16 files changed, 217 insertions, 60 deletions

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 4433a4be8171..b9e30daa0881 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -611,20 +611,20 @@ void __init acpi_pic_sci_set_trigger(unsigned int irq, u16 trigger)
 
 int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
 {
-	int irq;
-
-	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
-		*irqp = gsi;
-	} else {
-		mutex_lock(&acpi_ioapic_lock);
-		irq = mp_map_gsi_to_irq(gsi,
-					IOAPIC_MAP_ALLOC | IOAPIC_MAP_CHECK);
-		mutex_unlock(&acpi_ioapic_lock);
-		if (irq < 0)
-			return -1;
-		*irqp = irq;
+	int rc, irq, trigger, polarity;
+
+	rc = acpi_get_override_irq(gsi, &trigger, &polarity);
+	if (rc == 0) {
+		trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
+		polarity = polarity ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
+		irq = acpi_register_gsi(NULL, gsi, trigger, polarity);
+		if (irq >= 0) {
+			*irqp = irq;
+			return 0;
+		}
 	}
-	return 0;
+
+	return -1;
 }
 EXPORT_SYMBOL_GPL(acpi_gsi_to_irq);
 
@@ -750,13 +750,13 @@ static int _acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
 }
 
 /* wrapper to silence section mismatch warning */
-int __ref acpi_map_lsapic(acpi_handle handle, int physid, int *pcpu)
+int __ref acpi_map_cpu(acpi_handle handle, int physid, int *pcpu)
 {
 	return _acpi_map_lsapic(handle, physid, pcpu);
 }
-EXPORT_SYMBOL(acpi_map_lsapic);
+EXPORT_SYMBOL(acpi_map_cpu);
 
-int acpi_unmap_lsapic(int cpu)
+int acpi_unmap_cpu(int cpu)
 {
 #ifdef CONFIG_ACPI_NUMA
 	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
@@ -768,8 +768,7 @@ int acpi_unmap_lsapic(int cpu)
 
 	return (0);
 }
-
-EXPORT_SYMBOL(acpi_unmap_lsapic);
+EXPORT_SYMBOL(acpi_unmap_cpu);
 #endif				/* CONFIG_ACPI_HOTPLUG_CPU */
 
 int acpi_register_ioapic(acpi_handle handle, u64 phys_addr, u32 gsi_base)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index e27b49d7c922..80091ae54c2b 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -66,3 +66,4 @@ targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE
 	$(call if_changed,mkcapflags)
 endif
+clean-files += capflags.c
diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh
index e2b22df964cd..36d99a337b49 100644
--- a/arch/x86/kernel/cpu/mkcapflags.sh
+++ b/arch/x86/kernel/cpu/mkcapflags.sh
@@ -28,7 +28,7 @@ function dump_array()
 		# If the /* comment */ starts with a quote string, grab that.
 		VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')"
 		[ -z "$VALUE" ] && VALUE="\"$NAME\""
-		[ "$VALUE" == '""' ] && continue
+		[ "$VALUE" = '""' ] && continue
 
 		# Name is uppercase, VALUE is all lowercase
 		VALUE="$(echo "$VALUE" | tr A-Z a-z)"
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a450373e8e91..939155ffdece 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -107,6 +107,7 @@ static struct clocksource hyperv_cs = {
 	.rating		= 400, /* use this when running on Hyperv*/
 	.read		= read_hv_clock,
 	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static void __init ms_hyperv_init_platform(void)
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 944bf019b74f..498b6d967138 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2431,6 +2431,7 @@ __init int intel_pmu_init(void)
 		break;
 
 	case 55: /* 22nm Atom "Silvermont"                */
+	case 76: /* 14nm Atom "Airmont"                   */
 	case 77: /* 22nm Atom "Silvermont Avoton/Rangely" */
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 3c895d480cd7..073983398364 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -568,8 +568,8 @@ struct event_constraint intel_atom_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_slm_pebs_event_constraints[] = {
-	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
-	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
+	/* INST_RETIRED.ANY_P, inv=1, cmask=16 (cycles:p). */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x108000c0, 0x1),
 	/* Allow all events as PEBS with no flags */
 	INTEL_ALL_EVENT_CONSTRAINT(0, 0x1),
 	EVENT_CONSTRAINT_END
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 673f930c700f..c4bb8b8e5017 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -103,6 +103,13 @@ static struct kobj_attribute format_attr_##_var =		\
 
 #define RAPL_CNTR_WIDTH 32 /* 32-bit rapl counters */
 
+#define RAPL_EVENT_ATTR_STR(_name, v, str)				\
+static struct perf_pmu_events_attr event_attr_##v = {			\
+	.attr		= __ATTR(_name, 0444, rapl_sysfs_show, NULL),	\
+	.id		= 0,						\
+	.event_str	= str,						\
+};
+
 struct rapl_pmu {
 	spinlock_t	 lock;
 	int		 hw_unit;  /* 1/2^hw_unit Joule */
@@ -135,7 +142,7 @@ static inline u64 rapl_scale(u64 v)
 	 * or use ldexp(count, -32).
 	 * Watts = Joules/Time delta
 	 */
-	return v << (32 - __this_cpu_read(rapl_pmu->hw_unit));
+	return v << (32 - __this_cpu_read(rapl_pmu)->hw_unit);
 }
 
 static u64 rapl_event_update(struct perf_event *event)
@@ -379,23 +386,36 @@ static struct attribute_group rapl_pmu_attr_group = {
 	.attrs = rapl_pmu_attrs,
 };
 
-EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
-EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
-EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
-EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
+static ssize_t rapl_sysfs_show(struct device *dev,
+			       struct device_attribute *attr,
+			       char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr = \
+		container_of(attr, struct perf_pmu_events_attr, attr);
+
+	if (pmu_attr->event_str)
+		return sprintf(page, "%s", pmu_attr->event_str);
+
+	return 0;
+}
+
+RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
+RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
+RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
+RAPL_EVENT_ATTR_STR(energy-gpu  ,   rapl_gpu, "event=0x04");
 
-EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
-EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
-EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
-EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-cores.unit, rapl_cores_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-pkg.unit  ,   rapl_pkg_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-ram.unit  ,   rapl_ram_unit, "Joules");
+RAPL_EVENT_ATTR_STR(energy-gpu.unit  ,   rapl_gpu_unit, "Joules");
 
 /*
  * we compute in 0.23 nJ increments regardless of MSR
  */
-EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
-EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-cores.scale, rapl_cores_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-pkg.scale,     rapl_pkg_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-ram.scale,     rapl_ram_scale, "2.3283064365386962890625e-10");
+RAPL_EVENT_ATTR_STR(energy-gpu.scale,     rapl_gpu_scale, "2.3283064365386962890625e-10");
 
 static struct attribute *rapl_events_srv_attr[] = {
 	EVENT_PTR(rapl_cores),
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 10b8d3eaaf15..c635b8b49e93 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -840,7 +840,6 @@ static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id
 	box->phys_id = phys_id;
 	box->pci_dev = pdev;
 	box->pmu = pmu;
-	uncore_box_init(box);
 	pci_set_drvdata(pdev, box);
 
 	raw_spin_lock(&uncore_box_lock);
@@ -1004,10 +1003,8 @@ static int uncore_cpu_starting(int cpu)
 			pmu = &type->pmus[j];
 			box = *per_cpu_ptr(pmu->box, cpu);
 			/* called by uncore_cpu_init? */
-			if (box && box->phys_id >= 0) {
-				uncore_box_init(box);
+			if (box && box->phys_id >= 0)
 				continue;
-			}
 
 			for_each_online_cpu(k) {
 				exist = *per_cpu_ptr(pmu->box, k);
@@ -1023,10 +1020,8 @@ static int uncore_cpu_starting(int cpu)
 				}
 			}
 
-			if (box) {
+			if (box)
 				box->phys_id = phys_id;
-				uncore_box_init(box);
-			}
 		}
 	}
 	return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index 18eb78bbdd10..6c8c1e7e69d8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -17,7 +17,7 @@
 #define UNCORE_PCI_DEV_TYPE(data)	((data >> 8) & 0xff)
 #define UNCORE_PCI_DEV_IDX(data)	(data & 0xff)
 #define UNCORE_EXTRA_PCI_DEV		0xff
-#define UNCORE_EXTRA_PCI_DEV_MAX	2
+#define UNCORE_EXTRA_PCI_DEV_MAX	3
 
 /* support up to 8 sockets */
 #define UNCORE_SOCKET_MAX		8
@@ -257,6 +257,14 @@ static inline int uncore_num_counters(struct intel_uncore_box *box)
 	return box->pmu->type->num_counters;
 }
 
+static inline void uncore_box_init(struct intel_uncore_box *box)
+{
+	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
+		if (box->pmu->type->ops->init_box)
+			box->pmu->type->ops->init_box(box);
+	}
+}
+
 static inline void uncore_disable_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->type->ops->disable_box)
@@ -265,6 +273,8 @@ static inline void uncore_disable_box(struct intel_uncore_box *box)
 
 static inline void uncore_enable_box(struct intel_uncore_box *box)
 {
+	uncore_box_init(box);
+
 	if (box->pmu->type->ops->enable_box)
 		box->pmu->type->ops->enable_box(box);
 }
@@ -287,14 +297,6 @@ static inline u64 uncore_read_counter(struct intel_uncore_box *box,
 	return box->pmu->type->ops->read_counter(box, event);
 }
 
-static inline void uncore_box_init(struct intel_uncore_box *box)
-{
-	if (!test_and_set_bit(UNCORE_BOX_FLAG_INITIATED, &box->flags)) {
-		if (box->pmu->type->ops->init_box)
-			box->pmu->type->ops->init_box(box);
-	}
-}
-
 static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
 {
 	return (box->phys_id < 0);
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index 745b158e9a65..21af6149edf2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -891,6 +891,7 @@ void snbep_uncore_cpu_init(void)
 enum {
 	SNBEP_PCI_QPI_PORT0_FILTER,
 	SNBEP_PCI_QPI_PORT1_FILTER,
+	HSWEP_PCI_PCU_3,
 };
 
 static int snbep_qpi_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -2026,6 +2027,17 @@ void hswep_uncore_cpu_init(void)
 {
 	if (hswep_uncore_cbox.num_boxes > boot_cpu_data.x86_max_cores)
 		hswep_uncore_cbox.num_boxes = boot_cpu_data.x86_max_cores;
+
+	/* Detect 6-8 core systems with only two SBOXes */
+	if (uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3]) {
+		u32 capid4;
+
+		pci_read_config_dword(uncore_extra_pci_dev[0][HSWEP_PCI_PCU_3],
+				      0x94, &capid4);
+		if (((capid4 >> 6) & 0x3) == 0)
+			hswep_uncore_sbox.num_boxes = 2;
+	}
+
 	uncore_msr_uncores = hswep_msr_uncores;
 }
 
@@ -2287,6 +2299,11 @@ static DEFINE_PCI_DEVICE_TABLE(hswep_uncore_pci_ids) = {
 		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
 						   SNBEP_PCI_QPI_PORT1_FILTER),
 	},
+	{ /* PCU.3 (for Capability registers) */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x2fc0),
+		.driver_data = UNCORE_PCI_DEV_DATA(UNCORE_EXTRA_PCI_DEV,
+						   HSWEP_PCI_PCU_3),
+	},
 	{ /* end: all zeroes */ }
 };
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 2142376dc8c6..8b7b0a51e742 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -674,7 +674,7 @@ static inline void *alloc_tramp(unsigned long size)
 }
 static inline void tramp_free(void *tramp)
 {
-	module_free(NULL, tramp);
+	module_memfree(tramp);
 }
 #else
 /* Trampolines can only be created if modules are supported */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 6307a0f0cf17..705ef8d48e2d 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -127,7 +127,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	seq_puts(p, "  Machine check polls\n");
 #endif
 #if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
-	seq_printf(p, "%*s: ", prec, "THR");
+	seq_printf(p, "%*s: ", prec, "HYP");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
 	seq_puts(p, "  Hypervisor callback interrupts\n");
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index f7e3cd50ece0..98f654d466e5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -1020,6 +1020,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->flags &= ~X86_EFLAGS_IF;
 	trace_hardirqs_off();
 	regs->ip = (unsigned long)(jp->entry);
+
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer to get messed up.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -1048,24 +1057,25 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 	u8 *addr = (u8 *) (regs->ip - 1);
 	struct jprobe *jp = container_of(p, struct jprobe, kp);
+	void *saved_sp = kcb->jprobe_saved_sp;
 
 	if ((addr > (u8 *) jprobe_return) &&
 	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != kcb->jprobe_saved_sp) {
+		if (stack_addr(regs) != saved_sp) {
 			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
 			printk(KERN_ERR
 			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), kcb->jprobe_saved_sp);
+			       stack_addr(regs), saved_sp);
 			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
 			show_regs(saved_regs);
 			printk(KERN_ERR "Current registers\n");
 			show_regs(regs);
 			BUG();
 		}
+		/* It's OK to start function graph tracing again */
+		unpause_graph_tracing();
 		*regs = kcb->jprobe_saved_regs;
-		memcpy((kprobe_opcode_t *)(kcb->jprobe_saved_sp),
-		       kcb->jprobes_stack,
-		       MIN_STACK_SIZE(kcb->jprobe_saved_sp));
+		memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
 		preempt_enable_no_resched();
 		return 1;
 	}
diff --git a/arch/x86/kernel/perf_regs.c b/arch/x86/kernel/perf_regs.c
index e309cc5c276e..781861cc5ee8 100644
--- a/arch/x86/kernel/perf_regs.c
+++ b/arch/x86/kernel/perf_regs.c
@@ -78,6 +78,14 @@ u64 perf_reg_abi(struct task_struct *task)
 {
 	return PERF_SAMPLE_REGS_ABI_32;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	regs_user->regs = task_pt_regs(current);
+	regs_user->abi = perf_reg_abi(current);
+}
 #else /* CONFIG_X86_64 */
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
@@ -102,4 +110,86 @@ u64 perf_reg_abi(struct task_struct *task)
 	else
 		return PERF_SAMPLE_REGS_ABI_64;
 }
+
+void perf_get_regs_user(struct perf_regs *regs_user,
+			struct pt_regs *regs,
+			struct pt_regs *regs_user_copy)
+{
+	struct pt_regs *user_regs = task_pt_regs(current);
+
+	/*
+	 * If we're in an NMI that interrupted task_pt_regs setup, then
+	 * we can't sample user regs at all.  This check isn't really
+	 * sufficient, though, as we could be in an NMI inside an interrupt
+	 * that happened during task_pt_regs setup.
+	 */
+	if (regs->sp > (unsigned long)&user_regs->r11 &&
+	    regs->sp <= (unsigned long)(user_regs + 1)) {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
+		return;
+	}
+
+	/*
+	 * RIP, flags, and the argument registers are usually saved.
+	 * orig_ax is probably okay, too.
+	 */
+	regs_user_copy->ip = user_regs->ip;
+	regs_user_copy->cx = user_regs->cx;
+	regs_user_copy->dx = user_regs->dx;
+	regs_user_copy->si = user_regs->si;
+	regs_user_copy->di = user_regs->di;
+	regs_user_copy->r8 = user_regs->r8;
+	regs_user_copy->r9 = user_regs->r9;
+	regs_user_copy->r10 = user_regs->r10;
+	regs_user_copy->r11 = user_regs->r11;
+	regs_user_copy->orig_ax = user_regs->orig_ax;
+	regs_user_copy->flags = user_regs->flags;
+
+	/*
+	 * Don't even try to report the "rest" regs.
+	 */
+	regs_user_copy->bx = -1;
+	regs_user_copy->bp = -1;
+	regs_user_copy->r12 = -1;
+	regs_user_copy->r13 = -1;
+	regs_user_copy->r14 = -1;
+	regs_user_copy->r15 = -1;
+
+	/*
+	 * For this to be at all useful, we need a reasonable guess for
+	 * sp and the ABI.  Be careful: we're in NMI context, and we're
+	 * considering current to be the current task, so we should
+	 * be careful not to look at any other percpu variables that might
+	 * change during context switches.
+	 */
+	if (IS_ENABLED(CONFIG_IA32_EMULATION) &&
+	    task_thread_info(current)->status & TS_COMPAT) {
+		/* Easy case: we're in a compat syscall. */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	} else if (user_regs->orig_ax != -1) {
+		/*
+		 * We're probably in a 64-bit syscall.
+		 * Warning: this code is severely racy.  At least it's better
+		 * than just blindly copying user_regs.
+		 */
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_64;
+		regs_user_copy->sp = this_cpu_read(old_rsp);
+		regs_user_copy->cs = __USER_CS;
+		regs_user_copy->ss = __USER_DS;
+		regs_user_copy->cx = -1;  /* usually contains garbage */
+	} else {
+		/* We're probably in an interrupt or exception. */
+		regs_user->abi = user_64bit_mode(user_regs) ?
+			PERF_SAMPLE_REGS_ABI_64 : PERF_SAMPLE_REGS_ABI_32;
+		regs_user_copy->sp = user_regs->sp;
+		regs_user_copy->cs = user_regs->cs;
+		regs_user_copy->ss = user_regs->ss;
+	}
+
+	regs_user->regs = regs_user_copy;
+}
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c
index 4e942f31b1a7..7fc5e843f247 100644
--- a/arch/x86/kernel/tls.c
+++ b/arch/x86/kernel/tls.c
@@ -29,7 +29,28 @@ static int get_free_idx(void)
 
 static bool tls_desc_okay(const struct user_desc *info)
 {
-	if (LDT_empty(info))
+	/*
+	 * For historical reasons (i.e. no one ever documented how any
+	 * of the segmentation APIs work), user programs can and do
+	 * assume that a struct user_desc that's all zeros except for
+	 * entry_number means "no segment at all".  This never actually
+	 * worked.  In fact, up to Linux 3.19, a struct user_desc like
+	 * this would create a 16-bit read-write segment with base and
+	 * limit both equal to zero.
+	 *
+	 * That was close enough to "no segment at all" until we
+	 * hardened this function to disallow 16-bit TLS segments.  Fix
+	 * it up by interpreting these zeroed segments the way that they
+	 * were almost certainly intended to be interpreted.
+	 *
+	 * The correct way to ask for "no segment at all" is to specify
+	 * a user_desc that satisfies LDT_empty.  To keep everything
+	 * working, we accept both.
+	 *
+	 * Note that there's a similar kludge in modify_ldt -- look at
+	 * the distinction between modes 1 and 0x11.
+	 */
+	if (LDT_empty(info) || LDT_zero(info))
 		return true;
 
 	/*
@@ -71,7 +92,7 @@ static void set_tls_desc(struct task_struct *p, int idx,
 	cpu = get_cpu();
 
 	while (n-- > 0) {
-		if (LDT_empty(info))
+		if (LDT_empty(info) || LDT_zero(info))
 			desc->a = desc->b = 0;
 		else
 			fill_ldt(desc, info);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index b7e50bba3bbb..505449700e0c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -617,7 +617,7 @@ static unsigned long quick_pit_calibrate(void)
 			goto success;
 		}
 	}
-	pr_err("Fast TSC calibration failed\n");
+	pr_info("Fast TSC calibration failed\n");
 	return 0;
 
 success: