Merge branch 'x86/paravirt' into x86/entry

Merge in the recent paravirt changes to resolve conflicts caused
by objtool annotations.

Conflicts:
	arch/x86/xen/xen-asm.S

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

36 files changed, 166 insertions, 194 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 05e17351e4f3..f39568b28ec1 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -174,8 +174,6 @@ config ARM64
 	select HAVE_NMI
 	select HAVE_PATA_PLATFORM
 	select HAVE_PERF_EVENTS
-	select HAVE_PERF_EVENTS_NMI if ARM64_PSEUDO_NMI && HW_PERF_EVENTS
-	select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
index ba1c6dfdc4b6..d945c84ab697 100644
--- a/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-axg.dtsi
@@ -280,8 +280,6 @@
 				      "timing-adjustment";
 			rx-fifo-depth = <4096>;
 			tx-fifo-depth = <2048>;
-			resets = <&reset RESET_ETHERNET>;
-			reset-names = "stmmaceth";
 			power-domains = <&pwrc PWRC_AXG_ETHERNET_MEM_ID>;
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
index 9c90d562ada1..b858c5e43cc8 100644
--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
@@ -224,8 +224,6 @@
 				      "timing-adjustment";
 			rx-fifo-depth = <4096>;
 			tx-fifo-depth = <2048>;
-			resets = <&reset RESET_ETHERNET>;
-			reset-names = "stmmaceth";
 			status = "disabled";
 
 			mdio0: mdio {
@@ -2390,7 +2388,7 @@
 				interrupts = <GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>;
 				dr_mode = "host";
 				snps,dis_u2_susphy_quirk;
-				snps,quirk-frame-length-adjustment;
+				snps,quirk-frame-length-adjustment = <0x20>;
 				snps,parkmode-disable-ss-quirk;
 			};
 		};
diff --git a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
index 726b91d3a905..0edd137151f8 100644
--- a/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
+++ b/arch/arm64/boot/dts/amlogic/meson-gx.dtsi
@@ -13,7 +13,6 @@
 #include <dt-bindings/interrupt-controller/irq.h>
 #include <dt-bindings/interrupt-controller/arm-gic.h>
 #include <dt-bindings/power/meson-gxbb-power.h>
-#include <dt-bindings/reset/amlogic,meson-gxbb-reset.h>
 #include <dt-bindings/thermal/thermal.h>
 
 / {
@@ -576,8 +575,6 @@
 			interrupt-names = "macirq";
 			rx-fifo-depth = <4096>;
 			tx-fifo-depth = <2048>;
-			resets = <&reset RESET_ETHERNET>;
-			reset-names = "stmmaceth";
 			power-domains = <&pwrc PWRC_GXBB_ETHERNET_MEM_ID>;
 			status = "disabled";
 		};
diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts
index cf5a98f0e47c..a712273c905a 100644
--- a/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts
+++ b/arch/arm64/boot/dts/amlogic/meson-sm1-odroid-c4.dts
@@ -52,7 +52,7 @@
 		regulator-min-microvolt = <3300000>;
 		regulator-max-microvolt = <3300000>;
 
-		gpio = <&gpio_ao GPIOAO_3 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio_ao GPIOAO_3 GPIO_OPEN_DRAIN>;
 		enable-active-high;
 		regulator-always-on;
 	};
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi
index aef8f2b00778..5401a646c840 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray-usb.dtsi
@@ -4,11 +4,16 @@
  */
 	usb {
 		compatible = "simple-bus";
-		dma-ranges;
 		#address-cells = <2>;
 		#size-cells = <2>;
 		ranges = <0x0 0x0 0x0 0x68500000 0x0 0x00400000>;
 
+		/*
+		 * Internally, USB bus to the interconnect can only address up
+		 * to 40-bit
+		 */
+		dma-ranges = <0 0 0 0 0x100 0x0>;
+
 		usbphy0: usb-phy@0 {
 			compatible = "brcm,sr-usb-combo-phy";
 			reg = <0x0 0x00000000 0x0 0x100>;
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index 60ff19fa53b4..6c8a61c2cc74 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -101,7 +101,7 @@
 	reboot {
 		compatible ="syscon-reboot";
 		regmap = <&rst>;
-		offset = <0xb0>;
+		offset = <0>;
 		mask = <0x02>;
 	};
 
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
index 025e1f587662..565934cbfa28 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1046a.dtsi
@@ -385,7 +385,7 @@
 
 		dcfg: dcfg@1ee0000 {
 			compatible = "fsl,ls1046a-dcfg", "syscon";
-			reg = <0x0 0x1ee0000 0x0 0x10000>;
+			reg = <0x0 0x1ee0000 0x0 0x1000>;
 			big-endian;
 		};
 
diff --git a/arch/arm64/boot/dts/freescale/imx8mn.dtsi b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
index ee1790230490..2a79e89f821e 100644
--- a/arch/arm64/boot/dts/freescale/imx8mn.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mn.dtsi
@@ -253,7 +253,7 @@
 			#size-cells = <1>;
 			ranges;
 
-			spba: bus@30000000 {
+			spba: spba-bus@30000000 {
 				compatible = "fsl,spba-bus", "simple-bus";
 				#address-cells = <1>;
 				#size-cells = <1>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index ecccfbb4f5ad..23f5a5e37167 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -266,7 +266,7 @@
 				#gpio-cells = <2>;
 				interrupt-controller;
 				#interrupt-cells = <2>;
-				gpio-ranges = <&iomuxc 0 56 26>, <&iomuxc 0 144 4>;
+				gpio-ranges = <&iomuxc 0 56 26>, <&iomuxc 26 144 4>;
 			};
 
 			gpio4: gpio@30230000 {
diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
index 7cc236575ee2..c0b93813ea9a 100644
--- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
+++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
@@ -415,7 +415,9 @@
 &gcc {
 	protected-clocks = <GCC_QSPI_CORE_CLK>,
 			   <GCC_QSPI_CORE_CLK_SRC>,
-			   <GCC_QSPI_CNOC_PERIPH_AHB_CLK>;
+			   <GCC_QSPI_CNOC_PERIPH_AHB_CLK>,
+			   <GCC_LPASS_Q6_AXI_CLK>,
+			   <GCC_LPASS_SWAY_CLK>;
 };
 
 &gpu {
diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
index 13fdd02cffe6..8b40f96e9780 100644
--- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
+++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
@@ -302,7 +302,9 @@
 &gcc {
 	protected-clocks = <GCC_QSPI_CORE_CLK>,
 			   <GCC_QSPI_CORE_CLK_SRC>,
-			   <GCC_QSPI_CNOC_PERIPH_AHB_CLK>;
+			   <GCC_QSPI_CNOC_PERIPH_AHB_CLK>,
+			   <GCC_LPASS_Q6_AXI_CLK>,
+			   <GCC_LPASS_SWAY_CLK>;
 };
 
 &gpu {
@@ -320,6 +322,8 @@
 &i2c3 {
 	status = "okay";
 	clock-frequency = <400000>;
+	/* Overwrite pinctrl-0 from sdm845.dtsi */
+	pinctrl-0 = <&qup_i2c3_default &i2c3_hid_active>;
 
 	tsel: hid@15 {
 		compatible = "hid-over-i2c";
@@ -327,9 +331,6 @@
 		hid-descr-addr = <0x1>;
 
 		interrupts-extended = <&tlmm 37 IRQ_TYPE_LEVEL_HIGH>;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c3_hid_active>;
 	};
 
 	tsc2: hid@2c {
@@ -338,11 +339,6 @@
 		hid-descr-addr = <0x20>;
 
 		interrupts-extended = <&tlmm 37 IRQ_TYPE_LEVEL_HIGH>;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&i2c3_hid_active>;
-
-		status = "disabled";
 	};
 };
 
diff --git a/arch/arm64/boot/dts/rockchip/px30.dtsi b/arch/arm64/boot/dts/rockchip/px30.dtsi
index 2695ea8cda14..64193292d26c 100644
--- a/arch/arm64/boot/dts/rockchip/px30.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30.dtsi
@@ -1097,7 +1097,7 @@
 	vopl_mmu: iommu@ff470f00 {
 		compatible = "rockchip,iommu";
 		reg = <0x0 0xff470f00 0x0 0x100>;
-		interrupts = <GIC_SPI 79 IRQ_TYPE_LEVEL_HIGH>;
+		interrupts = <GIC_SPI 78 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-names = "vopl_mmu";
 		clocks = <&cru ACLK_VOPL>, <&cru HCLK_VOPL>;
 		clock-names = "aclk", "iface";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts
index 2ee07d15a6e3..1eecad724f04 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-nanopi-r2s.dts
@@ -114,6 +114,10 @@
 	cpu-supply = <&vdd_arm>;
 };
 
+&display_subsystem {
+	status = "disabled";
+};
+
 &gmac2io {
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clk>, <&gmac_clk>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
index 06d48338c836..219b7507a10f 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
@@ -790,7 +790,6 @@
 &pcie0 {
 	bus-scan-delay-ms = <1000>;
 	ep-gpios = <&gpio2 RK_PD4 GPIO_ACTIVE_HIGH>;
-	max-link-speed = <2>;
 	num-lanes = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie_clkreqn_cpm>;
diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
index f5dee5f447bb..2551b238b97c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi
@@ -234,6 +234,7 @@
 		reg = <0x0 0xf8000000 0x0 0x2000000>,
 		      <0x0 0xfd000000 0x0 0x1000000>;
 		reg-names = "axi-base", "apb-base";
+		device_type = "pci";
 		#address-cells = <3>;
 		#size-cells = <2>;
 		#interrupt-cells = <1>;
@@ -252,7 +253,6 @@
 				<0 0 0 2 &pcie0_intc 1>,
 				<0 0 0 3 &pcie0_intc 2>,
 				<0 0 0 4 &pcie0_intc 3>;
-		linux,pci-domain = <0>;
 		max-link-speed = <1>;
 		msi-map = <0x0 &its 0x0 0x1000>;
 		phys = <&pcie_phy 0>, <&pcie_phy 1>,
@@ -1278,7 +1278,6 @@
 		compatible = "rockchip,rk3399-vdec";
 		reg = <0x0 0xff660000 0x0 0x400>;
 		interrupts = <GIC_SPI 116 IRQ_TYPE_LEVEL_HIGH 0>;
-		interrupt-names = "vdpu";
 		clocks = <&cru ACLK_VDU>, <&cru HCLK_VDU>,
 			 <&cru SCLK_VDU_CA>, <&cru SCLK_VDU_CORE>;
 		clock-names = "axi", "ahb", "cabac", "core";
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 838301650a79..01aa3eee90e8 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -991,8 +991,6 @@ CONFIG_ARCH_TEGRA_210_SOC=y
 CONFIG_ARCH_TEGRA_186_SOC=y
 CONFIG_ARCH_TEGRA_194_SOC=y
 CONFIG_ARCH_TEGRA_234_SOC=y
-CONFIG_ARCH_K3_AM6_SOC=y
-CONFIG_ARCH_K3_J721E_SOC=y
 CONFIG_TI_SCI_PM_DOMAINS=y
 CONFIG_EXTCON_PTN5150=m
 CONFIG_EXTCON_USB_GPIO=y
@@ -1078,7 +1076,7 @@ CONFIG_INTERCONNECT=y
 CONFIG_INTERCONNECT_QCOM=y
 CONFIG_INTERCONNECT_QCOM_MSM8916=m
 CONFIG_INTERCONNECT_QCOM_OSM_L3=m
-CONFIG_INTERCONNECT_QCOM_SDM845=m
+CONFIG_INTERCONNECT_QCOM_SDM845=y
 CONFIG_INTERCONNECT_QCOM_SM8150=m
 CONFIG_INTERCONNECT_QCOM_SM8250=m
 CONFIG_EXT2_FS=y
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 015ddffaf6ca..b56a4b2bc248 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -17,7 +17,7 @@
 #include <asm/lse.h>
 
 #define ATOMIC_OP(op)							\
-static inline void arch_##op(int i, atomic_t *v)			\
+static __always_inline void arch_##op(int i, atomic_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -32,7 +32,7 @@ ATOMIC_OP(atomic_sub)
 #undef ATOMIC_OP
 
 #define ATOMIC_FETCH_OP(name, op)					\
-static inline int arch_##op##name(int i, atomic_t *v)			\
+static __always_inline int arch_##op##name(int i, atomic_t *v)		\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -56,7 +56,7 @@ ATOMIC_FETCH_OPS(atomic_sub_return)
 #undef ATOMIC_FETCH_OPS
 
 #define ATOMIC64_OP(op)							\
-static inline void arch_##op(long i, atomic64_t *v)			\
+static __always_inline void arch_##op(long i, atomic64_t *v)		\
 {									\
 	__lse_ll_sc_body(op, i, v);					\
 }
@@ -71,7 +71,7 @@ ATOMIC64_OP(atomic64_sub)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, op)					\
-static inline long arch_##op##name(long i, atomic64_t *v)		\
+static __always_inline long arch_##op##name(long i, atomic64_t *v)	\
 {									\
 	return __lse_ll_sc_body(op##name, i, v);			\
 }
@@ -94,7 +94,7 @@ ATOMIC64_FETCH_OPS(atomic64_sub_return)
 #undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_FETCH_OPS
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	return __lse_ll_sc_body(atomic64_dec_if_positive, v);
 }
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 18fce223b67b..ff4732785c32 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -247,11 +247,13 @@ static inline const void *__tag_set(const void *addr, u8 tag)
 
 
 /*
- * The linear kernel range starts at the bottom of the virtual address space.
+ * Check whether an arbitrary address is within the linear map, which
+ * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the
+ * kernel's TTBR1 address range.
  */
-#define __is_lm_address(addr)	(((u64)(addr) & ~PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET))
+#define __is_lm_address(addr)	(((u64)(addr) - PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET))
 
-#define __lm_to_phys(addr)	(((addr) & ~PAGE_OFFSET) + PHYS_OFFSET)
+#define __lm_to_phys(addr)	(((addr) - PAGE_OFFSET) + PHYS_OFFSET)
 #define __kimg_to_phys(addr)	((addr) - kimage_voffset)
 
 #define __virt_to_phys_nodebug(x) ({					\
@@ -330,7 +332,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 #endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */
 
 #define virt_addr_valid(addr)	({					\
-	__typeof__(addr) __addr = addr;					\
+	__typeof__(addr) __addr = __tag_reset(addr);			\
 	__is_lm_address(__addr) && pfn_valid(virt_to_pfn(__addr));	\
 })
 
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 69ad25fbeae4..ca2cd75d3286 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -94,8 +94,7 @@
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
 extern phys_addr_t arm64_dma_phys_limit;
-extern phys_addr_t arm64_dma32_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT	((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
+#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
 
 struct debug_info {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index f42fd9e33981..301784463587 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -75,7 +75,7 @@ int main(void)
   DEFINE(S_SDEI_TTBR1,		offsetof(struct pt_regs, sdei_ttbr1));
   DEFINE(S_PMR_SAVE,		offsetof(struct pt_regs, pmr_save));
   DEFINE(S_STACKFRAME,		offsetof(struct pt_regs, stackframe));
-  DEFINE(S_FRAME_SIZE,		sizeof(struct pt_regs));
+  DEFINE(PT_REGS_SIZE,		sizeof(struct pt_regs));
   BLANK();
 #ifdef CONFIG_COMPAT
   DEFINE(COMPAT_SIGFRAME_REGS_OFFSET,		offsetof(struct compat_sigframe, uc.uc_mcontext.arm_r0));
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index a338f40e64d3..b3e4f9a088b1 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -35,7 +35,7 @@
  */
 	.macro  ftrace_regs_entry, allregs=0
 	/* Make room for pt_regs, plus a callee frame */
-	sub	sp, sp, #(S_FRAME_SIZE + 16)
+	sub	sp, sp, #(PT_REGS_SIZE + 16)
 
 	/* Save function arguments (and x9 for simplicity) */
 	stp	x0, x1, [sp, #S_X0]
@@ -61,15 +61,15 @@
 	.endif
 
 	/* Save the callsite's SP and LR */
-	add	x10, sp, #(S_FRAME_SIZE + 16)
+	add	x10, sp, #(PT_REGS_SIZE + 16)
 	stp	x9, x10, [sp, #S_LR]
 
 	/* Save the PC after the ftrace callsite */
 	str	x30, [sp, #S_PC]
 
 	/* Create a frame record for the callsite above pt_regs */
-	stp	x29, x9, [sp, #S_FRAME_SIZE]
-	add	x29, sp, #S_FRAME_SIZE
+	stp	x29, x9, [sp, #PT_REGS_SIZE]
+	add	x29, sp, #PT_REGS_SIZE
 
 	/* Create our frame record within pt_regs. */
 	stp	x29, x30, [sp, #S_STACKFRAME]
@@ -120,7 +120,7 @@ ftrace_common_return:
 	ldr	x9, [sp, #S_PC]
 
 	/* Restore the callsite's SP */
-	add	sp, sp, #S_FRAME_SIZE + 16
+	add	sp, sp, #PT_REGS_SIZE + 16
 
 	ret	x9
 SYM_CODE_END(ftrace_common)
@@ -130,7 +130,7 @@ SYM_CODE_START(ftrace_graph_caller)
 	ldr	x0, [sp, #S_PC]
 	sub	x0, x0, #AARCH64_INSN_SIZE	// ip (callsite's BL insn)
 	add	x1, sp, #S_LR			// parent_ip (callsite's LR)
-	ldr	x2, [sp, #S_FRAME_SIZE]	   	// parent fp (callsite's FP)
+	ldr	x2, [sp, #PT_REGS_SIZE]	   	// parent fp (callsite's FP)
 	bl	prepare_ftrace_return
 	b	ftrace_common_return
 SYM_CODE_END(ftrace_graph_caller)
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a8c3e7aaca74..c9bae73f2621 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -75,7 +75,7 @@ alternative_else_nop_endif
 	.endif
 #endif
 
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 #ifdef CONFIG_VMAP_STACK
 	/*
 	 * Test whether the SP has overflowed, without corrupting a GPR.
@@ -96,7 +96,7 @@ alternative_else_nop_endif
 	 * userspace, and can clobber EL0 registers to free up GPRs.
 	 */
 
-	/* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+	/* Stash the original SP (minus PT_REGS_SIZE) in tpidr_el0. */
 	msr	tpidr_el0, x0
 
 	/* Recover the original x0 value and stash it in tpidrro_el0 */
@@ -253,7 +253,7 @@ alternative_else_nop_endif
 
 	scs_load tsk, x20
 	.else
-	add	x21, sp, #S_FRAME_SIZE
+	add	x21, sp, #PT_REGS_SIZE
 	get_current_task tsk
 	.endif /* \el == 0 */
 	mrs	x22, elr_el1
@@ -377,7 +377,7 @@ alternative_else_nop_endif
 	ldp	x26, x27, [sp, #16 * 13]
 	ldp	x28, x29, [sp, #16 * 14]
 	ldr	lr, [sp, #S_LR]
-	add	sp, sp, #S_FRAME_SIZE		// restore sp
+	add	sp, sp, #PT_REGS_SIZE		// restore sp
 
 	.if	\el == 0
 alternative_insn eret, nop, ARM64_UNMAP_KERNEL_AT_EL0
@@ -580,12 +580,12 @@ __bad_stack:
 
 	/*
 	 * Store the original GPRs to the new stack. The orginal SP (minus
-	 * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+	 * PT_REGS_SIZE) was stashed in tpidr_el0 by kernel_ventry.
 	 */
-	sub	sp, sp, #S_FRAME_SIZE
+	sub	sp, sp, #PT_REGS_SIZE
 	kernel_entry 1
 	mrs	x0, tpidr_el0
-	add	x0, x0, #S_FRAME_SIZE
+	add	x0, x0, #PT_REGS_SIZE
 	str	x0, [sp, #S_SP]
 
 	/* Stash the regs for handle_bad_stack */
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 38bb07eff872..3605f77ad4df 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -23,8 +23,6 @@
 #include <linux/platform_device.h>
 #include <linux/sched_clock.h>
 #include <linux/smp.h>
-#include <linux/nmi.h>
-#include <linux/cpufreq.h>
 
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
@@ -1250,21 +1248,10 @@ static struct platform_driver armv8_pmu_driver = {
 
 static int __init armv8_pmu_driver_init(void)
 {
-	int ret;
-
 	if (acpi_disabled)
-		ret = platform_driver_register(&armv8_pmu_driver);
+		return platform_driver_register(&armv8_pmu_driver);
 	else
-		ret = arm_pmu_acpi_probe(armv8_pmuv3_init);
-
-	/*
-	 * Try to re-initialize lockup detector after PMU init in
-	 * case PMU events are triggered via NMIs.
-	 */
-	if (ret == 0 && arm_pmu_irq_is_nmi())
-		lockup_detector_init();
-
-	return ret;
+		return arm_pmu_acpi_probe(armv8_pmuv3_init);
 }
 device_initcall(armv8_pmu_driver_init)
 
@@ -1322,27 +1309,3 @@ void arch_perf_update_userpage(struct perf_event *event,
 	userpg->cap_user_time_zero = 1;
 	userpg->cap_user_time_short = 1;
 }
-
-#ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
-/*
- * Safe maximum CPU frequency in case a particular platform doesn't implement
- * cpufreq driver. Although, architecture doesn't put any restrictions on
- * maximum frequency but 5 GHz seems to be safe maximum given the available
- * Arm CPUs in the market which are clocked much less than 5 GHz. On the other
- * hand, we can't make it much higher as it would lead to a large hard-lockup
- * detection timeout on parts which are running slower (eg. 1GHz on
- * Developerbox) and doesn't possess a cpufreq driver.
- */
-#define SAFE_MAX_CPU_FREQ	5000000000UL // 5 GHz
-u64 hw_nmi_get_sample_period(int watchdog_thresh)
-{
-	unsigned int cpu = smp_processor_id();
-	unsigned long max_cpu_freq;
-
-	max_cpu_freq = cpufreq_get_hw_max_freq(cpu) * 1000UL;
-	if (!max_cpu_freq)
-		max_cpu_freq = SAFE_MAX_CPU_FREQ;
-
-	return (u64)max_cpu_freq * watchdog_thresh;
-}
-#endif
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 89c64ada8732..66aac2881ba8 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -352,8 +352,8 @@ kprobe_breakpoint_ss_handler(struct pt_regs *regs, unsigned int esr)
 	unsigned long addr = instruction_pointer(regs);
 	struct kprobe *cur = kprobe_running();
 
-	if (cur && (kcb->kprobe_status == KPROBE_HIT_SS)
-	    && ((unsigned long)&cur->ainsn.api.insn[1] == addr)) {
+	if (cur && (kcb->kprobe_status & (KPROBE_HIT_SS | KPROBE_REENTER)) &&
+	    ((unsigned long)&cur->ainsn.api.insn[1] == addr)) {
 		kprobes_restore_local_irqflag(kcb, regs);
 		post_kprobe_handler(cur, kcb, regs);
 
diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S
index 890ca72c5a51..288a84e253cc 100644
--- a/arch/arm64/kernel/probes/kprobes_trampoline.S
+++ b/arch/arm64/kernel/probes/kprobes_trampoline.S
@@ -25,7 +25,7 @@
 	stp x24, x25, [sp, #S_X24]
 	stp x26, x27, [sp, #S_X26]
 	stp x28, x29, [sp, #S_X28]
-	add x0, sp, #S_FRAME_SIZE
+	add x0, sp, #PT_REGS_SIZE
 	stp lr, x0, [sp, #S_LR]
 	/*
 	 * Construct a useful saved PSTATE
@@ -62,7 +62,7 @@
 	.endm
 
 SYM_CODE_START(kretprobe_trampoline)
-	sub sp, sp, #S_FRAME_SIZE
+	sub sp, sp, #PT_REGS_SIZE
 
 	save_all_base_regs
 
@@ -76,7 +76,7 @@ SYM_CODE_START(kretprobe_trampoline)
 
 	restore_all_base_regs
 
-	add sp, sp, #S_FRAME_SIZE
+	add sp, sp, #PT_REGS_SIZE
 	ret
 
 SYM_CODE_END(kretprobe_trampoline)
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index f71d6ce4673f..6237486ff6bb 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -914,13 +914,6 @@ static void do_signal(struct pt_regs *regs)
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned long thread_flags)
 {
-	/*
-	 * The assembly code enters us with IRQs off, but it hasn't
-	 * informed the tracing code of that for efficiency reasons.
-	 * Update the trace code with the current status.
-	 */
-	trace_hardirqs_off();
-
 	do {
 		if (thread_flags & _TIF_NEED_RESCHED) {
 			/* Unmask Debug and SError for the next task */
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index f61e9d8cc55a..c2877c332f2d 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -9,6 +9,7 @@
 
 #include <asm/daifflags.h>
 #include <asm/debug-monitors.h>
+#include <asm/exception.h>
 #include <asm/fpsimd.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
@@ -165,15 +166,8 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP)) {
-			/*
-			 * We're off to userspace, where interrupts are
-			 * always enabled after we restore the flags from
-			 * the SPSR.
-			 */
-			trace_hardirqs_on();
+		if (!has_syscall_work(flags) && !(flags & _TIF_SINGLESTEP))
 			return;
-		}
 		local_daif_restore(DAIF_PROCCTX);
 	}
 
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 04c44853b103..fe60d25c000e 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1396,8 +1396,9 @@ static void cpu_init_hyp_mode(void)
 	 * Calculate the raw per-cpu offset without a translation from the
 	 * kernel's mapping to the linear mapping, and store it in tpidr_el2
 	 * so that we can use adr_l to access per-cpu variables in EL2.
+	 * Also drop the KASAN tag which gets in the way...
 	 */
-	params->tpidr_el2 = (unsigned long)this_cpu_ptr_nvhe_sym(__per_cpu_start) -
+	params->tpidr_el2 = (unsigned long)kasan_reset_tag(this_cpu_ptr_nvhe_sym(__per_cpu_start)) -
 			    (unsigned long)kvm_ksym_ref(CHOOSE_NVHE_SYM(__per_cpu_start));
 
 	params->mair_el2 = read_sysreg(mair_el1);
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 31b060a44045..b17bf19217f1 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -47,6 +47,8 @@ __invalid:
 	b	.
 
 	/*
+	 * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers.
+	 *
 	 * x0: SMCCC function ID
 	 * x1: struct kvm_nvhe_init_params PA
 	 */
@@ -70,9 +72,9 @@ __do_hyp_init:
 	eret
 
 1:	mov	x0, x1
-	mov	x4, lr
-	bl	___kvm_hyp_init
-	mov	lr, x4
+	mov	x3, lr
+	bl	___kvm_hyp_init			// Clobbers x0..x2
+	mov	lr, x3
 
 	/* Hello, World! */
 	mov	x0, #SMCCC_RET_SUCCESS
@@ -82,8 +84,8 @@ SYM_CODE_END(__kvm_hyp_init)
 /*
  * Initialize the hypervisor in EL2.
  *
- * Only uses x0..x3 so as to not clobber callee-saved SMCCC registers
- * and leave x4 for the caller.
+ * Only uses x0..x2 so as to not clobber callee-saved SMCCC registers
+ * and leave x3 for the caller.
  *
  * x0: struct kvm_nvhe_init_params PA
  */
@@ -112,9 +114,9 @@ alternative_else_nop_endif
 	/*
 	 * Set the PS bits in TCR_EL2.
 	 */
-	ldr	x1, [x0, #NVHE_INIT_TCR_EL2]
-	tcr_compute_pa_size x1, #TCR_EL2_PS_SHIFT, x2, x3
-	msr	tcr_el2, x1
+	ldr	x0, [x0, #NVHE_INIT_TCR_EL2]
+	tcr_compute_pa_size x0, #TCR_EL2_PS_SHIFT, x1, x2
+	msr	tcr_el2, x0
 
 	isb
 
@@ -193,7 +195,7 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28
-	bl	___kvm_hyp_init			// Clobbers x0..x3
+	bl	___kvm_hyp_init			// Clobbers x0..x2
 
 	/* Leave idmap. */
 	mov	x0, x29
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index e3947846ffcb..8e7128cb7667 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -77,12 +77,6 @@ static unsigned long psci_forward(struct kvm_cpu_context *host_ctxt)
 			 cpu_reg(host_ctxt, 2), cpu_reg(host_ctxt, 3));
 }
 
-static __noreturn unsigned long psci_forward_noreturn(struct kvm_cpu_context *host_ctxt)
-{
-	psci_forward(host_ctxt);
-	hyp_panic(); /* unreachable */
-}
-
 static unsigned int find_cpu_id(u64 mpidr)
 {
 	unsigned int i;
@@ -251,10 +245,13 @@ static unsigned long psci_0_2_handler(u64 func_id, struct kvm_cpu_context *host_
 	case PSCI_0_2_FN_MIGRATE_INFO_TYPE:
 	case PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU:
 		return psci_forward(host_ctxt);
+	/*
+	 * SYSTEM_OFF/RESET should not return according to the spec.
+	 * Allow it so as to stay robust to broken firmware.
+	 */
 	case PSCI_0_2_FN_SYSTEM_OFF:
 	case PSCI_0_2_FN_SYSTEM_RESET:
-		psci_forward_noreturn(host_ctxt);
-		unreachable();
+		return psci_forward(host_ctxt);
 	case PSCI_0_2_FN64_CPU_SUSPEND:
 		return psci_cpu_suspend(func_id, host_ctxt);
 	case PSCI_0_2_FN64_CPU_ON:
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 4ad66a532e38..247422ac78a9 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -788,7 +788,7 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 {
 	unsigned long *bmap = vcpu->kvm->arch.pmu_filter;
 	u64 val, mask = 0;
-	int base, i;
+	int base, i, nr_events;
 
 	if (!pmceid1) {
 		val = read_sysreg(pmceid0_el0);
@@ -801,13 +801,17 @@ u64 kvm_pmu_get_pmceid(struct kvm_vcpu *vcpu, bool pmceid1)
 	if (!bmap)
 		return val;
 
+	nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1;
+
 	for (i = 0; i < 32; i += 8) {
 		u64 byte;
 
 		byte = bitmap_get_value8(bmap, base + i);
 		mask |= byte << i;
-		byte = bitmap_get_value8(bmap, 0x4000 + base + i);
-		mask |= byte << (32 + i);
+		if (nr_events >= (0x4000 + base + 32)) {
+			byte = bitmap_get_value8(bmap, 0x4000 + base + i);
+			mask |= byte << (32 + i);
+		}
 	}
 
 	return val & mask;
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 42ccc27fb684..7c4f79532406 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -43,6 +43,10 @@
  * 64bit interface.
  */
 
+#define reg_to_encoding(x)						\
+	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
+		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
+
 static bool read_from_write_only(struct kvm_vcpu *vcpu,
 				 struct sys_reg_params *params,
 				 const struct sys_reg_desc *r)
@@ -273,8 +277,7 @@ static bool trap_loregion(struct kvm_vcpu *vcpu,
 			  const struct sys_reg_desc *r)
 {
 	u64 val = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1);
-	u32 sr = sys_reg((u32)r->Op0, (u32)r->Op1,
-			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u32 sr = reg_to_encoding(r);
 
 	if (!(val & (0xfUL << ID_AA64MMFR1_LOR_SHIFT))) {
 		kvm_inject_undefined(vcpu);
@@ -590,6 +593,15 @@ static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	vcpu_write_sys_reg(vcpu, (1ULL << 31) | mpidr, MPIDR_EL1);
 }
 
+static unsigned int pmu_visibility(const struct kvm_vcpu *vcpu,
+				   const struct sys_reg_desc *r)
+{
+	if (kvm_vcpu_has_pmu(vcpu))
+		return 0;
+
+	return REG_HIDDEN;
+}
+
 static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 pmcr, val;
@@ -613,9 +625,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 static bool check_pmu_access_disabled(struct kvm_vcpu *vcpu, u64 flags)
 {
 	u64 reg = __vcpu_sys_reg(vcpu, PMUSERENR_EL0);
-	bool enabled = kvm_vcpu_has_pmu(vcpu);
+	bool enabled = (reg & flags) || vcpu_mode_priv(vcpu);
 
-	enabled &= (reg & flags) || vcpu_mode_priv(vcpu);
 	if (!enabled)
 		kvm_inject_undefined(vcpu);
 
@@ -900,11 +911,6 @@ static bool access_pmswinc(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			     const struct sys_reg_desc *r)
 {
-	if (!kvm_vcpu_has_pmu(vcpu)) {
-		kvm_inject_undefined(vcpu);
-		return false;
-	}
-
 	if (p->is_write) {
 		if (!vcpu_mode_priv(vcpu)) {
 			kvm_inject_undefined(vcpu);
@@ -921,10 +927,6 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	return true;
 }
 
-#define reg_to_encoding(x)						\
-	sys_reg((u32)(x)->Op0, (u32)(x)->Op1,				\
-		(u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2)
-
 /* Silly macro to expand the DBG{BCR,BVR,WVR,WCR}n_EL1 registers in one go */
 #define DBG_BCR_BVR_WCR_WVR_EL1(n)					\
 	{ SYS_DESC(SYS_DBGBVRn_EL1(n)),					\
@@ -936,15 +938,18 @@ static bool access_pmuserenr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	{ SYS_DESC(SYS_DBGWCRn_EL1(n)),					\
 	  trap_wcr, reset_wcr, 0, 0,  get_wcr, set_wcr }
 
+#define PMU_SYS_REG(r)						\
+	SYS_DESC(r), .reset = reset_unknown, .visibility = pmu_visibility
+
 /* Macro to expand the PMEVCNTRn_EL0 register */
 #define PMU_PMEVCNTR_EL0(n)						\
-	{ SYS_DESC(SYS_PMEVCNTRn_EL0(n)),					\
-	  access_pmu_evcntr, reset_unknown, (PMEVCNTR0_EL0 + n), }
+	{ PMU_SYS_REG(SYS_PMEVCNTRn_EL0(n)),				\
+	  .access = access_pmu_evcntr, .reg = (PMEVCNTR0_EL0 + n), }
 
 /* Macro to expand the PMEVTYPERn_EL0 register */
 #define PMU_PMEVTYPER_EL0(n)						\
-	{ SYS_DESC(SYS_PMEVTYPERn_EL0(n)),					\
-	  access_pmu_evtyper, reset_unknown, (PMEVTYPER0_EL0 + n), }
+	{ PMU_SYS_REG(SYS_PMEVTYPERn_EL0(n)),				\
+	  .access = access_pmu_evtyper, .reg = (PMEVTYPER0_EL0 + n), }
 
 static bool undef_access(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 			 const struct sys_reg_desc *r)
@@ -1020,8 +1025,7 @@ static bool access_arch_timer(struct kvm_vcpu *vcpu,
 static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 		struct sys_reg_desc const *r, bool raz)
 {
-	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
-			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u32 id = reg_to_encoding(r);
 	u64 val = raz ? 0 : read_sanitised_ftr_reg(id);
 
 	if (id == SYS_ID_AA64PFR0_EL1) {
@@ -1062,8 +1066,7 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
 				  const struct sys_reg_desc *r)
 {
-	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
-			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+	u32 id = reg_to_encoding(r);
 
 	switch (id) {
 	case SYS_ID_AA64ZFR0_EL1:
@@ -1486,8 +1489,10 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_FAR_EL1), access_vm_reg, reset_unknown, FAR_EL1 },
 	{ SYS_DESC(SYS_PAR_EL1), NULL, reset_unknown, PAR_EL1 },
 
-	{ SYS_DESC(SYS_PMINTENSET_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
-	{ SYS_DESC(SYS_PMINTENCLR_EL1), access_pminten, reset_unknown, PMINTENSET_EL1 },
+	{ PMU_SYS_REG(SYS_PMINTENSET_EL1),
+	  .access = access_pminten, .reg = PMINTENSET_EL1 },
+	{ PMU_SYS_REG(SYS_PMINTENCLR_EL1),
+	  .access = access_pminten, .reg = PMINTENSET_EL1 },
 
 	{ SYS_DESC(SYS_MAIR_EL1), access_vm_reg, reset_unknown, MAIR_EL1 },
 	{ SYS_DESC(SYS_AMAIR_EL1), access_vm_reg, reset_amair_el1, AMAIR_EL1 },
@@ -1526,23 +1531,36 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	{ SYS_DESC(SYS_CSSELR_EL1), access_csselr, reset_unknown, CSSELR_EL1 },
 	{ SYS_DESC(SYS_CTR_EL0), access_ctr },
 
-	{ SYS_DESC(SYS_PMCR_EL0), access_pmcr, reset_pmcr, PMCR_EL0 },
-	{ SYS_DESC(SYS_PMCNTENSET_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
-	{ SYS_DESC(SYS_PMCNTENCLR_EL0), access_pmcnten, reset_unknown, PMCNTENSET_EL0 },
-	{ SYS_DESC(SYS_PMOVSCLR_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 },
-	{ SYS_DESC(SYS_PMSWINC_EL0), access_pmswinc, reset_unknown, PMSWINC_EL0 },
-	{ SYS_DESC(SYS_PMSELR_EL0), access_pmselr, reset_unknown, PMSELR_EL0 },
-	{ SYS_DESC(SYS_PMCEID0_EL0), access_pmceid },
-	{ SYS_DESC(SYS_PMCEID1_EL0), access_pmceid },
-	{ SYS_DESC(SYS_PMCCNTR_EL0), access_pmu_evcntr, reset_unknown, PMCCNTR_EL0 },
-	{ SYS_DESC(SYS_PMXEVTYPER_EL0), access_pmu_evtyper },
-	{ SYS_DESC(SYS_PMXEVCNTR_EL0), access_pmu_evcntr },
+	{ PMU_SYS_REG(SYS_PMCR_EL0), .access = access_pmcr,
+	  .reset = reset_pmcr, .reg = PMCR_EL0 },
+	{ PMU_SYS_REG(SYS_PMCNTENSET_EL0),
+	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMCNTENCLR_EL0),
+	  .access = access_pmcnten, .reg = PMCNTENSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMOVSCLR_EL0),
+	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMSWINC_EL0),
+	  .access = access_pmswinc, .reg = PMSWINC_EL0 },
+	{ PMU_SYS_REG(SYS_PMSELR_EL0),
+	  .access = access_pmselr, .reg = PMSELR_EL0 },
+	{ PMU_SYS_REG(SYS_PMCEID0_EL0),
+	  .access = access_pmceid, .reset = NULL },
+	{ PMU_SYS_REG(SYS_PMCEID1_EL0),
+	  .access = access_pmceid, .reset = NULL },
+	{ PMU_SYS_REG(SYS_PMCCNTR_EL0),
+	  .access = access_pmu_evcntr, .reg = PMCCNTR_EL0 },
+	{ PMU_SYS_REG(SYS_PMXEVTYPER_EL0),
+	  .access = access_pmu_evtyper, .reset = NULL },
+	{ PMU_SYS_REG(SYS_PMXEVCNTR_EL0),
+	  .access = access_pmu_evcntr, .reset = NULL },
 	/*
 	 * PMUSERENR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ SYS_DESC(SYS_PMUSERENR_EL0), access_pmuserenr, reset_val, PMUSERENR_EL0, 0 },
-	{ SYS_DESC(SYS_PMOVSSET_EL0), access_pmovs, reset_unknown, PMOVSSET_EL0 },
+	{ PMU_SYS_REG(SYS_PMUSERENR_EL0), .access = access_pmuserenr,
+	  .reset = reset_val, .reg = PMUSERENR_EL0, .val = 0 },
+	{ PMU_SYS_REG(SYS_PMOVSSET_EL0),
+	  .access = access_pmovs, .reg = PMOVSSET_EL0 },
 
 	{ SYS_DESC(SYS_TPIDR_EL0), NULL, reset_unknown, TPIDR_EL0 },
 	{ SYS_DESC(SYS_TPIDRRO_EL0), NULL, reset_unknown, TPIDRRO_EL0 },
@@ -1694,7 +1712,8 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	 * PMCCFILTR_EL0 resets as unknown in 64bit mode while it resets as zero
 	 * in 32bit mode. Here we choose to reset it as zero for consistency.
 	 */
-	{ SYS_DESC(SYS_PMCCFILTR_EL0), access_pmu_evtyper, reset_val, PMCCFILTR_EL0, 0 },
+	{ PMU_SYS_REG(SYS_PMCCFILTR_EL0), .access = access_pmu_evtyper,
+	  .reset = reset_val, .reg = PMCCFILTR_EL0, .val = 0 },
 
 	{ SYS_DESC(SYS_DACR32_EL2), NULL, reset_unknown, DACR32_EL2 },
 	{ SYS_DESC(SYS_IFSR32_EL2), NULL, reset_unknown, IFSR32_EL2 },
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 3c40da479899..35d75c60e2b8 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -709,10 +709,11 @@ static int do_tag_check_fault(unsigned long far, unsigned int esr,
 			      struct pt_regs *regs)
 {
 	/*
-	 * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN for tag
-	 * check faults. Mask them out now so that userspace doesn't see them.
+	 * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN
+	 * for tag check faults. Set them to corresponding bits in the untagged
+	 * address.
 	 */
-	far &= (1UL << 60) - 1;
+	far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK);
 	do_bad_area(far, esr, regs);
 	return 0;
 }
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7deddf56f7c3..709d98fea90c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
 
 /*
- * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
- * memory as some devices, namely the Raspberry Pi 4, have peripherals with
- * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
- * bit addressable memory area.
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
-phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+		crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 	unsigned int __maybe_unused acpi_zone_dma_bits;
 	unsigned int __maybe_unused dt_zone_dma_bits;
+	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
 
 #ifdef CONFIG_ZONE_DMA
 	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
@@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -394,16 +399,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma32_phys_limit = max_zone_phys(32);
-	else
-		arm64_dma32_phys_limit = PHYS_MASK + 1;
-
 	reserve_elfcorehdr();
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
-	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -439,6 +437,11 @@ void __init bootmem_init(void)
 	zone_sizes_init(min, max);
 
 	/*
+	 * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+	 */
+	dma_contiguous_reserve(arm64_dma_phys_limit);
+
+	/*
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
@@ -455,7 +458,7 @@ void __init bootmem_init(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
diff --git a/arch/arm64/mm/physaddr.c b/arch/arm64/mm/physaddr.c
index 67a9ba9eaa96..cde44c13dda1 100644
--- a/arch/arm64/mm/physaddr.c
+++ b/arch/arm64/mm/physaddr.c
@@ -9,7 +9,7 @@
 
 phys_addr_t __virt_to_phys(unsigned long x)
 {
-	WARN(!__is_lm_address(x),
+	WARN(!__is_lm_address(__tag_reset(x)),
 	     "virt_to_phys used for non-linear address: %pK (%pS)\n",
 	      (void *)x,
 	      (void *)x);