Merge remote-tracking branch 'tip/perf/urgent' into perf/core

To pick up fixes.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

54 files changed, 544 insertions, 255 deletions

diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index b4441b0764d7..a045f3086047 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -149,7 +149,7 @@ config ARC_CPU_770
 	  Support for ARC770 core introduced with Rel 4.10 (Summer 2011)
 	  This core has a bunch of cool new features:
 	  -MMU-v3: Variable Page Sz (4k, 8k, 16k), bigger J-TLB (128x4)
-                   Shared Address Spaces (for sharing TLB entires in MMU)
+                   Shared Address Spaces (for sharing TLB entries in MMU)
 	  -Caches: New Prog Model, Region Flush
 	  -Insns: endian swap, load-locked/store-conditional, time-stamp-ctr
 
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 99cce77ab98f..644815c0516e 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -6,33 +6,11 @@
 # published by the Free Software Foundation.
 #
 
-ifeq ($(CROSS_COMPILE),)
-ifndef CONFIG_CPU_BIG_ENDIAN
-CROSS_COMPILE := arc-linux-
-else
-CROSS_COMPILE := arceb-linux-
-endif
-endif
-
 KBUILD_DEFCONFIG := nsim_700_defconfig
 
 cflags-y	+= -fno-common -pipe -fno-builtin -mmedium-calls -D__linux__
 cflags-$(CONFIG_ISA_ARCOMPACT)	+= -mA7
-cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=archs
-
-is_700 = $(shell $(CC) -dM -E - < /dev/null | grep -q "ARC700" && echo 1 || echo 0)
-
-ifdef CONFIG_ISA_ARCOMPACT
-ifeq ($(is_700), 0)
-    $(error Toolchain not configured for ARCompact builds)
-endif
-endif
-
-ifdef CONFIG_ISA_ARCV2
-ifeq ($(is_700), 1)
-    $(error Toolchain not configured for ARCv2 builds)
-endif
-endif
+cflags-$(CONFIG_ISA_ARCV2)	+= -mcpu=hs38
 
 ifdef CONFIG_ARC_CURR_IN_REG
 # For a global register defintion, make sure it gets passed to every file
@@ -79,7 +57,7 @@ cflags-$(disable_small_data)		+= -mno-sdata -fcall-used-gp
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -mbig-endian
 ldflags-$(CONFIG_CPU_BIG_ENDIAN)	+= -EB
 
-LIBGCC	:= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
+LIBGCC	= $(shell $(CC) $(cflags-y) --print-libgcc-file-name)
 
 # Modules with short calls might break for calls into builtin-kernel
 KBUILD_CFLAGS_MODULE	+= -mlong-calls -mno-millicode
diff --git a/arch/arc/kernel/process.c b/arch/arc/kernel/process.c
index 4674541eba3f..8ce6e7235915 100644
--- a/arch/arc/kernel/process.c
+++ b/arch/arc/kernel/process.c
@@ -241,6 +241,26 @@ int copy_thread(unsigned long clone_flags,
 		task_thread_info(current)->thr_ptr;
 	}
 
+
+	/*
+	 * setup usermode thread pointer #1:
+	 * when child is picked by scheduler, __switch_to() uses @c_callee to
+	 * populate usermode callee regs: this works (despite being in a kernel
+	 * function) since special return path for child @ret_from_fork()
+	 * ensures those regs are not clobbered all the way to RTIE to usermode
+	 */
+	c_callee->r25 = task_thread_info(p)->thr_ptr;
+
+#ifdef CONFIG_ARC_CURR_IN_REG
+	/*
+	 * setup usermode thread pointer #2:
+	 * however for this special use of r25 in kernel, __switch_to() sets
+	 * r25 for kernel needs and only in the final return path is usermode
+	 * r25 setup, from pt_regs->user_r25. So set that up as well
+	 */
+	c_regs->user_r25 = c_callee->r25;
+#endif
+
 	return 0;
 }
 
diff --git a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
index b10dccd0958f..3b1baa8605a7 100644
--- a/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
+++ b/arch/arm/boot/dts/at91-sama5d2_ptc_ek.dts
@@ -11,6 +11,7 @@
 #include "sama5d2-pinfunc.h"
 #include <dt-bindings/mfd/atmel-flexcom.h>
 #include <dt-bindings/gpio/gpio.h>
+#include <dt-bindings/pinctrl/at91.h>
 
 / {
 	model = "Atmel SAMA5D2 PTC EK";
@@ -299,6 +300,7 @@
 							 <PIN_PA30__NWE_NANDWE>,
 							 <PIN_PB2__NRD_NANDOE>;
 						bias-pull-up;
+						atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>;
 					};
 
 					ale_cle_rdy_cs {
diff --git a/arch/arm/boot/dts/bcm63138.dtsi b/arch/arm/boot/dts/bcm63138.dtsi
index 43ee992ccdcf..6df61518776f 100644
--- a/arch/arm/boot/dts/bcm63138.dtsi
+++ b/arch/arm/boot/dts/bcm63138.dtsi
@@ -106,21 +106,23 @@
 		global_timer: timer@1e200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x1e200 0x20>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&axi_clk>;
 		};
 
 		local_timer: local-timer@1e600 {
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x1e600 0x20>;
-			interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) |
+						  IRQ_TYPE_EDGE_RISING)>;
 			clocks = <&axi_clk>;
 		};
 
 		twd_watchdog: watchdog@1e620 {
 			compatible = "arm,cortex-a9-twd-wdt";
 			reg = <0x1e620 0x20>;
-			interrupts = <GIC_PPI 14 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) |
+						  IRQ_TYPE_LEVEL_HIGH)>;
 		};
 
 		armpll: armpll {
@@ -158,7 +160,7 @@
 		serial0: serial@600 {
 			compatible = "brcm,bcm6345-uart";
 			reg = <0x600 0x1b>;
-			interrupts = <GIC_SPI 32 0>;
+			interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&periph_clk>;
 			clock-names = "periph";
 			status = "disabled";
@@ -167,7 +169,7 @@
 		serial1: serial@620 {
 			compatible = "brcm,bcm6345-uart";
 			reg = <0x620 0x1b>;
-			interrupts = <GIC_SPI 33 0>;
+			interrupts = <GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&periph_clk>;
 			clock-names = "periph";
 			status = "disabled";
@@ -180,7 +182,7 @@
 			reg = <0x2000 0x600>, <0xf0 0x10>;
 			reg-names = "nand", "nand-int-base";
 			status = "disabled";
-			interrupts = <GIC_SPI 38 0>;
+			interrupts = <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>;
 			interrupt-names = "nand";
 		};
 
diff --git a/arch/arm/boot/dts/imx53-qsb-common.dtsi b/arch/arm/boot/dts/imx53-qsb-common.dtsi
index 7423d462d1e4..50dde84b72ed 100644
--- a/arch/arm/boot/dts/imx53-qsb-common.dtsi
+++ b/arch/arm/boot/dts/imx53-qsb-common.dtsi
@@ -123,6 +123,17 @@
 	};
 };
 
+&cpu0 {
+	/* CPU rated to 1GHz, not 1.2GHz as per the default settings */
+	operating-points = <
+		/* kHz   uV */
+		166666  850000
+		400000  900000
+		800000  1050000
+		1000000 1200000
+	>;
+};
+
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
diff --git a/arch/arm/boot/dts/stm32mp157c.dtsi b/arch/arm/boot/dts/stm32mp157c.dtsi
index 661be948ab74..185541a5b69f 100644
--- a/arch/arm/boot/dts/stm32mp157c.dtsi
+++ b/arch/arm/boot/dts/stm32mp157c.dtsi
@@ -1078,8 +1078,8 @@
 			interrupts = <GIC_SPI 86 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&rcc SPI6_K>;
 			resets = <&rcc SPI6_R>;
-			dmas = <&mdma1 34 0x0 0x40008 0x0 0x0 0>,
-			       <&mdma1 35 0x0 0x40002 0x0 0x0 0>;
+			dmas = <&mdma1 34 0x0 0x40008 0x0 0x0>,
+			       <&mdma1 35 0x0 0x40002 0x0 0x0>;
 			dma-names = "rx", "tx";
 			status = "disabled";
 		};
diff --git a/arch/arm/boot/dts/sun8i-r40.dtsi b/arch/arm/boot/dts/sun8i-r40.dtsi
index ffd9f00f74a4..5f547c161baf 100644
--- a/arch/arm/boot/dts/sun8i-r40.dtsi
+++ b/arch/arm/boot/dts/sun8i-r40.dtsi
@@ -800,8 +800,7 @@
 		};
 
 		hdmi_phy: hdmi-phy@1ef0000 {
-			compatible = "allwinner,sun8i-r40-hdmi-phy",
-				     "allwinner,sun50i-a64-hdmi-phy";
+			compatible = "allwinner,sun8i-r40-hdmi-phy";
 			reg = <0x01ef0000 0x10000>;
 			clocks = <&ccu CLK_BUS_HDMI1>, <&ccu CLK_HDMI_SLOW>,
 				 <&ccu 7>, <&ccu 16>;
diff --git a/arch/arm/kernel/vmlinux.lds.h b/arch/arm/kernel/vmlinux.lds.h
index ae5fdff18406..8247bc15addc 100644
--- a/arch/arm/kernel/vmlinux.lds.h
+++ b/arch/arm/kernel/vmlinux.lds.h
@@ -49,6 +49,8 @@
 #define ARM_DISCARD							\
 		*(.ARM.exidx.exit.text)					\
 		*(.ARM.extab.exit.text)					\
+		*(.ARM.exidx.text.exit)					\
+		*(.ARM.extab.text.exit)					\
 		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))		\
 		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))		\
 		ARM_EXIT_DISCARD(EXIT_TEXT)				\
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 450c7a4fbc8a..cb094e55dc5f 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -478,15 +478,15 @@ static const struct coproc_reg cp15_regs[] = {
 
 	/* ICC_SGI1R */
 	{ CRm64(12), Op1( 0), is64, access_gic_sgi},
-	/* ICC_ASGI1R */
-	{ CRm64(12), Op1( 1), is64, access_gic_sgi},
-	/* ICC_SGI0R */
-	{ CRm64(12), Op1( 2), is64, access_gic_sgi},
 
 	/* VBAR: swapped by interrupt.S. */
 	{ CRn(12), CRm( 0), Op1( 0), Op2( 0), is32,
 			NULL, reset_val, c12_VBAR, 0x00000000 },
 
+	/* ICC_ASGI1R */
+	{ CRm64(12), Op1( 1), is64, access_gic_sgi},
+	/* ICC_SGI0R */
+	{ CRm64(12), Op1( 2), is64, access_gic_sgi},
 	/* ICC_SRE */
 	{ CRn(12), CRm(12), Op1( 0), Op2(5), is32, access_gic_sre },
 
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index fc91205ff46c..5bf9443cfbaa 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -473,7 +473,7 @@ void pci_ioremap_set_mem_type(int mem_type)
 
 int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
 {
-	BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT);
+	BUG_ON(offset + SZ_64K - 1 > IO_SPACE_LIMIT);
 
 	return ioremap_page_range(PCI_IO_VIRT_BASE + offset,
 				  PCI_IO_VIRT_BASE + offset + SZ_64K,
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index fbc74b5fa3ed..8edf93b4490f 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -413,3 +413,4 @@
 396	common	pkey_free		sys_pkey_free
 397	common	statx			sys_statx
 398	common	rseq			sys_rseq
+399	common	io_pgetevents		sys_io_pgetevents
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 8e38d5267f22..e213f8e867f6 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -966,6 +966,12 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 	return 0;
 }
 
+static int armv8pmu_filter_match(struct perf_event *event)
+{
+	unsigned long evtype = event->hw.config_base & ARMV8_PMU_EVTYPE_EVENT;
+	return evtype != ARMV8_PMUV3_PERFCTR_CHAIN;
+}
+
 static void armv8pmu_reset(void *info)
 {
 	struct arm_pmu *cpu_pmu = (struct arm_pmu *)info;
@@ -1114,6 +1120,7 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->stop			= armv8pmu_stop,
 	cpu_pmu->reset			= armv8pmu_reset,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
+	cpu_pmu->filter_match		= armv8pmu_filter_match;
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 5b4fac434c84..b3354ff94e79 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -64,6 +64,9 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/mmu_context.h>
 
+static int num_standard_resources;
+static struct resource *standard_resources;
+
 phys_addr_t __fdt_pointer __initdata;
 
 /*
@@ -206,14 +209,19 @@ static void __init request_standard_resources(void)
 {
 	struct memblock_region *region;
 	struct resource *res;
+	unsigned long i = 0;
 
 	kernel_code.start   = __pa_symbol(_text);
 	kernel_code.end     = __pa_symbol(__init_begin - 1);
 	kernel_data.start   = __pa_symbol(_sdata);
 	kernel_data.end     = __pa_symbol(_end - 1);
 
+	num_standard_resources = memblock.memory.cnt;
+	standard_resources = alloc_bootmem_low(num_standard_resources *
+					       sizeof(*standard_resources));
+
 	for_each_memblock(memory, region) {
-		res = alloc_bootmem_low(sizeof(*res));
+		res = &standard_resources[i++];
 		if (memblock_is_nomap(region)) {
 			res->name  = "reserved";
 			res->flags = IORESOURCE_MEM;
@@ -243,36 +251,26 @@ static void __init request_standard_resources(void)
 
 static int __init reserve_memblock_reserved_regions(void)
 {
-	phys_addr_t start, end, roundup_end = 0;
-	struct resource *mem, *res;
-	u64 i;
-
-	for_each_reserved_mem_region(i, &start, &end) {
-		if (end <= roundup_end)
-			continue; /* done already */
-
-		start = __pfn_to_phys(PFN_DOWN(start));
-		end = __pfn_to_phys(PFN_UP(end)) - 1;
-		roundup_end = end;
-
-		res = kzalloc(sizeof(*res), GFP_ATOMIC);
-		if (WARN_ON(!res))
-			return -ENOMEM;
-		res->start = start;
-		res->end = end;
-		res->name  = "reserved";
-		res->flags = IORESOURCE_MEM;
-
-		mem = request_resource_conflict(&iomem_resource, res);
-		/*
-		 * We expected memblock_reserve() regions to conflict with
-		 * memory created by request_standard_resources().
-		 */
-		if (WARN_ON_ONCE(!mem))
+	u64 i, j;
+
+	for (i = 0; i < num_standard_resources; ++i) {
+		struct resource *mem = &standard_resources[i];
+		phys_addr_t r_start, r_end, mem_size = resource_size(mem);
+
+		if (!memblock_is_region_reserved(mem->start, mem_size))
 			continue;
-		kfree(res);
 
-		reserve_region_with_split(mem, start, end, "reserved");
+		for_each_reserved_mem_region(j, &r_start, &r_end) {
+			resource_size_t start, end;
+
+			start = max(PFN_PHYS(PFN_DOWN(r_start)), mem->start);
+			end = min(PFN_PHYS(PFN_UP(r_end)) - 1, mem->end);
+
+			if (start > mem->end || end < mem->start)
+				continue;
+
+			reserve_region_with_split(mem, start, end, "reserved");
+		}
 	}
 
 	return 0;
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 07256b08226c..a6c9fbaeaefc 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -57,6 +57,45 @@ static u64 core_reg_offset_from_id(u64 id)
 	return id & ~(KVM_REG_ARCH_MASK | KVM_REG_SIZE_MASK | KVM_REG_ARM_CORE);
 }
 
+static int validate_core_offset(const struct kvm_one_reg *reg)
+{
+	u64 off = core_reg_offset_from_id(reg->id);
+	int size;
+
+	switch (off) {
+	case KVM_REG_ARM_CORE_REG(regs.regs[0]) ...
+	     KVM_REG_ARM_CORE_REG(regs.regs[30]):
+	case KVM_REG_ARM_CORE_REG(regs.sp):
+	case KVM_REG_ARM_CORE_REG(regs.pc):
+	case KVM_REG_ARM_CORE_REG(regs.pstate):
+	case KVM_REG_ARM_CORE_REG(sp_el1):
+	case KVM_REG_ARM_CORE_REG(elr_el1):
+	case KVM_REG_ARM_CORE_REG(spsr[0]) ...
+	     KVM_REG_ARM_CORE_REG(spsr[KVM_NR_SPSR - 1]):
+		size = sizeof(__u64);
+		break;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.vregs[0]) ...
+	     KVM_REG_ARM_CORE_REG(fp_regs.vregs[31]):
+		size = sizeof(__uint128_t);
+		break;
+
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpsr):
+	case KVM_REG_ARM_CORE_REG(fp_regs.fpcr):
+		size = sizeof(__u32);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (KVM_REG_SIZE(reg->id) == size &&
+	    IS_ALIGNED(off, size / sizeof(__u32)))
+		return 0;
+
+	return -EINVAL;
+}
+
 static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 {
 	/*
@@ -76,6 +115,9 @@ static int get_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
+	if (validate_core_offset(reg))
+		return -EINVAL;
+
 	if (copy_to_user(uaddr, ((u32 *)regs) + off, KVM_REG_SIZE(reg->id)))
 		return -EFAULT;
 
@@ -98,6 +140,9 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	    (off + (KVM_REG_SIZE(reg->id) / sizeof(__u32))) >= nr_regs)
 		return -ENOENT;
 
+	if (validate_core_offset(reg))
+		return -EINVAL;
+
 	if (KVM_REG_SIZE(reg->id) > sizeof(tmp))
 		return -EINVAL;
 
@@ -107,17 +152,25 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
-		u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK;
+		u64 mode = (*(u64 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
 		case PSR_AA32_MODE_USR:
+			if (!system_supports_32bit_el0())
+				return -EINVAL;
+			break;
 		case PSR_AA32_MODE_FIQ:
 		case PSR_AA32_MODE_IRQ:
 		case PSR_AA32_MODE_SVC:
 		case PSR_AA32_MODE_ABT:
 		case PSR_AA32_MODE_UND:
+			if (!vcpu_el1_is_32bit(vcpu))
+				return -EINVAL;
+			break;
 		case PSR_MODE_EL0t:
 		case PSR_MODE_EL1t:
 		case PSR_MODE_EL1h:
+			if (vcpu_el1_is_32bit(vcpu))
+				return -EINVAL;
 			break;
 		default:
 			err = -EINVAL;
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 192b3ba07075..f58ea503ad01 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -117,11 +117,14 @@ static pte_t get_clear_flush(struct mm_struct *mm,
 
 		/*
 		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty bit for any page in the set, so check
-		 * them all.  All hugetlb entries are already young.
+		 * the dirty or accessed bit for any page in the set,
+		 * so check them all.
 		 */
 		if (pte_dirty(pte))
 			orig_pte = pte_mkdirty(orig_pte);
+
+		if (pte_young(pte))
+			orig_pte = pte_mkyoung(orig_pte);
 	}
 
 	if (valid) {
@@ -320,11 +323,40 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return get_clear_flush(mm, addr, ptep, pgsize, ncontig);
 }
 
+/*
+ * huge_ptep_set_access_flags will update access flags (dirty, accesssed)
+ * and write permission.
+ *
+ * For a contiguous huge pte range we need to check whether or not write
+ * permission has to change only on the first pte in the set. Then for
+ * all the contiguous ptes we need to check whether or not there is a
+ * discrepancy between dirty or young.
+ */
+static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig)
+{
+	int i;
+
+	if (pte_write(pte) != pte_write(huge_ptep_get(ptep)))
+		return 1;
+
+	for (i = 0; i < ncontig; i++) {
+		pte_t orig_pte = huge_ptep_get(ptep + i);
+
+		if (pte_dirty(pte) != pte_dirty(orig_pte))
+			return 1;
+
+		if (pte_young(pte) != pte_young(orig_pte))
+			return 1;
+	}
+
+	return 0;
+}
+
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 			       unsigned long addr, pte_t *ptep,
 			       pte_t pte, int dirty)
 {
-	int ncontig, i, changed = 0;
+	int ncontig, i;
 	size_t pgsize = 0;
 	unsigned long pfn = pte_pfn(pte), dpfn;
 	pgprot_t hugeprot;
@@ -336,19 +368,23 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	ncontig = find_num_contig(vma->vm_mm, addr, ptep, &pgsize);
 	dpfn = pgsize >> PAGE_SHIFT;
 
+	if (!__cont_access_flags_changed(ptep, pte, ncontig))
+		return 0;
+
 	orig_pte = get_clear_flush(vma->vm_mm, addr, ptep, pgsize, ncontig);
-	if (!pte_same(orig_pte, pte))
-		changed = 1;
 
-	/* Make sure we don't lose the dirty state */
+	/* Make sure we don't lose the dirty or young state */
 	if (pte_dirty(orig_pte))
 		pte = pte_mkdirty(pte);
 
+	if (pte_young(orig_pte))
+		pte = pte_mkyoung(pte);
+
 	hugeprot = pte_pgprot(pte);
 	for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn)
 		set_pte_at(vma->vm_mm, addr, ptep, pfn_pte(pfn, hugeprot));
 
-	return changed;
+	return 1;
 }
 
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index b2fa62922d88..49d6046ca1d0 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -13,6 +13,7 @@
 
 #include <linux/atomic.h>
 #include <linux/cpumask.h>
+#include <linux/sizes.h>
 #include <linux/threads.h>
 
 #include <asm/cachectl.h>
@@ -80,11 +81,10 @@ extern unsigned int vced_count, vcei_count;
 
 #endif
 
-/*
- * One page above the stack is used for branch delay slot "emulation".
- * See dsemul.c for details.
- */
-#define STACK_TOP	((TASK_SIZE & PAGE_MASK) - PAGE_SIZE)
+#define VDSO_RANDOMIZE_SIZE	(TASK_IS_32BIT_ADDR ? SZ_1M : SZ_256M)
+
+extern unsigned long mips_stack_top(void);
+#define STACK_TOP		mips_stack_top()
 
 /*
  * This decides where the kernel will search for a free chunk of vm
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 8fc69891e117..d4f7fd4550e1 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -32,6 +32,7 @@
 #include <linux/nmi.h>
 #include <linux/cpu.h>
 
+#include <asm/abi.h>
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
 #include <asm/cpu.h>
@@ -39,6 +40,7 @@
 #include <asm/dsp.h>
 #include <asm/fpu.h>
 #include <asm/irq.h>
+#include <asm/mips-cps.h>
 #include <asm/msa.h>
 #include <asm/pgtable.h>
 #include <asm/mipsregs.h>
@@ -645,6 +647,29 @@ out:
 	return pc;
 }
 
+unsigned long mips_stack_top(void)
+{
+	unsigned long top = TASK_SIZE & PAGE_MASK;
+
+	/* One page for branch delay slot "emulation" */
+	top -= PAGE_SIZE;
+
+	/* Space for the VDSO, data page & GIC user page */
+	top -= PAGE_ALIGN(current->thread.abi->vdso->size);
+	top -= PAGE_SIZE;
+	top -= mips_gic_present() ? PAGE_SIZE : 0;
+
+	/* Space for cache colour alignment */
+	if (cpu_has_dc_aliases)
+		top -= shm_align_mask + 1;
+
+	/* Space to randomize the VDSO base */
+	if (current->flags & PF_RANDOMIZE)
+		top -= VDSO_RANDOMIZE_SIZE;
+
+	return top;
+}
+
 /*
  * Don't forget that the stack pointer must be aligned on a 8 bytes
  * boundary for 32-bits ABI and 16 bytes for 64-bits ABI.
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index c71d1eb7da59..8aaaa42f91ed 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -846,6 +846,34 @@ static void __init arch_mem_init(char **cmdline_p)
 	struct memblock_region *reg;
 	extern void plat_mem_setup(void);
 
+	/*
+	 * Initialize boot_command_line to an innocuous but non-empty string in
+	 * order to prevent early_init_dt_scan_chosen() from copying
+	 * CONFIG_CMDLINE into it without our knowledge. We handle
+	 * CONFIG_CMDLINE ourselves below & don't want to duplicate its
+	 * content because repeating arguments can be problematic.
+	 */
+	strlcpy(boot_command_line, " ", COMMAND_LINE_SIZE);
+
+	/* call board setup routine */
+	plat_mem_setup();
+
+	/*
+	 * Make sure all kernel memory is in the maps.  The "UP" and
+	 * "DOWN" are opposite for initdata since if it crosses over
+	 * into another memory section you don't want that to be
+	 * freed when the initdata is freed.
+	 */
+	arch_mem_addpart(PFN_DOWN(__pa_symbol(&_text)) << PAGE_SHIFT,
+			 PFN_UP(__pa_symbol(&_edata)) << PAGE_SHIFT,
+			 BOOT_MEM_RAM);
+	arch_mem_addpart(PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT,
+			 PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT,
+			 BOOT_MEM_INIT_RAM);
+
+	pr_info("Determined physical RAM map:\n");
+	print_memory_map();
+
 #if defined(CONFIG_CMDLINE_BOOL) && defined(CONFIG_CMDLINE_OVERRIDE)
 	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
 #else
@@ -873,26 +901,6 @@ static void __init arch_mem_init(char **cmdline_p)
 	}
 #endif
 #endif
-
-	/* call board setup routine */
-	plat_mem_setup();
-
-	/*
-	 * Make sure all kernel memory is in the maps.  The "UP" and
-	 * "DOWN" are opposite for initdata since if it crosses over
-	 * into another memory section you don't want that to be
-	 * freed when the initdata is freed.
-	 */
-	arch_mem_addpart(PFN_DOWN(__pa_symbol(&_text)) << PAGE_SHIFT,
-			 PFN_UP(__pa_symbol(&_edata)) << PAGE_SHIFT,
-			 BOOT_MEM_RAM);
-	arch_mem_addpart(PFN_UP(__pa_symbol(&__init_begin)) << PAGE_SHIFT,
-			 PFN_DOWN(__pa_symbol(&__init_end)) << PAGE_SHIFT,
-			 BOOT_MEM_INIT_RAM);
-
-	pr_info("Determined physical RAM map:\n");
-	print_memory_map();
-
 	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 
 	*cmdline_p = command_line;
diff --git a/arch/mips/kernel/vdso.c b/arch/mips/kernel/vdso.c
index 8f845f6e5f42..48a9c6b90e07 100644
--- a/arch/mips/kernel/vdso.c
+++ b/arch/mips/kernel/vdso.c
@@ -15,6 +15,7 @@
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/random.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/timekeeper_internal.h>
@@ -97,6 +98,21 @@ void update_vsyscall_tz(void)
 	}
 }
 
+static unsigned long vdso_base(void)
+{
+	unsigned long base;
+
+	/* Skip the delay slot emulation page */
+	base = STACK_TOP + PAGE_SIZE;
+
+	if (current->flags & PF_RANDOMIZE) {
+		base += get_random_int() & (VDSO_RANDOMIZE_SIZE - 1);
+		base = PAGE_ALIGN(base);
+	}
+
+	return base;
+}
+
 int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mips_vdso_image *image = current->thread.abi->vdso;
@@ -137,7 +153,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
 	if (cpu_has_dc_aliases)
 		size += shm_align_mask + 1;
 
-	base = get_unmapped_area(NULL, 0, size, 0, 0);
+	base = get_unmapped_area(NULL, vdso_base(), size, 0, 0);
 	if (IS_ERR_VALUE(base)) {
 		ret = base;
 		goto out;
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 3a6f34ef5ffc..069acec3df9f 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -280,9 +280,11 @@
 	 * unset_bytes = end_addr - current_addr + 1
 	 *      a2     =    t1    -      a0      + 1
 	 */
+	.set		reorder
 	PTR_SUBU	a2, t1, a0
+	PTR_ADDIU	a2, 1
 	jr		ra
-	 PTR_ADDIU	a2, 1
+	.set		noreorder
 
 	.endm
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 2fdc865ca374..2a2486526d1f 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -114,7 +114,7 @@
  */
 #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
 			 _PAGE_ACCESSED | H_PAGE_THP_HUGE | _PAGE_PTE | \
-			 _PAGE_SOFT_DIRTY)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
 /*
  * user access blocked by key
  */
@@ -132,7 +132,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
 			 _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE |	\
-			 _PAGE_SOFT_DIRTY)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
 
 #define H_PTE_PKEY  (H_PTE_PKEY_BIT0 | H_PTE_PKEY_BIT1 | H_PTE_PKEY_BIT2 | \
 		     H_PTE_PKEY_BIT3 | H_PTE_PKEY_BIT4)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 913c5725cdb2..bb6ac471a784 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1306,6 +1306,16 @@ void show_user_instructions(struct pt_regs *regs)
 
 	pc = regs->nip - (instructions_to_print * 3 / 4 * sizeof(int));
 
+	/*
+	 * Make sure the NIP points at userspace, not kernel text/data or
+	 * elsewhere.
+	 */
+	if (!__access_ok(pc, instructions_to_print * sizeof(int), USER_DS)) {
+		pr_info("%s[%d]: Bad NIP, not dumping instructions.\n",
+			current->comm, current->pid);
+		return;
+	}
+
 	pr_info("%s[%d]: code: ", current->comm, current->pid);
 
 	for (i = 0; i < instructions_to_print; i++) {
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 933c574e1cf7..998f8d089ac7 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -646,6 +646,16 @@ int kvmppc_book3s_radix_page_fault(struct kvm_run *run, struct kvm_vcpu *vcpu,
 	 */
 	local_irq_disable();
 	ptep = __find_linux_pte(vcpu->arch.pgdir, hva, NULL, &shift);
+	/*
+	 * If the PTE disappeared temporarily due to a THP
+	 * collapse, just return and let the guest try again.
+	 */
+	if (!ptep) {
+		local_irq_enable();
+		if (page)
+			put_page(page);
+		return RESUME_GUEST;
+	}
 	pte = *ptep;
 	local_irq_enable();
 
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index 6ae2777c220d..5ffee298745f 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -28,12 +28,6 @@ static int __patch_instruction(unsigned int *exec_addr, unsigned int instr,
 {
 	int err;
 
-	/* Make sure we aren't patching a freed init section */
-	if (init_mem_is_free && init_section_contains(exec_addr, 4)) {
-		pr_debug("Skipping init section patching addr: 0x%px\n", exec_addr);
-		return 0;
-	}
-
 	__put_user_size(instr, patch_addr, 4, err);
 	if (err)
 		return err;
@@ -148,7 +142,7 @@ static inline int unmap_patch_area(unsigned long addr)
 	return 0;
 }
 
-int patch_instruction(unsigned int *addr, unsigned int instr)
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	int err;
 	unsigned int *patch_addr = NULL;
@@ -188,12 +182,22 @@ out:
 }
 #else /* !CONFIG_STRICT_KERNEL_RWX */
 
-int patch_instruction(unsigned int *addr, unsigned int instr)
+static int do_patch_instruction(unsigned int *addr, unsigned int instr)
 {
 	return raw_patch_instruction(addr, instr);
 }
 
 #endif /* CONFIG_STRICT_KERNEL_RWX */
+
+int patch_instruction(unsigned int *addr, unsigned int instr)
+{
+	/* Make sure we aren't patching a freed init section */
+	if (init_mem_is_free && init_section_contains(addr, 4)) {
+		pr_debug("Skipping init section patching addr: 0x%px\n", addr);
+		return 0;
+	}
+	return do_patch_instruction(addr, instr);
+}
 NOKPROBE_SYMBOL(patch_instruction);
 
 int patch_branch(unsigned int *addr, unsigned long target, int flags)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 59d07bd5374a..055b211b7126 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1217,9 +1217,10 @@ int find_and_online_cpu_nid(int cpu)
 		 * Need to ensure that NODE_DATA is initialized for a node from
 		 * available memory (see memblock_alloc_try_nid). If unable to
 		 * init the node, then default to nearest node that has memory
-		 * installed.
+		 * installed. Skip onlining a node if the subsystems are not
+		 * yet initialized.
 		 */
-		if (try_online_node(new_nid))
+		if (!topology_inited || try_online_node(new_nid))
 			new_nid = first_online_node;
 #else
 		/*
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index aee603123030..b2d26d9d8489 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -186,7 +186,7 @@ static void __init setup_bootmem(void)
 	BUG_ON(mem_size == 0);
 
 	set_max_mapnr(PFN_DOWN(mem_size));
-	max_low_pfn = pfn_base + PFN_DOWN(mem_size);
+	max_low_pfn = memblock_end_of_DRAM();
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	setup_initrd();
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index 3cae9168f63c..e44a8d7959f5 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -108,7 +108,8 @@ int sclp_early_get_core_info(struct sclp_core_info *info);
 void sclp_early_get_ipl_info(struct sclp_ipl_info *info);
 void sclp_early_detect(void);
 void sclp_early_printk(const char *s);
-void __sclp_early_printk(const char *s, unsigned int len);
+void sclp_early_printk_force(const char *s);
+void __sclp_early_printk(const char *s, unsigned int len, unsigned int force);
 
 int _sclp_get_core_info(struct sclp_core_info *info);
 int sclp_core_configure(u8 core);
diff --git a/arch/s390/kernel/early_printk.c b/arch/s390/kernel/early_printk.c
index 9431784d7796..40c1dfec944e 100644
--- a/arch/s390/kernel/early_printk.c
+++ b/arch/s390/kernel/early_printk.c
@@ -10,7 +10,7 @@
 
 static void sclp_early_write(struct console *con, const char *s, unsigned int len)
 {
-	__sclp_early_printk(s, len);
+	__sclp_early_printk(s, len, 0);
 }
 
 static struct console sclp_early_console = {
diff --git a/arch/s390/kernel/swsusp.S b/arch/s390/kernel/swsusp.S
index a049a7b9d6e8..c1a080b11ae9 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -198,12 +198,10 @@ pgm_check_entry:
 
 	/* Suspend CPU not available -> panic */
 	larl	%r15,init_thread_union
-	ahi	%r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
+	aghi	%r15,1<<(PAGE_SHIFT+THREAD_SIZE_ORDER)
+	aghi	%r15,-STACK_FRAME_OVERHEAD
 	larl	%r2,.Lpanic_string
-	lghi	%r1,0
-	sam31
-	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE
-	brasl	%r14,sclp_early_printk
+	brasl	%r14,sclp_early_printk_force
 	larl	%r3,.Ldisabled_wait_31
 	lpsw	0(%r3)
 4:
diff --git a/arch/sparc/include/asm/cpudata_64.h b/arch/sparc/include/asm/cpudata_64.h
index 666d6b5c0440..9c3fc03abe9a 100644
--- a/arch/sparc/include/asm/cpudata_64.h
+++ b/arch/sparc/include/asm/cpudata_64.h
@@ -28,7 +28,7 @@ typedef struct {
 	unsigned short	sock_id;	/* physical package */
 	unsigned short	core_id;
 	unsigned short  max_cache_id;	/* groupings of highest shared cache */
-	unsigned short	proc_id;	/* strand (aka HW thread) id */
+	signed short	proc_id;	/* strand (aka HW thread) id */
 } cpuinfo_sparc;
 
 DECLARE_PER_CPU(cpuinfo_sparc, __cpu_data);
diff --git a/arch/sparc/include/uapi/asm/unistd.h b/arch/sparc/include/uapi/asm/unistd.h
index 09acf0ddec10..45b4bf1875e6 100644
--- a/arch/sparc/include/uapi/asm/unistd.h
+++ b/arch/sparc/include/uapi/asm/unistd.h
@@ -427,8 +427,9 @@
 #define __NR_preadv2		358
 #define __NR_pwritev2		359
 #define __NR_statx		360
+#define __NR_io_pgetevents	361
 
-#define NR_syscalls		361
+#define NR_syscalls		362
 
 /* Bitmask values returned from kern_features system call.  */
 #define KERN_FEATURE_MIXED_MODE_STACK	0x00000001
diff --git a/arch/sparc/kernel/kgdb_32.c b/arch/sparc/kernel/kgdb_32.c
index 5868fc333ea8..639c8e54530a 100644
--- a/arch/sparc/kernel/kgdb_32.c
+++ b/arch/sparc/kernel/kgdb_32.c
@@ -122,7 +122,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 			linux_regs->pc = addr;
 			linux_regs->npc = addr + 4;
 		}
-		/* fallthru */
+		/* fall through */
 
 	case 'D':
 	case 'k':
diff --git a/arch/sparc/kernel/kgdb_64.c b/arch/sparc/kernel/kgdb_64.c
index d5f7dc6323d5..a68bbddbdba4 100644
--- a/arch/sparc/kernel/kgdb_64.c
+++ b/arch/sparc/kernel/kgdb_64.c
@@ -148,7 +148,7 @@ int kgdb_arch_handle_exception(int e_vector, int signo, int err_code,
 			linux_regs->tpc = addr;
 			linux_regs->tnpc = addr + 4;
 		}
-		/* fallthru */
+		/* fall through */
 
 	case 'D':
 	case 'k':
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index d3149baaa33c..67b3e6b3ce5d 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -24,6 +24,7 @@
 #include <asm/cpudata.h>
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
+#include <linux/sched/clock.h>
 #include <asm/nmi.h>
 #include <asm/pcr.h>
 #include <asm/cacheflush.h>
@@ -927,6 +928,8 @@ static void read_in_all_counters(struct cpu_hw_events *cpuc)
 			sparc_perf_event_update(cp, &cp->hw,
 						cpuc->current_idx[i]);
 			cpuc->current_idx[i] = PIC_NO_INDEX;
+			if (cp->hw.state & PERF_HES_STOPPED)
+				cp->hw.state |= PERF_HES_ARCH;
 		}
 	}
 }
@@ -959,10 +962,12 @@ static void calculate_single_pcr(struct cpu_hw_events *cpuc)
 
 		enc = perf_event_get_enc(cpuc->events[i]);
 		cpuc->pcr[0] &= ~mask_for_index(idx);
-		if (hwc->state & PERF_HES_STOPPED)
+		if (hwc->state & PERF_HES_ARCH) {
 			cpuc->pcr[0] |= nop_for_index(idx);
-		else
+		} else {
 			cpuc->pcr[0] |= event_encoding(enc, idx);
+			hwc->state = 0;
+		}
 	}
 out:
 	cpuc->pcr[0] |= cpuc->event[0]->hw.config_base;
@@ -988,6 +993,9 @@ static void calculate_multiple_pcrs(struct cpu_hw_events *cpuc)
 
 		cpuc->current_idx[i] = idx;
 
+		if (cp->hw.state & PERF_HES_ARCH)
+			continue;
+
 		sparc_pmu_start(cp, PERF_EF_RELOAD);
 	}
 out:
@@ -1079,6 +1087,8 @@ static void sparc_pmu_start(struct perf_event *event, int flags)
 	event->hw.state = 0;
 
 	sparc_pmu_enable_event(cpuc, &event->hw, idx);
+
+	perf_event_update_userpage(event);
 }
 
 static void sparc_pmu_stop(struct perf_event *event, int flags)
@@ -1371,9 +1381,9 @@ static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 	cpuc->events[n0] = event->hw.event_base;
 	cpuc->current_idx[n0] = PIC_NO_INDEX;
 
-	event->hw.state = PERF_HES_UPTODATE;
+	event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 	if (!(ef_flags & PERF_EF_START))
-		event->hw.state |= PERF_HES_STOPPED;
+		event->hw.state |= PERF_HES_ARCH;
 
 	/*
 	 * If group events scheduling transaction was started,
@@ -1603,6 +1613,8 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
 	struct pt_regs *regs;
+	u64 finish_clock;
+	u64 start_clock;
 	int i;
 
 	if (!atomic_read(&active_events))
@@ -1616,6 +1628,8 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 		return NOTIFY_DONE;
 	}
 
+	start_clock = sched_clock();
+
 	regs = args->regs;
 
 	cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1654,6 +1668,10 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 			sparc_pmu_stop(event, 0);
 	}
 
+	finish_clock = sched_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+
 	return NOTIFY_STOP;
 }
 
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index f6528884a2c8..4073e2b87dd0 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -84,8 +84,9 @@ __handle_signal:
 		ldx			[%sp + PTREGS_OFF + PT_V9_TSTATE], %l1
 		sethi			%hi(0xf << 20), %l4
 		and			%l1, %l4, %l4
+		andn			%l1, %l4, %l1
 		ba,pt			%xcc, __handle_preemption_continue
-		 andn			%l1, %l4, %l1
+		 srl			%l4, 20, %l4
 
 		/* When returning from a NMI (%pil==15) interrupt we want to
 		 * avoid running softirqs, doing IRQ tracing, preempting, etc.
diff --git a/arch/sparc/kernel/systbls_32.S b/arch/sparc/kernel/systbls_32.S
index 12bee14b552c..621a363098ec 100644
--- a/arch/sparc/kernel/systbls_32.S
+++ b/arch/sparc/kernel/systbls_32.S
@@ -90,4 +90,4 @@ sys_call_table:
 /*345*/	.long sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.long sys_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
 /*355*/	.long sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2
-/*360*/	.long sys_statx
+/*360*/	.long sys_statx, sys_io_pgetevents
diff --git a/arch/sparc/kernel/systbls_64.S b/arch/sparc/kernel/systbls_64.S
index 387ef993880a..bb68c805b891 100644
--- a/arch/sparc/kernel/systbls_64.S
+++ b/arch/sparc/kernel/systbls_64.S
@@ -91,7 +91,7 @@ sys_call_table32:
 	.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.word sys32_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
 	.word compat_sys_setsockopt, sys_mlock2, sys_copy_file_range, compat_sys_preadv2, compat_sys_pwritev2
-/*360*/	.word sys_statx
+/*360*/	.word sys_statx, compat_sys_io_pgetevents
 
 #endif /* CONFIG_COMPAT */
 
@@ -173,4 +173,4 @@ sys_call_table:
 	.word sys_renameat2, sys_seccomp, sys_getrandom, sys_memfd_create, sys_bpf
 /*350*/	.word sys64_execveat, sys_membarrier, sys_userfaultfd, sys_bind, sys_listen
 	.word sys_setsockopt, sys_mlock2, sys_copy_file_range, sys_preadv2, sys_pwritev2
-/*360*/	.word sys_statx
+/*360*/	.word sys_statx, sys_io_pgetevents
diff --git a/arch/sparc/kernel/viohs.c b/arch/sparc/kernel/viohs.c
index 635d67ffc9a3..7db5aabe9708 100644
--- a/arch/sparc/kernel/viohs.c
+++ b/arch/sparc/kernel/viohs.c
@@ -180,11 +180,17 @@ static int send_dreg(struct vio_driver_state *vio)
 		struct vio_dring_register pkt;
 		char all[sizeof(struct vio_dring_register) +
 			 (sizeof(struct ldc_trans_cookie) *
-			  dr->ncookies)];
+			  VIO_MAX_RING_COOKIES)];
 	} u;
+	size_t bytes = sizeof(struct vio_dring_register) +
+		       (sizeof(struct ldc_trans_cookie) *
+			dr->ncookies);
 	int i;
 
-	memset(&u, 0, sizeof(u));
+	if (WARN_ON(bytes > sizeof(u)))
+		return -EINVAL;
+
+	memset(&u, 0, bytes);
 	init_tag(&u.pkt.tag, VIO_TYPE_CTRL, VIO_SUBTYPE_INFO, VIO_DRING_REG);
 	u.pkt.dring_ident = 0;
 	u.pkt.num_descr = dr->num_entries;
@@ -206,7 +212,7 @@ static int send_dreg(struct vio_driver_state *vio)
 		       (unsigned long long) u.pkt.cookies[i].cookie_size);
 	}
 
-	return send_ctrl(vio, &u.pkt.tag, sizeof(u));
+	return send_ctrl(vio, &u.pkt.tag, bytes);
 }
 
 static int send_rdx(struct vio_driver_state *vio)
diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
index dd0b5a92ffd0..dc85570d8839 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
@@ -31,23 +31,21 @@ obj-y += $(vdso_img_objs)
 targets += $(vdso_img_cfiles)
 targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
 
-export CPPFLAGS_vdso.lds += -P -C
+CPPFLAGS_vdso.lds += -P -C
 
 VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 			-Wl,--no-undefined \
 			-Wl,-z,max-page-size=8192 -Wl,-z,common-page-size=8192 \
 			$(DISABLE_LTO)
 
-$(obj)/vdso64.so.dbg: $(src)/vdso.lds $(vobjs) FORCE
+$(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
-define cmd_vdso2c
-	$(obj)/vdso2c $< $(<:%.dbg=%) $@
-endef
+      cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@
 
 $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 	$(call if_changed,vdso2c)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index fa3f439f0a92..141d415a8c80 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -68,7 +68,13 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
        $(filter -g%,$(KBUILD_CFLAGS)) $(call cc-option, -fno-stack-protector) \
        -fno-omit-frame-pointer -foptimize-sibling-calls \
-       -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO $(RETPOLINE_VDSO_CFLAGS)
+       -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+  CFL += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
 
 $(vobjs): KBUILD_CFLAGS := $(filter-out $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
 
@@ -138,7 +144,13 @@ KBUILD_CFLAGS_32 += $(call cc-option, -fno-stack-protector)
 KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
 KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
 KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+
+ifdef CONFIG_RETPOLINE
+ifneq ($(RETPOLINE_VDSO_CFLAGS),)
+  KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
+endif
+endif
+
 $(obj)/vdso32.so.dbg: KBUILD_CFLAGS = $(KBUILD_CFLAGS_32)
 
 $(obj)/vdso32.so.dbg: FORCE \
diff --git a/arch/x86/entry/vdso/vclock_gettime.c b/arch/x86/entry/vdso/vclock_gettime.c
index f19856d95c60..e48ca3afa091 100644
--- a/arch/x86/entry/vdso/vclock_gettime.c
+++ b/arch/x86/entry/vdso/vclock_gettime.c
@@ -43,8 +43,9 @@ extern u8 hvclock_page
 notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_clock_gettime), "D" (clock), "S" (ts) : "memory");
+	asm ("syscall" : "=a" (ret), "=m" (*ts) :
+	     "0" (__NR_clock_gettime), "D" (clock), "S" (ts) :
+	     "memory", "rcx", "r11");
 	return ret;
 }
 
@@ -52,8 +53,9 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
 
-	asm("syscall" : "=a" (ret) :
-	    "0" (__NR_gettimeofday), "D" (tv), "S" (tz) : "memory");
+	asm ("syscall" : "=a" (ret), "=m" (*tv), "=m" (*tz) :
+	     "0" (__NR_gettimeofday), "D" (tv), "S" (tz) :
+	     "memory", "rcx", "r11");
 	return ret;
 }
 
@@ -64,13 +66,13 @@ notrace static long vdso_fallback_gettime(long clock, struct timespec *ts)
 {
 	long ret;
 
-	asm(
+	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[clock], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
-		: "=a" (ret)
-		: "0" (__NR_clock_gettime), "g" (clock), "c" (ts)
+		: "=a" (ret), "=m" (*ts)
+		: "0" (__NR_clock_gettime), [clock] "g" (clock), "c" (ts)
 		: "memory", "edx");
 	return ret;
 }
@@ -79,13 +81,13 @@ notrace static long vdso_fallback_gtod(struct timeval *tv, struct timezone *tz)
 {
 	long ret;
 
-	asm(
+	asm (
 		"mov %%ebx, %%edx \n"
-		"mov %2, %%ebx \n"
+		"mov %[tv], %%ebx \n"
 		"call __kernel_vsyscall \n"
 		"mov %%edx, %%ebx \n"
-		: "=a" (ret)
-		: "0" (__NR_gettimeofday), "g" (tv), "c" (tz)
+		: "=a" (ret), "=m" (*tv), "=m" (*tz)
+		: "0" (__NR_gettimeofday), [tv] "g" (tv), "c" (tz)
 		: "memory", "edx");
 	return ret;
 }
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b64acb08a62b..106b7d0e2dae 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -124,7 +124,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
 			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY |	\
-			 _PAGE_SOFT_DIRTY)
+			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
 #define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE)
 
 /*
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index a80c0673798f..e60c45fd3679 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -10,8 +10,13 @@ struct cpumask;
 struct mm_struct;
 
 #ifdef CONFIG_X86_UV
+#include <linux/efi.h>
 
 extern enum uv_system_type get_uv_system_type(void);
+static inline bool is_early_uv_system(void)
+{
+	return !((efi.uv_systab == EFI_INVALID_TABLE_ADDR) || !efi.uv_systab);
+}
 extern int is_uv_system(void);
 extern int is_uv_hubless(void);
 extern void uv_cpu_init(void);
@@ -23,6 +28,7 @@ extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 #else	/* X86_UV */
 
 static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
+static inline bool is_early_uv_system(void)	{ return 0; }
 static inline int is_uv_system(void)	{ return 0; }
 static inline int is_uv_hubless(void)	{ return 0; }
 static inline void uv_cpu_init(void)	{ }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 22ab408177b2..eeea634bee0a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -922,7 +922,7 @@ static void init_amd(struct cpuinfo_x86 *c)
 static unsigned int amd_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 {
 	/* AMD errata T13 (order #21922) */
-	if ((c->x86 == 6)) {
+	if (c->x86 == 6) {
 		/* Duron Rev A0 */
 		if (c->x86_model == 3 && c->x86_stepping == 0)
 			size = 64;
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 285eb3ec4200..3736f6dc9545 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -529,14 +529,14 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
 bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 _cbm, int closid, bool exclusive);
+			   unsigned long cbm, int closid, bool exclusive);
 unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
-				  u32 cbm);
+				  unsigned long cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 int rdtgroup_tasks_assigned(struct rdtgroup *r);
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
 int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm);
 bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
 int rdt_pseudo_lock_init(void);
 void rdt_pseudo_lock_release(void);
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 676c8a3ecdb2..6d06e0b8ecf3 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -789,25 +789,27 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 /**
  * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
  * @d: RDT domain
- * @_cbm: CBM to test
+ * @cbm: CBM to test
  *
- * @d represents a cache instance and @_cbm a capacity bitmask that is
- * considered for it. Determine if @_cbm overlaps with any existing
+ * @d represents a cache instance and @cbm a capacity bitmask that is
+ * considered for it. Determine if @cbm overlaps with any existing
  * pseudo-locked region on @d.
  *
- * Return: true if @_cbm overlaps with pseudo-locked region on @d, false
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
+ * Return: true if @cbm overlaps with pseudo-locked region on @d, false
  * otherwise.
  */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm)
 {
-	unsigned long *cbm = (unsigned long *)&_cbm;
-	unsigned long *cbm_b;
 	unsigned int cbm_len;
+	unsigned long cbm_b;
 
 	if (d->plr) {
 		cbm_len = d->plr->r->cache.cbm_len;
-		cbm_b = (unsigned long *)&d->plr->cbm;
-		if (bitmap_intersects(cbm, cbm_b, cbm_len))
+		cbm_b = d->plr->cbm;
+		if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
 			return true;
 	}
 	return false;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 1b8e86a5d5e1..b140c68bc14b 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -975,33 +975,34 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
  * is false then overlaps with any resource group or hardware entities
  * will be considered.
  *
+ * @cbm is unsigned long, even if only 32 bits are used, to make the
+ * bitmap functions work correctly.
+ *
  * Return: false if CBM does not overlap, true if it does.
  */
 bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
-			   u32 _cbm, int closid, bool exclusive)
+			   unsigned long cbm, int closid, bool exclusive)
 {
-	unsigned long *cbm = (unsigned long *)&_cbm;
-	unsigned long *ctrl_b;
 	enum rdtgrp_mode mode;
+	unsigned long ctrl_b;
 	u32 *ctrl;
 	int i;
 
 	/* Check for any overlap with regions used by hardware directly */
 	if (!exclusive) {
-		if (bitmap_intersects(cbm,
-				      (unsigned long *)&r->cache.shareable_bits,
-				      r->cache.cbm_len))
+		ctrl_b = r->cache.shareable_bits;
+		if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
 			return true;
 	}
 
 	/* Check for overlap with other resource groups */
 	ctrl = d->ctrl_val;
 	for (i = 0; i < closids_supported(); i++, ctrl++) {
-		ctrl_b = (unsigned long *)ctrl;
+		ctrl_b = *ctrl;
 		mode = rdtgroup_mode_by_closid(i);
 		if (closid_allocated(i) && i != closid &&
 		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
-			if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
+			if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
 				if (exclusive) {
 					if (mode == RDT_MODE_EXCLUSIVE)
 						return true;
@@ -1138,15 +1139,18 @@ out:
  * computed by first dividing the total cache size by the CBM length to
  * determine how many bytes each bit in the bitmask represents. The result
  * is multiplied with the number of bits set in the bitmask.
+ *
+ * @cbm is unsigned long, even if only 32 bits are used to make the
+ * bitmap functions work correctly.
  */
 unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
-				  struct rdt_domain *d, u32 cbm)
+				  struct rdt_domain *d, unsigned long cbm)
 {
 	struct cpu_cacheinfo *ci;
 	unsigned int size = 0;
 	int num_b, i;
 
-	num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len);
+	num_b = bitmap_weight(&cbm, r->cache.cbm_len);
 	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
 	for (i = 0; i < ci->num_leaves; i++) {
 		if (ci->info_list[i].level == r->cache_level) {
@@ -2353,6 +2357,7 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 	u32 used_b = 0, unused_b = 0;
 	u32 closid = rdtgrp->closid;
 	struct rdt_resource *r;
+	unsigned long tmp_cbm;
 	enum rdtgrp_mode mode;
 	struct rdt_domain *d;
 	int i, ret;
@@ -2390,9 +2395,14 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			 * modify the CBM based on system availability.
 			 */
 			cbm_ensure_valid(&d->new_ctrl, r);
-			if (bitmap_weight((unsigned long *) &d->new_ctrl,
-					  r->cache.cbm_len) <
-					r->cache.min_cbm_bits) {
+			/*
+			 * Assign the u32 CBM to an unsigned long to ensure
+			 * that bitmap_weight() does not access out-of-bound
+			 * memory.
+			 */
+			tmp_cbm = d->new_ctrl;
+			if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) <
+			    r->cache.min_cbm_bits) {
 				rdt_last_cmd_printf("no space on %s:%d\n",
 						    r->name, d->id);
 				return -ENOSPC;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index dd6b564f65e3..19c3c6bec325 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -26,6 +26,7 @@
 #include <asm/apic.h>
 #include <asm/intel-family.h>
 #include <asm/i8259.h>
+#include <asm/uv/uv.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -1433,6 +1434,9 @@ void __init tsc_early_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_TSC))
 		return;
+	/* Don't change UV TSC multi-chassis synchronization */
+	if (is_early_uv_system())
+		return;
 	if (!determine_cpu_tsc_frequencies(true))
 		return;
 	loops_per_jiffy = get_loops_per_jiffy();
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d7e9bce6ff61..51b953ad9d4e 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -249,6 +249,17 @@ static u64 __read_mostly shadow_nonpresent_or_rsvd_mask;
  */
 static const u64 shadow_nonpresent_or_rsvd_mask_len = 5;
 
+/*
+ * In some cases, we need to preserve the GFN of a non-present or reserved
+ * SPTE when we usurp the upper five bits of the physical address space to
+ * defend against L1TF, e.g. for MMIO SPTEs.  To preserve the GFN, we'll
+ * shift bits of the GFN that overlap with shadow_nonpresent_or_rsvd_mask
+ * left into the reserved bits, i.e. the GFN in the SPTE will be split into
+ * high and low parts.  This mask covers the lower bits of the GFN.
+ */
+static u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
+
+
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static union kvm_mmu_page_role
 kvm_mmu_calc_root_page_role(struct kvm_vcpu *vcpu);
@@ -357,9 +368,7 @@ static bool is_mmio_spte(u64 spte)
 
 static gfn_t get_mmio_spte_gfn(u64 spte)
 {
-	u64 mask = generation_mmio_spte_mask(MMIO_GEN_MASK) | shadow_mmio_mask |
-		   shadow_nonpresent_or_rsvd_mask;
-	u64 gpa = spte & ~mask;
+	u64 gpa = spte & shadow_nonpresent_or_rsvd_lower_gfn_mask;
 
 	gpa |= (spte >> shadow_nonpresent_or_rsvd_mask_len)
 	       & shadow_nonpresent_or_rsvd_mask;
@@ -423,6 +432,8 @@ EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
 static void kvm_mmu_reset_all_pte_masks(void)
 {
+	u8 low_phys_bits;
+
 	shadow_user_mask = 0;
 	shadow_accessed_mask = 0;
 	shadow_dirty_mask = 0;
@@ -437,12 +448,17 @@ static void kvm_mmu_reset_all_pte_masks(void)
 	 * appropriate mask to guard against L1TF attacks. Otherwise, it is
 	 * assumed that the CPU is not vulnerable to L1TF.
 	 */
+	low_phys_bits = boot_cpu_data.x86_phys_bits;
 	if (boot_cpu_data.x86_phys_bits <
-	    52 - shadow_nonpresent_or_rsvd_mask_len)
+	    52 - shadow_nonpresent_or_rsvd_mask_len) {
 		shadow_nonpresent_or_rsvd_mask =
 			rsvd_bits(boot_cpu_data.x86_phys_bits -
 				  shadow_nonpresent_or_rsvd_mask_len,
 				  boot_cpu_data.x86_phys_bits - 1);
+		low_phys_bits -= shadow_nonpresent_or_rsvd_mask_len;
+	}
+	shadow_nonpresent_or_rsvd_lower_gfn_mask =
+		GENMASK_ULL(low_phys_bits - 1, PAGE_SHIFT);
 }
 
 static int is_cpuid_PSE36(void)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d96092b35936..61ccfb13899e 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -436,14 +436,18 @@ static inline struct kvm_svm *to_kvm_svm(struct kvm *kvm)
 
 static inline bool svm_sev_enabled(void)
 {
-	return max_sev_asid;
+	return IS_ENABLED(CONFIG_KVM_AMD_SEV) ? max_sev_asid : 0;
 }
 
 static inline bool sev_guest(struct kvm *kvm)
 {
+#ifdef CONFIG_KVM_AMD_SEV
 	struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info;
 
 	return sev->active;
+#else
+	return false;
+#endif
 }
 
 static inline int sev_get_asid(struct kvm *kvm)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 06412ba46aa3..e665aa7167cf 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -121,7 +121,6 @@ module_param_named(pml, enable_pml, bool, S_IRUGO);
 
 #define MSR_BITMAP_MODE_X2APIC		1
 #define MSR_BITMAP_MODE_X2APIC_APICV	2
-#define MSR_BITMAP_MODE_LM		4
 
 #define KVM_VMX_TSC_MULTIPLIER_MAX     0xffffffffffffffffULL
 
@@ -857,6 +856,7 @@ struct nested_vmx {
 
 	/* to migrate it to L2 if VM_ENTRY_LOAD_DEBUG_CONTROLS is off */
 	u64 vmcs01_debugctl;
+	u64 vmcs01_guest_bndcfgs;
 
 	u16 vpid02;
 	u16 last_vpid;
@@ -1572,8 +1572,12 @@ static int vmx_hv_remote_flush_tlb(struct kvm *kvm)
 		goto out;
 	}
 
+	/*
+	 * FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE hypercall needs the address of the
+	 * base of EPT PML4 table, strip off EPT configuration information.
+	 */
 	ret = hyperv_flush_guest_mapping(
-			to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer);
+			to_vmx(kvm_get_vcpu(kvm, 0))->ept_pointer & PAGE_MASK);
 
 out:
 	spin_unlock(&to_kvm_vmx(kvm)->ept_pointer_lock);
@@ -2899,8 +2903,7 @@ static void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 		vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
 	}
 
-	if (is_long_mode(&vmx->vcpu))
-		wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+	wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #else
 	savesegment(fs, fs_sel);
 	savesegment(gs, gs_sel);
@@ -2951,8 +2954,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 	vmx->loaded_cpu_state = NULL;
 
 #ifdef CONFIG_X86_64
-	if (is_long_mode(&vmx->vcpu))
-		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+	rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
 #endif
 	if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
 		kvm_load_ldt(host_state->ldt_sel);
@@ -2980,24 +2982,19 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 #ifdef CONFIG_X86_64
 static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
 {
-	if (is_long_mode(&vmx->vcpu)) {
-		preempt_disable();
-		if (vmx->loaded_cpu_state)
-			rdmsrl(MSR_KERNEL_GS_BASE,
-			       vmx->msr_guest_kernel_gs_base);
-		preempt_enable();
-	}
+	preempt_disable();
+	if (vmx->loaded_cpu_state)
+		rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+	preempt_enable();
 	return vmx->msr_guest_kernel_gs_base;
 }
 
 static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
 {
-	if (is_long_mode(&vmx->vcpu)) {
-		preempt_disable();
-		if (vmx->loaded_cpu_state)
-			wrmsrl(MSR_KERNEL_GS_BASE, data);
-		preempt_enable();
-	}
+	preempt_disable();
+	if (vmx->loaded_cpu_state)
+		wrmsrl(MSR_KERNEL_GS_BASE, data);
+	preempt_enable();
 	vmx->msr_guest_kernel_gs_base = data;
 }
 #endif
@@ -3533,9 +3530,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
 		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
 
-	if (kvm_mpx_supported())
-		msrs->exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
-
 	/* We support free control of debug control saving. */
 	msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
 
@@ -3552,8 +3546,6 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		VM_ENTRY_LOAD_IA32_PAT;
 	msrs->entry_ctls_high |=
 		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
-	if (kvm_mpx_supported())
-		msrs->entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
 	/* We support free control of debug control loading. */
 	msrs->entry_ctls_low &= ~VM_ENTRY_LOAD_DEBUG_CONTROLS;
@@ -3601,12 +3593,12 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		msrs->secondary_ctls_high);
 	msrs->secondary_ctls_low = 0;
 	msrs->secondary_ctls_high &=
-		SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 		SECONDARY_EXEC_DESC |
 		SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
 		SECONDARY_EXEC_APIC_REGISTER_VIRT |
 		SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
 		SECONDARY_EXEC_WBINVD_EXITING;
+
 	/*
 	 * We can emulate "VMCS shadowing," even if the hardware
 	 * doesn't support it.
@@ -3663,6 +3655,10 @@ static void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, bool apicv)
 		msrs->secondary_ctls_high |=
 			SECONDARY_EXEC_UNRESTRICTED_GUEST;
 
+	if (flexpriority_enabled)
+		msrs->secondary_ctls_high |=
+			SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+
 	/* miscellaneous data */
 	rdmsr(MSR_IA32_VMX_MISC,
 		msrs->misc_low,
@@ -5073,19 +5069,6 @@ static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
 	if (!msr)
 		return;
 
-	/*
-	 * MSR_KERNEL_GS_BASE is not intercepted when the guest is in
-	 * 64-bit mode as a 64-bit kernel may frequently access the
-	 * MSR.  This means we need to manually save/restore the MSR
-	 * when switching between guest and host state, but only if
-	 * the guest is in 64-bit mode.  Sync our cached value if the
-	 * guest is transitioning to 32-bit mode and the CPU contains
-	 * guest state, i.e. the cache is stale.
-	 */
-#ifdef CONFIG_X86_64
-	if (!(efer & EFER_LMA))
-		(void)vmx_read_guest_kernel_gs_base(vmx);
-#endif
 	vcpu->arch.efer = efer;
 	if (efer & EFER_LMA) {
 		vm_entry_controls_setbit(to_vmx(vcpu), VM_ENTRY_IA32E_MODE);
@@ -6078,9 +6061,6 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
 			mode |= MSR_BITMAP_MODE_X2APIC_APICV;
 	}
 
-	if (is_long_mode(vcpu))
-		mode |= MSR_BITMAP_MODE_LM;
-
 	return mode;
 }
 
@@ -6121,9 +6101,6 @@ static void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
 	if (!changed)
 		return;
 
-	vmx_set_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW,
-				  !(mode & MSR_BITMAP_MODE_LM));
-
 	if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
 		vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
 
@@ -6189,6 +6166,11 @@ static void vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
 	nested_mark_vmcs12_pages_dirty(vcpu);
 }
 
+static u8 vmx_get_rvi(void)
+{
+	return vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+}
+
 static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -6201,7 +6183,7 @@ static bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
 		WARN_ON_ONCE(!vmx->nested.virtual_apic_page))
 		return false;
 
-	rvi = vmcs_read16(GUEST_INTR_STATUS) & 0xff;
+	rvi = vmx_get_rvi();
 
 	vapic_page = kmap(vmx->nested.virtual_apic_page);
 	vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
@@ -10245,15 +10227,16 @@ static void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 	if (!lapic_in_kernel(vcpu))
 		return;
 
+	if (!flexpriority_enabled &&
+	    !cpu_has_vmx_virtualize_x2apic_mode())
+		return;
+
 	/* Postpone execution until vmcs01 is the current VMCS. */
 	if (is_guest_mode(vcpu)) {
 		to_vmx(vcpu)->nested.change_vmcs01_virtual_apic_mode = true;
 		return;
 	}
 
-	if (!cpu_need_tpr_shadow(vcpu))
-		return;
-
 	sec_exec_control = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
 	sec_exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
 			      SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE);
@@ -10375,6 +10358,14 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
 	return max_irr;
 }
 
+static u8 vmx_has_apicv_interrupt(struct kvm_vcpu *vcpu)
+{
+	u8 rvi = vmx_get_rvi();
+	u8 vppr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_PROCPRI);
+
+	return ((rvi & 0xf0) > (vppr & 0xf0));
+}
+
 static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
 {
 	if (!kvm_vcpu_apicv_active(vcpu))
@@ -11264,6 +11255,23 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 #undef cr4_fixed1_update
 }
 
+static void nested_vmx_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	if (kvm_mpx_supported()) {
+		bool mpx_enabled = guest_cpuid_has(vcpu, X86_FEATURE_MPX);
+
+		if (mpx_enabled) {
+			vmx->nested.msrs.entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
+			vmx->nested.msrs.exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
+		} else {
+			vmx->nested.msrs.entry_ctls_high &= ~VM_ENTRY_LOAD_BNDCFGS;
+			vmx->nested.msrs.exit_ctls_high &= ~VM_EXIT_CLEAR_BNDCFGS;
+		}
+	}
+}
+
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -11280,8 +11288,10 @@ static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 		to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
 			~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
 
-	if (nested_vmx_allowed(vcpu))
+	if (nested_vmx_allowed(vcpu)) {
 		nested_vmx_cr_fixed1_bits_update(vcpu);
+		nested_vmx_entry_exit_ctls_update(vcpu);
+	}
 }
 
 static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
@@ -12049,8 +12059,13 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 
 	set_cr4_guest_host_mask(vmx);
 
-	if (vmx_mpx_supported())
-		vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+	if (kvm_mpx_supported()) {
+		if (vmx->nested.nested_run_pending &&
+			(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+			vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+		else
+			vmcs_write64(GUEST_BNDCFGS, vmx->nested.vmcs01_guest_bndcfgs);
+	}
 
 	if (enable_vpid) {
 		if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
@@ -12595,15 +12610,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	bool from_vmentry = !!exit_qual;
 	u32 dummy_exit_qual;
-	u32 vmcs01_cpu_exec_ctrl;
+	bool evaluate_pending_interrupts;
 	int r = 0;
 
-	vmcs01_cpu_exec_ctrl = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+	evaluate_pending_interrupts = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL) &
+		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
+	if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
+		evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
 
 	enter_guest_mode(vcpu);
 
 	if (!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
 		vmx->nested.vmcs01_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+	if (kvm_mpx_supported() &&
+		!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS))
+		vmx->nested.vmcs01_guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
 
 	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
 	vmx_segment_cache_clear(vmx);
@@ -12643,16 +12664,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, u32 *exit_qual)
 	 * to L1 or delivered directly to L2 (e.g. In case L1 don't
 	 * intercept EXTERNAL_INTERRUPT).
 	 *
-	 * Usually this would be handled by L0 requesting a
-	 * IRQ/NMI window by setting VMCS accordingly. However,
-	 * this setting was done on VMCS01 and now VMCS02 is active
-	 * instead. Thus, we force L0 to perform pending event
-	 * evaluation by requesting a KVM_REQ_EVENT.
-	 */
-	if (vmcs01_cpu_exec_ctrl &
-		(CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING)) {
+	 * Usually this would be handled by the processor noticing an
+	 * IRQ/NMI window request, or checking RVI during evaluation of
+	 * pending virtual interrupts.  However, this setting was done
+	 * on VMCS01 and now VMCS02 is active instead. Thus, we force L0
+	 * to perform pending event evaluation by requesting a KVM_REQ_EVENT.
+	 */
+	if (unlikely(evaluate_pending_interrupts))
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
-	}
 
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index edbf00ec56b3..ca717737347e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4698,7 +4698,7 @@ static void kvm_init_msr_list(void)
 		 */
 		switch (msrs_to_save[i]) {
 		case MSR_IA32_BNDCFGS:
-			if (!kvm_x86_ops->mpx_supported())
+			if (!kvm_mpx_supported())
 				continue;
 			break;
 		case MSR_TSC_AUX:
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 089e78c4effd..59274e2c1ac4 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -115,6 +115,8 @@ static inline void pgd_list_del(pgd_t *pgd)
 
 #define UNSHARED_PTRS_PER_PGD				\
 	(SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
+#define MAX_UNSHARED_PTRS_PER_PGD			\
+	max_t(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
 
 
 static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
@@ -181,6 +183,7 @@ static void pgd_dtor(pgd_t *pgd)
  * and initialize the kernel pmds here.
  */
 #define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD
+#define MAX_PREALLOCATED_PMDS	MAX_UNSHARED_PTRS_PER_PGD
 
 /*
  * We allocate separate PMDs for the kernel part of the user page-table
@@ -189,6 +192,7 @@ static void pgd_dtor(pgd_t *pgd)
  */
 #define PREALLOCATED_USER_PMDS	 (static_cpu_has(X86_FEATURE_PTI) ? \
 					KERNEL_PGD_PTRS : 0)
+#define MAX_PREALLOCATED_USER_PMDS KERNEL_PGD_PTRS
 
 void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 {
@@ -210,7 +214,9 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 
 /* No need to prepopulate any pagetable entries in non-PAE modes. */
 #define PREALLOCATED_PMDS	0
+#define MAX_PREALLOCATED_PMDS	0
 #define PREALLOCATED_USER_PMDS	 0
+#define MAX_PREALLOCATED_USER_PMDS 0
 #endif	/* CONFIG_X86_PAE */
 
 static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
@@ -428,8 +434,8 @@ static inline void _pgd_free(pgd_t *pgd)
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
-	pmd_t *u_pmds[PREALLOCATED_USER_PMDS];
-	pmd_t *pmds[PREALLOCATED_PMDS];
+	pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
+	pmd_t *pmds[MAX_PREALLOCATED_PMDS];
 
 	pgd = _pgd_alloc();