Merge branch 'x86/cpu' into x86/asm, to pick up dependent commits

Signed-off-by: Ingo Molnar <mingo@kernel.org>

130 files changed, 1116 insertions, 1532 deletions

diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1815748f5d2a..bae5edf348ef 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -381,7 +381,7 @@ void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
 void iounmap(volatile void __iomem *io_addr);
 #define iounmap iounmap
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size);
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
 #define arch_memremap_wb arch_memremap_wb
 
 /*
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 89f1c97f3079..748698e91a4b 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -436,7 +436,7 @@ void __arm_iomem_set_ro(void __iomem *ptr, size_t size)
 	set_memory_ro((unsigned long)ptr, PAGE_ALIGN(size) / PAGE_SIZE);
 }
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (__force void *)arch_ioremap_caller(phys_addr, size,
 						   MT_MEMORY_RW,
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 1a8f6914ee59..d638cc87807e 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -248,7 +248,7 @@ void __iomem *pci_remap_cfgspace(resource_size_t res_cookie, size_t size)
 EXPORT_SYMBOL_GPL(pci_remap_cfgspace);
 #endif
 
-void *arch_memremap_wb(phys_addr_t phys_addr, size_t size)
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
 {
 	return (void *)phys_addr;
 }
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index e4517f47d519..eb9470a00e54 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -226,7 +226,6 @@
 };
 
 &uart5 {
-	pinctrl-0 = <&uart5_xfer>;
 	rts-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index ae050cc6cd05..e80412abec08 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -396,6 +396,12 @@
 	status = "okay";
 };
 
+&uart5 {
+	/delete-property/ dmas;
+	/delete-property/ dma-names;
+	pinctrl-0 = <&uart5_xfer>;
+};
+
 /* Mule UCAN */
 &usb_host0_ehci {
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
index 67c246ad8b8c..ec2ce894da1f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
@@ -17,8 +17,7 @@
 
 &gmac2io {
 	phy-handle = <&yt8531c>;
-	tx_delay = <0x19>;
-	rx_delay = <0x05>;
+	phy-mode = "rgmii-id";
 	status = "okay";
 
 	mdio {
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
index 324a8e951f7e..846b931e16d2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
@@ -15,6 +15,7 @@
 
 &gmac2io {
 	phy-handle = <&rtl8211e>;
+	phy-mode = "rgmii";
 	tx_delay = <0x24>;
 	rx_delay = <0x18>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
index 4f193704e5dc..09508e324a28 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
@@ -109,7 +109,6 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clk>, <&gmac_clk>;
 	clock_in_out = "input";
-	phy-mode = "rgmii";
 	phy-supply = <&vcc_io>;
 	pinctrl-0 = <&rgmiim1_pins>;
 	pinctrl-names = "default";
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
index 988e6ca32fac..a9ea4b0daa04 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
@@ -22,11 +22,11 @@
 	};
 
 	/* EC turns on w/ pp900_usb_en */
-	pp900_usb: pp900-ap {
+	pp900_usb: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pcie_en */
-	pp900_pcie: pp900-ap {
+	pp900_pcie: regulator-pp900-ap {
 	};
 
 	pp3000: regulator-pp3000 {
@@ -126,7 +126,7 @@
 	};
 
 	/* Always on; plain and simple */
-	pp3000_ap: pp3000_emmc: pp3000 {
+	pp3000_ap: pp3000_emmc: regulator-pp3000 {
 	};
 
 	pp1500_ap_io: regulator-pp1500-ap-io {
@@ -160,7 +160,7 @@
 	};
 
 	/* EC turns on w/ pp3300_usb_en_l */
-	pp3300_usb: pp3300 {
+	pp3300_usb: regulator-pp3300 {
 	};
 
 	/* gpio is shared with pp1800_pcie and pinctrl is set there */
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
index 19b23b438965..5e068377a0a2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
@@ -92,7 +92,7 @@
 	};
 
 	/* EC turns on pp1800_s3_en */
-	pp1800_s3: pp1800 {
+	pp1800_s3: regulator-pp1800 {
 	};
 
 	/* pp3300 children, sorted by name */
@@ -109,11 +109,11 @@
 	};
 
 	/* EC turns on pp3300_s0_en */
-	pp3300_s0: pp3300 {
+	pp3300_s0: regulator-pp3300 {
 	};
 
 	/* EC turns on pp3300_s3_en */
-	pp3300_s3: pp3300 {
+	pp3300_s3: regulator-pp3300 {
 	};
 
 	/*
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index 6d9e60b01225..7eca1da78cff 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -189,39 +189,39 @@
 	};
 
 	/* EC turns on w/ pp900_ddrpll_en */
-	pp900_ddrpll: pp900-ap {
+	pp900_ddrpll: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pll_en */
-	pp900_pll: pp900-ap {
+	pp900_pll: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pmu_en */
-	pp900_pmu: pp900-ap {
+	pp900_pmu: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp1800_s0_en_l */
-	pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: pp1800 {
+	pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_avdd_en_l */
-	pp1800_avdd: pp1800 {
+	pp1800_avdd: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_lid_en_l */
-	pp1800_lid: pp1800_mic: pp1800 {
+	pp1800_lid: pp1800_mic: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ lpddr_pwr_en */
-	pp1800_lpddr: pp1800 {
+	pp1800_lpddr: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_pmu_en_l */
-	pp1800_pmu: pp1800 {
+	pp1800_pmu: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_usb_en_l */
-	pp1800_usb: pp1800 {
+	pp1800_usb: regulator-pp1800 {
 	};
 
 	pp3000_sd_slot: regulator-pp3000-sd-slot {
@@ -259,11 +259,11 @@
 	};
 
 	/* EC turns on w/ pp3300_trackpad_en_l */
-	pp3300_trackpad: pp3300-trackpad {
+	pp3300_trackpad: regulator-pp3300-trackpad {
 	};
 
 	/* EC turns on w/ usb_a_en */
-	pp5000_usb_a_vbus: pp5000 {
+	pp5000_usb_a_vbus: regulator-pp5000 {
 	};
 
 	ap_rtc_clk: ap-rtc-clk {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
index 8cfa30837ce7..c3abdfb04f8f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
@@ -549,10 +549,10 @@
 	mmu600_pcie: iommu@fc900000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfc900000 0x0 0x200000>;
-		interrupts = <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 369 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 371 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 374 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 367 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 	};
@@ -560,10 +560,10 @@
 	mmu600_php: iommu@fcb00000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfcb00000 0x0 0x200000>;
-		interrupts = <GIC_SPI 381 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 383 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 386 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 381 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 383 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 386 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 379 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 		status = "disabled";
@@ -2668,9 +2668,9 @@
 		rockchip,hw-tshut-temp = <120000>;
 		rockchip,hw-tshut-mode = <0>; /* tshut mode 0:CRU 1:GPIO */
 		rockchip,hw-tshut-polarity = <0>; /* tshut polarity 0:LOW 1:HIGH */
-		pinctrl-0 = <&tsadc_gpio_func>;
-		pinctrl-1 = <&tsadc_shut>;
-		pinctrl-names = "gpio", "otpout";
+		pinctrl-0 = <&tsadc_shut_org>;
+		pinctrl-1 = <&tsadc_gpio_func>;
+		pinctrl-names = "default", "sleep";
 		#thermal-sensor-cells = <1>;
 		status = "disabled";
 	};
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
index 92f0ed83c990..bc6b43a77153 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
@@ -113,7 +113,7 @@
 		compatible = "regulator-fixed";
 		regulator-name = "vcc3v3_lcd";
 		enable-active-high;
-		gpio = <&gpio1 RK_PC4 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&lcdpwr_en>;
 		vin-supply = <&vcc3v3_sys>;
@@ -241,7 +241,7 @@
 &pinctrl {
 	lcd {
 		lcdpwr_en: lcdpwr-en {
-			rockchip,pins = <1 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
+			rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
 		};
 
 		bl_en: bl-en {
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
index 4a950907ea6f..840b638af1c2 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
@@ -213,7 +213,6 @@
 		interrupt-names = "sys", "pmc", "msg", "legacy", "err",
 				  "dma0", "dma1", "dma2", "dma3";
 		max-link-speed = <3>;
-		iommus = <&mmu600_pcie 0x0000>;
 		num-lanes = <4>;
 		phys = <&pcie30phy>;
 		phy-names = "pcie-phy";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
index 672d748fcc67..f229cb49da68 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
@@ -23,3 +23,7 @@
 	vpcie3v3-supply = <&vcc3v3_pcie30>;
 	status = "okay";
 };
+
+&mmu600_pcie {
+	status = "disabled";
+};
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index cb7da4415599..1f25423de383 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1551,6 +1551,8 @@ CONFIG_PWM_VISCONTI=m
 CONFIG_SL28CPLD_INTC=y
 CONFIG_QCOM_PDC=y
 CONFIG_QCOM_MPM=y
+CONFIG_TI_SCI_INTR_IRQCHIP=y
+CONFIG_TI_SCI_INTA_IRQCHIP=y
 CONFIG_RESET_GPIO=m
 CONFIG_RESET_IMX7=y
 CONFIG_RESET_QCOM_AOSS=y
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index c6dff3e69539..07fbf5bf85a7 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,8 +42,8 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
@@ -76,12 +76,22 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 {
 	unsigned long stride = huge_page_size(hstate_vma(vma));
 
-	if (stride == PMD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 2);
-	else if (stride == PUD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 1);
-	else
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+	switch (stride) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		__flush_tlb_range(vma, start, end, PUD_SIZE, false, 1);
+		break;
+#endif
+	case CONT_PMD_SIZE:
+	case PMD_SIZE:
+		__flush_tlb_range(vma, start, end, PMD_SIZE, false, 2);
+		break;
+	case CONT_PTE_SIZE:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 3);
+		break;
+	default:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+	}
 }
 
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 8d94a6c0ed5c..c2417a424b98 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -119,7 +119,7 @@
 #define TCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
 #define TCR_EL2_T0SZ_MASK	0x3f
 #define TCR_EL2_MASK	(TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
-			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
+			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK)
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_DS		TCR_EL2_DS
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3a7ec98ef123..d919557af5e5 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1259,7 +1259,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 extern unsigned int __ro_after_init kvm_arm_vmid_bits;
 int __init kvm_arm_vmid_alloc_init(void);
 void __init kvm_arm_vmid_alloc_free(void);
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index b8e55a441282..0160b4924351 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -560,6 +560,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
 	/*
+	 * Ensure a VMID is allocated for the MMU before programming VTTBR_EL2,
+	 * which happens eagerly in VHE.
+	 *
+	 * Also, the VMID allocator only preserves VMIDs that are active at the
+	 * time of rollover, so KVM might need to grab a new VMID for the MMU if
+	 * this is called from kvm_sched_in().
+	 */
+	kvm_arm_vmid_update(&mmu->vmid);
+
+	/*
 	 * We guarantee that both TLBs and I-cache are private to each
 	 * vcpu. If detecting that a vcpu from the same VM has
 	 * previously run on the same physical CPU, call into the
@@ -1138,18 +1148,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
-		/*
-		 * The VMID allocator only tracks active VMIDs per
-		 * physical CPU, and therefore the VMID allocated may not be
-		 * preserved on VMID roll-over if the task was preempted,
-		 * making a thread's VMID inactive. So we need to call
-		 * kvm_arm_vmid_update() in non-premptible context.
-		 */
-		if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
-		    has_vhe())
-			__load_stage2(vcpu->arch.hw_mmu,
-				      vcpu->arch.hw_mmu->arch);
-
 		kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
@@ -1980,7 +1978,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
-	unsigned long tcr, ips;
+	unsigned long tcr;
 
 	/*
 	 * Calculate the raw per-cpu offset without a translation from the
@@ -1994,19 +1992,18 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	params->mair_el2 = read_sysreg(mair_el1);
 
 	tcr = read_sysreg(tcr_el1);
-	ips = FIELD_GET(TCR_IPS_MASK, tcr);
 	if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
+		tcr &= ~(TCR_HD | TCR_HA | TCR_A1 | TCR_T0SZ_MASK);
 		tcr |= TCR_EPD1_MASK;
 	} else {
+		unsigned long ips = FIELD_GET(TCR_IPS_MASK, tcr);
+
 		tcr &= TCR_EL2_MASK;
-		tcr |= TCR_EL2_RES1;
+		tcr |= TCR_EL2_RES1 | FIELD_PREP(TCR_EL2_PS_MASK, ips);
+		if (lpa2_is_enabled())
+			tcr |= TCR_EL2_DS;
 	}
-	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
-	tcr &= ~TCR_EL2_PS_MASK;
-	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips);
-	if (lpa2_is_enabled())
-		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index 806223b7022a..7fe8ba1a2851 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -135,11 +135,10 @@ void kvm_arm_vmid_clear_active(void)
 	atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
 }
 
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 {
 	unsigned long flags;
 	u64 vmid, old_active_vmid;
-	bool updated = false;
 
 	vmid = atomic64_read(&kvm_vmid->id);
 
@@ -157,21 +156,17 @@ bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 	if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
 	    0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
 					  old_active_vmid, vmid))
-		return false;
+		return;
 
 	raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
 
 	/* Check that our VMID belongs to the current generation. */
 	vmid = atomic64_read(&kvm_vmid->id);
-	if (!vmid_gen_match(vmid)) {
+	if (!vmid_gen_match(vmid))
 		vmid = new_vmid(kvm_vmid);
-		updated = true;
-	}
 
 	atomic64_set(this_cpu_ptr(&active_vmids), vmid);
 	raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
-
-	return updated;
 }
 
 /*
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 98a2a0e64e25..b3a7fafe8892 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -100,20 +100,11 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
-	int contig_ptes = 0;
+	int contig_ptes = 1;
 
 	*pgsize = size;
 
 	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		if (pud_sect_supported())
-			contig_ptes = 1;
-		break;
-#endif
-	case PMD_SIZE:
-		contig_ptes = 1;
-		break;
 	case CONT_PMD_SIZE:
 		*pgsize = PMD_SIZE;
 		contig_ptes = CONT_PMDS;
@@ -122,6 +113,8 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 		*pgsize = PAGE_SIZE;
 		contig_ptes = CONT_PTES;
 		break;
+	default:
+		WARN_ON(!__hugetlb_valid_size(size));
 	}
 
 	return contig_ptes;
@@ -163,24 +156,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = __ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
-
-		/*
-		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty or accessed bit for any page in the set,
-		 * so check them all.
-		 */
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = __ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += pgsize;
+		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -396,18 +388,13 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = __ptep_get(ptep);
-
-	if (!pte_cont(orig_pte))
-		return __ptep_get_and_clear(mm, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
+	ncontig = num_contig_ptes(sz, &pgsize);
 	return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 }
 
@@ -549,6 +536,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
@@ -558,7 +547,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9c0b8d9558fc..ccdef53872a0 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -279,12 +279,7 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-
-		/*
-		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
-		 * map randomization can be enabled by shrinking the IPA space.
-		 */
-		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -
diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index c8e4057734d0..4dc4b3e04225 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -36,7 +36,8 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = ptep_get(ptep);
@@ -51,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/mips/boot/tools/relocs.c b/arch/mips/boot/tools/relocs.c
index a88d66c46d7f..9863e1d5c62e 100644
--- a/arch/mips/boot/tools/relocs.c
+++ b/arch/mips/boot/tools/relocs.c
@@ -468,6 +468,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 			Elf_Sym *sym, const char *symname))
 {
 	int i;
+	struct section *extab_sec = sec_lookup("__ex_table");
+	int extab_index = extab_sec ? extab_sec - secs : -1;
 
 	/* Walk through the relocations */
 	for (i = 0; i < ehdr.e_shnum; i++) {
@@ -480,6 +482,9 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 		if (sec->shdr.sh_type != SHT_REL_TYPE)
 			continue;
 
+		if (sec->shdr.sh_info == extab_index)
+			continue;
+
 		sec_symtab  = sec->link;
 		sec_applies = &secs[sec->shdr.sh_info];
 		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index d0a86ce83de9..fbc71ddcf0f6 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -27,7 +27,8 @@ static inline int prepare_hugepage_range(struct file *file,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = *ptep;
@@ -42,13 +43,14 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * clear the huge pte entry firstly, so that the other smp threads will
 	 * not get old pte entry after finishing flush_tlb_page and before
 	 * setting new huge pte entry
 	 */
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 5b3a5429f71b..21e9ace17739 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -10,7 +10,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index e9d18cf25b79..a94fe546d434 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -126,7 +126,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t entry;
 
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index c3efacab4b94..aa90a048f319 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -77,9 +77,17 @@
 /*
  * With 4K page size the real_pte machinery is all nops.
  */
-#define __real_pte(e, p, o)		((real_pte_t){(e)})
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
+{
+	return (real_pte_t){pte};
+}
+
 #define __rpte_to_pte(r)	((r).pte)
-#define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
+
+static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
+{
+	return pte_val(__rpte_to_pte(rpte)) >> H_PAGE_F_GIX_SHIFT;
+}
 
 #define pte_iterate_hashed_subpages(rpte, psize, va, index, shift)       \
 	do {							         \
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index dad2e7980f24..86326587e58d 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -45,7 +45,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 }
@@ -55,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_hugetlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/powerpc/lib/code-patching.c b/arch/powerpc/lib/code-patching.c
index af97fbb3c257..f84e0337cc02 100644
--- a/arch/powerpc/lib/code-patching.c
+++ b/arch/powerpc/lib/code-patching.c
@@ -108,7 +108,7 @@ static int text_area_cpu_up(unsigned int cpu)
 	unsigned long addr;
 	int err;
 
-	area = get_vm_area(PAGE_SIZE, VM_ALLOC);
+	area = get_vm_area(PAGE_SIZE, 0);
 	if (!area) {
 		WARN_ONCE(1, "Failed to create text area for cpu %d\n",
 			cpu);
@@ -493,7 +493,9 @@ static int __do_patch_instructions_mm(u32 *addr, u32 *code, size_t len, bool rep
 
 	orig_mm = start_using_temp_mm(patching_mm);
 
+	kasan_disable_current();
 	err = __patch_instructions(patch_addr, code, len, repeat_instr);
+	kasan_enable_current();
 
 	/* context synchronisation performed by __patch_instructions */
 	stop_using_temp_mm(patching_mm, orig_mm);
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 4cadc56220fe..427c41dde643 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -231,7 +231,7 @@
 		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
 			       sc_prepend, sc_append,			\
 			       cas_prepend, cas_append,			\
-			       __ret, __ptr, (long), __old, __new);	\
+			       __ret, __ptr, (long)(int)(long), __old, __new);	\
 		break;							\
 	case 8:								\
 		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\
diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index 72be100afa23..90c86b115e00 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r])	\
 		_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r])	\
 	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
-	: [ov] "Jr" (oldval), [nv] "Jr" (newval)
+	: [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval)
 	: "memory");
 	__disable_user_access();
 
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index faf3624d8057..446126497768 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep);
+			      unsigned long addr, pte_t *ptep,
+			      unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/riscv/include/asm/io.h b/arch/riscv/include/asm/io.h
index 1c5c641075d2..0257f4aa7ff4 100644
--- a/arch/riscv/include/asm/io.h
+++ b/arch/riscv/include/asm/io.h
@@ -136,7 +136,7 @@ __io_writes_outs(outs, u64, q, __io_pbr(), __io_paw())
 #include <asm-generic/io.h>
 
 #ifdef CONFIG_MMU
-#define arch_memremap_wb(addr, size)	\
+#define arch_memremap_wb(addr, size, flags)	\
 	((__force void *)ioremap_prot((addr), (size), _PAGE_KERNEL))
 #endif
 
diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 2d40736fc37c..26b085dbdd07 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -108,11 +108,11 @@ int populate_cache_leaves(unsigned int cpu)
 	if (!np)
 		return -ENOENT;
 
-	if (of_property_read_bool(np, "cache-size"))
+	if (of_property_present(np, "cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-	if (of_property_read_bool(np, "i-cache-size"))
+	if (of_property_present(np, "i-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-	if (of_property_read_bool(np, "d-cache-size"))
+	if (of_property_present(np, "d-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 
 	prev = np;
@@ -125,11 +125,11 @@ int populate_cache_leaves(unsigned int cpu)
 			break;
 		if (level <= levels)
 			break;
-		if (of_property_read_bool(np, "cache-size"))
+		if (of_property_present(np, "cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-		if (of_property_read_bool(np, "i-cache-size"))
+		if (of_property_present(np, "i-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-		if (of_property_read_bool(np, "d-cache-size"))
+		if (of_property_present(np, "d-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 		levels = level;
 	}
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index c6ba750536c3..40ac72e407b6 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -479,7 +479,7 @@ static void __init riscv_resolve_isa(unsigned long *source_isa,
 			if (bit < RISCV_ISA_EXT_BASE)
 				*this_hwcap |= isa2hwcap[bit];
 		}
-	} while (loop && memcmp(prev_resolved_isa, resolved_isa, sizeof(prev_resolved_isa)));
+	} while (loop && !bitmap_equal(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX));
 }
 
 static void __init match_isa_ext(const char *name, const char *name_end, unsigned long *bitmap)
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f1793630fc51..4fe45daa6281 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -322,8 +322,8 @@ void __init setup_arch(char **cmdline_p)
 
 	riscv_init_cbo_blocksizes();
 	riscv_fill_hwcap();
-	init_rt_signal_env();
 	apply_boot_alternatives();
+	init_rt_signal_env();
 
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 94e905eea1de..08378fea3a11 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -215,12 +215,6 @@ static size_t get_rt_frame_size(bool cal_all)
 		if (cal_all || riscv_v_vstate_query(task_pt_regs(current)))
 			total_context_size += riscv_v_sc_size;
 	}
-	/*
-	 * Preserved a __riscv_ctx_hdr for END signal context header if an
-	 * extension uses __riscv_extra_ext_header
-	 */
-	if (total_context_size)
-		total_context_size += sizeof(struct __riscv_ctx_hdr);
 
 	frame_size += total_context_size;
 
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index a8085cd8215e..29ef9c2133a9 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -974,7 +974,6 @@ int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu,
 
 	if (imsic->vsfile_cpu >= 0) {
 		writel(iid, imsic->vsfile_va + IMSIC_MMIO_SETIPNUM_LE);
-		kvm_vcpu_kick(vcpu);
 	} else {
 		eix = &imsic->swfile->eix[iid / BITS_PER_TYPE(u64)];
 		set_bit(iid & (BITS_PER_TYPE(u64) - 1), eix->eip);
diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index dce667f4b6ab..3070bb31745d 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 #include <asm/sbi.h>
 #include <asm/kvm_vcpu_sbi.h>
 
@@ -79,12 +80,12 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
 	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
 	if (!target_vcpu)
 		return SBI_ERR_INVALID_PARAM;
-	if (!kvm_riscv_vcpu_stopped(target_vcpu))
-		return SBI_HSM_STATE_STARTED;
-	else if (vcpu->stat.generic.blocking)
+	if (kvm_riscv_vcpu_stopped(target_vcpu))
+		return SBI_HSM_STATE_STOPPED;
+	else if (target_vcpu->stat.generic.blocking)
 		return SBI_HSM_STATE_SUSPENDED;
 	else
-		return SBI_HSM_STATE_STOPPED;
+		return SBI_HSM_STATE_STARTED;
 }
 
 static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
@@ -109,7 +110,7 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		}
 		return 0;
 	case SBI_EXT_HSM_HART_SUSPEND:
-		switch (cp->a0) {
+		switch (lower_32_bits(cp->a0)) {
 		case SBI_HSM_SUSPEND_RET_DEFAULT:
 			kvm_riscv_vcpu_wfi(vcpu);
 			break;
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 9c2ab3dfa93a..5fbf3f94f1e8 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -21,7 +21,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	u64 next_cycle;
 
 	if (cp->a6 != SBI_EXT_TIME_SET_TIMER) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -51,9 +51,10 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 	unsigned long hmask = cp->a0;
 	unsigned long hbase = cp->a1;
+	unsigned long hart_bit = 0, sentmask = 0;
 
 	if (cp->a6 != SBI_EXT_IPI_SEND_IPI) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -62,15 +63,23 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (hbase != -1UL) {
 			if (tmp->vcpu_id < hbase)
 				continue;
-			if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+			hart_bit = tmp->vcpu_id - hbase;
+			if (hart_bit >= __riscv_xlen)
+				goto done;
+			if (!(hmask & (1UL << hart_bit)))
 				continue;
 		}
 		ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT);
 		if (ret < 0)
 			break;
+		sentmask |= 1UL << hart_bit;
 		kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD);
 	}
 
+done:
+	if (hbase != -1UL && (hmask ^ sentmask))
+		retdata->err_val = SBI_ERR_INVALID_PARAM;
+
 	return ret;
 }
 
diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c
index 5d55e08791fa..bc0ebba89003 100644
--- a/arch/riscv/kvm/vcpu_sbi_system.c
+++ b/arch/riscv/kvm/vcpu_sbi_system.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 
 #include <asm/kvm_vcpu_sbi.h>
 #include <asm/sbi.h>
@@ -19,7 +20,7 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	switch (funcid) {
 	case SBI_EXT_SUSP_SYSTEM_SUSPEND:
-		if (cp->a0 != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
+		if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
 			retdata->err_val = SBI_ERR_INVALID_PARAM;
 			return 0;
 		}
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 42314f093922..b4a78a4b35cf 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -293,7 +293,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 885bd1dd2c82..9276e0576d0a 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -86,7 +86,7 @@ static int cmma_test_essa(void)
 		: [reg1] "=&d" (reg1),
 		  [reg2] "=&a" (reg2),
 		  [rc] "+&d" (rc),
-		  [tmp] "=&d" (tmp),
+		  [tmp] "+&d" (tmp),
 		  "+Q" (get_lowcore()->program_new_psw),
 		  "=Q" (old)
 		: [psw_old] "a" (&old),
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 44f01a4bc810..80bdfbae6e5b 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -469,6 +469,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -874,6 +875,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 8bcd37edd3c9..449a0e996b96 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -459,6 +459,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -825,6 +826,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 7c52acaf9f82..663e87220e89 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -25,8 +25,16 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 #define __HAVE_ARCH_HUGE_PTEP_GET
 pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
+{
+	return __huge_ptep_get_and_clear(mm, addr, ptep);
+}
 
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
@@ -48,7 +56,7 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long address, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+	return __huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
 #define  __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -59,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 
 	if (changed) {
-		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+		__huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
@@ -69,7 +77,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+	pte_t pte = __huge_ptep_get_and_clear(mm, addr, ptep);
 
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d9ce199953de..2e568f175cd4 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -188,8 +188,8 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	return __rste_to_pte(pte_val(*ptep));
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get(mm, addr, ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index bdcf2a3b6c41..bd39b36e7bd6 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -8,7 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
+CFLAGS_sha256.o := -D__NO_FORTIFY
 
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
@@ -19,9 +19,11 @@ KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS += -D__DISABLE_EXPORTS
 
 # Since we link purgatory with -r unresolved symbols are not checked, so we
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index c714ca6a05aa..e7a9cdd498dc 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -20,7 +20,7 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index eee601a0d2cf..80504148d8a5 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -260,7 +260,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 79ea97d4797e..8be91974e786 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -440,25 +440,24 @@ void __init arch_cpu_finalize_init(void)
 	os_check_bugs();
 }
 
-void apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void apply_seal_endbr(s32 *start, s32 *end)
 {
 }
 
-void apply_retpolines(s32 *start, s32 *end, struct module *mod)
+void apply_retpolines(s32 *start, s32 *end)
 {
 }
 
-void apply_returns(s32 *start, s32 *end, struct module *mod)
+void apply_returns(s32 *start, s32 *end)
 {
 }
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 }
 
-void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			struct module *mod)
+void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 867ec8a4a9d2..79f6febd177f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -85,6 +85,7 @@ config X86
 	select ARCH_HAS_DMA_OPS			if GART_IOMMU || XEN
 	select ARCH_HAS_EARLY_DEBUG		if KGDB
 	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_EXECMEM_ROX		if X86_64
 	select ARCH_HAS_FAST_MULTIPLIER
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_GCOV_PROFILE_ALL
@@ -132,7 +133,7 @@ config X86
 	select ARCH_SUPPORTS_AUTOFDO_CLANG
 	select ARCH_SUPPORTS_PROPELLER_CLANG    if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
-	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CMPXCHG64
+	select ARCH_USE_CMPXCHG_LOCKREF		if X86_CX8
 	select ARCH_USE_MEMTEST
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
@@ -232,7 +233,7 @@ config X86
 	select HAVE_SAMPLE_FTRACE_DIRECT_MULTI	if X86_64
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select HAVE_EISA
+	select HAVE_EISA			if X86_32
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
@@ -277,7 +278,7 @@ config X86
 	select HAVE_PCI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
-	select MMU_GATHER_RCU_TABLE_FREE	if PARAVIRT
+	select MMU_GATHER_RCU_TABLE_FREE
 	select MMU_GATHER_MERGE_VMAS
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_REGS_AND_STACK_ACCESS_API
@@ -521,12 +522,6 @@ config X86_FRED
 	  ring transitions and exception/interrupt handling if the
 	  system supports it.
 
-config X86_BIGSMP
-	bool "Support for big SMP systems with more than 8 CPUs"
-	depends on SMP && X86_32
-	help
-	  This option is needed for the systems that have more than 8 CPUs.
-
 config X86_EXTENDED_PLATFORM
 	bool "Support for extended (non-PC) x86 platforms"
 	default y
@@ -544,13 +539,12 @@ config X86_EXTENDED_PLATFORM
 		AMD Elan
 		RDC R-321x SoC
 		SGI 320/540 (Visual Workstation)
-		STA2X11-based (e.g. Northville)
-		Moorestown MID devices
 
 	  64-bit platforms (CONFIG_64BIT=y):
 		Numascale NumaChip
 		ScaleMP vSMP
 		SGI Ultraviolet
+		Merrifield/Moorefield MID devices
 
 	  If you have one of these systems, or if you want to build a
 	  generic distribution kernel, say Y here - otherwise say N.
@@ -595,8 +589,31 @@ config X86_UV
 	  This option is needed in order to support SGI Ultraviolet systems.
 	  If you don't have one of these, you should say N here.
 
-# Following is an alphabetically sorted list of 32 bit extended platforms
-# Please maintain the alphabetic order if and when there are additions
+config X86_INTEL_MID
+	bool "Intel Z34xx/Z35xx MID platform support"
+	depends on X86_EXTENDED_PLATFORM
+	depends on X86_PLATFORM_DEVICES
+	depends on PCI
+	depends on X86_64 || (EXPERT && PCI_GOANY)
+	depends on X86_IO_APIC
+	select I2C
+	select DW_APB_TIMER
+	select INTEL_SCU_PCI
+	help
+	  Select to build a kernel capable of supporting 64-bit Intel MID
+	  (Mobile Internet Device) platform systems which do not have
+	  the PCI legacy interfaces.
+
+	  The only supported devices are the 22nm Merrified (Z34xx)
+	  and Moorefield (Z35xx) SoC used in the Intel Edison board and
+	  a small number of Android devices such as the Asus Zenfone 2,
+	  Asus FonePad 8 and Dell Venue 7.
+
+	  If you are building for a PC class system or non-MID tablet
+	  SoCs like Bay Trail (Z36xx/Z37xx), say N here.
+
+	  Intel MID platforms are based on an Intel processor and chipset which
+	  consume less power than most of the x86 derivatives.
 
 config X86_GOLDFISH
 	bool "Goldfish (Virtual Platform)"
@@ -606,6 +623,9 @@ config X86_GOLDFISH
 	  for Android development. Unless you are building for the Android
 	  Goldfish emulator say N here.
 
+# Following is an alphabetically sorted list of 32 bit extended platforms
+# Please maintain the alphabetic order if and when there are additions
+
 config X86_INTEL_CE
 	bool "CE4100 TV platform"
 	depends on PCI
@@ -621,24 +641,6 @@ config X86_INTEL_CE
 	  This option compiles in support for the CE4100 SOC for settop
 	  boxes and media devices.
 
-config X86_INTEL_MID
-	bool "Intel MID platform support"
-	depends on X86_EXTENDED_PLATFORM
-	depends on X86_PLATFORM_DEVICES
-	depends on PCI
-	depends on X86_64 || (PCI_GOANY && X86_32)
-	depends on X86_IO_APIC
-	select I2C
-	select DW_APB_TIMER
-	select INTEL_SCU_PCI
-	help
-	  Select to build a kernel capable of supporting Intel MID (Mobile
-	  Internet Device) platform systems which do not have the PCI legacy
-	  interfaces. If you are building for a PC class system say N here.
-
-	  Intel MID platforms are based on an Intel processor and chipset which
-	  consume less power than most of the x86 derivatives.
-
 config X86_INTEL_QUARK
 	bool "Intel Quark platform support"
 	depends on X86_32
@@ -720,18 +722,6 @@ config X86_RDC321X
 	  as R-8610-(G).
 	  If you don't have one of these chips, you should say N here.
 
-config X86_32_NON_STANDARD
-	bool "Support non-standard 32-bit SMP architectures"
-	depends on X86_32 && SMP
-	depends on X86_EXTENDED_PLATFORM
-	help
-	  This option compiles in the bigsmp and STA2X11 default
-	  subarchitectures.  It is intended for a generic binary
-	  kernel. If you select them all, kernel will probe it one by
-	  one and will fallback to default.
-
-# Alphabetically sorted list of Non standard 32 bit platforms
-
 config X86_SUPPORTS_MEMORY_FAILURE
 	def_bool y
 	# MCE code calls memory_failure():
@@ -741,19 +731,6 @@ config X86_SUPPORTS_MEMORY_FAILURE
 	depends on X86_64 || !SPARSEMEM
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 
-config STA2X11
-	bool "STA2X11 Companion Chip Support"
-	depends on X86_32_NON_STANDARD && PCI
-	select SWIOTLB
-	select MFD_STA2X11
-	select GPIOLIB
-	help
-	  This adds support for boards based on the STA2X11 IO-Hub,
-	  a.k.a. "ConneXt". The chip is used in place of the standard
-	  PC chipset, so all "standard" peripherals are missing. If this
-	  option is selected the kernel will still be able to boot on
-	  standard PC machines.
-
 config X86_32_IRIS
 	tristate "Eurobraille/Iris poweroff module"
 	depends on X86_32
@@ -1003,8 +980,7 @@ config NR_CPUS_RANGE_BEGIN
 config NR_CPUS_RANGE_END
 	int
 	depends on X86_32
-	default   64 if  SMP &&  X86_BIGSMP
-	default    8 if  SMP && !X86_BIGSMP
+	default    8 if  SMP
 	default    1 if !SMP
 
 config NR_CPUS_RANGE_END
@@ -1017,7 +993,6 @@ config NR_CPUS_RANGE_END
 config NR_CPUS_DEFAULT
 	int
 	depends on X86_32
-	default   32 if  X86_BIGSMP
 	default    8 if  SMP
 	default    1 if !SMP
 
@@ -1093,7 +1068,7 @@ config UP_LATE_INIT
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors" if !PCI_MSI
 	default PCI_MSI
-	depends on X86_32 && !SMP && !X86_32_NON_STANDARD
+	depends on X86_32 && !SMP
 	help
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -1118,7 +1093,7 @@ config X86_UP_IOAPIC
 
 config X86_LOCAL_APIC
 	def_bool y
-	depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_APIC || PCI_MSI
+	depends on X86_64 || SMP || X86_UP_APIC || PCI_MSI
 	select IRQ_DOMAIN_HIERARCHY
 
 config ACPI_MADT_WAKEUP
@@ -1386,15 +1361,11 @@ config X86_CPUID
 	  with major 203 and minors 0 to 31 for /dev/cpu/0/cpuid to
 	  /dev/cpu/31/cpuid.
 
-choice
-	prompt "High Memory Support"
-	default HIGHMEM4G
+config HIGHMEM4G
+	bool "High Memory Support"
 	depends on X86_32
-
-config NOHIGHMEM
-	bool "off"
 	help
-	  Linux can use up to 64 Gigabytes of physical memory on x86 systems.
+	  Linux can use up to 4 Gigabytes of physical memory on x86 systems.
 	  However, the address space of 32-bit x86 processors is only 4
 	  Gigabytes large. That means that, if you have a large amount of
 	  physical memory, not all of it can be "permanently mapped" by the
@@ -1410,38 +1381,9 @@ config NOHIGHMEM
 	  possible.
 
 	  If the machine has between 1 and 4 Gigabytes physical RAM, then
-	  answer "4GB" here.
-
-	  If more than 4 Gigabytes is used then answer "64GB" here. This
-	  selection turns Intel PAE (Physical Address Extension) mode on.
-	  PAE implements 3-level paging on IA32 processors. PAE is fully
-	  supported by Linux, PAE mode is implemented on all recent Intel
-	  processors (Pentium Pro and better). NOTE: If you say "64GB" here,
-	  then the kernel will not boot on CPUs that don't support PAE!
+	  answer "Y" here.
 
-	  The actual amount of total physical memory will either be
-	  auto detected or can be forced by using a kernel command line option
-	  such as "mem=256M". (Try "man bootparam" or see the documentation of
-	  your boot loader (lilo or loadlin) about how to pass options to the
-	  kernel at boot time.)
-
-	  If unsure, say "off".
-
-config HIGHMEM4G
-	bool "4GB"
-	help
-	  Select this if you have a 32-bit processor and between 1 and 4
-	  gigabytes of physical RAM.
-
-config HIGHMEM64G
-	bool "64GB"
-	depends on X86_HAVE_PAE
-	select X86_PAE
-	help
-	  Select this if you have a 32-bit processor and more than 4
-	  gigabytes of physical RAM.
-
-endchoice
+	  If unsure, say N.
 
 choice
 	prompt "Memory split" if EXPERT
@@ -1487,14 +1429,12 @@ config PAGE_OFFSET
 	depends on X86_32
 
 config HIGHMEM
-	def_bool y
-	depends on X86_32 && (HIGHMEM64G || HIGHMEM4G)
+	def_bool HIGHMEM4G
 
 config X86_PAE
 	bool "PAE (Physical Address Extension) Support"
 	depends on X86_32 && X86_HAVE_PAE
 	select PHYS_ADDR_T_64BIT
-	select SWIOTLB
 	help
 	  PAE is required for NX support, and furthermore enables
 	  larger swapspace support for non-overcommit purposes. It
@@ -1564,8 +1504,7 @@ config AMD_MEM_ENCRYPT
 config NUMA
 	bool "NUMA Memory Allocation and Scheduler Support"
 	depends on SMP
-	depends on X86_64 || (X86_32 && HIGHMEM64G && X86_BIGSMP)
-	default y if X86_BIGSMP
+	depends on X86_64
 	select USE_PERCPU_NUMA_NODE_ID
 	select OF_NUMA if OF
 	help
@@ -1578,9 +1517,6 @@ config NUMA
 	  For 64-bit this is recommended if the system is Intel Core i7
 	  (or later), AMD Opteron, or EM64T NUMA.
 
-	  For 32-bit this is only needed if you boot a 32-bit
-	  kernel on a 64-bit NUMA platform.
-
 	  Otherwise, you should say N.
 
 config AMD_NUMA
@@ -1619,7 +1555,7 @@ config ARCH_FLATMEM_ENABLE
 
 config ARCH_SPARSEMEM_ENABLE
 	def_bool y
-	depends on X86_64 || NUMA || X86_32 || X86_32_NON_STANDARD
+	depends on X86_64 || NUMA || X86_32
 	select SPARSEMEM_STATIC if X86_32
 	select SPARSEMEM_VMEMMAP_ENABLE if X86_64
 
@@ -1665,15 +1601,6 @@ config X86_PMEM_LEGACY
 
 	  Say Y if unsure.
 
-config HIGHPTE
-	bool "Allocate 3rd-level pagetables from highmem"
-	depends on HIGHMEM
-	help
-	  The VM uses one page table entry for each page of physical memory.
-	  For systems with a lot of RAM, this can be wasteful of precious
-	  low memory.  Setting this option will put user-space page table
-	  entries in high memory.
-
 config X86_CHECK_BIOS_CORRUPTION
 	bool "Check for low memory corruption"
 	help
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 2a7279d80460..f8b3296fe2e1 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 # Put here option for CPU selection and depending optimization
 choice
-	prompt "Processor family"
-	default M686 if X86_32
-	default GENERIC_CPU if X86_64
+	prompt "x86-32 Processor family"
+	depends on X86_32
+	default M686
 	help
 	  This is the processor type of your CPU. This information is
 	  used for optimizing purposes. In order to compile a kernel
@@ -31,7 +31,6 @@ choice
 	  - "Pentium-4" for the Intel Pentium 4 or P4-based Celeron.
 	  - "K6" for the AMD K6, K6-II and K6-III (aka K6-3D).
 	  - "Athlon" for the AMD K7 family (Athlon/Duron/Thunderbird).
-	  - "Opteron/Athlon64/Hammer/K8" for all K8 and newer AMD CPUs.
 	  - "Crusoe" for the Transmeta Crusoe series.
 	  - "Efficeon" for the Transmeta Efficeon series.
 	  - "Winchip-C6" for original IDT Winchip.
@@ -42,13 +41,10 @@ choice
 	  - "CyrixIII/VIA C3" for VIA Cyrix III or VIA C3.
 	  - "VIA C3-2" for VIA C3-2 "Nehemiah" (model 9 and above).
 	  - "VIA C7" for VIA C7.
-	  - "Intel P4" for the Pentium 4/Netburst microarchitecture.
-	  - "Core 2/newer Xeon" for all core2 and newer Intel CPUs.
 	  - "Intel Atom" for the Atom-microarchitecture CPUs.
-	  - "Generic-x86-64" for a kernel which runs on any x86-64 CPU.
 
 	  See each option's help text for additional details. If you don't know
-	  what to do, choose "486".
+	  what to do, choose "Pentium-Pro".
 
 config M486SX
 	bool "486SX"
@@ -114,11 +110,11 @@ config MPENTIUMIII
 	  extensions.
 
 config MPENTIUMM
-	bool "Pentium M"
+	bool "Pentium M/Pentium Dual Core/Core Solo/Core Duo"
 	depends on X86_32
 	help
 	  Select this for Intel Pentium M (not Pentium-4 M)
-	  notebook chips.
+	  "Merom" Core Solo/Duo notebook chips
 
 config MPENTIUM4
 	bool "Pentium-4/Celeron(P4-based)/Pentium-4 M/older Xeon"
@@ -139,22 +135,10 @@ config MPENTIUM4
 		-Mobile Pentium 4
 		-Mobile Pentium 4 M
 		-Extreme Edition (Gallatin)
-		-Prescott
-		-Prescott 2M
-		-Cedar Mill
-		-Presler
-		-Smithfiled
 	    Xeons (Intel Xeon, Xeon MP, Xeon LV, Xeon MV) corename:
 		-Foster
 		-Prestonia
 		-Gallatin
-		-Nocona
-		-Irwindale
-		-Cranford
-		-Potomac
-		-Paxville
-		-Dempsey
-
 
 config MK6
 	bool "K6/K6-II/K6-III"
@@ -172,13 +156,6 @@ config MK7
 	  some extended instructions, and passes appropriate optimization
 	  flags to GCC.
 
-config MK8
-	bool "Opteron/Athlon64/Hammer/K8"
-	help
-	  Select this for an AMD Opteron or Athlon64 Hammer-family processor.
-	  Enables use of some extended instructions, and passes appropriate
-	  optimization flags to GCC.
-
 config MCRUSOE
 	bool "Crusoe"
 	depends on X86_32
@@ -258,42 +235,14 @@ config MVIAC7
 	  Select this for a VIA C7.  Selecting this uses the correct cache
 	  shift and tells gcc to treat the CPU as a 686.
 
-config MPSC
-	bool "Intel P4 / older Netburst based Xeon"
-	depends on X86_64
-	help
-	  Optimize for Intel Pentium 4, Pentium D and older Nocona/Dempsey
-	  Xeon CPUs with Intel 64bit which is compatible with x86-64.
-	  Note that the latest Xeons (Xeon 51xx and 53xx) are not based on the
-	  Netburst core and shouldn't use this option. You can distinguish them
-	  using the cpu family field
-	  in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
-
-config MCORE2
-	bool "Core 2/newer Xeon"
-	help
-
-	  Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
-	  53xx) CPUs. You can distinguish newer from older Xeons by the CPU
-	  family in /proc/cpuinfo. Newer ones have 6 and older ones 15
-	  (not a typo)
-
 config MATOM
 	bool "Intel Atom"
 	help
-
 	  Select this for the Intel Atom platform. Intel Atom CPUs have an
 	  in-order pipelining architecture and thus can benefit from
 	  accordingly optimized code. Use a recent GCC with specific Atom
 	  support in order to fully benefit from selecting this option.
 
-config GENERIC_CPU
-	bool "Generic-x86-64"
-	depends on X86_64
-	help
-	  Generic x86-64 CPU.
-	  Run equally well on all x86-64 CPUs.
-
 endchoice
 
 config X86_GENERIC
@@ -317,8 +266,8 @@ config X86_INTERNODE_CACHE_SHIFT
 
 config X86_L1_CACHE_SHIFT
 	int
-	default "7" if MPENTIUM4 || MPSC
-	default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
+	default "7" if MPENTIUM4
+	default "6" if MK7 || MPENTIUMM || MATOM || MVIAC7 || X86_GENERIC || X86_64
 	default "4" if MELAN || M486SX || M486 || MGEODEGX1
 	default "5" if MWINCHIP3D || MWINCHIPC6 || MCRUSOE || MEFFICEON || MCYRIXIII || MK6 || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || M586 || MVIAC3_2 || MGEODE_LX
 
@@ -336,51 +285,35 @@ config X86_ALIGNMENT_16
 
 config X86_INTEL_USERCOPY
 	def_bool y
-	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK8 || MK7 || MEFFICEON || MCORE2
+	depends on MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M586MMX || X86_GENERIC || MK7 || MEFFICEON
 
 config X86_USE_PPRO_CHECKSUM
 	def_bool y
-	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MCORE2 || MATOM
-
-#
-# P6_NOPs are a relatively minor optimization that require a family >=
-# 6 processor, except that it is broken on certain VIA chips.
-# Furthermore, AMD chips prefer a totally different sequence of NOPs
-# (which work on all CPUs).  In addition, it looks like Virtual PC
-# does not understand them.
-#
-# As a result, disallow these if we're not compiling for X86_64 (these
-# NOPs do work on all x86-64 capable chips); the list of processors in
-# the right-hand clause are the cores that benefit from this optimization.
-#
-config X86_P6_NOP
-	def_bool y
-	depends on X86_64
-	depends on (MCORE2 || MPENTIUM4 || MPSC)
+	depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX || MATOM
 
 config X86_TSC
 	def_bool y
-	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MCORE2 || MATOM) || X86_64
+	depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MVIAC3_2 || MVIAC7 || MGEODEGX1 || MGEODE_LX || MATOM) || X86_64
 
 config X86_HAVE_PAE
 	def_bool y
-	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC7 || MCORE2 || MATOM || X86_64
+	depends on MCRUSOE || MEFFICEON || MCYRIXIII || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC7 || MATOM || X86_64
 
-config X86_CMPXCHG64
+config X86_CX8
 	def_bool y
-	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7
+	depends on X86_HAVE_PAE || M586TSC || M586MMX || MK6 || MK7 || MGEODEGX1 || MGEODE_LX
 
 # this should be set for all -march=.. options where the compiler
 # generates cmov.
 config X86_CMOV
 	def_bool y
-	depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX)
+	depends on (MK7 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || MATOM || MGEODE_LX || X86_64)
 
 config X86_MINIMUM_CPU_FAMILY
 	int
 	default "64" if X86_64
-	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8)
-	default "5" if X86_32 && X86_CMPXCHG64
+	default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MK7)
+	default "5" if X86_32 && X86_CX8
 	default "4"
 
 config X86_DEBUGCTLMSR
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 88a1705366f9..6784129328f6 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -171,20 +171,8 @@ else
 	# Use -mskip-rax-setup if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
 
-        # FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
-        cflags-$(CONFIG_MK8)		+= -march=k8
-        cflags-$(CONFIG_MPSC)		+= -march=nocona
-        cflags-$(CONFIG_MCORE2)		+= -march=core2
-        cflags-$(CONFIG_MATOM)		+= -march=atom
-        cflags-$(CONFIG_GENERIC_CPU)	+= -mtune=generic
-        KBUILD_CFLAGS += $(cflags-y)
-
-        rustflags-$(CONFIG_MK8)		+= -Ctarget-cpu=k8
-        rustflags-$(CONFIG_MPSC)	+= -Ctarget-cpu=nocona
-        rustflags-$(CONFIG_MCORE2)	+= -Ctarget-cpu=core2
-        rustflags-$(CONFIG_MATOM)	+= -Ctarget-cpu=atom
-        rustflags-$(CONFIG_GENERIC_CPU)	+= -Ztune-cpu=generic
-        KBUILD_RUSTFLAGS += $(rustflags-y)
+        KBUILD_CFLAGS += -march=x86-64 -mtune=generic
+        KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64 -Ztune-cpu=generic
 
         KBUILD_CFLAGS += -mno-red-zone
         KBUILD_CFLAGS += -mcmodel=kernel
diff --git a/arch/x86/Makefile_32.cpu b/arch/x86/Makefile_32.cpu
index 94834c4b5e5e..af7de9a42752 100644
--- a/arch/x86/Makefile_32.cpu
+++ b/arch/x86/Makefile_32.cpu
@@ -24,7 +24,6 @@ cflags-$(CONFIG_MK6)		+= -march=k6
 # Please note, that patches that add -march=athlon-xp and friends are pointless.
 # They make zero difference whatsosever to performance at this time.
 cflags-$(CONFIG_MK7)		+= -march=athlon
-cflags-$(CONFIG_MK8)		+= $(call cc-option,-march=k8,-march=athlon)
 cflags-$(CONFIG_MCRUSOE)	+= -march=i686 $(align)
 cflags-$(CONFIG_MEFFICEON)	+= -march=i686 $(call tune,pentium3) $(align)
 cflags-$(CONFIG_MWINCHIPC6)	+= $(call cc-option,-march=winchip-c6,-march=i586)
@@ -32,9 +31,7 @@ cflags-$(CONFIG_MWINCHIP3D)	+= $(call cc-option,-march=winchip2,-march=i586)
 cflags-$(CONFIG_MCYRIXIII)	+= $(call cc-option,-march=c3,-march=i486) $(align)
 cflags-$(CONFIG_MVIAC3_2)	+= $(call cc-option,-march=c3-2,-march=i686)
 cflags-$(CONFIG_MVIAC7)		+= -march=i686
-cflags-$(CONFIG_MCORE2)		+= -march=i686 $(call tune,core2)
-cflags-$(CONFIG_MATOM)		+= $(call cc-option,-march=atom,$(call cc-option,-march=core2,-march=i686)) \
-	$(call cc-option,-mtune=atom,$(call cc-option,-mtune=generic))
+cflags-$(CONFIG_MATOM)		+= -march=atom
 
 # AMD Elan support
 cflags-$(CONFIG_MELAN)		+= -march=i486
diff --git a/arch/x86/configs/xen.config b/arch/x86/configs/xen.config
index 581296255b39..d5d091e03bd3 100644
--- a/arch/x86/configs/xen.config
+++ b/arch/x86/configs/xen.config
@@ -1,6 +1,4 @@
 # global x86 required specific stuff
-# On 32-bit HIGHMEM4G is not allowed
-CONFIG_HIGHMEM64G=y
 CONFIG_64BIT=y
 
 # These enable us to allow some of the
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 94941c5a10ac..14db5b85114c 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -190,6 +190,7 @@ static __always_inline bool int80_is_external(void)
 
 /**
  * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ * @regs: syscall arguments in struct pt_args on the stack.
  *
  * This entry point can be used by 32-bit and 64-bit programs to perform
  * 32-bit system calls.  Instances of INT $0x80 can be found inline in
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 39e6efc1a9ca..bfc7cabf4017 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -48,8 +48,7 @@ int __init init_vdso_image(const struct vdso_image *image)
 
 	apply_alternatives((struct alt_instr *)(image->data + image->alt),
 			   (struct alt_instr *)(image->data + image->alt +
-						image->alt_len),
-			   NULL);
+						image->alt_len));
 
 	return 0;
 }
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445..2092d615333d 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -628,7 +628,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
+	if (!event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index e86333eee266..40a62bf6ef0a 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -397,34 +397,28 @@ static struct event_constraint intel_lnc_event_constraints[] = {
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
 
+	INTEL_EVENT_CONSTRAINT(0x20, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x012a, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x012b, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
 
 	INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
 	INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
-	/*
-	 * Generally event codes < 0x90 are restricted to counters 0-3.
-	 * The 0x2E and 0x3C are exception, which has no restriction.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
 
-	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x01cd, 0x3fc),
 	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
-	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
 
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
-	/*
-	 * Generally event codes >= 0x90 are likely to have no restrictions.
-	 * The exception are defined as above.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+	INTEL_UEVENT_CONSTRAINT(0x00e0, 0xf),
 
 	EVENT_CONSTRAINT_END
 };
@@ -3958,6 +3952,85 @@ static inline bool intel_pmu_has_cap(struct perf_event *event, int idx)
 	return test_bit(idx, (unsigned long *)&intel_cap->capabilities);
 }
 
+static u64 intel_pmu_freq_start_period(struct perf_event *event)
+{
+	int type = event->attr.type;
+	u64 config, factor;
+	s64 start;
+
+	/*
+	 * The 127 is the lowest possible recommended SAV (sample after value)
+	 * for a 4000 freq (default freq), according to the event list JSON file.
+	 * Also, assume the workload is idle 50% time.
+	 */
+	factor = 64 * 4000;
+	if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE)
+		goto end;
+
+	/*
+	 * The estimation of the start period in the freq mode is
+	 * based on the below assumption.
+	 *
+	 * For a cycles or an instructions event, 1GHZ of the
+	 * underlying platform, 1 IPC. The workload is idle 50% time.
+	 * The start period = 1,000,000,000 * 1 / freq / 2.
+	 *		    = 500,000,000 / freq
+	 *
+	 * Usually, the branch-related events occur less than the
+	 * instructions event. According to the Intel event list JSON
+	 * file, the SAV (sample after value) of a branch-related event
+	 * is usually 1/4 of an instruction event.
+	 * The start period of branch-related events = 125,000,000 / freq.
+	 *
+	 * The cache-related events occurs even less. The SAV is usually
+	 * 1/20 of an instruction event.
+	 * The start period of cache-related events = 25,000,000 / freq.
+	 */
+	config = event->attr.config & PERF_HW_EVENT_MASK;
+	if (type == PERF_TYPE_HARDWARE) {
+		switch (config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+		case PERF_COUNT_HW_INSTRUCTIONS:
+		case PERF_COUNT_HW_BUS_CYCLES:
+		case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND:
+		case PERF_COUNT_HW_STALLED_CYCLES_BACKEND:
+		case PERF_COUNT_HW_REF_CPU_CYCLES:
+			factor = 500000000;
+			break;
+		case PERF_COUNT_HW_BRANCH_INSTRUCTIONS:
+		case PERF_COUNT_HW_BRANCH_MISSES:
+			factor = 125000000;
+			break;
+		case PERF_COUNT_HW_CACHE_REFERENCES:
+		case PERF_COUNT_HW_CACHE_MISSES:
+			factor = 25000000;
+			break;
+		default:
+			goto end;
+		}
+	}
+
+	if (type == PERF_TYPE_HW_CACHE)
+		factor = 25000000;
+end:
+	/*
+	 * Usually, a prime or a number with less factors (close to prime)
+	 * is chosen as an SAV, which makes it less likely that the sampling
+	 * period synchronizes with some periodic event in the workload.
+	 * Minus 1 to make it at least avoiding values near power of twos
+	 * for the default freq.
+	 */
+	start = DIV_ROUND_UP_ULL(factor, event->attr.sample_freq) - 1;
+
+	if (start > x86_pmu.max_period)
+		start = x86_pmu.max_period;
+
+	if (x86_pmu.limit_period)
+		x86_pmu.limit_period(event, &start);
+
+	return start;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3969,6 +4042,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.freq && event->attr.sample_freq) {
+		event->hw.sample_period = intel_pmu_freq_start_period(event);
+		event->hw.last_period = event->hw.sample_period;
+		local64_set(&event->hw.period_left, event->hw.sample_period);
+	}
+
 	if (event->attr.precise_ip) {
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;
@@ -4606,9 +4685,9 @@ static int adl_hw_config(struct perf_event *event)
 	return -EOPNOTSUPP;
 }
 
-static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
+static enum intel_cpu_type adl_get_hybrid_cpu_type(void)
 {
-	return HYBRID_INTEL_CORE;
+	return INTEL_CPU_TYPE_CORE;
 }
 
 static inline bool erratum_hsw11(struct perf_event *event)
@@ -4953,7 +5032,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
 
 static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 {
-	u8 cpu_type = get_this_hybrid_cpu_type();
+	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+	enum intel_cpu_type cpu_type = c->topo.intel_type;
 	int i;
 
 	/*
@@ -4962,7 +5042,7 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 	 * on it. There should be a fixup function provided for these
 	 * troublesome CPUs (->get_hybrid_cpu_type).
 	 */
-	if (cpu_type == HYBRID_INTEL_NONE) {
+	if (cpu_type == INTEL_CPU_TYPE_UNKNOWN) {
 		if (x86_pmu.get_hybrid_cpu_type)
 			cpu_type = x86_pmu.get_hybrid_cpu_type();
 		else
@@ -4979,16 +5059,16 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 		enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
 		u32 native_id;
 
-		if (cpu_type == HYBRID_INTEL_CORE && pmu_type == hybrid_big)
+		if (cpu_type == INTEL_CPU_TYPE_CORE && pmu_type == hybrid_big)
 			return &x86_pmu.hybrid_pmu[i];
-		if (cpu_type == HYBRID_INTEL_ATOM) {
+		if (cpu_type == INTEL_CPU_TYPE_ATOM) {
 			if (x86_pmu.num_hybrid_pmus == 2 && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
 
-			native_id = get_this_hybrid_cpu_native_id();
-			if (native_id == skt_native_id && pmu_type == hybrid_small)
+			native_id = c->topo.intel_native_model_id;
+			if (native_id == INTEL_ATOM_SKT_NATIVE_ID && pmu_type == hybrid_small)
 				return &x86_pmu.hybrid_pmu[i];
-			if (native_id == cmt_native_id && pmu_type == hybrid_tiny)
+			if (native_id == INTEL_ATOM_CMT_NATIVE_ID && pmu_type == hybrid_tiny)
 				return &x86_pmu.hybrid_pmu[i];
 		}
 	}
@@ -6617,7 +6697,7 @@ __init int intel_pmu_init(void)
 	case INTEL_ATOM_SILVERMONT_D:
 	case INTEL_ATOM_SILVERMONT_MID:
 	case INTEL_ATOM_AIRMONT:
-	case INTEL_ATOM_AIRMONT_MID:
+	case INTEL_ATOM_SILVERMONT_MID2:
 		memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
 			sizeof(hw_cache_event_ids));
 		memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c2e2eae7309c..f122882ef278 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1199,7 +1199,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
-	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc),
 	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 31c2771545a6..7b18754084a6 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -669,18 +669,6 @@ enum {
 #define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
 #define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
-/*
- * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
- * of the core. Bits 31-24 indicates its core type (Core or Atom)
- * and Bits [23:0] indicates the native model ID of the core.
- * Core type and native model ID are defined in below enumerations.
- */
-enum hybrid_cpu_type {
-	HYBRID_INTEL_NONE,
-	HYBRID_INTEL_ATOM	= 0x20,
-	HYBRID_INTEL_CORE	= 0x40,
-};
-
 #define X86_HYBRID_PMU_ATOM_IDX		0
 #define X86_HYBRID_PMU_CORE_IDX		1
 #define X86_HYBRID_PMU_TINY_IDX		2
@@ -697,11 +685,6 @@ enum hybrid_pmu_type {
 	hybrid_big_small_tiny	= hybrid_big   | hybrid_small_tiny,
 };
 
-enum atom_native_id {
-	cmt_native_id           = 0x2,  /* Crestmont */
-	skt_native_id           = 0x3,  /* Skymont */
-};
-
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
 	const char			*name;
@@ -994,7 +977,7 @@ struct x86_pmu {
 	 */
 	int				num_hybrid_pmus;
 	struct x86_hybrid_pmu		*hybrid_pmu;
-	enum hybrid_cpu_type (*get_hybrid_cpu_type)	(void);
+	enum intel_cpu_type (*get_hybrid_cpu_type)	(void);
 };
 
 struct x86_perf_task_context_opt {
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 4952faf03e82..6941f4811bec 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -879,6 +879,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index cc8c3bd0e7c2..1f7c3082a36d 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -239,5 +239,4 @@ void hyperv_setup_mmu_ops(void)
 
 	pr_info("Using hypercall for remote TLB flush\n");
 	pv_ops.mmu.flush_tlb_multi = hyperv_flush_tlb_multi;
-	pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 }
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index e3903b731305..a2141665239b 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -87,16 +87,16 @@ extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
  * instructions were patched in already:
  */
 extern int alternatives_patched;
-struct module;
 
 extern void alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end,
-			       struct module *mod);
-extern void apply_retpolines(s32 *start, s32 *end, struct module *mod);
-extern void apply_returns(s32 *start, s32 *end, struct module *mod);
-extern void apply_seal_endbr(s32 *start, s32 *end, struct module *mod);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
+extern void apply_returns(s32 *start, s32 *end);
+extern void apply_seal_endbr(s32 *start, s32 *end);
 extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine,
-			  s32 *start_cfi, s32 *end_cfi, struct module *mod);
+			  s32 *start_cfi, s32 *end_cfi);
+
+struct module;
 
 struct callthunk_sites {
 	s32				*call_start, *call_end;
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 3674006e3974..8d9e62725202 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -16,7 +16,7 @@
 #include <asm/gsseg.h>
 #include <asm/nospec-branch.h>
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 extern void cmpxchg8b_emu(void);
 #endif
 
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 6c6e9b9f98a4..797085ecaaa4 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -48,7 +48,7 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
 	ATOMIC64_EXPORT(atomic64_##sym)
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 #define __alternative_atomic64(f, g, out, in...) \
 	asm volatile("call %c[func]" \
 		     : ALT_OUTPUT_SP(out) \
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index fd1282a783dd..c38d4ed94cb3 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -69,7 +69,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	return __arch_try_cmpxchg64(ptr, oldp, new,);
 }
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 
 #define arch_cmpxchg64 __cmpxchg64
 
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index 98eced5084ca..0c8ec62789a1 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -50,20 +50,6 @@ static inline void split_lock_init(void) {}
 static inline void bus_lock_init(void) {}
 #endif
 
-#ifdef CONFIG_CPU_SUP_INTEL
-u8 get_this_hybrid_cpu_type(void);
-u32 get_this_hybrid_cpu_native_id(void);
-#else
-static inline u8 get_this_hybrid_cpu_type(void)
-{
-	return 0;
-}
-
-static inline u32 get_this_hybrid_cpu_native_id(void)
-{
-	return 0;
-}
-#endif
 #ifdef CONFIG_IA32_FEAT_CTL
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
 #else
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index de1ad09fe8d7..e955da397e0e 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -37,19 +37,15 @@ enum cpuid_leafs
 	NR_CPUID_WORDS,
 };
 
-#define X86_CAP_FMT_NUM "%d:%d"
-#define x86_cap_flag_num(flag) ((flag) >> 5), ((flag) & 31)
-
 extern const char * const x86_cap_flags[NCAPINTS*32];
 extern const char * const x86_power_flags[32];
-#define X86_CAP_FMT "%s"
-#define x86_cap_flag(flag) x86_cap_flags[flag]
 
 /*
  * In order to save room, we index into this array by doing
  * X86_BUG_<name> - NCAPINTS*32.
  */
 extern const char * const x86_bug_flags[NBUGINTS*32];
+#define x86_bug_flag(flag) x86_bug_flags[flag]
 
 #define test_cpu_cap(c, bit)						\
 	 arch_test_bit(bit, (unsigned long *)((c)->x86_capability))
diff --git a/arch/x86/include/asm/cpuid.h b/arch/x86/include/asm/cpuid.h
index b2b9b4ef3dae..a92e4b08820a 100644
--- a/arch/x86/include/asm/cpuid.h
+++ b/arch/x86/include/asm/cpuid.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_X86_CPUID_H
 #define _ASM_X86_CPUID_H
 
+#include <linux/build_bug.h>
 #include <linux/types.h>
 
 #include <asm/string.h>
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 6d7b04ffc5fd..b657d78071c6 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -110,9 +110,9 @@
 
 #define INTEL_SAPPHIRERAPIDS_X		IFM(6, 0x8F) /* Golden Cove */
 
-#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF)
+#define INTEL_EMERALDRAPIDS_X		IFM(6, 0xCF) /* Raptor Cove */
 
-#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD)
+#define INTEL_GRANITERAPIDS_X		IFM(6, 0xAD) /* Redwood Cove */
 #define INTEL_GRANITERAPIDS_D		IFM(6, 0xAE)
 
 /* "Hybrid" Processors (P-Core/E-Core) */
@@ -126,16 +126,16 @@
 #define INTEL_RAPTORLAKE_P		IFM(6, 0xBA)
 #define INTEL_RAPTORLAKE_S		IFM(6, 0xBF)
 
-#define INTEL_METEORLAKE		IFM(6, 0xAC)
+#define INTEL_METEORLAKE		IFM(6, 0xAC) /* Redwood Cove / Crestmont */
 #define INTEL_METEORLAKE_L		IFM(6, 0xAA)
 
-#define INTEL_ARROWLAKE_H		IFM(6, 0xC5)
+#define INTEL_ARROWLAKE_H		IFM(6, 0xC5) /* Lion Cove / Skymont */
 #define INTEL_ARROWLAKE			IFM(6, 0xC6)
 #define INTEL_ARROWLAKE_U		IFM(6, 0xB5)
 
-#define INTEL_LUNARLAKE_M		IFM(6, 0xBD)
+#define INTEL_LUNARLAKE_M		IFM(6, 0xBD) /* Lion Cove / Skymont */
 
-#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC)
+#define INTEL_PANTHERLAKE_L		IFM(6, 0xCC) /* Cougar Cove / Crestmont */
 
 /* "Small Core" Processors (Atom/E-Core) */
 
@@ -149,9 +149,9 @@
 #define INTEL_ATOM_SILVERMONT		IFM(6, 0x37) /* Bay Trail, Valleyview */
 #define INTEL_ATOM_SILVERMONT_D		IFM(6, 0x4D) /* Avaton, Rangely */
 #define INTEL_ATOM_SILVERMONT_MID	IFM(6, 0x4A) /* Merriefield */
+#define INTEL_ATOM_SILVERMONT_MID2	IFM(6, 0x5A) /* Anniedale */
 
 #define INTEL_ATOM_AIRMONT		IFM(6, 0x4C) /* Cherry Trail, Braswell */
-#define INTEL_ATOM_AIRMONT_MID		IFM(6, 0x5A) /* Moorefield */
 #define INTEL_ATOM_AIRMONT_NP		IFM(6, 0x75) /* Lightning Mountain */
 
 #define INTEL_ATOM_GOLDMONT		IFM(6, 0x5C) /* Apollo Lake */
@@ -182,10 +182,23 @@
 /* Family 19 */
 #define INTEL_PANTHERCOVE_X		IFM(19, 0x01) /* Diamond Rapids */
 
-/* CPU core types */
+/*
+ * Intel CPU core types
+ *
+ * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
+ * of the core. Bits 31-24 indicates its core type (Core or Atom)
+ * and Bits [23:0] indicates the native model ID of the core.
+ * Core type and native model ID are defined in below enumerations.
+ */
 enum intel_cpu_type {
+	INTEL_CPU_TYPE_UNKNOWN,
 	INTEL_CPU_TYPE_ATOM = 0x20,
 	INTEL_CPU_TYPE_CORE = 0x40,
 };
 
+enum intel_native_id {
+	INTEL_ATOM_CMT_NATIVE_ID = 0x2,  /* Crestmont */
+	INTEL_ATOM_SKT_NATIVE_ID = 0x3,  /* Skymont */
+};
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ed580c7f9d0a..1a0dc2b2bf5b 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -175,6 +175,9 @@ extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size, un
 extern void __iomem *ioremap_encrypted(resource_size_t phys_addr, unsigned long size);
 #define ioremap_encrypted ioremap_encrypted
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags);
+#define arch_memremap_wb arch_memremap_wb
+
 /**
  * ioremap     -   map bus memory into CPU space
  * @offset:    bus address of the memory
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5..aee26bb8230f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -198,9 +198,8 @@
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -421,19 +420,26 @@ static inline void call_depth_return_thunk(void) {}
 #ifdef CONFIG_X86_64
 
 /*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
+/*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#ifdef CONFIG_MITIGATION_RETPOLINE
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
+#else
+#define CALL_NOSPEC	"call *%[thunk_target]\n"
+#endif
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index faf9cc1c14bb..25c32652f404 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -11,8 +11,8 @@
  * a virtual address space of one gigabyte, which limits the
  * amount of physical memory you can use to about 950MB.
  *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ * If you want more physical memory than this then see the CONFIG_VMSPLIT_2G
+ * and CONFIG_HIGHMEM4G options in the kernel configuration.
  */
 #define __PAGE_OFFSET_BASE	_AC(CONFIG_PAGE_OFFSET, UL)
 #define __PAGE_OFFSET		__PAGE_OFFSET_BASE
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 041aff51eb50..38a632a282d4 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -91,11 +91,6 @@ static inline void __flush_tlb_multi(const struct cpumask *cpumask,
 	PVOP_VCALL2(mmu.flush_tlb_multi, cpumask, info);
 }
 
-static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	PVOP_VCALL2(mmu.tlb_remove_table, tlb, table);
-}
-
 static inline void paravirt_arch_exit_mmap(struct mm_struct *mm)
 {
 	PVOP_VCALL1(mmu.exit_mmap, mm);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index fea56b04f436..e26633c00455 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -134,8 +134,6 @@ struct pv_mmu_ops {
 	void (*flush_tlb_multi)(const struct cpumask *cpus,
 				const struct flush_tlb_info *info);
 
-	void (*tlb_remove_table)(struct mmu_gather *tlb, void *table);
-
 	/* Hook for intercepting the destruction of an mm_struct. */
 	void (*exit_mmap)(struct mm_struct *mm);
 	void (*notify_page_enc_status_changed)(unsigned long pfn, int npages, bool enc);
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dd4841231bb9..a33147520044 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -29,11 +29,6 @@ static inline void paravirt_release_pud(unsigned long pfn) {}
 static inline void paravirt_release_p4d(unsigned long pfn) {}
 #endif
 
-/*
- * Flags to use when allocating a user page table page.
- */
-extern gfp_t __userpte_alloc_gfp;
-
 #ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
 /*
  * Instead of one PGD, we acquire two PGDs.  Being order-1, it is
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 4b804531b03c..c90e9c51edb7 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -33,6 +33,7 @@
 #define _PAGE_BIT_CPA_TEST	_PAGE_BIT_SOFTW1
 #define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
+#define _PAGE_BIT_KERNEL_4K	_PAGE_BIT_SOFTW3 /* page must not be converted to large */
 #define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 #ifdef CONFIG_X86_64
@@ -64,6 +65,7 @@
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
 #define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define _PAGE_KERNEL_4K	(_AT(pteval_t, 1) << _PAGE_BIT_KERNEL_4K)
 #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
 #define _PAGE_PKEY_BIT0	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT0)
 #define _PAGE_PKEY_BIT1	(_AT(pteval_t, 1) << _PAGE_BIT_PKEY_BIT1)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b3d153730f63..8f7023438626 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -60,18 +60,13 @@ struct vm86;
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
-enum tlb_infos {
-	ENTRIES,
-	NR_INFO
-};
-
-extern u16 __read_mostly tlb_lli_4k[NR_INFO];
-extern u16 __read_mostly tlb_lli_2m[NR_INFO];
-extern u16 __read_mostly tlb_lli_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4k[NR_INFO];
-extern u16 __read_mostly tlb_lld_2m[NR_INFO];
-extern u16 __read_mostly tlb_lld_4m[NR_INFO];
-extern u16 __read_mostly tlb_lld_1g[NR_INFO];
+extern u16 __read_mostly tlb_lli_4k;
+extern u16 __read_mostly tlb_lli_2m;
+extern u16 __read_mostly tlb_lli_4m;
+extern u16 __read_mostly tlb_lld_4k;
+extern u16 __read_mostly tlb_lld_2m;
+extern u16 __read_mostly tlb_lld_4m;
+extern u16 __read_mostly tlb_lld_1g;
 
 /*
  * CPU type and hardware bug flags. Kept separately for each CPU.
@@ -234,7 +229,7 @@ static inline unsigned long long l1tf_pfn_limit(void)
 void init_cpu_devs(void);
 void get_cpu_vendor(struct cpuinfo_x86 *c);
 extern void early_cpu_init(void);
-extern void identify_secondary_cpu(struct cpuinfo_x86 *);
+extern void identify_secondary_cpu(unsigned int cpu);
 extern void print_cpu_info(struct cpuinfo_x86 *);
 void print_cpu_msr(struct cpuinfo_x86 *);
 
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index e9187ddd3d1f..0068133cb622 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -23,7 +23,7 @@
 # define NEED_PAE	0
 #endif
 
-#ifdef CONFIG_X86_CMPXCHG64
+#ifdef CONFIG_X86_CX8
 # define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
 #else
 # define NEED_CX8	0
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index ca073f40698f..128e06a18e51 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -114,13 +114,12 @@ void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
 
 void smp_kick_mwait_play_dead(void);
+void __noreturn mwait_play_dead(unsigned int eax_hint);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);
 void native_send_call_func_single_ipi(int cpu);
 
-void smp_store_cpu_info(int id);
-
 asmlinkage __visible void smp_reboot_interrupt(void);
 __visible void smp_reschedule_interrupt(struct pt_regs *regs);
 __visible void smp_call_function_interrupt(struct pt_regs *regs);
@@ -164,6 +163,8 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 {
 	return (struct cpumask *)cpumask_of(0);
 }
+
+static inline void __noreturn mwait_play_dead(unsigned int eax_hint) { BUG(); }
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_DEBUG_NMI_SELFTEST
diff --git a/arch/x86/include/asm/sta2x11.h b/arch/x86/include/asm/sta2x11.h
deleted file mode 100644
index e0975e9c4f47..000000000000
--- a/arch/x86/include/asm/sta2x11.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Header file for STMicroelectronics ConneXt (STA2X11) IOHub
- */
-#ifndef __ASM_STA2X11_H
-#define __ASM_STA2X11_H
-
-#include <linux/pci.h>
-
-/* This needs to be called from the MFD to configure its sub-devices */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev);
-
-#endif /* __ASM_STA2X11_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 02fc2aa06e9e..3da645139748 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -242,7 +242,7 @@ void flush_tlb_multi(const struct cpumask *cpumask,
 	flush_tlb_mm_range((vma)->vm_mm, start, end,			\
 			   ((vma)->vm_flags & VM_HUGETLB)		\
 				? huge_page_shift(hstate_vma(vma))	\
-				: PAGE_SHIFT, false)
+				: PAGE_SHIFT, true)
 
 extern void flush_tlb_all(void);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
index 75884d2cdec3..5d471253c755 100644
--- a/arch/x86/include/asm/vermagic.h
+++ b/arch/x86/include/asm/vermagic.h
@@ -15,8 +15,6 @@
 #define MODULE_PROC_FAMILY "586TSC "
 #elif defined CONFIG_M586MMX
 #define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
 #elif defined CONFIG_MATOM
 #define MODULE_PROC_FAMILY "ATOM "
 #elif defined CONFIG_M686
@@ -33,8 +31,6 @@
 #define MODULE_PROC_FAMILY "K6 "
 #elif defined CONFIG_MK7
 #define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
 #elif defined CONFIG_MELAN
 #define MODULE_PROC_FAMILY "ELAN "
 #elif defined CONFIG_MCRUSOE
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index 5854f0b8f0f1..d25584255ab8 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -16,6 +16,7 @@
 #include <asm/cpuid.h>
 #include <asm/mwait.h>
 #include <asm/special_insns.h>
+#include <asm/smp.h>
 
 /*
  * Initialize bm_flags based on the CPU cache properties
@@ -205,6 +206,16 @@ int acpi_processor_ffh_cstate_probe(unsigned int cpu,
 }
 EXPORT_SYMBOL_GPL(acpi_processor_ffh_cstate_probe);
 
+void __noreturn acpi_processor_ffh_play_dead(struct acpi_processor_cx *cx)
+{
+	unsigned int cpu = smp_processor_id();
+	struct cstate_entry *percpu_entry;
+
+	percpu_entry = per_cpu_ptr(cpu_cstate_entry, cpu);
+	mwait_play_dead(percpu_entry->states[cx->index].eax);
+}
+EXPORT_SYMBOL_GPL(acpi_processor_ffh_play_dead);
+
 void __cpuidle acpi_processor_ffh_cstate_enter(struct acpi_processor_cx *cx)
 {
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c71b575bf229..8b66a555d2f0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -392,10 +392,8 @@ EXPORT_SYMBOL(BUG_func);
  * Rewrite the "call BUG_func" replacement to point to the target of the
  * indirect pv_ops call "call *disp(%ip)".
  */
-static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
-			    struct module *mod)
+static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a)
 {
-	u8 *wr_instr = module_writable_address(mod, instr);
 	void *target, *bug = &BUG_func;
 	s32 disp;
 
@@ -405,14 +403,14 @@ static int alt_replace_call(u8 *instr, u8 *insn_buff, struct alt_instr *a,
 	}
 
 	if (a->instrlen != 6 ||
-	    wr_instr[0] != CALL_RIP_REL_OPCODE ||
-	    wr_instr[1] != CALL_RIP_REL_MODRM) {
+	    instr[0] != CALL_RIP_REL_OPCODE ||
+	    instr[1] != CALL_RIP_REL_MODRM) {
 		pr_err("ALT_FLAG_DIRECT_CALL set for unrecognized indirect call\n");
 		BUG();
 	}
 
 	/* Skip CALL_RIP_REL_OPCODE and CALL_RIP_REL_MODRM */
-	disp = *(s32 *)(wr_instr + 2);
+	disp = *(s32 *)(instr + 2);
 #ifdef CONFIG_X86_64
 	/* ff 15 00 00 00 00   call   *0x0(%rip) */
 	/* target address is stored at "next instruction + disp". */
@@ -450,8 +448,7 @@ static inline u8 * instr_va(struct alt_instr *i)
  * to refetch changed I$ lines.
  */
 void __init_or_module noinline apply_alternatives(struct alt_instr *start,
-						  struct alt_instr *end,
-						  struct module *mod)
+						  struct alt_instr *end)
 {
 	u8 insn_buff[MAX_PATCH_LEN];
 	u8 *instr, *replacement;
@@ -480,7 +477,6 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
-		u8 *wr_instr, *wr_replacement;
 
 		/*
 		 * In case of nested ALTERNATIVE()s the outer alternative might
@@ -494,11 +490,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		}
 
 		instr = instr_va(a);
-		wr_instr = module_writable_address(mod, instr);
-
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
-		wr_replacement = module_writable_address(mod, replacement);
-
 		BUG_ON(a->instrlen > sizeof(insn_buff));
 		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
 
@@ -509,9 +501,9 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		 *   patch if feature is *NOT* present.
 		 */
 		if (!boot_cpu_has(a->cpuid) == !(a->flags & ALT_FLAG_NOT)) {
-			memcpy(insn_buff, wr_instr, a->instrlen);
+			memcpy(insn_buff, instr, a->instrlen);
 			optimize_nops(instr, insn_buff, a->instrlen);
-			text_poke_early(wr_instr, insn_buff, a->instrlen);
+			text_poke_early(instr, insn_buff, a->instrlen);
 			continue;
 		}
 
@@ -521,12 +513,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->flags);
 
-		memcpy(insn_buff, wr_replacement, a->replacementlen);
+		memcpy(insn_buff, replacement, a->replacementlen);
 		insn_buff_sz = a->replacementlen;
 
 		if (a->flags & ALT_FLAG_DIRECT_CALL) {
-			insn_buff_sz = alt_replace_call(instr, insn_buff, a,
-							mod);
+			insn_buff_sz = alt_replace_call(instr, insn_buff, a);
 			if (insn_buff_sz < 0)
 				continue;
 		}
@@ -536,11 +527,11 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 
 		apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
 
-		DUMP_BYTES(ALT, wr_instr, a->instrlen, "%px:   old_insn: ", instr);
+		DUMP_BYTES(ALT, instr, a->instrlen, "%px:   old_insn: ", instr);
 		DUMP_BYTES(ALT, replacement, a->replacementlen, "%px:   rpl_insn: ", replacement);
 		DUMP_BYTES(ALT, insn_buff, insn_buff_sz, "%px: final_insn: ", instr);
 
-		text_poke_early(wr_instr, insn_buff, insn_buff_sz);
+		text_poke_early(instr, insn_buff, insn_buff_sz);
 	}
 
 	kasan_enable_current();
@@ -731,20 +722,18 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 /*
  * Generated by 'objtool --retpoline'.
  */
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod)
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op1, op2;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -772,9 +761,9 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
 		len = patch_retpoline(addr, &insn, bytes);
 		if (len == insn.length) {
 			optimize_nops(addr, bytes, len);
-			DUMP_BYTES(RETPOLINE, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RETPOLINE, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RETPOLINE, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
@@ -810,8 +799,7 @@ static int patch_return(void *addr, struct insn *insn, u8 *bytes)
 	return i;
 }
 
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod)
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
 {
 	s32 *s;
 
@@ -820,13 +808,12 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
 
 	for (s = start; s < end; s++) {
 		void *dest = NULL, *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		struct insn insn;
 		int len, ret;
 		u8 bytes[16];
 		u8 op;
 
-		ret = insn_decode_kernel(&insn, wr_addr);
+		ret = insn_decode_kernel(&insn, addr);
 		if (WARN_ON_ONCE(ret < 0))
 			continue;
 
@@ -846,35 +833,32 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end,
 
 		len = patch_return(addr, &insn, bytes);
 		if (len == insn.length) {
-			DUMP_BYTES(RET, ((u8*)wr_addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(RET, ((u8*)addr),  len, "%px: orig: ", addr);
 			DUMP_BYTES(RET, ((u8*)bytes), len, "%px: repl: ", addr);
-			text_poke_early(wr_addr, bytes, len);
+			text_poke_early(addr, bytes, len);
 		}
 	}
 }
 #else
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 #endif /* CONFIG_MITIGATION_RETHUNK */
 
 #else /* !CONFIG_MITIGATION_RETPOLINE || !CONFIG_OBJTOOL */
 
-void __init_or_module noinline apply_retpolines(s32 *start, s32 *end,
-						struct module *mod) { }
-void __init_or_module noinline apply_returns(s32 *start, s32 *end,
-					     struct module *mod) { }
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_MITIGATION_RETPOLINE && CONFIG_OBJTOOL */
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
-static void poison_cfi(void *addr, void *wr_addr);
+static void poison_cfi(void *addr);
 
-static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
+static void __init_or_module poison_endbr(void *addr, bool warn)
 {
 	u32 endbr, poison = gen_endbr_poison();
 
-	if (WARN_ON_ONCE(get_kernel_nofault(endbr, wr_addr)))
+	if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
 		return;
 
 	if (!is_endbr(endbr)) {
@@ -889,7 +873,7 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
 	 */
 	DUMP_BYTES(ENDBR, ((u8*)addr), 4, "%px: orig: ", addr);
 	DUMP_BYTES(ENDBR, ((u8*)&poison), 4, "%px: repl: ", addr);
-	text_poke_early(wr_addr, &poison, 4);
+	text_poke_early(addr, &poison, 4);
 }
 
 /*
@@ -898,23 +882,22 @@ static void __init_or_module poison_endbr(void *addr, void *wr_addr, bool warn)
  * Seal the functions for indirect calls by clobbering the ENDBR instructions
  * and the kCFI hash value.
  */
-void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end, struct module *mod)
+void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr, wr_addr, true);
+		poison_endbr(addr, true);
 		if (IS_ENABLED(CONFIG_FINEIBT))
-			poison_cfi(addr - 16, wr_addr - 16);
+			poison_cfi(addr - 16);
 	}
 }
 
 #else
 
-void __init_or_module apply_seal_endbr(s32 *start, s32 *end, struct module *mod) { }
+void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_X86_KERNEL_IBT */
 
@@ -1136,7 +1119,7 @@ static u32 decode_caller_hash(void *addr)
 }
 
 /* .retpoline_sites */
-static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_disable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
@@ -1148,23 +1131,20 @@ static int cfi_disable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
-
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, jmp, 2);
+		text_poke_early(addr, jmp, 2);
 	}
 
 	return 0;
 }
 
-static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_enable_callers(s32 *start, s32 *end)
 {
 	/*
 	 * Re-enable kCFI, undo what cfi_disable_callers() did.
@@ -1174,115 +1154,106 @@ static int cfi_enable_callers(s32 *start, s32 *end, struct module *mod)
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (!hash) /* nocfi callers */
 			continue;
 
-		text_poke_early(wr_addr, mov, 2);
+		text_poke_early(addr, mov, 2);
 	}
 
 	return 0;
 }
 
 /* .cfi_sites */
-static int cfi_rand_preamble(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		hash = decode_preamble_hash(addr);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
 		hash = cfi_rehash(hash);
-		text_poke_early(wr_addr + 1, &hash, 4);
+		text_poke_early(addr + 1, &hash, 4);
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_preamble(s32 *start, s32 *end, struct module *mod)
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 		u32 hash;
 
-		hash = decode_preamble_hash(wr_addr);
+		hash = decode_preamble_hash(addr);
 		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
 			 addr, addr, 5, addr))
 			return -EINVAL;
 
-		text_poke_early(wr_addr, fineibt_preamble_start, fineibt_preamble_size);
-		WARN_ON(*(u32 *)(wr_addr + fineibt_preamble_hash) != 0x12345678);
-		text_poke_early(wr_addr + fineibt_preamble_hash, &hash, 4);
+		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
+		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
+		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
 	}
 
 	return 0;
 }
 
-static void cfi_rewrite_endbr(s32 *start, s32 *end, struct module *mod)
+static void cfi_rewrite_endbr(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr = module_writable_address(mod, addr);
 
-		poison_endbr(addr + 16, wr_addr + 16, false);
+		poison_endbr(addr+16, false);
 	}
 }
 
 /* .retpoline_sites */
-static int cfi_rand_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rand_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (hash) {
 			hash = -cfi_rehash(hash);
-			text_poke_early(wr_addr + 2, &hash, 4);
+			text_poke_early(addr + 2, &hash, 4);
 		}
 	}
 
 	return 0;
 }
 
-static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod)
+static int cfi_rewrite_callers(s32 *start, s32 *end)
 {
 	s32 *s;
 
 	for (s = start; s < end; s++) {
 		void *addr = (void *)s + *s;
-		void *wr_addr;
 		u32 hash;
 
 		addr -= fineibt_caller_size;
-		wr_addr = module_writable_address(mod, addr);
-		hash = decode_caller_hash(wr_addr);
+		hash = decode_caller_hash(addr);
 		if (hash) {
-			text_poke_early(wr_addr, fineibt_caller_start, fineibt_caller_size);
-			WARN_ON(*(u32 *)(wr_addr + fineibt_caller_hash) != 0x12345678);
-			text_poke_early(wr_addr + fineibt_caller_hash, &hash, 4);
+			text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
+			WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
+			text_poke_early(addr + fineibt_caller_hash, &hash, 4);
 		}
 		/* rely on apply_retpolines() */
 	}
@@ -1291,9 +1262,8 @@ static int cfi_rewrite_callers(s32 *start, s32 *end, struct module *mod)
 }
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
-	bool builtin = mod ? false : true;
 	int ret;
 
 	if (WARN_ONCE(fineibt_preamble_size != 16,
@@ -1311,7 +1281,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 	 * rewrite them. This disables all CFI. If this succeeds but any of the
 	 * later stages fails, we're without CFI.
 	 */
-	ret = cfi_disable_callers(start_retpoline, end_retpoline, mod);
+	ret = cfi_disable_callers(start_retpoline, end_retpoline);
 	if (ret)
 		goto err;
 
@@ -1322,11 +1292,11 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 			cfi_bpf_subprog_hash = cfi_rehash(cfi_bpf_subprog_hash);
 		}
 
-		ret = cfi_rand_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rand_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
-		ret = cfi_rand_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rand_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 	}
@@ -1338,7 +1308,7 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 		return;
 
 	case CFI_KCFI:
-		ret = cfi_enable_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_enable_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
@@ -1348,17 +1318,17 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
 
 	case CFI_FINEIBT:
 		/* place the FineIBT preamble at func()-16 */
-		ret = cfi_rewrite_preamble(start_cfi, end_cfi, mod);
+		ret = cfi_rewrite_preamble(start_cfi, end_cfi);
 		if (ret)
 			goto err;
 
 		/* rewrite the callers to target func()-16 */
-		ret = cfi_rewrite_callers(start_retpoline, end_retpoline, mod);
+		ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
 		if (ret)
 			goto err;
 
 		/* now that nobody targets func()+0, remove ENDBR there */
-		cfi_rewrite_endbr(start_cfi, end_cfi, mod);
+		cfi_rewrite_endbr(start_cfi, end_cfi);
 
 		if (builtin)
 			pr_info("Using FineIBT CFI\n");
@@ -1377,7 +1347,7 @@ static inline void poison_hash(void *addr)
 	*(u32 *)addr = 0;
 }
 
-static void poison_cfi(void *addr, void *wr_addr)
+static void poison_cfi(void *addr)
 {
 	switch (cfi_mode) {
 	case CFI_FINEIBT:
@@ -1389,8 +1359,8 @@ static void poison_cfi(void *addr, void *wr_addr)
 		 *	ud2
 		 * 1:	nop
 		 */
-		poison_endbr(addr, wr_addr, false);
-		poison_hash(wr_addr + fineibt_preamble_hash);
+		poison_endbr(addr, false);
+		poison_hash(addr + fineibt_preamble_hash);
 		break;
 
 	case CFI_KCFI:
@@ -1399,7 +1369,7 @@ static void poison_cfi(void *addr, void *wr_addr)
 		 *	movl	$0, %eax
 		 *	.skip	11, 0x90
 		 */
-		poison_hash(wr_addr + 1);
+		poison_hash(addr + 1);
 		break;
 
 	default:
@@ -1410,21 +1380,22 @@ static void poison_cfi(void *addr, void *wr_addr)
 #else
 
 static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-			    s32 *start_cfi, s32 *end_cfi, struct module *mod)
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
 {
 }
 
 #ifdef CONFIG_X86_KERNEL_IBT
-static void poison_cfi(void *addr, void *wr_addr) { }
+static void poison_cfi(void *addr) { }
 #endif
 
 #endif
 
 void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
-		   s32 *start_cfi, s32 *end_cfi, struct module *mod)
+		   s32 *start_cfi, s32 *end_cfi)
 {
 	return __apply_fineibt(start_retpoline, end_retpoline,
-			       start_cfi, end_cfi, mod);
+			       start_cfi, end_cfi,
+			       /* .builtin = */ false);
 }
 
 #ifdef CONFIG_SMP
@@ -1721,16 +1692,16 @@ void __init alternative_instructions(void)
 	paravirt_set_cap();
 
 	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
-			__cfi_sites, __cfi_sites_end, NULL);
+			__cfi_sites, __cfi_sites_end, true);
 
 	/*
 	 * Rewrite the retpolines, must be done before alternatives since
 	 * those can rewrite the retpoline thunks.
 	 */
-	apply_retpolines(__retpoline_sites, __retpoline_sites_end, NULL);
-	apply_returns(__return_sites, __return_sites_end, NULL);
+	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+	apply_returns(__return_sites, __return_sites_end);
 
-	apply_alternatives(__alt_instructions, __alt_instructions_end, NULL);
+	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 	/*
 	 * Now all calls are established. Apply the call thunks if
@@ -1741,7 +1712,7 @@ void __init alternative_instructions(void)
 	/*
 	 * Seal all functions that do not have their address taken.
 	 */
-	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end, NULL);
+	apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
 
 #ifdef CONFIG_SMP
 	/* Patch to UP if other cpus not imminent. */
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 3bf0487cf3b7..52d1808ee360 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -23,8 +23,5 @@ obj-$(CONFIG_X86_X2APIC)	+= x2apic_cluster.o
 obj-y				+= apic_flat_64.o
 endif
 
-# APIC probe will depend on the listing order here
-obj-$(CONFIG_X86_BIGSMP)	+= bigsmp_32.o
-
 # For 32bit, probe_32 need to be listed last
 obj-$(CONFIG_X86_LOCAL_APIC)	+= probe_$(BITS).o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index e893dc6f11c1..ddca8da6d468 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1371,8 +1371,6 @@ void __init apic_intr_mode_init(void)
 
 	x86_64_probe_apic();
 
-	x86_32_install_bigsmp();
-
 	if (x86_platform.apic_post_init)
 		x86_platform.apic_post_init();
 
@@ -1674,7 +1672,6 @@ static __init void apic_read_boot_cpu_id(bool x2apic)
 		boot_cpu_apic_version = GET_APIC_VERSION(apic_read(APIC_LVR));
 	}
 	topology_register_boot_apic(boot_cpu_physical_apicid);
-	x86_32_probe_bigsmp_early();
 }
 
 #ifdef CONFIG_X86_X2APIC
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
deleted file mode 100644
index 9285d500d5b4..000000000000
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * APIC driver for "bigsmp" xAPIC machines with more than 8 virtual CPUs.
- *
- * Drives the local APIC in "clustered mode".
- */
-#include <linux/cpumask.h>
-#include <linux/dmi.h>
-#include <linux/smp.h>
-
-#include <asm/apic.h>
-#include <asm/io_apic.h>
-
-#include "local.h"
-
-static u32 bigsmp_get_apic_id(u32 x)
-{
-	return (x >> 24) & 0xFF;
-}
-
-static void bigsmp_send_IPI_allbutself(int vector)
-{
-	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
-}
-
-static void bigsmp_send_IPI_all(int vector)
-{
-	default_send_IPI_mask_sequence_phys(cpu_online_mask, vector);
-}
-
-static int dmi_bigsmp; /* can be set by dmi scanners */
-
-static int hp_ht_bigsmp(const struct dmi_system_id *d)
-{
-	printk(KERN_NOTICE "%s detected: force use of apic=bigsmp\n", d->ident);
-	dmi_bigsmp = 1;
-
-	return 0;
-}
-
-
-static const struct dmi_system_id bigsmp_dmi_table[] = {
-	{ hp_ht_bigsmp, "HP ProLiant DL760 G2",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P44-"),
-		}
-	},
-
-	{ hp_ht_bigsmp, "HP ProLiant DL740",
-		{	DMI_MATCH(DMI_BIOS_VENDOR, "HP"),
-			DMI_MATCH(DMI_BIOS_VERSION, "P47-"),
-		}
-	},
-	{ } /* NULL entry stops DMI scanning */
-};
-
-static int probe_bigsmp(void)
-{
-	return dmi_check_system(bigsmp_dmi_table);
-}
-
-static struct apic apic_bigsmp __ro_after_init = {
-
-	.name				= "bigsmp",
-	.probe				= probe_bigsmp,
-
-	.dest_mode_logical		= false,
-
-	.disable_esr			= 1,
-
-	.cpu_present_to_apicid		= default_cpu_present_to_apicid,
-
-	.max_apic_id			= 0xFE,
-	.get_apic_id			= bigsmp_get_apic_id,
-
-	.calc_dest_apicid		= apic_default_calc_apicid,
-
-	.send_IPI			= default_send_IPI_single_phys,
-	.send_IPI_mask			= default_send_IPI_mask_sequence_phys,
-	.send_IPI_mask_allbutself	= NULL,
-	.send_IPI_allbutself		= bigsmp_send_IPI_allbutself,
-	.send_IPI_all			= bigsmp_send_IPI_all,
-	.send_IPI_self			= default_send_IPI_self,
-
-	.read				= native_apic_mem_read,
-	.write				= native_apic_mem_write,
-	.eoi				= native_apic_mem_eoi,
-	.icr_read			= native_apic_icr_read,
-	.icr_write			= native_apic_icr_write,
-	.wait_icr_idle			= apic_mem_wait_icr_idle,
-	.safe_wait_icr_idle		= apic_mem_wait_icr_idle_timeout,
-};
-
-bool __init apic_bigsmp_possible(bool cmdline_override)
-{
-	return apic == &apic_bigsmp || !cmdline_override;
-}
-
-void __init apic_bigsmp_force(void)
-{
-	if (apic != &apic_bigsmp)
-		apic_install_driver(&apic_bigsmp);
-}
-
-apic_driver(apic_bigsmp);
diff --git a/arch/x86/kernel/apic/local.h b/arch/x86/kernel/apic/local.h
index 842fe28496be..bdcf609eb283 100644
--- a/arch/x86/kernel/apic/local.h
+++ b/arch/x86/kernel/apic/local.h
@@ -65,17 +65,4 @@ void default_send_IPI_self(int vector);
 void default_send_IPI_mask_sequence_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_allbutself_logical(const struct cpumask *mask, int vector);
 void default_send_IPI_mask_logical(const struct cpumask *mask, int vector);
-void x86_32_probe_bigsmp_early(void);
-void x86_32_install_bigsmp(void);
-#else
-static inline void x86_32_probe_bigsmp_early(void) { }
-static inline void x86_32_install_bigsmp(void) { }
-#endif
-
-#ifdef CONFIG_X86_BIGSMP
-bool apic_bigsmp_possible(bool cmdline_selected);
-void apic_bigsmp_force(void);
-#else
-static inline bool apic_bigsmp_possible(bool cmdline_selected) { return false; };
-static inline void apic_bigsmp_force(void) { }
 #endif
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index f75ee345c02d..87bc9e7ca5d6 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -93,35 +93,6 @@ static int __init parse_apic(char *arg)
 }
 early_param("apic", parse_apic);
 
-void __init x86_32_probe_bigsmp_early(void)
-{
-	if (nr_cpu_ids <= 8 || xen_pv_domain())
-		return;
-
-	if (IS_ENABLED(CONFIG_X86_BIGSMP)) {
-		switch (boot_cpu_data.x86_vendor) {
-		case X86_VENDOR_INTEL:
-			if (!APIC_XAPIC(boot_cpu_apic_version))
-				break;
-			/* P4 and above */
-			fallthrough;
-		case X86_VENDOR_HYGON:
-		case X86_VENDOR_AMD:
-			if (apic_bigsmp_possible(cmdline_apic))
-				return;
-			break;
-		}
-	}
-	pr_info("Limiting to 8 possible CPUs\n");
-	set_nr_cpu_ids(8);
-}
-
-void __init x86_32_install_bigsmp(void)
-{
-	if (nr_cpu_ids > 8 && !xen_pv_domain())
-		apic_bigsmp_force();
-}
-
 void __init x86_32_probe_apic(void)
 {
 	if (!cmdline_apic) {
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 54194f5995de..315766440201 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -632,7 +632,7 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
 	 * (model = 0x14) and later actually support it.
 	 * (AMD Erratum #110, docId: 25759).
 	 */
-	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM)) {
+	if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) {
 		clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
 		if (!rdmsrl_amd_safe(0xc001100d, &value)) {
 			value &= ~BIT_64(32);
@@ -1105,8 +1105,8 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/*
 	 * K8 doesn't have 2M/4M entries in the L2 TLB so read out the L1 TLB
@@ -1119,26 +1119,26 @@ static void cpu_detect_tlb_amd(struct cpuinfo_x86 *c)
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		/* Erratum 658 */
 		if (c->x86 == 0x15 && c->x86_model <= 0x1f) {
-			tlb_lli_2m[ENTRIES] = 1024;
+			tlb_lli_2m = 1024;
 		} else {
 			cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-			tlb_lli_2m[ENTRIES] = eax & 0xff;
+			tlb_lli_2m = eax & 0xff;
 		}
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
 }
 
 static const struct cpu_dev amd_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index e6fa03ed9172..b3a520959b51 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -8,21 +8,19 @@
  *	Andi Kleen / Andreas Herrmann	: CPUID4 emulation on AMD.
  */
 
-#include <linux/slab.h>
 #include <linux/cacheinfo.h>
+#include <linux/capability.h>
 #include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
-#include <linux/sched.h>
-#include <linux/capability.h>
-#include <linux/sysfs.h>
 #include <linux/pci.h>
 #include <linux/stop_machine.h>
+#include <linux/sysfs.h>
 
-#include <asm/cpufeature.h>
-#include <asm/cacheinfo.h>
 #include <asm/amd_nb.h>
-#include <asm/smp.h>
+#include <asm/cacheinfo.h>
+#include <asm/cpufeature.h>
 #include <asm/mtrr.h>
+#include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 #include "cpu.h"
@@ -31,7 +29,6 @@
 #define LVL_1_DATA	2
 #define LVL_2		3
 #define LVL_3		4
-#define LVL_TRACE	5
 
 /* Shared last level cache maps */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
@@ -96,10 +93,6 @@ static const struct _cache_table cache_table[] =
 	{ 0x66, LVL_1_DATA, 8 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x67, LVL_1_DATA, 16 },	/* 4-way set assoc, sectored cache, 64 byte line size */
 	{ 0x68, LVL_1_DATA, 32 },	/* 4-way set assoc, sectored cache, 64 byte line size */
-	{ 0x70, LVL_TRACE,  12 },	/* 8-way set assoc */
-	{ 0x71, LVL_TRACE,  16 },	/* 8-way set assoc */
-	{ 0x72, LVL_TRACE,  32 },	/* 8-way set assoc */
-	{ 0x73, LVL_TRACE,  64 },	/* 8-way set assoc */
 	{ 0x78, LVL_2,      MB(1) },	/* 4-way set assoc, 64 byte line size */
 	{ 0x79, LVL_2,      128 },	/* 8-way set assoc, sectored cache, 64 byte line size */
 	{ 0x7a, LVL_2,      256 },	/* 8-way set assoc, sectored cache, 64 byte line size */
@@ -787,19 +780,13 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			}
 		}
 	}
-	/*
-	 * Don't use cpuid2 if cpuid4 is supported. For P4, we use cpuid2 for
-	 * trace cache
-	 */
-	if ((!ci->num_leaves || c->x86 == 15) && c->cpuid_level > 1) {
+
+	/* Don't use CPUID(2) if CPUID(4) is supported. */
+	if (!ci->num_leaves && c->cpuid_level > 1) {
 		/* supports eax=2  call */
 		int j, n;
 		unsigned int regs[4];
 		unsigned char *dp = (unsigned char *)regs;
-		int only_trace = 0;
-
-		if (ci->num_leaves && c->x86 == 15)
-			only_trace = 1;
 
 		/* Number of times to iterate */
 		n = cpuid_eax(2) & 0xFF;
@@ -808,7 +795,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 			/* If bit 31 is set, this is an unknown format */
-			for (j = 0 ; j < 3 ; j++)
+			for (j = 0 ; j < 4 ; j++)
 				if (regs[j] & (1 << 31))
 					regs[j] = 0;
 
@@ -820,8 +807,6 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 				/* look up this descriptor in the table */
 				while (cache_table[k].descriptor != 0) {
 					if (cache_table[k].descriptor == des) {
-						if (only_trace && cache_table[k].cache_type != LVL_TRACE)
-							break;
 						switch (cache_table[k].cache_type) {
 						case LVL_1_INST:
 							l1i += cache_table[k].size;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8b49b1338f76..88a6707b765c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -667,8 +667,8 @@ static void filter_cpuid_features(struct cpuinfo_x86 *c, bool warn)
 		if (!warn)
 			continue;
 
-		pr_warn("CPU: CPU feature " X86_CAP_FMT " disabled, no CPUID level 0x%x\n",
-			x86_cap_flag(df->feature), df->level);
+		pr_warn("CPU: CPU feature %s disabled, no CPUID level 0x%x\n",
+			x86_cap_flags[df->feature], df->level);
 	}
 }
 
@@ -846,13 +846,13 @@ void cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 	c->x86_cache_size = l2size;
 }
 
-u16 __read_mostly tlb_lli_4k[NR_INFO];
-u16 __read_mostly tlb_lli_2m[NR_INFO];
-u16 __read_mostly tlb_lli_4m[NR_INFO];
-u16 __read_mostly tlb_lld_4k[NR_INFO];
-u16 __read_mostly tlb_lld_2m[NR_INFO];
-u16 __read_mostly tlb_lld_4m[NR_INFO];
-u16 __read_mostly tlb_lld_1g[NR_INFO];
+u16 __read_mostly tlb_lli_4k;
+u16 __read_mostly tlb_lli_2m;
+u16 __read_mostly tlb_lli_4m;
+u16 __read_mostly tlb_lld_4k;
+u16 __read_mostly tlb_lld_2m;
+u16 __read_mostly tlb_lld_4m;
+u16 __read_mostly tlb_lld_1g;
 
 static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 {
@@ -860,12 +860,10 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		this_cpu->c_detect_tlb(c);
 
 	pr_info("Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n",
-		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
-		tlb_lli_4m[ENTRIES]);
+		tlb_lli_4k, tlb_lli_2m, tlb_lli_4m);
 
 	pr_info("Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d, 1GB %d\n",
-		tlb_lld_4k[ENTRIES], tlb_lld_2m[ENTRIES],
-		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
+		tlb_lld_4k, tlb_lld_2m, tlb_lld_4m, tlb_lld_1g);
 }
 
 void get_cpu_vendor(struct cpuinfo_x86 *c)
@@ -1164,7 +1162,7 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 
 	VULNWL_INTEL(INTEL_CORE_YONAH,		NO_SSB),
 
-	VULNWL_INTEL(INTEL_ATOM_AIRMONT_MID,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
+	VULNWL_INTEL(INTEL_ATOM_SILVERMONT_MID2,NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | MSBDS_ONLY),
 	VULNWL_INTEL(INTEL_ATOM_AIRMONT_NP,	NO_SSB | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT),
 
 	VULNWL_INTEL(INTEL_ATOM_GOLDMONT,	NO_MDS | NO_L1TF | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO),
@@ -1479,15 +1477,96 @@ static void detect_nopl(void)
 #endif
 }
 
+static inline bool parse_set_clear_cpuid(char *arg, bool set)
+{
+	char *opt;
+	int taint = 0;
+
+	while (arg) {
+		bool found __maybe_unused = false;
+		unsigned int bit;
+
+		opt = strsep(&arg, ",");
+
+		/*
+		 * Handle naked numbers first for feature flags which don't
+		 * have names. It doesn't make sense for a bug not to have a
+		 * name so don't handle bug flags here.
+		 */
+		if (!kstrtouint(opt, 10, &bit)) {
+			if (bit < NCAPINTS * 32) {
+
+				if (set) {
+					pr_warn("setcpuid: force-enabling CPU feature flag:");
+					setup_force_cpu_cap(bit);
+				} else {
+					pr_warn("clearcpuid: force-disabling CPU feature flag:");
+					setup_clear_cpu_cap(bit);
+				}
+				/* empty-string, i.e., ""-defined feature flags */
+				if (!x86_cap_flags[bit])
+					pr_cont(" %d:%d\n", bit >> 5, bit & 31);
+				else
+					pr_cont(" %s\n", x86_cap_flags[bit]);
+
+				taint++;
+			}
+			/*
+			 * The assumption is that there are no feature names with only
+			 * numbers in the name thus go to the next argument.
+			 */
+			continue;
+		}
+
+		for (bit = 0; bit < 32 * (NCAPINTS + NBUGINTS); bit++) {
+			const char *flag;
+			const char *kind;
+
+			if (bit < 32 * NCAPINTS) {
+				flag = x86_cap_flags[bit];
+				kind = "feature";
+			} else {
+				kind = "bug";
+				flag = x86_bug_flags[bit - (32 * NCAPINTS)];
+			}
+
+			if (!flag)
+				continue;
+
+			if (strcmp(flag, opt))
+				continue;
+
+			if (set) {
+				pr_warn("setcpuid: force-enabling CPU %s flag: %s\n",
+					kind, flag);
+				setup_force_cpu_cap(bit);
+			} else {
+				pr_warn("clearcpuid: force-disabling CPU %s flag: %s\n",
+					kind, flag);
+				setup_clear_cpu_cap(bit);
+			}
+			taint++;
+			found = true;
+			break;
+		}
+
+		if (!found)
+			pr_warn("%s: unknown CPU flag: %s", set ? "setcpuid" : "clearcpuid", opt);
+	}
+
+	return taint;
+}
+
+
 /*
  * We parse cpu parameters early because fpu__init_system() is executed
  * before parse_early_param().
  */
 static void __init cpu_parse_early_param(void)
 {
+	bool cpuid_taint = false;
 	char arg[128];
-	char *argptr = arg, *opt;
-	int arglen, taint = 0;
+	int arglen;
 
 #ifdef CONFIG_X86_32
 	if (cmdline_find_option_bool(boot_command_line, "no387"))
@@ -1519,61 +1598,17 @@ static void __init cpu_parse_early_param(void)
 		setup_clear_cpu_cap(X86_FEATURE_FRED);
 
 	arglen = cmdline_find_option(boot_command_line, "clearcpuid", arg, sizeof(arg));
-	if (arglen <= 0)
-		return;
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, false);
 
-	pr_info("Clearing CPUID bits:");
+	arglen = cmdline_find_option(boot_command_line, "setcpuid", arg, sizeof(arg));
+	if (arglen > 0)
+		cpuid_taint |= parse_set_clear_cpuid(arg, true);
 
-	while (argptr) {
-		bool found __maybe_unused = false;
-		unsigned int bit;
-
-		opt = strsep(&argptr, ",");
-
-		/*
-		 * Handle naked numbers first for feature flags which don't
-		 * have names.
-		 */
-		if (!kstrtouint(opt, 10, &bit)) {
-			if (bit < NCAPINTS * 32) {
-
-				/* empty-string, i.e., ""-defined feature flags */
-				if (!x86_cap_flags[bit])
-					pr_cont(" " X86_CAP_FMT_NUM, x86_cap_flag_num(bit));
-				else
-					pr_cont(" " X86_CAP_FMT, x86_cap_flag(bit));
-
-				setup_clear_cpu_cap(bit);
-				taint++;
-			}
-			/*
-			 * The assumption is that there are no feature names with only
-			 * numbers in the name thus go to the next argument.
-			 */
-			continue;
-		}
-
-		for (bit = 0; bit < 32 * NCAPINTS; bit++) {
-			if (!x86_cap_flag(bit))
-				continue;
-
-			if (strcmp(x86_cap_flag(bit), opt))
-				continue;
-
-			pr_cont(" %s", opt);
-			setup_clear_cpu_cap(bit);
-			taint++;
-			found = true;
-			break;
-		}
-
-		if (!found)
-			pr_cont(" (unknown: %s)", opt);
-	}
-	pr_cont("\n");
-
-	if (taint)
+	if (cpuid_taint) {
+		pr_warn("!!! setcpuid=/clearcpuid= in use, this is for TESTING ONLY, may break things horribly. Tainting kernel.\n");
 		add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+	}
 }
 
 /*
@@ -1962,9 +1997,15 @@ static __init void identify_boot_cpu(void)
 	lkgs_init();
 }
 
-void identify_secondary_cpu(struct cpuinfo_x86 *c)
+void identify_secondary_cpu(unsigned int cpu)
 {
-	BUG_ON(c == &boot_cpu_data);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	/* Copy boot_cpu_data only on the first bringup */
+	if (!c->initialized)
+		*c = boot_cpu_data;
+	c->cpu_index = cpu;
+
 	identify_cpu(c);
 #ifdef CONFIG_X86_32
 	enable_sep_cpu();
@@ -1975,6 +2016,7 @@ void identify_secondary_cpu(struct cpuinfo_x86 *c)
 		update_gds_msr();
 
 	tsx_ap_init();
+	c->initialized = true;
 }
 
 void print_cpu_info(struct cpuinfo_x86 *c)
@@ -2005,15 +2047,23 @@ void print_cpu_info(struct cpuinfo_x86 *c)
 }
 
 /*
- * clearcpuid= was already parsed in cpu_parse_early_param().  This dummy
- * function prevents it from becoming an environment variable for init.
+ * clearcpuid= and setcpuid= were already parsed in cpu_parse_early_param().
+ * These dummy functions prevent them from becoming an environment variable for
+ * init.
  */
+
 static __init int setup_clearcpuid(char *arg)
 {
 	return 1;
 }
 __setup("clearcpuid=", setup_clearcpuid);
 
+static __init int setup_setcpuid(char *arg)
+{
+	return 1;
+}
+__setup("setcpuid=", setup_setcpuid);
+
 DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
 	.current_task	= &init_task,
 	.preempt_count	= INIT_PREEMPT_COUNT,
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 1beccefbaff9..51deb60a9d26 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -33,14 +33,6 @@ struct cpu_dev {
 #endif
 };
 
-struct _tlb_table {
-	unsigned char descriptor;
-	char tlb_type;
-	unsigned int entries;
-	/* unsigned int ways; */
-	char info[128];
-};
-
 #define cpu_dev_register(cpu_devX) \
 	static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
 	__section(".x86_cpu_dev.init") = \
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 8bd84114c2d9..df838e3bdbe0 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -45,6 +45,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AES,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_SHA_NI,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_GFNI,			X86_FEATURE_XMM2      },
+	{ X86_FEATURE_AVX_VNNI,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_FMA,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VAES,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VPCLMULQDQ,		X86_FEATURE_AVX       },
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 9651275aecd1..dfec2c61e354 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -153,8 +153,8 @@ static void geode_configure(void)
 	u8 ccr3;
 	local_irq_save(flags);
 
-	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+	/* Suspend on halt power saving */
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x08);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */
diff --git a/arch/x86/kernel/cpu/debugfs.c b/arch/x86/kernel/cpu/debugfs.c
index cacfd3f6abef..1976fef2dfe5 100644
--- a/arch/x86/kernel/cpu/debugfs.c
+++ b/arch/x86/kernel/cpu/debugfs.c
@@ -16,8 +16,8 @@ static int cpu_debug_show(struct seq_file *m, void *p)
 	if (!c->initialized)
 		return 0;
 
-	seq_printf(m, "initial_apicid:      %x\n", c->topo.initial_apicid);
-	seq_printf(m, "apicid:              %x\n", c->topo.apicid);
+	seq_printf(m, "initial_apicid:	    0x%x\n", c->topo.initial_apicid);
+	seq_printf(m, "apicid:		    0x%x\n", c->topo.apicid);
 	seq_printf(m, "pkg_id:              %u\n", c->topo.pkg_id);
 	seq_printf(m, "die_id:              %u\n", c->topo.die_id);
 	seq_printf(m, "cu_id:               %u\n", c->topo.cu_id);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index c5191b06f9f2..6af4a4a90a52 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -240,26 +240,26 @@ static void cpu_detect_tlb_hygon(struct cpuinfo_x86 *c)
 
 	cpuid(0x80000006, &eax, &ebx, &ecx, &edx);
 
-	tlb_lld_4k[ENTRIES] = (ebx >> 16) & mask;
-	tlb_lli_4k[ENTRIES] = ebx & mask;
+	tlb_lld_4k = (ebx >> 16) & mask;
+	tlb_lli_4k = ebx & mask;
 
 	/* Handle DTLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!((eax >> 16) & mask))
-		tlb_lld_2m[ENTRIES] = (cpuid_eax(0x80000005) >> 16) & 0xff;
+		tlb_lld_2m = (cpuid_eax(0x80000005) >> 16) & 0xff;
 	else
-		tlb_lld_2m[ENTRIES] = (eax >> 16) & mask;
+		tlb_lld_2m = (eax >> 16) & mask;
 
 	/* a 4M entry uses two 2M entries */
-	tlb_lld_4m[ENTRIES] = tlb_lld_2m[ENTRIES] >> 1;
+	tlb_lld_4m = tlb_lld_2m >> 1;
 
 	/* Handle ITLB 2M and 4M sizes, fall back to L1 if L2 is disabled */
 	if (!(eax & mask)) {
 		cpuid(0x80000005, &eax, &ebx, &ecx, &edx);
-		tlb_lli_2m[ENTRIES] = eax & 0xff;
+		tlb_lli_2m = eax & 0xff;
 	} else
-		tlb_lli_2m[ENTRIES] = eax & mask;
+		tlb_lli_2m = eax & mask;
 
-	tlb_lli_4m[ENTRIES] = tlb_lli_2m[ENTRIES] >> 1;
+	tlb_lli_4m = tlb_lli_2m >> 1;
 }
 
 static const struct cpu_dev hygon_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3dce22f00dc3..291c82816797 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1,40 +1,31 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/kernel.h>
-#include <linux/pgtable.h>
 
-#include <linux/string.h>
 #include <linux/bitops.h>
-#include <linux/smp.h>
-#include <linux/sched.h>
-#include <linux/sched/clock.h>
-#include <linux/thread_info.h>
 #include <linux/init.h>
-#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/minmax.h>
+#include <linux/smp.h>
+#include <linux/string.h>
+
+#ifdef CONFIG_X86_64
+#include <linux/topology.h>
+#endif
 
-#include <asm/cpufeature.h>
-#include <asm/msr.h>
 #include <asm/bugs.h>
+#include <asm/cpu_device_id.h>
+#include <asm/cpufeature.h>
 #include <asm/cpu.h>
+#include <asm/hwcap2.h>
 #include <asm/intel-family.h>
 #include <asm/microcode.h>
-#include <asm/hwcap2.h>
-#include <asm/elf.h>
-#include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
+#include <asm/msr.h>
 #include <asm/numa.h>
+#include <asm/resctrl.h>
 #include <asm/thermal.h>
-
-#ifdef CONFIG_X86_64
-#include <linux/topology.h>
-#endif
+#include <asm/uaccess.h>
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_LOCAL_APIC
-#include <asm/mpspec.h>
-#include <asm/apic.h>
-#endif
-
 /*
  * Processors which have self-snooping capability can handle conflicting
  * memory type across CPUs by snooping its own cache. However, there exists
@@ -635,70 +626,90 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 }
 #endif
 
-#define TLB_INST_4K	0x01
-#define TLB_INST_4M	0x02
-#define TLB_INST_2M_4M	0x03
+#define TLB_INST_4K		0x01
+#define TLB_INST_4M		0x02
+#define TLB_INST_2M_4M		0x03
 
-#define TLB_INST_ALL	0x05
-#define TLB_INST_1G	0x06
+#define TLB_INST_ALL		0x05
+#define TLB_INST_1G		0x06
 
-#define TLB_DATA_4K	0x11
-#define TLB_DATA_4M	0x12
-#define TLB_DATA_2M_4M	0x13
-#define TLB_DATA_4K_4M	0x14
+#define TLB_DATA_4K		0x11
+#define TLB_DATA_4M		0x12
+#define TLB_DATA_2M_4M		0x13
+#define TLB_DATA_4K_4M		0x14
 
-#define TLB_DATA_1G	0x16
+#define TLB_DATA_1G		0x16
+#define TLB_DATA_1G_2M_4M	0x17
 
-#define TLB_DATA0_4K	0x21
-#define TLB_DATA0_4M	0x22
-#define TLB_DATA0_2M_4M	0x23
+#define TLB_DATA0_4K		0x21
+#define TLB_DATA0_4M		0x22
+#define TLB_DATA0_2M_4M		0x23
 
-#define STLB_4K		0x41
-#define STLB_4K_2M	0x42
+#define STLB_4K			0x41
+#define STLB_4K_2M		0x42
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of
+ * entries for their respective TLB types.  The 0x63 descriptor is an
+ * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
+ * for 2MB or 4MB pages.  Encode descriptor 0x63 dTLB entry count for
+ * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
+ * intel_tlb_table[] mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES	32
+
+struct _tlb_table {
+	unsigned char descriptor;
+	char tlb_type;
+	unsigned int entries;
+};
 
 static const struct _tlb_table intel_tlb_table[] = {
-	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0x02, TLB_INST_4M,		2,	" TLB_INST 4 MByte pages, full associative" },
-	{ 0x03, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
-	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
-	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages" },
-	{ 0x50, TLB_INST_ALL,		64,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
-	{ 0x55, TLB_INST_2M_4M,		7,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0x56, TLB_DATA0_4M,		16,	" TLB_DATA0 4 MByte pages, 4-way set associative" },
-	{ 0x57, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, 4-way associative" },
-	{ 0x59, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, fully associative" },
-	{ 0x5a, TLB_DATA0_2M_4M,	32,	" TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
-	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
-	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
-	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
-	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
-	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
-	{ 0x76, TLB_INST_2M_4M,		8,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
-	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
-	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
-	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
-	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
-	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xb5, TLB_INST_4K,		64,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xb6, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 8-way set associative" },
-	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
-	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
-	{ 0xc1, STLB_4K_2M,		1024,	" STLB 4 KByte and 2 MByte pages, 8-way associative" },
-	{ 0xc2, TLB_DATA_2M_4M,		16,	" TLB_DATA 2 MByte/4MByte pages, 4-way associative" },
-	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
+	{ 0x01, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages, 4-way set associative */
+	{ 0x02, TLB_INST_4M,		2},	/* TLB_INST 4 MByte pages, full associative */
+	{ 0x03, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	{ 0x04, TLB_DATA_4M,		8},	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	{ 0x05, TLB_DATA_4M,		32},	/* TLB_DATA 4 MByte pages, 4-way set associative */
+	{ 0x0b, TLB_INST_4M,		4},	/* TLB_INST 4 MByte pages, 4-way set associative */
+	{ 0x4f, TLB_INST_4K,		32},	/* TLB_INST 4 KByte pages */
+	{ 0x50, TLB_INST_ALL,		64},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x51, TLB_INST_ALL,		128},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x52, TLB_INST_ALL,		256},	/* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+	{ 0x55, TLB_INST_2M_4M,		7},	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	{ 0x56, TLB_DATA0_4M,		16},	/* TLB_DATA0 4 MByte pages, 4-way set associative */
+	{ 0x57, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, 4-way associative */
+	{ 0x59, TLB_DATA0_4K,		16},	/* TLB_DATA0 4 KByte pages, fully associative */
+	{ 0x5a, TLB_DATA0_2M_4M,	32},	/* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
+	{ 0x5b, TLB_DATA_4K_4M,		64},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x5c, TLB_DATA_4K_4M,		128},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x5d, TLB_DATA_4K_4M,		256},	/* TLB_DATA 4 KByte and 4 MByte pages */
+	{ 0x61, TLB_INST_4K,		48},	/* TLB_INST 4 KByte pages, full associative */
+	{ 0x63, TLB_DATA_1G_2M_4M,	4},	/* TLB_DATA 1 GByte pages, 4-way set associative
+						 * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
+	{ 0x6b, TLB_DATA_4K,		256},	/* TLB_DATA 4 KByte pages, 8-way associative */
+	{ 0x6c, TLB_DATA_2M_4M,		128},	/* TLB_DATA 2 MByte or 4 MByte pages, 8-way associative */
+	{ 0x6d, TLB_DATA_1G,		16},	/* TLB_DATA 1 GByte pages, fully associative */
+	{ 0x76, TLB_INST_2M_4M,		8},	/* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+	{ 0xb0, TLB_INST_4K,		128},	/* TLB_INST 4 KByte pages, 4-way set associative */
+	{ 0xb1, TLB_INST_2M_4M,		4},	/* TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries */
+	{ 0xb2, TLB_INST_4K,		64},	/* TLB_INST 4KByte pages, 4-way set associative */
+	{ 0xb3, TLB_DATA_4K,		128},	/* TLB_DATA 4 KByte pages, 4-way set associative */
+	{ 0xb4, TLB_DATA_4K,		256},	/* TLB_DATA 4 KByte pages, 4-way associative */
+	{ 0xb5, TLB_INST_4K,		64},	/* TLB_INST 4 KByte pages, 8-way set associative */
+	{ 0xb6, TLB_INST_4K,		128},	/* TLB_INST 4 KByte pages, 8-way set associative */
+	{ 0xba, TLB_DATA_4K,		64},	/* TLB_DATA 4 KByte pages, 4-way associative */
+	{ 0xc0, TLB_DATA_4K_4M,		8},	/* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
+	{ 0xc1, STLB_4K_2M,		1024},	/* STLB 4 KByte and 2 MByte pages, 8-way associative */
+	{ 0xc2, TLB_DATA_2M_4M,		16},	/* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
+	{ 0xca, STLB_4K,		512},	/* STLB 4 KByte pages, 4-way associative */
 	{ 0x00, 0, 0 }
 };
 
 static void intel_tlb_lookup(const unsigned char desc)
 {
+	unsigned int entries;
 	unsigned char k;
+
 	if (desc == 0)
 		return;
 
@@ -710,75 +721,58 @@ static void intel_tlb_lookup(const unsigned char desc)
 	if (intel_tlb_table[k].tlb_type == 0)
 		return;
 
+	entries = intel_tlb_table[k].entries;
 	switch (intel_tlb_table[k].tlb_type) {
 	case STLB_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case STLB_4K_2M:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_INST_ALL:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_4K:
-		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4k = max(tlb_lli_4k, entries);
 		break;
 	case TLB_INST_4M:
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_INST_2M_4M:
-		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lli_2m = max(tlb_lli_2m, entries);
+		tlb_lli_4m = max(tlb_lli_4m, entries);
 		break;
 	case TLB_DATA_4K:
 	case TLB_DATA0_4K:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k = max(tlb_lld_4k, entries);
 		break;
 	case TLB_DATA_4M:
 	case TLB_DATA0_4M:
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_2M_4M:
 	case TLB_DATA0_2M_4M:
-		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_2m = max(tlb_lld_2m, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
 	case TLB_DATA_4K_4M:
-		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
-		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_4k = max(tlb_lld_4k, entries);
+		tlb_lld_4m = max(tlb_lld_4m, entries);
 		break;
+	case TLB_DATA_1G_2M_4M:
+		tlb_lld_2m = max(tlb_lld_2m, TLB_0x63_2M_4M_ENTRIES);
+		tlb_lld_4m = max(tlb_lld_4m, TLB_0x63_2M_4M_ENTRIES);
+		fallthrough;
 	case TLB_DATA_1G:
-		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
-			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;
+		tlb_lld_1g = max(tlb_lld_1g, entries);
 		break;
 	}
 }
@@ -799,7 +793,7 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c)
 		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 3 ; j++)
+		for (j = 0 ; j < 4 ; j++)
 			if (regs[j] & (1 << 31))
 				regs[j] = 0;
 
@@ -873,34 +867,3 @@ static const struct cpu_dev intel_cpu_dev = {
 };
 
 cpu_dev_register(intel_cpu_dev);
-
-#define X86_HYBRID_CPU_TYPE_ID_SHIFT	24
-
-/**
- * get_this_hybrid_cpu_type() - Get the type of this hybrid CPU
- *
- * Returns the CPU type [31:24] (i.e., Atom or Core) of a CPU in
- * a hybrid processor. If the processor is not hybrid, returns 0.
- */
-u8 get_this_hybrid_cpu_type(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) >> X86_HYBRID_CPU_TYPE_ID_SHIFT;
-}
-
-/**
- * get_this_hybrid_cpu_native_id() - Get the native id of this hybrid CPU
- *
- * Returns the uarch native ID [23:0] of a CPU in a hybrid processor.
- * If the processor is not hybrid, returns 0.
- */
-u32 get_this_hybrid_cpu_native_id(void)
-{
-	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
-		return 0;
-
-	return cpuid_eax(0x0000001a) &
-	       (BIT_ULL(X86_HYBRID_CPU_TYPE_ID_SHIFT) - 1);
-}
diff --git a/arch/x86/kernel/cpu/mtrr/if.c b/arch/x86/kernel/cpu/mtrr/if.c
index a5c506f6da7f..4049235b1bfe 100644
--- a/arch/x86/kernel/cpu/mtrr/if.c
+++ b/arch/x86/kernel/cpu/mtrr/if.c
@@ -99,7 +99,6 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	char *ptr;
 	char line[LINE_SIZE];
 	int length;
-	size_t linelen;
 
 	memset(line, 0, LINE_SIZE);
 
@@ -108,9 +107,8 @@ mtrr_write(struct file *file, const char __user *buf, size_t len, loff_t * ppos)
 	if (length < 0)
 		return length;
 
-	linelen = strlen(line);
-	ptr = line + linelen - 1;
-	if (linelen && *ptr == '\n')
+	ptr = line + length - 1;
+	if (length && *ptr == '\n')
 		*ptr = '\0';
 
 	if (!strncmp(line, "disable=", 8)) {
diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 59d23cdf4ed0..dd8748c45529 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,6 +2,7 @@
 /*
  * Architecture specific OF callbacks.
  */
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
@@ -313,6 +314,6 @@ void __init x86_flattree_get_config(void)
 	if (initial_dtb)
 		early_memunmap(dt, map_len);
 #endif
-	if (of_have_populated_dt())
+	if (acpi_disabled && of_have_populated_dt())
 		x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
 }
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 166bc0ea3bdf..cace6e8d7cc7 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -118,13 +118,10 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
 		return ret;
 
 	/* replace the text with the new text */
-	if (ftrace_poke_late) {
+	if (ftrace_poke_late)
 		text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
-	} else {
-		mutex_lock(&text_mutex);
-		text_poke((void *)ip, new_code, MCOUNT_INSN_SIZE);
-		mutex_unlock(&text_mutex);
-	}
+	else
+		text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
 	return 0;
 }
 
@@ -321,7 +318,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	unsigned const char op_ref[] = { 0x48, 0x8b, 0x15 };
 	unsigned const char retq[] = { RET_INSN_OPCODE, INT3_INSN_OPCODE };
 	union ftrace_op_code_union op_ptr;
-	void *ret;
+	int ret;
 
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
 		start_offset = (unsigned long)ftrace_regs_caller;
@@ -352,15 +349,15 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
 
 	/* Copy ftrace_caller onto the trampoline memory */
-	ret = text_poke_copy(trampoline, (void *)start_offset, size);
-	if (WARN_ON(!ret))
+	ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
+	if (WARN_ON(ret < 0))
 		goto fail;
 
 	ip = trampoline + size;
 	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
 		__text_gen_insn(ip, JMP32_INSN_OPCODE, ip, x86_return_thunk, JMP32_INSN_SIZE);
 	else
-		text_poke_copy(ip, retq, sizeof(retq));
+		memcpy(ip, retq, sizeof(retq));
 
 	/* No need to test direct calls on created trampolines */
 	if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
@@ -368,7 +365,8 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 		ip = trampoline + (jmp_offset - start_offset);
 		if (WARN_ON(*(char *)ip != 0x75))
 			goto fail;
-		if (!text_poke_copy(ip, x86_nops[2], 2))
+		ret = copy_from_kernel_nofault(ip, x86_nops[2], 2);
+		if (ret < 0)
 			goto fail;
 	}
 
@@ -381,7 +379,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 */
 
 	ptr = (unsigned long *)(trampoline + size + RET_SIZE);
-	text_poke_copy(ptr, &ops, sizeof(unsigned long));
+	*ptr = (unsigned long)ops;
 
 	op_offset -= start_offset;
 	memcpy(&op_ptr, trampoline + op_offset, OP_REF_SIZE);
@@ -397,7 +395,7 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	op_ptr.offset = offset;
 
 	/* put in the new offset to the ftrace_ops */
-	text_poke_copy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
+	memcpy(trampoline + op_offset, &op_ptr, OP_REF_SIZE);
 
 	/* put in the call to the function */
 	mutex_lock(&text_mutex);
@@ -407,9 +405,9 @@ create_trampoline(struct ftrace_ops *ops, unsigned int *tramp_size)
 	 * the depth accounting before the call already.
 	 */
 	dest = ftrace_ops_get_func(ops);
-	text_poke_copy_locked(trampoline + call_offset,
-	      text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
-	      CALL_INSN_SIZE, false);
+	memcpy(trampoline + call_offset,
+	       text_gen_insn(CALL_INSN_OPCODE, trampoline + call_offset, dest),
+	       CALL_INSN_SIZE);
 	mutex_unlock(&text_mutex);
 
 	/* ALLOC_TRAMP flags lets us know we created it */
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 385e3a5fc304..feca4f20b06a 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -25,8 +25,10 @@
 #include <asm/posted_intr.h>
 #include <asm/irq_remapping.h>
 
+#if defined(CONFIG_X86_LOCAL_APIC) || defined(CONFIG_X86_THERMAL_VECTOR)
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
+#endif
 
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 7a422a6c5983..3be9b3342c67 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -838,7 +838,6 @@ static void __init kvm_guest_init(void)
 #ifdef CONFIG_SMP
 	if (pv_tlb_flush_supported()) {
 		pv_ops.mmu.flush_tlb_multi = kvm_flush_tlb_multi;
-		pv_ops.mmu.tlb_remove_table = tlb_remove_table;
 		pr_info("KVM setup pv remote TLB flush\n");
 	}
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index a286f32c5503..9929be7a76e7 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -161,21 +161,18 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
 		}
 
 		if (apply) {
-			void *wr_loc = module_writable_address(me, loc);
-
-			if (memcmp(wr_loc, &zero, size)) {
+			if (memcmp(loc, &zero, size)) {
 				pr_err("x86/modules: Invalid relocation target, existing value is nonzero for type %d, loc %p, val %Lx\n",
 				       (int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			write(wr_loc, &val, size);
+			write(loc, &val, size);
 		} else {
 			if (memcmp(loc, &val, size)) {
 				pr_warn("x86/modules: Invalid relocation target, existing value does not match expected value for type %d, loc %p, val %Lx\n",
 					(int)ELF64_R_TYPE(rel[i].r_info), loc, val);
 				return -ENOEXEC;
 			}
-			/* FIXME: needs care for ROX module allocations */
 			write(loc, &zero, size);
 		}
 	}
@@ -242,7 +239,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *me)
 {
-	const Elf_Shdr *s, *alt = NULL,
+	const Elf_Shdr *s, *alt = NULL, *locks = NULL,
 		*orc = NULL, *orc_ip = NULL,
 		*retpolines = NULL, *returns = NULL, *ibt_endbr = NULL,
 		*calls = NULL, *cfi = NULL;
@@ -251,6 +248,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
 		if (!strcmp(".altinstructions", secstrings + s->sh_name))
 			alt = s;
+		if (!strcmp(".smp_locks", secstrings + s->sh_name))
+			locks = s;
 		if (!strcmp(".orc_unwind", secstrings + s->sh_name))
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
@@ -281,20 +280,20 @@ int module_finalize(const Elf_Ehdr *hdr,
 			csize = cfi->sh_size;
 		}
 
-		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize, me);
+		apply_fineibt(rseg, rseg + rsize, cseg, cseg + csize);
 	}
 	if (retpolines) {
 		void *rseg = (void *)retpolines->sh_addr;
-		apply_retpolines(rseg, rseg + retpolines->sh_size, me);
+		apply_retpolines(rseg, rseg + retpolines->sh_size);
 	}
 	if (returns) {
 		void *rseg = (void *)returns->sh_addr;
-		apply_returns(rseg, rseg + returns->sh_size, me);
+		apply_returns(rseg, rseg + returns->sh_size);
 	}
 	if (alt) {
 		/* patch .altinstructions */
 		void *aseg = (void *)alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size, me);
+		apply_alternatives(aseg, aseg + alt->sh_size);
 	}
 	if (calls || alt) {
 		struct callthunk_sites cs = {};
@@ -313,28 +312,8 @@ int module_finalize(const Elf_Ehdr *hdr,
 	}
 	if (ibt_endbr) {
 		void *iseg = (void *)ibt_endbr->sh_addr;
-		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size, me);
+		apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size);
 	}
-
-	if (orc && orc_ip)
-		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
-				   (void *)orc->sh_addr, orc->sh_size);
-
-	return 0;
-}
-
-int module_post_finalize(const Elf_Ehdr *hdr,
-			 const Elf_Shdr *sechdrs,
-			 struct module *me)
-{
-	const Elf_Shdr *s, *locks = NULL;
-	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
-
-	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
-		if (!strcmp(".smp_locks", secstrings + s->sh_name))
-			locks = s;
-	}
-
 	if (locks) {
 		void *lseg = (void *)locks->sh_addr;
 		void *text = me->mem[MOD_TEXT].base;
@@ -344,6 +323,10 @@ int module_post_finalize(const Elf_Ehdr *hdr,
 					    text, text_end);
 	}
 
+	if (orc && orc_ip)
+		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
+				   (void *)orc->sh_addr, orc->sh_size);
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1ccaa3397a67..2aa251d0b308 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -59,21 +59,6 @@ void __init native_pv_lock_init(void)
 		static_branch_enable(&virt_spin_lock_key);
 }
 
-#ifndef CONFIG_PT_RECLAIM
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -195,7 +180,6 @@ struct paravirt_patch_template pv_ops = {
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
 	.mmu.flush_tlb_multi	= native_flush_tlb_multi,
-	.mmu.tlb_remove_table	= native_tlb_remove_table,
 
 	.mmu.exit_mmap		= paravirt_nop,
 	.mmu.notify_page_enc_status_changed	= paravirt_nop,
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c10850ae6f09..8ecf1bf57103 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -190,7 +190,7 @@ static void ap_starting(void)
 	apic_ap_setup();
 
 	/* Save the processor parameters. */
-	smp_store_cpu_info(cpuid);
+	identify_secondary_cpu(cpuid);
 
 	/*
 	 * The topology information must be up to date before
@@ -215,7 +215,7 @@ static void ap_calibrate_delay(void)
 {
 	/*
 	 * Calibrate the delay loop and update loops_per_jiffy in cpu_data.
-	 * smp_store_cpu_info() stored a value that is close but not as
+	 * identify_secondary_cpu() stored a value that is close but not as
 	 * accurate as the value just calculated.
 	 *
 	 * As this is invoked after the TSC synchronization check,
@@ -315,26 +315,6 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
-/*
- * The bootstrap kernel entry code has set these up. Save them for
- * a given CPU
- */
-void smp_store_cpu_info(int id)
-{
-	struct cpuinfo_x86 *c = &cpu_data(id);
-
-	/* Copy boot_cpu_data only on the first bringup */
-	if (!c->initialized)
-		*c = boot_cpu_data;
-	c->cpu_index = id;
-	/*
-	 * During boot time, CPU0 has this setup already. Save the info when
-	 * bringing up an AP.
-	 */
-	identify_secondary_cpu(c);
-	c->initialized = true;
-}
-
 static bool
 topology_same_node(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 {
@@ -1262,43 +1242,9 @@ void play_dead_common(void)
  * We need to flush the caches before going to sleep, lest we have
  * dirty data in our caches when we come back up.
  */
-static inline void mwait_play_dead(void)
+void __noreturn mwait_play_dead(unsigned int eax_hint)
 {
 	struct mwait_cpu_dead *md = this_cpu_ptr(&mwait_cpu_dead);
-	unsigned int eax, ebx, ecx, edx;
-	unsigned int highest_cstate = 0;
-	unsigned int highest_subcstate = 0;
-	int i;
-
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
-	    boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
-		return;
-	if (!this_cpu_has(X86_FEATURE_MWAIT))
-		return;
-	if (!this_cpu_has(X86_FEATURE_CLFLUSH))
-		return;
-
-	eax = CPUID_LEAF_MWAIT;
-	ecx = 0;
-	native_cpuid(&eax, &ebx, &ecx, &edx);
-
-	/*
-	 * eax will be 0 if EDX enumeration is not valid.
-	 * Initialized below to cstate, sub_cstate value when EDX is valid.
-	 */
-	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED)) {
-		eax = 0;
-	} else {
-		edx >>= MWAIT_SUBSTATE_SIZE;
-		for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
-			if (edx & MWAIT_SUBSTATE_MASK) {
-				highest_cstate = i;
-				highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
-			}
-		}
-		eax = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
-			(highest_subcstate - 1);
-	}
 
 	/* Set up state for the kexec() hack below */
 	md->status = CPUDEAD_MWAIT_WAIT;
@@ -1319,7 +1265,7 @@ static inline void mwait_play_dead(void)
 		mb();
 		__monitor(md, 0, 0);
 		mb();
-		__mwait(eax, 0);
+		__mwait(eax_hint, 0);
 
 		if (READ_ONCE(md->control) == CPUDEAD_MWAIT_KEXEC_HLT) {
 			/*
@@ -1391,9 +1337,9 @@ void native_play_dead(void)
 	play_dead_common();
 	tboot_shutdown(TB_SHUTDOWN_WFS);
 
-	mwait_play_dead();
-	if (cpuidle_play_dead())
-		hlt_play_dead();
+	/* Below returns only on error. */
+	cpuidle_play_dead();
+	hlt_play_dead();
 }
 
 #else /* ... !CONFIG_HOTPLUG_CPU */
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index deeb02825670..48e6cc1cb017 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -152,7 +152,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT,	&freq_desc_byt),
 	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID,	&freq_desc_tng),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT,	&freq_desc_cht),
-	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_MID,	&freq_desc_ann),
+	X86_MATCH_VFM(INTEL_ATOM_SILVERMONT_MID2,	&freq_desc_ann),
 	X86_MATCH_VFM(INTEL_ATOM_AIRMONT_NP,	&freq_desc_lgm),
 	{}
 };
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d4ac4a1f8b81..8160870398b9 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7460,7 +7460,7 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
-static void kvm_mmu_start_lpage_recovery(struct once *once)
+static int kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
@@ -7471,13 +7471,14 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm_nx_huge_page_recovery_worker_kill,
 				      kvm, "kvm-nx-lpage-recovery");
 
-	if (!nx_thread)
-		return;
+	if (IS_ERR(nx_thread))
+		return PTR_ERR(nx_thread);
 
 	vhost_task_start(nx_thread);
 
 	/* Make the task visible only once it is fully started. */
 	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+	return 0;
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
@@ -7485,10 +7486,7 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
-	if (!kvm->arch.nx_huge_page_recovery_thread)
-		return -ENOMEM;
-	return 0;
+	return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e..ed8a3cb53961 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5084,6 +5084,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		load_vmcs12_host_state(vcpu, vmcs12);
 
+		/*
+		 * Process events if an injectable IRQ or NMI is pending, even
+		 * if the event is blocked (RFLAGS.IF is cleared on VM-Exit).
+		 * If an event became pending while L2 was active, KVM needs to
+		 * either inject the event or request an IRQ/NMI window.  SMIs
+		 * don't need to be processed as SMM is mutually exclusive with
+		 * non-root mode.  INIT/SIPI don't need to be checked as INIT
+		 * is blocked post-VMXON, and SIPIs are ignored.
+		 */
+		if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		return;
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29..6fc4ddc606bd 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12877,11 +12877,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		mutex_unlock(&kvm->slots_lock);
 	}
 	kvm_unload_vcpu_mmus(kvm);
+	kvm_destroy_vcpus(kvm);
 	kvm_x86_call(vm_destroy)(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
-	kvm_destroy_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 8a59c61624c2..9bbe2819881f 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -56,7 +56,7 @@ ifeq ($(CONFIG_X86_32),y)
         lib-y += string_32.o
         lib-y += memmove_32.o
         lib-y += cmpxchg8b_emu.o
-ifneq ($(CONFIG_X86_CMPXCHG64),y)
+ifneq ($(CONFIG_X86_CX8),y)
         lib-y += atomic64_386_32.o
 endif
 else
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 1c96be769adc..d4bb24347ff8 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -7,7 +7,7 @@
 
 .text
 
-#ifndef CONFIG_X86_CMPXCHG64
+#ifndef CONFIG_X86_CX8
 
 /*
  * Emulate 'cmpxchg8b (%esi)' on UP
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index ac41b1e0940d..f288aad8dc74 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -582,7 +582,7 @@ static void __init lowmem_pfn_init(void)
 	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
 
 #define MSG_HIGHMEM_TRIMMED \
-	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
+	"Warning: only 4GB will be used. Support for for CONFIG_HIGHMEM64G was removed!\n"
 /*
  * We have more RAM than fits into lowmem - we try to put it into
  * highmem, also taking the highmem=x boot parameter into account:
@@ -606,18 +606,13 @@ static void __init highmem_pfn_init(void)
 #ifndef CONFIG_HIGHMEM
 	/* Maximum memory usable is what is directly addressable */
 	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
-	if (max_pfn > MAX_NONPAE_PFN)
-		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
-	else
-		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
 	max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
-#ifndef CONFIG_HIGHMEM64G
 	if (max_pfn > MAX_NONPAE_PFN) {
 		max_pfn = MAX_NONPAE_PFN;
 		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
 	}
-#endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
 }
 
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 38ff7791a9c7..42c90b420773 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -503,6 +503,14 @@ void iounmap(volatile void __iomem *addr)
 }
 EXPORT_SYMBOL(iounmap);
 
+void *arch_memremap_wb(phys_addr_t phys_addr, size_t size, unsigned long flags)
+{
+	if ((flags & MEMREMAP_DEC) || cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+		return (void __force *)ioremap_cache(phys_addr, size);
+
+	return (void __force *)ioremap_encrypted(phys_addr, size);
+}
+
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
  * access
diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
index 11a93542d198..3c306de52fd4 100644
--- a/arch/x86/mm/kaslr.c
+++ b/arch/x86/mm/kaslr.c
@@ -113,8 +113,14 @@ void __init kernel_randomize_memory(void)
 	memory_tb = DIV_ROUND_UP(max_pfn << PAGE_SHIFT, 1UL << TB_SHIFT) +
 		CONFIG_RANDOMIZE_MEMORY_PHYSICAL_PADDING;
 
-	/* Adapt physical memory region size based on available memory */
-	if (memory_tb < kaslr_regions[0].size_tb)
+	/*
+	 * Adapt physical memory region size based on available memory,
+	 * except when CONFIG_PCI_P2PDMA is enabled. P2PDMA exposes the
+	 * device BAR space assuming the direct map space is large enough
+	 * for creating a ZONE_DEVICE mapping in the direct map corresponding
+	 * to the physical BAR address.
+	 */
+	if (!IS_ENABLED(CONFIG_PCI_P2PDMA) && (memory_tb < kaslr_regions[0].size_tb))
 		kaslr_regions[0].size_tb = memory_tb;
 
 	/*
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index b8a6ffffb451..5ed2109211da 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -84,7 +84,6 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 {
 	unsigned long gap = rlim_stack->rlim_cur;
 	unsigned long pad = stack_maxrandom_size(task_size) + stack_guard_gap;
-	unsigned long gap_min, gap_max;
 
 	/* Values close to RLIM_INFINITY can overflow. */
 	if (gap + pad > gap)
@@ -94,13 +93,7 @@ static unsigned long mmap_base(unsigned long rnd, unsigned long task_size,
 	 * Top of mmap area (just below the process stack).
 	 * Leave an at least ~128 MB hole with possible stack randomization.
 	 */
-	gap_min = SIZE_128M;
-	gap_max = (task_size / 6) * 5;
-
-	if (gap < gap_min)
-		gap = gap_min;
-	else if (gap > gap_max)
-		gap = gap_max;
+	gap = clamp(gap, SIZE_128M, (task_size / 6) * 5);
 
 	return PAGE_ALIGN(task_size - gap - rnd);
 }
diff --git a/arch/x86/mm/pat/cpa-test.c b/arch/x86/mm/pat/cpa-test.c
index 3d2f7f0a6ed1..ad3c1feec990 100644
--- a/arch/x86/mm/pat/cpa-test.c
+++ b/arch/x86/mm/pat/cpa-test.c
@@ -183,7 +183,7 @@ static int pageattr_test(void)
 			break;
 
 		case 1:
-			err = change_page_attr_set(addrs, len[1], PAGE_CPA_TEST, 1);
+			err = change_page_attr_set(addrs, len[i], PAGE_CPA_TEST, 1);
 			break;
 
 		case 2:
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index ef4514d64c05..d1740159029e 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -73,6 +73,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
 #define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
+#define CPA_COLLAPSE 16 /* try to collapse large pages */
 
 static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm)
 {
@@ -105,6 +106,18 @@ static void split_page_count(int level)
 	direct_pages_count[level - 1] += PTRS_PER_PTE;
 }
 
+static void collapse_page_count(int level)
+{
+	direct_pages_count[level]++;
+	if (system_state == SYSTEM_RUNNING) {
+		if (level == PG_LEVEL_2M)
+			count_vm_event(DIRECT_MAP_LEVEL2_COLLAPSE);
+		else if (level == PG_LEVEL_1G)
+			count_vm_event(DIRECT_MAP_LEVEL3_COLLAPSE);
+	}
+	direct_pages_count[level - 1] -= PTRS_PER_PTE;
+}
+
 void arch_report_meminfo(struct seq_file *m)
 {
 	seq_printf(m, "DirectMap4k:    %8lu kB\n",
@@ -122,6 +135,7 @@ void arch_report_meminfo(struct seq_file *m)
 }
 #else
 static inline void split_page_count(int level) { }
+static inline void collapse_page_count(int level) { }
 #endif
 
 #ifdef CONFIG_X86_CPA_STATISTICS
@@ -211,14 +225,14 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 	return addr >= start && addr < end;
 }
 
+#ifdef CONFIG_X86_64
+
 static inline int
 within_inclusive(unsigned long addr, unsigned long start, unsigned long end)
 {
 	return addr >= start && addr <= end;
 }
 
-#ifdef CONFIG_X86_64
-
 /*
  * The kernel image is mapped into two places in the virtual address space
  * (addresses without KASLR, of course):
@@ -394,16 +408,49 @@ static void __cpa_flush_tlb(void *data)
 		flush_tlb_one_kernel(fix_addr(__cpa_addr(cpa, i)));
 }
 
-static void cpa_flush(struct cpa_data *data, int cache)
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables);
+
+static void cpa_collapse_large_pages(struct cpa_data *cpa)
+{
+	unsigned long start, addr, end;
+	struct ptdesc *ptdesc, *tmp;
+	LIST_HEAD(pgtables);
+	int collapsed = 0;
+	int i;
+
+	if (cpa->flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
+		for (i = 0; i < cpa->numpages; i++)
+			collapsed += collapse_large_pages(__cpa_addr(cpa, i),
+							  &pgtables);
+	} else {
+		addr = __cpa_addr(cpa, 0);
+		start = addr & PMD_MASK;
+		end = addr + PAGE_SIZE * cpa->numpages;
+
+		for (addr = start; within(addr, start, end); addr += PMD_SIZE)
+			collapsed += collapse_large_pages(addr, &pgtables);
+	}
+
+	if (!collapsed)
+		return;
+
+	flush_tlb_all();
+
+	list_for_each_entry_safe(ptdesc, tmp, &pgtables, pt_list) {
+		list_del(&ptdesc->pt_list);
+		__free_page(ptdesc_page(ptdesc));
+	}
+}
+
+static void cpa_flush(struct cpa_data *cpa, int cache)
 {
-	struct cpa_data *cpa = data;
 	unsigned int i;
 
 	BUG_ON(irqs_disabled() && !early_boot_irqs_disabled);
 
 	if (cache && !static_cpu_has(X86_FEATURE_CLFLUSH)) {
 		cpa_flush_all(cache);
-		return;
+		goto collapse_large_pages;
 	}
 
 	if (cpa->force_flush_all || cpa->numpages > tlb_single_page_flush_ceiling)
@@ -412,7 +459,7 @@ static void cpa_flush(struct cpa_data *data, int cache)
 		on_each_cpu(__cpa_flush_tlb, cpa, 1);
 
 	if (!cache)
-		return;
+		goto collapse_large_pages;
 
 	mb();
 	for (i = 0; i < cpa->numpages; i++) {
@@ -428,6 +475,10 @@ static void cpa_flush(struct cpa_data *data, int cache)
 			clflush_cache_range_opt((void *)fix_addr(addr), PAGE_SIZE);
 	}
 	mb();
+
+collapse_large_pages:
+	if (cpa->flags & CPA_COLLAPSE)
+		cpa_collapse_large_pages(cpa);
 }
 
 static bool overlaps(unsigned long r1_start, unsigned long r1_end,
@@ -1197,6 +1248,161 @@ static int split_large_page(struct cpa_data *cpa, pte_t *kpte,
 	return 0;
 }
 
+static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	pmd_t _pmd, old_pmd;
+	pte_t *pte, first;
+	unsigned long pfn;
+	pgprot_t pgprot;
+	int i = 0;
+
+	addr &= PMD_MASK;
+	pte = pte_offset_kernel(pmd, addr);
+	first = *pte;
+	pfn = pte_pfn(first);
+
+	/* Make sure alignment is suitable */
+	if (PFN_PHYS(pfn) & ~PMD_MASK)
+		return 0;
+
+	/* The page is 4k intentionally */
+	if (pte_flags(first) & _PAGE_KERNEL_4K)
+		return 0;
+
+	/* Check that the rest of PTEs are compatible with the first one */
+	for (i = 1, pte++; i < PTRS_PER_PTE; i++, pte++) {
+		pte_t entry = *pte;
+
+		if (!pte_present(entry))
+			return 0;
+		if (pte_flags(entry) != pte_flags(first))
+			return 0;
+		if (pte_pfn(entry) != pte_pfn(first) + i)
+			return 0;
+	}
+
+	old_pmd = *pmd;
+
+	/* Success: set up a large page */
+	pgprot = pgprot_4k_2_large(pte_pgprot(first));
+	pgprot_val(pgprot) |= _PAGE_PSE;
+	_pmd = pfn_pmd(pfn, pgprot);
+	set_pmd(pmd, _pmd);
+
+	/* Queue the page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
+
+	if (IS_ENABLED(CONFIG_X86_32) && !SHARED_KERNEL_PMD) {
+		struct page *page;
+
+		/* Update all PGD tables to use the same large page */
+		list_for_each_entry(page, &pgd_list, lru) {
+			pgd_t *pgd = (pgd_t *)page_address(page) + pgd_index(addr);
+			p4d_t *p4d = p4d_offset(pgd, addr);
+			pud_t *pud = pud_offset(p4d, addr);
+			pmd_t *pmd = pmd_offset(pud, addr);
+			/* Something is wrong if entries doesn't match */
+			if (WARN_ON(pmd_val(old_pmd) != pmd_val(*pmd)))
+				continue;
+			set_pmd(pmd, _pmd);
+		}
+	}
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_2M);
+
+	return 1;
+}
+
+static int collapse_pud_page(pud_t *pud, unsigned long addr,
+			     struct list_head *pgtables)
+{
+	unsigned long pfn;
+	pmd_t *pmd, first;
+	int i;
+
+	if (!direct_gbpages)
+		return 0;
+
+	addr &= PUD_MASK;
+	pmd = pmd_offset(pud, addr);
+	first = *pmd;
+
+	/*
+	 * To restore PUD page all PMD entries must be large and
+	 * have suitable alignment
+	 */
+	pfn = pmd_pfn(first);
+	if (!pmd_leaf(first) || (PFN_PHYS(pfn) & ~PUD_MASK))
+		return 0;
+
+	/*
+	 * To restore PUD page, all following PMDs must be compatible with the
+	 * first one.
+	 */
+	for (i = 1, pmd++; i < PTRS_PER_PMD; i++, pmd++) {
+		pmd_t entry = *pmd;
+
+		if (!pmd_present(entry) || !pmd_leaf(entry))
+			return 0;
+		if (pmd_flags(entry) != pmd_flags(first))
+			return 0;
+		if (pmd_pfn(entry) != pmd_pfn(first) + i * PTRS_PER_PTE)
+			return 0;
+	}
+
+	/* Restore PUD page and queue page table to be freed after TLB flush */
+	list_add(&page_ptdesc(pud_page(*pud))->pt_list, pgtables);
+	set_pud(pud, pfn_pud(pfn, pmd_pgprot(first)));
+
+	if (virt_addr_valid(addr) && pfn_range_is_mapped(pfn, pfn + 1))
+		collapse_page_count(PG_LEVEL_1G);
+
+	return 1;
+}
+
+/*
+ * Collapse PMD and PUD pages in the kernel mapping around the address where
+ * possible.
+ *
+ * Caller must flush TLB and free page tables queued on the list before
+ * touching the new entries. CPU must not see TLB entries of different size
+ * with different attributes.
+ */
+static int collapse_large_pages(unsigned long addr, struct list_head *pgtables)
+{
+	int collapsed = 0;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	addr &= PMD_MASK;
+
+	spin_lock(&pgd_lock);
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		goto out;
+	p4d = p4d_offset(pgd, addr);
+	if (p4d_none(*p4d))
+		goto out;
+	pud = pud_offset(p4d, addr);
+	if (!pud_present(*pud) || pud_leaf(*pud))
+		goto out;
+	pmd = pmd_offset(pud, addr);
+	if (!pmd_present(*pmd) || pmd_leaf(*pmd))
+		goto out;
+
+	collapsed = collapse_pmd_page(pmd, addr, pgtables);
+	if (collapsed)
+		collapsed += collapse_pud_page(pud, addr, pgtables);
+
+out:
+	spin_unlock(&pgd_lock);
+	return collapsed;
+}
+
 static bool try_to_free_pte_page(pte_t *pte)
 {
 	int i;
@@ -2120,7 +2326,8 @@ int set_memory_rox(unsigned long addr, int numpages)
 	if (__supported_pte_mask & _PAGE_NX)
 		clr.pgprot |= _PAGE_NX;
 
-	return change_page_attr_clear(&addr, numpages, clr, 0);
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0), clr, 0,
+					CPA_COLLAPSE, NULL);
 }
 
 int set_memory_rw(unsigned long addr, int numpages)
@@ -2147,7 +2354,8 @@ int set_memory_p(unsigned long addr, int numpages)
 
 int set_memory_4k(unsigned long addr, int numpages)
 {
-	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+	return change_page_attr_set_clr(&addr, numpages,
+					__pgprot(_PAGE_KERNEL_4K),
 					__pgprot(0), 1, 0, NULL);
 }
 
@@ -2420,7 +2628,7 @@ static int __set_pages_np(struct page *page, int numpages)
 				.pgd = NULL,
 				.numpages = numpages,
 				.mask_set = __pgprot(0),
-				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW),
+				.mask_clr = __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 				.flags = CPA_NO_CHECK_ALIAS };
 
 	/*
@@ -2507,7 +2715,7 @@ int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 		.pgd = pgd,
 		.numpages = numpages,
 		.mask_set = __pgprot(0),
-		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW)),
+		.mask_clr = __pgprot(~page_flags & (_PAGE_NX|_PAGE_RW|_PAGE_DIRTY)),
 		.flags = CPA_NO_CHECK_ALIAS,
 	};
 
@@ -2550,7 +2758,7 @@ int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
 		.pgd		= pgd,
 		.numpages	= numpages,
 		.mask_set	= __pgprot(0),
-		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW),
+		.mask_clr	= __pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY),
 		.flags		= CPA_NO_CHECK_ALIAS,
 	};
 
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 1fef5ad32d5a..cec321fb74f2 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -12,59 +12,15 @@ phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
 EXPORT_SYMBOL(physical_mask);
 #endif
 
-#ifdef CONFIG_HIGHPTE
-#define PGTABLE_HIGHMEM __GFP_HIGHMEM
-#else
-#define PGTABLE_HIGHMEM 0
-#endif
-
-#ifndef CONFIG_PARAVIRT
-#ifndef CONFIG_PT_RECLAIM
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	struct ptdesc *ptdesc = (struct ptdesc *)table;
-
-	pagetable_dtor(ptdesc);
-	tlb_remove_page(tlb, ptdesc_page(ptdesc));
-}
-#else
-static inline
-void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table)
-{
-	tlb_remove_table(tlb, table);
-}
-#endif /* !CONFIG_PT_RECLAIM */
-#endif /* !CONFIG_PARAVIRT */
-
-gfp_t __userpte_alloc_gfp = GFP_PGTABLE_USER | PGTABLE_HIGHMEM;
-
 pgtable_t pte_alloc_one(struct mm_struct *mm)
 {
-	return __pte_alloc_one(mm, __userpte_alloc_gfp);
-}
-
-static int __init setup_userpte(char *arg)
-{
-	if (!arg)
-		return -EINVAL;
-
-	/*
-	 * "userpte=nohigh" disables allocation of user pagetables in
-	 * high memory.
-	 */
-	if (strcmp(arg, "nohigh") == 0)
-		__userpte_alloc_gfp &= ~__GFP_HIGHMEM;
-	else
-		return -EINVAL;
-	return 0;
+	return __pte_alloc_one(mm, GFP_PGTABLE_USER);
 }
-early_param("userpte", setup_userpte);
 
 void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 {
 	paravirt_release_pte(page_to_pfn(pte));
-	paravirt_tlb_remove_table(tlb, page_ptdesc(pte));
+	tlb_remove_table(tlb, page_ptdesc(pte));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 2
@@ -78,21 +34,21 @@ void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 #ifdef CONFIG_X86_PAE
 	tlb->need_flush_all = 1;
 #endif
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pmd));
+	tlb_remove_table(tlb, virt_to_ptdesc(pmd));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 3
 void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud)
 {
 	paravirt_release_pud(__pa(pud) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(pud));
+	tlb_remove_table(tlb, virt_to_ptdesc(pud));
 }
 
 #if CONFIG_PGTABLE_LEVELS > 4
 void ___p4d_free_tlb(struct mmu_gather *tlb, p4d_t *p4d)
 {
 	paravirt_release_p4d(__pa(p4d) >> PAGE_SHIFT);
-	paravirt_tlb_remove_table(tlb, virt_to_ptdesc(p4d));
+	tlb_remove_table(tlb, virt_to_ptdesc(p4d));
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 4 */
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6cf881a942bb..ffc25b348041 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -1325,7 +1325,7 @@ bool nmi_uaccess_okay(void)
 	if (loaded_mm != current_mm)
 		return false;
 
-	VM_WARN_ON_ONCE(current_mm->pgd != __va(read_cr3_pa()));
+	VM_WARN_ON_ONCE(__pa(current_mm->pgd) != read_cr3_pa());
 
 	return true;
 }
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 48bcada5cabe..4933fb337983 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -12,8 +12,6 @@ obj-$(CONFIG_X86_INTEL_CE)      += ce4100.o
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-y				+= legacy.o irq.o
 
-obj-$(CONFIG_STA2X11)           += sta2x11-fixup.o
-
 obj-$(CONFIG_X86_NUMACHIP)	+= numachip.o
 
 obj-$(CONFIG_X86_INTEL_MID)	+= intel_mid_pci.o
diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c
deleted file mode 100644
index 8c8ddc4dcc08..000000000000
--- a/arch/x86/pci/sta2x11-fixup.c
+++ /dev/null
@@ -1,233 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * DMA translation between STA2x11 AMBA memory mapping and the x86 memory mapping
- *
- * ST Microelectronics ConneXt (STA2X11/STA2X10)
- *
- * Copyright (c) 2010-2011 Wind River Systems, Inc.
- */
-
-#include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/export.h>
-#include <linux/list.h>
-#include <linux/dma-map-ops.h>
-#include <linux/swiotlb.h>
-#include <asm/iommu.h>
-#include <asm/sta2x11.h>
-
-#define STA2X11_SWIOTLB_SIZE (4*1024*1024)
-
-/*
- * We build a list of bus numbers that are under the ConneXt. The
- * main bridge hosts 4 busses, which are the 4 endpoints, in order.
- */
-#define STA2X11_NR_EP		4	/* 0..3 included */
-#define STA2X11_NR_FUNCS	8	/* 0..7 included */
-#define STA2X11_AMBA_SIZE	(512 << 20)
-
-struct sta2x11_ahb_regs { /* saved during suspend */
-	u32 base, pexlbase, pexhbase, crw;
-};
-
-struct sta2x11_mapping {
-	int is_suspended;
-	struct sta2x11_ahb_regs regs[STA2X11_NR_FUNCS];
-};
-
-struct sta2x11_instance {
-	struct list_head list;
-	int bus0;
-	struct sta2x11_mapping map[STA2X11_NR_EP];
-};
-
-static LIST_HEAD(sta2x11_instance_list);
-
-/* At probe time, record new instances of this bridge (likely one only) */
-static void sta2x11_new_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = kzalloc(sizeof(*instance), GFP_ATOMIC);
-	if (!instance)
-		return;
-	/* This has a subordinate bridge, with 4 more-subordinate ones */
-	instance->bus0 = pdev->subordinate->number + 1;
-
-	if (list_empty(&sta2x11_instance_list)) {
-		int size = STA2X11_SWIOTLB_SIZE;
-		/* First instance: register your own swiotlb area */
-		dev_info(&pdev->dev, "Using SWIOTLB (size %i)\n", size);
-		if (swiotlb_init_late(size, GFP_DMA, NULL))
-			dev_emerg(&pdev->dev, "init swiotlb failed\n");
-	}
-	list_add(&instance->list, &sta2x11_instance_list);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, 0xcc17, sta2x11_new_instance);
-
-/*
- * Utility functions used in this file from below
- */
-static struct sta2x11_instance *sta2x11_pdev_to_instance(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	list_for_each_entry(instance, &sta2x11_instance_list, list) {
-		ep = pdev->bus->number - instance->bus0;
-		if (ep >= 0 && ep < STA2X11_NR_EP)
-			return instance;
-	}
-	return NULL;
-}
-
-static int sta2x11_pdev_to_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return -1;
-
-	return pdev->bus->number - instance->bus0;
-}
-
-/* This is exported, as some devices need to access the MFD registers */
-struct sta2x11_instance *sta2x11_get_instance(struct pci_dev *pdev)
-{
-	return sta2x11_pdev_to_instance(pdev);
-}
-EXPORT_SYMBOL(sta2x11_get_instance);
-
-/* At setup time, we use our own ops if the device is a ConneXt one */
-static void sta2x11_setup_pdev(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-
-	if (!instance) /* either a sta2x11 bridge or another ST device */
-		return;
-
-	/* We must enable all devices as master, for audio DMA to work */
-	pci_set_master(pdev);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_setup_pdev);
-
-/*
- * At boot we must set up the mappings for the pcie-to-amba bridge.
- * It involves device access, and the same happens at suspend/resume time
- */
-
-#define AHB_MAPB		0xCA4
-#define AHB_CRW(i)		(AHB_MAPB + 0  + (i) * 0x10)
-#define AHB_CRW_SZMASK			0xfffffc00UL
-#define AHB_CRW_ENABLE			(1 << 0)
-#define AHB_CRW_WTYPE_MEM		(2 << 1)
-#define AHB_CRW_ROE			(1UL << 3)	/* Relax Order Ena */
-#define AHB_CRW_NSE			(1UL << 4)	/* No Snoop Enable */
-#define AHB_BASE(i)		(AHB_MAPB + 4  + (i) * 0x10)
-#define AHB_PEXLBASE(i)		(AHB_MAPB + 8  + (i) * 0x10)
-#define AHB_PEXHBASE(i)		(AHB_MAPB + 12 + (i) * 0x10)
-
-/* At probe time, enable mapping for each endpoint, using the pdev */
-static void sta2x11_map_ep(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance = sta2x11_pdev_to_instance(pdev);
-	struct device *dev = &pdev->dev;
-	u32 amba_base, max_amba_addr;
-	int i, ret;
-
-	if (!instance)
-		return;
-
-	pci_read_config_dword(pdev, AHB_BASE(0), &amba_base);
-	max_amba_addr = amba_base + STA2X11_AMBA_SIZE - 1;
-
-	ret = dma_direct_set_offset(dev, 0, amba_base, STA2X11_AMBA_SIZE);
-	if (ret)
-		dev_err(dev, "sta2x11: could not set DMA offset\n");
-
-	dev->bus_dma_limit = max_amba_addr;
-	dma_set_mask_and_coherent(&pdev->dev, max_amba_addr);
-
-	/* Configure AHB mapping */
-	pci_write_config_dword(pdev, AHB_PEXLBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_PEXHBASE(0), 0);
-	pci_write_config_dword(pdev, AHB_CRW(0), STA2X11_AMBA_SIZE |
-			       AHB_CRW_WTYPE_MEM | AHB_CRW_ENABLE);
-
-	/* Disable all the other windows */
-	for (i = 1; i < STA2X11_NR_FUNCS; i++)
-		pci_write_config_dword(pdev, AHB_CRW(i), 0);
-
-	dev_info(&pdev->dev,
-		 "sta2x11: Map EP %i: AMBA address %#8x-%#8x\n",
-		 sta2x11_pdev_to_ep(pdev), amba_base, max_amba_addr);
-}
-DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, sta2x11_map_ep);
-
-#ifdef CONFIG_PM /* Some register values must be saved and restored */
-
-static struct sta2x11_mapping *sta2x11_pdev_to_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_instance *instance;
-	int ep;
-
-	instance = sta2x11_pdev_to_instance(pdev);
-	if (!instance)
-		return NULL;
-	ep = sta2x11_pdev_to_ep(pdev);
-	return instance->map + ep;
-}
-
-static void suspend_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-	if (map->is_suspended)
-		return;
-	map->is_suspended = 1;
-
-	/* Save all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_read_config_dword(pdev, AHB_BASE(i), &regs->base);
-		pci_read_config_dword(pdev, AHB_PEXLBASE(i), &regs->pexlbase);
-		pci_read_config_dword(pdev, AHB_PEXHBASE(i), &regs->pexhbase);
-		pci_read_config_dword(pdev, AHB_CRW(i), &regs->crw);
-	}
-}
-DECLARE_PCI_FIXUP_SUSPEND(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, suspend_mapping);
-
-static void resume_mapping(struct pci_dev *pdev)
-{
-	struct sta2x11_mapping *map = sta2x11_pdev_to_mapping(pdev);
-	int i;
-
-	if (!map)
-		return;
-
-
-	if (!map->is_suspended)
-		goto out;
-	map->is_suspended = 0;
-
-	/* Restore all window configs */
-	for (i = 0; i < STA2X11_NR_FUNCS; i++) {
-		struct sta2x11_ahb_regs *regs = map->regs + i;
-
-		pci_write_config_dword(pdev, AHB_BASE(i), regs->base);
-		pci_write_config_dword(pdev, AHB_PEXLBASE(i), regs->pexlbase);
-		pci_write_config_dword(pdev, AHB_PEXHBASE(i), regs->pexhbase);
-		pci_write_config_dword(pdev, AHB_CRW(i), regs->crw);
-	}
-out:
-	pci_set_master(pdev); /* Like at boot, enable master on all devices */
-}
-DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_STMICRO, PCI_ANY_ID, resume_mapping);
-
-#endif /* CONFIG_PM */
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index 77e788e928cd..98d8a50d2aed 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -9,7 +9,7 @@ config XEN
 	select PARAVIRT_CLOCK
 	select X86_HV_CALLBACK_VECTOR
 	depends on X86_64 || (X86_32 && X86_PAE)
-	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MCORE2 || MATOM || MK8)
+	depends on X86_64 || (X86_GENERIC || MPENTIUM4 || MATOM)
 	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index d078de2c952b..38971c6dcd4b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -2189,7 +2189,6 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
 		.flush_tlb_kernel = xen_flush_tlb,
 		.flush_tlb_one_user = xen_flush_tlb_one_user,
 		.flush_tlb_multi = xen_flush_tlb_multi,
-		.tlb_remove_table = tlb_remove_table,
 
 		.pgd_alloc = xen_pgd_alloc,
 		.pgd_free = xen_pgd_free,
diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c
index 6863d3da7dec..688ff59318ae 100644
--- a/arch/x86/xen/smp_pv.c
+++ b/arch/x86/xen/smp_pv.c
@@ -70,7 +70,7 @@ static void cpu_bringup(void)
 		xen_enable_syscall();
 	}
 	cpu = smp_processor_id();
-	smp_store_cpu_info(cpu);
+	identify_secondary_cpu(cpu);
 	set_cpu_sibling_map(cpu);
 
 	speculative_store_bypass_ht_init();