14 files changed, 128 insertions, 77 deletions

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 5c60bb162622..4f2821527014 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2547,7 +2547,9 @@ void __init setup_ioapic_dest(void)
 			mask = apic->target_cpus();
 
 		chip = irq_data_get_irq_chip(idata);
-		chip->irq_set_affinity(idata, mask, false);
+		/* Might be lapic_chip for irq 0 */
+		if (chip->irq_set_affinity)
+			chip->irq_set_affinity(idata, mask, false);
 	}
 }
 #endif
@@ -2907,6 +2909,7 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 	struct irq_data *irq_data;
 	struct mp_chip_data *data;
 	struct irq_alloc_info *info = arg;
+	unsigned long flags;
 
 	if (!info || nr_irqs > 1)
 		return -EINVAL;
@@ -2939,11 +2942,14 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq,
 
 	cfg = irqd_cfg(irq_data);
 	add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin);
+
+	local_irq_save(flags);
 	if (info->ioapic_entry)
 		mp_setup_entry(cfg, data, info->ioapic_entry);
 	mp_register_handler(virq, data->trigger);
 	if (virq < nr_legacy_irqs())
 		legacy_pic->mask(virq);
+	local_irq_restore(flags);
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG
 		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i Dest:%d)\n",
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 381c8b9b3a33..20e242ea1bc4 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -34,11 +34,10 @@
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
-static void (*hv_kexec_handler)(void);
-static void (*hv_crash_handler)(struct pt_regs *regs);
-
 #if IS_ENABLED(CONFIG_HYPERV)
 static void (*vmbus_handler)(void);
+static void (*hv_kexec_handler)(void);
+static void (*hv_crash_handler)(struct pt_regs *regs);
 
 void hyperv_vector_handler(struct pt_regs *regs)
 {
@@ -96,8 +95,8 @@ void hv_remove_crash_handler(void)
 	hv_crash_handler = NULL;
 }
 EXPORT_SYMBOL_GPL(hv_remove_crash_handler);
-#endif
 
+#ifdef CONFIG_KEXEC_CORE
 static void hv_machine_shutdown(void)
 {
 	if (kexec_in_progress && hv_kexec_handler)
@@ -111,7 +110,8 @@ static void hv_machine_crash_shutdown(struct pt_regs *regs)
 		hv_crash_handler(regs);
 	native_machine_crash_shutdown(regs);
 }
-
+#endif /* CONFIG_KEXEC_CORE */
+#endif /* CONFIG_HYPERV */
 
 static uint32_t  __init ms_hyperv_platform(void)
 {
@@ -186,8 +186,10 @@ static void __init ms_hyperv_init_platform(void)
 	no_timer_check = 1;
 #endif
 
+#if IS_ENABLED(CONFIG_HYPERV) && defined(CONFIG_KEXEC_CORE)
 	machine_ops.shutdown = hv_machine_shutdown;
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
+#endif
 	mark_tsc_unstable("running on Hyper-V");
 }
 
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5edf6d868fc1..165be83a7fa4 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -47,6 +47,7 @@ enum extra_reg_type {
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
 	EXTRA_REG_LBR   = 2,	/* lbr_select */
 	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
+	EXTRA_REG_FE    = 4,    /* fe_* */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3fefebfbdf4b..f63360be2238 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -205,6 +205,11 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	/*
+	 * Note the low 8 bits eventsel code is not a continuous field, containing
+	 * some #GPing bits. These are masked out.
+	 */
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
 	EVENT_EXTRA_END
 };
 
@@ -250,7 +255,7 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
-	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
 	EVENT_CONSTRAINT_END
 };
 
@@ -2891,6 +2896,8 @@ PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
 
+PMU_FORMAT_ATTR(frontend, "config1:0-23");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -2907,6 +2914,11 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static struct attribute *skl_format_attr[] = {
+	&format_attr_frontend.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -3516,7 +3528,8 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
+						  skl_format_attr);
 		WARN_ON(!x86_pmu.format_attrs);
 		x86_pmu.cpu_events = hsw_events_attrs;
 		pr_cont("Skylake events, ");
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
index 086b12eae794..f32ac13934f2 100644
--- a/arch/x86/kernel/cpu/perf_event_msr.c
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -10,12 +10,12 @@ enum perf_msr_id {
 	PERF_MSR_EVENT_MAX,
 };
 
-bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx)
 {
 	return boot_cpu_has(X86_FEATURE_APERFMPERF);
 }
 
-bool test_intel(int idx)
+static bool test_intel(int idx)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86 != 6)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 3d423a101fae..608fb26c7254 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -37,7 +37,7 @@ void init_scattered_cpuid_features(struct cpuinfo_x86 *c)
 		{ X86_FEATURE_PLN,		CR_EAX, 4, 0x00000006, 0 },
 		{ X86_FEATURE_PTS,		CR_EAX, 6, 0x00000006, 0 },
 		{ X86_FEATURE_HWP,		CR_EAX, 7, 0x00000006, 0 },
-		{ X86_FEATURE_HWP_NOITFY,	CR_EAX, 8, 0x00000006, 0 },
+		{ X86_FEATURE_HWP_NOTIFY,	CR_EAX, 8, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_ACT_WINDOW,	CR_EAX, 9, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_EPP,		CR_EAX,10, 0x00000006, 0 },
 		{ X86_FEATURE_HWP_PKG_REQ,	CR_EAX,11, 0x00000006, 0 },
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index e068d6683dba..74ca2fe7a0b3 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -185,10 +185,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_KEXEC_FILE
-static int get_nr_ram_ranges_callback(unsigned long start_pfn,
-				unsigned long nr_pfn, void *arg)
+static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
 {
-	int *nr_ranges = arg;
+	unsigned int *nr_ranges = arg;
 
 	(*nr_ranges)++;
 	return 0;
@@ -214,7 +213,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 
 	ced->image = image;
 
-	walk_system_ram_range(0, -1, &nr_ranges,
+	walk_system_ram_res(0, -1, &nr_ranges,
 				get_nr_ram_ranges_callback);
 
 	ced->max_nr_ranges = nr_ranges;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f68e48f5f6c2..c2130aef3f9d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -41,10 +41,18 @@
 #include <asm/timer.h>
 #include <asm/special_insns.h>
 
-/* nop stub */
-void _paravirt_nop(void)
-{
-}
+/*
+ * nop stub, which must not clobber anything *including the stack* to
+ * avoid confusing the entry prologues.
+ */
+extern void _paravirt_nop(void);
+asm (".pushsection .entry.text, \"ax\"\n"
+     ".global _paravirt_nop\n"
+     "_paravirt_nop:\n\t"
+     "ret\n\t"
+     ".size _paravirt_nop, . - _paravirt_nop\n\t"
+     ".type _paravirt_nop, @function\n\t"
+     ".popsection");
 
 /* identity function, which can be inlined */
 u32 _paravirt_ident_32(u32 x)
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1b55de1267cf..cd99433b8ba1 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -131,11 +131,12 @@ void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr,
 
 bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
 {
+	if (!*dev)
+		*dev = &x86_dma_fallback_dev;
+
 	*gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
 	*gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
 
-	if (!*dev)
-		*dev = &x86_dma_fallback_dev;
 	if (!is_device_dma_capable(*dev))
 		return false;
 	return true;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 6d0e62ae8516..9f7c21c22477 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -84,6 +84,9 @@ EXPORT_SYMBOL_GPL(idle_notifier_unregister);
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	memcpy(dst, src, arch_task_struct_size);
+#ifdef CONFIG_VM86
+	dst->thread.vm86 = NULL;
+#endif
 
 	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
 }
@@ -506,3 +509,58 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 	return randomize_range(mm->brk, range_end, 0) ? : mm->brk;
 }
 
+/*
+ * Called from fs/proc with a reference on @p to find the function
+ * which called into schedule(). This needs to be done carefully
+ * because the task might wake up and we might look at a stack
+ * changing under us.
+ */
+unsigned long get_wchan(struct task_struct *p)
+{
+	unsigned long start, bottom, top, sp, fp, ip;
+	int count = 0;
+
+	if (!p || p == current || p->state == TASK_RUNNING)
+		return 0;
+
+	start = (unsigned long)task_stack_page(p);
+	if (!start)
+		return 0;
+
+	/*
+	 * Layout of the stack page:
+	 *
+	 * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
+	 * PADDING
+	 * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
+	 * stack
+	 * ----------- bottom = start + sizeof(thread_info)
+	 * thread_info
+	 * ----------- start
+	 *
+	 * The tasks stack pointer points at the location where the
+	 * framepointer is stored. The data on the stack is:
+	 * ... IP FP ... IP FP
+	 *
+	 * We need to read FP and IP, so we need to adjust the upper
+	 * bound by another unsigned long.
+	 */
+	top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
+	top -= 2 * sizeof(unsigned long);
+	bottom = start + sizeof(struct thread_info);
+
+	sp = READ_ONCE(p->thread.sp);
+	if (sp < bottom || sp > top)
+		return 0;
+
+	fp = READ_ONCE_NOCHECK(*(unsigned long *)sp);
+	do {
+		if (fp < bottom || fp > top)
+			return 0;
+		ip = READ_ONCE_NOCHECK(*(unsigned long *)(fp + sizeof(unsigned long)));
+		if (!in_sched_functions(ip))
+			return ip;
+		fp = READ_ONCE_NOCHECK(*(unsigned long *)fp);
+	} while (count++ < 16 && p->state != TASK_RUNNING);
+	return 0;
+}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c13df2c735f8..737527b40e5b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -324,31 +324,3 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	return prev_p;
 }
-
-#define top_esp                (THREAD_SIZE - sizeof(unsigned long))
-#define top_ebp                (THREAD_SIZE - 2*sizeof(unsigned long))
-
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long bp, sp, ip;
-	unsigned long stack_page;
-	int count = 0;
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-	stack_page = (unsigned long)task_stack_page(p);
-	sp = p->thread.sp;
-	if (!stack_page || sp < stack_page || sp > top_esp+stack_page)
-		return 0;
-	/* include/asm-i386/system.h:switch_to() pushes bp last. */
-	bp = *(unsigned long *) sp;
-	do {
-		if (bp < stack_page || bp > top_ebp+stack_page)
-			return 0;
-		ip = *(unsigned long *) (bp+4);
-		if (!in_sched_functions(ip))
-			return ip;
-		bp = *(unsigned long *) bp;
-	} while (count++ < 16);
-	return 0;
-}
-
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 3c1bbcf12924..b35921a670b2 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -499,30 +499,6 @@ void set_personality_ia32(bool x32)
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);
 
-unsigned long get_wchan(struct task_struct *p)
-{
-	unsigned long stack;
-	u64 fp, ip;
-	int count = 0;
-
-	if (!p || p == current || p->state == TASK_RUNNING)
-		return 0;
-	stack = (unsigned long)task_stack_page(p);
-	if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE)
-		return 0;
-	fp = *(u64 *)(p->thread.sp);
-	do {
-		if (fp < (unsigned long)stack ||
-		    fp >= (unsigned long)stack+THREAD_SIZE)
-			return 0;
-		ip = *(u64 *)(fp+8);
-		if (!in_sched_functions(ip))
-			return ip;
-		fp = *(u64 *)fp;
-	} while (count++ < 16);
-	return 0;
-}
-
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr)
 {
 	int ret = 0;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index fdb7f2a2d328..a3cccbfc5f77 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1173,6 +1173,14 @@ void __init setup_arch(char **cmdline_p)
 	clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
 			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
 			KERNEL_PGD_PTRS);
+
+	/*
+	 * sync back low identity map too.  It is used for example
+	 * in the 32-bit EFI stub.
+	 */
+	clone_pgd_range(initial_page_table,
+			swapper_pg_dir     + KERNEL_PGD_BOUNDARY,
+			KERNEL_PGD_PTRS);
 #endif
 
 	tboot_probe();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index e0c198e5f920..892ee2e5ecbc 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -509,7 +509,7 @@ void __inquire_remote_apic(int apicid)
  */
 #define UDELAY_10MS_DEFAULT 10000
 
-static unsigned int init_udelay = UDELAY_10MS_DEFAULT;
+static unsigned int init_udelay = INT_MAX;
 
 static int __init cpu_init_udelay(char *str)
 {
@@ -522,13 +522,16 @@ early_param("cpu_init_udelay", cpu_init_udelay);
 static void __init smp_quirk_init_udelay(void)
 {
 	/* if cmdline changed it from default, leave it alone */
-	if (init_udelay != UDELAY_10MS_DEFAULT)
+	if (init_udelay != INT_MAX)
 		return;
 
 	/* if modern processor, use no delay */
 	if (((boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) && (boot_cpu_data.x86 == 6)) ||
 	    ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) && (boot_cpu_data.x86 >= 0xF)))
 		init_udelay = 0;
+
+	/* else, use legacy delay */
+	init_udelay = UDELAY_10MS_DEFAULT;
 }
 
 /*
@@ -657,7 +660,9 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 		/*
 		 * Give the other CPU some time to accept the IPI.
 		 */
-		if (init_udelay)
+		if (init_udelay == 0)
+			udelay(10);
+		else
 			udelay(300);
 
 		pr_debug("Startup point 1\n");
@@ -668,7 +673,9 @@ wakeup_secondary_cpu_via_init(int phys_apicid, unsigned long start_eip)
 		/*
 		 * Give the other CPU some time to accept the IPI.
 		 */
-		if (init_udelay)
+		if (init_udelay == 0)
+			udelay(10);
+		else
 			udelay(200);
 
 		if (maxlvt > 3)		/* Due to the Pentium erratum 3AP.  */