Merge remote-tracking branch 'tip/sched/arm64' into for-next/core

* tip/sched/arm64: (785 commits)
  Documentation: arm64: describe asymmetric 32-bit support
  arm64: Remove logic to kill 32-bit tasks on 64-bit-only cores
  arm64: Hook up cmdline parameter to allow mismatched 32-bit EL0
  arm64: Advertise CPUs capable of running 32-bit applications in sysfs
  arm64: Prevent offlining first CPU with 32-bit EL0 on mismatched system
  arm64: exec: Adjust affinity for compat tasks with mismatched 32-bit EL0
  arm64: Implement task_cpu_possible_mask()
  sched: Introduce dl_task_check_affinity() to check proposed affinity
  sched: Allow task CPU affinity to be restricted on asymmetric systems
  sched: Split the guts of sched_setaffinity() into a helper function
  sched: Introduce task_struct::user_cpus_ptr to track requested affinity
  sched: Reject CPU affinity changes based on task_cpu_possible_mask()
  cpuset: Cleanup cpuset_cpus_allowed_fallback() use in select_fallback_rq()
  cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus()
  cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1
  sched: Introduce task_cpu_possible_mask() to limit fallback rq selection
  sched: Cgroup SCHED_IDLE support
  sched/topology: Skip updating masks for non-online nodes
  Linux 5.14-rc6
  lib: use PFN_PHYS() in devmem_is_allowed()
  ...

23 files changed, 236 insertions, 90 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b5b13a932561..fdcd54d39c1e 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1800,11 +1800,11 @@ config RANDOMIZE_BASE
 	  If unsure, say N.
 
 config RANDOMIZE_MODULE_REGION_FULL
-	bool "Randomize the module region over a 4 GB range"
+	bool "Randomize the module region over a 2 GB range"
 	depends on RANDOMIZE_BASE
 	default y
 	help
-	  Randomizes the location of the module region inside a 4 GB window
+	  Randomizes the location of the module region inside a 2 GB window
 	  covering the core kernel. This way, it is less likely for modules
 	  to leak information about the location of core kernel data structures
 	  but it does imply that function calls between modules and the core
@@ -1812,7 +1812,10 @@ config RANDOMIZE_MODULE_REGION_FULL
 
 	  When this option is not set, the module region will be randomized over
 	  a limited range that contains the [_stext, _etext] interval of the
-	  core kernel, so branch relocations are always in range.
+	  core kernel, so branch relocations are almost always in range unless
+	  ARM64_MODULE_PLTS is enabled and the region is exhausted. In this
+	  particular case of region exhaustion, modules might be able to fall
+	  back to a larger 2GB area.
 
 config CC_HAVE_STACKPROTECTOR_SYSREG
 	def_bool $(cc-option,-mstack-protector-guard=sysreg -mstack-protector-guard-reg=sp_el0 -mstack-protector-guard-offset=0)
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index ded13230f901..8b0fd9d92390 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -21,19 +21,11 @@ LDFLAGS_vmlinux		+= -shared -Bsymbolic -z notext \
 endif
 
 ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
-  ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
-$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum)
-  else
+  ifeq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
 LDFLAGS_vmlinux	+= --fix-cortex-a53-843419
   endif
 endif
 
-ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS), y)
-  ifneq ($(CONFIG_ARM64_LSE_ATOMICS), y)
-$(warning LSE atomics not supported by binutils)
-  endif
-endif
-
 cc_has_k_constraint := $(call try-run,echo				\
 	'int main(void) {						\
 		asm volatile("and w0, w0, %w0" :: "K" (4294967295));	\
@@ -179,6 +171,17 @@ vdso_install:
 
 archprepare:
 	$(Q)$(MAKE) $(build)=arch/arm64/tools kapi
+ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
+  ifneq ($(CONFIG_ARM64_LD_HAS_FIX_ERRATUM_843419),y)
+	@echo "warning: ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum" >&2
+  endif
+endif
+ifeq ($(CONFIG_ARM64_USE_LSE_ATOMICS),y)
+  ifneq ($(CONFIG_ARM64_LSE_ATOMICS),y)
+	@echo "warning: LSE atomics not supported by binutils" >&2
+  endif
+endif
+
 
 # We use MRPROPER_FILES and CLEAN_FILES now
 archclean:
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts
index dd764b720fb0..f6a79c8080d1 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a-kontron-sl28-var2.dts
@@ -54,6 +54,7 @@
 
 &mscc_felix_port0 {
 	label = "swp0";
+	managed = "in-band-status";
 	phy-handle = <&phy0>;
 	phy-mode = "sgmii";
 	status = "okay";
@@ -61,6 +62,7 @@
 
 &mscc_felix_port1 {
 	label = "swp1";
+	managed = "in-band-status";
 	phy-handle = <&phy1>;
 	phy-mode = "sgmii";
 	status = "okay";
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
index b2e3e5d2a108..343ecf0e8973 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi
@@ -66,7 +66,7 @@
 		};
 	};
 
-	sysclk: clock-sysclk {
+	sysclk: sysclk {
 		compatible = "fixed-clock";
 		#clock-cells = <0>;
 		clock-frequency = <100000000>;
diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
index ca38d0d6c3c4..f4eaab3ecf03 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
@@ -579,7 +579,7 @@
 			};
 
 			flexcan1: can@308c0000 {
-				compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+				compatible = "fsl,imx8mp-flexcan";
 				reg = <0x308c0000 0x10000>;
 				interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
@@ -594,7 +594,7 @@
 			};
 
 			flexcan2: can@308d0000 {
-				compatible = "fsl,imx8mp-flexcan", "fsl,imx6q-flexcan";
+				compatible = "fsl,imx8mp-flexcan";
 				reg = <0x308d0000 0x10000>;
 				interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>;
 				clocks = <&clk IMX8MP_CLK_IPG_ROOT>,
diff --git a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
index ce2bcddf396f..a05b1ab2dd12 100644
--- a/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
+++ b/arch/arm64/boot/dts/marvell/armada-3720-turris-mox.dts
@@ -19,6 +19,8 @@
 	aliases {
 		spi0 = &spi0;
 		ethernet1 = &eth1;
+		mmc0 = &sdhci0;
+		mmc1 = &sdhci1;
 	};
 
 	chosen {
@@ -119,6 +121,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&i2c1_pins>;
 	clock-frequency = <100000>;
+	/delete-property/ mrvl,i2c-fast-mode;
 	status = "okay";
 
 	rtc@6f {
diff --git a/arch/arm64/boot/dts/nvidia/tegra194.dtsi b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
index 076d5efc4c3d..5ba7a4519b95 100644
--- a/arch/arm64/boot/dts/nvidia/tegra194.dtsi
+++ b/arch/arm64/boot/dts/nvidia/tegra194.dtsi
@@ -1840,7 +1840,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE1R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE1W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE1>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE1 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14120000 {
@@ -1890,7 +1894,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE2AR &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE2AW &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE2>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE2 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14140000 {
@@ -1940,7 +1948,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE3R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE3W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE3>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE3 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14160000 {
@@ -1990,7 +2002,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE4>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@14180000 {
@@ -2040,7 +2056,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE0>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie@141a0000 {
@@ -2094,7 +2114,11 @@
 
 		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>,
 				<&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>;
-		interconnect-names = "read", "write";
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE5>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie_ep@14160000 {
@@ -2127,6 +2151,14 @@
 		nvidia,aspm-cmrt-us = <60>;
 		nvidia,aspm-pwr-on-t-us = <20>;
 		nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE4R &emc>,
+				<&mc TEGRA194_MEMORY_CLIENT_PCIE4W &emc>;
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE4>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE4 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie_ep@14180000 {
@@ -2159,6 +2191,14 @@
 		nvidia,aspm-cmrt-us = <60>;
 		nvidia,aspm-pwr-on-t-us = <20>;
 		nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE0R &emc>,
+				<&mc TEGRA194_MEMORY_CLIENT_PCIE0W &emc>;
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE0>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE0 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	pcie_ep@141a0000 {
@@ -2194,6 +2234,14 @@
 		nvidia,aspm-cmrt-us = <60>;
 		nvidia,aspm-pwr-on-t-us = <20>;
 		nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+		interconnects = <&mc TEGRA194_MEMORY_CLIENT_PCIE5R &emc>,
+				<&mc TEGRA194_MEMORY_CLIENT_PCIE5W &emc>;
+		interconnect-names = "dma-mem", "write";
+		iommus = <&smmu TEGRA194_SID_PCIE5>;
+		iommu-map = <0x0 &smmu TEGRA194_SID_PCIE5 0x1000>;
+		iommu-map-mask = <0x0>;
+		dma-coherent;
 	};
 
 	sram@40000000 {
diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h
index 8d1c8dcb87fd..97932fbf973d 100644
--- a/arch/arm64/include/asm/elf.h
+++ b/arch/arm64/include/asm/elf.h
@@ -213,10 +213,8 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 
 /* AArch32 EABI. */
 #define EF_ARM_EABI_MASK		0xff000000
-#define compat_elf_check_arch(x)	(system_supports_32bit_el0() && \
-					 ((x)->e_machine == EM_ARM) && \
-					 ((x)->e_flags & EF_ARM_EABI_MASK))
-
+int compat_elf_check_arch(const struct elf32_hdr *);
+#define compat_elf_check_arch		compat_elf_check_arch
 #define compat_start_thread		compat_start_thread
 /*
  * Unlike the native SET_PERSONALITY macro, the compat version maintains
diff --git a/arch/arm64/include/asm/mmu_context.h b/arch/arm64/include/asm/mmu_context.h
index eeb210997149..f4ba93d4ffeb 100644
--- a/arch/arm64/include/asm/mmu_context.h
+++ b/arch/arm64/include/asm/mmu_context.h
@@ -231,6 +231,19 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	update_saved_ttbr0(tsk, next);
 }
 
+static inline const struct cpumask *
+task_cpu_possible_mask(struct task_struct *p)
+{
+	if (!static_branch_unlikely(&arm64_mismatched_32bit_el0))
+		return cpu_possible_mask;
+
+	if (!is_compat_thread(task_thread_info(p)))
+		return cpu_possible_mask;
+
+	return system_32bit_el0_cpumask();
+}
+#define task_cpu_possible_mask	task_cpu_possible_mask
+
 void verify_cpu_asid_bits(void);
 void post_ttbr_update_workaround(void);
 
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index e58bca832dff..41b332c054ab 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -320,7 +320,17 @@ static inline unsigned long kernel_stack_pointer(struct pt_regs *regs)
 
 static inline unsigned long regs_return_value(struct pt_regs *regs)
 {
-	return regs->regs[0];
+	unsigned long val = regs->regs[0];
+
+	/*
+	 * Audit currently uses regs_return_value() instead of
+	 * syscall_get_return_value(). Apply the same sign-extension here until
+	 * audit is updated to use syscall_get_return_value().
+	 */
+	if (compat_user_mode(regs))
+		val = sign_extend64(val, 31);
+
+	return val;
 }
 
 static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc)
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 1801399204d7..8aebc00c1718 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -35,7 +35,7 @@ struct stack_info {
  * accounting information necessary for robust unwinding.
  *
  * @fp:          The fp value in the frame record (or the real fp)
- * @pc:          The fp value in the frame record (or the real lr)
+ * @pc:          The lr value in the frame record (or the real lr)
  *
  * @stacks_done: Stacks which have been entirely unwound, for which it is no
  *               longer valid to unwind to.
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index cfc0672013f6..03e20895453a 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -29,22 +29,23 @@ static inline void syscall_rollback(struct task_struct *task,
 	regs->regs[0] = regs->orig_x0;
 }
 
-
-static inline long syscall_get_error(struct task_struct *task,
-				     struct pt_regs *regs)
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
 {
-	unsigned long error = regs->regs[0];
+	unsigned long val = regs->regs[0];
 
 	if (is_compat_thread(task_thread_info(task)))
-		error = sign_extend64(error, 31);
+		val = sign_extend64(val, 31);
 
-	return IS_ERR_VALUE(error) ? error : 0;
+	return val;
 }
 
-static inline long syscall_get_return_value(struct task_struct *task,
-					    struct pt_regs *regs)
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
 {
-	return regs->regs[0];
+	unsigned long error = syscall_get_return_value(task, regs);
+
+	return IS_ERR_VALUE(error) ? error : 0;
 }
 
 static inline void syscall_set_return_value(struct task_struct *task,
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 23b1e3d83603..b2770d753ba3 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -67,6 +67,7 @@
 #include <linux/crash_dump.h>
 #include <linux/sort.h>
 #include <linux/stop_machine.h>
+#include <linux/sysfs.h>
 #include <linux/types.h>
 #include <linux/minmax.h>
 #include <linux/mm.h>
@@ -1321,6 +1322,31 @@ const struct cpumask *system_32bit_el0_cpumask(void)
 	return cpu_possible_mask;
 }
 
+static int __init parse_32bit_el0_param(char *str)
+{
+	allow_mismatched_32bit_el0 = true;
+	return 0;
+}
+early_param("allow_mismatched_32bit_el0", parse_32bit_el0_param);
+
+static ssize_t aarch32_el0_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	const struct cpumask *mask = system_32bit_el0_cpumask();
+
+	return sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(mask));
+}
+static const DEVICE_ATTR_RO(aarch32_el0);
+
+static int __init aarch32_el0_sysfs_init(void)
+{
+	if (!allow_mismatched_32bit_el0)
+		return 0;
+
+	return device_create_file(cpu_subsys.dev_root, &dev_attr_aarch32_el0);
+}
+device_initcall(aarch32_el0_sysfs_init);
+
 static bool has_32bit_el0(const struct arm64_cpu_capabilities *entry, int scope)
 {
 	if (!has_cpuid_feature(entry, scope))
@@ -2902,15 +2928,38 @@ void __init setup_cpu_features(void)
 
 static int enable_mismatched_32bit_el0(unsigned int cpu)
 {
+	/*
+	 * The first 32-bit-capable CPU we detected and so can no longer
+	 * be offlined by userspace. -1 indicates we haven't yet onlined
+	 * a 32-bit-capable CPU.
+	 */
+	static int lucky_winner = -1;
+
 	struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu);
 	bool cpu_32bit = id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0);
 
 	if (cpu_32bit) {
 		cpumask_set_cpu(cpu, cpu_32bit_el0_mask);
 		static_branch_enable_cpuslocked(&arm64_mismatched_32bit_el0);
-		setup_elf_hwcaps(compat_elf_hwcaps);
 	}
 
+	if (cpumask_test_cpu(0, cpu_32bit_el0_mask) == cpu_32bit)
+		return 0;
+
+	if (lucky_winner >= 0)
+		return 0;
+
+	/*
+	 * We've detected a mismatch. We need to keep one of our CPUs with
+	 * 32-bit EL0 online so that is_cpu_allowed() doesn't end up rejecting
+	 * every CPU in the system for a 32-bit task.
+	 */
+	lucky_winner = cpu_32bit ? cpu : cpumask_any_and(cpu_32bit_el0_mask,
+							 cpu_active_mask);
+	get_cpu_device(lucky_winner)->offline_disabled = true;
+	setup_elf_hwcaps(compat_elf_hwcaps);
+	pr_info("Asymmetric 32-bit EL0 support detected on CPU %u; CPU hot-unplug disabled on CPU %u\n",
+		cpu, lucky_winner);
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c
index cfa2cfde3019..418b2bba1521 100644
--- a/arch/arm64/kernel/kaslr.c
+++ b/arch/arm64/kernel/kaslr.c
@@ -162,7 +162,9 @@ u64 __init kaslr_early_init(void)
 		 * a PAGE_SIZE multiple in the range [_etext - MODULES_VSIZE,
 		 * _stext) . This guarantees that the resulting region still
 		 * covers [_stext, _etext], and that all relative branches can
-		 * be resolved without veneers.
+		 * be resolved without veneers unless this region is exhausted
+		 * and we fall back to a larger 2GB window in module_alloc()
+		 * when ARM64_MODULE_PLTS is enabled.
 		 */
 		module_range = MODULES_VSIZE - (u64)(_etext - _stext);
 		module_alloc_base = (u64)_etext + offset - MODULES_VSIZE;
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 5464d575192b..2bd270cd603e 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -21,6 +21,7 @@
 #include <linux/mman.h>
 #include <linux/mm.h>
 #include <linux/nospec.h>
+#include <linux/sched.h>
 #include <linux/stddef.h>
 #include <linux/sysctl.h>
 #include <linux/unistd.h>
@@ -472,15 +473,6 @@ static void erratum_1418040_thread_switch(struct task_struct *prev,
 	write_sysreg(val, cntkctl_el1);
 }
 
-static void compat_thread_switch(struct task_struct *next)
-{
-	if (!is_compat_thread(task_thread_info(next)))
-		return;
-
-	if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
-		set_tsk_thread_flag(next, TIF_NOTIFY_RESUME);
-}
-
 /*
  * __switch_to() checks current->thread.sctlr_user as an optimisation. Therefore
  * this function must be called with preemption disabled and the update to
@@ -515,7 +507,6 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev,
 	ssbs_thread_switch(next);
 	erratum_1418040_thread_switch(prev, next);
 	ptrauth_thread_switch_user(next);
-	compat_thread_switch(next);
 
 	/*
 	 * Complete any pending TLB or cache maintenance on this CPU in case
@@ -576,6 +567,28 @@ unsigned long arch_align_stack(unsigned long sp)
 	return sp & ~0xf;
 }
 
+#ifdef CONFIG_COMPAT
+int compat_elf_check_arch(const struct elf32_hdr *hdr)
+{
+	if (!system_supports_32bit_el0())
+		return false;
+
+	if ((hdr)->e_machine != EM_ARM)
+		return false;
+
+	if (!((hdr)->e_flags & EF_ARM_EABI_MASK))
+		return false;
+
+	/*
+	 * Prevent execve() of a 32-bit program from a deadline task
+	 * if the restricted affinity mask would be inadmissible on an
+	 * asymmetric system.
+	 */
+	return !static_branch_unlikely(&arm64_mismatched_32bit_el0) ||
+	       !dl_task_check_affinity(current, system_32bit_el0_cpumask());
+}
+#endif
+
 /*
  * Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY.
  */
@@ -585,8 +598,20 @@ void arch_setup_new_exec(void)
 
 	if (is_compat_task()) {
 		mmflags = MMCF_AARCH32;
+
+		/*
+		 * Restrict the CPU affinity mask for a 32-bit task so that
+		 * it contains only 32-bit-capable CPUs.
+		 *
+		 * From the perspective of the task, this looks similar to
+		 * what would happen if the 64-bit-only CPUs were hot-unplugged
+		 * at the point of execve(), although we try a bit harder to
+		 * honour the cpuset hierarchy.
+		 */
 		if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
-			set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+			force_compatible_cpus_allowed_ptr(current);
+	} else if (static_branch_unlikely(&arm64_mismatched_32bit_el0)) {
+		relax_compatible_cpus_allowed_ptr(current);
 	}
 
 	current->mm->context.flags = mmflags;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 956e2df27180..e26196a33cf4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1867,7 +1867,7 @@ void syscall_trace_exit(struct pt_regs *regs)
 	audit_syscall_exit(regs);
 
 	if (flags & _TIF_SYSCALL_TRACEPOINT)
-		trace_sys_exit(regs, regs_return_value(regs));
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
 
 	if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index e93ffd7d38e1..fb54fb76e17f 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -29,6 +29,7 @@
 #include <asm/unistd.h>
 #include <asm/fpsimd.h>
 #include <asm/ptrace.h>
+#include <asm/syscall.h>
 #include <asm/signal32.h>
 #include <asm/traps.h>
 #include <asm/vdso.h>
@@ -895,7 +896,7 @@ static void do_signal(struct pt_regs *regs)
 		     retval == -ERESTART_RESTARTBLOCK ||
 		     (retval == -ERESTARTSYS &&
 		      !(ksig.ka.sa.sa_flags & SA_RESTART)))) {
-			regs->regs[0] = -EINTR;
+			syscall_set_return_value(current, regs, -EINTR, 0);
 			regs->pc = continue_addr;
 		}
 
@@ -916,19 +917,6 @@ static void do_signal(struct pt_regs *regs)
 	restore_saved_sigmask();
 }
 
-static bool cpu_affinity_invalid(struct pt_regs *regs)
-{
-	if (!compat_user_mode(regs))
-		return false;
-
-	/*
-	 * We're preemptible, but a reschedule will cause us to check the
-	 * affinity again.
-	 */
-	return !cpumask_test_cpu(raw_smp_processor_id(),
-				 system_32bit_el0_cpumask());
-}
-
 void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags)
 {
 	do {
@@ -955,19 +943,6 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_flags)
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
 				tracehook_notify_resume(regs);
 				rseq_handle_notify_resume(NULL, regs);
-
-				/*
-				 * If we reschedule after checking the affinity
-				 * then we must ensure that TIF_NOTIFY_RESUME
-				 * is set so that we check the affinity again.
-				 * Since tracehook_notify_resume() clears the
-				 * flag, ensure that the compiler doesn't move
-				 * it after the affinity check.
-				 */
-				barrier();
-
-				if (cpu_affinity_invalid(regs))
-					force_sig(SIGKILL);
 			}
 
 			if (thread_flags & _TIF_FOREIGN_FPSTATE)
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index b83c8d911930..8982a2b78acf 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -218,7 +218,7 @@ void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl)
 
 #ifdef CONFIG_STACKTRACE
 
-noinline void arch_stack_walk(stack_trace_consume_fn consume_entry,
+noinline notrace void arch_stack_walk(stack_trace_consume_fn consume_entry,
 			      void *cookie, struct task_struct *task,
 			      struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 263d6c1a525f..50a0f1a38e84 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -54,10 +54,7 @@ static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 		ret = do_ni_syscall(regs, scno);
 	}
 
-	if (is_compat_task())
-		ret = lower_32_bits(ret);
-
-	regs->regs[0] = ret;
+	syscall_set_return_value(current, regs, 0, ret);
 
 	/*
 	 * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
@@ -115,7 +112,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 		 * syscall. do_notify_resume() will send a signal to userspace
 		 * before the syscall is restarted.
 		 */
-		regs->regs[0] = -ERESTARTNOINTR;
+		syscall_set_return_value(current, regs, -ERESTARTNOINTR, 0);
 		return;
 	}
 
@@ -136,7 +133,7 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 		 * anyway.
 		 */
 		if (scno == NO_SYSCALL)
-			regs->regs[0] = -ENOSYS;
+			syscall_set_return_value(current, regs, -ENOSYS, 0);
 		scno = syscall_trace_enter(regs);
 		if (scno == NO_SYSCALL)
 			goto trace_exit;
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index e9a2b8f27792..0ca72f5cda41 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -94,10 +94,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
 		kvm->arch.return_nisv_io_abort_to_user = true;
 		break;
 	case KVM_CAP_ARM_MTE:
-		if (!system_supports_mte() || kvm->created_vcpus)
-			return -EINVAL;
-		r = 0;
-		kvm->arch.mte_enabled = true;
+		mutex_lock(&kvm->lock);
+		if (!system_supports_mte() || kvm->created_vcpus) {
+			r = -EINVAL;
+		} else {
+			r = 0;
+			kvm->arch.mte_enabled = true;
+		}
+		mutex_unlock(&kvm->lock);
 		break;
 	default:
 		r = -EINVAL;
diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
index d938ce95d3bd..a6ce991b1467 100644
--- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
+++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
@@ -193,7 +193,7 @@ static bool range_is_memory(u64 start, u64 end)
 {
 	struct kvm_mem_range r1, r2;
 
-	if (!find_mem_range(start, &r1) || !find_mem_range(end, &r2))
+	if (!find_mem_range(start, &r1) || !find_mem_range(end - 1, &r2))
 		return false;
 	if (r1.start != r2.start)
 		return false;
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 3155c9e778f0..0625bf2353c2 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -947,7 +947,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 		vma_shift = get_vma_page_shift(vma, hva);
 	}
 
-	shared = (vma->vm_flags & VM_PFNMAP);
+	shared = (vma->vm_flags & VM_SHARED);
 
 	switch (vma_shift) {
 #ifndef __PAGETABLE_PMD_FOLDED
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index dccf98a37283..41c23f474ea6 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -823,6 +823,19 @@ emit_cond_jmp:
 			return ret;
 		break;
 
+	/* speculation barrier */
+	case BPF_ST | BPF_NOSPEC:
+		/*
+		 * Nothing required here.
+		 *
+		 * In case of arm64, we rely on the firmware mitigation of
+		 * Speculative Store Bypass as controlled via the ssbd kernel
+		 * parameter. Whenever the mitigation is enabled, it works
+		 * for all of the kernel code with no need to provide any
+		 * additional instructions.
+		 */
+		break;
+
 	/* ST: *(size *)(dst + off) = imm */
 	case BPF_ST | BPF_MEM | BPF_W:
 	case BPF_ST | BPF_MEM | BPF_H: