Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

82 files changed, 699 insertions, 884 deletions

diff --git a/arch/arm/boot/dts/am3517-evm.dts b/arch/arm/boot/dts/am3517-evm.dts
index ebfe28c2f544..a1fd3e63e86e 100644
--- a/arch/arm/boot/dts/am3517-evm.dts
+++ b/arch/arm/boot/dts/am3517-evm.dts
@@ -124,10 +124,11 @@
 	};
 
 	lcd0: display@0 {
-		compatible = "panel-dpi";
+		/* This isn't the exact LCD, but the timings meet spec */
+		/* To make it work, set CONFIG_OMAP2_DSS_MIN_FCK_PER_PCK=4 */
+		compatible = "newhaven,nhd-4.3-480272ef-atxl";
 		label = "15";
-		status = "okay";
-		pinctrl-names = "default";
+		backlight = <&bl>;
 		enable-gpios = <&gpio6 16 GPIO_ACTIVE_HIGH>;	/* gpio176, lcd INI */
 		vcc-supply = <&vdd_io_reg>;
 
@@ -136,22 +137,6 @@
 				remote-endpoint = <&dpi_out>;
 			};
 		};
-
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <3>;
-			hback-porch = <2>;
-			hsync-len = <42>;
-			vback-porch = <3>;
-			vfront-porch = <4>;
-			vsync-len = <11>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
 	};
 
 	bl: backlight {
diff --git a/arch/arm/boot/dts/logicpd-som-lv.dtsi b/arch/arm/boot/dts/logicpd-som-lv.dtsi
index 5563ee54c960..b56524cc7fe2 100644
--- a/arch/arm/boot/dts/logicpd-som-lv.dtsi
+++ b/arch/arm/boot/dts/logicpd-som-lv.dtsi
@@ -228,6 +228,20 @@
 		>;
 	};
 
+	i2c2_pins: pinmux_i2c2_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT | MUX_MODE0)	/* i2c2_scl */
+			OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT | MUX_MODE0)	/* i2c2_sda */
+		>;
+	};
+
+	i2c3_pins: pinmux_i2c3_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT | MUX_MODE0)	/* i2c3_scl */
+			OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT | MUX_MODE0)	/* i2c3_sda */
+		>;
+	};
+
 	tsc2004_pins: pinmux_tsc2004_pins {
 		pinctrl-single,pins = <
 			OMAP3_CORE1_IOPAD(0x2186, PIN_INPUT | MUX_MODE4)	/* mcbsp4_dr.gpio_153 */
@@ -249,18 +263,6 @@
 			OMAP3_WKUP_IOPAD(0x2a0c, PIN_OUTPUT | MUX_MODE4)	/* sys_boot1.gpio_3 */
 		>;
 	};
-	i2c2_pins: pinmux_i2c2_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x21be, PIN_INPUT | MUX_MODE0)	/* i2c2_scl */
-			OMAP3_CORE1_IOPAD(0x21c0, PIN_INPUT | MUX_MODE0)	/* i2c2_sda */
-		>;
-	};
-	i2c3_pins: pinmux_i2c3_pins {
-		pinctrl-single,pins = <
-			OMAP3_CORE1_IOPAD(0x21c2, PIN_INPUT | MUX_MODE0)	/* i2c3_scl */
-			OMAP3_CORE1_IOPAD(0x21c4, PIN_INPUT | MUX_MODE0)	/* i2c3_sda */
-		>;
-	};
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
index 642e809e757a..449cc7616da6 100644
--- a/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
+++ b/arch/arm/boot/dts/logicpd-torpedo-baseboard.dtsi
@@ -108,7 +108,6 @@
 &dss {
 	status = "ok";
 	vdds_dsi-supply = <&vpll2>;
-	vdda_video-supply = <&video_reg>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&dss_dpi_pins1>;
 	port {
@@ -124,44 +123,20 @@
 		display0 = &lcd0;
 	};
 
-	video_reg: video_reg {
-		pinctrl-names = "default";
-		pinctrl-0 = <&panel_pwr_pins>;
-		compatible = "regulator-fixed";
-		regulator-name = "fixed-supply";
-		regulator-min-microvolt = <3300000>;
-		regulator-max-microvolt = <3300000>;
-		gpio = <&gpio5 27 GPIO_ACTIVE_HIGH>;	/* gpio155, lcd INI */
-	};
-
 	lcd0: display {
-		compatible = "panel-dpi";
+		/* This isn't the exact LCD, but the timings meet spec */
+		/* To make it work, set CONFIG_OMAP2_DSS_MIN_FCK_PER_PCK=4 */
+		compatible = "newhaven,nhd-4.3-480272ef-atxl";
 		label = "15";
-		status = "okay";
-		/* default-on; */
 		pinctrl-names = "default";
-
+		pinctrl-0 = <&panel_pwr_pins>;
+		backlight = <&bl>;
+		enable-gpios = <&gpio5 27 GPIO_ACTIVE_HIGH>;
 		port {
 			lcd_in: endpoint {
 				remote-endpoint = <&dpi_out>;
 			};
 		};
-
-		panel-timing {
-			clock-frequency = <9000000>;
-			hactive = <480>;
-			vactive = <272>;
-			hfront-porch = <3>;
-			hback-porch = <2>;
-			hsync-len = <42>;
-			vback-porch = <3>;
-			vfront-porch = <4>;
-			vsync-len = <11>;
-			hsync-active = <0>;
-			vsync-active = <0>;
-			de-active = <1>;
-			pixelclk-active = <1>;
-		};
 	};
 
 	bl: backlight {
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index c7bf9c493646..64eb896907bf 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -363,6 +363,7 @@ CONFIG_DRM_OMAP_PANEL_TPO_TD028TTEC1=m
 CONFIG_DRM_OMAP_PANEL_TPO_TD043MTEA1=m
 CONFIG_DRM_OMAP_PANEL_NEC_NL8048HL11=m
 CONFIG_DRM_TILCDC=m
+CONFIG_DRM_PANEL_SIMPLE=m
 CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_MODE_HELPERS=y
diff --git a/arch/arm/include/asm/xen/xen-ops.h b/arch/arm/include/asm/xen/xen-ops.h
deleted file mode 100644
index ec154e719b11..000000000000
--- a/arch/arm/include/asm/xen/xen-ops.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_XEN_OPS_H
-#define _ASM_XEN_OPS_H
-
-void xen_efi_runtime_setup(void);
-
-#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm/mach-aspeed/Kconfig b/arch/arm/mach-aspeed/Kconfig
index 56007b0b6120..e8d6e9957d65 100644
--- a/arch/arm/mach-aspeed/Kconfig
+++ b/arch/arm/mach-aspeed/Kconfig
@@ -26,7 +26,6 @@ config MACH_ASPEED_G4
 config MACH_ASPEED_G5
 	bool "Aspeed SoC 5th Generation"
 	depends on ARCH_MULTI_V6
-	select CPU_V6
 	select PINCTRL_ASPEED_G5
 	select FTTMR010_TIMER
 	help
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 6c6f8fce854e..d942a3357090 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -491,11 +491,11 @@ static int ti_sysc_clkdm_init(struct device *dev,
 			      struct clk *fck, struct clk *ick,
 			      struct ti_sysc_cookie *cookie)
 {
-	if (fck)
+	if (!IS_ERR(fck))
 		cookie->clkdm = ti_sysc_find_one_clockdomain(fck);
 	if (cookie->clkdm)
 		return 0;
-	if (ick)
+	if (!IS_ERR(ick))
 		cookie->clkdm = ti_sysc_find_one_clockdomain(ick);
 	if (cookie->clkdm)
 		return 0;
diff --git a/arch/arm/xen/Makefile b/arch/arm/xen/Makefile
index 7ed28982c4c3..c32d04713ba0 100644
--- a/arch/arm/xen/Makefile
+++ b/arch/arm/xen/Makefile
@@ -1,3 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y		:= enlighten.o hypercall.o grant-table.o p2m.o mm.o
-obj-$(CONFIG_XEN_EFI) += efi.o
diff --git a/arch/arm/xen/efi.c b/arch/arm/xen/efi.c
deleted file mode 100644
index d687a73044bf..000000000000
--- a/arch/arm/xen/efi.c
+++ /dev/null
@@ -1,28 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (c) 2015, Linaro Limited, Shannon Zhao
- */
-
-#include <linux/efi.h>
-#include <xen/xen-ops.h>
-#include <asm/xen/xen-ops.h>
-
-/* Set XEN EFI runtime services function pointers. Other fields of struct efi,
- * e.g. efi.systab, will be set like normal EFI.
- */
-void __init xen_efi_runtime_setup(void)
-{
-	efi.get_time                 = xen_efi_get_time;
-	efi.set_time                 = xen_efi_set_time;
-	efi.get_wakeup_time          = xen_efi_get_wakeup_time;
-	efi.set_wakeup_time          = xen_efi_set_wakeup_time;
-	efi.get_variable             = xen_efi_get_variable;
-	efi.get_next_variable        = xen_efi_get_next_variable;
-	efi.set_variable             = xen_efi_set_variable;
-	efi.query_variable_info      = xen_efi_query_variable_info;
-	efi.update_capsule           = xen_efi_update_capsule;
-	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
-	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
-	efi.reset_system             = xen_efi_reset_system;
-}
-EXPORT_SYMBOL_GPL(xen_efi_runtime_setup);
diff --git a/arch/arm/xen/enlighten.c b/arch/arm/xen/enlighten.c
index 1e57692552d9..dd6804a64f1a 100644
--- a/arch/arm/xen/enlighten.c
+++ b/arch/arm/xen/enlighten.c
@@ -15,7 +15,6 @@
 #include <xen/xen-ops.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
-#include <asm/xen/xen-ops.h>
 #include <asm/system_misc.h>
 #include <asm/efi.h>
 #include <linux/interrupt.h>
@@ -437,7 +436,7 @@ EXPORT_SYMBOL_GPL(HYPERVISOR_memory_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_physdev_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vcpu_op);
 EXPORT_SYMBOL_GPL(HYPERVISOR_tmem_op);
-EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op);
+EXPORT_SYMBOL_GPL(HYPERVISOR_platform_op_raw);
 EXPORT_SYMBOL_GPL(HYPERVISOR_multicall);
 EXPORT_SYMBOL_GPL(HYPERVISOR_vm_assist);
 EXPORT_SYMBOL_GPL(HYPERVISOR_dm_op);
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index 2b2c208408bb..38fa917c8585 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -28,7 +28,10 @@ unsigned long xen_get_swiotlb_free_pages(unsigned int order)
 
 	for_each_memblock(memory, reg) {
 		if (reg->base < (phys_addr_t)0xffffffff) {
-			flags |= __GFP_DMA;
+			if (IS_ENABLED(CONFIG_ZONE_DMA32))
+				flags |= __GFP_DMA32;
+			else
+				flags |= __GFP_DMA;
 			break;
 		}
 	}
diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index 86825aa20852..97f21cc66657 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -47,30 +47,6 @@
 #define read_sysreg_el2(r)	read_sysreg_elx(r, _EL2, _EL1)
 #define write_sysreg_el2(v,r)	write_sysreg_elx(v, r, _EL2, _EL1)
 
-/**
- * hyp_alternate_select - Generates patchable code sequences that are
- * used to switch between two implementations of a function, depending
- * on the availability of a feature.
- *
- * @fname: a symbol name that will be defined as a function returning a
- * function pointer whose type will match @orig and @alt
- * @orig: A pointer to the default function, as returned by @fname when
- * @cond doesn't hold
- * @alt: A pointer to the alternate function, as returned by @fname
- * when @cond holds
- * @cond: a CPU feature (as described in asm/cpufeature.h)
- */
-#define hyp_alternate_select(fname, orig, alt, cond)			\
-typeof(orig) * __hyp_text fname(void)					\
-{									\
-	typeof(alt) *val = orig;					\
-	asm volatile(ALTERNATIVE("nop		\n",			\
-				 "mov	%0, %1	\n",			\
-				 cond)					\
-		     : "+r" (val) : "r" (alt));				\
-	return val;							\
-}
-
 int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu);
 
 void __vgic_v3_save_state(struct kvm_vcpu *vcpu);
diff --git a/arch/arm64/include/asm/xen/xen-ops.h b/arch/arm64/include/asm/xen/xen-ops.h
deleted file mode 100644
index e6e784051932..000000000000
--- a/arch/arm64/include/asm/xen/xen-ops.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_XEN_OPS_H
-#define _ASM_XEN_OPS_H
-
-void xen_efi_runtime_setup(void);
-
-#endif /* _ASM_XEN_OPS_H */
diff --git a/arch/arm64/kvm/hyp/switch.c b/arch/arm64/kvm/hyp/switch.c
index bd978ad71936..3d3815020e36 100644
--- a/arch/arm64/kvm/hyp/switch.c
+++ b/arch/arm64/kvm/hyp/switch.c
@@ -229,20 +229,6 @@ static void __hyp_text __hyp_vgic_restore_state(struct kvm_vcpu *vcpu)
 	}
 }
 
-static bool __hyp_text __true_value(void)
-{
-	return true;
-}
-
-static bool __hyp_text __false_value(void)
-{
-	return false;
-}
-
-static hyp_alternate_select(__check_arm_834220,
-			    __false_value, __true_value,
-			    ARM64_WORKAROUND_834220);
-
 static bool __hyp_text __translate_far_to_hpfar(u64 far, u64 *hpfar)
 {
 	u64 par, tmp;
@@ -298,7 +284,8 @@ static bool __hyp_text __populate_fault_info(struct kvm_vcpu *vcpu)
 	 * resolve the IPA using the AT instruction.
 	 */
 	if (!(esr & ESR_ELx_S1PTW) &&
-	    (__check_arm_834220()() || (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
+	    (cpus_have_const_cap(ARM64_WORKAROUND_834220) ||
+	     (esr & ESR_ELx_FSC_TYPE) == FSC_PERM)) {
 		if (!__translate_far_to_hpfar(far, &hpfar))
 			return false;
 	} else {
diff --git a/arch/arm64/kvm/hyp/tlb.c b/arch/arm64/kvm/hyp/tlb.c
index c466060b76d6..eb0efc5557f3 100644
--- a/arch/arm64/kvm/hyp/tlb.c
+++ b/arch/arm64/kvm/hyp/tlb.c
@@ -67,10 +67,14 @@ static void __hyp_text __tlb_switch_to_guest_nvhe(struct kvm *kvm,
 	isb();
 }
 
-static hyp_alternate_select(__tlb_switch_to_guest,
-			    __tlb_switch_to_guest_nvhe,
-			    __tlb_switch_to_guest_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
+static void __hyp_text __tlb_switch_to_guest(struct kvm *kvm,
+					     struct tlb_inv_context *cxt)
+{
+	if (has_vhe())
+		__tlb_switch_to_guest_vhe(kvm, cxt);
+	else
+		__tlb_switch_to_guest_nvhe(kvm, cxt);
+}
 
 static void __hyp_text __tlb_switch_to_host_vhe(struct kvm *kvm,
 						struct tlb_inv_context *cxt)
@@ -98,10 +102,14 @@ static void __hyp_text __tlb_switch_to_host_nvhe(struct kvm *kvm,
 	write_sysreg(0, vttbr_el2);
 }
 
-static hyp_alternate_select(__tlb_switch_to_host,
-			    __tlb_switch_to_host_nvhe,
-			    __tlb_switch_to_host_vhe,
-			    ARM64_HAS_VIRT_HOST_EXTN);
+static void __hyp_text __tlb_switch_to_host(struct kvm *kvm,
+					    struct tlb_inv_context *cxt)
+{
+	if (has_vhe())
+		__tlb_switch_to_host_vhe(kvm, cxt);
+	else
+		__tlb_switch_to_host_nvhe(kvm, cxt);
+}
 
 void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 {
@@ -111,7 +119,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest()(kvm, &cxt);
+	__tlb_switch_to_guest(kvm, &cxt);
 
 	/*
 	 * We could do so much better if we had the VA as well.
@@ -154,7 +162,7 @@ void __hyp_text __kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
 	if (!has_vhe() && icache_is_vpipt())
 		__flush_icache_all();
 
-	__tlb_switch_to_host()(kvm, &cxt);
+	__tlb_switch_to_host(kvm, &cxt);
 }
 
 void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
@@ -165,13 +173,13 @@ void __hyp_text __kvm_tlb_flush_vmid(struct kvm *kvm)
 
 	/* Switch to requested VMID */
 	kvm = kern_hyp_va(kvm);
-	__tlb_switch_to_guest()(kvm, &cxt);
+	__tlb_switch_to_guest(kvm, &cxt);
 
 	__tlbi(vmalls12e1is);
 	dsb(ish);
 	isb();
 
-	__tlb_switch_to_host()(kvm, &cxt);
+	__tlb_switch_to_host(kvm, &cxt);
 }
 
 void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
@@ -180,13 +188,13 @@ void __hyp_text __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu)
 	struct tlb_inv_context cxt;
 
 	/* Switch to requested VMID */
-	__tlb_switch_to_guest()(kvm, &cxt);
+	__tlb_switch_to_guest(kvm, &cxt);
 
 	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 
-	__tlb_switch_to_host()(kvm, &cxt);
+	__tlb_switch_to_host(kvm, &cxt);
 }
 
 void __hyp_text __kvm_flush_vm_context(void)
diff --git a/arch/arm64/xen/Makefile b/arch/arm64/xen/Makefile
index a4fc65f3928d..b66215e8658e 100644
--- a/arch/arm64/xen/Makefile
+++ b/arch/arm64/xen/Makefile
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 xen-arm-y	+= $(addprefix ../../arm/xen/, enlighten.o grant-table.o p2m.o mm.o)
 obj-y		:= xen-arm.o hypercall.o
-obj-$(CONFIG_XEN_EFI) += $(addprefix ../../arm/xen/, efi.o)
diff --git a/arch/csky/abiv1/alignment.c b/arch/csky/abiv1/alignment.c
index 27ef5b2c43ab..cb2a0d94a144 100644
--- a/arch/csky/abiv1/alignment.c
+++ b/arch/csky/abiv1/alignment.c
@@ -5,8 +5,10 @@
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
 
-static int align_enable = 1;
-static int align_count;
+static int align_kern_enable = 1;
+static int align_usr_enable = 1;
+static int align_kern_count = 0;
+static int align_usr_count = 0;
 
 static inline uint32_t get_ptreg(struct pt_regs *regs, uint32_t rx)
 {
@@ -32,9 +34,6 @@ static int ldb_asm(uint32_t addr, uint32_t *valp)
 	uint32_t val;
 	int err;
 
-	if (!access_ok((void *)addr, 1))
-		return 1;
-
 	asm volatile (
 		"movi	%0, 0\n"
 		"1:\n"
@@ -67,9 +66,6 @@ static int stb_asm(uint32_t addr, uint32_t val)
 {
 	int err;
 
-	if (!access_ok((void *)addr, 1))
-		return 1;
-
 	asm volatile (
 		"movi	%0, 0\n"
 		"1:\n"
@@ -203,8 +199,6 @@ static int stw_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
 	if (stb_asm(addr, byte3))
 		return 1;
 
-	align_count++;
-
 	return 0;
 }
 
@@ -226,7 +220,14 @@ void csky_alignment(struct pt_regs *regs)
 	uint32_t addr   = 0;
 
 	if (!user_mode(regs))
+		goto kernel_area;
+
+	if (!align_usr_enable) {
+		pr_err("%s user disabled.\n", __func__);
 		goto bad_area;
+	}
+
+	align_usr_count++;
 
 	ret = get_user(tmp, (uint16_t *)instruction_pointer(regs));
 	if (ret) {
@@ -234,6 +235,19 @@ void csky_alignment(struct pt_regs *regs)
 		goto bad_area;
 	}
 
+	goto good_area;
+
+kernel_area:
+	if (!align_kern_enable) {
+		pr_err("%s kernel disabled.\n", __func__);
+		goto bad_area;
+	}
+
+	align_kern_count++;
+
+	tmp = *(uint16_t *)instruction_pointer(regs);
+
+good_area:
 	opcode = (uint32_t)tmp;
 
 	rx  = opcode & 0xf;
@@ -286,18 +300,32 @@ bad_area:
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
 }
 
-static struct ctl_table alignment_tbl[4] = {
+static struct ctl_table alignment_tbl[5] = {
+	{
+		.procname = "kernel_enable",
+		.data = &align_kern_enable,
+		.maxlen = sizeof(align_kern_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "user_enable",
+		.data = &align_usr_enable,
+		.maxlen = sizeof(align_usr_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
 	{
-		.procname = "enable",
-		.data = &align_enable,
-		.maxlen = sizeof(align_enable),
+		.procname = "kernel_count",
+		.data = &align_kern_count,
+		.maxlen = sizeof(align_kern_count),
 		.mode = 0666,
 		.proc_handler = &proc_dointvec
 	},
 	{
-		.procname = "count",
-		.data = &align_count,
-		.maxlen = sizeof(align_count),
+		.procname = "user_count",
+		.data = &align_usr_count,
+		.maxlen = sizeof(align_usr_count),
 		.mode = 0666,
 		.proc_handler = &proc_dointvec
 	},
diff --git a/arch/csky/abiv1/cacheflush.c b/arch/csky/abiv1/cacheflush.c
index 10af8b6fe322..9f1fe80cc847 100644
--- a/arch/csky/abiv1/cacheflush.c
+++ b/arch/csky/abiv1/cacheflush.c
@@ -11,42 +11,66 @@
 #include <asm/cacheflush.h>
 #include <asm/cachectl.h>
 
+#define PG_dcache_clean		PG_arch_1
+
 void flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
-	unsigned long addr;
+	struct address_space *mapping;
 
-	if (mapping && !mapping_mapped(mapping)) {
-		set_bit(PG_arch_1, &(page)->flags);
+	if (page == ZERO_PAGE(0))
 		return;
-	}
 
-	/*
-	 * We could delay the flush for the !page_mapping case too.  But that
-	 * case is for exec env/arg pages and those are %99 certainly going to
-	 * get faulted into the tlb (and thus flushed) anyways.
-	 */
-	addr = (unsigned long) page_address(page);
-	dcache_wb_range(addr, addr + PAGE_SIZE);
+	mapping = page_mapping_file(page);
+
+	if (mapping && !page_mapcount(page))
+		clear_bit(PG_dcache_clean, &page->flags);
+	else {
+		dcache_wbinv_all();
+		if (mapping)
+			icache_inv_all();
+		set_bit(PG_dcache_clean, &page->flags);
+	}
 }
+EXPORT_SYMBOL(flush_dcache_page);
 
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
-		      pte_t *pte)
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
+	pte_t *ptep)
 {
-	unsigned long addr;
+	unsigned long pfn = pte_pfn(*ptep);
 	struct page *page;
-	unsigned long pfn;
 
-	pfn = pte_pfn(*pte);
-	if (unlikely(!pfn_valid(pfn)))
+	if (!pfn_valid(pfn))
 		return;
 
 	page = pfn_to_page(pfn);
-	addr = (unsigned long) page_address(page);
+	if (page == ZERO_PAGE(0))
+		return;
+
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		dcache_wbinv_all();
 
-	if (vma->vm_flags & VM_EXEC ||
-	    pages_do_alias(addr, address & PAGE_MASK))
-		cache_wbinv_all();
+	if (page_mapping_file(page)) {
+		if (vma->vm_flags & VM_EXEC)
+			icache_inv_all();
+	}
+}
+
+void flush_kernel_dcache_page(struct page *page)
+{
+	struct address_space *mapping;
+
+	mapping = page_mapping_file(page);
+
+	if (!mapping || mapping_mapped(mapping))
+		dcache_wbinv_all();
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
+	unsigned long end)
+{
+	dcache_wbinv_all();
 
-	clear_bit(PG_arch_1, &(page)->flags);
+	if (vma->vm_flags & VM_EXEC)
+		icache_inv_all();
 }
diff --git a/arch/csky/abiv1/inc/abi/cacheflush.h b/arch/csky/abiv1/inc/abi/cacheflush.h
index 5f663aef9b1b..79ef9e8c1afd 100644
--- a/arch/csky/abiv1/inc/abi/cacheflush.h
+++ b/arch/csky/abiv1/inc/abi/cacheflush.h
@@ -4,46 +4,63 @@
 #ifndef __ABI_CSKY_CACHEFLUSH_H
 #define __ABI_CSKY_CACHEFLUSH_H
 
-#include <linux/compiler.h>
+#include <linux/mm.h>
 #include <asm/string.h>
 #include <asm/cache.h>
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
-#define flush_cache_mm(mm)			cache_wbinv_all()
+#define flush_cache_mm(mm)			dcache_wbinv_all()
 #define flush_cache_page(vma, page, pfn)	cache_wbinv_all()
 #define flush_cache_dup_mm(mm)			cache_wbinv_all()
 
+#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+extern void flush_kernel_dcache_page(struct page *);
+
+#define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
+#define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
+
+static inline void flush_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+static inline void invalidate_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+
+#define ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma,
+			 struct page *page, unsigned long vmaddr)
+{
+	if (PageAnon(page))
+		cache_wbinv_all();
+}
+
 /*
  * if (current_mm != vma->mm) cache_wbinv_range(start, end) will be broken.
  * Use cache_wbinv_all() here and need to be improved in future.
  */
-#define flush_cache_range(vma, start, end)	cache_wbinv_all()
-#define flush_cache_vmap(start, end)		cache_wbinv_range(start, end)
-#define flush_cache_vunmap(start, end)		cache_wbinv_range(start, end)
+extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+#define flush_cache_vmap(start, end)		cache_wbinv_all()
+#define flush_cache_vunmap(start, end)		cache_wbinv_all()
 
-#define flush_icache_page(vma, page)		cache_wbinv_all()
+#define flush_icache_page(vma, page)		do {} while (0);
 #define flush_icache_range(start, end)		cache_wbinv_range(start, end)
 
-#define flush_icache_user_range(vma, pg, adr, len) \
-				cache_wbinv_range(adr, adr + len)
+#define flush_icache_user_range(vma,page,addr,len) \
+	flush_dcache_page(page)
 
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 do { \
-	cache_wbinv_all(); \
 	memcpy(dst, src, len); \
-	cache_wbinv_all(); \
 } while (0)
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 do { \
-	cache_wbinv_all(); \
 	memcpy(dst, src, len); \
 	cache_wbinv_all(); \
 } while (0)
 
-#define flush_dcache_mmap_lock(mapping)		do {} while (0)
-#define flush_dcache_mmap_unlock(mapping)	do {} while (0)
-
 #endif /* __ABI_CSKY_CACHEFLUSH_H */
diff --git a/arch/csky/abiv1/inc/abi/page.h b/arch/csky/abiv1/inc/abi/page.h
index 6336e92a103a..c864519117c7 100644
--- a/arch/csky/abiv1/inc/abi/page.h
+++ b/arch/csky/abiv1/inc/abi/page.h
@@ -1,13 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
-extern unsigned long shm_align_mask;
+#include <asm/shmparam.h>
+
 extern void flush_dcache_page(struct page *page);
 
 static inline unsigned long pages_do_alias(unsigned long addr1,
 					   unsigned long addr2)
 {
-	return (addr1 ^ addr2) & shm_align_mask;
+	return (addr1 ^ addr2) & (SHMLBA-1);
 }
 
 static inline void clear_user_page(void *addr, unsigned long vaddr,
diff --git a/arch/csky/abiv1/mmap.c b/arch/csky/abiv1/mmap.c
index b462fd50b23a..6792aca49999 100644
--- a/arch/csky/abiv1/mmap.c
+++ b/arch/csky/abiv1/mmap.c
@@ -9,58 +9,63 @@
 #include <linux/random.h>
 #include <linux/io.h>
 
-unsigned long shm_align_mask = (0x4000 >> 1) - 1;   /* Sane caches */
+#define COLOUR_ALIGN(addr,pgoff)		\
+	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
+	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
 
-#define COLOUR_ALIGN(addr, pgoff) \
-	((((addr) + shm_align_mask) & ~shm_align_mask) + \
-	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
-
-unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
+/*
+ * We need to ensure that shared mappings are correctly aligned to
+ * avoid aliasing issues with VIPT caches.  We need to ensure that
+ * a specific page of an object is always mapped at a multiple of
+ * SHMLBA bytes.
+ *
+ * We unconditionally provide this function for all cases.
+ */
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
-	struct vm_area_struct *vmm;
-	int do_color_align;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	int do_align = 0;
+	struct vm_unmapped_area_info info;
+
+	/*
+	 * We only need to do colour alignment if either the I or D
+	 * caches alias.
+	 */
+	do_align = filp || (flags & MAP_SHARED);
 
+	/*
+	 * We enforce the MAP_FIXED case.
+	 */
 	if (flags & MAP_FIXED) {
-		/*
-		 * We do not accept a shared mapping if it would violate
-		 * cache aliasing constraints.
-		 */
-		if ((flags & MAP_SHARED) &&
-			((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
+		if (flags & MAP_SHARED &&
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
 			return -EINVAL;
 		return addr;
 	}
 
 	if (len > TASK_SIZE)
 		return -ENOMEM;
-	do_color_align = 0;
-	if (filp || (flags & MAP_SHARED))
-		do_color_align = 1;
+
 	if (addr) {
-		if (do_color_align)
+		if (do_align)
 			addr = COLOUR_ALIGN(addr, pgoff);
 		else
 			addr = PAGE_ALIGN(addr);
-		vmm = find_vma(current->mm, addr);
+
+		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-				(!vmm || addr + len <= vmm->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
-	addr = TASK_UNMAPPED_BASE;
-	if (do_color_align)
-		addr = COLOUR_ALIGN(addr, pgoff);
-	else
-		addr = PAGE_ALIGN(addr);
 
-	for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
-		/* At this point: (!vmm || addr < vmm->vm_end). */
-		if (TASK_SIZE - len < addr)
-			return -ENOMEM;
-		if (!vmm || addr + len <= vmm->vm_start)
-			return addr;
-		addr = vmm->vm_end;
-		if (do_color_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
-	}
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = mm->mmap_base;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_offset = pgoff << PAGE_SHIFT;
+	return vm_unmapped_area(&info);
 }
diff --git a/arch/csky/include/asm/barrier.h b/arch/csky/include/asm/barrier.h
index 476eb786f22d..a430e7fddf35 100644
--- a/arch/csky/include/asm/barrier.h
+++ b/arch/csky/include/asm/barrier.h
@@ -9,11 +9,12 @@
 #define nop()	asm volatile ("nop\n":::"memory")
 
 /*
- * sync:        completion barrier
- * sync.s:      completion barrier and shareable to other cores
- * sync.i:      completion barrier with flush cpu pipeline
- * sync.is:     completion barrier with flush cpu pipeline and shareable to
- *		other cores
+ * sync:        completion barrier, all sync.xx instructions
+ *              guarantee the last response recieved by bus transaction
+ *              made by ld/st instructions before sync.s
+ * sync.s:      inherit from sync, but also shareable to other cores
+ * sync.i:      inherit from sync, but also flush cpu pipeline
+ * sync.is:     the same with sync.i + sync.s
  *
  * bar.brwarw:  ordering barrier for all load/store instructions before it
  * bar.brwarws: ordering barrier for all load/store instructions before it
@@ -27,9 +28,7 @@
  */
 
 #ifdef CONFIG_CPU_HAS_CACHEV2
-#define mb()		asm volatile ("bar.brwarw\n":::"memory")
-#define rmb()		asm volatile ("bar.brar\n":::"memory")
-#define wmb()		asm volatile ("bar.bwaw\n":::"memory")
+#define mb()		asm volatile ("sync.s\n":::"memory")
 
 #ifdef CONFIG_SMP
 #define __smp_mb()	asm volatile ("bar.brwarws\n":::"memory")
diff --git a/arch/csky/include/asm/cache.h b/arch/csky/include/asm/cache.h
index d68373463676..1d5fc2f78fd7 100644
--- a/arch/csky/include/asm/cache.h
+++ b/arch/csky/include/asm/cache.h
@@ -24,6 +24,7 @@ void cache_wbinv_range(unsigned long start, unsigned long end);
 void cache_wbinv_all(void);
 
 void dma_wbinv_range(unsigned long start, unsigned long end);
+void dma_inv_range(unsigned long start, unsigned long end);
 void dma_wb_range(unsigned long start, unsigned long end);
 
 #endif
diff --git a/arch/csky/include/asm/io.h b/arch/csky/include/asm/io.h
index c1dfa9c10e36..80d071e2567f 100644
--- a/arch/csky/include/asm/io.h
+++ b/arch/csky/include/asm/io.h
@@ -4,17 +4,10 @@
 #ifndef __ASM_CSKY_IO_H
 #define __ASM_CSKY_IO_H
 
-#include <abi/pgtable-bits.h>
+#include <asm/pgtable.h>
 #include <linux/types.h>
 #include <linux/version.h>
 
-extern void __iomem *ioremap(phys_addr_t offset, size_t size);
-
-extern void iounmap(void *addr);
-
-extern int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
-		size_t size, unsigned long flags);
-
 /*
  * I/O memory access primitives. Reads are ordered relative to any
  * following Normal memory access. Writes are ordered relative to any prior
@@ -40,9 +33,17 @@ extern int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
 #define writel(v,c)		({ wmb(); writel_relaxed((v),(c)); mb(); })
 #endif
 
-#define ioremap_nocache(phy, sz)	ioremap(phy, sz)
-#define ioremap_wc ioremap_nocache
-#define ioremap_wt ioremap_nocache
+/*
+ * I/O memory mapping functions.
+ */
+extern void __iomem *ioremap_cache(phys_addr_t addr, size_t size);
+extern void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot);
+extern void iounmap(void *addr);
+
+#define ioremap(addr, size)		__ioremap((addr), (size), pgprot_noncached(PAGE_KERNEL))
+#define ioremap_wc(addr, size)		__ioremap((addr), (size), pgprot_writecombine(PAGE_KERNEL))
+#define ioremap_nocache(addr, size)	ioremap((addr), (size))
+#define ioremap_cache			ioremap_cache
 
 #include <asm-generic/io.h>
 
diff --git a/arch/csky/include/asm/pgtable.h b/arch/csky/include/asm/pgtable.h
index 0040b3a05b61..7c21985c60dc 100644
--- a/arch/csky/include/asm/pgtable.h
+++ b/arch/csky/include/asm/pgtable.h
@@ -258,6 +258,16 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
 {
 	unsigned long prot = pgprot_val(_prot);
 
+	prot = (prot & ~_CACHE_MASK) | _CACHE_UNCACHED | _PAGE_SO;
+
+	return __pgprot(prot);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
 	prot = (prot & ~_CACHE_MASK) | _CACHE_UNCACHED;
 
 	return __pgprot(prot);
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index a7e84ccccbd8..a7a5b67df898 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -17,6 +17,12 @@
 #define PTE_INDX_SHIFT  10
 #define _PGDIR_SHIFT    22
 
+.macro	zero_fp
+#ifdef CONFIG_STACKTRACE
+	movi	r8, 0
+#endif
+.endm
+
 .macro tlbop_begin name, val0, val1, val2
 ENTRY(csky_\name)
 	mtcr    a3, ss2
@@ -96,6 +102,7 @@ ENTRY(csky_\name)
 	SAVE_ALL 0
 .endm
 .macro tlbop_end is_write
+	zero_fp
 	RD_MEH	a2
 	psrset  ee, ie
 	mov     a0, sp
@@ -120,6 +127,7 @@ tlbop_end 1
 
 ENTRY(csky_systemcall)
 	SAVE_ALL TRAP0_SIZE
+	zero_fp
 
 	psrset  ee, ie
 
@@ -136,9 +144,9 @@ ENTRY(csky_systemcall)
 	mov     r9, sp
 	bmaski  r10, THREAD_SHIFT
 	andn    r9, r10
-	ldw     r8, (r9, TINFO_FLAGS)
-	ANDI_R3	r8, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
-	cmpnei	r8, 0
+	ldw     r12, (r9, TINFO_FLAGS)
+	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
+	cmpnei	r12, 0
 	bt      csky_syscall_trace
 #if defined(__CSKYABIV2__)
 	subi    sp, 8
@@ -180,7 +188,7 @@ csky_syscall_trace:
 
 ENTRY(ret_from_kernel_thread)
 	jbsr	schedule_tail
-	mov	a0, r8
+	mov	a0, r10
 	jsr	r9
 	jbsr	ret_from_exception
 
@@ -189,9 +197,9 @@ ENTRY(ret_from_fork)
 	mov	r9, sp
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10
-	ldw	r8, (r9, TINFO_FLAGS)
-	ANDI_R3	r8, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
-	cmpnei	r8, 0
+	ldw	r12, (r9, TINFO_FLAGS)
+	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
+	cmpnei	r12, 0
 	bf	ret_from_exception
 	mov	a0, sp			/* sp = pt_regs pointer */
 	jbsr	syscall_trace_exit
@@ -209,9 +217,9 @@ ret_from_exception:
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10
 
-	ldw	r8, (r9, TINFO_FLAGS)
-	andi	r8, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
-	cmpnei	r8, 0
+	ldw	r12, (r9, TINFO_FLAGS)
+	andi	r12, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+	cmpnei	r12, 0
 	bt	exit_work
 1:
 	RESTORE_ALL
@@ -220,11 +228,11 @@ exit_work:
 	lrw	syscallid, ret_from_exception
 	mov	lr, syscallid
 
-	btsti	r8, TIF_NEED_RESCHED
+	btsti	r12, TIF_NEED_RESCHED
 	bt	work_resched
 
 	mov	a0, sp
-	mov	a1, r8
+	mov	a1, r12
 	jmpi	do_notify_resume
 
 work_resched:
@@ -232,6 +240,7 @@ work_resched:
 
 ENTRY(csky_trap)
 	SAVE_ALL 0
+	zero_fp
 	psrset	ee
 	mov	a0, sp                 /* Push Stack pointer arg */
 	jbsr	trap_c                 /* Call C-level trap handler */
@@ -265,6 +274,7 @@ ENTRY(csky_get_tls)
 
 ENTRY(csky_irq)
 	SAVE_ALL 0
+	zero_fp
 	psrset	ee
 
 #ifdef CONFIG_PREEMPT
@@ -276,27 +286,23 @@ ENTRY(csky_irq)
 	 * Get task_struct->stack.preempt_count for current,
 	 * and increase 1.
 	 */
-	ldw	r8, (r9, TINFO_PREEMPT)
-	addi	r8, 1
-	stw	r8, (r9, TINFO_PREEMPT)
+	ldw	r12, (r9, TINFO_PREEMPT)
+	addi	r12, 1
+	stw	r12, (r9, TINFO_PREEMPT)
 #endif
 
 	mov	a0, sp
 	jbsr	csky_do_IRQ
 
 #ifdef CONFIG_PREEMPT
-	subi	r8, 1
-	stw	r8, (r9, TINFO_PREEMPT)
-	cmpnei	r8, 0
+	subi	r12, 1
+	stw	r12, (r9, TINFO_PREEMPT)
+	cmpnei	r12, 0
 	bt	2f
-	ldw	r8, (r9, TINFO_FLAGS)
-	btsti	r8, TIF_NEED_RESCHED
+	ldw	r12, (r9, TINFO_FLAGS)
+	btsti	r12, TIF_NEED_RESCHED
 	bf	2f
-1:
 	jbsr	preempt_schedule_irq	/* irq en/disable is done inside */
-	ldw	r7, (r9, TINFO_FLAGS)	/* get new tasks TI_FLAGS */
-	btsti	r7, TIF_NEED_RESCHED
-	bt	1b			/* go again */
 #endif
 2:
 	jmpi	ret_from_exception
diff --git a/arch/csky/kernel/perf_event.c b/arch/csky/kernel/perf_event.c
index 4c1a1934d76a..1a29f1157449 100644
--- a/arch/csky/kernel/perf_event.c
+++ b/arch/csky/kernel/perf_event.c
@@ -1306,7 +1306,7 @@ int csky_pmu_device_probe(struct platform_device *pdev,
 				 &csky_pmu.count_width)) {
 		csky_pmu.count_width = DEFAULT_COUNT_WIDTH;
 	}
-	csky_pmu.max_period = BIT(csky_pmu.count_width) - 1;
+	csky_pmu.max_period = BIT_ULL(csky_pmu.count_width) - 1;
 
 	csky_pmu.plat_device = pdev;
 
@@ -1337,7 +1337,7 @@ int csky_pmu_device_probe(struct platform_device *pdev,
 	return ret;
 }
 
-const static struct of_device_id csky_pmu_of_device_ids[] = {
+static const struct of_device_id csky_pmu_of_device_ids[] = {
 	{.compatible = "csky,csky-pmu"},
 	{},
 };
diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index e555740c0be5..f320d9248a22 100644
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -55,7 +55,7 @@ int copy_thread(unsigned long clone_flags,
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childstack->r15 = (unsigned long) ret_from_kernel_thread;
-		childstack->r8 = kthread_arg;
+		childstack->r10 = kthread_arg;
 		childstack->r9 = usp;
 		childregs->sr = mfcr("psr");
 	} else {
diff --git a/arch/csky/mm/cachev1.c b/arch/csky/mm/cachev1.c
index b8a75cce0b8c..494ec912abff 100644
--- a/arch/csky/mm/cachev1.c
+++ b/arch/csky/mm/cachev1.c
@@ -120,7 +120,12 @@ void dma_wbinv_range(unsigned long start, unsigned long end)
 	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
 }
 
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
+}
+
 void dma_wb_range(unsigned long start, unsigned long end)
 {
-	cache_op_range(start, end, DATA_CACHE|CACHE_INV, 1);
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
 }
diff --git a/arch/csky/mm/cachev2.c b/arch/csky/mm/cachev2.c
index baaf05d69f44..b61be6518e21 100644
--- a/arch/csky/mm/cachev2.c
+++ b/arch/csky/mm/cachev2.c
@@ -69,11 +69,20 @@ void dma_wbinv_range(unsigned long start, unsigned long end)
 	sync_is();
 }
 
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("dcache.iva %0\n"::"r"(i):"memory");
+	sync_is();
+}
+
 void dma_wb_range(unsigned long start, unsigned long end)
 {
 	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
 
 	for (; i < end; i += L1_CACHE_BYTES)
-		asm volatile("dcache.civa %0\n"::"r"(i):"memory");
+		asm volatile("dcache.cva %0\n"::"r"(i):"memory");
 	sync_is();
 }
diff --git a/arch/csky/mm/dma-mapping.c b/arch/csky/mm/dma-mapping.c
index 602a60d47a94..06e85b565454 100644
--- a/arch/csky/mm/dma-mapping.c
+++ b/arch/csky/mm/dma-mapping.c
@@ -14,69 +14,50 @@
 #include <linux/version.h>
 #include <asm/cache.h>
 
-void arch_dma_prep_coherent(struct page *page, size_t size)
-{
-	if (PageHighMem(page)) {
-		unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-		do {
-			void *ptr = kmap_atomic(page);
-			size_t _size = (size < PAGE_SIZE) ? size : PAGE_SIZE;
-
-			memset(ptr, 0, _size);
-			dma_wbinv_range((unsigned long)ptr,
-					(unsigned long)ptr + _size);
-
-			kunmap_atomic(ptr);
-
-			page++;
-			size -= PAGE_SIZE;
-			count--;
-		} while (count);
-	} else {
-		void *ptr = page_address(page);
-
-		memset(ptr, 0, size);
-		dma_wbinv_range((unsigned long)ptr, (unsigned long)ptr + size);
-	}
-}
-
 static inline void cache_op(phys_addr_t paddr, size_t size,
 			    void (*fn)(unsigned long start, unsigned long end))
 {
-	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
-	unsigned int offset = paddr & ~PAGE_MASK;
-	size_t left = size;
-	unsigned long start;
+	struct page *page    = phys_to_page(paddr);
+	void *start          = __va(page_to_phys(page));
+	unsigned long offset = offset_in_page(paddr);
+	size_t left          = size;
 
 	do {
 		size_t len = left;
 
+		if (offset + len > PAGE_SIZE)
+			len = PAGE_SIZE - offset;
+
 		if (PageHighMem(page)) {
-			void *addr;
+			start = kmap_atomic(page);
 
-			if (offset + len > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset >> PAGE_SHIFT;
-					offset &= ~PAGE_MASK;
-				}
-				len = PAGE_SIZE - offset;
-			}
+			fn((unsigned long)start + offset,
+					(unsigned long)start + offset + len);
 
-			addr = kmap_atomic(page);
-			start = (unsigned long)(addr + offset);
-			fn(start, start + len);
-			kunmap_atomic(addr);
+			kunmap_atomic(start);
 		} else {
-			start = (unsigned long)phys_to_virt(paddr);
-			fn(start, start + size);
+			fn((unsigned long)start + offset,
+					(unsigned long)start + offset + len);
 		}
 		offset = 0;
+
 		page++;
+		start += PAGE_SIZE;
 		left -= len;
 	} while (left);
 }
 
+static void dma_wbinv_set_zero_range(unsigned long start, unsigned long end)
+{
+	memset((void *)start, 0, end - start);
+	dma_wbinv_range(start, end);
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	cache_op(page_to_phys(page), size, dma_wbinv_set_zero_range);
+}
+
 void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 			      size_t size, enum dma_data_direction dir)
 {
@@ -98,11 +79,10 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
-		cache_op(paddr, size, dma_wb_range);
-		break;
+		return;
 	case DMA_FROM_DEVICE:
 	case DMA_BIDIRECTIONAL:
-		cache_op(paddr, size, dma_wbinv_range);
+		cache_op(paddr, size, dma_inv_range);
 		break;
 	default:
 		BUG();
diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c
index eb0dc9e5065f..d4c2292ea46b 100644
--- a/arch/csky/mm/init.c
+++ b/arch/csky/mm/init.c
@@ -60,22 +60,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		pr_info("Freeing initrd memory: %ldk freed\n",
-			(end - start) >> 10);
-
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages_inc();
-	}
-}
-#endif
-
 extern char __init_begin[], __init_end[];
 
 void free_initmem(void)
diff --git a/arch/csky/mm/ioremap.c b/arch/csky/mm/ioremap.c
index 8473b6bdf512..e13cd3497628 100644
--- a/arch/csky/mm/ioremap.c
+++ b/arch/csky/mm/ioremap.c
@@ -8,12 +8,12 @@
 
 #include <asm/pgtable.h>
 
-void __iomem *ioremap(phys_addr_t addr, size_t size)
+static void __iomem *__ioremap_caller(phys_addr_t addr, size_t size,
+				      pgprot_t prot, void *caller)
 {
 	phys_addr_t last_addr;
 	unsigned long offset, vaddr;
 	struct vm_struct *area;
-	pgprot_t prot;
 
 	last_addr = addr + size - 1;
 	if (!size || last_addr < addr)
@@ -23,15 +23,12 @@ void __iomem *ioremap(phys_addr_t addr, size_t size)
 	addr &= PAGE_MASK;
 	size = PAGE_ALIGN(size + offset);
 
-	area = get_vm_area_caller(size, VM_ALLOC, __builtin_return_address(0));
+	area = get_vm_area_caller(size, VM_IOREMAP, caller);
 	if (!area)
 		return NULL;
 
 	vaddr = (unsigned long)area->addr;
 
-	prot = __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE |
-			_PAGE_GLOBAL | _CACHE_UNCACHED | _PAGE_SO);
-
 	if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) {
 		free_vm_area(area);
 		return NULL;
@@ -39,7 +36,20 @@ void __iomem *ioremap(phys_addr_t addr, size_t size)
 
 	return (void __iomem *)(vaddr + offset);
 }
-EXPORT_SYMBOL(ioremap);
+
+void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot)
+{
+	return __ioremap_caller(phys_addr, size, prot,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(__ioremap);
+
+void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
+{
+	return __ioremap_caller(phys_addr, size, PAGE_KERNEL,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
 
 void iounmap(void __iomem *addr)
 {
@@ -51,10 +61,9 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
 	if (!pfn_valid(pfn)) {
-		vma_prot.pgprot |= _PAGE_SO;
 		return pgprot_noncached(vma_prot);
 	} else if (file->f_flags & O_SYNC) {
-		return pgprot_noncached(vma_prot);
+		return pgprot_writecombine(vma_prot);
 	}
 
 	return vma_prot;
diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi
index 63a9f33aa43e..5cfc9d347826 100644
--- a/arch/mips/boot/dts/qca/ar9331.dtsi
+++ b/arch/mips/boot/dts/qca/ar9331.dtsi
@@ -99,7 +99,7 @@
 
 			miscintc: interrupt-controller@18060010 {
 				compatible = "qca,ar7240-misc-intc";
-				reg = <0x18060010 0x4>;
+				reg = <0x18060010 0x8>;
 
 				interrupt-parent = <&cpuintc>;
 				interrupts = <6>;
diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c
index af44b35d79a1..b4328b3b5288 100644
--- a/arch/mips/fw/arc/memory.c
+++ b/arch/mips/fw/arc/memory.c
@@ -160,7 +160,6 @@ void __init prom_meminit(void)
 
 void __init prom_free_prom_memory(void)
 {
-	unsigned long addr;
 	int i;
 
 	if (prom_flags & PROM_FLAG_DONT_FREE_TEMP)
diff --git a/arch/mips/include/asm/octeon/cvmx-ipd.h b/arch/mips/include/asm/octeon/cvmx-ipd.h
index cbdc14b77435..adab7b54c3b4 100644
--- a/arch/mips/include/asm/octeon/cvmx-ipd.h
+++ b/arch/mips/include/asm/octeon/cvmx-ipd.h
@@ -36,6 +36,7 @@
 #include <asm/octeon/octeon-feature.h>
 
 #include <asm/octeon/cvmx-ipd-defs.h>
+#include <asm/octeon/cvmx-pip-defs.h>
 
 enum cvmx_ipd_mode {
    CVMX_IPD_OPC_MODE_STT = 0LL,	  /* All blocks DRAM, not cached in L2 */
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index 071053ece677..5d70babfc9ee 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -52,6 +52,7 @@
 # endif
 #define __ARCH_WANT_SYS_FORK
 #define __ARCH_WANT_SYS_CLONE
+#define __ARCH_WANT_SYS_CLONE3
 
 /* whitelists for checksyscalls */
 #define __IGNORE_fadvise64_64
diff --git a/arch/mips/kernel/cpu-bugs64.c b/arch/mips/kernel/cpu-bugs64.c
index fa62cd1dff93..6a7afe7ef4d3 100644
--- a/arch/mips/kernel/cpu-bugs64.c
+++ b/arch/mips/kernel/cpu-bugs64.c
@@ -24,7 +24,8 @@ static char r4kwar[] __initdata =
 static char daddiwar[] __initdata =
 	"Enable CPU_DADDI_WORKAROUNDS to rectify.";
 
-static inline void align_mod(const int align, const int mod)
+static __always_inline __init
+void align_mod(const int align, const int mod)
 {
 	asm volatile(
 		".set	push\n\t"
@@ -38,8 +39,9 @@ static inline void align_mod(const int align, const int mod)
 		: "n"(align), "n"(mod));
 }
 
-static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w,
-					      const int align, const int mod)
+static __always_inline __init
+void mult_sh_align_mod(long *v1, long *v2, long *w,
+		       const int align, const int mod)
 {
 	unsigned long flags;
 	int m1, m2;
@@ -113,7 +115,7 @@ static __always_inline void mult_sh_align_mod(long *v1, long *v2, long *w,
 	*w = lw;
 }
 
-static inline void check_mult_sh(void)
+static __always_inline __init void check_mult_sh(void)
 {
 	long v1[8], v2[8], w[8];
 	int bug, fix, i;
@@ -176,7 +178,7 @@ asmlinkage void __init do_daddi_ov(struct pt_regs *regs)
 	exception_exit(prev_state);
 }
 
-static inline void check_daddi(void)
+static __init void check_daddi(void)
 {
 	extern asmlinkage void handle_daddi_ov(void);
 	unsigned long flags;
@@ -242,7 +244,7 @@ static inline void check_daddi(void)
 
 int daddiu_bug	= IS_ENABLED(CONFIG_CPU_MIPSR6) ? 0 : -1;
 
-static inline void check_daddiu(void)
+static __init void check_daddiu(void)
 {
 	long v, w, tmp;
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index b8249c233754..5eec13b8d222 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -108,6 +108,9 @@ void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
 		return;
 	}
 
+	if (start < PHYS_OFFSET)
+		return;
+
 	memblock_add(start, size);
 	/* Reserve any memory except the ordinary RAM ranges. */
 	switch (type) {
@@ -321,7 +324,7 @@ static void __init bootmem_init(void)
 	 * Reserve any memory between the start of RAM and PHYS_OFFSET
 	 */
 	if (ramstart > PHYS_OFFSET)
-		memblock_reserve(PHYS_OFFSET, PFN_UP(ramstart) - PHYS_OFFSET);
+		memblock_reserve(PHYS_OFFSET, ramstart - PHYS_OFFSET);
 
 	if (PFN_UP(ramstart) > ARCH_PFN_OFFSET) {
 		pr_info("Wasting %lu bytes for tracking %lu unused pages\n",
diff --git a/arch/mips/kernel/syscall.c b/arch/mips/kernel/syscall.c
index b0e25e913bdb..3f16f3823031 100644
--- a/arch/mips/kernel/syscall.c
+++ b/arch/mips/kernel/syscall.c
@@ -80,6 +80,7 @@ SYSCALL_DEFINE6(mips_mmap2, unsigned long, addr, unsigned long, len,
 
 save_static_function(sys_fork);
 save_static_function(sys_clone);
+save_static_function(sys_clone3);
 
 SYSCALL_DEFINE1(set_thread_area, unsigned long, addr)
 {
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index c9c879ec9b6d..e7c5ab38e403 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -373,4 +373,4 @@
 432	n32	fsmount				sys_fsmount
 433	n32	fspick				sys_fspick
 434	n32	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	n32	clone3				__sys_clone3
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index bbce9159caa1..13cd66581f3b 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -349,4 +349,4 @@
 432	n64	fsmount				sys_fsmount
 433	n64	fspick				sys_fspick
 434	n64	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	n64	clone3				__sys_clone3
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 9653591428ec..353539ea4140 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -422,4 +422,4 @@
 432	o32	fsmount				sys_fsmount
 433	o32	fspick				sys_fspick
 434	o32	pidfd_open			sys_pidfd_open
-# 435 reserved for clone3
+435	o32	clone3				__sys_clone3
diff --git a/arch/mips/loongson64/common/mem.c b/arch/mips/loongson64/common/mem.c
index 4abb92e0fc39..4254ac4ec616 100644
--- a/arch/mips/loongson64/common/mem.c
+++ b/arch/mips/loongson64/common/mem.c
@@ -3,6 +3,7 @@
  */
 #include <linux/fs.h>
 #include <linux/fcntl.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 
 #include <asm/bootinfo.h>
@@ -64,24 +65,22 @@ void __init prom_init_memory(void)
 		node_id = loongson_memmap->map[i].node_id;
 		mem_type = loongson_memmap->map[i].mem_type;
 
-		if (node_id == 0) {
-			switch (mem_type) {
-			case SYSTEM_RAM_LOW:
-				add_memory_region(loongson_memmap->map[i].mem_start,
-					(u64)loongson_memmap->map[i].mem_size << 20,
-					BOOT_MEM_RAM);
-				break;
-			case SYSTEM_RAM_HIGH:
-				add_memory_region(loongson_memmap->map[i].mem_start,
-					(u64)loongson_memmap->map[i].mem_size << 20,
-					BOOT_MEM_RAM);
-				break;
-			case SYSTEM_RAM_RESERVED:
-				add_memory_region(loongson_memmap->map[i].mem_start,
-					(u64)loongson_memmap->map[i].mem_size << 20,
-					BOOT_MEM_RESERVED);
-				break;
-			}
+		if (node_id != 0)
+			continue;
+
+		switch (mem_type) {
+		case SYSTEM_RAM_LOW:
+			memblock_add(loongson_memmap->map[i].mem_start,
+				(u64)loongson_memmap->map[i].mem_size << 20);
+			break;
+		case SYSTEM_RAM_HIGH:
+			memblock_add(loongson_memmap->map[i].mem_start,
+				(u64)loongson_memmap->map[i].mem_size << 20);
+			break;
+		case SYSTEM_RAM_RESERVED:
+			memblock_reserve(loongson_memmap->map[i].mem_start,
+				(u64)loongson_memmap->map[i].mem_size << 20);
+			break;
 		}
 	}
 }
diff --git a/arch/mips/loongson64/common/serial.c b/arch/mips/loongson64/common/serial.c
index ffefc1cb2612..98c3a7feb10f 100644
--- a/arch/mips/loongson64/common/serial.c
+++ b/arch/mips/loongson64/common/serial.c
@@ -110,7 +110,7 @@ static int __init serial_init(void)
 }
 module_init(serial_init);
 
-static void __init serial_exit(void)
+static void __exit serial_exit(void)
 {
 	platform_device_unregister(&uart8250_device);
 }
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index 414e97de5dc0..8f20d2cb3767 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -142,8 +142,6 @@ static void __init szmem(unsigned int node)
 				(u32)node_id, mem_type, mem_start, mem_size);
 			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
 				start_pfn, end_pfn, num_physpages);
-			add_memory_region((node_id << 44) + mem_start,
-				(u64)mem_size << 20, BOOT_MEM_RAM);
 			memblock_add_node(PFN_PHYS(start_pfn),
 				PFN_PHYS(end_pfn - start_pfn), node);
 			break;
@@ -156,16 +154,12 @@ static void __init szmem(unsigned int node)
 				(u32)node_id, mem_type, mem_start, mem_size);
 			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
 				start_pfn, end_pfn, num_physpages);
-			add_memory_region((node_id << 44) + mem_start,
-				(u64)mem_size << 20, BOOT_MEM_RAM);
 			memblock_add_node(PFN_PHYS(start_pfn),
 				PFN_PHYS(end_pfn - start_pfn), node);
 			break;
 		case SYSTEM_RAM_RESERVED:
 			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
 				(u32)node_id, mem_type, mem_start, mem_size);
-			add_memory_region((node_id << 44) + mem_start,
-				(u64)mem_size << 20, BOOT_MEM_RESERVED);
 			memblock_reserve(((node_id << 44) + mem_start),
 				mem_size << 20);
 			break;
@@ -191,8 +185,6 @@ static void __init node_mem_init(unsigned int node)
 	NODE_DATA(node)->node_start_pfn = start_pfn;
 	NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
 
-	free_bootmem_with_active_regions(node, end_pfn);
-
 	if (node == 0) {
 		/* kernel end address */
 		unsigned long kernel_end_pfn = PFN_UP(__pa_symbol(&_end));
@@ -209,8 +201,6 @@ static void __init node_mem_init(unsigned int node)
 			memblock_reserve((node_addrspace_offset | 0xfe000000),
 					 32 << 20);
 	}
-
-	sparse_memory_present_with_active_regions(node);
 }
 
 static __init void prom_meminit(void)
@@ -227,6 +217,7 @@ static __init void prom_meminit(void)
 			cpumask_clear(&__node_data[(node)]->cpumask);
 		}
 	}
+	memblocks_present();
 	max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
 
 	for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) {
diff --git a/arch/mips/pmcs-msp71xx/msp_prom.c b/arch/mips/pmcs-msp71xx/msp_prom.c
index dfb527961a27..800a21b8b8b0 100644
--- a/arch/mips/pmcs-msp71xx/msp_prom.c
+++ b/arch/mips/pmcs-msp71xx/msp_prom.c
@@ -61,6 +61,7 @@ int init_debug = 1;
 /* memory blocks */
 struct prom_pmemblock mdesc[PROM_MAX_PMEMBLOCKS];
 
+#define MAX_PROM_MEM 5
 static phys_addr_t prom_mem_base[MAX_PROM_MEM] __initdata;
 static phys_addr_t prom_mem_size[MAX_PROM_MEM] __initdata;
 static unsigned int nr_prom_mem __initdata;
@@ -358,7 +359,7 @@ void __init prom_meminit(void)
 		p++;
 
 		if (type == BOOT_MEM_ROM_DATA) {
-			if (nr_prom_mem >= 5) {
+			if (nr_prom_mem >= MAX_PROM_MEM) {
 				pr_err("Too many ROM DATA regions");
 				continue;
 			}
@@ -377,7 +378,6 @@ void __init prom_free_prom_memory(void)
 	char	*ptr;
 	int	len = 0;
 	int	i;
-	unsigned long addr;
 
 	/*
 	 * preserve environment variables and command line from pmon/bbload
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 69cfa0a5339e..807f0f782f75 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -59,7 +59,7 @@ CFLAGS_REMOVE_vgettimeofday.o = -pg
 ifndef CONFIG_CPU_MIPSR6
   ifeq ($(call ld-ifversion, -lt, 225000000, y),y)
     $(warning MIPS VDSO requires binutils >= 2.25)
-    obj-vdso-y := $(filter-out gettimeofday.o, $(obj-vdso-y))
+    obj-vdso-y := $(filter-out vgettimeofday.o, $(obj-vdso-y))
     ccflags-vdso += -DDISABLE_MIPS_VDSO
   endif
 endif
diff --git a/arch/mips/vdso/gettimeofday.c b/arch/mips/vdso/gettimeofday.c
deleted file mode 100644
index e8243c7fd5b5..000000000000
--- a/arch/mips/vdso/gettimeofday.c
+++ /dev/null
@@ -1,269 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Copyright (C) 2015 Imagination Technologies
- * Author: Alex Smith <alex.smith@imgtec.com>
- */
-
-#include "vdso.h"
-
-#include <linux/compiler.h>
-#include <linux/time.h>
-
-#include <asm/clocksource.h>
-#include <asm/io.h>
-#include <asm/unistd.h>
-#include <asm/vdso.h>
-
-#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
-
-static __always_inline long gettimeofday_fallback(struct timeval *_tv,
-					  struct timezone *_tz)
-{
-	register struct timezone *tz asm("a1") = _tz;
-	register struct timeval *tv asm("a0") = _tv;
-	register long ret asm("v0");
-	register long nr asm("v0") = __NR_gettimeofday;
-	register long error asm("a3");
-
-	asm volatile(
-	"       syscall\n"
-	: "=r" (ret), "=r" (error)
-	: "r" (tv), "r" (tz), "r" (nr)
-	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
-
-	return error ? -ret : ret;
-}
-
-#endif
-
-static __always_inline long clock_gettime_fallback(clockid_t _clkid,
-					   struct timespec *_ts)
-{
-	register struct timespec *ts asm("a1") = _ts;
-	register clockid_t clkid asm("a0") = _clkid;
-	register long ret asm("v0");
-	register long nr asm("v0") = __NR_clock_gettime;
-	register long error asm("a3");
-
-	asm volatile(
-	"       syscall\n"
-	: "=r" (ret), "=r" (error)
-	: "r" (clkid), "r" (ts), "r" (nr)
-	: "$1", "$3", "$8", "$9", "$10", "$11", "$12", "$13",
-	  "$14", "$15", "$24", "$25", "hi", "lo", "memory");
-
-	return error ? -ret : ret;
-}
-
-static __always_inline int do_realtime_coarse(struct timespec *ts,
-					      const union mips_vdso_data *data)
-{
-	u32 start_seq;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		ts->tv_sec = data->xtime_sec;
-		ts->tv_nsec = data->xtime_nsec >> data->cs_shift;
-	} while (vdso_data_read_retry(data, start_seq));
-
-	return 0;
-}
-
-static __always_inline int do_monotonic_coarse(struct timespec *ts,
-					       const union mips_vdso_data *data)
-{
-	u32 start_seq;
-	u64 to_mono_sec;
-	u64 to_mono_nsec;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		ts->tv_sec = data->xtime_sec;
-		ts->tv_nsec = data->xtime_nsec >> data->cs_shift;
-
-		to_mono_sec = data->wall_to_mono_sec;
-		to_mono_nsec = data->wall_to_mono_nsec;
-	} while (vdso_data_read_retry(data, start_seq));
-
-	ts->tv_sec += to_mono_sec;
-	timespec_add_ns(ts, to_mono_nsec);
-
-	return 0;
-}
-
-#ifdef CONFIG_CSRC_R4K
-
-static __always_inline u64 read_r4k_count(void)
-{
-	unsigned int count;
-
-	__asm__ __volatile__(
-	"	.set push\n"
-	"	.set mips32r2\n"
-	"	rdhwr	%0, $2\n"
-	"	.set pop\n"
-	: "=r" (count));
-
-	return count;
-}
-
-#endif
-
-#ifdef CONFIG_CLKSRC_MIPS_GIC
-
-static __always_inline u64 read_gic_count(const union mips_vdso_data *data)
-{
-	void __iomem *gic = get_gic(data);
-	u32 hi, hi2, lo;
-
-	do {
-		hi = __raw_readl(gic + sizeof(lo));
-		lo = __raw_readl(gic);
-		hi2 = __raw_readl(gic + sizeof(lo));
-	} while (hi2 != hi);
-
-	return (((u64)hi) << 32) + lo;
-}
-
-#endif
-
-static __always_inline u64 get_ns(const union mips_vdso_data *data)
-{
-	u64 cycle_now, delta, nsec;
-
-	switch (data->clock_mode) {
-#ifdef CONFIG_CSRC_R4K
-	case VDSO_CLOCK_R4K:
-		cycle_now = read_r4k_count();
-		break;
-#endif
-#ifdef CONFIG_CLKSRC_MIPS_GIC
-	case VDSO_CLOCK_GIC:
-		cycle_now = read_gic_count(data);
-		break;
-#endif
-	default:
-		return 0;
-	}
-
-	delta = (cycle_now - data->cs_cycle_last) & data->cs_mask;
-
-	nsec = (delta * data->cs_mult) + data->xtime_nsec;
-	nsec >>= data->cs_shift;
-
-	return nsec;
-}
-
-static __always_inline int do_realtime(struct timespec *ts,
-				       const union mips_vdso_data *data)
-{
-	u32 start_seq;
-	u64 ns;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		if (data->clock_mode == VDSO_CLOCK_NONE)
-			return -ENOSYS;
-
-		ts->tv_sec = data->xtime_sec;
-		ns = get_ns(data);
-	} while (vdso_data_read_retry(data, start_seq));
-
-	ts->tv_nsec = 0;
-	timespec_add_ns(ts, ns);
-
-	return 0;
-}
-
-static __always_inline int do_monotonic(struct timespec *ts,
-					const union mips_vdso_data *data)
-{
-	u32 start_seq;
-	u64 ns;
-	u64 to_mono_sec;
-	u64 to_mono_nsec;
-
-	do {
-		start_seq = vdso_data_read_begin(data);
-
-		if (data->clock_mode == VDSO_CLOCK_NONE)
-			return -ENOSYS;
-
-		ts->tv_sec = data->xtime_sec;
-		ns = get_ns(data);
-
-		to_mono_sec = data->wall_to_mono_sec;
-		to_mono_nsec = data->wall_to_mono_nsec;
-	} while (vdso_data_read_retry(data, start_seq));
-
-	ts->tv_sec += to_mono_sec;
-	ts->tv_nsec = 0;
-	timespec_add_ns(ts, ns + to_mono_nsec);
-
-	return 0;
-}
-
-#ifdef CONFIG_MIPS_CLOCK_VSYSCALL
-
-/*
- * This is behind the ifdef so that we don't provide the symbol when there's no
- * possibility of there being a usable clocksource, because there's nothing we
- * can do without it. When libc fails the symbol lookup it should fall back on
- * the standard syscall path.
- */
-int __vdso_gettimeofday(struct timeval *tv, struct timezone *tz)
-{
-	const union mips_vdso_data *data = get_vdso_data();
-	struct timespec ts;
-	int ret;
-
-	ret = do_realtime(&ts, data);
-	if (ret)
-		return gettimeofday_fallback(tv, tz);
-
-	if (tv) {
-		tv->tv_sec = ts.tv_sec;
-		tv->tv_usec = ts.tv_nsec / 1000;
-	}
-
-	if (tz) {
-		tz->tz_minuteswest = data->tz_minuteswest;
-		tz->tz_dsttime = data->tz_dsttime;
-	}
-
-	return 0;
-}
-
-#endif /* CONFIG_MIPS_CLOCK_VSYSCALL */
-
-int __vdso_clock_gettime(clockid_t clkid, struct timespec *ts)
-{
-	const union mips_vdso_data *data = get_vdso_data();
-	int ret = -1;
-
-	switch (clkid) {
-	case CLOCK_REALTIME_COARSE:
-		ret = do_realtime_coarse(ts, data);
-		break;
-	case CLOCK_MONOTONIC_COARSE:
-		ret = do_monotonic_coarse(ts, data);
-		break;
-	case CLOCK_REALTIME:
-		ret = do_realtime(ts, data);
-		break;
-	case CLOCK_MONOTONIC:
-		ret = do_monotonic(ts, data);
-		break;
-	default:
-		break;
-	}
-
-	if (ret)
-		ret = clock_gettime_fallback(clkid, ts);
-
-	return ret;
-}
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 6841bd52738b..dfbd7f22eef5 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -50,7 +50,7 @@ endif
 
 BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -nostdinc
 
-BOOTARFLAGS	:= -cr$(KBUILD_ARFLAGS)
+BOOTARFLAGS	:= -crD
 
 ifdef CONFIG_CC_IS_CLANG
 BOOTCFLAGS += $(CLANG_FLAGS)
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 574eca33f893..d97db3ad9aae 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -254,7 +254,13 @@ extern void radix__pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 extern pgtable_t radix__pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
 extern pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
 				      unsigned long addr, pmd_t *pmdp);
-extern int radix__has_transparent_hugepage(void);
+static inline int radix__has_transparent_hugepage(void)
+{
+	/* For radix 2M at PMD level means thp */
+	if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
+		return 1;
+	return 0;
+}
 #endif
 
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d7fcdfa7fee4..ec2547cc5ecb 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -36,8 +36,8 @@
 #include "book3s.h"
 #include "trace.h"
 
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
 /* #define EXIT_DEBUG */
 
@@ -69,8 +69,8 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pthru_all",       VCPU_STAT(pthru_all) },
 	{ "pthru_host",      VCPU_STAT(pthru_host) },
 	{ "pthru_bad_aff",   VCPU_STAT(pthru_bad_aff) },
-	{ "largepages_2M",    VM_STAT(num_2M_pages) },
-	{ "largepages_1G",    VM_STAT(num_1G_pages) },
+	{ "largepages_2M",    VM_STAT(num_2M_pages, .mode = 0444) },
+	{ "largepages_1G",    VM_STAT(num_1G_pages, .mode = 0444) },
 	{ NULL }
 };
 
diff --git a/arch/powerpc/mm/book3s64/hash_pgtable.c b/arch/powerpc/mm/book3s64/hash_pgtable.c
index d1f390ac9cdb..64733b9cb20a 100644
--- a/arch/powerpc/mm/book3s64/hash_pgtable.c
+++ b/arch/powerpc/mm/book3s64/hash_pgtable.c
@@ -406,6 +406,8 @@ int hash__has_transparent_hugepage(void)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(hash__has_transparent_hugepage);
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #ifdef CONFIG_STRICT_KERNEL_RWX
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c
index 3a1fbf9cb8f8..6ee17d09649c 100644
--- a/arch/powerpc/mm/book3s64/radix_pgtable.c
+++ b/arch/powerpc/mm/book3s64/radix_pgtable.c
@@ -1027,13 +1027,6 @@ pmd_t radix__pmdp_huge_get_and_clear(struct mm_struct *mm,
 	return old_pmd;
 }
 
-int radix__has_transparent_hugepage(void)
-{
-	/* For radix 2M at PMD level means thp */
-	if (mmu_psize_defs[MMU_PAGE_2M].shift == PMD_SHIFT)
-		return 1;
-	return 0;
-}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index a44f6281ca3a..4e08246acd79 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -172,6 +172,21 @@ static __meminit void vmemmap_list_populate(unsigned long phys,
 	vmemmap_list = vmem_back;
 }
 
+static bool altmap_cross_boundary(struct vmem_altmap *altmap, unsigned long start,
+				unsigned long page_size)
+{
+	unsigned long nr_pfn = page_size / sizeof(struct page);
+	unsigned long start_pfn = page_to_pfn((struct page *)start);
+
+	if ((start_pfn + nr_pfn) > altmap->end_pfn)
+		return true;
+
+	if (start_pfn < altmap->base_pfn)
+		return true;
+
+	return false;
+}
+
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
@@ -194,7 +209,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		 * fail due to alignment issues when using 16MB hugepages, so
 		 * fall back to system memory if the altmap allocation fail.
 		 */
-		if (altmap) {
+		if (altmap && !altmap_cross_boundary(altmap, start, page_size)) {
 			p = altmap_alloc_block_buf(page_size, altmap);
 			if (!p)
 				pr_debug("altmap block allocation failed, falling back to system memory");
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 5a02b7d50940..9c992a88d858 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -22,6 +22,7 @@
 
 #define REG_L		__REG_SEL(ld, lw)
 #define REG_S		__REG_SEL(sd, sw)
+#define REG_SC		__REG_SEL(sc.d, sc.w)
 #define SZREG		__REG_SEL(8, 4)
 #define LGREG		__REG_SEL(3, 2)
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index da7aa88113c2..2d592da1e776 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -98,7 +98,26 @@ _save_context:
  */
 	.macro RESTORE_ALL
 	REG_L a0, PT_SSTATUS(sp)
-	REG_L a2, PT_SEPC(sp)
+	/*
+	 * The current load reservation is effectively part of the processor's
+	 * state, in the sense that load reservations cannot be shared between
+	 * different hart contexts.  We can't actually save and restore a load
+	 * reservation, so instead here we clear any existing reservation --
+	 * it's always legal for implementations to clear load reservations at
+	 * any point (as long as the forward progress guarantee is kept, but
+	 * we'll ignore that here).
+	 *
+	 * Dangling load reservations can be the result of taking a trap in the
+	 * middle of an LR/SC sequence, but can also be the result of a taken
+	 * forward branch around an SC -- which is how we implement CAS.  As a
+	 * result we need to clear reservations between the last CAS and the
+	 * jump back to the new context.  While it is unlikely the store
+	 * completes, implementations are allowed to expand reservations to be
+	 * arbitrarily large.
+	 */
+	REG_L  a2, PT_SEPC(sp)
+	REG_SC x0, a2, PT_SEPC(sp)
+
 	csrw CSR_SSTATUS, a0
 	csrw CSR_SEPC, a2
 
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index f0ba71304b6e..83f7d12042fb 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -11,6 +11,7 @@
 #include <linux/swap.h>
 #include <linux/sizes.h>
 #include <linux/of_fdt.h>
+#include <linux/libfdt.h>
 
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
@@ -82,6 +83,8 @@ disable:
 }
 #endif /* CONFIG_BLK_DEV_INITRD */
 
+static phys_addr_t dtb_early_pa __initdata;
+
 void __init setup_bootmem(void)
 {
 	struct memblock_region *reg;
@@ -117,7 +120,12 @@ void __init setup_bootmem(void)
 	setup_initrd();
 #endif /* CONFIG_BLK_DEV_INITRD */
 
-	early_init_fdt_reserve_self();
+	/*
+	 * Avoid using early_init_fdt_reserve_self() since __pa() does
+	 * not work for DTB pointers that are fixmap addresses
+	 */
+	memblock_reserve(dtb_early_pa, fdt_totalsize(dtb_early_va));
+
 	early_init_fdt_scan_reserved_mem();
 	memblock_allow_resize();
 	memblock_dump_all();
@@ -393,6 +401,8 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
 
 	/* Save pointer to DTB for early FDT parsing */
 	dtb_early_va = (void *)fix_to_virt(FIX_FDT) + (dtb_pa & ~PAGE_MASK);
+	/* Save physical address for memblock reservation */
+	dtb_early_pa = dtb_pa;
 }
 
 static void __init setup_vm_final(void)
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 347f48702edb..38d64030aacf 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -44,6 +44,7 @@ CONFIG_NR_CPUS=512
 CONFIG_NUMA=y
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
@@ -69,12 +70,13 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG=y
 CONFIG_MODULE_SIG_SHA256=y
+CONFIG_UNUSED_SYMBOLS=y
 CONFIG_BLK_DEV_INTEGRITY=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -370,6 +372,7 @@ CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 CONFIG_PCI_DEBUG=y
 CONFIG_HOTPLUG_PCI=y
@@ -424,6 +427,7 @@ CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_LOG_USERSPACE=m
 CONFIG_DM_RAID=m
@@ -435,6 +439,7 @@ CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
 CONFIG_DM_VERITY=m
+CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_NETDEVICES=y
 CONFIG_BONDING=m
@@ -489,6 +494,7 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
 # CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_PENSANDO is not set
 # CONFIG_NET_VENDOR_QLOGIC is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RDC is not set
@@ -538,15 +544,16 @@ CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
-CONFIG_DRM=y
-CONFIG_DRM_VIRTIO_GPU=y
+CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
+CONFIG_SYNC_FILE=y
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
 CONFIG_VFIO_MDEV=m
@@ -580,6 +587,8 @@ CONFIG_NILFS2_FS=m
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
+CONFIG_FS_VERITY=y
+CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
@@ -589,6 +598,7 @@ CONFIG_QFMT_V2=m
 CONFIG_AUTOFS4_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
@@ -648,12 +658,15 @@ CONFIG_FORTIFY_SOURCE=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_LOCKDOWN_LSM=y
+CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
 CONFIG_INTEGRITY_SIGNATURE=y
 CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
 CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
+CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
 CONFIG_CRYPTO_PCRYPT=m
@@ -664,10 +677,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -739,7 +748,6 @@ CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
 CONFIG_HEADERS_INSTALL=y
 CONFIG_HEADERS_CHECK=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 8514b8b9500f..25f799849582 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -44,6 +44,7 @@ CONFIG_NUMA=y
 # CONFIG_NUMA_EMU is not set
 CONFIG_HZ_100=y
 CONFIG_KEXEC_FILE=y
+CONFIG_KEXEC_SIG=y
 CONFIG_EXPOLINE=y
 CONFIG_EXPOLINE_AUTO=y
 CONFIG_CHSC_SCH=y
@@ -66,11 +67,12 @@ CONFIG_MODULE_UNLOAD=y
 CONFIG_MODULE_FORCE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-CONFIG_MODULE_SIG=y
 CONFIG_MODULE_SIG_SHA256=y
+CONFIG_UNUSED_SYMBOLS=y
 CONFIG_BLK_DEV_THROTTLING=y
 CONFIG_BLK_WBT=y
 CONFIG_BLK_CGROUP_IOLATENCY=y
+CONFIG_BLK_CGROUP_IOCOST=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_BSD_DISKLABEL=y
@@ -363,6 +365,7 @@ CONFIG_NETLINK_DIAG=m
 CONFIG_CGROUP_NET_PRIO=y
 CONFIG_BPF_JIT=y
 CONFIG_NET_PKTGEN=m
+# CONFIG_NET_DROP_MONITOR is not set
 CONFIG_PCI=y
 CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
@@ -418,6 +421,7 @@ CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
 CONFIG_DM_WRITECACHE=m
+CONFIG_DM_CLONE=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_LOG_USERSPACE=m
 CONFIG_DM_RAID=m
@@ -429,6 +433,7 @@ CONFIG_DM_DELAY=m
 CONFIG_DM_UEVENT=y
 CONFIG_DM_FLAKEY=m
 CONFIG_DM_VERITY=m
+CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG=y
 CONFIG_DM_SWITCH=m
 CONFIG_DM_INTEGRITY=m
 CONFIG_NETDEVICES=y
@@ -484,6 +489,7 @@ CONFIG_MLX5_CORE_EN=y
 # CONFIG_NET_VENDOR_NVIDIA is not set
 # CONFIG_NET_VENDOR_OKI is not set
 # CONFIG_NET_VENDOR_PACKET_ENGINES is not set
+# CONFIG_NET_VENDOR_PENSANDO is not set
 # CONFIG_NET_VENDOR_QLOGIC is not set
 # CONFIG_NET_VENDOR_QUALCOMM is not set
 # CONFIG_NET_VENDOR_RDC is not set
@@ -533,16 +539,16 @@ CONFIG_WATCHDOG_CORE=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
 CONFIG_DIAG288_WATCHDOG=m
-CONFIG_DRM=y
-CONFIG_DRM_VIRTIO_GPU=y
-# CONFIG_BACKLIGHT_CLASS_DEVICE is not set
+CONFIG_FB=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
 CONFIG_INFINIBAND_USER_ACCESS=m
 CONFIG_MLX4_INFINIBAND=m
 CONFIG_MLX5_INFINIBAND=m
+CONFIG_SYNC_FILE=y
 CONFIG_VFIO=m
 CONFIG_VFIO_PCI=m
 CONFIG_VFIO_MDEV=m
@@ -573,6 +579,8 @@ CONFIG_NILFS2_FS=m
 CONFIG_FS_DAX=y
 CONFIG_EXPORTFS_BLOCK_OPS=y
 CONFIG_FS_ENCRYPTION=y
+CONFIG_FS_VERITY=y
+CONFIG_FS_VERITY_BUILTIN_SIGNATURES=y
 CONFIG_FANOTIFY=y
 CONFIG_FANOTIFY_ACCESS_PERMISSIONS=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
@@ -581,6 +589,7 @@ CONFIG_QFMT_V2=m
 CONFIG_AUTOFS4_FS=m
 CONFIG_FUSE_FS=y
 CONFIG_CUSE=m
+CONFIG_VIRTIO_FS=m
 CONFIG_OVERLAY_FS=m
 CONFIG_FSCACHE=m
 CONFIG_CACHEFILES=m
@@ -639,12 +648,15 @@ CONFIG_SECURITY_NETWORK=y
 CONFIG_SECURITY_SELINUX=y
 CONFIG_SECURITY_SELINUX_BOOTPARAM=y
 CONFIG_SECURITY_SELINUX_DISABLE=y
+CONFIG_SECURITY_LOCKDOWN_LSM=y
+CONFIG_SECURITY_LOCKDOWN_LSM_EARLY=y
 CONFIG_INTEGRITY_SIGNATURE=y
 CONFIG_INTEGRITY_ASYMMETRIC_KEYS=y
 CONFIG_IMA=y
 CONFIG_IMA_DEFAULT_HASH_SHA256=y
 CONFIG_IMA_WRITE_POLICY=y
 CONFIG_IMA_APPRAISE=y
+CONFIG_LSM="yama,loadpin,safesetid,integrity,selinux,smack,tomoyo,apparmor"
 CONFIG_CRYPTO_FIPS=y
 CONFIG_CRYPTO_USER=m
 # CONFIG_CRYPTO_MANAGER_DISABLE_TESTS is not set
@@ -656,10 +668,6 @@ CONFIG_CRYPTO_ECDH=m
 CONFIG_CRYPTO_ECRDSA=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_CRYPTO_AEGIS128=m
-CONFIG_CRYPTO_AEGIS128L=m
-CONFIG_CRYPTO_AEGIS256=m
-CONFIG_CRYPTO_MORUS640=m
-CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_OFB=m
@@ -727,7 +735,6 @@ CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_INFO_DWARF4=y
 CONFIG_GDB_SCRIPTS=y
 CONFIG_FRAME_WARN=1024
-CONFIG_UNUSED_SYMBOLS=y
 CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_MEMORY_INIT=y
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index be09a208b608..20c51e5d9353 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -61,7 +61,7 @@ CONFIG_RAW_DRIVER=y
 CONFIG_CONFIGFS_FS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_DIMLIB is not set
+CONFIG_LSM="yama,loadpin,safesetid,integrity"
 CONFIG_PRINTK_TIME=y
 CONFIG_DEBUG_INFO=y
 CONFIG_DEBUG_FS=y
diff --git a/arch/s390/include/asm/atomic_ops.h b/arch/s390/include/asm/atomic_ops.h
index d3f09526ee19..61467b9eecc7 100644
--- a/arch/s390/include/asm/atomic_ops.h
+++ b/arch/s390/include/asm/atomic_ops.h
@@ -41,7 +41,7 @@ __ATOMIC_OPS(__atomic64_xor, long, "laxg")
 #undef __ATOMIC_OP
 
 #define __ATOMIC_CONST_OP(op_name, op_type, op_string, op_barrier)	\
-static inline void op_name(op_type val, op_type *ptr)			\
+static __always_inline void op_name(op_type val, op_type *ptr)		\
 {									\
 	asm volatile(							\
 		op_string "	%[ptr],%[val]\n"			\
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index b8833ac983fa..eb7eed43e780 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -56,7 +56,7 @@ __bitops_byte(unsigned long nr, volatile unsigned long *ptr)
 	return ((unsigned char *)ptr) + ((nr ^ (BITS_PER_LONG - 8)) >> 3);
 }
 
-static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
 {
 	unsigned long *addr = __bitops_word(nr, ptr);
 	unsigned long mask;
@@ -77,7 +77,7 @@ static inline void arch_set_bit(unsigned long nr, volatile unsigned long *ptr)
 	__atomic64_or(mask, (long *)addr);
 }
 
-static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
+static __always_inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 {
 	unsigned long *addr = __bitops_word(nr, ptr);
 	unsigned long mask;
@@ -98,8 +98,8 @@ static inline void arch_clear_bit(unsigned long nr, volatile unsigned long *ptr)
 	__atomic64_and(mask, (long *)addr);
 }
 
-static inline void arch_change_bit(unsigned long nr,
-				   volatile unsigned long *ptr)
+static __always_inline void arch_change_bit(unsigned long nr,
+					    volatile unsigned long *ptr)
 {
 	unsigned long *addr = __bitops_word(nr, ptr);
 	unsigned long mask;
diff --git a/arch/s390/include/asm/cpacf.h b/arch/s390/include/asm/cpacf.h
index a092f63aac6a..c0f3bfeddcbe 100644
--- a/arch/s390/include/asm/cpacf.h
+++ b/arch/s390/include/asm/cpacf.h
@@ -171,7 +171,7 @@ typedef struct { unsigned char bytes[16]; } cpacf_mask_t;
  *
  * Returns 1 if @func is available for @opcode, 0 otherwise
  */
-static inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
+static __always_inline void __cpacf_query(unsigned int opcode, cpacf_mask_t *mask)
 {
 	register unsigned long r0 asm("0") = 0;	/* query function */
 	register unsigned long r1 asm("1") = (unsigned long) mask;
diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index ceeb552d3472..819803a97c2b 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -28,6 +28,8 @@ asm(".include \"asm/cpu_mf-insn.h\"\n");
 				 CPU_MF_INT_SF_PRA|CPU_MF_INT_SF_SACA|	\
 				 CPU_MF_INT_SF_LSDA)
 
+#define CPU_MF_SF_RIBM_NOTAV	0x1		/* Sampling unavailable */
+
 /* CPU measurement facility support */
 static inline int cpum_cf_avail(void)
 {
@@ -69,7 +71,8 @@ struct hws_qsi_info_block {	    /* Bit(s) */
 	unsigned long max_sampl_rate; /* 16-23: maximum sampling interval*/
 	unsigned long tear;	    /* 24-31: TEAR contents		 */
 	unsigned long dear;	    /* 32-39: DEAR contents		 */
-	unsigned int rsvrd0;	    /* 40-43: reserved			 */
+	unsigned int rsvrd0:24;	    /* 40-42: reserved			 */
+	unsigned int ribm:8;	    /* 43: Reserved by IBM		 */
 	unsigned int cpu_speed;     /* 44-47: CPU speed			 */
 	unsigned long long rsvrd1;  /* 48-55: reserved			 */
 	unsigned long long rsvrd2;  /* 56-63: reserved			 */
@@ -220,7 +223,8 @@ enum stcctm_ctr_set {
 	MT_DIAG = 5,
 	MT_DIAG_CLEARING = 9,	/* clears loss-of-MT-ctr-data alert */
 };
-static inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest)
+
+static __always_inline int stcctm(enum stcctm_ctr_set set, u64 range, u64 *dest)
 {
 	int cc;
 
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index bb59dd964590..de8f0bf5f238 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -12,8 +12,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 
-
-#define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range			free_pgd_range
 #define hugepages_supported()			(MACHINE_HAS_EDAT1)
 
@@ -23,6 +21,13 @@ pte_t huge_ptep_get(pte_t *ptep);
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr, pte_t *ptep);
 
+static inline bool is_hugepage_only_range(struct mm_struct *mm,
+					  unsigned long addr,
+					  unsigned long len)
+{
+	return false;
+}
+
 /*
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
diff --git a/arch/s390/include/asm/jump_label.h b/arch/s390/include/asm/jump_label.h
index e548ec1ec12c..39f747d63758 100644
--- a/arch/s390/include/asm/jump_label.h
+++ b/arch/s390/include/asm/jump_label.h
@@ -20,7 +20,7 @@
  * We use a brcl 0,2 instruction for jump labels at compile time so it
  * can be easily distinguished from a hotpatch generated instruction.
  */
-static inline bool arch_static_branch(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("0:	brcl	0,"__stringify(JUMP_LABEL_NOP_OFFSET)"\n"
 			  ".pushsection __jump_table,\"aw\"\n"
@@ -34,7 +34,7 @@ label:
 	return true;
 }
 
-static inline bool arch_static_branch_jump(struct static_key *key, bool branch)
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("0:	brcl 15,%l[label]\n"
 			  ".pushsection __jump_table,\"aw\"\n"
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 36c578c0ff96..5ff98d76a66c 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -997,9 +997,9 @@ static inline pte_t pte_mkhuge(pte_t pte)
 #define IPTE_NODAT	0x400
 #define IPTE_GUEST_ASCE	0x800
 
-static inline void __ptep_ipte(unsigned long address, pte_t *ptep,
-			       unsigned long opt, unsigned long asce,
-			       int local)
+static __always_inline void __ptep_ipte(unsigned long address, pte_t *ptep,
+					unsigned long opt, unsigned long asce,
+					int local)
 {
 	unsigned long pto = (unsigned long) ptep;
 
@@ -1020,8 +1020,8 @@ static inline void __ptep_ipte(unsigned long address, pte_t *ptep,
 		: [r1] "a" (pto), [m4] "i" (local) : "memory");
 }
 
-static inline void __ptep_ipte_range(unsigned long address, int nr,
-				     pte_t *ptep, int local)
+static __always_inline void __ptep_ipte_range(unsigned long address, int nr,
+					      pte_t *ptep, int local)
 {
 	unsigned long pto = (unsigned long) ptep;
 
@@ -1269,7 +1269,8 @@ static inline pte_t *pte_offset(pmd_t *pmd, unsigned long address)
 
 #define pte_offset_kernel(pmd, address) pte_offset(pmd, address)
 #define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_unmap(pte) do { } while (0)
+
+static inline void pte_unmap(pte_t *pte) { }
 
 static inline bool gup_fast_permitted(unsigned long start, unsigned long end)
 {
@@ -1435,9 +1436,9 @@ static inline void __pmdp_csp(pmd_t *pmdp)
 #define IDTE_NODAT	0x1000
 #define IDTE_GUEST_ASCE	0x2000
 
-static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
-			       unsigned long opt, unsigned long asce,
-			       int local)
+static __always_inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
+					unsigned long opt, unsigned long asce,
+					int local)
 {
 	unsigned long sto;
 
@@ -1461,9 +1462,9 @@ static inline void __pmdp_idte(unsigned long addr, pmd_t *pmdp,
 	}
 }
 
-static inline void __pudp_idte(unsigned long addr, pud_t *pudp,
-			       unsigned long opt, unsigned long asce,
-			       int local)
+static __always_inline void __pudp_idte(unsigned long addr, pud_t *pudp,
+					unsigned long opt, unsigned long asce,
+					int local)
 {
 	unsigned long r3o;
 
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 78e8a888306d..e3f238e8c611 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -111,7 +111,7 @@ struct qib {
 	/* private: */
 	u8 res[88];
 	/* public: */
-	u8 parm[QDIO_MAX_BUFFERS_PER_Q];
+	u8 parm[128];
 } __attribute__ ((packed, aligned(256)));
 
 /**
diff --git a/arch/s390/kernel/perf_cpum_cf_diag.c b/arch/s390/kernel/perf_cpum_cf_diag.c
index 5f1fd1581330..2654e348801a 100644
--- a/arch/s390/kernel/perf_cpum_cf_diag.c
+++ b/arch/s390/kernel/perf_cpum_cf_diag.c
@@ -390,7 +390,7 @@ static size_t cf_diag_getctrset(struct cf_ctrset_entry *ctrdata, int ctrset,
 
 	debug_sprintf_event(cf_diag_dbg, 6,
 			    "%s ctrset %d ctrset_size %zu cfvn %d csvn %d"
-			    " need %zd rc:%d\n",
+			    " need %zd rc %d\n",
 			    __func__, ctrset, ctrset_size, cpuhw->info.cfvn,
 			    cpuhw->info.csvn, need, rc);
 	return need;
@@ -567,7 +567,7 @@ static int cf_diag_add(struct perf_event *event, int flags)
 	int err = 0;
 
 	debug_sprintf_event(cf_diag_dbg, 5,
-			    "%s event %p cpu %d flags %#x cpuhw:%p\n",
+			    "%s event %p cpu %d flags %#x cpuhw %p\n",
 			    __func__, event, event->cpu, flags, cpuhw);
 
 	if (cpuhw->flags & PMU_F_IN_USE) {
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 544a02e944c6..3d8b12a9a6ff 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -803,6 +803,12 @@ static int __hw_perf_event_init(struct perf_event *event)
 		goto out;
 	}
 
+	if (si.ribm & CPU_MF_SF_RIBM_NOTAV) {
+		pr_warn("CPU Measurement Facility sampling is temporarily not available\n");
+		err = -EBUSY;
+		goto out;
+	}
+
 	/* Always enable basic sampling */
 	SAMPL_FLAGS(hwc) = PERF_CPUM_SF_BASIC_MODE;
 
@@ -895,7 +901,7 @@ static int cpumsf_pmu_event_init(struct perf_event *event)
 
 	/* Check online status of the CPU to which the event is pinned */
 	if (event->cpu >= 0 && !cpu_online(event->cpu))
-			return -ENODEV;
+		return -ENODEV;
 
 	/* Force reset of idle/hv excludes regardless of what the
 	 * user requested.
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f6db0f1bc867..d047e846e1b9 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -332,7 +332,7 @@ static inline int plo_test_bit(unsigned char nr)
 	return cc == 0;
 }
 
-static inline void __insn32_query(unsigned int opcode, u8 query[32])
+static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
 {
 	register unsigned long r0 asm("0") = 0;	/* query function */
 	register unsigned long r1 asm("1") = (unsigned long) query;
@@ -340,9 +340,9 @@ static inline void __insn32_query(unsigned int opcode, u8 query[32])
 	asm volatile(
 		/* Parameter regs are ignored */
 		"	.insn	rrf,%[opc] << 16,2,4,6,0\n"
-		: "=m" (*query)
+		:
 		: "d" (r0), "a" (r1), [opc] "i" (opcode)
-		: "cc");
+		: "cc", "memory");
 }
 
 #define INSN_SORTL 0xb938
diff --git a/arch/s390/pci/pci_clp.c b/arch/s390/pci/pci_clp.c
index 9bdff4defef1..e585a62d6530 100644
--- a/arch/s390/pci/pci_clp.c
+++ b/arch/s390/pci/pci_clp.c
@@ -66,7 +66,7 @@ static inline int clp_get_ilp(unsigned long *ilp)
 /*
  * Call Logical Processor with c=0, the give constant lps and an lpcb request.
  */
-static inline int clp_req(void *data, unsigned int lps)
+static __always_inline int clp_req(void *data, unsigned int lps)
 {
 	struct { u8 _[CLP_BLK_SIZE]; } *req = data;
 	u64 ignored;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 23edf56cf577..50eb430b0ad8 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -219,13 +219,6 @@ enum {
 				 PFERR_WRITE_MASK |		\
 				 PFERR_PRESENT_MASK)
 
-/*
- * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
- * Access Tracking SPTEs. We use bit 62 instead of bit 63 to avoid conflicting
- * with the SVE bit in EPT PTEs.
- */
-#define SPTE_SPECIAL_MASK (1ULL << 62)
-
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
 /*
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 63316036f85a..9c5029cf6f3f 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -485,6 +485,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
 
 	/* cpuid 0x80000008.ebx */
 	const u32 kvm_cpuid_8000_0008_ebx_x86_features =
+		F(CLZERO) | F(XSAVEERPTR) |
 		F(WBNOINVD) | F(AMD_IBPB) | F(AMD_IBRS) | F(AMD_SSBD) | F(VIRT_SSBD) |
 		F(AMD_SSB_NO) | F(AMD_STIBP) | F(AMD_STIBP_ALWAYS_ON);
 
@@ -618,16 +619,20 @@ static inline int __do_cpuid_func(struct kvm_cpuid_entry2 *entry, u32 function,
 	 */
 	case 0x1f:
 	case 0xb: {
-		int i, level_type;
+		int i;
 
-		/* read more entries until level_type is zero */
-		for (i = 1; ; ++i) {
+		/*
+		 * We filled in entry[0] for CPUID(EAX=<function>,
+		 * ECX=00H) above.  If its level type (ECX[15:8]) is
+		 * zero, then the leaf is unimplemented, and we're
+		 * done.  Otherwise, continue to populate entries
+		 * until the level type (ECX[15:8]) of the previously
+		 * added entry is zero.
+		 */
+		for (i = 1; entry[i - 1].ecx & 0xff00; ++i) {
 			if (*nent >= maxnent)
 				goto out;
 
-			level_type = entry[i - 1].ecx & 0xff00;
-			if (!level_type)
-				break;
 			do_host_cpuid(&entry[i], function, i);
 			++*nent;
 		}
@@ -969,53 +974,66 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
 
 /*
- * If no match is found, check whether we exceed the vCPU's limit
- * and return the content of the highest valid _standard_ leaf instead.
- * This is to satisfy the CPUID specification.
+ * If the basic or extended CPUID leaf requested is higher than the
+ * maximum supported basic or extended leaf, respectively, then it is
+ * out of range.
  */
-static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
-                                                  u32 function, u32 index)
+static bool cpuid_function_in_range(struct kvm_vcpu *vcpu, u32 function)
 {
-	struct kvm_cpuid_entry2 *maxlevel;
-
-	maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
-	if (!maxlevel || maxlevel->eax >= function)
-		return NULL;
-	if (function & 0x80000000) {
-		maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
-		if (!maxlevel)
-			return NULL;
-	}
-	return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
+	struct kvm_cpuid_entry2 *max;
+
+	max = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
+	return max && function <= max->eax;
 }
 
 bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
 	       u32 *ecx, u32 *edx, bool check_limit)
 {
 	u32 function = *eax, index = *ecx;
-	struct kvm_cpuid_entry2 *best;
-	bool entry_found = true;
-
-	best = kvm_find_cpuid_entry(vcpu, function, index);
-
-	if (!best) {
-		entry_found = false;
-		if (!check_limit)
-			goto out;
+	struct kvm_cpuid_entry2 *entry;
+	struct kvm_cpuid_entry2 *max;
+	bool found;
 
-		best = check_cpuid_limit(vcpu, function, index);
+	entry = kvm_find_cpuid_entry(vcpu, function, index);
+	found = entry;
+	/*
+	 * Intel CPUID semantics treats any query for an out-of-range
+	 * leaf as if the highest basic leaf (i.e. CPUID.0H:EAX) were
+	 * requested. AMD CPUID semantics returns all zeroes for any
+	 * undefined leaf, whether or not the leaf is in range.
+	 */
+	if (!entry && check_limit && !guest_cpuid_is_amd(vcpu) &&
+	    !cpuid_function_in_range(vcpu, function)) {
+		max = kvm_find_cpuid_entry(vcpu, 0, 0);
+		if (max) {
+			function = max->eax;
+			entry = kvm_find_cpuid_entry(vcpu, function, index);
+		}
 	}
-
-out:
-	if (best) {
-		*eax = best->eax;
-		*ebx = best->ebx;
-		*ecx = best->ecx;
-		*edx = best->edx;
-	} else
+	if (entry) {
+		*eax = entry->eax;
+		*ebx = entry->ebx;
+		*ecx = entry->ecx;
+		*edx = entry->edx;
+	} else {
 		*eax = *ebx = *ecx = *edx = 0;
-	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, entry_found);
-	return entry_found;
+		/*
+		 * When leaf 0BH or 1FH is defined, CL is pass-through
+		 * and EDX is always the x2APIC ID, even for undefined
+		 * subleaves. Index 1 will exist iff the leaf is
+		 * implemented, so we pass through CL iff leaf 1
+		 * exists. EDX can be copied from any existing index.
+		 */
+		if (function == 0xb || function == 0x1f) {
+			entry = kvm_find_cpuid_entry(vcpu, function, 1);
+			if (entry) {
+				*ecx = index & 0xff;
+				*edx = entry->edx;
+			}
+		}
+	}
+	trace_kvm_cpuid(function, *eax, *ebx, *ecx, *edx, found);
+	return found;
 }
 EXPORT_SYMBOL_GPL(kvm_cpuid);
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 3a3a6854dcca..87b0fcc23ef8 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -66,9 +66,10 @@
 #define X2APIC_BROADCAST		0xFFFFFFFFul
 
 static bool lapic_timer_advance_dynamic __read_mostly;
-#define LAPIC_TIMER_ADVANCE_ADJUST_MIN 100
-#define LAPIC_TIMER_ADVANCE_ADJUST_MAX 5000
-#define LAPIC_TIMER_ADVANCE_ADJUST_INIT 1000
+#define LAPIC_TIMER_ADVANCE_ADJUST_MIN	100	/* clock cycles */
+#define LAPIC_TIMER_ADVANCE_ADJUST_MAX	10000	/* clock cycles */
+#define LAPIC_TIMER_ADVANCE_NS_INIT	1000
+#define LAPIC_TIMER_ADVANCE_NS_MAX     5000
 /* step-by-step approximation to mitigate fluctuation */
 #define LAPIC_TIMER_ADVANCE_ADJUST_STEP 8
 
@@ -1504,8 +1505,8 @@ static inline void adjust_lapic_timer_advance(struct kvm_vcpu *vcpu,
 		timer_advance_ns += ns/LAPIC_TIMER_ADVANCE_ADJUST_STEP;
 	}
 
-	if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_ADJUST_MAX))
-		timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
+	if (unlikely(timer_advance_ns > LAPIC_TIMER_ADVANCE_NS_MAX))
+		timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
 	apic->lapic_timer.timer_advance_ns = timer_advance_ns;
 }
 
@@ -2302,7 +2303,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu, int timer_advance_ns)
 		     HRTIMER_MODE_ABS_HARD);
 	apic->lapic_timer.timer.function = apic_timer_fn;
 	if (timer_advance_ns == -1) {
-		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_ADJUST_INIT;
+		apic->lapic_timer.timer_advance_ns = LAPIC_TIMER_ADVANCE_NS_INIT;
 		lapic_timer_advance_dynamic = true;
 	} else {
 		apic->lapic_timer.timer_advance_ns = timer_advance_ns;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5269aa057dfa..24c23c66b226 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -83,7 +83,17 @@ module_param(dbg, bool, 0644);
 #define PTE_PREFETCH_NUM		8
 
 #define PT_FIRST_AVAIL_BITS_SHIFT 10
-#define PT64_SECOND_AVAIL_BITS_SHIFT 52
+#define PT64_SECOND_AVAIL_BITS_SHIFT 54
+
+/*
+ * The mask used to denote special SPTEs, which can be either MMIO SPTEs or
+ * Access Tracking SPTEs.
+ */
+#define SPTE_SPECIAL_MASK (3ULL << 52)
+#define SPTE_AD_ENABLED_MASK (0ULL << 52)
+#define SPTE_AD_DISABLED_MASK (1ULL << 52)
+#define SPTE_AD_WRPROT_ONLY_MASK (2ULL << 52)
+#define SPTE_MMIO_MASK (3ULL << 52)
 
 #define PT64_LEVEL_BITS 9
 
@@ -219,12 +229,11 @@ static u64 __read_mostly shadow_present_mask;
 static u64 __read_mostly shadow_me_mask;
 
 /*
- * SPTEs used by MMUs without A/D bits are marked with shadow_acc_track_value.
- * Non-present SPTEs with shadow_acc_track_value set are in place for access
- * tracking.
+ * SPTEs used by MMUs without A/D bits are marked with SPTE_AD_DISABLED_MASK;
+ * shadow_acc_track_mask is the set of bits to be cleared in non-accessed
+ * pages.
  */
 static u64 __read_mostly shadow_acc_track_mask;
-static const u64 shadow_acc_track_value = SPTE_SPECIAL_MASK;
 
 /*
  * The mask/shift to use for saving the original R/X bits when marking the PTE
@@ -304,7 +313,7 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask, u64 mmio_value, u64 access_mask)
 {
 	BUG_ON((u64)(unsigned)access_mask != access_mask);
 	BUG_ON((mmio_mask & mmio_value) != mmio_value);
-	shadow_mmio_value = mmio_value | SPTE_SPECIAL_MASK;
+	shadow_mmio_value = mmio_value | SPTE_MMIO_MASK;
 	shadow_mmio_mask = mmio_mask | SPTE_SPECIAL_MASK;
 	shadow_mmio_access_mask = access_mask;
 }
@@ -320,10 +329,27 @@ static inline bool sp_ad_disabled(struct kvm_mmu_page *sp)
 	return sp->role.ad_disabled;
 }
 
+static inline bool kvm_vcpu_ad_need_write_protect(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * When using the EPT page-modification log, the GPAs in the log
+	 * would come from L2 rather than L1.  Therefore, we need to rely
+	 * on write protection to record dirty pages.  This also bypasses
+	 * PML, since writes now result in a vmexit.
+	 */
+	return vcpu->arch.mmu == &vcpu->arch.guest_mmu;
+}
+
 static inline bool spte_ad_enabled(u64 spte)
 {
 	MMU_WARN_ON(is_mmio_spte(spte));
-	return !(spte & shadow_acc_track_value);
+	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_DISABLED_MASK;
+}
+
+static inline bool spte_ad_need_write_protect(u64 spte)
+{
+	MMU_WARN_ON(is_mmio_spte(spte));
+	return (spte & SPTE_SPECIAL_MASK) != SPTE_AD_ENABLED_MASK;
 }
 
 static inline u64 spte_shadow_accessed_mask(u64 spte)
@@ -461,7 +487,7 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 {
 	BUG_ON(!dirty_mask != !accessed_mask);
 	BUG_ON(!accessed_mask && !acc_track_mask);
-	BUG_ON(acc_track_mask & shadow_acc_track_value);
+	BUG_ON(acc_track_mask & SPTE_SPECIAL_MASK);
 
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
@@ -1589,16 +1615,16 @@ static bool spte_clear_dirty(u64 *sptep)
 
 	rmap_printk("rmap_clear_dirty: spte %p %llx\n", sptep, *sptep);
 
+	MMU_WARN_ON(!spte_ad_enabled(spte));
 	spte &= ~shadow_dirty_mask;
-
 	return mmu_spte_update(sptep, spte);
 }
 
-static bool wrprot_ad_disabled_spte(u64 *sptep)
+static bool spte_wrprot_for_clear_dirty(u64 *sptep)
 {
 	bool was_writable = test_and_clear_bit(PT_WRITABLE_SHIFT,
 					       (unsigned long *)sptep);
-	if (was_writable)
+	if (was_writable && !spte_ad_enabled(*sptep))
 		kvm_set_pfn_dirty(spte_to_pfn(*sptep));
 
 	return was_writable;
@@ -1617,10 +1643,10 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head)
 	bool flush = false;
 
 	for_each_rmap_spte(rmap_head, &iter, sptep)
-		if (spte_ad_enabled(*sptep))
-			flush |= spte_clear_dirty(sptep);
+		if (spte_ad_need_write_protect(*sptep))
+			flush |= spte_wrprot_for_clear_dirty(sptep);
 		else
-			flush |= wrprot_ad_disabled_spte(sptep);
+			flush |= spte_clear_dirty(sptep);
 
 	return flush;
 }
@@ -1631,6 +1657,11 @@ static bool spte_set_dirty(u64 *sptep)
 
 	rmap_printk("rmap_set_dirty: spte %p %llx\n", sptep, *sptep);
 
+	/*
+	 * Similar to the !kvm_x86_ops->slot_disable_log_dirty case,
+	 * do not bother adding back write access to pages marked
+	 * SPTE_AD_WRPROT_ONLY_MASK.
+	 */
 	spte |= shadow_dirty_mask;
 
 	return mmu_spte_update(sptep, spte);
@@ -2622,7 +2653,7 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
 	       shadow_user_mask | shadow_x_mask | shadow_me_mask;
 
 	if (sp_ad_disabled(sp))
-		spte |= shadow_acc_track_value;
+		spte |= SPTE_AD_DISABLED_MASK;
 	else
 		spte |= shadow_accessed_mask;
 
@@ -2968,7 +2999,9 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 
 	sp = page_header(__pa(sptep));
 	if (sp_ad_disabled(sp))
-		spte |= shadow_acc_track_value;
+		spte |= SPTE_AD_DISABLED_MASK;
+	else if (kvm_vcpu_ad_need_write_protect(vcpu))
+		spte |= SPTE_AD_WRPROT_ONLY_MASK;
 
 	/*
 	 * For the EPT case, shadow_present_mask is 0 if hardware
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 41abc62c9a8a..e76eb4f07f6c 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2610,7 +2610,7 @@ static int nested_check_vm_entry_controls(struct kvm_vcpu *vcpu,
 
 		/* VM-entry exception error code */
 		if (CC(has_error_code &&
-		       vmcs12->vm_entry_exception_error_code & GENMASK(31, 15)))
+		       vmcs12->vm_entry_exception_error_code & GENMASK(31, 16)))
 			return -EINVAL;
 
 		/* VM-entry interruption-info field: reserved bits */
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 4dea0e0e7e39..3e9c059099e9 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -262,6 +262,7 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct x86_pmu_capability x86_pmu;
 	struct kvm_cpuid_entry2 *entry;
 	union cpuid10_eax eax;
 	union cpuid10_edx edx;
@@ -283,8 +284,10 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	if (!pmu->version)
 		return;
 
+	perf_get_x86_pmu_capability(&x86_pmu);
+
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
-					INTEL_PMC_MAX_GENERIC);
+					 x86_pmu.num_counters_gp);
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
 	pmu->available_event_types = ~entry->ebx &
 					((1ull << eax.split.mask_length) - 1);
@@ -294,7 +297,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	} else {
 		pmu->nr_arch_fixed_counters =
 			min_t(int, edx.split.num_counters_fixed,
-				INTEL_PMC_MAX_FIXED);
+			      x86_pmu.num_counters_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index d4575ffb3cec..e7970a2e8eae 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -209,6 +209,11 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 	struct page *page;
 	unsigned int i;
 
+	if (!boot_cpu_has_bug(X86_BUG_L1TF)) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+		return 0;
+	}
+
 	if (!enable_ept) {
 		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
 		return 0;
@@ -7995,12 +8000,10 @@ static int __init vmx_init(void)
 	 * contain 'auto' which will be turned into the default 'cond'
 	 * mitigation mode.
 	 */
-	if (boot_cpu_has(X86_BUG_L1TF)) {
-		r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
-		if (r) {
-			vmx_exit();
-			return r;
-		}
+	r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+	if (r) {
+		vmx_exit();
+		return r;
 	}
 
 #ifdef CONFIG_KEXEC_CORE
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0ed07d8d2caa..661e2bf38526 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -92,8 +92,8 @@ u64 __read_mostly efer_reserved_bits = ~((u64)(EFER_SCE | EFER_LME | EFER_LMA));
 static u64 __read_mostly efer_reserved_bits = ~((u64)EFER_SCE);
 #endif
 
-#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
-#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
+#define VM_STAT(x, ...) offsetof(struct kvm, stat.x), KVM_STAT_VM, ## __VA_ARGS__
+#define VCPU_STAT(x, ...) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU, ## __VA_ARGS__
 
 #define KVM_X2APIC_API_VALID_FLAGS (KVM_X2APIC_API_USE_32BIT_IDS | \
                                     KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK)
@@ -212,7 +212,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "mmu_cache_miss", VM_STAT(mmu_cache_miss) },
 	{ "mmu_unsync", VM_STAT(mmu_unsync) },
 	{ "remote_tlb_flush", VM_STAT(remote_tlb_flush) },
-	{ "largepages", VM_STAT(lpages) },
+	{ "largepages", VM_STAT(lpages, .mode = 0444) },
 	{ "max_mmu_page_hash_collisions",
 		VM_STAT(max_mmu_page_hash_collisions) },
 	{ NULL }
@@ -885,34 +885,42 @@ int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 }
 EXPORT_SYMBOL_GPL(kvm_set_xcr);
 
-int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+static int kvm_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
-				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
-
 	if (cr4 & CR4_RESERVED_BITS)
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) && (cr4 & X86_CR4_OSXSAVE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMEP) && (cr4 & X86_CR4_SMEP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SMAP) && (cr4 & X86_CR4_SMAP))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_FSGSBASE) && (cr4 & X86_CR4_FSGSBASE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_PKU) && (cr4 & X86_CR4_PKE))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_LA57) && (cr4 & X86_CR4_LA57))
-		return 1;
+		return -EINVAL;
 
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_UMIP) && (cr4 & X86_CR4_UMIP))
+		return -EINVAL;
+
+	return 0;
+}
+
+int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+	unsigned long old_cr4 = kvm_read_cr4(vcpu);
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP | X86_CR4_PKE;
+
+	if (kvm_valid_cr4(vcpu, cr4))
 		return 1;
 
 	if (is_long_mode(vcpu)) {
@@ -1161,13 +1169,6 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_PERFCTR0 + 12, MSR_ARCH_PERFMON_PERFCTR0 + 13,
 	MSR_ARCH_PERFMON_PERFCTR0 + 14, MSR_ARCH_PERFMON_PERFCTR0 + 15,
 	MSR_ARCH_PERFMON_PERFCTR0 + 16, MSR_ARCH_PERFMON_PERFCTR0 + 17,
-	MSR_ARCH_PERFMON_PERFCTR0 + 18, MSR_ARCH_PERFMON_PERFCTR0 + 19,
-	MSR_ARCH_PERFMON_PERFCTR0 + 20, MSR_ARCH_PERFMON_PERFCTR0 + 21,
-	MSR_ARCH_PERFMON_PERFCTR0 + 22, MSR_ARCH_PERFMON_PERFCTR0 + 23,
-	MSR_ARCH_PERFMON_PERFCTR0 + 24, MSR_ARCH_PERFMON_PERFCTR0 + 25,
-	MSR_ARCH_PERFMON_PERFCTR0 + 26, MSR_ARCH_PERFMON_PERFCTR0 + 27,
-	MSR_ARCH_PERFMON_PERFCTR0 + 28, MSR_ARCH_PERFMON_PERFCTR0 + 29,
-	MSR_ARCH_PERFMON_PERFCTR0 + 30, MSR_ARCH_PERFMON_PERFCTR0 + 31,
 	MSR_ARCH_PERFMON_EVENTSEL0, MSR_ARCH_PERFMON_EVENTSEL1,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 2, MSR_ARCH_PERFMON_EVENTSEL0 + 3,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 4, MSR_ARCH_PERFMON_EVENTSEL0 + 5,
@@ -1177,13 +1178,6 @@ static u32 msrs_to_save[] = {
 	MSR_ARCH_PERFMON_EVENTSEL0 + 12, MSR_ARCH_PERFMON_EVENTSEL0 + 13,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 14, MSR_ARCH_PERFMON_EVENTSEL0 + 15,
 	MSR_ARCH_PERFMON_EVENTSEL0 + 16, MSR_ARCH_PERFMON_EVENTSEL0 + 17,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 18, MSR_ARCH_PERFMON_EVENTSEL0 + 19,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 20, MSR_ARCH_PERFMON_EVENTSEL0 + 21,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 22, MSR_ARCH_PERFMON_EVENTSEL0 + 23,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 24, MSR_ARCH_PERFMON_EVENTSEL0 + 25,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 26, MSR_ARCH_PERFMON_EVENTSEL0 + 27,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 28, MSR_ARCH_PERFMON_EVENTSEL0 + 29,
-	MSR_ARCH_PERFMON_EVENTSEL0 + 30, MSR_ARCH_PERFMON_EVENTSEL0 + 31,
 };
 
 static unsigned num_msrs_to_save;
@@ -5097,13 +5091,14 @@ out:
 
 static void kvm_init_msr_list(void)
 {
+	struct x86_pmu_capability x86_pmu;
 	u32 dummy[2];
 	unsigned i, j;
 
 	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
 			 "Please update the fixed PMCs in msrs_to_save[]");
-	BUILD_BUG_ON_MSG(INTEL_PMC_MAX_GENERIC != 32,
-			 "Please update the generic perfctr/eventsel MSRs in msrs_to_save[]");
+
+	perf_get_x86_pmu_capability(&x86_pmu);
 
 	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
 		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
@@ -5145,6 +5140,15 @@ static void kvm_init_msr_list(void)
 				intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2)
 				continue;
 			break;
+		case MSR_ARCH_PERFMON_PERFCTR0 ... MSR_ARCH_PERFMON_PERFCTR0 + 17:
+			if (msrs_to_save[i] - MSR_ARCH_PERFMON_PERFCTR0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
+			break;
+		case MSR_ARCH_PERFMON_EVENTSEL0 ... MSR_ARCH_PERFMON_EVENTSEL0 + 17:
+			if (msrs_to_save[i] - MSR_ARCH_PERFMON_EVENTSEL0 >=
+			    min(INTEL_PMC_MAX_GENERIC, x86_pmu.num_counters_gp))
+				continue;
 		}
 		default:
 			break;
@@ -8714,10 +8718,6 @@ EXPORT_SYMBOL_GPL(kvm_task_switch);
 
 static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 {
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
-			(sregs->cr4 & X86_CR4_OSXSAVE))
-		return  -EINVAL;
-
 	if ((sregs->efer & EFER_LME) && (sregs->cr0 & X86_CR0_PG)) {
 		/*
 		 * When EFER.LME and CR0.PG are set, the processor is in
@@ -8736,7 +8736,7 @@ static int kvm_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 			return -EINVAL;
 	}
 
-	return 0;
+	return kvm_valid_cr4(vcpu, sregs->cr4);
 }
 
 static int __set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
diff --git a/arch/x86/xen/efi.c b/arch/x86/xen/efi.c
index 0d3365cb64de..a04551ee5568 100644
--- a/arch/x86/xen/efi.c
+++ b/arch/x86/xen/efi.c
@@ -57,19 +57,7 @@ static efi_system_table_t __init *xen_efi_probe(void)
 		return NULL;
 
 	/* Here we know that Xen runs on EFI platform. */
-
-	efi.get_time                 = xen_efi_get_time;
-	efi.set_time                 = xen_efi_set_time;
-	efi.get_wakeup_time          = xen_efi_get_wakeup_time;
-	efi.set_wakeup_time          = xen_efi_set_wakeup_time;
-	efi.get_variable             = xen_efi_get_variable;
-	efi.get_next_variable        = xen_efi_get_next_variable;
-	efi.set_variable             = xen_efi_set_variable;
-	efi.query_variable_info      = xen_efi_query_variable_info;
-	efi.update_capsule           = xen_efi_update_capsule;
-	efi.query_capsule_caps       = xen_efi_query_capsule_caps;
-	efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
-	efi.reset_system             = xen_efi_reset_system;
+	xen_efi_runtime_setup();
 
 	efi_systab_xen.tables = info->cfg.addr;
 	efi_systab_xen.nr_tables = info->cfg.nent;