regs, unsigned long val)
 {
-	unsigned long new_sp = regs->sp - sizeof_long();
+	unsigned long new_sp = regs->sp - sizeof_long(regs);
 
-	if (copy_to_user((void __user *)new_sp, &val, sizeof_long()))
+	if (copy_to_user((void __user *)new_sp, &val, sizeof_long(regs)))
 		return -EFAULT;
 
 	regs->sp = new_sp;
@@ -556,7 +559,7 @@ static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs
 		long correction = utask->vaddr - utask->xol_vaddr;
 		regs->ip += correction;
 	} else if (auprobe->defparam.fixups & UPROBE_FIX_CALL) {
-		regs->sp += sizeof_long(); /* Pop incorrect return address */
+		regs->sp += sizeof_long(regs); /* Pop incorrect return address */
 		if (emulate_push_stack(regs, utask->vaddr + auprobe->defparam.ilen))
 			return -ERESTART;
 	}
@@ -675,7 +678,7 @@ static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs)
 	 * "call" insn was executed out-of-line. Just restore ->sp and restart.
 	 * We could also restore ->ip and try to call branch_emulate_op() again.
 	 */
-	regs->sp += sizeof_long();
+	regs->sp += sizeof_long(regs);
 	return -ERESTART;
 }
 
@@ -1056,7 +1059,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
 unsigned long
 arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs)
 {
-	int rasize = sizeof_long(), nleft;
+	int rasize = sizeof_long(regs), nleft;
 	unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */
 
 	if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize))

arch/x86/kvm/hyperv.c

@@ -1781,7 +1781,7 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args)
 int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 				struct kvm_cpuid_entry2 __user *entries)
 {
-	uint16_t evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+	uint16_t evmcs_ver = 0;
 	struct kvm_cpuid_entry2 cpuid_entries[] = {
 		{ .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS },
 		{ .function = HYPERV_CPUID_INTERFACE },
@@ -1793,6 +1793,9 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 	};
 	int i, nent = ARRAY_SIZE(cpuid_entries);
 
+	if (kvm_x86_ops->nested_get_evmcs_version)
+		evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+
 	/* Skip NESTED_FEATURES if eVMCS is not supported */
 	if (!evmcs_ver)
 		--nent;

arch/x86/kvm/svm.c

@@ -7128,12 +7128,6 @@ failed:
 	return ret;
 }
 
-static uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
-{
-	/* Not supported */
-	return 0;
-}
-
 static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 				   uint16_t *vmcs_version)
 {
@@ -7332,7 +7326,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.mem_enc_unreg_region = svm_unregister_enc_region,
 
 	.nested_enable_evmcs = nested_enable_evmcs,
-	.nested_get_evmcs_version = nested_get_evmcs_version,
+	.nested_get_evmcs_version = NULL,
 
 	.need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
 };

arch/x86/kvm/vmx/vmx.c

@@ -7797,6 +7797,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.set_nested_state = NULL,
 	.get_vmcs12_pages = NULL,
 	.nested_enable_evmcs = NULL,
+	.nested_get_evmcs_version = NULL,
 	.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
 };
 

arch/x86/kvm/x86.c

@@ -6594,12 +6594,13 @@ restart:
 		unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
-		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE && ctxt->tf)
-			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
-		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+		    exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+			kvm_rip_write(vcpu, ctxt->eip);
+			if (r == EMULATE_DONE && ctxt->tf)
+				kvm_vcpu_do_singlestep(vcpu, &r);
 			__kvm_set_rflags(vcpu, ctxt->eflags);
+		}
 
 		/*
 		 * For STI, interrupts are shadowed; so KVM_REQ_EVENT will

arch/x86/mm/pageattr.c

@@ -516,7 +516,7 @@ static inline void check_conflict(int warnlvl, pgprot_t prot, pgprotval_t val,
  */
 static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
 					  unsigned long pfn, unsigned long npg,
-					  int warnlvl)
+					  unsigned long lpsize, int warnlvl)
 {
 	pgprotval_t forbidden, res;
 	unsigned long end;
@@ -535,9 +535,17 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long start,
 	check_conflict(warnlvl, prot, res, start, end, pfn, "Text NX");
 	forbidden = res;
 
-	res = protect_kernel_text_ro(start, end);
-	check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO");
-	forbidden |= res;
+	/*
+	 * Special case to preserve a large page. If the change spawns the
+	 * full large page mapping then there is no point to split it
+	 * up. Happens with ftrace and is going to be removed once ftrace
+	 * switched to text_poke().
+	 */
+	if (lpsize != (npg * PAGE_SIZE) || (start & (lpsize - 1))) {
+		res = protect_kernel_text_ro(start, end);
+		check_conflict(warnlvl, prot, res, start, end, pfn, "Text RO");
+		forbidden |= res;
+	}
 
 	/* Check the PFN directly */
 	res = protect_pci_bios(pfn, pfn + npg - 1);
@@ -819,7 +827,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	 * extra conditional required here.
 	 */
 	chk_prot = static_protections(old_prot, lpaddr, old_pfn, numpages,
-				      CPA_CONFLICT);
+				      psize, CPA_CONFLICT);
 
 	if (WARN_ON_ONCE(pgprot_val(chk_prot) != pgprot_val(old_prot))) {
 		/*
@@ -855,7 +863,7 @@ static int __should_split_large_page(pte_t *kpte, unsigned long address,
 	 * protection requirement in the large page.
 	 */
 	new_prot = static_protections(req_prot, lpaddr, old_pfn, numpages,
-				      CPA_DETECT);
+				      psize, CPA_DETECT);
 
 	/*
 	 * If there is a conflict, split the large page.
@@ -906,7 +914,8 @@ static void split_set_pte(struct cpa_data *cpa, pte_t *pte, unsigned long pfn,
 	if (!cpa->force_static_prot)
 		goto set;
 
-	prot = static_protections(ref_prot, address, pfn, npg, CPA_PROTECT);
+	/* Hand in lpsize = 0 to enforce the protection mechanism */
+	prot = static_protections(ref_prot, address, pfn, npg, 0, CPA_PROTECT);
 
 	if (pgprot_val(prot) == pgprot_val(ref_prot))
 		goto set;
@@ -1503,7 +1512,8 @@ repeat:
 		pgprot_val(new_prot) |= pgprot_val(cpa->mask_set);
 
 		cpa_inc_4k_install();
-		new_prot = static_protections(new_prot, address, pfn, 1,
+		/* Hand in lpsize = 0 to enforce the protection mechanism */
+		new_prot = static_protections(new_prot, address, pfn, 1, 0,
 					      CPA_PROTECT);
 
 		new_prot = pgprot_clear_protnone_bits(new_prot);