Backmerge tag 'v4.9-rc8' into drm-next

Linux 4.9-rc8

Daniel requested this so we could apply some follow on fixes cleanly to -next.

arch/x86/boot/compressed/Makefile

@@ -40,8 +40,8 @@ GCOV_PROFILE := n
 UBSAN_SANITIZE :=n
 
 LDFLAGS := -m elf_$(UTS_MACHINE)
-ifeq ($(CONFIG_RELOCATABLE),y)
-# If kernel is relocatable, build compressed kernel as PIE.
+# Compressed kernel should be built as PIE since it may be loaded at any
+# address by the bootloader.
 ifeq ($(CONFIG_X86_32),y)
 LDFLAGS += $(call ld-option, -pie) $(call ld-option, --no-dynamic-linker)
 else
@@ -51,7 +51,6 @@ else
 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

arch/x86/boot/cpu.c

@@ -87,6 +87,12 @@ int validate_cpu(void)
 		return -1;
 	}
 
+	if (CONFIG_X86_MINIMUM_CPU_FAMILY <= 4 && !IS_ENABLED(CONFIG_M486) &&
+	    !has_eflag(X86_EFLAGS_ID)) {
+		printf("This kernel requires a CPU with the CPUID instruction.  Build with CONFIG_M486=y to run on this CPU.\n");
+		return -1;
+	}
+
 	if (err_flags) {
 		puts("This kernel requires the following features "
 		     "not present on the CPU:\n");

arch/x86/events/amd/core.c

@@ -662,7 +662,13 @@ static int __init amd_core_pmu_init(void)
 		pr_cont("Fam15h ");
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f15h;
 		break;
-
+	case 0x17:
+		pr_cont("Fam17h ");
+		/*
+		 * In family 17h, there are no event constraints in the PMC hardware.
+		 * We fallback to using default amd_get_event_constraints.
+		 */
+		break;
 	default:
 		pr_err("core perfctr but no constraints; unknown hardware!\n");
 		return -ENODEV;

arch/x86/events/core.c

@@ -2352,7 +2352,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 		frame.next_frame     = 0;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 8))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 4);
@@ -2362,9 +2362,6 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent
 		if (bytes != 0)
 			break;
 
-		if (!valid_user_frame(fp, sizeof(frame)))
-			break;
-
 		perf_callchain_store(entry, cs_base + frame.return_address);
 		fp = compat_ptr(ss_base + frame.next_frame);
 	}
@@ -2413,7 +2410,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
+		if (!valid_user_frame(fp, sizeof(frame)))
 			break;
 
 		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
@@ -2423,9 +2420,6 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 		if (bytes != 0)
 			break;
 
-		if (!valid_user_frame(fp, sizeof(frame)))
-			break;
-
 		perf_callchain_store(entry, frame.return_address);
 		fp = (void __user *)frame.next_frame;
 	}

arch/x86/events/intel/ds.c

@@ -1108,20 +1108,20 @@ static void setup_pebs_sample_data(struct perf_event *event,
 	}
 
 	/*
-	 * We use the interrupt regs as a base because the PEBS record
-	 * does not contain a full regs set, specifically it seems to
-	 * lack segment descriptors, which get used by things like
-	 * user_mode().
+	 * We use the interrupt regs as a base because the PEBS record does not
+	 * contain a full regs set, specifically it seems to lack segment
+	 * descriptors, which get used by things like user_mode().
 	 *
-	 * In the simple case fix up only the IP and BP,SP regs, for
-	 * PERF_SAMPLE_IP and PERF_SAMPLE_CALLCHAIN to function properly.
-	 * A possible PERF_SAMPLE_REGS will have to transfer all regs.
+	 * In the simple case fix up only the IP for PERF_SAMPLE_IP.
+	 *
+	 * We must however always use BP,SP from iregs for the unwinder to stay
+	 * sane; the record BP,SP can point into thin air when the record is
+	 * from a previous PMI context or an (I)RET happend between the record
+	 * and PMI.
 	 */
 	*regs = *iregs;
 	regs->flags = pebs->flags;
 	set_linear_ip(regs, pebs->ip);
-	regs->bp = pebs->bp;
-	regs->sp = pebs->sp;
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR) {
 		regs->ax = pebs->ax;
@@ -1130,10 +1130,21 @@ static void setup_pebs_sample_data(struct perf_event *event,
 		regs->dx = pebs->dx;
 		regs->si = pebs->si;
 		regs->di = pebs->di;
-		regs->bp = pebs->bp;
-		regs->sp = pebs->sp;
 
-		regs->flags = pebs->flags;
+		/*
+		 * Per the above; only set BP,SP if we don't need callchains.
+		 *
+		 * XXX: does this make sense?
+		 */
+		if (!(sample_type & PERF_SAMPLE_CALLCHAIN)) {
+			regs->bp = pebs->bp;
+			regs->sp = pebs->sp;
+		}
+
+		/*
+		 * Preserve PERF_EFLAGS_VM from set_linear_ip().
+		 */
+		regs->flags = pebs->flags | (regs->flags & PERF_EFLAGS_VM);
 #ifndef CONFIG_X86_32
 		regs->r8 = pebs->r8;
 		regs->r9 = pebs->r9;

arch/x86/events/intel/uncore.c

@@ -319,9 +319,9 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
  */
 static int uncore_pmu_event_init(struct perf_event *event);
 
-static bool is_uncore_event(struct perf_event *event)
+static bool is_box_event(struct intel_uncore_box *box, struct perf_event *event)
 {
-	return event->pmu->event_init == uncore_pmu_event_init;
+	return &box->pmu->pmu == event->pmu;
 }
 
 static int
@@ -340,7 +340,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
 
 	n = box->n_events;
 
-	if (is_uncore_event(leader)) {
+	if (is_box_event(box, leader)) {
 		box->event_list[n] = leader;
 		n++;
 	}
@@ -349,7 +349,7 @@ uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader,
 		return n;
 
 	list_for_each_entry(event, &leader->sibling_list, group_entry) {
-		if (!is_uncore_event(event) ||
+		if (!is_box_event(box, event) ||
 		    event->state <= PERF_EVENT_STATE_OFF)
 			continue;
 

arch/x86/events/intel/uncore_snb.c

@@ -8,8 +8,12 @@
 #define PCI_DEVICE_ID_INTEL_HSW_IMC	0x0c00
 #define PCI_DEVICE_ID_INTEL_HSW_U_IMC	0x0a04
 #define PCI_DEVICE_ID_INTEL_BDW_IMC	0x1604
-#define PCI_DEVICE_ID_INTEL_SKL_IMC	0x191f
-#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_U_IMC	0x1904
+#define PCI_DEVICE_ID_INTEL_SKL_Y_IMC	0x190c
+#define PCI_DEVICE_ID_INTEL_SKL_HD_IMC	0x1900
+#define PCI_DEVICE_ID_INTEL_SKL_HQ_IMC	0x1910
+#define PCI_DEVICE_ID_INTEL_SKL_SD_IMC	0x190f
+#define PCI_DEVICE_ID_INTEL_SKL_SQ_IMC	0x191f
 
 /* SNB event control */
 #define SNB_UNC_CTL_EV_SEL_MASK			0x000000ff
@@ -486,24 +490,12 @@ static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
 
 	snb_uncore_imc_event_start(event, 0);
 
-	box->n_events++;
-
 	return 0;
 }
 
 static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
 {
-	struct intel_uncore_box *box = uncore_event_to_box(event);
-	int i;
-
 	snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
-
-	for (i = 0; i < box->n_events; i++) {
-		if (event == box->event_list[i]) {
-			--box->n_events;
-			break;
-		}
-	}
 }
 
 int snb_pci2phy_map_init(int devid)
@@ -616,13 +608,29 @@ static const struct pci_device_id bdw_uncore_pci_ids[] = {
 
 static const struct pci_device_id skl_uncore_pci_ids[] = {
 	{ /* IMC */
-		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_IMC),
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_Y_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
 	{ /* IMC */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_U_IMC),
 		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
 	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_HQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SD_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
+	{ /* IMC */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SKL_SQ_IMC),
+		.driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+	},
 
 	{ /* end: all zeroes */ },
 };
@@ -666,8 +674,12 @@ static const struct imc_uncore_pci_dev desktop_imc_pci_ids[] = {
 	IMC_DEV(HSW_IMC, &hsw_uncore_pci_driver),    /* 4th Gen Core Processor */
 	IMC_DEV(HSW_U_IMC, &hsw_uncore_pci_driver),  /* 4th Gen Core ULT Mobile Processor */
 	IMC_DEV(BDW_IMC, &bdw_uncore_pci_driver),    /* 5th Gen Core U */
-	IMC_DEV(SKL_IMC, &skl_uncore_pci_driver),    /* 6th Gen Core */
+	IMC_DEV(SKL_Y_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core Y */
 	IMC_DEV(SKL_U_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core U */
+	IMC_DEV(SKL_HD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Dual Core */
+	IMC_DEV(SKL_HQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core H Quad Core */
+	IMC_DEV(SKL_SD_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Dual Core */
+	IMC_DEV(SKL_SQ_IMC, &skl_uncore_pci_driver),  /* 6th Gen Core S Quad Core */
 	{  /* end marker */ }
 };
 

arch/x86/events/perf_event.h

@@ -113,7 +113,7 @@ struct debug_store {
  * Per register state.
  */
 struct er_account {
-	raw_spinlock_t		lock;	/* per-core: protect structure */
+	raw_spinlock_t      lock;	/* per-core: protect structure */
 	u64                 config;	/* extra MSR config */
 	u64                 reg;	/* extra MSR number */
 	atomic_t            ref;	/* reference count */

arch/x86/include/asm/intel-mid.h

@@ -17,6 +17,7 @@
 
 extern int intel_mid_pci_init(void);
 extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state);
+extern pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev);
 
 extern void intel_mid_pwr_power_off(void);
 

arch/x86/kernel/cpu/amd.c

@@ -347,7 +347,6 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	unsigned bits;
 	int cpu = smp_processor_id();
-	unsigned int socket_id, core_complex_id;
 
 	bits = c->x86_coreid_bits;
 	/* Low order bits define the core id (index of core in socket) */
@@ -365,10 +364,7 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c)
 	 if (c->x86 != 0x17 || !cpuid_edx(0x80000006))
 		return;
 
-	socket_id	= (c->apicid >> bits) - 1;
-	core_complex_id	= (c->apicid & ((1 << bits) - 1)) >> 3;
-
-	per_cpu(cpu_llc_id, cpu) = (socket_id << 3) | core_complex_id;
+	per_cpu(cpu_llc_id, cpu) = c->apicid >> 3;
 #endif
 }
 

arch/x86/kernel/cpu/common.c

@@ -978,6 +978,35 @@ static void x86_init_cache_qos(struct cpuinfo_x86 *c)
 	}
 }
 
+/*
+ * The physical to logical package id mapping is initialized from the
+ * acpi/mptables information. Make sure that CPUID actually agrees with
+ * that.
+ */
+static void sanitize_package_id(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int pkg, apicid, cpu = smp_processor_id();
+
+	apicid = apic->cpu_present_to_apicid(cpu);
+	pkg = apicid >> boot_cpu_data.x86_coreid_bits;
+
+	if (apicid != c->initial_apicid) {
+		pr_err(FW_BUG "CPU%u: APIC id mismatch. Firmware: %x CPUID: %x\n",
+		       cpu, apicid, c->initial_apicid);
+		c->initial_apicid = apicid;
+	}
+	if (pkg != c->phys_proc_id) {
+		pr_err(FW_BUG "CPU%u: Using firmware package id %u instead of %u\n",
+		       cpu, pkg, c->phys_proc_id);
+		c->phys_proc_id = pkg;
+	}
+	c->logical_proc_id = topology_phys_to_logical_pkg(pkg);
+#else
+	c->logical_proc_id = 0;
+#endif
+}
+
 /*
  * This does the hard work of actually picking apart the CPU stuff...
  */
@@ -1103,8 +1132,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 #ifdef CONFIG_NUMA
 	numa_add_cpu(smp_processor_id());
 #endif
-	/* The boot/hotplug time assigment got cleared, restore it */
-	c->logical_proc_id = topology_phys_to_logical_pkg(c->phys_proc_id);
+	sanitize_package_id(c);
 }
 
 /*

arch/x86/kernel/dumpstack.c

@@ -112,7 +112,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		for (; stack < stack_info.end; stack++) {
 			unsigned long real_addr;
 			int reliable = 0;
-			unsigned long addr = *stack;
+			unsigned long addr = READ_ONCE_NOCHECK(*stack);
 			unsigned long *ret_addr_p =
 				unwind_get_return_address_ptr(&state);
 

arch/x86/kernel/fpu/core.c

@@ -521,14 +521,14 @@ void fpu__clear(struct fpu *fpu)
 {
 	WARN_ON_FPU(fpu != &current->thread.fpu); /* Almost certainly an anomaly */
 
-	if (!use_eager_fpu() || !static_cpu_has(X86_FEATURE_FPU)) {
-		/* FPU state will be reallocated lazily at the first use. */
-		fpu__drop(fpu);
-	} else {
-		if (!fpu->fpstate_active) {
-			fpu__activate_curr(fpu);
-			user_fpu_begin();
-		}
+	fpu__drop(fpu);
+
+	/*
+	 * Make sure fpstate is cleared and initialized.
+	 */
+	if (static_cpu_has(X86_FEATURE_FPU)) {
+		fpu__activate_curr(fpu);
+		user_fpu_begin();
 		copy_init_fpstate_to_fpregs();
 	}
 }

arch/x86/kernel/head_32.S

@@ -665,14 +665,17 @@ __PAGE_ALIGNED_BSS
 initial_pg_pmd:
 	.fill 1024*KPMDS,4,0
 #else
-ENTRY(initial_page_table)
+.globl initial_page_table
+initial_page_table:
 	.fill 1024,4,0
 #endif
 initial_pg_fixmap:
 	.fill 1024,4,0
-ENTRY(empty_zero_page)
+.globl empty_zero_page
+empty_zero_page:
 	.fill 4096,1,0
-ENTRY(swapper_pg_dir)
+.globl swapper_pg_dir
+swapper_pg_dir:
 	.fill 1024,4,0
 EXPORT_SYMBOL(empty_zero_page)
 

arch/x86/kernel/sysfb_simplefb.c

@@ -66,13 +66,36 @@ __init int create_simplefb(const struct screen_info *si,
 {
 	struct platform_device *pd;
 	struct resource res;
-	unsigned long len;
+	u64 base, size;
+	u32 length;
 
-	/* don't use lfb_size as it may contain the whole VMEM instead of only
-	 * the part that is occupied by the framebuffer */
-	len = mode->height * mode->stride;
-	len = PAGE_ALIGN(len);
-	if (len > (u64)si->lfb_size << 16) {
+	/*
+	 * If the 64BIT_BASE capability is set, ext_lfb_base will contain the
+	 * upper half of the base address. Assemble the address, then make sure
+	 * it is valid and we can actually access it.
+	 */
+	base = si->lfb_base;
+	if (si->capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		base |= (u64)si->ext_lfb_base << 32;
+	if (!base || (u64)(resource_size_t)base != base) {
+		printk(KERN_DEBUG "sysfb: inaccessible VRAM base\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Don't use lfb_size as IORESOURCE size, since it may contain the
+	 * entire VMEM, and thus require huge mappings. Use just the part we
+	 * need, that is, the part where the framebuffer is located. But verify
+	 * that it does not exceed the advertised VMEM.
+	 * Note that in case of VBE, the lfb_size is shifted by 16 bits for
+	 * historical reasons.
+	 */
+	size = si->lfb_size;
+	if (si->orig_video_isVGA == VIDEO_TYPE_VLFB)
+		size <<= 16;
+	length = mode->height * mode->stride;
+	length = PAGE_ALIGN(length);
+	if (length > size) {
 		printk(KERN_WARNING "sysfb: VRAM smaller than advertised\n");
 		return -EINVAL;
 	}
@@ -81,8 +104,8 @@ __init int create_simplefb(const struct screen_info *si,
 	memset(&res, 0, sizeof(res));
 	res.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	res.name = simplefb_resname;
-	res.start = si->lfb_base;
-	res.end = si->lfb_base + len - 1;
+	res.start = base;
+	res.end = res.start + length - 1;
 	if (res.end <= res.start)
 		return -EINVAL;
 

arch/x86/kernel/unwind_guess.c

@@ -7,11 +7,13 @@
 
 unsigned long unwind_get_return_address(struct unwind_state *state)
 {
+	unsigned long addr = READ_ONCE_NOCHECK(*state->sp);
+
 	if (unwind_done(state))
 		return 0;
 
 	return ftrace_graph_ret_addr(state->task, &state->graph_idx,
-				     *state->sp, state->sp);
+				     addr, state->sp);
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
@@ -23,8 +25,10 @@ bool unwind_next_frame(struct unwind_state *state)
 		return false;
 
 	do {
+		unsigned long addr = READ_ONCE_NOCHECK(*state->sp);
+
 		for (state->sp++; state->sp < info->end; state->sp++)
-			if (__kernel_text_address(*state->sp))
+			if (__kernel_text_address(addr))
 				return true;
 
 		state->sp = info->next_sp;

arch/x86/kvm/emulate.c

@@ -2105,16 +2105,10 @@ static int em_iret(struct x86_emulate_ctxt *ctxt)
 static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
-	unsigned short sel, old_sel;
-	struct desc_struct old_desc, new_desc;
-	const struct x86_emulate_ops *ops = ctxt->ops;
+	unsigned short sel;
+	struct desc_struct new_desc;
 	u8 cpl = ctxt->ops->cpl(ctxt);
 
-	/* Assignment of RIP may only fail in 64-bit mode */
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		ops->get_segment(ctxt, &old_sel, &old_desc, NULL,
-				 VCPU_SREG_CS);
-
 	memcpy(&sel, ctxt->src.valptr + ctxt->op_bytes, 2);
 
 	rc = __load_segment_descriptor(ctxt, sel, VCPU_SREG_CS, cpl,
@@ -2124,12 +2118,10 @@ static int em_jmp_far(struct x86_emulate_ctxt *ctxt)
 		return rc;
 
 	rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
-	if (rc != X86EMUL_CONTINUE) {
-		WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
-		/* assigning eip failed; restore the old cs */
-		ops->set_segment(ctxt, old_sel, &old_desc, 0, VCPU_SREG_CS);
-		return rc;
-	}
+	/* Error handling is not implemented. */
+	if (rc != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
 	return rc;
 }
 
@@ -2189,14 +2181,8 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 {
 	int rc;
 	unsigned long eip, cs;
-	u16 old_cs;
 	int cpl = ctxt->ops->cpl(ctxt);
-	struct desc_struct old_desc, new_desc;
-	const struct x86_emulate_ops *ops = ctxt->ops;
-
-	if (ctxt->mode == X86EMUL_MODE_PROT64)
-		ops->get_segment(ctxt, &old_cs, &old_desc, NULL,
-				 VCPU_SREG_CS);
+	struct desc_struct new_desc;
 
 	rc = emulate_pop(ctxt, &eip, ctxt->op_bytes);
 	if (rc != X86EMUL_CONTINUE)
@@ -2213,10 +2199,10 @@ static int em_ret_far(struct x86_emulate_ctxt *ctxt)
 	if (rc != X86EMUL_CONTINUE)
 		return rc;
 	rc = assign_eip_far(ctxt, eip, &new_desc);
-	if (rc != X86EMUL_CONTINUE) {
-		WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
-		ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
-	}
+	/* Error handling is not implemented. */
+	if (rc != X86EMUL_CONTINUE)
+		return X86EMUL_UNHANDLEABLE;
+
 	return rc;
 }
 

arch/x86/kvm/ioapic.c

@@ -94,7 +94,7 @@ static unsigned long ioapic_read_indirect(struct kvm_ioapic *ioapic,
 static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 {
 	ioapic->rtc_status.pending_eoi = 0;
-	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPUS);
+	bitmap_zero(ioapic->rtc_status.dest_map.map, KVM_MAX_VCPU_ID);
 }
 
 static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);

arch/x86/kvm/ioapic.h

@@ -42,13 +42,13 @@ struct kvm_vcpu;
 
 struct dest_map {
 	/* vcpu bitmap where IRQ has been sent */
-	DECLARE_BITMAP(map, KVM_MAX_VCPUS);
+	DECLARE_BITMAP(map, KVM_MAX_VCPU_ID);
 
 	/*
 	 * Vector sent to a given vcpu, only valid when
 	 * the vcpu's bit in map is set
 	 */
-	u8 vectors[KVM_MAX_VCPUS];
+	u8 vectors[KVM_MAX_VCPU_ID];
 };
 
 

arch/x86/kvm/irq_comm.c

@@ -41,6 +41,15 @@ static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
 			   bool line_status)
 {
 	struct kvm_pic *pic = pic_irqchip(kvm);
+
+	/*
+	 * XXX: rejecting pic routes when pic isn't in use would be better,
+	 * but the default routing table is installed while kvm->arch.vpic is
+	 * NULL and KVM_CREATE_IRQCHIP can race with KVM_IRQ_LINE.
+	 */
+	if (!pic)
+		return -1;
+
 	return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
 }
 
@@ -49,6 +58,10 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
 			      bool line_status)
 {
 	struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+	if (!ioapic)
+		return -1;
+
 	return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
 				line_status);
 }
@@ -156,6 +169,16 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 }
 
 
+static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
+		    struct kvm *kvm, int irq_source_id, int level,
+		    bool line_status)
+{
+	if (!level)
+		return -1;
+
+	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
+}
+
 int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 			      struct kvm *kvm, int irq_source_id, int level,
 			      bool line_status)
@@ -163,18 +186,26 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	struct kvm_lapic_irq irq;
 	int r;
 
-	if (unlikely(e->type != KVM_IRQ_ROUTING_MSI))
-		return -EWOULDBLOCK;
+	switch (e->type) {
+	case KVM_IRQ_ROUTING_HV_SINT:
+		return kvm_hv_set_sint(e, kvm, irq_source_id, level,
+				       line_status);
 
-	if (kvm_msi_route_invalid(kvm, e))
-		return -EINVAL;
+	case KVM_IRQ_ROUTING_MSI:
+		if (kvm_msi_route_invalid(kvm, e))
+			return -EINVAL;
 
-	kvm_set_msi_irq(kvm, e, &irq);
+		kvm_set_msi_irq(kvm, e, &irq);
 
-	if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
-		return r;
-	else
-		return -EWOULDBLOCK;
+		if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+			return r;
+		break;
+
+	default:
+		break;
+	}
+
+	return -EWOULDBLOCK;
 }
 
 int kvm_request_irq_source_id(struct kvm *kvm)
@@ -254,16 +285,6 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
-		    struct kvm *kvm, int irq_source_id, int level,
-		    bool line_status)
-{
-	if (!level)
-		return -1;
-
-	return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
-}
-
 int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue)
@@ -423,18 +444,6 @@ void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
 	srcu_read_unlock(&kvm->irq_srcu, idx);
 }
 
-int kvm_arch_set_irq(struct kvm_kernel_irq_routing_entry *irq, struct kvm *kvm,
-		     int irq_source_id, int level, bool line_status)
-{
-	switch (irq->type) {
-	case KVM_IRQ_ROUTING_HV_SINT:
-		return kvm_hv_set_sint(irq, kvm, irq_source_id, level,
-				       line_status);
-	default:
-		return -EWOULDBLOCK;
-	}
-}
-
 void kvm_arch_irq_routing_update(struct kvm *kvm)
 {
 	kvm_hv_irq_routing_update(kvm);

arch/x86/kvm/lapic.c

@@ -138,7 +138,7 @@ static inline bool kvm_apic_map_get_logical_dest(struct kvm_apic_map *map,
 		*mask = dest_id & 0xff;
 		return true;
 	case KVM_APIC_MODE_XAPIC_CLUSTER:
-		*cluster = map->xapic_cluster_map[dest_id >> 4];
+		*cluster = map->xapic_cluster_map[(dest_id >> 4) & 0xf];
 		*mask = dest_id & 0xf;
 		return true;
 	default:

arch/x86/kvm/x86.c

@@ -210,7 +210,18 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 	struct kvm_shared_msrs *locals
 		= container_of(urn, struct kvm_shared_msrs, urn);
 	struct kvm_shared_msr_values *values;
+	unsigned long flags;
 
+	/*
+	 * Disabling irqs at this point since the following code could be
+	 * interrupted and executed through kvm_arch_hardware_disable()
+	 */
+	local_irq_save(flags);
+	if (locals->registered) {
+		locals->registered = false;
+		user_return_notifier_unregister(urn);
+	}
+	local_irq_restore(flags);
 	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
 		values = &locals->values[slot];
 		if (values->host != values->curr) {
@@ -218,8 +229,6 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
 			values->curr = values->host;
 		}
 	}
-	locals->registered = false;
-	user_return_notifier_unregister(urn);
 }
 
 static void shared_msr_update(unsigned slot, u32 msr)
@@ -1724,18 +1733,23 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
 
 static u64 __get_kvmclock_ns(struct kvm *kvm)
 {
-	struct kvm_vcpu *vcpu = kvm_get_vcpu(kvm, 0);
 	struct kvm_arch *ka = &kvm->arch;
-	s64 ns;
+	struct pvclock_vcpu_time_info hv_clock;
 
-	if (vcpu->arch.hv_clock.flags & PVCLOCK_TSC_STABLE_BIT) {
-		u64 tsc = kvm_read_l1_tsc(vcpu, rdtsc());
-		ns = __pvclock_read_cycles(&vcpu->arch.hv_clock, tsc);
-	} else {
-		ns = ktime_get_boot_ns() + ka->kvmclock_offset;
+	spin_lock(&ka->pvclock_gtod_sync_lock);
+	if (!ka->use_master_clock) {
+		spin_unlock(&ka->pvclock_gtod_sync_lock);
+		return ktime_get_boot_ns() + ka->kvmclock_offset;
 	}
 
-	return ns;
+	hv_clock.tsc_timestamp = ka->master_cycle_now;
+	hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
+	spin_unlock(&ka->pvclock_gtod_sync_lock);
+
+	kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
+			   &hv_clock.tsc_shift,
+			   &hv_clock.tsc_to_system_mul);
+	return __pvclock_read_cycles(&hv_clock, rdtsc());
 }
 
 u64 get_kvmclock_ns(struct kvm *kvm)
@@ -2596,7 +2610,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_XEN_HVM:
-	case KVM_CAP_ADJUST_CLOCK:
 	case KVM_CAP_VCPU_EVENTS:
 	case KVM_CAP_HYPERV:
 	case KVM_CAP_HYPERV_VAPIC:
@@ -2623,6 +2636,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 #endif
 		r = 1;
 		break;
+	case KVM_CAP_ADJUST_CLOCK:
+		r = KVM_CLOCK_TSC_STABLE;
+		break;
 	case KVM_CAP_X86_SMM:
 		/* SMBASE is usually relocated above 1M on modern chipsets,
 		 * and SMM handlers might indeed rely on 4G segment limits,
@@ -3415,6 +3431,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	};
 	case KVM_SET_VAPIC_ADDR: {
 		struct kvm_vapic_addr va;
+		int idx;
 
 		r = -EINVAL;
 		if (!lapic_in_kernel(vcpu))
@@ -3422,7 +3439,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = -EFAULT;
 		if (copy_from_user(&va, argp, sizeof va))
 			goto out;
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_X86_SETUP_MCE: {
@@ -4103,9 +4122,11 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		struct kvm_clock_data user_ns;
 		u64 now_ns;
 
-		now_ns = get_kvmclock_ns(kvm);
+		local_irq_disable();
+		now_ns = __get_kvmclock_ns(kvm);
 		user_ns.clock = now_ns;
-		user_ns.flags = 0;
+		user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0;
+		local_irq_enable();
 		memset(&user_ns.pad, 0, sizeof(user_ns.pad));
 
 		r = -EFAULT;

arch/x86/mm/extable.c

@@ -135,7 +135,12 @@ void __init early_fixup_exception(struct pt_regs *regs, int trapnr)
 	if (early_recursion_flag > 2)
 		goto halt_loop;
 
-	if (regs->cs != __KERNEL_CS)
+	/*
+	 * 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.
+	 */
+	if ((regs->cs & 0xFFFF) != __KERNEL_CS)
 		goto fail;
 
 	/*

arch/x86/platform/efi/efi.c

@@ -861,7 +861,7 @@ static void __init __efi_enter_virtual_mode(void)
 	int count = 0, pg_shift = 0;
 	void *new_memmap = NULL;
 	efi_status_t status;
-	phys_addr_t pa;
+	unsigned long pa;
 
 	efi.systab = NULL;
 

arch/x86/platform/efi/efi_64.c

@@ -31,6 +31,7 @@
 #include <linux/io.h>
 #include <linux/reboot.h>
 #include <linux/slab.h>
+#include <linux/ucs2_string.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
@@ -211,6 +212,35 @@ void efi_sync_low_kernel_mappings(void)
 	memcpy(pud_efi, pud_k, sizeof(pud_t) * num_entries);
 }
 
+/*
+ * Wrapper for slow_virt_to_phys() that handles NULL addresses.
+ */
+static inline phys_addr_t
+virt_to_phys_or_null_size(void *va, unsigned long size)
+{
+	bool bad_size;
+
+	if (!va)
+		return 0;
+
+	if (virt_addr_valid(va))
+		return virt_to_phys(va);
+
+	/*
+	 * A fully aligned variable on the stack is guaranteed not to
+	 * cross a page bounary. Try to catch strings on the stack by
+	 * checking that 'size' is a power of two.
+	 */
+	bad_size = size > PAGE_SIZE || !is_power_of_2(size);
+
+	WARN_ON(!IS_ALIGNED((unsigned long)va, size) || bad_size);
+
+	return slow_virt_to_phys(va);
+}
+
+#define virt_to_phys_or_null(addr)				\
+	virt_to_phys_or_null_size((addr), sizeof(*(addr)))
+
 int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
 	unsigned long pfn, text;
@@ -494,8 +524,8 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 
 	spin_lock(&rtc_lock);
 
-	phys_tm = virt_to_phys(tm);
-	phys_tc = virt_to_phys(tc);
+	phys_tm = virt_to_phys_or_null(tm);
+	phys_tc = virt_to_phys_or_null(tc);
 
 	status = efi_thunk(get_time, phys_tm, phys_tc);
 
@@ -511,7 +541,7 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm)
 
 	spin_lock(&rtc_lock);
 
-	phys_tm = virt_to_phys(tm);
+	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_time, phys_tm);
 
@@ -529,9 +559,9 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 
 	spin_lock(&rtc_lock);
 
-	phys_enabled = virt_to_phys(enabled);
-	phys_pending = virt_to_phys(pending);
-	phys_tm = virt_to_phys(tm);
+	phys_enabled = virt_to_phys_or_null(enabled);
+	phys_pending = virt_to_phys_or_null(pending);
+	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(get_wakeup_time, phys_enabled,
 			     phys_pending, phys_tm);
@@ -549,7 +579,7 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 
 	spin_lock(&rtc_lock);
 
-	phys_tm = virt_to_phys(tm);
+	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_wakeup_time, enabled, phys_tm);
 
@@ -558,6 +588,10 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 	return status;
 }
 
+static unsigned long efi_name_size(efi_char16_t *name)
+{
+	return ucs2_strsize(name, EFI_VAR_NAME_LEN) + 1;
+}
 
 static efi_status_t
 efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
@@ -567,11 +601,11 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	u32 phys_name, phys_vendor, phys_attr;
 	u32 phys_data_size, phys_data;
 
-	phys_data_size = virt_to_phys(data_size);
-	phys_vendor = virt_to_phys(vendor);
-	phys_name = virt_to_phys(name);
-	phys_attr = virt_to_phys(attr);
-	phys_data = virt_to_phys(data);
+	phys_data_size = virt_to_phys_or_null(data_size);
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_attr = virt_to_phys_or_null(attr);
+	phys_data = virt_to_phys_or_null_size(data, *data_size);
 
 	status = efi_thunk(get_variable, phys_name, phys_vendor,
 			   phys_attr, phys_data_size, phys_data);
@@ -586,9 +620,9 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	u32 phys_name, phys_vendor, phys_data;
 	efi_status_t status;
 
-	phys_name = virt_to_phys(name);
-	phys_vendor = virt_to_phys(vendor);
-	phys_data = virt_to_phys(data);
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
 
 	/* If data_size is > sizeof(u32) we've got problems */
 	status = efi_thunk(set_variable, phys_name, phys_vendor,
@@ -605,9 +639,9 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 	efi_status_t status;
 	u32 phys_name_size, phys_name, phys_vendor;
 
-	phys_name_size = virt_to_phys(name_size);
-	phys_vendor = virt_to_phys(vendor);
-	phys_name = virt_to_phys(name);
+	phys_name_size = virt_to_phys_or_null(name_size);
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_name = virt_to_phys_or_null_size(name, *name_size);
 
 	status = efi_thunk(get_next_variable, phys_name_size,
 			   phys_name, phys_vendor);
@@ -621,7 +655,7 @@ efi_thunk_get_next_high_mono_count(u32 *count)
 	efi_status_t status;
 	u32 phys_count;
 
-	phys_count = virt_to_phys(count);
+	phys_count = virt_to_phys_or_null(count);
 	status = efi_thunk(get_next_high_mono_count, phys_count);
 
 	return status;
@@ -633,7 +667,7 @@ efi_thunk_reset_system(int reset_type, efi_status_t status,
 {
 	u32 phys_data;
 
-	phys_data = virt_to_phys(data);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
 
 	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
 }
@@ -661,9 +695,9 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
-	phys_storage = virt_to_phys(storage_space);
-	phys_remaining = virt_to_phys(remaining_space);
-	phys_max = virt_to_phys(max_variable_size);
+	phys_storage = virt_to_phys_or_null(storage_space);
+	phys_remaining = virt_to_phys_or_null(remaining_space);
+	phys_max = virt_to_phys_or_null(max_variable_size);
 
 	status = efi_thunk(query_variable_info, attr, phys_storage,
 			   phys_remaining, phys_max);

arch/x86/platform/intel-mid/device_libs/Makefile

@@ -28,4 +28,4 @@ obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_pcal9555a.o
 obj-$(subst m,y,$(CONFIG_GPIO_PCA953X)) += platform_tca6416.o
 # MISC Devices
 obj-$(subst m,y,$(CONFIG_KEYBOARD_GPIO)) += platform_gpio_keys.o
-obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_wdt.o
+obj-$(subst m,y,$(CONFIG_INTEL_MID_WATCHDOG)) += platform_mrfld_wdt.o

arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c

@@ -1,5 +1,5 @@
 /*
- * platform_wdt.c: Watchdog platform library file
+ * Intel Merrifield watchdog platform device library file
  *
  * (C) Copyright 2014 Intel Corporation
  * Author: David Cohen <david.a.cohen@linux.intel.com>
@@ -14,7 +14,9 @@
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
 #include <linux/platform_data/intel-mid_wdt.h>
+
 #include <asm/intel-mid.h>
+#include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
 
 #define TANGIER_EXT_TIMER0_MSI 15
@@ -50,14 +52,34 @@ static struct intel_mid_wdt_pdata tangier_pdata = {
 	.probe = tangier_probe,
 };
 
-static int __init register_mid_wdt(void)
+static int wdt_scu_status_change(struct notifier_block *nb,
+				 unsigned long code, void *data)
 {
-	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER) {
-		wdt_dev.dev.platform_data = &tangier_pdata;
-		return platform_device_register(&wdt_dev);
+	if (code == SCU_DOWN) {
+		platform_device_unregister(&wdt_dev);
+		return 0;
 	}
 
-	return -ENODEV;
+	return platform_device_register(&wdt_dev);
 }
 
+static struct notifier_block wdt_scu_notifier = {
+	.notifier_call	= wdt_scu_status_change,
+};
+
+static int __init register_mid_wdt(void)
+{
+	if (intel_mid_identify_cpu() != INTEL_MID_CPU_CHIP_TANGIER)
+		return -ENODEV;
+
+	wdt_dev.dev.platform_data = &tangier_pdata;
+
+	/*
+	 * We need to be sure that the SCU IPC is ready before watchdog device
+	 * can be registered:
+	 */
+	intel_scu_notifier_add(&wdt_scu_notifier);
+
+	return 0;
+}
 rootfs_initcall(register_mid_wdt);

arch/x86/platform/intel-mid/pwr.c

@@ -272,6 +272,25 @@ int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state)
 }
 EXPORT_SYMBOL_GPL(intel_mid_pci_set_power_state);
 
+pci_power_t intel_mid_pci_get_power_state(struct pci_dev *pdev)
+{
+	struct mid_pwr *pwr = midpwr;
+	int id, reg, bit;
+	u32 power;
+
+	if (!pwr || !pwr->available)
+		return PCI_UNKNOWN;
+
+	id = intel_mid_pwr_get_lss_id(pdev);
+	if (id < 0)
+		return PCI_UNKNOWN;
+
+	reg = (id * LSS_PWS_BITS) / 32;
+	bit = (id * LSS_PWS_BITS) % 32;
+	power = mid_pwr_get_state(pwr, reg);
+	return (__force pci_power_t)((power >> bit) & 3);
+}
+
 void intel_mid_pwr_power_off(void)
 {
 	struct mid_pwr *pwr = midpwr;

arch/x86/purgatory/Makefile

@@ -16,6 +16,7 @@ KCOV_INSTRUMENT := n
 
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes -fno-zero-initialized-in-bss -fno-builtin -ffreestanding -c -MD -Os -mcmodel=large
 KBUILD_CFLAGS += -m$(BITS)
+KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)