Merge tag 'v5.0-rc5' into rdma.git for-next

Linux 5.0-rc5

Needed to merge the include/uapi changes so we have an up to date
single-tree for these files. Patches already posted are also expected to
need this for dependencies.

117 files changed, 881 insertions, 449 deletions

diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index feed50ce89fa..caa270261521 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -3,23 +3,19 @@ generic-y += bugs.h
 generic-y += compat.h
 generic-y += device.h
 generic-y += div64.h
-generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += extable.h
-generic-y += fb.h
 generic-y += ftrace.h
 generic-y += hardirq.h
 generic-y += hw_irq.h
 generic-y += irq_regs.h
 generic-y += irq_work.h
-generic-y += kmap_types.h
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += msi.h
 generic-y += parport.h
-generic-y += pci.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += topology.h
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 49bfbd879caa..f1b86cef0905 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -216,6 +216,14 @@ struct bcr_fp_arcv2 {
 #endif
 };
 
+struct bcr_actionpoint {
+#ifdef CONFIG_CPU_BIG_ENDIAN
+	unsigned int pad:21, min:1, num:2, ver:8;
+#else
+	unsigned int ver:8, num:2, min:1, pad:21;
+#endif
+};
+
 #include <soc/arc/timers.h>
 
 struct bcr_bpu_arcompact {
@@ -283,7 +291,7 @@ struct cpuinfo_arc_cache {
 };
 
 struct cpuinfo_arc_bpu {
-	unsigned int ver, full, num_cache, num_pred;
+	unsigned int ver, full, num_cache, num_pred, ret_stk;
 };
 
 struct cpuinfo_arc_ccm {
@@ -302,7 +310,7 @@ struct cpuinfo_arc {
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
 			     fpu_sp:1, fpu_dp:1, dual:1, dual_enb:1, pad2:4,
-			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
+			     ap_num:4, ap_full:1, smart:1, rtt:1, pad3:1,
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
 	struct bcr_mpy extn_mpy;
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index ee9246184033..202b74c339f0 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -340,7 +340,7 @@ static inline __attribute__ ((const)) int __fls(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long word)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long word)
 {
 	if (!word)
 		return word;
@@ -400,9 +400,9 @@ static inline __attribute__ ((const)) int ffs(unsigned long x)
 /*
  * __ffs: Similar to ffs, but zero based (0-31)
  */
-static inline __attribute__ ((const)) int __ffs(unsigned long x)
+static inline __attribute__ ((const)) unsigned long __ffs(unsigned long x)
 {
-	int n;
+	unsigned long n;
 
 	asm volatile(
 	"	ffs.f	%0, %1		\n"  /* 0:31; 31(Z) if src 0 */
diff --git a/arch/arc/include/asm/perf_event.h b/arch/arc/include/asm/perf_event.h
index 9185541035cc..6958545390f0 100644
--- a/arch/arc/include/asm/perf_event.h
+++ b/arch/arc/include/asm/perf_event.h
@@ -103,7 +103,8 @@ static const char * const arc_pmu_ev_hw_map[] = {
 
 	/* counts condition */
 	[PERF_COUNT_HW_INSTRUCTIONS] = "iall",
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmp", /* Excludes ZOL jumps */
+	/* All jump instructions that are taken */
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = "ijmptak",
 	[PERF_COUNT_ARC_BPOK]         = "bpok",	  /* NP-NT, PT-T, PNT-NT */
 #ifdef CONFIG_ISA_ARCV2
 	[PERF_COUNT_HW_BRANCH_MISSES] = "bpmp",
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 8aec462d90fb..861a8aea51f9 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -1,15 +1,10 @@
-/*
- * Linux performance counter support for ARC700 series
- *
- * Copyright (C) 2013-2015 Synopsys, Inc. (www.synopsys.com)
- *
- * This code is inspired by the perf support of various other architectures.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Linux performance counter support for ARC CPUs.
+// This code is inspired by the perf support of various other architectures.
+//
+// Copyright (C) 2013-2018 Synopsys, Inc. (www.synopsys.com)
+
 #include <linux/errno.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
@@ -19,12 +14,31 @@
 #include <asm/arcregs.h>
 #include <asm/stacktrace.h>
 
+/* HW holds 8 symbols + one for null terminator */
+#define ARCPMU_EVENT_NAME_LEN	9
+
+enum arc_pmu_attr_groups {
+	ARCPMU_ATTR_GR_EVENTS,
+	ARCPMU_ATTR_GR_FORMATS,
+	ARCPMU_NR_ATTR_GR
+};
+
+struct arc_pmu_raw_event_entry {
+	char name[ARCPMU_EVENT_NAME_LEN];
+};
+
 struct arc_pmu {
 	struct pmu	pmu;
 	unsigned int	irq;
 	int		n_counters;
+	int		n_events;
 	u64		max_period;
 	int		ev_hw_idx[PERF_COUNT_ARC_HW_MAX];
+
+	struct arc_pmu_raw_event_entry	*raw_entry;
+	struct attribute		**attrs;
+	struct perf_pmu_events_attr	*attr;
+	const struct attribute_group	*attr_groups[ARCPMU_NR_ATTR_GR + 1];
 };
 
 struct arc_pmu_cpu {
@@ -49,6 +63,7 @@ static int callchain_trace(unsigned int addr, void *data)
 {
 	struct arc_callchain_trace *ctrl = data;
 	struct perf_callchain_entry_ctx *entry = ctrl->perf_stuff;
+
 	perf_callchain_store(entry, addr);
 
 	if (ctrl->depth++ < 3)
@@ -57,8 +72,8 @@ static int callchain_trace(unsigned int addr, void *data)
 	return -1;
 }
 
-void
-perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
+			   struct pt_regs *regs)
 {
 	struct arc_callchain_trace ctrl = {
 		.depth = 0,
@@ -68,8 +83,8 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	arc_unwind_core(NULL, regs, callchain_trace, &ctrl);
 }
 
-void
-perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
+void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+			 struct pt_regs *regs)
 {
 	/*
 	 * User stack can't be unwound trivially with kernel dwarf unwinder
@@ -82,10 +97,10 @@ static struct arc_pmu *arc_pmu;
 static DEFINE_PER_CPU(struct arc_pmu_cpu, arc_pmu_cpu);
 
 /* read counter #idx; note that counter# != event# on ARC! */
-static uint64_t arc_pmu_read_counter(int idx)
+static u64 arc_pmu_read_counter(int idx)
 {
-	uint32_t tmp;
-	uint64_t result;
+	u32 tmp;
+	u64 result;
 
 	/*
 	 * ARC supports making 'snapshots' of the counters, so we don't
@@ -94,7 +109,7 @@ static uint64_t arc_pmu_read_counter(int idx)
 	write_aux_reg(ARC_REG_PCT_INDEX, idx);
 	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
 	write_aux_reg(ARC_REG_PCT_CONTROL, tmp | ARC_REG_PCT_CONTROL_SN);
-	result = (uint64_t) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
+	result = (u64) (read_aux_reg(ARC_REG_PCT_SNAPH)) << 32;
 	result |= read_aux_reg(ARC_REG_PCT_SNAPL);
 
 	return result;
@@ -103,9 +118,9 @@ static uint64_t arc_pmu_read_counter(int idx)
 static void arc_perf_event_update(struct perf_event *event,
 				  struct hw_perf_event *hwc, int idx)
 {
-	uint64_t prev_raw_count = local64_read(&hwc->prev_count);
-	uint64_t new_raw_count = arc_pmu_read_counter(idx);
-	int64_t delta = new_raw_count - prev_raw_count;
+	u64 prev_raw_count = local64_read(&hwc->prev_count);
+	u64 new_raw_count = arc_pmu_read_counter(idx);
+	s64 delta = new_raw_count - prev_raw_count;
 
 	/*
 	 * We aren't afraid of hwc->prev_count changing beneath our feet
@@ -155,7 +170,7 @@ static int arc_pmu_event_init(struct perf_event *event)
 	int ret;
 
 	if (!is_sampling_event(event)) {
-		hwc->sample_period  = arc_pmu->max_period;
+		hwc->sample_period = arc_pmu->max_period;
 		hwc->last_period = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
@@ -192,6 +207,18 @@ static int arc_pmu_event_init(struct perf_event *event)
 		pr_debug("init cache event with h/w %08x \'%s\'\n",
 			 (int)hwc->config, arc_pmu_ev_hw_map[ret]);
 		return 0;
+
+	case PERF_TYPE_RAW:
+		if (event->attr.config >= arc_pmu->n_events)
+			return -ENOENT;
+
+		hwc->config |= event->attr.config;
+		pr_debug("init raw event with idx %lld \'%s\'\n",
+			 event->attr.config,
+			 arc_pmu->raw_entry[event->attr.config].name);
+
+		return 0;
+
 	default:
 		return -ENOENT;
 	}
@@ -200,7 +227,7 @@ static int arc_pmu_event_init(struct perf_event *event)
 /* starts all counters */
 static void arc_pmu_enable(struct pmu *pmu)
 {
-	uint32_t tmp;
+	u32 tmp;
 	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
 	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x1);
 }
@@ -208,7 +235,7 @@ static void arc_pmu_enable(struct pmu *pmu)
 /* stops all counters */
 static void arc_pmu_disable(struct pmu *pmu)
 {
-	uint32_t tmp;
+	u32 tmp;
 	tmp = read_aux_reg(ARC_REG_PCT_CONTROL);
 	write_aux_reg(ARC_REG_PCT_CONTROL, (tmp & 0xffff0000) | 0x0);
 }
@@ -228,7 +255,7 @@ static int arc_pmu_event_set_period(struct perf_event *event)
 		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		overflow = 1;
-	} else	if (unlikely(left <= 0)) {
+	} else if (unlikely(left <= 0)) {
 		/* left underflowed by less than period. */
 		left += period;
 		local64_set(&hwc->period_left, left);
@@ -246,8 +273,8 @@ static int arc_pmu_event_set_period(struct perf_event *event)
 	write_aux_reg(ARC_REG_PCT_INDEX, idx);
 
 	/* Write value */
-	write_aux_reg(ARC_REG_PCT_COUNTL, (u32)value);
-	write_aux_reg(ARC_REG_PCT_COUNTH, (value >> 32));
+	write_aux_reg(ARC_REG_PCT_COUNTL, lower_32_bits(value));
+	write_aux_reg(ARC_REG_PCT_COUNTH, upper_32_bits(value));
 
 	perf_event_update_userpage(event);
 
@@ -277,7 +304,7 @@ static void arc_pmu_start(struct perf_event *event, int flags)
 	/* Enable interrupt for this counter */
 	if (is_sampling_event(event))
 		write_aux_reg(ARC_REG_PCT_INT_CTRL,
-			      read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
 
 	/* enable ARC pmu here */
 	write_aux_reg(ARC_REG_PCT_INDEX, idx);		/* counter # */
@@ -295,9 +322,9 @@ static void arc_pmu_stop(struct perf_event *event, int flags)
 		 * Reset interrupt flag by writing of 1. This is required
 		 * to make sure pending interrupt was not left.
 		 */
-		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+		write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
 		write_aux_reg(ARC_REG_PCT_INT_CTRL,
-			      read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~(1 << idx));
+			      read_aux_reg(ARC_REG_PCT_INT_CTRL) & ~BIT(idx));
 	}
 
 	if (!(event->hw.state & PERF_HES_STOPPED)) {
@@ -349,9 +376,10 @@ static int arc_pmu_add(struct perf_event *event, int flags)
 
 	if (is_sampling_event(event)) {
 		/* Mimic full counter overflow as other arches do */
-		write_aux_reg(ARC_REG_PCT_INT_CNTL, (u32)arc_pmu->max_period);
+		write_aux_reg(ARC_REG_PCT_INT_CNTL,
+			      lower_32_bits(arc_pmu->max_period));
 		write_aux_reg(ARC_REG_PCT_INT_CNTH,
-			      (arc_pmu->max_period >> 32));
+			      upper_32_bits(arc_pmu->max_period));
 	}
 
 	write_aux_reg(ARC_REG_PCT_CONFIG, 0);
@@ -392,7 +420,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 		idx = __ffs(active_ints);
 
 		/* Reset interrupt flag by writing of 1 */
-		write_aux_reg(ARC_REG_PCT_INT_ACT, 1 << idx);
+		write_aux_reg(ARC_REG_PCT_INT_ACT, BIT(idx));
 
 		/*
 		 * On reset of "interrupt active" bit corresponding
@@ -400,7 +428,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 		 * Now we need to re-enable interrupt for the counter.
 		 */
 		write_aux_reg(ARC_REG_PCT_INT_CTRL,
-			read_aux_reg(ARC_REG_PCT_INT_CTRL) | (1 << idx));
+			read_aux_reg(ARC_REG_PCT_INT_CTRL) | BIT(idx));
 
 		event = pmu_cpu->act_counter[idx];
 		hwc = &event->hw;
@@ -414,7 +442,7 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 				arc_pmu_stop(event, 0);
 		}
 
-		active_ints &= ~(1U << idx);
+		active_ints &= ~BIT(idx);
 	} while (active_ints);
 
 done:
@@ -441,19 +469,108 @@ static void arc_cpu_pmu_irq_init(void *data)
 	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
 }
 
+/* Event field occupies the bottom 15 bits of our config field */
+PMU_FORMAT_ATTR(event, "config:0-14");
+static struct attribute *arc_pmu_format_attrs[] = {
+	&format_attr_event.attr,
+	NULL,
+};
+
+static struct attribute_group arc_pmu_format_attr_gr = {
+	.name = "format",
+	.attrs = arc_pmu_format_attrs,
+};
+
+static ssize_t arc_pmu_events_sysfs_show(struct device *dev,
+					 struct device_attribute *attr,
+					 char *page)
+{
+	struct perf_pmu_events_attr *pmu_attr;
+
+	pmu_attr = container_of(attr, struct perf_pmu_events_attr, attr);
+	return sprintf(page, "event=0x%04llx\n", pmu_attr->id);
+}
+
+/*
+ * We don't add attrs here as we don't have pre-defined list of perf events.
+ * We will generate and add attrs dynamically in probe() after we read HW
+ * configuration.
+ */
+static struct attribute_group arc_pmu_events_attr_gr = {
+	.name = "events",
+};
+
+static void arc_pmu_add_raw_event_attr(int j, char *str)
+{
+	memmove(arc_pmu->raw_entry[j].name, str, ARCPMU_EVENT_NAME_LEN - 1);
+	arc_pmu->attr[j].attr.attr.name = arc_pmu->raw_entry[j].name;
+	arc_pmu->attr[j].attr.attr.mode = VERIFY_OCTAL_PERMISSIONS(0444);
+	arc_pmu->attr[j].attr.show = arc_pmu_events_sysfs_show;
+	arc_pmu->attr[j].id = j;
+	arc_pmu->attrs[j] = &(arc_pmu->attr[j].attr.attr);
+}
+
+static int arc_pmu_raw_alloc(struct device *dev)
+{
+	arc_pmu->attr = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+		sizeof(*arc_pmu->attr), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->attr)
+		return -ENOMEM;
+
+	arc_pmu->attrs = devm_kmalloc_array(dev, arc_pmu->n_events + 1,
+		sizeof(*arc_pmu->attrs), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->attrs)
+		return -ENOMEM;
+
+	arc_pmu->raw_entry = devm_kmalloc_array(dev, arc_pmu->n_events,
+		sizeof(*arc_pmu->raw_entry), GFP_KERNEL | __GFP_ZERO);
+	if (!arc_pmu->raw_entry)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline bool event_in_hw_event_map(int i, char *name)
+{
+	if (!arc_pmu_ev_hw_map[i])
+		return false;
+
+	if (!strlen(arc_pmu_ev_hw_map[i]))
+		return false;
+
+	if (strcmp(arc_pmu_ev_hw_map[i], name))
+		return false;
+
+	return true;
+}
+
+static void arc_pmu_map_hw_event(int j, char *str)
+{
+	int i;
+
+	/* See if HW condition has been mapped to a perf event_id */
+	for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
+		if (event_in_hw_event_map(i, str)) {
+			pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
+				 i, str, j);
+			arc_pmu->ev_hw_idx[i] = j;
+		}
+	}
+}
+
 static int arc_pmu_device_probe(struct platform_device *pdev)
 {
 	struct arc_reg_pct_build pct_bcr;
 	struct arc_reg_cc_build cc_bcr;
-	int i, j, has_interrupts;
+	int i, has_interrupts;
 	int counter_size;	/* in bits */
 
 	union cc_name {
 		struct {
-			uint32_t word0, word1;
+			u32 word0, word1;
 			char sentinel;
 		} indiv;
-		char str[9];
+		char str[ARCPMU_EVENT_NAME_LEN];
 	} cc_name;
 
 
@@ -463,15 +580,22 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 	BUILD_BUG_ON(ARC_PERF_MAX_COUNTERS > 32);
-	BUG_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS);
+	if (WARN_ON(pct_bcr.c > ARC_PERF_MAX_COUNTERS))
+		return -EINVAL;
 
 	READ_BCR(ARC_REG_CC_BUILD, cc_bcr);
-	BUG_ON(!cc_bcr.v); /* Counters exist but No countable conditions ? */
+	if (WARN(!cc_bcr.v, "Counters exist but No countable conditions?"))
+		return -EINVAL;
 
 	arc_pmu = devm_kzalloc(&pdev->dev, sizeof(struct arc_pmu), GFP_KERNEL);
 	if (!arc_pmu)
 		return -ENOMEM;
 
+	arc_pmu->n_events = cc_bcr.c;
+
+	if (arc_pmu_raw_alloc(&pdev->dev))
+		return -ENOMEM;
+
 	has_interrupts = is_isa_arcv2() ? pct_bcr.i : 0;
 
 	arc_pmu->n_counters = pct_bcr.c;
@@ -481,30 +605,26 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 	pr_info("ARC perf\t: %d counters (%d bits), %d conditions%s\n",
 		arc_pmu->n_counters, counter_size, cc_bcr.c,
-		has_interrupts ? ", [overflow IRQ support]":"");
+		has_interrupts ? ", [overflow IRQ support]" : "");
 
-	cc_name.str[8] = 0;
+	cc_name.str[ARCPMU_EVENT_NAME_LEN - 1] = 0;
 	for (i = 0; i < PERF_COUNT_ARC_HW_MAX; i++)
 		arc_pmu->ev_hw_idx[i] = -1;
 
 	/* loop thru all available h/w condition indexes */
-	for (j = 0; j < cc_bcr.c; j++) {
-		write_aux_reg(ARC_REG_CC_INDEX, j);
+	for (i = 0; i < cc_bcr.c; i++) {
+		write_aux_reg(ARC_REG_CC_INDEX, i);
 		cc_name.indiv.word0 = read_aux_reg(ARC_REG_CC_NAME0);
 		cc_name.indiv.word1 = read_aux_reg(ARC_REG_CC_NAME1);
 
-		/* See if it has been mapped to a perf event_id */
-		for (i = 0; i < ARRAY_SIZE(arc_pmu_ev_hw_map); i++) {
-			if (arc_pmu_ev_hw_map[i] &&
-			    !strcmp(arc_pmu_ev_hw_map[i], cc_name.str) &&
-			    strlen(arc_pmu_ev_hw_map[i])) {
-				pr_debug("mapping perf event %2d to h/w event \'%8s\' (idx %d)\n",
-					 i, cc_name.str, j);
-				arc_pmu->ev_hw_idx[i] = j;
-			}
-		}
+		arc_pmu_map_hw_event(i, cc_name.str);
+		arc_pmu_add_raw_event_attr(i, cc_name.str);
 	}
 
+	arc_pmu_events_attr_gr.attrs = arc_pmu->attrs;
+	arc_pmu->attr_groups[ARCPMU_ATTR_GR_EVENTS] = &arc_pmu_events_attr_gr;
+	arc_pmu->attr_groups[ARCPMU_ATTR_GR_FORMATS] = &arc_pmu_format_attr_gr;
+
 	arc_pmu->pmu = (struct pmu) {
 		.pmu_enable	= arc_pmu_enable,
 		.pmu_disable	= arc_pmu_disable,
@@ -514,6 +634,7 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 		.start		= arc_pmu_start,
 		.stop		= arc_pmu_stop,
 		.read		= arc_pmu_read,
+		.attr_groups	= arc_pmu->attr_groups,
 	};
 
 	if (has_interrupts) {
@@ -535,17 +656,19 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 	} else
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 
-	return perf_pmu_register(&arc_pmu->pmu, pdev->name, PERF_TYPE_RAW);
+	/*
+	 * perf parser doesn't really like '-' symbol in events name, so let's
+	 * use '_' in arc pct name as it goes to kernel PMU event prefix.
+	 */
+	return perf_pmu_register(&arc_pmu->pmu, "arc_pct", PERF_TYPE_RAW);
 }
 
-#ifdef CONFIG_OF
 static const struct of_device_id arc_pmu_match[] = {
 	{ .compatible = "snps,arc700-pct" },
 	{ .compatible = "snps,archs-pct" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, arc_pmu_match);
-#endif
 
 static struct platform_driver arc_pmu_driver = {
 	.driver	= {
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 2e018b8c2e19..feb90093e6b1 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -123,6 +123,7 @@ static void read_arc_build_cfg_regs(void)
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	const struct id_to_str *tbl;
 	struct bcr_isa_arcv2 isa;
+	struct bcr_actionpoint ap;
 
 	FIX_PTR(cpu);
 
@@ -195,6 +196,7 @@ static void read_arc_build_cfg_regs(void)
 		cpu->bpu.full = bpu.ft;
 		cpu->bpu.num_cache = 256 << bpu.bce;
 		cpu->bpu.num_pred = 2048 << bpu.pte;
+		cpu->bpu.ret_stk = 4 << bpu.rse;
 
 		if (cpu->core.family >= 0x54) {
 			unsigned int exec_ctrl;
@@ -207,8 +209,11 @@ static void read_arc_build_cfg_regs(void)
 		}
 	}
 
-	READ_BCR(ARC_REG_AP_BCR, bcr);
-	cpu->extn.ap = bcr.ver ? 1 : 0;
+	READ_BCR(ARC_REG_AP_BCR, ap);
+	if (ap.ver) {
+		cpu->extn.ap_num = 2 << ap.num;
+		cpu->extn.ap_full = !!ap.min;
+	}
 
 	READ_BCR(ARC_REG_SMART_BCR, bcr);
 	cpu->extn.smart = bcr.ver ? 1 : 0;
@@ -216,8 +221,6 @@ static void read_arc_build_cfg_regs(void)
 	READ_BCR(ARC_REG_RTT_BCR, bcr);
 	cpu->extn.rtt = bcr.ver ? 1 : 0;
 
-	cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
-
 	READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
 
 	/* some hacks for lack of feature BCR info in old ARC700 cores */
@@ -299,10 +302,10 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 
 	if (cpu->bpu.ver)
 		n += scnprintf(buf + n, len - n,
-			      "BPU\t\t: %s%s match, cache:%d, Predict Table:%d",
+			      "BPU\t\t: %s%s match, cache:%d, Predict Table:%d Return stk: %d",
 			      IS_AVAIL1(cpu->bpu.full, "full"),
 			      IS_AVAIL1(!cpu->bpu.full, "partial"),
-			      cpu->bpu.num_cache, cpu->bpu.num_pred);
+			      cpu->bpu.num_cache, cpu->bpu.num_pred, cpu->bpu.ret_stk);
 
 	if (is_isa_arcv2()) {
 		struct bcr_lpb lpb;
@@ -336,11 +339,17 @@ static char *arc_extn_mumbojumbo(int cpu_id, char *buf, int len)
 			       IS_AVAIL1(cpu->extn.fpu_sp, "SP "),
 			       IS_AVAIL1(cpu->extn.fpu_dp, "DP "));
 
-	if (cpu->extn.debug)
-		n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s%s\n",
-			       IS_AVAIL1(cpu->extn.ap, "ActionPoint "),
+	if (cpu->extn.ap_num | cpu->extn.smart | cpu->extn.rtt) {
+		n += scnprintf(buf + n, len - n, "DEBUG\t\t: %s%s",
 			       IS_AVAIL1(cpu->extn.smart, "smaRT "),
 			       IS_AVAIL1(cpu->extn.rtt, "RTT "));
+		if (cpu->extn.ap_num) {
+			n += scnprintf(buf + n, len - n, "ActionPoint %d/%s",
+				       cpu->extn.ap_num,
+				       cpu->extn.ap_full ? "full":"min");
+		}
+		n += scnprintf(buf + n, len - n, "\n");
+	}
 
 	if (cpu->dccm.sz || cpu->iccm.sz)
 		n += scnprintf(buf + n, len - n, "Extn [CCM]\t: DCCM @ %x, %d KB / ICCM: @ %x, %d KB\n",
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index e8d9fb452346..215f515442e0 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -18,6 +18,8 @@
 #include <asm/arcregs.h>
 #include <asm/irqflags.h>
 
+#define ARC_PATH_MAX	256
+
 /*
  * Common routine to print scratch regs (r0-r12) or callee regs (r13-r25)
  *   -Prints 3 regs per line and a CR.
@@ -58,11 +60,12 @@ static void show_callee_regs(struct callee_regs *cregs)
 	print_reg_file(&(cregs->r13), 13);
 }
 
-static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
+static void print_task_path_n_nm(struct task_struct *tsk)
 {
 	char *path_nm = NULL;
 	struct mm_struct *mm;
 	struct file *exe_file;
+	char buf[ARC_PATH_MAX];
 
 	mm = get_task_mm(tsk);
 	if (!mm)
@@ -72,7 +75,7 @@ static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 	mmput(mm);
 
 	if (exe_file) {
-		path_nm = file_path(exe_file, buf, 255);
+		path_nm = file_path(exe_file, buf, ARC_PATH_MAX-1);
 		fput(exe_file);
 	}
 
@@ -80,10 +83,9 @@ done:
 	pr_info("Path: %s\n", !IS_ERR(path_nm) ? path_nm : "?");
 }
 
-static void show_faulting_vma(unsigned long address, char *buf)
+static void show_faulting_vma(unsigned long address)
 {
 	struct vm_area_struct *vma;
-	char *nm = buf;
 	struct mm_struct *active_mm = current->active_mm;
 
 	/* can't use print_vma_addr() yet as it doesn't check for
@@ -96,8 +98,11 @@ static void show_faulting_vma(unsigned long address, char *buf)
 	 * if the container VMA is not found
 	 */
 	if (vma && (vma->vm_start <= address)) {
+		char buf[ARC_PATH_MAX];
+		char *nm = "?";
+
 		if (vma->vm_file) {
-			nm = file_path(vma->vm_file, buf, PAGE_SIZE - 1);
+			nm = file_path(vma->vm_file, buf, ARC_PATH_MAX-1);
 			if (IS_ERR(nm))
 				nm = "?";
 		}
@@ -173,13 +178,14 @@ void show_regs(struct pt_regs *regs)
 {
 	struct task_struct *tsk = current;
 	struct callee_regs *cregs;
-	char *buf;
 
-	buf = (char *)__get_free_page(GFP_KERNEL);
-	if (!buf)
-		return;
+	/*
+	 * generic code calls us with preemption disabled, but some calls
+	 * here could sleep, so re-enable to avoid lockdep splat
+	 */
+	preempt_enable();
 
-	print_task_path_n_nm(tsk, buf);
+	print_task_path_n_nm(tsk);
 	show_regs_print_info(KERN_INFO);
 
 	show_ecr_verbose(regs);
@@ -189,7 +195,7 @@ void show_regs(struct pt_regs *regs)
 		(void *)regs->blink, (void *)regs->ret);
 
 	if (user_mode(regs))
-		show_faulting_vma(regs->ret, buf); /* faulting code, not data */
+		show_faulting_vma(regs->ret); /* faulting code, not data */
 
 	pr_info("[STAT32]: 0x%08lx", regs->status32);
 
@@ -222,7 +228,7 @@ void show_regs(struct pt_regs *regs)
 	if (cregs)
 		show_callee_regs(cregs);
 
-	free_page((unsigned long)buf);
+	preempt_disable();
 }
 
 void show_kernel_fault_diag(const char *str, struct pt_regs *regs,
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 62ad4bcb841a..f230bb7092fd 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -7,11 +7,39 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/cache.h>
 
-#undef PREALLOC_NOT_AVAIL
+/*
+ * The memset implementation below is optimized to use prefetchw and prealloc
+ * instruction in case of CPU with 64B L1 data cache line (L1_CACHE_SHIFT == 6)
+ * If you want to implement optimized memset for other possible L1 data cache
+ * line lengths (32B and 128B) you should rewrite code carefully checking
+ * we don't call any prefetchw/prealloc instruction for L1 cache lines which
+ * don't belongs to memset area.
+ */
+
+#if L1_CACHE_SHIFT == 6
+
+.macro PREALLOC_INSTR	reg, off
+	prealloc	[\reg, \off]
+.endm
+
+.macro PREFETCHW_INSTR	reg, off
+	prefetchw	[\reg, \off]
+.endm
+
+#else
+
+.macro PREALLOC_INSTR
+.endm
+
+.macro PREFETCHW_INSTR
+.endm
+
+#endif
 
 ENTRY_CFI(memset)
-	prefetchw [r0]		; Prefetch the write location
+	PREFETCHW_INSTR	r0, 0	; Prefetch the first write location
 	mov.f	0, r2
 ;;; if size is zero
 	jz.d	[blink]
@@ -48,11 +76,8 @@ ENTRY_CFI(memset)
 
 	lpnz	@.Lset64bytes
 	;; LOOP START
-#ifdef PREALLOC_NOT_AVAIL
-	prefetchw [r3, 64]	;Prefetch the next write location
-#else
-	prealloc  [r3, 64]
-#endif
+	PREALLOC_INSTR	r3, 64	; alloc next line w/o fetching
+
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -85,7 +110,6 @@ ENTRY_CFI(memset)
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
-	prefetchw   [r3, 32]	;Prefetch the next write location
 #ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c
index a1d723197084..8df1638259f3 100644
--- a/arch/arc/mm/fault.c
+++ b/arch/arc/mm/fault.c
@@ -141,12 +141,17 @@ good_area:
 	 */
 	fault = handle_mm_fault(vma, address, flags);
 
-	/* If Pagefault was interrupted by SIGKILL, exit page fault "early" */
 	if (fatal_signal_pending(current)) {
-		if ((fault & VM_FAULT_ERROR) && !(fault & VM_FAULT_RETRY))
-			up_read(&mm->mmap_sem);
-		if (user_mode(regs))
+
+		/*
+		 * if fault retry, mmap_sem already relinquished by core mm
+		 * so OK to return to user mode (with signal handled first)
+		 */
+		if (fault & VM_FAULT_RETRY) {
+			if (!user_mode(regs))
+				goto no_context;
 			return;
+		}
 	}
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index 43bf4c3a1290..e1ab2d7f1d64 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -119,7 +119,8 @@ void __init setup_arch_memory(void)
 	 */
 
 	memblock_add_node(low_mem_start, low_mem_sz, 0);
-	memblock_reserve(low_mem_start, __pa(_end) - low_mem_start);
+	memblock_reserve(CONFIG_LINUX_LINK_BASE,
+			 __pa(_end) - CONFIG_LINUX_LINK_BASE);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (phys_initrd_size) {
diff --git a/arch/arm/include/asm/xen/page-coherent.h b/arch/arm/include/asm/xen/page-coherent.h
index b3ef061d8b74..2c403e7c782d 100644
--- a/arch/arm/include/asm/xen/page-coherent.h
+++ b/arch/arm/include/asm/xen/page-coherent.h
@@ -1 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM_XEN_PAGE_COHERENT_H
+#define _ASM_ARM_XEN_PAGE_COHERENT_H
+
+#include <linux/dma-mapping.h>
+#include <asm/page.h>
 #include <xen/arm/page-coherent.h>
+
+static inline const struct dma_map_ops *xen_get_dma_ops(struct device *dev)
+{
+	if (dev && dev->archdata.dev_dma_ops)
+		return dev->archdata.dev_dma_ops;
+	return get_arch_dma_ops(NULL);
+}
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
+{
+	return xen_get_dma_ops(hwdev)->alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
+{
+	xen_get_dma_ops(hwdev)->free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can span across
+	 * multiple Xen pages, it's not possible for it to contain a
+	 * mix of local and foreign Xen pages. So if the first xen_pfn
+	 * == mfn the page is local otherwise it's a foreign page
+	 * grant-mapped in dom0. If the page is local we can safely
+	 * call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
+	if (local)
+		xen_get_dma_ops(hwdev)->map_page(hwdev, page, offset, size, dir, attrs);
+	else
+		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+	 * foreign mfn will always return false. If the page is local we can
+	 * safely call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
+	if (pfn_valid(pfn)) {
+		if (xen_get_dma_ops(hwdev)->unmap_page)
+			xen_get_dma_ops(hwdev)->unmap_page(hwdev, handle, size, dir, attrs);
+	} else
+		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (xen_get_dma_ops(hwdev)->sync_single_for_cpu)
+			xen_get_dma_ops(hwdev)->sync_single_for_cpu(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn)) {
+		if (xen_get_dma_ops(hwdev)->sync_single_for_device)
+			xen_get_dma_ops(hwdev)->sync_single_for_device(hwdev, handle, size, dir);
+	} else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+#endif /* _ASM_ARM_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm/mach-cns3xxx/pcie.c b/arch/arm/mach-cns3xxx/pcie.c
index 318394ed5c7a..95a11d5b3587 100644
--- a/arch/arm/mach-cns3xxx/pcie.c
+++ b/arch/arm/mach-cns3xxx/pcie.c
@@ -83,7 +83,7 @@ static void __iomem *cns3xxx_pci_map_bus(struct pci_bus *bus,
 	} else /* remote PCI bus */
 		base = cnspci->cfg1_regs + ((busno & 0xf) << 20);
 
-	return base + (where & 0xffc) + (devfn << 12);
+	return base + where + (devfn << 12);
 }
 
 static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,
@@ -93,7 +93,7 @@ static int cns3xxx_pci_read_config(struct pci_bus *bus, unsigned int devfn,
 	u32 mask = (0x1ull << (size * 8)) - 1;
 	int shift = (where % 4) * 8;
 
-	ret = pci_generic_config_read32(bus, devfn, where, size, val);
+	ret = pci_generic_config_read(bus, devfn, where, size, val);
 
 	if (ret == PCIBIOS_SUCCESSFUL && !bus->number && !devfn &&
 	    (where & 0xffc) == PCI_CLASS_REVISION)
diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index eb43e09c1980..926434f413fa 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -60,8 +60,6 @@
 
 #ifdef CONFIG_KASAN_SW_TAGS
 #define ARCH_SLAB_MINALIGN	(1ULL << KASAN_SHADOW_SCALE_SHIFT)
-#else
-#define ARCH_SLAB_MINALIGN	__alignof__(unsigned long long)
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/arm64/include/asm/device.h b/arch/arm64/include/asm/device.h
index 3dd3d664c5c5..4658c937e173 100644
--- a/arch/arm64/include/asm/device.h
+++ b/arch/arm64/include/asm/device.h
@@ -20,9 +20,6 @@ struct dev_archdata {
 #ifdef CONFIG_IOMMU_API
 	void *iommu;			/* private IOMMU data */
 #endif
-#ifdef CONFIG_XEN
-	const struct dma_map_ops *dev_dma_ops;
-#endif
 };
 
 struct pdev_archdata {
diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h
index ac352accb3d9..3e8063f4f9d3 100644
--- a/arch/arm64/include/asm/mmu.h
+++ b/arch/arm64/include/asm/mmu.h
@@ -60,8 +60,11 @@ static inline bool arm64_kernel_use_ng_mappings(void)
 	 * later determine that kpti is required, then
 	 * kpti_install_ng_mappings() will make them non-global.
 	 */
+	if (arm64_kernel_unmapped_at_el0())
+		return true;
+
 	if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE))
-		return arm64_kernel_unmapped_at_el0();
+		return false;
 
 	/*
 	 * KASLR is enabled so we're going to be enabling kpti on non-broken
diff --git a/arch/arm64/include/asm/xen/page-coherent.h b/arch/arm64/include/asm/xen/page-coherent.h
index b3ef061d8b74..d88e56b90b93 100644
--- a/arch/arm64/include/asm/xen/page-coherent.h
+++ b/arch/arm64/include/asm/xen/page-coherent.h
@@ -1 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ARM64_XEN_PAGE_COHERENT_H
+#define _ASM_ARM64_XEN_PAGE_COHERENT_H
+
+#include <linux/dma-mapping.h>
+#include <asm/page.h>
 #include <xen/arm/page-coherent.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags, unsigned long attrs)
+{
+	return dma_direct_alloc(hwdev, size, dma_handle, flags, attrs);
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle, unsigned long attrs)
+{
+	dma_direct_free(hwdev, size, cpu_addr, dma_handle, attrs);
+}
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_cpu(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_cpu(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	if (pfn_valid(pfn))
+		dma_direct_sync_single_for_device(hwdev, handle, size, dir);
+	else
+		__xen_dma_sync_single_for_device(hwdev, handle, size, dir);
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     dma_addr_t dev_addr, unsigned long offset, size_t size,
+	     enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long page_pfn = page_to_xen_pfn(page);
+	unsigned long dev_pfn = XEN_PFN_DOWN(dev_addr);
+	unsigned long compound_pages =
+		(1<<compound_order(page)) * XEN_PFN_PER_PAGE;
+	bool local = (page_pfn <= dev_pfn) &&
+		(dev_pfn - page_pfn < compound_pages);
+
+	if (local)
+		dma_direct_map_page(hwdev, page, offset, size, dir, attrs);
+	else
+		__xen_dma_map_page(hwdev, page, dev_addr, offset, size, dir, attrs);
+}
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	unsigned long pfn = PFN_DOWN(handle);
+	/*
+	 * Dom0 is mapped 1:1, while the Linux page can be spanned accross
+	 * multiple Xen page, it's not possible to have a mix of local and
+	 * foreign Xen page. Dom0 is mapped 1:1, so calling pfn_valid on a
+	 * foreign mfn will always return false. If the page is local we can
+	 * safely call the native dma_ops function, otherwise we call the xen
+	 * specific function.
+	 */
+	if (pfn_valid(pfn))
+		dma_direct_unmap_page(hwdev, handle, size, dir, attrs);
+	else
+		__xen_dma_unmap_page(hwdev, handle, size, dir, attrs);
+}
+
+#endif /* _ASM_ARM64_XEN_PAGE_COHERENT_H */
diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c
index 29cdc99688f3..9859e1178e6b 100644
--- a/arch/arm64/kernel/hibernate.c
+++ b/arch/arm64/kernel/hibernate.c
@@ -299,8 +299,10 @@ int swsusp_arch_suspend(void)
 		dcache_clean_range(__idmap_text_start, __idmap_text_end);
 
 		/* Clean kvm setup code to PoC? */
-		if (el2_reset_needed())
+		if (el2_reset_needed()) {
 			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
+			dcache_clean_range(__hyp_text_start, __hyp_text_end);
+		}
 
 		/* make the crash dump kernel image protected again */
 		crash_post_resume();
diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S
index e1261fbaa374..17f325ba831e 100644
--- a/arch/arm64/kernel/hyp-stub.S
+++ b/arch/arm64/kernel/hyp-stub.S
@@ -28,6 +28,8 @@
 #include <asm/virt.h>
 
 	.text
+	.pushsection	.hyp.text, "ax"
+
 	.align 11
 
 ENTRY(__hyp_stub_vectors)
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index f0e6ab8abe9c..b09b6f75f759 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -14,6 +14,7 @@
 #include <linux/sched.h>
 #include <linux/types.h>
 
+#include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/memory.h>
@@ -43,7 +44,7 @@ static __init u64 get_kaslr_seed(void *fdt)
 	return ret;
 }
 
-static __init const u8 *get_cmdline(void *fdt)
+static __init const u8 *kaslr_get_cmdline(void *fdt)
 {
 	static __initconst const u8 default_cmdline[] = CONFIG_CMDLINE;
 
@@ -87,6 +88,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * we end up running with module randomization disabled.
 	 */
 	module_alloc_base = (u64)_etext - MODULES_VSIZE;
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
 
 	/*
 	 * Try to map the FDT early. If this fails, we simply bail,
@@ -109,7 +111,7 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	 * Check if 'nokaslr' appears on the command line, and
 	 * return 0 if that is the case.
 	 */
-	cmdline = get_cmdline(fdt);
+	cmdline = kaslr_get_cmdline(fdt);
 	str = strstr(cmdline, "nokaslr");
 	if (str == cmdline || (str > cmdline && *(str - 1) == ' '))
 		return 0;
@@ -169,5 +171,8 @@ u64 __init kaslr_early_init(u64 dt_phys)
 	module_alloc_base += (module_range * (seed & ((1 << 21) - 1))) >> 21;
 	module_alloc_base &= PAGE_MASK;
 
+	__flush_dcache_area(&module_alloc_base, sizeof(module_alloc_base));
+	__flush_dcache_area(&memstart_offset_seed, sizeof(memstart_offset_seed));
+
 	return offset;
 }
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 2a5b338b2542..f17afb99890c 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -478,13 +478,13 @@ bool arch_within_kprobe_blacklist(unsigned long addr)
 	    addr < (unsigned long)__entry_text_end) ||
 	    (addr >= (unsigned long)__idmap_text_start &&
 	    addr < (unsigned long)__idmap_text_end) ||
+	    (addr >= (unsigned long)__hyp_text_start &&
+	    addr < (unsigned long)__hyp_text_end) ||
 	    !!search_exception_tables(addr))
 		return true;
 
 	if (!is_kernel_in_hyp_mode()) {
-		if ((addr >= (unsigned long)__hyp_text_start &&
-		    addr < (unsigned long)__hyp_text_end) ||
-		    (addr >= (unsigned long)__hyp_idmap_text_start &&
+		if ((addr >= (unsigned long)__hyp_idmap_text_start &&
 		    addr < (unsigned long)__hyp_idmap_text_end))
 			return true;
 	}
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index fb0908456a1f..78c0a72f822c 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -466,9 +466,7 @@ void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);
 
 #ifdef CONFIG_XEN
-	if (xen_initial_domain()) {
-		dev->archdata.dev_dma_ops = dev->dma_ops;
+	if (xen_initial_domain())
 		dev->dma_ops = xen_dma_ops;
-	}
 #endif
 }
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 30695a868107..5c9073bace83 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -33,7 +33,11 @@ void sync_icache_aliases(void *kaddr, unsigned long len)
 		__clean_dcache_area_pou(kaddr, len);
 		__flush_icache_all();
 	} else {
-		flush_icache_range(addr, addr + len);
+		/*
+		 * Don't issue kick_all_cpus_sync() after I-cache invalidation
+		 * for user mappings.
+		 */
+		__flush_icache_range(addr, addr + len);
 	}
 }
 
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 33a2c94fed0d..63b4a1705182 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -30,6 +30,7 @@ generic-y += pgalloc.h
 generic-y += preempt.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += tlbflush.h
 generic-y += topology.h
 generic-y += trace_clock.h
diff --git a/arch/c6x/include/uapi/asm/Kbuild b/arch/c6x/include/uapi/asm/Kbuild
index 6c6f6301012e..0febf1a07c30 100644
--- a/arch/c6x/include/uapi/asm/Kbuild
+++ b/arch/c6x/include/uapi/asm/Kbuild
@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h
diff --git a/arch/h8300/Makefile b/arch/h8300/Makefile
index 4003ddc616e1..f801f3708a89 100644
--- a/arch/h8300/Makefile
+++ b/arch/h8300/Makefile
@@ -37,8 +37,6 @@ libs-y	+= arch/$(ARCH)/lib/
 
 boot := arch/h8300/boot
 
-archmrproper:
-
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index cd400d353d18..961c1dc064e1 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -40,6 +40,7 @@ generic-y += preempt.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += spinlock.h
 generic-y += timex.h
diff --git a/arch/h8300/include/uapi/asm/Kbuild b/arch/h8300/include/uapi/asm/Kbuild
index 6c6f6301012e..0febf1a07c30 100644
--- a/arch/h8300/include/uapi/asm/Kbuild
+++ b/arch/h8300/include/uapi/asm/Kbuild
@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 47c4da3d64a4..b25fd42aa0f4 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -30,6 +30,7 @@ generic-y += rwsem.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += topology.h
 generic-y += trace_clock.h
diff --git a/arch/hexagon/include/uapi/asm/Kbuild b/arch/hexagon/include/uapi/asm/Kbuild
index 61d955c1747a..c1b06dcf6cf8 100644
--- a/arch/hexagon/include/uapi/asm/Kbuild
+++ b/arch/hexagon/include/uapi/asm/Kbuild
@@ -1,4 +1,3 @@
 include include/uapi/asm-generic/Kbuild.asm
 
-generic-y += shmparam.h
 generic-y += ucontext.h
diff --git a/arch/ia64/Makefile b/arch/ia64/Makefile
index 320d86f192ee..171290f9f1de 100644
--- a/arch/ia64/Makefile
+++ b/arch/ia64/Makefile
@@ -16,8 +16,6 @@ KBUILD_DEFCONFIG := generic_defconfig
 NM := $(CROSS_COMPILE)nm -B
 READELF := $(CROSS_COMPILE)readelf
 
-export AWK
-
 CHECKFLAGS	+= -D__ia64=1 -D__ia64__=1 -D_LP64 -D__LP64__
 
 OBJCOPYFLAGS	:= --strip-all
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 9f1dd26903e3..95f8f631c4df 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -20,6 +20,7 @@ generic-y += mm-arch-hooks.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += sections.h
+generic-y += shmparam.h
 generic-y += spinlock.h
 generic-y += topology.h
 generic-y += trace_clock.h
diff --git a/arch/m68k/include/uapi/asm/Kbuild b/arch/m68k/include/uapi/asm/Kbuild
index b8b3525271fa..960bf1e4be53 100644
--- a/arch/m68k/include/uapi/asm/Kbuild
+++ b/arch/m68k/include/uapi/asm/Kbuild
@@ -2,4 +2,3 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generated-y += unistd_32.h
 generic-y += kvm_para.h
-generic-y += shmparam.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 9c7d1d25bf3d..791cc8d54d0a 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -26,6 +26,7 @@ generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += syscalls.h
 generic-y += topology.h
 generic-y += trace_clock.h
diff --git a/arch/microblaze/include/uapi/asm/Kbuild b/arch/microblaze/include/uapi/asm/Kbuild
index 28823e3db825..97823ec46e97 100644
--- a/arch/microblaze/include/uapi/asm/Kbuild
+++ b/arch/microblaze/include/uapi/asm/Kbuild
@@ -2,5 +2,4 @@ include include/uapi/asm-generic/Kbuild.asm
 
 generated-y += unistd_32.h
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 787290781b8c..0d14f51d0002 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -3155,6 +3155,7 @@ config MIPS32_O32
 config MIPS32_N32
 	bool "Kernel support for n32 binaries"
 	depends on 64BIT
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	select COMPAT
 	select MIPS32_COMPAT
 	select SYSVIPC_COMPAT if SYSVIPC
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index 6054d49e608e..fe3773539eff 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -173,6 +173,31 @@ void __init plat_mem_setup(void)
 	pm_power_off = bcm47xx_machine_halt;
 }
 
+#ifdef CONFIG_BCM47XX_BCMA
+static struct device * __init bcm47xx_setup_device(void)
+{
+	struct device *dev;
+	int err;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	err = dev_set_name(dev, "bcm47xx_soc");
+	if (err) {
+		pr_err("Failed to set SoC device name: %d\n", err);
+		kfree(dev);
+		return NULL;
+	}
+
+	err = dma_coerce_mask_and_coherent(dev, DMA_BIT_MASK(32));
+	if (err)
+		pr_err("Failed to set SoC DMA mask: %d\n", err);
+
+	return dev;
+}
+#endif
+
 /*
  * This finishes bus initialization doing things that were not possible without
  * kmalloc. Make sure to call it late enough (after mm_init).
@@ -183,6 +208,10 @@ void __init bcm47xx_bus_setup(void)
 	if (bcm47xx_bus_type == BCM47XX_BUS_TYPE_BCMA) {
 		int err;
 
+		bcm47xx_bus.bcma.dev = bcm47xx_setup_device();
+		if (!bcm47xx_bus.bcma.dev)
+			panic("Failed to setup SoC device\n");
+
 		err = bcma_host_soc_init(&bcm47xx_bus.bcma);
 		if (err)
 			panic("Failed to initialize BCMA bus (err %d)", err);
@@ -235,6 +264,8 @@ static int __init bcm47xx_register_bus_complete(void)
 #endif
 #ifdef CONFIG_BCM47XX_BCMA
 	case BCM47XX_BUS_TYPE_BCMA:
+		if (device_register(bcm47xx_bus.bcma.dev))
+			pr_err("Failed to register SoC device\n");
 		bcma_bus_register(&bcm47xx_bus.bcma.bus);
 		break;
 #endif
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 2c79ab52977a..8bf43c5a7bc7 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -98,7 +98,7 @@ static void octeon_kexec_smp_down(void *ignored)
 	"	sync						\n"
 	"	synci	($0)					\n");
 
-	relocated_kexec_smp_wait(NULL);
+	kexec_reboot();
 }
 #endif
 
diff --git a/arch/mips/configs/ath79_defconfig b/arch/mips/configs/ath79_defconfig
index 4e4ec779f182..6f981af67826 100644
--- a/arch/mips/configs/ath79_defconfig
+++ b/arch/mips/configs/ath79_defconfig
@@ -66,6 +66,7 @@ CONFIG_SERIAL_8250_CONSOLE=y
 # CONFIG_SERIAL_8250_PCI is not set
 CONFIG_SERIAL_8250_NR_UARTS=1
 CONFIG_SERIAL_8250_RUNTIME_UARTS=1
+CONFIG_SERIAL_OF_PLATFORM=y
 CONFIG_SERIAL_AR933X=y
 CONFIG_SERIAL_AR933X_CONSOLE=y
 # CONFIG_HW_RANDOM is not set
diff --git a/arch/mips/include/asm/mach-lantiq/falcon/falcon_irq.h b/arch/mips/include/asm/mach-lantiq/falcon/falcon_irq.h
index c6b63a409641..6dd8ad2409dc 100644
--- a/arch/mips/include/asm/mach-lantiq/falcon/falcon_irq.h
+++ b/arch/mips/include/asm/mach-lantiq/falcon/falcon_irq.h
@@ -18,8 +18,6 @@
 #define INT_NUM_EXTRA_START		(INT_NUM_IM4_IRL0 + 32)
 #define INT_NUM_IM_OFFSET		(INT_NUM_IM1_IRL0 - INT_NUM_IM0_IRL0)
 
-#define MIPS_CPU_TIMER_IRQ			7
-
 #define MAX_IM			5
 
 #endif /* _FALCON_IRQ__ */
diff --git a/arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h b/arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h
index 141076325307..0b424214a5e9 100644
--- a/arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h
+++ b/arch/mips/include/asm/mach-lantiq/xway/lantiq_irq.h
@@ -19,8 +19,6 @@
 
 #define LTQ_DMA_CH0_INT		(INT_NUM_IM2_IRL0)
 
-#define MIPS_CPU_TIMER_IRQ	7
-
 #define MAX_IM			5
 
 #endif
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index 6256d35dbf4d..bedb5047aff3 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -74,14 +74,15 @@ static int __init vdma_init(void)
 						    get_order(VDMA_PGTBL_SIZE));
 	BUG_ON(!pgtbl);
 	dma_cache_wback_inv((unsigned long)pgtbl, VDMA_PGTBL_SIZE);
-	pgtbl = (VDMA_PGTBL_ENTRY *)KSEG1ADDR(pgtbl);
+	pgtbl = (VDMA_PGTBL_ENTRY *)CKSEG1ADDR((unsigned long)pgtbl);
 
 	/*
 	 * Clear the R4030 translation table
 	 */
 	vdma_pgtbl_init();
 
-	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE, CPHYSADDR(pgtbl));
+	r4030_write_reg32(JAZZ_R4030_TRSTBL_BASE,
+			  CPHYSADDR((unsigned long)pgtbl));
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_LIM, VDMA_PGTBL_SIZE);
 	r4030_write_reg32(JAZZ_R4030_TRSTBL_INV, 0);
 
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index f0bc3312ed11..6549499eb202 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -224,9 +224,11 @@ static struct irq_chip ltq_eiu_type = {
 	.irq_set_type = ltq_eiu_settype,
 };
 
-static void ltq_hw_irqdispatch(int module)
+static void ltq_hw_irq_handler(struct irq_desc *desc)
 {
+	int module = irq_desc_get_irq(desc) - 2;
 	u32 irq;
+	int hwirq;
 
 	irq = ltq_icu_r32(module, LTQ_ICU_IM0_IOSR);
 	if (irq == 0)
@@ -237,7 +239,8 @@ static void ltq_hw_irqdispatch(int module)
 	 * other bits might be bogus
 	 */
 	irq = __fls(irq);
-	do_IRQ((int)irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module));
+	hwirq = irq + MIPS_CPU_IRQ_CASCADE + (INT_NUM_IM_OFFSET * module);
+	generic_handle_irq(irq_linear_revmap(ltq_domain, hwirq));
 
 	/* if this is a EBU irq, we need to ack it or get a deadlock */
 	if ((irq == LTQ_ICU_EBU_IRQ) && (module == 0) && LTQ_EBU_PCC_ISTAT)
@@ -245,49 +248,6 @@ static void ltq_hw_irqdispatch(int module)
 			LTQ_EBU_PCC_ISTAT);
 }
 
-#define DEFINE_HWx_IRQDISPATCH(x)					\
-	static void ltq_hw ## x ## _irqdispatch(void)			\
-	{								\
-		ltq_hw_irqdispatch(x);					\
-	}
-DEFINE_HWx_IRQDISPATCH(0)
-DEFINE_HWx_IRQDISPATCH(1)
-DEFINE_HWx_IRQDISPATCH(2)
-DEFINE_HWx_IRQDISPATCH(3)
-DEFINE_HWx_IRQDISPATCH(4)
-
-#if MIPS_CPU_TIMER_IRQ == 7
-static void ltq_hw5_irqdispatch(void)
-{
-	do_IRQ(MIPS_CPU_TIMER_IRQ);
-}
-#else
-DEFINE_HWx_IRQDISPATCH(5)
-#endif
-
-static void ltq_hw_irq_handler(struct irq_desc *desc)
-{
-	ltq_hw_irqdispatch(irq_desc_get_irq(desc) - 2);
-}
-
-asmlinkage void plat_irq_dispatch(void)
-{
-	unsigned int pending = read_c0_status() & read_c0_cause() & ST0_IM;
-	int irq;
-
-	if (!pending) {
-		spurious_interrupt();
-		return;
-	}
-
-	pending >>= CAUSEB_IP;
-	while (pending) {
-		irq = fls(pending) - 1;
-		do_IRQ(MIPS_CPU_IRQ_BASE + irq);
-		pending &= ~BIT(irq);
-	}
-}
-
 static int icu_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw)
 {
 	struct irq_chip *chip = &ltq_irq_type;
@@ -343,38 +303,13 @@ int __init icu_of_init(struct device_node *node, struct device_node *parent)
 	for (i = 0; i < MAX_IM; i++)
 		irq_set_chained_handler(i + 2, ltq_hw_irq_handler);
 
-	if (cpu_has_vint) {
-		pr_info("Setting up vectored interrupts\n");
-		set_vi_handler(2, ltq_hw0_irqdispatch);
-		set_vi_handler(3, ltq_hw1_irqdispatch);
-		set_vi_handler(4, ltq_hw2_irqdispatch);
-		set_vi_handler(5, ltq_hw3_irqdispatch);
-		set_vi_handler(6, ltq_hw4_irqdispatch);
-		set_vi_handler(7, ltq_hw5_irqdispatch);
-	}
-
 	ltq_domain = irq_domain_add_linear(node,
 		(MAX_IM * INT_NUM_IM_OFFSET) + MIPS_CPU_IRQ_CASCADE,
 		&irq_domain_ops, 0);
 
-#ifndef CONFIG_MIPS_MT_SMP
-	set_c0_status(IE_IRQ0 | IE_IRQ1 | IE_IRQ2 |
-		IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#else
-	set_c0_status(IE_SW0 | IE_SW1 | IE_IRQ0 | IE_IRQ1 |
-		IE_IRQ2 | IE_IRQ3 | IE_IRQ4 | IE_IRQ5);
-#endif
-
 	/* tell oprofile which irq to use */
 	ltq_perfcount_irq = irq_create_mapping(ltq_domain, LTQ_PERF_IRQ);
 
-	/*
-	 * if the timer irq is not one of the mips irqs we need to
-	 * create a mapping
-	 */
-	if (MIPS_CPU_TIMER_IRQ != 7)
-		irq_create_mapping(ltq_domain, MIPS_CPU_TIMER_IRQ);
-
 	/* the external interrupts are optional and xway only */
 	eiu_node = of_find_compatible_node(NULL, NULL, "lantiq,eiu-xway");
 	if (eiu_node && !of_address_to_resource(eiu_node, 0, &res)) {
@@ -411,7 +346,7 @@ EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
-	return MIPS_CPU_TIMER_IRQ;
+	return CP0_LEGACY_COMPARE_IRQ;
 }
 
 static struct of_device_id __initdata of_irq_ids[] = {
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index 2a5bb849b10e..288b58b00dc8 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -369,7 +369,9 @@ int __init octeon_msi_initialize(void)
 	int irq;
 	struct irq_chip *msi;
 
-	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
+	if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_INVALID) {
+		return 0;
+	} else if (octeon_dma_bar_type == OCTEON_DMA_BAR_TYPE_PCIE) {
 		msi_rcv_reg[0] = CVMX_PEXP_NPEI_MSI_RCV0;
 		msi_rcv_reg[1] = CVMX_PEXP_NPEI_MSI_RCV1;
 		msi_rcv_reg[2] = CVMX_PEXP_NPEI_MSI_RCV2;
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 0a935c136ec2..ac3482882cf9 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -3,9 +3,6 @@ OBJCOPYFLAGS	:= -O binary -R .note -R .note.gnu.build-id -R .comment -S
 
 KBUILD_DEFCONFIG := defconfig
 
-comma = ,
-
-
 ifdef CONFIG_FUNCTION_TRACER
 arch-y += -malways-save-lp -mno-relax
 endif
@@ -54,8 +51,6 @@ endif
 boot := arch/nds32/boot
 core-y += $(boot)/dts/
 
-.PHONY: FORCE
-
 Image: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
@@ -68,9 +63,6 @@ prepare: vdso_prepare
 vdso_prepare: prepare0
 	$(Q)$(MAKE) $(build)=arch/nds32/kernel/vdso include/generated/vdso-offsets.h
 
-CLEAN_FILES += include/asm-nds32/constants.h*
-
-# We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
 	$(Q)$(MAKE) $(clean)=$(boot)
 
diff --git a/arch/openrisc/Makefile b/arch/openrisc/Makefile
index 70e06d34006c..bf10141c7426 100644
--- a/arch/openrisc/Makefile
+++ b/arch/openrisc/Makefile
@@ -20,7 +20,6 @@
 KBUILD_DEFCONFIG := or1ksim_defconfig
 
 OBJCOPYFLAGS    := -O binary -R .note -R .comment -S
-LDFLAGS_vmlinux :=
 LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 
 KBUILD_CFLAGS	+= -pipe -ffixed-r10 -D__linux__
@@ -50,5 +49,3 @@ else
 BUILTIN_DTB := n
 endif
 core-$(BUILTIN_DTB) += arch/openrisc/boot/dts/
-
-all: vmlinux
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index eb87cd8327c8..1f04844b6b82 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -34,6 +34,7 @@ generic-y += qrwlock_types.h
 generic-y += qrwlock.h
 generic-y += sections.h
 generic-y += segment.h
+generic-y += shmparam.h
 generic-y += string.h
 generic-y += switch_to.h
 generic-y += topology.h
diff --git a/arch/openrisc/include/uapi/asm/Kbuild b/arch/openrisc/include/uapi/asm/Kbuild
index 6c6f6301012e..0febf1a07c30 100644
--- a/arch/openrisc/include/uapi/asm/Kbuild
+++ b/arch/openrisc/include/uapi/asm/Kbuild
@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h
diff --git a/arch/powerpc/include/uapi/asm/perf_regs.h b/arch/powerpc/include/uapi/asm/perf_regs.h
index ff91192407d1..f599064dd8dc 100644
--- a/arch/powerpc/include/uapi/asm/perf_regs.h
+++ b/arch/powerpc/include/uapi/asm/perf_regs.h
@@ -47,6 +47,7 @@ enum perf_event_powerpc_regs {
 	PERF_REG_POWERPC_DAR,
 	PERF_REG_POWERPC_DSISR,
 	PERF_REG_POWERPC_SIER,
+	PERF_REG_POWERPC_MMCRA,
 	PERF_REG_POWERPC_MAX,
 };
 #endif /* _UAPI_ASM_POWERPC_PERF_REGS_H */
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 57deb1e9ffea..20cc816b3508 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -852,11 +852,12 @@ start_here:
 
 	/* set up the PTE pointers for the Abatron bdiGDB.
 	*/
-	tovirt(r6,r6)
 	lis	r5, abatron_pteptrs@h
 	ori	r5, r5, abatron_pteptrs@l
 	stw	r5, 0xf0(0)	/* Must match your Abatron config file */
 	tophys(r5,r5)
+	lis	r6, swapper_pg_dir@h
+	ori	r6, r6, swapper_pg_dir@l
 	stw	r6, 0(r5)
 
 /* Now turn on the MMU for real! */
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index bd5e6834ca69..6794466f6420 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -755,11 +755,12 @@ SYSCALL_DEFINE0(rt_sigreturn)
 		if (restore_tm_sigcontexts(current, &uc->uc_mcontext,
 					   &uc_transact->uc_mcontext))
 			goto badframe;
-	}
+	} else
 #endif
-	/* Fall through, for non-TM restore */
-	if (!MSR_TM_ACTIVE(msr)) {
+	{
 		/*
+		 * Fall through, for non-TM restore
+		 *
 		 * Unset MSR[TS] on the thread regs since MSR from user
 		 * context does not have MSR active, and recheckpoint was
 		 * not called since restore_tm_sigcontexts() was not called
diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c
index 29746dc28df5..517662a56bdc 100644
--- a/arch/powerpc/kernel/trace/ftrace.c
+++ b/arch/powerpc/kernel/trace/ftrace.c
@@ -967,13 +967,6 @@ out:
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
-#if defined(CONFIG_FTRACE_SYSCALLS) && defined(CONFIG_PPC64)
-unsigned long __init arch_syscall_addr(int nr)
-{
-	return sys_call_table[nr*2];
-}
-#endif /* CONFIG_FTRACE_SYSCALLS && CONFIG_PPC64 */
-
 #ifdef PPC64_ELF_ABI_v1
 char *arch_ftrace_match_adjust(char *str, const char *search)
 {
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index 5c36b3a8d47a..3349f3f8fe84 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -70,6 +70,7 @@ static unsigned int pt_regs_offset[PERF_REG_POWERPC_MAX] = {
 	PT_REGS_OFFSET(PERF_REG_POWERPC_DAR, dar),
 	PT_REGS_OFFSET(PERF_REG_POWERPC_DSISR, dsisr),
 	PT_REGS_OFFSET(PERF_REG_POWERPC_SIER, dar),
+	PT_REGS_OFFSET(PERF_REG_POWERPC_MMCRA, dsisr),
 };
 
 u64 perf_reg_value(struct pt_regs *regs, int idx)
@@ -83,6 +84,11 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	    !is_sier_available()))
 		return 0;
 
+	if (idx == PERF_REG_POWERPC_MMCRA &&
+	   (IS_ENABLED(CONFIG_FSL_EMB_PERF_EVENT) ||
+	    IS_ENABLED(CONFIG_PPC32)))
+		return 0;
+
 	return regs_get_register(regs, pt_regs_offset[idx]);
 }
 
diff --git a/arch/powerpc/platforms/4xx/ocm.c b/arch/powerpc/platforms/4xx/ocm.c
index a1aaa1569d7c..f0e488d97567 100644
--- a/arch/powerpc/platforms/4xx/ocm.c
+++ b/arch/powerpc/platforms/4xx/ocm.c
@@ -237,12 +237,12 @@ static int ocm_debugfs_show(struct seq_file *m, void *v)
 			continue;
 
 		seq_printf(m, "PPC4XX OCM   : %d\n", ocm->index);
-		seq_printf(m, "PhysAddr     : %pa[p]\n", &(ocm->phys));
+		seq_printf(m, "PhysAddr     : %pa\n", &(ocm->phys));
 		seq_printf(m, "MemTotal     : %d Bytes\n", ocm->memtotal);
 		seq_printf(m, "MemTotal(NC) : %d Bytes\n", ocm->nc.memtotal);
 		seq_printf(m, "MemTotal(C)  : %d Bytes\n\n", ocm->c.memtotal);
 
-		seq_printf(m, "NC.PhysAddr  : %pa[p]\n", &(ocm->nc.phys));
+		seq_printf(m, "NC.PhysAddr  : %pa\n", &(ocm->nc.phys));
 		seq_printf(m, "NC.VirtAddr  : 0x%p\n", ocm->nc.virt);
 		seq_printf(m, "NC.MemTotal  : %d Bytes\n", ocm->nc.memtotal);
 		seq_printf(m, "NC.MemFree   : %d Bytes\n", ocm->nc.memfree);
@@ -252,7 +252,7 @@ static int ocm_debugfs_show(struct seq_file *m, void *v)
 							blk->size, blk->owner);
 		}
 
-		seq_printf(m, "\nC.PhysAddr   : %pa[p]\n", &(ocm->c.phys));
+		seq_printf(m, "\nC.PhysAddr   : %pa\n", &(ocm->c.phys));
 		seq_printf(m, "C.VirtAddr   : 0x%p\n", ocm->c.virt);
 		seq_printf(m, "C.MemTotal   : %d Bytes\n", ocm->c.memtotal);
 		seq_printf(m, "C.MemFree    : %d Bytes\n", ocm->c.memfree);
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index e66644e0fb40..9438fa0fc355 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -538,8 +538,7 @@ static void __init chrp_init_IRQ(void)
 	/* see if there is a keyboard in the device tree
 	   with a parent of type "adb" */
 	for_each_node_by_name(kbd, "keyboard")
-		if (kbd->parent && kbd->parent->type
-		    && strcmp(kbd->parent->type, "adb") == 0)
+		if (of_node_is_type(kbd->parent, "adb"))
 			break;
 	of_node_put(kbd);
 	if (kbd)
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index d7f742ed48ba..3f58c7dbd581 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -564,7 +564,7 @@ struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe)
 		}
 	} else {
 		/* Create a group for 1 GPU and attached NPUs for POWER8 */
-		pe->npucomp = kzalloc(sizeof(pe->npucomp), GFP_KERNEL);
+		pe->npucomp = kzalloc(sizeof(*pe->npucomp), GFP_KERNEL);
 		table_group = &pe->npucomp->table_group;
 		table_group->ops = &pnv_npu_peers_ops;
 		iommu_register_group(table_group, hose->global_number,
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 1d6406a051f1..7db3119f8a5b 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2681,7 +2681,8 @@ static void pnv_pci_ioda_setup_iommu_api(void)
 	list_for_each_entry(hose, &hose_list, list_node) {
 		phb = hose->private_data;
 
-		if (phb->type == PNV_PHB_NPU_NVLINK)
+		if (phb->type == PNV_PHB_NPU_NVLINK ||
+		    phb->type == PNV_PHB_NPU_OCAPI)
 			continue;
 
 		list_for_each_entry(pe, &phb->ioda.pe_list, list) {
diff --git a/arch/powerpc/platforms/pseries/pci.c b/arch/powerpc/platforms/pseries/pci.c
index 7725825d887d..37a77e57893e 100644
--- a/arch/powerpc/platforms/pseries/pci.c
+++ b/arch/powerpc/platforms/pseries/pci.c
@@ -264,7 +264,9 @@ void __init pSeries_final_fixup(void)
 			if (!of_device_is_compatible(nvdn->parent,
 						"ibm,power9-npu"))
 				continue;
+#ifdef CONFIG_PPC_POWERNV
 			WARN_ON_ONCE(pnv_npu2_init(hose));
+#endif
 			break;
 		}
 	}
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index feeeaa60697c..515fc3cc9687 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -103,7 +103,7 @@ choice
 	prompt "Base ISA"
 	default ARCH_RV64I
 	help
-	  This selects the base ISA that this kernel will traget and must match
+	  This selects the base ISA that this kernel will target and must match
 	  the target platform.
 
 config ARCH_RV32I
diff --git a/arch/riscv/configs/defconfig b/arch/riscv/configs/defconfig
index f399659d3b8d..2fd3461e50ab 100644
--- a/arch/riscv/configs/defconfig
+++ b/arch/riscv/configs/defconfig
@@ -13,8 +13,6 @@ CONFIG_BLK_DEV_INITRD=y
 CONFIG_EXPERT=y
 CONFIG_BPF_SYSCALL=y
 CONFIG_SMP=y
-CONFIG_PCI=y
-CONFIG_PCIE_XILINX=y
 CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_NET=y
@@ -28,6 +26,10 @@ CONFIG_IP_PNP_DHCP=y
 CONFIG_IP_PNP_BOOTP=y
 CONFIG_IP_PNP_RARP=y
 CONFIG_NETLINK_DIAG=y
+CONFIG_PCI=y
+CONFIG_PCIEPORTBUS=y
+CONFIG_PCI_HOST_GENERIC=y
+CONFIG_PCIE_XILINX=y
 CONFIG_DEVTMPFS=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_VIRTIO_BLK=y
@@ -63,7 +65,6 @@ CONFIG_USB_STORAGE=y
 CONFIG_USB_UAS=y
 CONFIG_VIRTIO_MMIO=y
 CONFIG_SIFIVE_PLIC=y
-CONFIG_RAS=y
 CONFIG_EXT4_FS=y
 CONFIG_EXT4_FS_POSIX_ACL=y
 CONFIG_AUTOFS4_FS=y
@@ -77,5 +78,6 @@ CONFIG_NFS_V4_1=y
 CONFIG_NFS_V4_2=y
 CONFIG_ROOT_NFS=y
 CONFIG_CRYPTO_USER_API_HASH=y
+CONFIG_CRYPTO_DEV_VIRTIO=y
 CONFIG_PRINTK_TIME=y
 # CONFIG_RCU_TRACE is not set
diff --git a/arch/riscv/include/asm/page.h b/arch/riscv/include/asm/page.h
index 06cfbb3aacbb..2a546a52f02a 100644
--- a/arch/riscv/include/asm/page.h
+++ b/arch/riscv/include/asm/page.h
@@ -80,7 +80,7 @@ typedef struct page *pgtable_t;
 #define __pgd(x)	((pgd_t) { (x) })
 #define __pgprot(x)	((pgprot_t) { (x) })
 
-#ifdef CONFIG_64BITS
+#ifdef CONFIG_64BIT
 #define PTE_FMT "%016lx"
 #else
 #define PTE_FMT "%08lx"
diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
index 0531f49af5c3..ce70bceb8872 100644
--- a/arch/riscv/include/asm/processor.h
+++ b/arch/riscv/include/asm/processor.h
@@ -22,7 +22,7 @@
  * This decides where the kernel will search for a free chunk of vm
  * space during mmap's.
  */
-#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE >> 1)
+#define TASK_UNMAPPED_BASE	PAGE_ALIGN(TASK_SIZE / 3)
 
 #define STACK_TOP		TASK_SIZE
 #define STACK_TOP_MAX		STACK_TOP
diff --git a/arch/riscv/kernel/asm-offsets.c b/arch/riscv/kernel/asm-offsets.c
index 6a92a2fe198e..dac98348c6a3 100644
--- a/arch/riscv/kernel/asm-offsets.c
+++ b/arch/riscv/kernel/asm-offsets.c
@@ -39,6 +39,7 @@ void asm_offsets(void)
 	OFFSET(TASK_STACK, task_struct, stack);
 	OFFSET(TASK_TI, task_struct, thread_info);
 	OFFSET(TASK_TI_FLAGS, task_struct, thread_info.flags);
+	OFFSET(TASK_TI_PREEMPT_COUNT, task_struct, thread_info.preempt_count);
 	OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
 	OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
 	OFFSET(TASK_TI_CPU, task_struct, thread_info.cpu);
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 355166f57205..fd9b57c8b4ce 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -144,6 +144,10 @@ _save_context:
 	REG_L x2,  PT_SP(sp)
 	.endm
 
+#if !IS_ENABLED(CONFIG_PREEMPT)
+.set resume_kernel, restore_all
+#endif
+
 ENTRY(handle_exception)
 	SAVE_ALL
 
@@ -228,7 +232,7 @@ ret_from_exception:
 	REG_L s0, PT_SSTATUS(sp)
 	csrc sstatus, SR_SIE
 	andi s0, s0, SR_SPP
-	bnez s0, restore_all
+	bnez s0, resume_kernel
 
 resume_userspace:
 	/* Interrupts must be disabled here so flags are checked atomically */
@@ -250,6 +254,18 @@ restore_all:
 	RESTORE_ALL
 	sret
 
+#if IS_ENABLED(CONFIG_PREEMPT)
+resume_kernel:
+	REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
+	bnez s0, restore_all
+need_resched:
+	REG_L s0, TASK_TI_FLAGS(tp)
+	andi s0, s0, _TIF_NEED_RESCHED
+	beqz s0, restore_all
+	call preempt_schedule_irq
+	j need_resched
+#endif
+
 work_pending:
 	/* Enter slow path for supplementary processing */
 	la ra, ret_from_exception
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 6e079e94b638..77564310235f 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -181,7 +181,7 @@ static void __init setup_bootmem(void)
 	BUG_ON(mem_size == 0);
 
 	set_max_mapnr(PFN_DOWN(mem_size));
-	max_low_pfn = memblock_end_of_DRAM();
+	max_low_pfn = PFN_DOWN(memblock_end_of_DRAM());
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index fc185ecabb0a..18cda0e8cf94 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -57,15 +57,12 @@ void __init setup_smp(void)
 
 	while ((dn = of_find_node_by_type(dn, "cpu"))) {
 		hart = riscv_of_processor_hartid(dn);
-		if (hart < 0) {
-			of_node_put(dn);
+		if (hart < 0)
 			continue;
-		}
 
 		if (hart == cpuid_to_hartid_map(0)) {
 			BUG_ON(found_boot_cpu);
 			found_boot_cpu = 1;
-			of_node_put(dn);
 			continue;
 		}
 
@@ -73,7 +70,6 @@ void __init setup_smp(void)
 		set_cpu_possible(cpuid, true);
 		set_cpu_present(cpuid, true);
 		cpuid++;
-		of_node_put(dn);
 	}
 
 	BUG_ON(!found_boot_cpu);
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 1d9bfaff60bc..658ebf645f42 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -28,7 +28,8 @@ static void __init zone_sizes_init(void)
 	unsigned long max_zone_pfns[MAX_NR_ZONES] = { 0, };
 
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G, max_low_pfn));
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(min(4UL * SZ_1G,
+			(unsigned long) PFN_PHYS(max_low_pfn)));
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index ccbb53e22024..8d04e6f3f796 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -25,7 +25,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	atomic_set(&mm->context.flush_count, 0);
 	mm->context.gmap_asce = 0;
 	mm->context.flush_mm = 0;
-	mm->context.compat_mm = 0;
+	mm->context.compat_mm = test_thread_flag(TIF_31BIT);
 #ifdef CONFIG_PGSTE
 	mm->context.alloc_pgste = page_table_allocate_pgste ||
 		test_thread_flag(TIF_PGSTE) ||
@@ -90,8 +90,6 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 {
 	int cpu = smp_processor_id();
 
-	if (prev == next)
-		return;
 	S390_lowcore.user_asce = next->context.asce;
 	cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
 	/* Clear previous user-ASCE from CR1 and CR7 */
@@ -103,7 +101,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		__ctl_load(S390_lowcore.vdso_asce, 7, 7);
 		clear_cpu_flag(CIF_ASCE_SECONDARY);
 	}
-	cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
+	if (prev != next)
+		cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
 }
 
 #define finish_arch_post_lock_switch finish_arch_post_lock_switch
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index af5c2b3f7065..a8c7789b246b 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -63,10 +63,10 @@ static noinline __init void detect_machine_type(void)
 	if (stsi(vmms, 3, 2, 2) || !vmms->count)
 		return;
 
-	/* Running under KVM? If not we assume z/VM */
+	/* Detect known hypervisors */
 	if (!memcmp(vmms->vm[0].cpi, "\xd2\xe5\xd4", 3))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_KVM;
-	else
+	else if (!memcmp(vmms->vm[0].cpi, "\xa9\x61\xe5\xd4", 4))
 		S390_lowcore.machine_flags |= MACHINE_FLAG_VM;
 }
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 72dd23ef771b..7ed90a759135 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -1006,6 +1006,8 @@ void __init setup_arch(char **cmdline_p)
 		pr_info("Linux is running under KVM in 64-bit mode\n");
 	else if (MACHINE_IS_LPAR)
 		pr_info("Linux is running natively in 64-bit mode\n");
+	else
+		pr_info("Linux is running as a guest in 64-bit mode\n");
 
 	/* Have one command line that is parsed and saved in /proc/cmdline */
 	/* boot_command_line has been already set up in early.c */
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index f82b3d3c36e2..b198ece2aad6 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -381,8 +381,13 @@ void smp_call_online_cpu(void (*func)(void *), void *data)
  */
 void smp_call_ipl_cpu(void (*func)(void *), void *data)
 {
+	struct lowcore *lc = pcpu_devices->lowcore;
+
+	if (pcpu_devices[0].address == stap())
+		lc = &S390_lowcore;
+
 	pcpu_delegate(&pcpu_devices[0], func, data,
-		      pcpu_devices->lowcore->nodat_stack);
+		      lc->nodat_stack);
 }
 
 int smp_find_processor_id(u16 address)
@@ -1166,7 +1171,11 @@ static ssize_t __ref rescan_store(struct device *dev,
 {
 	int rc;
 
+	rc = lock_device_hotplug_sysfs();
+	if (rc)
+		return rc;
 	rc = smp_rescan_cpus();
+	unlock_device_hotplug();
 	return rc ? rc : count;
 }
 static DEVICE_ATTR_WO(rescan);
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index ebe748a9f472..4ff354887db4 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -224,10 +224,9 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 
 	vdso_pages = vdso64_pages;
 #ifdef CONFIG_COMPAT
-	if (is_compat_task()) {
+	mm->context.compat_mm = is_compat_task();
+	if (mm->context.compat_mm)
 		vdso_pages = vdso32_pages;
-		mm->context.compat_mm = 1;
-	}
 #endif
 	/*
 	 * vDSO has a problem and was disabled, just don't "enable" it for
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 1372553dc0a9..1d1544b6ca74 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -28,6 +28,7 @@ generic-y += preempt.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
+generic-y += shmparam.h
 generic-y += sizes.h
 generic-y += syscalls.h
 generic-y += topology.h
diff --git a/arch/unicore32/include/uapi/asm/Kbuild b/arch/unicore32/include/uapi/asm/Kbuild
index 6c6f6301012e..0febf1a07c30 100644
--- a/arch/unicore32/include/uapi/asm/Kbuild
+++ b/arch/unicore32/include/uapi/asm/Kbuild
@@ -1,5 +1,4 @@
 include include/uapi/asm-generic/Kbuild.asm
 
 generic-y += kvm_para.h
-generic-y += shmparam.h
 generic-y += ucontext.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 15af091611e2..68261430fe6e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -198,7 +198,7 @@ config X86
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_DOMAINS			if PCI
-	select PCI_LOCKLESS_CONFIG
+	select PCI_LOCKLESS_CONFIG		if PCI
 	select PERF_EVENTS
 	select RTC_LIB
 	select RTC_MC146818_LIB
@@ -446,12 +446,12 @@ config RETPOLINE
 	  branches. Requires a compiler with -mindirect-branch=thunk-extern
 	  support for full protection. The kernel may run slower.
 
-config X86_RESCTRL
-	bool "Resource Control support"
+config X86_CPU_RESCTRL
+	bool "x86 CPU resource control support"
 	depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
 	select KERNFS
 	help
-	  Enable Resource Control support.
+	  Enable x86 CPU resource control support.
 
 	  Provide support for the allocation and monitoring of system resources
 	  usage by the CPU.
@@ -617,7 +617,7 @@ config X86_INTEL_QUARK
 
 config X86_INTEL_LPSS
 	bool "Intel Low Power Subsystem Support"
-	depends on X86 && ACPI
+	depends on X86 && ACPI && PCI
 	select COMMON_CLK
 	select PINCTRL
 	select IOSF_MBI
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 64037895b085..f105ae8651c9 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -600,6 +600,14 @@ ENTRY(trampoline_32bit_src)
 	leal	TRAMPOLINE_32BIT_PGTABLE_OFFSET(%ecx), %eax
 	movl	%eax, %cr3
 3:
+	/* Set EFER.LME=1 as a precaution in case hypervsior pulls the rug */
+	pushl	%ecx
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	btsl	$_EFER_LME, %eax
+	wrmsr
+	popl	%ecx
+
 	/* Enable PAE and LA57 (if required) paging modes */
 	movl	$X86_CR4_PAE, %eax
 	cmpl	$0, %edx
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
index 91f75638f6e6..6ff7e81b5628 100644
--- a/arch/x86/boot/compressed/pgtable.h
+++ b/arch/x86/boot/compressed/pgtable.h
@@ -6,7 +6,7 @@
 #define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
 
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0x60
+#define TRAMPOLINE_32BIT_CODE_SIZE	0x70
 
 #define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index 8eaf8952c408..39913770a44d 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -361,7 +361,8 @@ ENTRY(entry_INT80_compat)
 
 	/* Need to switch before accessing the thread stack. */
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-	movq	%rsp, %rdi
+	/* In the Xen PV case we already run on the thread stack. */
+	ALTERNATIVE "movq %rsp, %rdi", "jmp .Lint80_keep_stack", X86_FEATURE_XENPV
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
 	pushq	6*8(%rdi)		/* regs->ss */
@@ -370,8 +371,9 @@ ENTRY(entry_INT80_compat)
 	pushq	3*8(%rdi)		/* regs->cs */
 	pushq	2*8(%rdi)		/* regs->ip */
 	pushq	1*8(%rdi)		/* regs->orig_ax */
-
 	pushq	(%rdi)			/* pt_regs->di */
+.Lint80_keep_stack:
+
 	pushq	%rsi			/* pt_regs->si */
 	xorl	%esi, %esi		/* nospec   si */
 	pushq	%rdx			/* pt_regs->dx */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 0dd6b0f4000e..d9a9993af882 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -6,7 +6,7 @@
  * "Big Core" Processors (Branded as Core, Xeon, etc...)
  *
  * The "_X" parts are generally the EP and EX Xeons, or the
- * "Extreme" ones, like Broadwell-E.
+ * "Extreme" ones, like Broadwell-E, or Atom microserver.
  *
  * While adding a new CPUID for a new microarchitecture, add a new
  * group to keep logically sorted out in chronological order. Within
@@ -71,6 +71,7 @@
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C /* Apollo Lake */
 #define INTEL_FAM6_ATOM_GOLDMONT_X	0x5F /* Denverton */
 #define INTEL_FAM6_ATOM_GOLDMONT_PLUS	0x7A /* Gemini Lake */
+#define INTEL_FAM6_ATOM_TREMONT_X	0x86 /* Jacobsville */
 
 /* Xeon Phi */
 
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 0ca50611e8ce..19d18fae6ec6 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -178,6 +178,10 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 
 void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
+/*
+ * Init a new mm.  Used on mm copies, like at fork()
+ * and on mm's that are brand-new, like at execve().
+ */
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
@@ -228,8 +232,22 @@ do {						\
 } while (0)
 #endif
 
+static inline void arch_dup_pkeys(struct mm_struct *oldmm,
+				  struct mm_struct *mm)
+{
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+	if (!cpu_feature_enabled(X86_FEATURE_OSPKE))
+		return;
+
+	/* Duplicate the oldmm pkey state in mm: */
+	mm->context.pkey_allocation_map = oldmm->context.pkey_allocation_map;
+	mm->context.execute_only_pkey   = oldmm->context.execute_only_pkey;
+#endif
+}
+
 static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
+	arch_dup_pkeys(oldmm, mm);
 	paravirt_arch_dup_mmap(oldmm, mm);
 	return ldt_dup_context(oldmm, mm);
 }
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8f657286d599..0ce558a8150d 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -7,7 +7,11 @@
 #endif
 
 #ifdef CONFIG_KASAN
+#ifdef CONFIG_KASAN_EXTRA
+#define KASAN_STACK_ORDER 2
+#else
 #define KASAN_STACK_ORDER 1
+#endif
 #else
 #define KASAN_STACK_ORDER 0
 #endif
diff --git a/arch/x86/include/asm/resctrl_sched.h b/arch/x86/include/asm/resctrl_sched.h
index 40ebddde6ac2..f6b7fe2833cc 100644
--- a/arch/x86/include/asm/resctrl_sched.h
+++ b/arch/x86/include/asm/resctrl_sched.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_RESCTRL_SCHED_H
 #define _ASM_X86_RESCTRL_SCHED_H
 
-#ifdef CONFIG_X86_RESCTRL
+#ifdef CONFIG_X86_CPU_RESCTRL
 
 #include <linux/sched.h>
 #include <linux/jump_label.h>
@@ -88,6 +88,6 @@ static inline void resctrl_sched_in(void)
 
 static inline void resctrl_sched_in(void) {}
 
-#endif /* CONFIG_X86_RESCTRL */
+#endif /* CONFIG_X86_CPU_RESCTRL */
 
 #endif /* _ASM_X86_RESCTRL_SCHED_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a77445d1b034..780f2b42c8ef 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -711,7 +711,7 @@ static __must_check inline bool user_access_begin(const void __user *ptr, size_t
 {
 	if (unlikely(!access_ok(ptr,len)))
 		return 0;
-	__uaccess_begin();
+	__uaccess_begin_nospec();
 	return 1;
 }
 #define user_access_begin(a,b)	user_access_begin(a,b)
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index b6fa0869f7aa..cfd24f9f7614 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -39,7 +39,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 obj-$(CONFIG_X86_MCE)			+= mce/
 obj-$(CONFIG_MTRR)			+= mtrr/
 obj-$(CONFIG_MICROCODE)			+= microcode/
-obj-$(CONFIG_X86_RESCTRL)		+= resctrl/
+obj-$(CONFIG_X86_CPU_RESCTRL)		+= resctrl/
 
 obj-$(CONFIG_X86_LOCAL_APIC)		+= perfctr-watchdog.o
 
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1de0f4170178..01874d54f4fd 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -71,7 +71,7 @@ void __init check_bugs(void)
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
 	 */
-	cpu_smt_check_topology_early();
+	cpu_smt_check_topology();
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 51adde0a0f1a..e1f3ba19ba54 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -855,7 +855,7 @@ load_microcode_amd(bool save, u8 family, const u8 *data, size_t size)
 	if (!p) {
 		return ret;
 	} else {
-		if (boot_cpu_data.microcode == p->patch_id)
+		if (boot_cpu_data.microcode >= p->patch_id)
 			return ret;
 
 		ret = UCODE_NEW;
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
index 1cabe6fd8e11..4a06c37b9cf1 100644
--- a/arch/x86/kernel/cpu/resctrl/Makefile
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_X86_RESCTRL)	+= core.o rdtgroup.o monitor.o
-obj-$(CONFIG_X86_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
+obj-$(CONFIG_X86_CPU_RESCTRL)	+= core.o rdtgroup.o monitor.o
+obj-$(CONFIG_X86_CPU_RESCTRL)	+= ctrlmondata.o pseudo_lock.o
 CFLAGS_pseudo_lock.o = -I$(src)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index c8b07d8ea5a2..17ffc869cab8 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -470,6 +470,7 @@ int crash_load_segments(struct kimage *image)
 
 	kbuf.memsz = kbuf.bufsz;
 	kbuf.buf_align = ELF_CORE_HEADER_ALIGN;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret) {
 		vfree((void *)image->arch.elf_headers);
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index b0acb22e5a46..dfd3aca82c61 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -21,10 +21,6 @@
 
 #define HPET_MASK			CLOCKSOURCE_MASK(32)
 
-/* FSEC = 10^-15
-   NSEC = 10^-9 */
-#define FSEC_PER_NSEC			1000000L
-
 #define HPET_DEV_USED_BIT		2
 #define HPET_DEV_USED			(1 << HPET_DEV_USED_BIT)
 #define HPET_DEV_VALID			0x8
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 278cd07228dd..53917a3ebf94 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -167,6 +167,9 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr,
 	struct efi_info *current_ei = &boot_params.efi_info;
 	struct efi_info *ei = &params->efi_info;
 
+	if (!efi_enabled(EFI_RUNTIME_SERVICES))
+		return 0;
+
 	if (!current_ei->efi_memmap_size)
 		return 0;
 
@@ -434,6 +437,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 	kbuf.memsz = PAGE_ALIGN(header->init_size);
 	kbuf.buf_align = header->kernel_alignment;
 	kbuf.buf_min = MIN_KERNEL_LOAD_ADDR;
+	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	ret = kexec_add_buffer(&kbuf);
 	if (ret)
 		goto out_free_params;
@@ -448,6 +452,7 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
 		kbuf.bufsz = kbuf.memsz = initrd_len;
 		kbuf.buf_align = PAGE_SIZE;
 		kbuf.buf_min = MIN_INITRD_LOAD_ADDR;
+		kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 		ret = kexec_add_buffer(&kbuf);
 		if (ret)
 			goto out_free_params;
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index ba4bfb7f6a36..5c93a65ee1e5 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -457,6 +457,7 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 #else
 	u64 ipi_bitmap = 0;
 #endif
+	long ret;
 
 	if (cpumask_empty(mask))
 		return;
@@ -482,8 +483,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 		} else if (apic_id < min + KVM_IPI_CLUSTER_SIZE) {
 			max = apic_id < max ? max : apic_id;
 		} else {
-			kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+			ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
 				(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+			WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
 			min = max = apic_id;
 			ipi_bitmap = 0;
 		}
@@ -491,8 +493,9 @@ static void __send_ipi_mask(const struct cpumask *mask, int vector)
 	}
 
 	if (ipi_bitmap) {
-		kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
+		ret = kvm_hypercall4(KVM_HC_SEND_IPI, (unsigned long)ipi_bitmap,
 			(unsigned long)(ipi_bitmap >> BITS_PER_LONG), min, icr);
+		WARN_ONCE(ret < 0, "KVM: failed to send PV IPI: %ld", ret);
 	}
 
 	local_irq_restore(flags);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index e9f777bfed40..3fae23834069 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -297,15 +297,16 @@ static int __init tsc_setup(char *str)
 
 __setup("tsc=", tsc_setup);
 
-#define MAX_RETRIES     5
-#define SMI_TRESHOLD    50000
+#define MAX_RETRIES		5
+#define TSC_DEFAULT_THRESHOLD	0x20000
 
 /*
- * Read TSC and the reference counters. Take care of SMI disturbance
+ * Read TSC and the reference counters. Take care of any disturbances
  */
 static u64 tsc_read_refs(u64 *p, int hpet)
 {
 	u64 t1, t2;
+	u64 thresh = tsc_khz ? tsc_khz >> 5 : TSC_DEFAULT_THRESHOLD;
 	int i;
 
 	for (i = 0; i < MAX_RETRIES; i++) {
@@ -315,7 +316,7 @@ static u64 tsc_read_refs(u64 *p, int hpet)
 		else
 			*p = acpi_pm_read_early();
 		t2 = get_cycles();
-		if ((t2 - t1) < SMI_TRESHOLD)
+		if ((t2 - t1) < thresh)
 			return t2;
 	}
 	return ULLONG_MAX;
@@ -703,15 +704,15 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 	 * zero. In each wait loop iteration we read the TSC and check
 	 * the delta to the previous read. We keep track of the min
 	 * and max values of that delta. The delta is mostly defined
-	 * by the IO time of the PIT access, so we can detect when a
-	 * SMI/SMM disturbance happened between the two reads. If the
+	 * by the IO time of the PIT access, so we can detect when
+	 * any disturbance happened between the two reads. If the
 	 * maximum time is significantly larger than the minimum time,
 	 * then we discard the result and have another try.
 	 *
 	 * 2) Reference counter. If available we use the HPET or the
 	 * PMTIMER as a reference to check the sanity of that value.
 	 * We use separate TSC readouts and check inside of the
-	 * reference read for a SMI/SMM disturbance. We dicard
+	 * reference read for any possible disturbance. We dicard
 	 * disturbed values here as well. We do that around the PIT
 	 * calibration delay loop as we have to wait for a certain
 	 * amount of time anyway.
@@ -744,7 +745,7 @@ static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 		if (ref1 == ref2)
 			continue;
 
-		/* Check, whether the sampling was disturbed by an SMI */
+		/* Check, whether the sampling was disturbed */
 		if (tsc1 == ULLONG_MAX || tsc2 == ULLONG_MAX)
 			continue;
 
@@ -1268,7 +1269,7 @@ static DECLARE_DELAYED_WORK(tsc_irqwork, tsc_refine_calibration_work);
  */
 static void tsc_refine_calibration_work(struct work_struct *work)
 {
-	static u64 tsc_start = -1, ref_start;
+	static u64 tsc_start = ULLONG_MAX, ref_start;
 	static int hpet;
 	u64 tsc_stop, ref_stop, delta;
 	unsigned long freq;
@@ -1283,14 +1284,15 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	 * delayed the first time we expire. So set the workqueue
 	 * again once we know timers are working.
 	 */
-	if (tsc_start == -1) {
+	if (tsc_start == ULLONG_MAX) {
+restart:
 		/*
 		 * Only set hpet once, to avoid mixing hardware
 		 * if the hpet becomes enabled later.
 		 */
 		hpet = is_hpet_enabled();
-		schedule_delayed_work(&tsc_irqwork, HZ);
 		tsc_start = tsc_read_refs(&ref_start, hpet);
+		schedule_delayed_work(&tsc_irqwork, HZ);
 		return;
 	}
 
@@ -1300,9 +1302,9 @@ static void tsc_refine_calibration_work(struct work_struct *work)
 	if (ref_start == ref_stop)
 		goto out;
 
-	/* Check, whether the sampling was disturbed by an SMI */
-	if (tsc_start == ULLONG_MAX || tsc_stop == ULLONG_MAX)
-		goto out;
+	/* Check, whether the sampling was disturbed */
+	if (tsc_stop == ULLONG_MAX)
+		goto restart;
 
 	delta = tsc_stop - tsc_start;
 	delta *= 1000000LL;
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index 69b3a7c30013..31ecf7a76d5a 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -2,10 +2,6 @@
 
 ccflags-y += -Iarch/x86/kvm
 
-CFLAGS_x86.o := -I.
-CFLAGS_svm.o := -I.
-CFLAGS_vmx.o := -I.
-
 KVM := ../../../virt/kvm
 
 kvm-y			+= $(KVM)/kvm_main.o $(KVM)/coalesced_mmio.o \
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index c90a5352d158..89d20ed1d2e8 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1636,7 +1636,7 @@ int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
 		ret = kvm_hvcall_signal_event(vcpu, fast, ingpa);
 		if (ret != HV_STATUS_INVALID_PORT_ID)
 			break;
-		/* maybe userspace knows this conn_id: fall through */
+		/* fall through - maybe userspace knows this conn_id. */
 	case HVCALL_POST_MESSAGE:
 		/* don't bother userspace if it has no way to handle it */
 		if (unlikely(rep || !vcpu_to_synic(vcpu)->active)) {
@@ -1832,7 +1832,6 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 			ent->eax |= HV_X64_MSR_VP_INDEX_AVAILABLE;
 			ent->eax |= HV_X64_MSR_RESET_AVAILABLE;
 			ent->eax |= HV_MSR_REFERENCE_TSC_AVAILABLE;
-			ent->eax |= HV_X64_MSR_GUEST_IDLE_AVAILABLE;
 			ent->eax |= HV_X64_ACCESS_FREQUENCY_MSRS;
 			ent->eax |= HV_X64_ACCESS_REENLIGHTENMENT;
 
@@ -1848,11 +1847,11 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 		case HYPERV_CPUID_ENLIGHTMENT_INFO:
 			ent->eax |= HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED;
 			ent->eax |= HV_X64_APIC_ACCESS_RECOMMENDED;
-			ent->eax |= HV_X64_SYSTEM_RESET_RECOMMENDED;
 			ent->eax |= HV_X64_RELAXED_TIMING_RECOMMENDED;
 			ent->eax |= HV_X64_CLUSTER_IPI_RECOMMENDED;
 			ent->eax |= HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED;
-			ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
+			if (evmcs_ver)
+				ent->eax |= HV_X64_ENLIGHTENED_VMCS_RECOMMENDED;
 
 			/*
 			 * Default number of spinlock retry attempts, matches
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 9f089e2e09d0..4b6c2da7265c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1035,6 +1035,7 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 	switch (delivery_mode) {
 	case APIC_DM_LOWEST:
 		vcpu->arch.apic_arb_prio++;
+		/* fall through */
 	case APIC_DM_FIXED:
 		if (unlikely(trig_mode && !level))
 			break;
@@ -1874,6 +1875,7 @@ int kvm_lapic_reg_write(struct kvm_lapic *apic, u32 reg, u32 val)
 
 	case APIC_LVT0:
 		apic_manage_nmi_watchdog(apic, val);
+		/* fall through */
 	case APIC_LVTTHMR:
 	case APIC_LVTPC:
 	case APIC_LVT1:
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index ce770b446238..da9c42349b1f 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -4371,6 +4371,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 			rsvd_bits(maxphyaddr, 51);
 		rsvd_check->rsvd_bits_mask[1][4] =
 			rsvd_check->rsvd_bits_mask[0][4];
+		/* fall through */
 	case PT64_ROOT_4LEVEL:
 		rsvd_check->rsvd_bits_mask[0][3] = exb_bit_rsvd |
 			nonleaf_bit8_rsvd | rsvd_bits(7, 7) |
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index a157ca5b6869..f13a3a24d360 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3414,6 +3414,14 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	kvm_mmu_reset_context(&svm->vcpu);
 	kvm_mmu_load(&svm->vcpu);
 
+	/*
+	 * Drop what we picked up for L2 via svm_complete_interrupts() so it
+	 * doesn't end up in L1.
+	 */
+	svm->vcpu.arch.nmi_injected = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
+
 	return 0;
 }
 
@@ -4395,7 +4403,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_IA32_APICBASE:
 		if (kvm_vcpu_apicv_active(vcpu))
 			avic_update_vapic_bar(to_svm(vcpu), data);
-		/* Follow through */
+		/* Fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4504,28 +4512,19 @@ static int avic_incomplete_ipi_interception(struct vcpu_svm *svm)
 		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING: {
-		int i;
-		struct kvm_vcpu *vcpu;
-		struct kvm *kvm = svm->vcpu.kvm;
 		struct kvm_lapic *apic = svm->vcpu.arch.apic;
 
 		/*
-		 * At this point, we expect that the AVIC HW has already
-		 * set the appropriate IRR bits on the valid target
-		 * vcpus. So, we just need to kick the appropriate vcpu.
+		 * Update ICR high and low, then emulate sending IPI,
+		 * which is handled when writing APIC_ICR.
 		 */
-		kvm_for_each_vcpu(i, vcpu, kvm) {
-			bool m = kvm_apic_match_dest(vcpu, apic,
-						     icrl & KVM_APIC_SHORT_MASK,
-						     GET_APIC_DEST_FIELD(icrh),
-						     icrl & KVM_APIC_DEST_MASK);
-
-			if (m && !avic_vcpu_is_running(vcpu))
-				kvm_vcpu_wake_up(vcpu);
-		}
+		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
+		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
 		break;
 	}
 	case AVIC_IPI_FAILURE_INVALID_TARGET:
+		WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n",
+			  index, svm->vcpu.vcpu_id, icrh, icrl);
 		break;
 	case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
 		WARN_ONCE(1, "Invalid backing page\n");
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 705f40ae2532..6432d08c7de7 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -1465,7 +1465,7 @@ TRACE_EVENT(kvm_hv_send_ipi_ex,
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH
-#define TRACE_INCLUDE_PATH arch/x86/kvm
+#define TRACE_INCLUDE_PATH ../../arch/x86/kvm
 #undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE trace
 
diff --git a/arch/x86/kvm/vmx/evmcs.c b/arch/x86/kvm/vmx/evmcs.c
index 95bc2247478d..5466c6d85cf3 100644
--- a/arch/x86/kvm/vmx/evmcs.c
+++ b/arch/x86/kvm/vmx/evmcs.c
@@ -332,16 +332,17 @@ int nested_enable_evmcs(struct kvm_vcpu *vcpu,
 			uint16_t *vmcs_version)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	bool evmcs_already_enabled = vmx->nested.enlightened_vmcs_enabled;
+
+	vmx->nested.enlightened_vmcs_enabled = true;
 
 	if (vmcs_version)
 		*vmcs_version = nested_get_evmcs_version(vcpu);
 
 	/* We don't support disabling the feature for simplicity. */
-	if (vmx->nested.enlightened_vmcs_enabled)
+	if (evmcs_already_enabled)
 		return 0;
 
-	vmx->nested.enlightened_vmcs_enabled = true;
-
 	vmx->nested.msrs.pinbased_ctls_high &= ~EVMCS1_UNSUPPORTED_PINCTRL;
 	vmx->nested.msrs.entry_ctls_high &= ~EVMCS1_UNSUPPORTED_VMENTRY_CTRL;
 	vmx->nested.msrs.exit_ctls_high &= ~EVMCS1_UNSUPPORTED_VMEXIT_CTRL;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 2616bd2c7f2c..8ff20523661b 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -55,7 +55,7 @@ static u16 shadow_read_write_fields[] = {
 static int max_shadow_read_write_fields =
 	ARRAY_SIZE(shadow_read_write_fields);
 
-void init_vmcs_shadow_fields(void)
+static void init_vmcs_shadow_fields(void)
 {
 	int i, j;
 
@@ -4140,11 +4140,11 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
 	if (r < 0)
 		goto out_vmcs02;
 
-	vmx->nested.cached_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+	vmx->nested.cached_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL);
 	if (!vmx->nested.cached_vmcs12)
 		goto out_cached_vmcs12;
 
-	vmx->nested.cached_shadow_vmcs12 = kmalloc(VMCS12_SIZE, GFP_KERNEL);
+	vmx->nested.cached_shadow_vmcs12 = kzalloc(VMCS12_SIZE, GFP_KERNEL);
 	if (!vmx->nested.cached_shadow_vmcs12)
 		goto out_cached_shadow_vmcs12;
 
@@ -5263,13 +5263,17 @@ static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
 			copy_shadow_to_vmcs12(vmx);
 	}
 
-	if (copy_to_user(user_kvm_nested_state->data, vmcs12, sizeof(*vmcs12)))
+	/*
+	 * Copy over the full allocated size of vmcs12 rather than just the size
+	 * of the struct.
+	 */
+	if (copy_to_user(user_kvm_nested_state->data, vmcs12, VMCS12_SIZE))
 		return -EFAULT;
 
 	if (nested_cpu_has_shadow_vmcs(vmcs12) &&
 	    vmcs12->vmcs_link_pointer != -1ull) {
 		if (copy_to_user(user_kvm_nested_state->data + VMCS12_SIZE,
-				 get_shadow_vmcs12(vcpu), sizeof(*vmcs12)))
+				 get_shadow_vmcs12(vcpu), VMCS12_SIZE))
 			return -EFAULT;
 	}
 
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index f6915f10e584..95d618045001 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -26,6 +26,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/smt.h>
 #include <linux/slab.h>
 #include <linux/tboot.h>
 #include <linux/trace_events.h>
@@ -423,7 +424,7 @@ static void check_ept_pointer_match(struct kvm *kvm)
 	to_kvm_vmx(kvm)->ept_pointers_match = EPT_POINTERS_MATCH;
 }
 
-int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
+static int kvm_fill_hv_flush_list_func(struct hv_guest_mapping_flush_list *flush,
 		void *data)
 {
 	struct kvm_tlb_range *range = data;
@@ -1773,7 +1774,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP))
 			return 1;
-		/* Otherwise falls through */
+		/* Else, falls through */
 	default:
 		msr = find_msr_entry(vmx, msr_info->index);
 		if (msr) {
@@ -2014,7 +2015,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		/* Check reserved bit, higher 32 bits should be zero */
 		if ((data >> 32) != 0)
 			return 1;
-		/* Otherwise falls through */
+		/* Else, falls through */
 	default:
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
@@ -2344,7 +2345,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 		case 37: /* AAT100 */
 		case 44: /* BC86,AAY89,BD102 */
 		case 46: /* BA97 */
-			_vmexit_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+			_vmentry_control &= ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
 			_vmexit_control &= ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
 			pr_warn_once("kvm: VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL "
 					"does not work properly. Using workaround\n");
@@ -6362,72 +6363,9 @@ static void vmx_update_hv_timer(struct kvm_vcpu *vcpu)
 	vmx->loaded_vmcs->hv_timer_armed = false;
 }
 
-static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
+static void __vmx_vcpu_run(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr3, cr4, evmcs_rsp;
-
-	/* Record the guest's net vcpu time for enforced NMI injections. */
-	if (unlikely(!enable_vnmi &&
-		     vmx->loaded_vmcs->soft_vnmi_blocked))
-		vmx->loaded_vmcs->entry_time = ktime_get();
-
-	/* Don't enter VMX if guest state is invalid, let the exit handler
-	   start emulation until we arrive back to a valid state */
-	if (vmx->emulation_required)
-		return;
-
-	if (vmx->ple_window_dirty) {
-		vmx->ple_window_dirty = false;
-		vmcs_write32(PLE_WINDOW, vmx->ple_window);
-	}
-
-	if (vmx->nested.need_vmcs12_sync)
-		nested_sync_from_vmcs12(vcpu);
-
-	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
-		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
-	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
-		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
-
-	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
-		vmcs_writel(HOST_CR3, cr3);
-		vmx->loaded_vmcs->host_state.cr3 = cr3;
-	}
-
-	cr4 = cr4_read_shadow();
-	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
-		vmcs_writel(HOST_CR4, cr4);
-		vmx->loaded_vmcs->host_state.cr4 = cr4;
-	}
-
-	/* When single-stepping over STI and MOV SS, we must clear the
-	 * corresponding interruptibility bits in the guest state. Otherwise
-	 * vmentry fails as it then expects bit 14 (BS) in pending debug
-	 * exceptions being set, but that's not correct for the guest debugging
-	 * case. */
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		vmx_set_interrupt_shadow(vcpu, 0);
-
-	if (static_cpu_has(X86_FEATURE_PKU) &&
-	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
-	    vcpu->arch.pkru != vmx->host_pkru)
-		__write_pkru(vcpu->arch.pkru);
-
-	pt_guest_enter(vmx);
-
-	atomic_switch_perf_msrs(vmx);
-
-	vmx_update_hv_timer(vcpu);
-
-	/*
-	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
-	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
-	 * is no need to worry about the conditional branch over the wrmsr
-	 * being speculatively taken.
-	 */
-	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+	unsigned long evmcs_rsp;
 
 	vmx->__launched = vmx->loaded_vmcs->launched;
 
@@ -6567,6 +6505,77 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		, "eax", "ebx", "edi"
 #endif
 	      );
+}
+STACK_FRAME_NON_STANDARD(__vmx_vcpu_run);
+
+static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long cr3, cr4;
+
+	/* Record the guest's net vcpu time for enforced NMI injections. */
+	if (unlikely(!enable_vnmi &&
+		     vmx->loaded_vmcs->soft_vnmi_blocked))
+		vmx->loaded_vmcs->entry_time = ktime_get();
+
+	/* Don't enter VMX if guest state is invalid, let the exit handler
+	   start emulation until we arrive back to a valid state */
+	if (vmx->emulation_required)
+		return;
+
+	if (vmx->ple_window_dirty) {
+		vmx->ple_window_dirty = false;
+		vmcs_write32(PLE_WINDOW, vmx->ple_window);
+	}
+
+	if (vmx->nested.need_vmcs12_sync)
+		nested_sync_from_vmcs12(vcpu);
+
+	if (test_bit(VCPU_REGS_RSP, (unsigned long *)&vcpu->arch.regs_dirty))
+		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
+	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
+		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
+
+	cr3 = __get_current_cr3_fast();
+	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		vmx->loaded_vmcs->host_state.cr3 = cr3;
+	}
+
+	cr4 = cr4_read_shadow();
+	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
+		vmcs_writel(HOST_CR4, cr4);
+		vmx->loaded_vmcs->host_state.cr4 = cr4;
+	}
+
+	/* When single-stepping over STI and MOV SS, we must clear the
+	 * corresponding interruptibility bits in the guest state. Otherwise
+	 * vmentry fails as it then expects bit 14 (BS) in pending debug
+	 * exceptions being set, but that's not correct for the guest debugging
+	 * case. */
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vmx_set_interrupt_shadow(vcpu, 0);
+
+	if (static_cpu_has(X86_FEATURE_PKU) &&
+	    kvm_read_cr4_bits(vcpu, X86_CR4_PKE) &&
+	    vcpu->arch.pkru != vmx->host_pkru)
+		__write_pkru(vcpu->arch.pkru);
+
+	pt_guest_enter(vmx);
+
+	atomic_switch_perf_msrs(vmx);
+
+	vmx_update_hv_timer(vcpu);
+
+	/*
+	 * If this vCPU has touched SPEC_CTRL, restore the guest's value if
+	 * it's non-zero. Since vmentry is serialising on affected CPUs, there
+	 * is no need to worry about the conditional branch over the wrmsr
+	 * being speculatively taken.
+	 */
+	x86_spec_ctrl_set_guest(vmx->spec_ctrl, 0);
+
+	__vmx_vcpu_run(vcpu, vmx);
 
 	/*
 	 * We do not use IBRS in the kernel. If this vCPU has used the
@@ -6648,7 +6657,6 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx_recover_nmi_blocking(vmx);
 	vmx_complete_interrupts(vmx);
 }
-STACK_FRAME_NON_STANDARD(vmx_vcpu_run);
 
 static struct kvm *vmx_vm_alloc(void)
 {
@@ -6816,7 +6824,7 @@ static int vmx_vm_init(struct kvm *kvm)
 			 * Warn upon starting the first VM in a potentially
 			 * insecure environment.
 			 */
-			if (cpu_smt_control == CPU_SMT_ENABLED)
+			if (sched_smt_active())
 				pr_warn_once(L1TF_MSG_SMT);
 			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
 				pr_warn_once(L1TF_MSG_L1D);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02c8e095a239..3d27206f6c01 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3834,6 +3834,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	case KVM_CAP_HYPERV_SYNIC2:
 		if (cap->args[0])
 			return -EINVAL;
+		/* fall through */
+
 	case KVM_CAP_HYPERV_SYNIC:
 		if (!irqchip_in_kernel(vcpu->kvm))
 			return -EINVAL;
@@ -6480,8 +6482,7 @@ restart:
 		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 || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+		if (r == EMULATE_DONE && ctxt->tf)
 			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
@@ -7093,10 +7094,10 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 	case KVM_HC_CLOCK_PAIRING:
 		ret = kvm_pv_clock_pairing(vcpu, a0, a1);
 		break;
+#endif
 	case KVM_HC_SEND_IPI:
 		ret = kvm_pv_send_ipi(vcpu->kvm, a0, a1, a2, a3, op_64_bit);
 		break;
-#endif
 	default:
 		ret = -KVM_ENOSYS;
 		break;
@@ -7937,6 +7938,7 @@ static inline int vcpu_block(struct kvm *kvm, struct kvm_vcpu *vcpu)
 		vcpu->arch.pv.pv_unhalted = false;
 		vcpu->arch.mp_state =
 			KVM_MP_STATE_RUNNABLE;
+		/* fall through */
 	case KVM_MP_STATE_RUNNABLE:
 		vcpu->arch.apf.halted = false;
 		break;
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index 66894675f3c8..df50451d94ef 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -2,8 +2,11 @@
 #include <linux/module.h>
 #include <linux/io.h>
 
+#define movs(type,to,from) \
+	asm volatile("movs" type:"=&D" (to), "=&S" (from):"0" (to), "1" (from):"memory")
+
 /* Originally from i386/string.h */
-static __always_inline void __iomem_memcpy(void *to, const void *from, size_t n)
+static __always_inline void rep_movs(void *to, const void *from, size_t n)
 {
 	unsigned long d0, d1, d2;
 	asm volatile("rep ; movsl\n\t"
@@ -21,13 +24,37 @@ static __always_inline void __iomem_memcpy(void *to, const void *from, size_t n)
 
 void memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
 {
-	__iomem_memcpy(to, (const void *)from, n);
+	if (unlikely(!n))
+		return;
+
+	/* Align any unaligned source IO */
+	if (unlikely(1 & (unsigned long)from)) {
+		movs("b", to, from);
+		n--;
+	}
+	if (n > 1 && unlikely(2 & (unsigned long)from)) {
+		movs("w", to, from);
+		n-=2;
+	}
+	rep_movs(to, (const void *)from, n);
 }
 EXPORT_SYMBOL(memcpy_fromio);
 
 void memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
 {
-	__iomem_memcpy((void *)to, (const void *) from, n);
+	if (unlikely(!n))
+		return;
+
+	/* Align any unaligned destination IO */
+	if (unlikely(1 & (unsigned long)to)) {
+		movs("b", to, from);
+		n--;
+	}
+	if (n > 1 && unlikely(2 & (unsigned long)to)) {
+		movs("w", to, from);
+		n-=2;
+	}
+	rep_movs((void *)to, (const void *) from, n);
 }
 EXPORT_SYMBOL(memcpy_toio);
 
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index 79778ab200e4..a53665116458 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -36,8 +36,8 @@ static inline u16 i8254(void)
 	u16 status, timer;
 
 	do {
-		outb(I8254_PORT_CONTROL,
-		     I8254_CMD_READBACK | I8254_SELECT_COUNTER0);
+		outb(I8254_CMD_READBACK | I8254_SELECT_COUNTER0,
+		     I8254_PORT_CONTROL);
 		status = inb(I8254_PORT_COUNTER0);
 		timer  = inb(I8254_PORT_COUNTER0);
 		timer |= inb(I8254_PORT_COUNTER0) << 8;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2ff25ad33233..9d5c75f02295 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -595,7 +595,7 @@ static void show_ldttss(const struct desc_ptr *gdt, const char *name, u16 index)
 		return;
 	}
 
-	addr = desc.base0 | (desc.base1 << 16) | (desc.base2 << 24);
+	addr = desc.base0 | (desc.base1 << 16) | ((unsigned long)desc.base2 << 24);
 #ifdef CONFIG_X86_64
 	addr |= ((u64)desc.base3 << 32);
 #endif
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c
index a19ef1a416ff..4aa9b1480866 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/mm/mem_encrypt_identity.c
@@ -158,8 +158,8 @@ static void __init sme_populate_pgd(struct sme_populate_pgd_data *ppd)
 	pmd = pmd_offset(pud, ppd->vaddr);
 	if (pmd_none(*pmd)) {
 		pte = ppd->pgtable_area;
-		memset(pte, 0, sizeof(pte) * PTRS_PER_PTE);
-		ppd->pgtable_area += sizeof(pte) * PTRS_PER_PTE;
+		memset(pte, 0, sizeof(*pte) * PTRS_PER_PTE);
+		ppd->pgtable_area += sizeof(*pte) * PTRS_PER_PTE;
 		set_pmd(pmd, __pmd(PMD_FLAGS | __pa(pte)));
 	}
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 2f6787fc7106..c54a493e139a 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -898,10 +898,7 @@ static u64 xen_read_msr_safe(unsigned int msr, int *err)
 	val = native_read_msr_safe(msr, err);
 	switch (msr) {
 	case MSR_IA32_APICBASE:
-#ifdef CONFIG_X86_X2APIC
-		if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
-#endif
-			val &= ~X2APIC_ENABLE;
+		val &= ~X2APIC_ENABLE;
 		break;
 	}
 	return val;
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 72bf446c3fee..6e29794573b7 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -361,8 +361,6 @@ void xen_timer_resume(void)
 {
 	int cpu;
 
-	pvclock_resume();
-
 	if (xen_clockevent != &xen_vcpuop_clockevent)
 		return;
 
@@ -379,12 +377,15 @@ static const struct pv_time_ops xen_time_ops __initconst = {
 };
 
 static struct pvclock_vsyscall_time_info *xen_clock __read_mostly;
+static u64 xen_clock_value_saved;
 
 void xen_save_time_memory_area(void)
 {
 	struct vcpu_register_time_memory_area t;
 	int ret;
 
+	xen_clock_value_saved = xen_clocksource_read() - xen_sched_clock_offset;
+
 	if (!xen_clock)
 		return;
 
@@ -404,7 +405,7 @@ void xen_restore_time_memory_area(void)
 	int ret;
 
 	if (!xen_clock)
-		return;
+		goto out;
 
 	t.addr.v = &xen_clock->pvti;
 
@@ -421,6 +422,11 @@ void xen_restore_time_memory_area(void)
 	if (ret != 0)
 		pr_notice("Cannot restore secondary vcpu_time_info (err %d)",
 			  ret);
+
+out:
+	/* Need pvclock_resume() before using xen_clocksource_read(). */
+	pvclock_resume();
+	xen_sched_clock_offset = xen_clocksource_read() - xen_clock_value_saved;
 }
 
 static void xen_setup_vsyscall_time_info(void)
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 20a0756f27ef..ce91682770cb 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -164,7 +164,7 @@ config XTENSA_FAKE_NMI
 	  If unsure, say N.
 
 config XTENSA_UNALIGNED_USER
-	bool "Unaligned memory access in use space"
+	bool "Unaligned memory access in user space"
 	help
 	  The Xtensa architecture currently does not handle unaligned
 	  memory accesses in hardware but through an exception handler.
@@ -451,7 +451,7 @@ config USE_OF
 	help
 	  Include support for flattened device tree machine descriptions.
 
-config BUILTIN_DTB
+config BUILTIN_DTB_SOURCE
 	string "DTB to build into the kernel image"
 	depends on OF
 
diff --git a/arch/xtensa/boot/dts/Makefile b/arch/xtensa/boot/dts/Makefile
index f8052ba5aea8..0b8d00cdae7c 100644
--- a/arch/xtensa/boot/dts/Makefile
+++ b/arch/xtensa/boot/dts/Makefile
@@ -7,9 +7,9 @@
 #
 #
 
-BUILTIN_DTB := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB)).dtb.o
-ifneq ($(CONFIG_BUILTIN_DTB),"")
-obj-$(CONFIG_OF) += $(BUILTIN_DTB)
+BUILTIN_DTB_SOURCE := $(patsubst "%",%,$(CONFIG_BUILTIN_DTB_SOURCE)).dtb.o
+ifneq ($(CONFIG_BUILTIN_DTB_SOURCE),"")
+obj-$(CONFIG_OF) += $(BUILTIN_DTB_SOURCE)
 endif
 
 # for CONFIG_OF_ALL_DTBS test
diff --git a/arch/xtensa/configs/audio_kc705_defconfig b/arch/xtensa/configs/audio_kc705_defconfig
index 2bf964df37ba..f378e56f9ce6 100644
--- a/arch/xtensa/configs/audio_kc705_defconfig
+++ b/arch/xtensa/configs/audio_kc705_defconfig
@@ -34,7 +34,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="kc705"
+CONFIG_BUILTIN_DTB_SOURCE="kc705"
 # CONFIG_COMPACTION is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_PM=y
diff --git a/arch/xtensa/configs/cadence_csp_defconfig b/arch/xtensa/configs/cadence_csp_defconfig
index 3221b7053fa3..62f32a902568 100644
--- a/arch/xtensa/configs/cadence_csp_defconfig
+++ b/arch/xtensa/configs/cadence_csp_defconfig
@@ -38,7 +38,7 @@ CONFIG_HIGHMEM=y
 # CONFIG_PCI is not set
 CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="csp"
+CONFIG_BUILTIN_DTB_SOURCE="csp"
 # CONFIG_COMPACTION is not set
 CONFIG_XTFPGA_LCD=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
diff --git a/arch/xtensa/configs/generic_kc705_defconfig b/arch/xtensa/configs/generic_kc705_defconfig
index 985fa8546e4e..8bebe07f1060 100644
--- a/arch/xtensa/configs/generic_kc705_defconfig
+++ b/arch/xtensa/configs/generic_kc705_defconfig
@@ -33,7 +33,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=0x38000000@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="kc705"
+CONFIG_BUILTIN_DTB_SOURCE="kc705"
 # CONFIG_COMPACTION is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_NET=y
diff --git a/arch/xtensa/configs/nommu_kc705_defconfig b/arch/xtensa/configs/nommu_kc705_defconfig
index f3fc4f970ca8..933ab2adf434 100644
--- a/arch/xtensa/configs/nommu_kc705_defconfig
+++ b/arch/xtensa/configs/nommu_kc705_defconfig
@@ -39,7 +39,7 @@ CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0x9d050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=256M@0x60000000"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="kc705_nommu"
+CONFIG_BUILTIN_DTB_SOURCE="kc705_nommu"
 CONFIG_BINFMT_FLAT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
diff --git a/arch/xtensa/configs/smp_lx200_defconfig b/arch/xtensa/configs/smp_lx200_defconfig
index 11fed6c06a7c..e29c5b179a5b 100644
--- a/arch/xtensa/configs/smp_lx200_defconfig
+++ b/arch/xtensa/configs/smp_lx200_defconfig
@@ -33,11 +33,12 @@ CONFIG_SMP=y
 CONFIG_HOTPLUG_CPU=y
 # CONFIG_INITIALIZE_XTENSA_MMU_INSIDE_VMLINUX is not set
 # CONFIG_PCI is not set
+CONFIG_VECTORS_OFFSET=0x00002000
 CONFIG_XTENSA_PLATFORM_XTFPGA=y
 CONFIG_CMDLINE_BOOL=y
 CONFIG_CMDLINE="earlycon=uart8250,mmio32native,0xfd050020,115200n8 console=ttyS0,115200n8 ip=dhcp root=/dev/nfs rw debug memmap=96M@0"
 CONFIG_USE_OF=y
-CONFIG_BUILTIN_DTB="lx200mx"
+CONFIG_BUILTIN_DTB_SOURCE="lx200mx"
 # CONFIG_COMPACTION is not set
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_NET=y
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index da08e75100ab..7f009719304e 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -276,12 +276,13 @@ should_never_return:
 
 	movi	a2, cpu_start_ccount
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	movi	a3, 0
 	s32i	a3, a2, 0
-	memw
 1:
+	memw
 	l32i	a3, a2, 0
 	beqi	a3, 0, 1b
 	wsr	a3, ccount
@@ -317,11 +318,13 @@ ENTRY(cpu_restart)
 	rsr	a0, prid
 	neg	a2, a0
 	movi	a3, cpu_start_id
+	memw
 	s32i	a2, a3, 0
 #if XCHAL_DCACHE_IS_WRITEBACK
 	dhwbi	a3, 0
 #endif
 1:
+	memw
 	l32i	a2, a3, 0
 	dhi	a3, 0
 	bne	a2, a0, 1b
diff --git a/arch/xtensa/kernel/smp.c b/arch/xtensa/kernel/smp.c
index 932d64689bac..be1f280c322c 100644
--- a/arch/xtensa/kernel/smp.c
+++ b/arch/xtensa/kernel/smp.c
@@ -83,7 +83,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	unsigned i;
 
-	for (i = 0; i < max_cpus; ++i)
+	for_each_possible_cpu(i)
 		set_cpu_present(i, true);
 }
 
@@ -96,6 +96,11 @@ void __init smp_init_cpus(void)
 	pr_info("%s: Core Count = %d\n", __func__, ncpus);
 	pr_info("%s: Core Id = %d\n", __func__, core_id);
 
+	if (ncpus > NR_CPUS) {
+		ncpus = NR_CPUS;
+		pr_info("%s: limiting core count by %d\n", __func__, ncpus);
+	}
+
 	for (i = 0; i < ncpus; ++i)
 		set_cpu_possible(i, true);
 }
@@ -195,9 +200,11 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 	int i;
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpu_start_id = cpu;
-	system_flush_invalidate_dcache_range(
-			(unsigned long)&cpu_start_id, sizeof(cpu_start_id));
+	WRITE_ONCE(cpu_start_id, cpu);
+	/* Pairs with the third memw in the cpu_restart */
+	mb();
+	system_flush_invalidate_dcache_range((unsigned long)&cpu_start_id,
+					     sizeof(cpu_start_id));
 #endif
 	smp_call_function_single(0, mx_cpu_start, (void *)cpu, 1);
 
@@ -206,18 +213,21 @@ static int boot_secondary(unsigned int cpu, struct task_struct *ts)
 			ccount = get_ccount();
 		while (!ccount);
 
-		cpu_start_ccount = ccount;
+		WRITE_ONCE(cpu_start_ccount, ccount);
 
-		while (time_before(jiffies, timeout)) {
+		do {
+			/*
+			 * Pairs with the first two memws in the
+			 * .Lboot_secondary.
+			 */
 			mb();
-			if (!cpu_start_ccount)
-				break;
-		}
+			ccount = READ_ONCE(cpu_start_ccount);
+		} while (ccount && time_before(jiffies, timeout));
 
-		if (cpu_start_ccount) {
+		if (ccount) {
 			smp_call_function_single(0, mx_cpu_stop,
-					(void *)cpu, 1);
-			cpu_start_ccount = 0;
+						 (void *)cpu, 1);
+			WRITE_ONCE(cpu_start_ccount, 0);
 			return -EIO;
 		}
 	}
@@ -237,6 +247,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	pr_debug("%s: Calling wakeup_secondary(cpu:%d, idle:%p, sp: %08lx)\n",
 			__func__, cpu, idle, start_info.stack);
 
+	init_completion(&cpu_running);
 	ret = boot_secondary(cpu, idle);
 	if (ret == 0) {
 		wait_for_completion_timeout(&cpu_running,
@@ -298,8 +309,10 @@ void __cpu_die(unsigned int cpu)
 	unsigned long timeout = jiffies + msecs_to_jiffies(1000);
 	while (time_before(jiffies, timeout)) {
 		system_invalidate_dcache_range((unsigned long)&cpu_start_id,
-				sizeof(cpu_start_id));
-		if (cpu_start_id == -cpu) {
+					       sizeof(cpu_start_id));
+		/* Pairs with the second memw in the cpu_restart */
+		mb();
+		if (READ_ONCE(cpu_start_id) == -cpu) {
 			platform_cpu_kill(cpu);
 			return;
 		}
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index fd524a54d2ab..378186b5eb40 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -89,7 +89,7 @@ static int ccount_timer_shutdown(struct clock_event_device *evt)
 		container_of(evt, struct ccount_timer, evt);
 
 	if (timer->irq_enabled) {
-		disable_irq(evt->irq);
+		disable_irq_nosync(evt->irq);
 		timer->irq_enabled = 0;
 	}
 	return 0;