Merging upstream version 6.8.9.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

36 files changed, 1581 insertions, 556 deletions

diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index 40d054939a..604d6bf7e4 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -12,7 +12,7 @@ endif
 CFLAGS_syscall_table.o	+= $(call cc-option,-Wno-override-init,)
 CFLAGS_compat_syscall_table.o += $(call cc-option,-Wno-override-init,)
 
-ifdef CONFIG_KEXEC
+ifdef CONFIG_KEXEC_CORE
 AFLAGS_kexec_relocate.o := -mcmodel=medany $(call cc-option,-mno-relax)
 endif
 
@@ -52,6 +52,7 @@ obj-y	+= setup.o
 obj-y	+= signal.o
 obj-y	+= syscall_table.o
 obj-y	+= sys_riscv.o
+obj-y	+= sys_hwprobe.o
 obj-y	+= time.o
 obj-y	+= traps.o
 obj-y	+= riscv_ksyms.o
@@ -65,6 +66,7 @@ obj-$(CONFIG_MMU) += vdso.o vdso/
 obj-$(CONFIG_RISCV_MISALIGNED)	+= traps_misaligned.o
 obj-$(CONFIG_FPU)		+= fpu.o
 obj-$(CONFIG_RISCV_ISA_V)	+= vector.o
+obj-$(CONFIG_RISCV_ISA_V)	+= kernel_mode_vector.o
 obj-$(CONFIG_SMP)		+= smpboot.o
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_SMP)		+= cpu_ops.o
@@ -87,6 +89,7 @@ obj-$(CONFIG_SMP)		+= sbi-ipi.o
 obj-$(CONFIG_SMP) += cpu_ops_sbi.o
 endif
 obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_KEXEC_CORE)	+= kexec_relocate.o crash_save_regs.o machine_kexec.o
 obj-$(CONFIG_KEXEC_FILE)	+= elf_kexec.o machine_kexec_file.o
diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c
index 820158d7a2..6ec9dbd729 100644
--- a/arch/riscv/kernel/cfi.c
+++ b/arch/riscv/kernel/cfi.c
@@ -4,7 +4,7 @@
  *
  * Copyright (C) 2023 Google LLC
  */
-#include <asm/cfi.h>
+#include <linux/cfi.h>
 #include <asm/insn.h>
 
 /*
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
index 457a18efcb..28b58fc5ad 100644
--- a/arch/riscv/kernel/cpu-hotplug.c
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -18,7 +18,7 @@
 
 bool cpu_has_hotplug(unsigned int cpu)
 {
-	if (cpu_ops[cpu]->cpu_stop)
+	if (cpu_ops->cpu_stop)
 		return true;
 
 	return false;
@@ -29,25 +29,18 @@ bool cpu_has_hotplug(unsigned int cpu)
  */
 int __cpu_disable(void)
 {
-	int ret = 0;
 	unsigned int cpu = smp_processor_id();
 
-	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+	if (!cpu_ops->cpu_stop)
 		return -EOPNOTSUPP;
 
-	if (cpu_ops[cpu]->cpu_disable)
-		ret = cpu_ops[cpu]->cpu_disable(cpu);
-
-	if (ret)
-		return ret;
-
 	remove_cpu_topology(cpu);
 	numa_remove_cpu(cpu);
 	set_cpu_online(cpu, false);
 	riscv_ipi_disable();
 	irq_migrate_all_off_this_cpu();
 
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -62,8 +55,8 @@ void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu)
 	pr_notice("CPU%u: off\n", cpu);
 
 	/* Verify from the firmware if the cpu is really stopped*/
-	if (cpu_ops[cpu]->cpu_is_stopped)
-		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (cpu_ops->cpu_is_stopped)
+		ret = cpu_ops->cpu_is_stopped(cpu);
 	if (ret)
 		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
 }
@@ -77,7 +70,7 @@ void __noreturn arch_cpu_idle_dead(void)
 
 	cpuhp_ap_report_dead();
 
-	cpu_ops[smp_processor_id()]->cpu_stop();
+	cpu_ops->cpu_stop();
 	/* It should never reach here */
 	BUG();
 }
diff --git a/arch/riscv/kernel/cpu_ops.c b/arch/riscv/kernel/cpu_ops.c
index eb479a88a9..6a8bd8f4db 100644
--- a/arch/riscv/kernel/cpu_ops.c
+++ b/arch/riscv/kernel/cpu_ops.c
@@ -13,25 +13,21 @@
 #include <asm/sbi.h>
 #include <asm/smp.h>
 
-const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
+const struct cpu_operations *cpu_ops __ro_after_init = &cpu_ops_spinwait;
 
 extern const struct cpu_operations cpu_ops_sbi;
 #ifndef CONFIG_RISCV_BOOT_SPINWAIT
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "",
-	.cpu_prepare	= NULL,
 	.cpu_start	= NULL,
 };
 #endif
 
-void __init cpu_set_ops(int cpuid)
+void __init cpu_set_ops(void)
 {
 #if IS_ENABLED(CONFIG_RISCV_SBI)
 	if (sbi_probe_extension(SBI_EXT_HSM)) {
-		if (!cpuid)
-			pr_info("SBI HSM extension detected\n");
-		cpu_ops[cpuid] = &cpu_ops_sbi;
-	} else
+		pr_info("SBI HSM extension detected\n");
+		cpu_ops = &cpu_ops_sbi;
+	}
 #endif
-		cpu_ops[cpuid] = &cpu_ops_spinwait;
 }
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index efa0f08166..1cc7df740e 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -79,23 +79,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	return sbi_hsm_hart_start(hartid, boot_addr, hsm_data);
 }
 
-static int sbi_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
-static int sbi_cpu_disable(unsigned int cpuid)
-{
-	if (!cpu_ops_sbi.cpu_stop)
-		return -EOPNOTSUPP;
-	return 0;
-}
-
 static void sbi_cpu_stop(void)
 {
 	int ret;
@@ -118,11 +102,8 @@ static int sbi_cpu_is_stopped(unsigned int cpuid)
 #endif
 
 const struct cpu_operations cpu_ops_sbi = {
-	.name		= "sbi",
-	.cpu_prepare	= sbi_cpu_prepare,
 	.cpu_start	= sbi_cpu_start,
 #ifdef CONFIG_HOTPLUG_CPU
-	.cpu_disable	= sbi_cpu_disable,
 	.cpu_stop	= sbi_cpu_stop,
 	.cpu_is_stopped	= sbi_cpu_is_stopped,
 #endif
diff --git a/arch/riscv/kernel/cpu_ops_spinwait.c b/arch/riscv/kernel/cpu_ops_spinwait.c
index d98d19226b..613872b0a2 100644
--- a/arch/riscv/kernel/cpu_ops_spinwait.c
+++ b/arch/riscv/kernel/cpu_ops_spinwait.c
@@ -39,15 +39,6 @@ static void cpu_update_secondary_bootdata(unsigned int cpuid,
 	WRITE_ONCE(__cpu_spinwait_task_pointer[hartid], tidle);
 }
 
-static int spinwait_cpu_prepare(unsigned int cpuid)
-{
-	if (!cpu_ops_spinwait.cpu_start) {
-		pr_err("cpu start method not defined for CPU [%d]\n", cpuid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 {
 	/*
@@ -64,7 +55,5 @@ static int spinwait_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 }
 
 const struct cpu_operations cpu_ops_spinwait = {
-	.name		= "spinwait",
-	.cpu_prepare	= spinwait_cpu_prepare,
 	.cpu_start	= spinwait_cpu_start,
 };
diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index 8677788133..79a5a35fab 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -8,8 +8,10 @@
 
 #include <linux/acpi.h>
 #include <linux/bitmap.h>
+#include <linux/cpu.h>
 #include <linux/cpuhotplug.h>
 #include <linux/ctype.h>
+#include <linux/jump_label.h>
 #include <linux/log2.h>
 #include <linux/memory.h>
 #include <linux/module.h>
@@ -45,6 +47,8 @@ struct riscv_isainfo hart_isa[NR_CPUS];
 /* Performance information */
 DEFINE_PER_CPU(long, misaligned_access_speed);
 
+static cpumask_t fast_misaligned_access;
+
 /**
  * riscv_isa_extension_base() - Get base extension word
  *
@@ -71,7 +75,7 @@ EXPORT_SYMBOL_GPL(riscv_isa_extension_base);
  *
  * NOTE: If isa_bitmap is NULL then Host ISA bitmap will be used.
  */
-bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, int bit)
+bool __riscv_isa_extension_available(const unsigned long *isa_bitmap, unsigned int bit)
 {
 	const unsigned long *bmap = (isa_bitmap) ? isa_bitmap : riscv_isa;
 
@@ -103,17 +107,111 @@ static bool riscv_isa_extension_check(int id)
 			return false;
 		}
 		return true;
+	case RISCV_ISA_EXT_INVALID:
+		return false;
 	}
 
 	return true;
 }
 
-#define __RISCV_ISA_EXT_DATA(_name, _id) {	\
-	.name = #_name,				\
-	.property = #_name,			\
-	.id = _id,				\
+#define _RISCV_ISA_EXT_DATA(_name, _id, _subset_exts, _subset_exts_size) {	\
+	.name = #_name,								\
+	.property = #_name,							\
+	.id = _id,								\
+	.subset_ext_ids = _subset_exts,						\
+	.subset_ext_size = _subset_exts_size					\
 }
 
+#define __RISCV_ISA_EXT_DATA(_name, _id) _RISCV_ISA_EXT_DATA(_name, _id, NULL, 0)
+
+/* Used to declare pure "lasso" extension (Zk for instance) */
+#define __RISCV_ISA_EXT_BUNDLE(_name, _bundled_exts) \
+	_RISCV_ISA_EXT_DATA(_name, RISCV_ISA_EXT_INVALID, _bundled_exts, ARRAY_SIZE(_bundled_exts))
+
+/* Used to declare extensions that are a superset of other extensions (Zvbb for instance) */
+#define __RISCV_ISA_EXT_SUPERSET(_name, _id, _sub_exts) \
+	_RISCV_ISA_EXT_DATA(_name, _id, _sub_exts, ARRAY_SIZE(_sub_exts))
+
+static const unsigned int riscv_zk_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKR,
+	RISCV_ISA_EXT_ZKT,
+};
+
+static const unsigned int riscv_zkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZBKX,
+	RISCV_ISA_EXT_ZKND,
+	RISCV_ISA_EXT_ZKNE,
+	RISCV_ISA_EXT_ZKNH,
+};
+
+static const unsigned int riscv_zks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZBKB,
+	RISCV_ISA_EXT_ZBKC,
+	RISCV_ISA_EXT_ZKSED,
+	RISCV_ISA_EXT_ZKSH
+};
+
+#define RISCV_ISA_EXT_ZVKN	\
+	RISCV_ISA_EXT_ZVKNED,	\
+	RISCV_ISA_EXT_ZVKNHB,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvkn_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN
+};
+
+static const unsigned int riscv_zvknc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvkng_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKN,
+	RISCV_ISA_EXT_ZVKG
+};
+
+#define RISCV_ISA_EXT_ZVKS	\
+	RISCV_ISA_EXT_ZVKSED,	\
+	RISCV_ISA_EXT_ZVKSH,	\
+	RISCV_ISA_EXT_ZVKB,	\
+	RISCV_ISA_EXT_ZVKT
+
+static const unsigned int riscv_zvks_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS
+};
+
+static const unsigned int riscv_zvksc_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVBC
+};
+
+static const unsigned int riscv_zvksg_bundled_exts[] = {
+	RISCV_ISA_EXT_ZVKS,
+	RISCV_ISA_EXT_ZVKG
+};
+
+static const unsigned int riscv_zvbb_exts[] = {
+	RISCV_ISA_EXT_ZVKB
+};
+
+/*
+ * While the [ms]envcfg CSRs were not defined until version 1.12 of the RISC-V
+ * privileged ISA, the existence of the CSRs is implied by any extension which
+ * specifies [ms]envcfg bit(s). Hence, we define a custom ISA extension for the
+ * existence of the CSR, and treat it as a subset of those other extensions.
+ */
+static const unsigned int riscv_xlinuxenvcfg_exts[] = {
+	RISCV_ISA_EXT_XLINUXENVCFG
+};
+
 /*
  * The canonical order of ISA extension names in the ISA string is defined in
  * chapter 27 of the unprivileged specification.
@@ -161,23 +259,57 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 	__RISCV_ISA_EXT_DATA(d, RISCV_ISA_EXT_d),
 	__RISCV_ISA_EXT_DATA(q, RISCV_ISA_EXT_q),
 	__RISCV_ISA_EXT_DATA(c, RISCV_ISA_EXT_c),
-	__RISCV_ISA_EXT_DATA(b, RISCV_ISA_EXT_b),
-	__RISCV_ISA_EXT_DATA(k, RISCV_ISA_EXT_k),
-	__RISCV_ISA_EXT_DATA(j, RISCV_ISA_EXT_j),
-	__RISCV_ISA_EXT_DATA(p, RISCV_ISA_EXT_p),
 	__RISCV_ISA_EXT_DATA(v, RISCV_ISA_EXT_v),
 	__RISCV_ISA_EXT_DATA(h, RISCV_ISA_EXT_h),
-	__RISCV_ISA_EXT_DATA(zicbom, RISCV_ISA_EXT_ZICBOM),
-	__RISCV_ISA_EXT_DATA(zicboz, RISCV_ISA_EXT_ZICBOZ),
+	__RISCV_ISA_EXT_SUPERSET(zicbom, RISCV_ISA_EXT_ZICBOM, riscv_xlinuxenvcfg_exts),
+	__RISCV_ISA_EXT_SUPERSET(zicboz, RISCV_ISA_EXT_ZICBOZ, riscv_xlinuxenvcfg_exts),
 	__RISCV_ISA_EXT_DATA(zicntr, RISCV_ISA_EXT_ZICNTR),
 	__RISCV_ISA_EXT_DATA(zicond, RISCV_ISA_EXT_ZICOND),
 	__RISCV_ISA_EXT_DATA(zicsr, RISCV_ISA_EXT_ZICSR),
 	__RISCV_ISA_EXT_DATA(zifencei, RISCV_ISA_EXT_ZIFENCEI),
+	__RISCV_ISA_EXT_DATA(zihintntl, RISCV_ISA_EXT_ZIHINTNTL),
 	__RISCV_ISA_EXT_DATA(zihintpause, RISCV_ISA_EXT_ZIHINTPAUSE),
 	__RISCV_ISA_EXT_DATA(zihpm, RISCV_ISA_EXT_ZIHPM),
+	__RISCV_ISA_EXT_DATA(zacas, RISCV_ISA_EXT_ZACAS),
+	__RISCV_ISA_EXT_DATA(zfa, RISCV_ISA_EXT_ZFA),
+	__RISCV_ISA_EXT_DATA(zfh, RISCV_ISA_EXT_ZFH),
+	__RISCV_ISA_EXT_DATA(zfhmin, RISCV_ISA_EXT_ZFHMIN),
 	__RISCV_ISA_EXT_DATA(zba, RISCV_ISA_EXT_ZBA),
 	__RISCV_ISA_EXT_DATA(zbb, RISCV_ISA_EXT_ZBB),
+	__RISCV_ISA_EXT_DATA(zbc, RISCV_ISA_EXT_ZBC),
+	__RISCV_ISA_EXT_DATA(zbkb, RISCV_ISA_EXT_ZBKB),
+	__RISCV_ISA_EXT_DATA(zbkc, RISCV_ISA_EXT_ZBKC),
+	__RISCV_ISA_EXT_DATA(zbkx, RISCV_ISA_EXT_ZBKX),
 	__RISCV_ISA_EXT_DATA(zbs, RISCV_ISA_EXT_ZBS),
+	__RISCV_ISA_EXT_BUNDLE(zk, riscv_zk_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zkn, riscv_zkn_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zknd, RISCV_ISA_EXT_ZKND),
+	__RISCV_ISA_EXT_DATA(zkne, RISCV_ISA_EXT_ZKNE),
+	__RISCV_ISA_EXT_DATA(zknh, RISCV_ISA_EXT_ZKNH),
+	__RISCV_ISA_EXT_DATA(zkr, RISCV_ISA_EXT_ZKR),
+	__RISCV_ISA_EXT_BUNDLE(zks, riscv_zks_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zkt, RISCV_ISA_EXT_ZKT),
+	__RISCV_ISA_EXT_DATA(zksed, RISCV_ISA_EXT_ZKSED),
+	__RISCV_ISA_EXT_DATA(zksh, RISCV_ISA_EXT_ZKSH),
+	__RISCV_ISA_EXT_DATA(ztso, RISCV_ISA_EXT_ZTSO),
+	__RISCV_ISA_EXT_SUPERSET(zvbb, RISCV_ISA_EXT_ZVBB, riscv_zvbb_exts),
+	__RISCV_ISA_EXT_DATA(zvbc, RISCV_ISA_EXT_ZVBC),
+	__RISCV_ISA_EXT_DATA(zvfh, RISCV_ISA_EXT_ZVFH),
+	__RISCV_ISA_EXT_DATA(zvfhmin, RISCV_ISA_EXT_ZVFHMIN),
+	__RISCV_ISA_EXT_DATA(zvkb, RISCV_ISA_EXT_ZVKB),
+	__RISCV_ISA_EXT_DATA(zvkg, RISCV_ISA_EXT_ZVKG),
+	__RISCV_ISA_EXT_BUNDLE(zvkn, riscv_zvkn_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvknc, riscv_zvknc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkned, RISCV_ISA_EXT_ZVKNED),
+	__RISCV_ISA_EXT_BUNDLE(zvkng, riscv_zvkng_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvknha, RISCV_ISA_EXT_ZVKNHA),
+	__RISCV_ISA_EXT_DATA(zvknhb, RISCV_ISA_EXT_ZVKNHB),
+	__RISCV_ISA_EXT_BUNDLE(zvks, riscv_zvks_bundled_exts),
+	__RISCV_ISA_EXT_BUNDLE(zvksc, riscv_zvksc_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvksed, RISCV_ISA_EXT_ZVKSED),
+	__RISCV_ISA_EXT_DATA(zvksh, RISCV_ISA_EXT_ZVKSH),
+	__RISCV_ISA_EXT_BUNDLE(zvksg, riscv_zvksg_bundled_exts),
+	__RISCV_ISA_EXT_DATA(zvkt, RISCV_ISA_EXT_ZVKT),
 	__RISCV_ISA_EXT_DATA(smaia, RISCV_ISA_EXT_SMAIA),
 	__RISCV_ISA_EXT_DATA(smstateen, RISCV_ISA_EXT_SMSTATEEN),
 	__RISCV_ISA_EXT_DATA(ssaia, RISCV_ISA_EXT_SSAIA),
@@ -190,6 +322,31 @@ const struct riscv_isa_ext_data riscv_isa_ext[] = {
 
 const size_t riscv_isa_ext_count = ARRAY_SIZE(riscv_isa_ext);
 
+static void __init match_isa_ext(const struct riscv_isa_ext_data *ext, const char *name,
+				 const char *name_end, struct riscv_isainfo *isainfo)
+{
+	if ((name_end - name == strlen(ext->name)) &&
+	     !strncasecmp(name, ext->name, name_end - name)) {
+		/*
+		 * If this is a bundle, enable all the ISA extensions that
+		 * comprise the bundle.
+		 */
+		if (ext->subset_ext_size) {
+			for (int i = 0; i < ext->subset_ext_size; i++) {
+				if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+					set_bit(ext->subset_ext_ids[i], isainfo->isa);
+			}
+		}
+
+		/*
+		 * This is valid even for bundle extensions which uses the RISCV_ISA_EXT_INVALID id
+		 * (rejected by riscv_isa_extension_check()).
+		 */
+		if (riscv_isa_extension_check(ext->id))
+			set_bit(ext->id, isainfo->isa);
+	}
+}
+
 static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct riscv_isainfo *isainfo,
 					  unsigned long *isa2hwcap, const char *isa)
 {
@@ -322,14 +479,6 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 		if (*isa == '_')
 			++isa;
 
-#define SET_ISA_EXT_MAP(name, bit)						\
-		do {								\
-			if ((ext_end - ext == strlen(name)) &&			\
-			     !strncasecmp(ext, name, strlen(name)) &&		\
-			     riscv_isa_extension_check(bit))			\
-				set_bit(bit, isainfo->isa);			\
-		} while (false)							\
-
 		if (unlikely(ext_err))
 			continue;
 		if (!ext_long) {
@@ -341,10 +490,8 @@ static void __init riscv_parse_isa_string(unsigned long *this_hwcap, struct risc
 			}
 		} else {
 			for (int i = 0; i < riscv_isa_ext_count; i++)
-				SET_ISA_EXT_MAP(riscv_isa_ext[i].name,
-						riscv_isa_ext[i].id);
+				match_isa_ext(&riscv_isa_ext[i], ext, ext_end, isainfo);
 		}
-#undef SET_ISA_EXT_MAP
 	}
 }
 
@@ -457,18 +604,26 @@ static int __init riscv_fill_hwcap_from_ext_list(unsigned long *isa2hwcap)
 		}
 
 		for (int i = 0; i < riscv_isa_ext_count; i++) {
+			const struct riscv_isa_ext_data *ext = &riscv_isa_ext[i];
+
 			if (of_property_match_string(cpu_node, "riscv,isa-extensions",
-						     riscv_isa_ext[i].property) < 0)
+						     ext->property) < 0)
 				continue;
 
-			if (!riscv_isa_extension_check(riscv_isa_ext[i].id))
-				continue;
+			if (ext->subset_ext_size) {
+				for (int j = 0; j < ext->subset_ext_size; j++) {
+					if (riscv_isa_extension_check(ext->subset_ext_ids[i]))
+						set_bit(ext->subset_ext_ids[j], isainfo->isa);
+				}
+			}
 
-			/* Only single letter extensions get set in hwcap */
-			if (strnlen(riscv_isa_ext[i].name, 2) == 1)
-				this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			if (riscv_isa_extension_check(ext->id)) {
+				set_bit(ext->id, isainfo->isa);
 
-			set_bit(riscv_isa_ext[i].id, isainfo->isa);
+				/* Only single letter extensions get set in hwcap */
+				if (strnlen(riscv_isa_ext[i].name, 2) == 1)
+					this_hwcap |= isa2hwcap[riscv_isa_ext[i].id];
+			}
 		}
 
 		of_node_put(cpu_node);
@@ -658,6 +813,16 @@ static int check_unaligned_access(void *param)
 		(speed == RISCV_HWPROBE_MISALIGNED_FAST) ? "fast" : "slow");
 
 	per_cpu(misaligned_access_speed, cpu) = speed;
+
+	/*
+	 * Set the value of fast_misaligned_access of a CPU. These operations
+	 * are atomic to avoid race conditions.
+	 */
+	if (speed == RISCV_HWPROBE_MISALIGNED_FAST)
+		cpumask_set_cpu(cpu, &fast_misaligned_access);
+	else
+		cpumask_clear_cpu(cpu, &fast_misaligned_access);
+
 	return 0;
 }
 
@@ -670,13 +835,69 @@ static void check_unaligned_access_nonboot_cpu(void *param)
 		check_unaligned_access(pages[cpu]);
 }
 
+DEFINE_STATIC_KEY_FALSE(fast_misaligned_access_speed_key);
+
+static void modify_unaligned_access_branches(cpumask_t *mask, int weight)
+{
+	if (cpumask_weight(mask) == weight)
+		static_branch_enable_cpuslocked(&fast_misaligned_access_speed_key);
+	else
+		static_branch_disable_cpuslocked(&fast_misaligned_access_speed_key);
+}
+
+static void set_unaligned_access_static_branches_except_cpu(int cpu)
+{
+	/*
+	 * Same as set_unaligned_access_static_branches, except excludes the
+	 * given CPU from the result. When a CPU is hotplugged into an offline
+	 * state, this function is called before the CPU is set to offline in
+	 * the cpumask, and thus the CPU needs to be explicitly excluded.
+	 */
+
+	cpumask_t fast_except_me;
+
+	cpumask_and(&fast_except_me, &fast_misaligned_access, cpu_online_mask);
+	cpumask_clear_cpu(cpu, &fast_except_me);
+
+	modify_unaligned_access_branches(&fast_except_me, num_online_cpus() - 1);
+}
+
+static void set_unaligned_access_static_branches(void)
+{
+	/*
+	 * This will be called after check_unaligned_access_all_cpus so the
+	 * result of unaligned access speed for all CPUs will be available.
+	 *
+	 * To avoid the number of online cpus changing between reading
+	 * cpu_online_mask and calling num_online_cpus, cpus_read_lock must be
+	 * held before calling this function.
+	 */
+
+	cpumask_t fast_and_online;
+
+	cpumask_and(&fast_and_online, &fast_misaligned_access, cpu_online_mask);
+
+	modify_unaligned_access_branches(&fast_and_online, num_online_cpus());
+}
+
+static int lock_and_set_unaligned_access_static_branch(void)
+{
+	cpus_read_lock();
+	set_unaligned_access_static_branches();
+	cpus_read_unlock();
+
+	return 0;
+}
+
+arch_initcall_sync(lock_and_set_unaligned_access_static_branch);
+
 static int riscv_online_cpu(unsigned int cpu)
 {
 	static struct page *buf;
 
 	/* We are already set since the last check */
 	if (per_cpu(misaligned_access_speed, cpu) != RISCV_HWPROBE_MISALIGNED_UNKNOWN)
-		return 0;
+		goto exit;
 
 	buf = alloc_pages(GFP_KERNEL, MISALIGNED_BUFFER_ORDER);
 	if (!buf) {
@@ -686,6 +907,17 @@ static int riscv_online_cpu(unsigned int cpu)
 
 	check_unaligned_access(buf);
 	__free_pages(buf, MISALIGNED_BUFFER_ORDER);
+
+exit:
+	set_unaligned_access_static_branches();
+
+	return 0;
+}
+
+static int riscv_offline_cpu(unsigned int cpu)
+{
+	set_unaligned_access_static_branches_except_cpu(cpu);
+
 	return 0;
 }
 
@@ -720,9 +952,12 @@ static int check_unaligned_access_all_cpus(void)
 	/* Check core 0. */
 	smp_call_on_cpu(0, check_unaligned_access, bufs[0], true);
 
-	/* Setup hotplug callback for any new CPUs that come online. */
+	/*
+	 * Setup hotplug callbacks for any new CPUs that come online or go
+	 * offline.
+	 */
 	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "riscv:online",
-				  riscv_online_cpu, NULL);
+				  riscv_online_cpu, riscv_offline_cpu);
 
 out:
 	unaligned_emulation_finish();
diff --git a/arch/riscv/kernel/efi.c b/arch/riscv/kernel/efi.c
index aa6209a74c..b64bf1624a 100644
--- a/arch/riscv/kernel/efi.c
+++ b/arch/riscv/kernel/efi.c
@@ -60,7 +60,7 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data)
 {
 	efi_memory_desc_t *md = data;
-	pte_t pte = READ_ONCE(*ptep);
+	pte_t pte = ptep_get(ptep);
 	unsigned long val;
 
 	if (md->attribute & EFI_MEMORY_RO) {
diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c
index e60fbd8660..5bd1ec3341 100644
--- a/arch/riscv/kernel/elf_kexec.c
+++ b/arch/riscv/kernel/elf_kexec.c
@@ -216,7 +216,6 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 	if (ret)
 		goto out;
 	kernel_start = image->start;
-	pr_notice("The entry point of kernel at 0x%lx\n", image->start);
 
 	/* Add the kernel binary to the image */
 	ret = riscv_kexec_elf_load(image, &ehdr, &elf_info,
@@ -252,8 +251,8 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		image->elf_load_addr = kbuf.mem;
 		image->elf_headers_sz = headers_sz;
 
-		pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
-			 image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
+		kexec_dprintk("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n",
+			      image->elf_load_addr, kbuf.bufsz, kbuf.memsz);
 
 		/* Setup cmdline for kdump kernel case */
 		modified_cmdline = setup_kdump_cmdline(image, cmdline,
@@ -275,6 +274,8 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		pr_err("Error loading purgatory ret=%d\n", ret);
 		goto out;
 	}
+	kexec_dprintk("Loaded purgatory at 0x%lx\n", kbuf.mem);
+
 	ret = kexec_purgatory_get_set_symbol(image, "riscv_kernel_entry",
 					     &kernel_start,
 					     sizeof(kernel_start), 0);
@@ -293,7 +294,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 		if (ret)
 			goto out;
 		initrd_pbase = kbuf.mem;
-		pr_notice("Loaded initrd at 0x%lx\n", initrd_pbase);
+		kexec_dprintk("Loaded initrd at 0x%lx\n", initrd_pbase);
 	}
 
 	/* Add the DTB to the image */
@@ -318,7 +319,7 @@ static void *elf_kexec_load(struct kimage *image, char *kernel_buf,
 	}
 	/* Cache the fdt buffer address for memory cleanup */
 	image->arch.fdt = fdt;
-	pr_notice("Loaded device tree at 0x%lx\n", kbuf.mem);
+	kexec_dprintk("Loaded device tree at 0x%lx\n", kbuf.mem);
 	goto out;
 
 out_free_fdt:
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 54ca4564a9..9d1a305d55 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -83,6 +83,10 @@ SYM_CODE_START(handle_exception)
 	/* Load the kernel shadow call stack pointer if coming from userspace */
 	scs_load_current_if_task_changed s5
 
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_start
+#endif
 	move a0, sp /* pt_regs */
 	la ra, ret_from_exception
 
@@ -138,6 +142,10 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 	 */
 	csrw CSR_SCRATCH, tp
 1:
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	move a0, sp
+	call riscv_v_context_nesting_end
+#endif
 	REG_L a0, PT_STATUS(sp)
 	/*
 	 * The current load reservation is effectively part of the processor's
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 03a6434a8c..f5aa24d9e1 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -178,32 +178,28 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
+		       struct ftrace_ops *op, struct ftrace_regs *fregs)
+{
+	struct pt_regs *regs = arch_ftrace_get_regs(fregs);
+	unsigned long *parent = (unsigned long *)&regs->ra;
+
+	prepare_ftrace_return(parent, ip, frame_pointer(regs));
+}
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 extern void ftrace_graph_call(void);
-extern void ftrace_graph_regs_call(void);
 int ftrace_enable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, true, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, true, true);
 }
 
 int ftrace_disable_ftrace_graph_caller(void)
 {
-	int ret;
-
-	ret = __ftrace_modify_call((unsigned long)&ftrace_graph_call,
-				    (unsigned long)&prepare_ftrace_return, false, true);
-	if (ret)
-		return ret;
-
-	return __ftrace_modify_call((unsigned long)&ftrace_graph_regs_call,
+	return __ftrace_modify_call((unsigned long)&ftrace_graph_call,
 				    (unsigned long)&prepare_ftrace_return, false, true);
 }
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 #endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
index 663881785b..4236a69c35 100644
--- a/arch/riscv/kernel/head.S
+++ b/arch/riscv/kernel/head.S
@@ -11,7 +11,6 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/csr.h>
-#include <asm/cpu_ops_sbi.h>
 #include <asm/hwcap.h>
 #include <asm/image.h>
 #include <asm/scs.h>
@@ -266,10 +265,12 @@ SYM_CODE_START(_start_kernel)
 	la sp, _end + THREAD_SIZE
 	XIP_FIXUP_OFFSET sp
 	mv s0, a0
+	mv s1, a1
 	call __copy_data
 
-	/* Restore a0 copy */
+	/* Restore a0 & a1 copy */
 	mv a0, s0
+	mv a1, s1
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
diff --git a/arch/riscv/kernel/kernel_mode_vector.c b/arch/riscv/kernel/kernel_mode_vector.c
new file mode 100644
index 0000000000..6afe80c7f0
--- /dev/null
+++ b/arch/riscv/kernel/kernel_mode_vector.c
@@ -0,0 +1,247 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ * Author: Catalin Marinas <catalin.marinas@arm.com>
+ * Copyright (C) 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2021 SiFive
+ */
+#include <linux/compiler.h>
+#include <linux/irqflags.h>
+#include <linux/percpu.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+#include <asm/vector.h>
+#include <asm/switch_to.h>
+#include <asm/simd.h>
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+#include <asm/asm-prototypes.h>
+#endif
+
+static inline void riscv_v_flags_set(u32 flags)
+{
+	WRITE_ONCE(current->thread.riscv_v_flags, flags);
+}
+
+static inline void riscv_v_start(u32 flags)
+{
+	int orig;
+
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) != 0);
+	riscv_v_flags_set(orig | flags);
+	barrier();
+}
+
+static inline void riscv_v_stop(u32 flags)
+{
+	int orig;
+
+	barrier();
+	orig = riscv_v_flags();
+	BUG_ON((orig & flags) == 0);
+	riscv_v_flags_set(orig & ~flags);
+}
+
+/*
+ * Claim ownership of the CPU vector context for use by the calling context.
+ *
+ * The caller may freely manipulate the vector context metadata until
+ * put_cpu_vector_context() is called.
+ */
+void get_cpu_vector_context(void)
+{
+	/*
+	 * disable softirqs so it is impossible for softirqs to nest
+	 * get_cpu_vector_context() when kernel is actively using Vector.
+	 */
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_disable();
+	else
+		preempt_disable();
+
+	riscv_v_start(RISCV_KERNEL_MODE_V);
+}
+
+/*
+ * Release the CPU vector context.
+ *
+ * Must be called from a context in which get_cpu_vector_context() was
+ * previously called, with no call to put_cpu_vector_context() in the
+ * meantime.
+ */
+void put_cpu_vector_context(void)
+{
+	riscv_v_stop(RISCV_KERNEL_MODE_V);
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		local_bh_enable();
+	else
+		preempt_enable();
+}
+
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static __always_inline u32 *riscv_v_flags_ptr(void)
+{
+	return &current->thread.riscv_v_flags;
+}
+
+static inline void riscv_preempt_v_set_dirty(void)
+{
+	*riscv_v_flags_ptr() |= RISCV_PREEMPT_V_DIRTY;
+}
+
+static inline void riscv_preempt_v_reset_flags(void)
+{
+	*riscv_v_flags_ptr() &= ~(RISCV_PREEMPT_V_DIRTY | RISCV_PREEMPT_V_NEED_RESTORE);
+}
+
+static inline void riscv_v_ctx_depth_inc(void)
+{
+	*riscv_v_flags_ptr() += RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline void riscv_v_ctx_depth_dec(void)
+{
+	*riscv_v_flags_ptr() -= RISCV_V_CTX_UNIT_DEPTH;
+}
+
+static inline u32 riscv_v_ctx_get_depth(void)
+{
+	return *riscv_v_flags_ptr() & RISCV_V_CTX_DEPTH_MASK;
+}
+
+static int riscv_v_stop_kernel_context(void)
+{
+	if (riscv_v_ctx_get_depth() != 0 || !riscv_preempt_v_started(current))
+		return 1;
+
+	riscv_preempt_v_clear_dirty(current);
+	riscv_v_stop(RISCV_PREEMPT_V);
+	return 0;
+}
+
+static int riscv_v_start_kernel_context(bool *is_nested)
+{
+	struct __riscv_v_ext_state *kvstate, *uvstate;
+
+	kvstate = &current->thread.kernel_vstate;
+	if (!kvstate->datap)
+		return -ENOENT;
+
+	if (riscv_preempt_v_started(current)) {
+		WARN_ON(riscv_v_ctx_get_depth() == 0);
+		*is_nested = true;
+		get_cpu_vector_context();
+		if (riscv_preempt_v_dirty(current)) {
+			__riscv_v_vstate_save(kvstate, kvstate->datap);
+			riscv_preempt_v_clear_dirty(current);
+		}
+		riscv_preempt_v_set_restore(current);
+		return 0;
+	}
+
+	/* Transfer the ownership of V from user to kernel, then save */
+	riscv_v_start(RISCV_PREEMPT_V | RISCV_PREEMPT_V_DIRTY);
+	if ((task_pt_regs(current)->status & SR_VS) == SR_VS_DIRTY) {
+		uvstate = &current->thread.vstate;
+		__riscv_v_vstate_save(uvstate, uvstate->datap);
+	}
+	riscv_preempt_v_clear_dirty(current);
+	return 0;
+}
+
+/* low-level V context handling code, called with irq disabled */
+asmlinkage void riscv_v_context_nesting_start(struct pt_regs *regs)
+{
+	int depth;
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0 && (regs->status & SR_VS) == SR_VS_DIRTY)
+		riscv_preempt_v_set_dirty();
+
+	riscv_v_ctx_depth_inc();
+}
+
+asmlinkage void riscv_v_context_nesting_end(struct pt_regs *regs)
+{
+	struct __riscv_v_ext_state *vstate = &current->thread.kernel_vstate;
+	u32 depth;
+
+	WARN_ON(!irqs_disabled());
+
+	if (!riscv_preempt_v_started(current))
+		return;
+
+	riscv_v_ctx_depth_dec();
+	depth = riscv_v_ctx_get_depth();
+	if (depth == 0) {
+		if (riscv_preempt_v_restore(current)) {
+			__riscv_v_vstate_restore(vstate, vstate->datap);
+			__riscv_v_vstate_clean(regs);
+			riscv_preempt_v_reset_flags();
+		}
+	}
+}
+#else
+#define riscv_v_start_kernel_context(nested)	(-ENOENT)
+#define riscv_v_stop_kernel_context()		(-ENOENT)
+#endif /* CONFIG_RISCV_ISA_V_PREEMPTIVE */
+
+/*
+ * kernel_vector_begin(): obtain the CPU vector registers for use by the calling
+ * context
+ *
+ * Must not be called unless may_use_simd() returns true.
+ * Task context in the vector registers is saved back to memory as necessary.
+ *
+ * A matching call to kernel_vector_end() must be made before returning from the
+ * calling context.
+ *
+ * The caller may freely use the vector registers until kernel_vector_end() is
+ * called.
+ */
+void kernel_vector_begin(void)
+{
+	bool nested = false;
+
+	if (WARN_ON(!has_vector()))
+		return;
+
+	BUG_ON(!may_use_simd());
+
+	if (riscv_v_start_kernel_context(&nested)) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+	}
+
+	if (!nested)
+		riscv_v_vstate_set_restore(current, task_pt_regs(current));
+
+	riscv_v_enable();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_begin);
+
+/*
+ * kernel_vector_end(): give the CPU vector registers back to the current task
+ *
+ * Must be called from a context in which kernel_vector_begin() was previously
+ * called, with no call to kernel_vector_end() in the meantime.
+ *
+ * The caller must not use the vector registers after this function is called,
+ * unless kernel_vector_begin() is called again in the meantime.
+ */
+void kernel_vector_end(void)
+{
+	if (WARN_ON(!has_vector()))
+		return;
+
+	riscv_v_disable();
+
+	if (riscv_v_stop_kernel_context())
+		put_cpu_vector_context();
+}
+EXPORT_SYMBOL_GPL(kernel_vector_end);
diff --git a/arch/riscv/kernel/machine_kexec.c b/arch/riscv/kernel/machine_kexec.c
index 2d139b724b..ed9cad20c0 100644
--- a/arch/riscv/kernel/machine_kexec.c
+++ b/arch/riscv/kernel/machine_kexec.c
@@ -19,30 +19,6 @@
 #include <linux/irq.h>
 
 /*
- * kexec_image_info - Print received image details
- */
-static void
-kexec_image_info(const struct kimage *image)
-{
-	unsigned long i;
-
-	pr_debug("Kexec image info:\n");
-	pr_debug("\ttype:        %d\n", image->type);
-	pr_debug("\tstart:       %lx\n", image->start);
-	pr_debug("\thead:        %lx\n", image->head);
-	pr_debug("\tnr_segments: %lu\n", image->nr_segments);
-
-	for (i = 0; i < image->nr_segments; i++) {
-		pr_debug("\t    segment[%lu]: %016lx - %016lx", i,
-			image->segment[i].mem,
-			image->segment[i].mem + image->segment[i].memsz);
-		pr_debug("\t\t0x%lx bytes, %lu pages\n",
-			(unsigned long) image->segment[i].memsz,
-			(unsigned long) image->segment[i].memsz /  PAGE_SIZE);
-	}
-}
-
-/*
  * machine_kexec_prepare - Initialize kexec
  *
  * This function is called from do_kexec_load, when the user has
@@ -60,8 +36,6 @@ machine_kexec_prepare(struct kimage *image)
 	unsigned int control_code_buffer_sz = 0;
 	int i = 0;
 
-	kexec_image_info(image);
-
 	/* Find the Flattened Device Tree and save its physical address */
 	for (i = 0; i < image->nr_segments; i++) {
 		if (image->segment[i].memsz <= sizeof(fdt))
diff --git a/arch/riscv/kernel/mcount-dyn.S b/arch/riscv/kernel/mcount-dyn.S
index 58dd96a2a1..b7561288e8 100644
--- a/arch/riscv/kernel/mcount-dyn.S
+++ b/arch/riscv/kernel/mcount-dyn.S
@@ -3,12 +3,12 @@
 
 #include <linux/init.h>
 #include <linux/linkage.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text
@@ -57,31 +57,150 @@
 	.endm
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
-	.macro SAVE_ALL
+
+/**
+* SAVE_ABI_REGS - save regs against the pt_regs struct
+*
+* @all: tell if saving all the regs
+*
+* If all is set, all the regs will be saved, otherwise only ABI
+* related regs (a0-a7,epc,ra and optional s0) will be saved.
+*
+* After the stack is established,
+*
+* 0(sp) stores the PC of the traced function which can be accessed
+* by &(fregs)->regs->epc in tracing function. Note that the real
+* function entry address should be computed with -FENTRY_RA_OFFSET.
+*
+* 8(sp) stores the function return address (i.e. parent IP) that
+* can be accessed by &(fregs)->regs->ra in tracing function.
+*
+* The other regs are saved at the respective localtion and accessed
+* by the respective pt_regs member.
+*
+* Here is the layout of stack for your reference.
+*
+* PT_SIZE_ON_STACK  ->  +++++++++
+*                       + ..... +
+*                       + t3-t6 +
+*                       + s2-s11+
+*                       + a0-a7 + --++++-> ftrace_caller saved
+*                       + s1    +   +
+*                       + s0    + --+
+*                       + t0-t2 +   +
+*                       + tp    +   +
+*                       + gp    +   +
+*                       + sp    +   +
+*                       + ra    + --+ // parent IP
+*               sp  ->  + epc   + --+ // PC
+*                       +++++++++
+**/
+	.macro SAVE_ABI_REGS, all=0
 	addi	sp, sp, -PT_SIZE_ON_STACK
 
-	REG_S t0,  PT_EPC(sp)
-	REG_S x1,  PT_RA(sp)
-	REG_S x2,  PT_SP(sp)
-	REG_S x3,  PT_GP(sp)
-	REG_S x4,  PT_TP(sp)
-	REG_S x5,  PT_T0(sp)
-	save_from_x6_to_x31
+	REG_S	t0,  PT_EPC(sp)
+	REG_S	x1,  PT_RA(sp)
+
+	// save the ABI regs
+
+	REG_S	x10, PT_A0(sp)
+	REG_S	x11, PT_A1(sp)
+	REG_S	x12, PT_A2(sp)
+	REG_S	x13, PT_A3(sp)
+	REG_S	x14, PT_A4(sp)
+	REG_S	x15, PT_A5(sp)
+	REG_S	x16, PT_A6(sp)
+	REG_S	x17, PT_A7(sp)
+
+	// save the leftover regs
+
+	.if \all == 1
+	REG_S	x2, PT_SP(sp)
+	REG_S	x3, PT_GP(sp)
+	REG_S	x4, PT_TP(sp)
+	REG_S	x5, PT_T0(sp)
+	REG_S	x6, PT_T1(sp)
+	REG_S	x7, PT_T2(sp)
+	REG_S	x8, PT_S0(sp)
+	REG_S	x9, PT_S1(sp)
+	REG_S	x18, PT_S2(sp)
+	REG_S	x19, PT_S3(sp)
+	REG_S	x20, PT_S4(sp)
+	REG_S	x21, PT_S5(sp)
+	REG_S	x22, PT_S6(sp)
+	REG_S	x23, PT_S7(sp)
+	REG_S	x24, PT_S8(sp)
+	REG_S	x25, PT_S9(sp)
+	REG_S	x26, PT_S10(sp)
+	REG_S	x27, PT_S11(sp)
+	REG_S	x28, PT_T3(sp)
+	REG_S	x29, PT_T4(sp)
+	REG_S	x30, PT_T5(sp)
+	REG_S	x31, PT_T6(sp)
+
+	// save s0 if FP_TEST defined
+
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_S	x8, PT_S0(sp)
+#endif
+	.endif
 	.endm
 
-	.macro RESTORE_ALL
-	REG_L x1,  PT_RA(sp)
-	REG_L x2,  PT_SP(sp)
-	REG_L x3,  PT_GP(sp)
-	REG_L x4,  PT_TP(sp)
-	/* Restore t0 with PT_EPC */
-	REG_L x5,  PT_EPC(sp)
-	restore_from_x6_to_x31
+	.macro RESTORE_ABI_REGS, all=0
+	REG_L	t0, PT_EPC(sp)
+	REG_L	x1, PT_RA(sp)
+	REG_L	x10, PT_A0(sp)
+	REG_L	x11, PT_A1(sp)
+	REG_L	x12, PT_A2(sp)
+	REG_L	x13, PT_A3(sp)
+	REG_L	x14, PT_A4(sp)
+	REG_L	x15, PT_A5(sp)
+	REG_L	x16, PT_A6(sp)
+	REG_L	x17, PT_A7(sp)
 
+	.if \all == 1
+	REG_L	x2, PT_SP(sp)
+	REG_L	x3, PT_GP(sp)
+	REG_L	x4, PT_TP(sp)
+	REG_L	x6, PT_T1(sp)
+	REG_L	x7, PT_T2(sp)
+	REG_L	x8, PT_S0(sp)
+	REG_L	x9, PT_S1(sp)
+	REG_L	x18, PT_S2(sp)
+	REG_L	x19, PT_S3(sp)
+	REG_L	x20, PT_S4(sp)
+	REG_L	x21, PT_S5(sp)
+	REG_L	x22, PT_S6(sp)
+	REG_L	x23, PT_S7(sp)
+	REG_L	x24, PT_S8(sp)
+	REG_L	x25, PT_S9(sp)
+	REG_L	x26, PT_S10(sp)
+	REG_L	x27, PT_S11(sp)
+	REG_L	x28, PT_T3(sp)
+	REG_L	x29, PT_T4(sp)
+	REG_L	x30, PT_T5(sp)
+	REG_L	x31, PT_T6(sp)
+
+	.else
+#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
+	REG_L	x8, PT_S0(sp)
+#endif
+	.endif
 	addi	sp, sp, PT_SIZE_ON_STACK
 	.endm
+
+	.macro PREPARE_ARGS
+	addi	a0, t0, -FENTRY_RA_OFFSET
+	la	a1, function_trace_op
+	REG_L	a2, 0(a1)
+	mv	a1, ra
+	mv	a3, sp
+	.endm
+
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
+#ifndef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 SYM_FUNC_START(ftrace_caller)
 	SAVE_ABI
 
@@ -105,34 +224,39 @@ SYM_INNER_LABEL(ftrace_graph_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 #endif
 	RESTORE_ABI
-	jr t0
+	jr	t0
 SYM_FUNC_END(ftrace_caller)
 
-#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
+#else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 SYM_FUNC_START(ftrace_regs_caller)
-	SAVE_ALL
-
-	addi	a0, t0, -FENTRY_RA_OFFSET
-	la	a1, function_trace_op
-	REG_L	a2, 0(a1)
-	mv	a1, ra
-	mv	a3, sp
+	mv	t1, zero
+	SAVE_ABI_REGS 1
+	PREPARE_ARGS
 
 SYM_INNER_LABEL(ftrace_regs_call, SYM_L_GLOBAL)
 	call	ftrace_stub
 
-#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	addi	a0, sp, PT_RA
-	REG_L	a1, PT_EPC(sp)
-	addi	a1, a1, -FENTRY_RA_OFFSET
-#ifdef HAVE_FUNCTION_GRAPH_FP_TEST
-	mv	a2, s0
-#endif
-SYM_INNER_LABEL(ftrace_graph_regs_call, SYM_L_GLOBAL)
+	RESTORE_ABI_REGS 1
+	bnez	t1, .Ldirect
+	jr	t0
+.Ldirect:
+	jr	t1
+SYM_FUNC_END(ftrace_regs_caller)
+
+SYM_FUNC_START(ftrace_caller)
+	SAVE_ABI_REGS 0
+	PREPARE_ARGS
+
+SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	call	ftrace_stub
-#endif
 
-	RESTORE_ALL
-	jr t0
-SYM_FUNC_END(ftrace_regs_caller)
+	RESTORE_ABI_REGS 0
+	jr	t0
+SYM_FUNC_END(ftrace_caller)
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
+
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+SYM_CODE_START(ftrace_stub_direct_tramp)
+	jr	t0
+SYM_CODE_END(ftrace_stub_direct_tramp)
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
diff --git a/arch/riscv/kernel/mcount.S b/arch/riscv/kernel/mcount.S
index b4dd9ed684..d7ec69ac69 100644
--- a/arch/riscv/kernel/mcount.S
+++ b/arch/riscv/kernel/mcount.S
@@ -4,12 +4,12 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 #include <linux/cfi_types.h>
+#include <linux/export.h>
 #include <asm/asm.h>
 #include <asm/csr.h>
 #include <asm/unistd.h>
 #include <asm/thread_info.h>
 #include <asm/asm-offsets.h>
-#include <asm-generic/export.h>
 #include <asm/ftrace.h>
 
 	.text
diff --git a/arch/riscv/kernel/module.c b/arch/riscv/kernel/module.c
index c9d59a5448..5e5a826444 100644
--- a/arch/riscv/kernel/module.c
+++ b/arch/riscv/kernel/module.c
@@ -783,6 +783,7 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 	Elf_Sym *sym;
 	void *location;
 	unsigned int i, type;
+	unsigned int j_idx = 0;
 	Elf_Addr v;
 	int res;
 	unsigned int num_relocations = sechdrs[relsec].sh_size / sizeof(*rel);
@@ -833,9 +834,10 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 		v = sym->st_value + rel[i].r_addend;
 
 		if (type == R_RISCV_PCREL_LO12_I || type == R_RISCV_PCREL_LO12_S) {
-			unsigned int j;
+			unsigned int j = j_idx;
+			bool found = false;
 
-			for (j = 0; j < sechdrs[relsec].sh_size / sizeof(*rel); j++) {
+			do {
 				unsigned long hi20_loc =
 					sechdrs[sechdrs[relsec].sh_info].sh_addr
 					+ rel[j].r_offset;
@@ -864,16 +866,26 @@ int apply_relocate_add(Elf_Shdr *sechdrs, const char *strtab,
 					hi20 = (offset + 0x800) & 0xfffff000;
 					lo12 = offset - hi20;
 					v = lo12;
+					found = true;
 
 					break;
 				}
-			}
-			if (j == sechdrs[relsec].sh_size / sizeof(*rel)) {
+
+				j++;
+				if (j > sechdrs[relsec].sh_size / sizeof(*rel))
+					j = 0;
+
+			} while (j_idx != j);
+
+			if (!found) {
 				pr_err(
 				  "%s: Can not find HI20 relocation information\n",
 				  me->name);
 				return -EINVAL;
 			}
+
+			/* Record the previous j-loop end index */
+			j_idx = j;
 		}
 
 		if (reloc_handlers[type].accumulate_handler)
diff --git a/arch/riscv/kernel/paravirt.c b/arch/riscv/kernel/paravirt.c
new file mode 100644
index 0000000000..0d6225fd31
--- /dev/null
+++ b/arch/riscv/kernel/paravirt.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023 Ventana Micro Systems Inc.
+ */
+
+#define pr_fmt(fmt) "riscv-pv: " fmt
+
+#include <linux/cpuhotplug.h>
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/jump_label.h>
+#include <linux/kconfig.h>
+#include <linux/kernel.h>
+#include <linux/percpu-defs.h>
+#include <linux/printk.h>
+#include <linux/static_call.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+#include <asm/page.h>
+#include <asm/paravirt.h>
+#include <asm/sbi.h>
+
+struct static_key paravirt_steal_enabled;
+struct static_key paravirt_steal_rq_enabled;
+
+static u64 native_steal_clock(int cpu)
+{
+	return 0;
+}
+
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+
+static bool steal_acc = true;
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+
+early_param("no-steal-acc", parse_no_stealacc);
+
+static DEFINE_PER_CPU(struct sbi_sta_struct, steal_time) __aligned(64);
+
+static bool __init has_pv_steal_clock(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_STA) > 0) {
+		pr_info("SBI STA extension detected\n");
+		return true;
+	}
+
+	return false;
+}
+
+static int sbi_sta_steal_time_set_shmem(unsigned long lo, unsigned long hi,
+					unsigned long flags)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_STA, SBI_EXT_STA_STEAL_TIME_SET_SHMEM,
+			lo, hi, flags, 0, 0, 0);
+	if (ret.error) {
+		if (lo == SBI_STA_SHMEM_DISABLE && hi == SBI_STA_SHMEM_DISABLE)
+			pr_warn("Failed to disable steal-time shmem");
+		else
+			pr_warn("Failed to set steal-time shmem");
+		return sbi_err_map_linux_errno(ret.error);
+	}
+
+	return 0;
+}
+
+static int pv_time_cpu_online(unsigned int cpu)
+{
+	struct sbi_sta_struct *st = this_cpu_ptr(&steal_time);
+	phys_addr_t pa = __pa(st);
+	unsigned long lo = (unsigned long)pa;
+	unsigned long hi = IS_ENABLED(CONFIG_32BIT) ? upper_32_bits((u64)pa) : 0;
+
+	return sbi_sta_steal_time_set_shmem(lo, hi, 0);
+}
+
+static int pv_time_cpu_down_prepare(unsigned int cpu)
+{
+	return sbi_sta_steal_time_set_shmem(SBI_STA_SHMEM_DISABLE,
+					    SBI_STA_SHMEM_DISABLE, 0);
+}
+
+static u64 pv_time_steal_clock(int cpu)
+{
+	struct sbi_sta_struct *st = per_cpu_ptr(&steal_time, cpu);
+	__le32 sequence;
+	__le64 steal;
+
+	/*
+	 * Check the sequence field before and after reading the steal
+	 * field. Repeat the read if it is different or odd.
+	 */
+	do {
+		sequence = READ_ONCE(st->sequence);
+		virt_rmb();
+		steal = READ_ONCE(st->steal);
+		virt_rmb();
+	} while ((le32_to_cpu(sequence) & 1) ||
+		 sequence != READ_ONCE(st->sequence));
+
+	return le64_to_cpu(steal);
+}
+
+int __init pv_time_init(void)
+{
+	int ret;
+
+	if (!has_pv_steal_clock())
+		return 0;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
+				"riscv/pv_time:online",
+				pv_time_cpu_online,
+				pv_time_cpu_down_prepare);
+	if (ret < 0)
+		return ret;
+
+	static_call_update(pv_steal_clock, pv_time_steal_clock);
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+	if (steal_acc)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+
+	pr_info("Computing paravirt steal-time\n");
+
+	return 0;
+}
diff --git a/arch/riscv/kernel/patch.c b/arch/riscv/kernel/patch.c
index 37e87fdcf6..30e12b310c 100644
--- a/arch/riscv/kernel/patch.c
+++ b/arch/riscv/kernel/patch.c
@@ -80,6 +80,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
 	 */
 	lockdep_assert_held(&text_mutex);
 
+	preempt_disable();
+
 	if (across_pages)
 		patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
 
@@ -92,6 +94,8 @@ static int __patch_insn_set(void *addr, u8 c, size_t len)
 	if (across_pages)
 		patch_unmap(FIX_TEXT_POKE1);
 
+	preempt_enable();
+
 	return 0;
 }
 NOKPROBE_SYMBOL(__patch_insn_set);
@@ -122,6 +126,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
 	if (!riscv_patch_in_stop_machine)
 		lockdep_assert_held(&text_mutex);
 
+	preempt_disable();
+
 	if (across_pages)
 		patch_map(addr + PAGE_SIZE, FIX_TEXT_POKE1);
 
@@ -134,6 +140,8 @@ static int __patch_insn_write(void *addr, const void *insn, size_t len)
 	if (across_pages)
 		patch_unmap(FIX_TEXT_POKE1);
 
+	preempt_enable();
+
 	return ret;
 }
 NOKPROBE_SYMBOL(__patch_insn_write);
diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 4f21d970a1..e4bc61c4e5 100644
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -27,8 +27,6 @@
 #include <asm/vector.h>
 #include <asm/cpufeature.h>
 
-register unsigned long gp_in_global __asm__("gp");
-
 #if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
 #include <linux/stackprotector.h>
 unsigned long __stack_chk_guard __read_mostly;
@@ -37,7 +35,7 @@ EXPORT_SYMBOL(__stack_chk_guard);
 
 extern asmlinkage void ret_from_fork(void);
 
-void arch_cpu_idle(void)
+void noinstr arch_cpu_idle(void)
 {
 	cpu_do_idle();
 }
@@ -171,6 +169,7 @@ void flush_thread(void)
 	riscv_v_vstate_off(task_pt_regs(current));
 	kfree(current->thread.vstate.datap);
 	memset(&current->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(current, TIF_RISCV_V_DEFER_RESTORE);
 #endif
 }
 
@@ -178,7 +177,7 @@ void arch_release_task_struct(struct task_struct *tsk)
 {
 	/* Free the vector context of datap. */
 	if (has_vector())
-		kfree(tsk->thread.vstate.datap);
+		riscv_v_thread_free(tsk);
 }
 
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
@@ -187,6 +186,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	*dst = *src;
 	/* clear entire V context, including datap for a new task */
 	memset(&dst->thread.vstate, 0, sizeof(struct __riscv_v_ext_state));
+	memset(&dst->thread.kernel_vstate, 0, sizeof(struct __riscv_v_ext_state));
+	clear_tsk_thread_flag(dst, TIF_RISCV_V_DEFER_RESTORE);
 
 	return 0;
 }
@@ -204,7 +205,6 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 	if (unlikely(args->fn)) {
 		/* Kernel thread */
 		memset(childregs, 0, sizeof(struct pt_regs));
-		childregs->gp = gp_in_global;
 		/* Supervisor/Machine, irqs on: */
 		childregs->status = SR_PP | SR_PIE;
 
@@ -221,7 +221,15 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 		childregs->a0 = 0; /* Return value of fork() */
 		p->thread.s[0] = 0;
 	}
+	p->thread.riscv_v_flags = 0;
+	if (has_vector())
+		riscv_v_thread_alloc(p);
 	p->thread.ra = (unsigned long)ret_from_fork;
 	p->thread.sp = (unsigned long)childregs; /* kernel sp */
 	return 0;
 }
+
+void __init arch_task_cache_init(void)
+{
+	riscv_v_setup_ctx_cache();
+}
diff --git a/arch/riscv/kernel/ptrace.c b/arch/riscv/kernel/ptrace.c
index 2afe460de1..e8515aa9d8 100644
--- a/arch/riscv/kernel/ptrace.c
+++ b/arch/riscv/kernel/ptrace.c
@@ -99,8 +99,11 @@ static int riscv_vr_get(struct task_struct *target,
 	 * Ensure the vector registers have been saved to the memory before
 	 * copying them to membuf.
 	 */
-	if (target == current)
-		riscv_v_vstate_save(current, task_pt_regs(current));
+	if (target == current) {
+		get_cpu_vector_context();
+		riscv_v_vstate_save(&current->thread.vstate, task_pt_regs(current));
+		put_cpu_vector_context();
+	}
 
 	ptrace_vstate.vstart = vstate->vstart;
 	ptrace_vstate.vl = vstate->vl;
diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
index 5a62ed1da4..e66e0999a8 100644
--- a/arch/riscv/kernel/sbi.c
+++ b/arch/riscv/kernel/sbi.c
@@ -7,6 +7,7 @@
 
 #include <linux/bits.h>
 #include <linux/init.h>
+#include <linux/mm.h>
 #include <linux/pm.h>
 #include <linux/reboot.h>
 #include <asm/sbi.h>
@@ -571,6 +572,66 @@ long sbi_get_mimpid(void)
 }
 EXPORT_SYMBOL_GPL(sbi_get_mimpid);
 
+bool sbi_debug_console_available;
+
+int sbi_debug_console_write(const char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_WRITE,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
+int sbi_debug_console_read(char *bytes, unsigned int num_bytes)
+{
+	phys_addr_t base_addr;
+	struct sbiret ret;
+
+	if (!sbi_debug_console_available)
+		return -EOPNOTSUPP;
+
+	if (is_vmalloc_addr(bytes))
+		base_addr = page_to_phys(vmalloc_to_page(bytes)) +
+			    offset_in_page(bytes);
+	else
+		base_addr = __pa(bytes);
+	if (PAGE_SIZE < (offset_in_page(bytes) + num_bytes))
+		num_bytes = PAGE_SIZE - offset_in_page(bytes);
+
+	if (IS_ENABLED(CONFIG_32BIT))
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, lower_32_bits(base_addr),
+				upper_32_bits(base_addr), 0, 0, 0);
+	else
+		ret = sbi_ecall(SBI_EXT_DBCN, SBI_EXT_DBCN_CONSOLE_READ,
+				num_bytes, base_addr, 0, 0, 0, 0);
+
+	if (ret.error == SBI_ERR_FAILURE)
+		return -EIO;
+	return ret.error ? sbi_err_map_linux_errno(ret.error) : ret.value;
+}
+
 void __init sbi_init(void)
 {
 	int ret;
@@ -612,6 +673,11 @@ void __init sbi_init(void)
 			sbi_srst_reboot_nb.priority = 192;
 			register_restart_handler(&sbi_srst_reboot_nb);
 		}
+		if ((sbi_spec_version >= sbi_mk_version(2, 0)) &&
+		    (sbi_probe_extension(SBI_EXT_DBCN) > 0)) {
+			pr_info("SBI DBCN extension detected\n");
+			sbi_debug_console_available = true;
+		}
 	} else {
 		__sbi_set_timer = __sbi_set_timer_v01;
 		__sbi_send_ipi	= __sbi_send_ipi_v01;
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 535a837de5..4f73c0ae44 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -26,7 +26,6 @@
 #include <asm/alternative.h>
 #include <asm/cacheflush.h>
 #include <asm/cpufeature.h>
-#include <asm/cpu_ops.h>
 #include <asm/early_ioremap.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
@@ -51,7 +50,6 @@ atomic_t hart_lottery __section(".sdata")
 #endif
 ;
 unsigned long boot_cpu_hartid;
-static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 /*
  * Place kernel memory regions on the resource tree so that
@@ -299,23 +297,10 @@ void __init setup_arch(char **cmdline_p)
 	riscv_user_isa_enable();
 }
 
-static int __init topology_init(void)
+bool arch_cpu_is_hotpluggable(int cpu)
 {
-	int i, ret;
-
-	for_each_possible_cpu(i) {
-		struct cpu *cpu = &per_cpu(cpu_devices, i);
-
-		cpu->hotpluggable = cpu_has_hotplug(i);
-		ret = register_cpu(cpu, i);
-		if (unlikely(ret))
-			pr_warn("Warning: %s: register_cpu %d failed (%d)\n",
-			       __func__, i, ret);
-	}
-
-	return 0;
+	return cpu_has_hotplug(cpu);
 }
-subsys_initcall(topology_init);
 
 void free_initmem(void)
 {
diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 88b6220b26..5a2edd7f02 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -86,12 +86,15 @@ static long save_v_state(struct pt_regs *regs, void __user **sc_vec)
 	/* datap is designed to be 16 byte aligned for better performance */
 	WARN_ON(unlikely(!IS_ALIGNED((unsigned long)datap, 16)));
 
-	riscv_v_vstate_save(current, regs);
+	get_cpu_vector_context();
+	riscv_v_vstate_save(&current->thread.vstate, regs);
+	put_cpu_vector_context();
+
 	/* Copy everything of vstate but datap. */
 	err = __copy_to_user(&state->v_state, &current->thread.vstate,
 			     offsetof(struct __riscv_v_ext_state, datap));
 	/* Copy the pointer datap itself. */
-	err |= __put_user(datap, &state->v_state.datap);
+	err |= __put_user((__force void *)datap, &state->v_state.datap);
 	/* Copy the whole vector content to user space datap. */
 	err |= __copy_to_user(datap, current->thread.vstate.datap, riscv_v_vsize);
 	/* Copy magic to the user space after saving  all vector conetext */
@@ -116,6 +119,13 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	struct __sc_riscv_v_state __user *state = sc_vec;
 	void __user *datap;
 
+	/*
+	 * Mark the vstate as clean prior performing the actual copy,
+	 * to avoid getting the vstate incorrectly clobbered by the
+	 *  discarded vector state.
+	 */
+	riscv_v_vstate_set_restore(current, regs);
+
 	/* Copy everything of __sc_riscv_v_state except datap. */
 	err = __copy_from_user(&current->thread.vstate, &state->v_state,
 			       offsetof(struct __riscv_v_ext_state, datap));
@@ -130,13 +140,7 @@ static long __restore_v_state(struct pt_regs *regs, void __user *sc_vec)
 	 * Copy the whole vector content from user space datap. Use
 	 * copy_from_user to prevent information leak.
 	 */
-	err = copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
-	if (unlikely(err))
-		return err;
-
-	riscv_v_vstate_restore(current, regs);
-
-	return err;
+	return copy_from_user(current->thread.vstate.datap, datap, riscv_v_vsize);
 }
 #else
 #define save_v_state(task, regs) (0)
diff --git a/arch/riscv/kernel/smp.c b/arch/riscv/kernel/smp.c
index 40420afbb1..45dd403541 100644
--- a/arch/riscv/kernel/smp.c
+++ b/arch/riscv/kernel/smp.c
@@ -81,7 +81,7 @@ static inline void ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
 
 #ifdef CONFIG_HOTPLUG_CPU
 	if (cpu_has_hotplug(cpu))
-		cpu_ops[cpu]->cpu_stop();
+		cpu_ops->cpu_stop();
 #endif
 
 	for(;;)
diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
index d162bf339b..519b6bd946 100644
--- a/arch/riscv/kernel/smpboot.c
+++ b/arch/riscv/kernel/smpboot.c
@@ -49,7 +49,6 @@ void __init smp_prepare_boot_cpu(void)
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
 	int cpuid;
-	int ret;
 	unsigned int curr_cpuid;
 
 	init_cpu_topology();
@@ -66,11 +65,6 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	for_each_possible_cpu(cpuid) {
 		if (cpuid == curr_cpuid)
 			continue;
-		if (cpu_ops[cpuid]->cpu_prepare) {
-			ret = cpu_ops[cpuid]->cpu_prepare(cpuid);
-			if (ret)
-				continue;
-		}
 		set_cpu_present(cpuid, true);
 		numa_store_cpu_info(cpuid);
 	}
@@ -125,18 +119,7 @@ static int __init acpi_parse_rintc(union acpi_subtable_headers *header, const un
 
 static void __init acpi_parse_and_init_cpus(void)
 {
-	int cpuid;
-
-	cpu_set_ops(0);
-
 	acpi_table_parse_madt(ACPI_MADT_TYPE_RINTC, acpi_parse_rintc, 0);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 #else
 #define acpi_parse_and_init_cpus(...)	do { } while (0)
@@ -150,8 +133,6 @@ static void __init of_parse_and_init_cpus(void)
 	int cpuid = 1;
 	int rc;
 
-	cpu_set_ops(0);
-
 	for_each_of_cpu_node(dn) {
 		rc = riscv_early_of_processor_hartid(dn, &hart);
 		if (rc < 0)
@@ -179,27 +160,28 @@ static void __init of_parse_and_init_cpus(void)
 	if (cpuid > nr_cpu_ids)
 		pr_warn("Total number of cpus [%d] is greater than nr_cpus option value [%d]\n",
 			cpuid, nr_cpu_ids);
-
-	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++) {
-		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID) {
-			cpu_set_ops(cpuid);
-			set_cpu_possible(cpuid, true);
-		}
-	}
 }
 
 void __init setup_smp(void)
 {
+	int cpuid;
+
+	cpu_set_ops();
+
 	if (acpi_disabled)
 		of_parse_and_init_cpus();
 	else
 		acpi_parse_and_init_cpus();
+
+	for (cpuid = 1; cpuid < nr_cpu_ids; cpuid++)
+		if (cpuid_to_hartid_map(cpuid) != INVALID_HARTID)
+			set_cpu_possible(cpuid, true);
 }
 
 static int start_secondary_cpu(int cpu, struct task_struct *tidle)
 {
-	if (cpu_ops[cpu]->cpu_start)
-		return cpu_ops[cpu]->cpu_start(cpu, tidle);
+	if (cpu_ops->cpu_start)
+		return cpu_ops->cpu_start(cpu, tidle);
 
 	return -EOPNOTSUPP;
 }
diff --git a/arch/riscv/kernel/suspend.c b/arch/riscv/kernel/suspend.c
index 3c89b8ec69..299795341e 100644
--- a/arch/riscv/kernel/suspend.c
+++ b/arch/riscv/kernel/suspend.c
@@ -4,13 +4,19 @@
  * Copyright (c) 2022 Ventana Micro Systems Inc.
  */
 
+#define pr_fmt(fmt) "suspend: " fmt
+
 #include <linux/ftrace.h>
+#include <linux/suspend.h>
 #include <asm/csr.h>
+#include <asm/sbi.h>
 #include <asm/suspend.h>
 
 void suspend_save_csrs(struct suspend_context *context)
 {
 	context->scratch = csr_read(CSR_SCRATCH);
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+		context->envcfg = csr_read(CSR_ENVCFG);
 	context->tvec = csr_read(CSR_TVEC);
 	context->ie = csr_read(CSR_IE);
 
@@ -32,6 +38,8 @@ void suspend_save_csrs(struct suspend_context *context)
 void suspend_restore_csrs(struct suspend_context *context)
 {
 	csr_write(CSR_SCRATCH, context->scratch);
+	if (riscv_cpu_has_extension_unlikely(smp_processor_id(), RISCV_ISA_EXT_XLINUXENVCFG))
+		csr_write(CSR_ENVCFG, context->envcfg);
 	csr_write(CSR_TVEC, context->tvec);
 	csr_write(CSR_IE, context->ie);
 
@@ -85,3 +93,43 @@ int cpu_suspend(unsigned long arg,
 
 	return rc;
 }
+
+#ifdef CONFIG_RISCV_SBI
+static int sbi_system_suspend(unsigned long sleep_type,
+			      unsigned long resume_addr,
+			      unsigned long opaque)
+{
+	struct sbiret ret;
+
+	ret = sbi_ecall(SBI_EXT_SUSP, SBI_EXT_SUSP_SYSTEM_SUSPEND,
+			sleep_type, resume_addr, opaque, 0, 0, 0);
+	if (ret.error)
+		return sbi_err_map_linux_errno(ret.error);
+
+	return ret.value;
+}
+
+static int sbi_system_suspend_enter(suspend_state_t state)
+{
+	return cpu_suspend(SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM, sbi_system_suspend);
+}
+
+static const struct platform_suspend_ops sbi_system_suspend_ops = {
+	.valid = suspend_valid_only_mem,
+	.enter = sbi_system_suspend_enter,
+};
+
+static int __init sbi_system_suspend_init(void)
+{
+	if (sbi_spec_version >= sbi_mk_version(2, 0) &&
+	    sbi_probe_extension(SBI_EXT_SUSP) > 0) {
+		pr_info("SBI SUSP extension detected\n");
+		if (IS_ENABLED(CONFIG_SUSPEND))
+			suspend_set_ops(&sbi_system_suspend_ops);
+	}
+
+	return 0;
+}
+
+arch_initcall(sbi_system_suspend_init);
+#endif /* CONFIG_RISCV_SBI */
diff --git a/arch/riscv/kernel/sys_hwprobe.c b/arch/riscv/kernel/sys_hwprobe.c
new file mode 100644
index 0000000000..a7c56b41ef
--- /dev/null
+++ b/arch/riscv/kernel/sys_hwprobe.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * The hwprobe interface, for allowing userspace to probe to see which features
+ * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for
+ * more details.
+ */
+#include <linux/syscalls.h>
+#include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
+#include <asm/hwprobe.h>
+#include <asm/sbi.h>
+#include <asm/switch_to.h>
+#include <asm/uaccess.h>
+#include <asm/unistd.h>
+#include <asm/vector.h>
+#include <vdso/vsyscall.h>
+
+
+static void hwprobe_arch_id(struct riscv_hwprobe *pair,
+			    const struct cpumask *cpus)
+{
+	u64 id = -1ULL;
+	bool first = true;
+	int cpu;
+
+	for_each_cpu(cpu, cpus) {
+		u64 cpu_id;
+
+		switch (pair->key) {
+		case RISCV_HWPROBE_KEY_MVENDORID:
+			cpu_id = riscv_cached_mvendorid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MIMPID:
+			cpu_id = riscv_cached_mimpid(cpu);
+			break;
+		case RISCV_HWPROBE_KEY_MARCHID:
+			cpu_id = riscv_cached_marchid(cpu);
+			break;
+		}
+
+		if (first) {
+			id = cpu_id;
+			first = false;
+		}
+
+		/*
+		 * If there's a mismatch for the given set, return -1 in the
+		 * value.
+		 */
+		if (id != cpu_id) {
+			id = -1ULL;
+			break;
+		}
+	}
+
+	pair->value = id;
+}
+
+static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	int cpu;
+	u64 missing = 0;
+
+	pair->value = 0;
+	if (has_fpu())
+		pair->value |= RISCV_HWPROBE_IMA_FD;
+
+	if (riscv_isa_extension_available(NULL, c))
+		pair->value |= RISCV_HWPROBE_IMA_C;
+
+	if (has_vector())
+		pair->value |= RISCV_HWPROBE_IMA_V;
+
+	/*
+	 * Loop through and record extensions that 1) anyone has, and 2) anyone
+	 * doesn't have.
+	 */
+	for_each_cpu(cpu, cpus) {
+		struct riscv_isainfo *isainfo = &hart_isa[cpu];
+
+#define EXT_KEY(ext)									\
+	do {										\
+		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
+			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
+		else									\
+			missing |= RISCV_HWPROBE_EXT_##ext;				\
+	} while (false)
+
+		/*
+		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
+		 * regardless of the kernel's configuration, as no other checks, besides
+		 * presence in the hart_isa bitmap, are made.
+		 */
+		EXT_KEY(ZBA);
+		EXT_KEY(ZBB);
+		EXT_KEY(ZBS);
+		EXT_KEY(ZICBOZ);
+		EXT_KEY(ZBC);
+
+		EXT_KEY(ZBKB);
+		EXT_KEY(ZBKC);
+		EXT_KEY(ZBKX);
+		EXT_KEY(ZKND);
+		EXT_KEY(ZKNE);
+		EXT_KEY(ZKNH);
+		EXT_KEY(ZKSED);
+		EXT_KEY(ZKSH);
+		EXT_KEY(ZKT);
+		EXT_KEY(ZIHINTNTL);
+		EXT_KEY(ZTSO);
+		EXT_KEY(ZACAS);
+		EXT_KEY(ZICOND);
+
+		if (has_vector()) {
+			EXT_KEY(ZVBB);
+			EXT_KEY(ZVBC);
+			EXT_KEY(ZVKB);
+			EXT_KEY(ZVKG);
+			EXT_KEY(ZVKNED);
+			EXT_KEY(ZVKNHA);
+			EXT_KEY(ZVKNHB);
+			EXT_KEY(ZVKSED);
+			EXT_KEY(ZVKSH);
+			EXT_KEY(ZVKT);
+			EXT_KEY(ZVFH);
+			EXT_KEY(ZVFHMIN);
+		}
+
+		if (has_fpu()) {
+			EXT_KEY(ZFH);
+			EXT_KEY(ZFHMIN);
+			EXT_KEY(ZFA);
+		}
+#undef EXT_KEY
+	}
+
+	/* Now turn off reporting features if any CPU is missing it. */
+	pair->value &= ~missing;
+}
+
+static bool hwprobe_ext0_has(const struct cpumask *cpus, unsigned long ext)
+{
+	struct riscv_hwprobe pair;
+
+	hwprobe_isa_ext0(&pair, cpus);
+	return (pair.value & ext);
+}
+
+static u64 hwprobe_misaligned(const struct cpumask *cpus)
+{
+	int cpu;
+	u64 perf = -1ULL;
+
+	for_each_cpu(cpu, cpus) {
+		int this_perf = per_cpu(misaligned_access_speed, cpu);
+
+		if (perf == -1ULL)
+			perf = this_perf;
+
+		if (perf != this_perf) {
+			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+			break;
+		}
+	}
+
+	if (perf == -1ULL)
+		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
+
+	return perf;
+}
+
+static void hwprobe_one_pair(struct riscv_hwprobe *pair,
+			     const struct cpumask *cpus)
+{
+	switch (pair->key) {
+	case RISCV_HWPROBE_KEY_MVENDORID:
+	case RISCV_HWPROBE_KEY_MARCHID:
+	case RISCV_HWPROBE_KEY_MIMPID:
+		hwprobe_arch_id(pair, cpus);
+		break;
+	/*
+	 * The kernel already assumes that the base single-letter ISA
+	 * extensions are supported on all harts, and only supports the
+	 * IMA base, so just cheat a bit here and tell that to
+	 * userspace.
+	 */
+	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
+		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
+		break;
+
+	case RISCV_HWPROBE_KEY_IMA_EXT_0:
+		hwprobe_isa_ext0(pair, cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_CPUPERF_0:
+		pair->value = hwprobe_misaligned(cpus);
+		break;
+
+	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
+		pair->value = 0;
+		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
+			pair->value = riscv_cboz_block_size;
+		break;
+
+	/*
+	 * For forward compatibility, unknown keys don't fail the whole
+	 * call, but get their element key set to -1 and value set to 0
+	 * indicating they're unrecognized.
+	 */
+	default:
+		pair->key = -1;
+		pair->value = 0;
+		break;
+	}
+}
+
+static int hwprobe_get_values(struct riscv_hwprobe __user *pairs,
+			      size_t pair_count, size_t cpusetsize,
+			      unsigned long __user *cpus_user,
+			      unsigned int flags)
+{
+	size_t out;
+	int ret;
+	cpumask_t cpus;
+
+	/* Check the reserved flags. */
+	if (flags != 0)
+		return -EINVAL;
+
+	/*
+	 * The interface supports taking in a CPU mask, and returns values that
+	 * are consistent across that mask. Allow userspace to specify NULL and
+	 * 0 as a shortcut to all online CPUs.
+	 */
+	cpumask_clear(&cpus);
+	if (!cpusetsize && !cpus_user) {
+		cpumask_copy(&cpus, cpu_online_mask);
+	} else {
+		if (cpusetsize > cpumask_size())
+			cpusetsize = cpumask_size();
+
+		ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+		if (ret)
+			return -EFAULT;
+
+		/*
+		 * Userspace must provide at least one online CPU, without that
+		 * there's no way to define what is supported.
+		 */
+		cpumask_and(&cpus, &cpus, cpu_online_mask);
+		if (cpumask_empty(&cpus))
+			return -EINVAL;
+	}
+
+	for (out = 0; out < pair_count; out++, pairs++) {
+		struct riscv_hwprobe pair;
+
+		if (get_user(pair.key, &pairs->key))
+			return -EFAULT;
+
+		pair.value = 0;
+		hwprobe_one_pair(&pair, &cpus);
+		ret = put_user(pair.key, &pairs->key);
+		if (ret == 0)
+			ret = put_user(pair.value, &pairs->value);
+
+		if (ret)
+			return -EFAULT;
+	}
+
+	return 0;
+}
+
+static int hwprobe_get_cpus(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	cpumask_t cpus, one_cpu;
+	bool clear_all = false;
+	size_t i;
+	int ret;
+
+	if (flags != RISCV_HWPROBE_WHICH_CPUS)
+		return -EINVAL;
+
+	if (!cpusetsize || !cpus_user)
+		return -EINVAL;
+
+	if (cpusetsize > cpumask_size())
+		cpusetsize = cpumask_size();
+
+	ret = copy_from_user(&cpus, cpus_user, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	if (cpumask_empty(&cpus))
+		cpumask_copy(&cpus, cpu_online_mask);
+
+	cpumask_and(&cpus, &cpus, cpu_online_mask);
+
+	cpumask_clear(&one_cpu);
+
+	for (i = 0; i < pair_count; i++) {
+		struct riscv_hwprobe pair, tmp;
+		int cpu;
+
+		ret = copy_from_user(&pair, &pairs[i], sizeof(pair));
+		if (ret)
+			return -EFAULT;
+
+		if (!riscv_hwprobe_key_is_valid(pair.key)) {
+			clear_all = true;
+			pair = (struct riscv_hwprobe){ .key = -1, };
+			ret = copy_to_user(&pairs[i], &pair, sizeof(pair));
+			if (ret)
+				return -EFAULT;
+		}
+
+		if (clear_all)
+			continue;
+
+		tmp = (struct riscv_hwprobe){ .key = pair.key, };
+
+		for_each_cpu(cpu, &cpus) {
+			cpumask_set_cpu(cpu, &one_cpu);
+
+			hwprobe_one_pair(&tmp, &one_cpu);
+
+			if (!riscv_hwprobe_pair_cmp(&tmp, &pair))
+				cpumask_clear_cpu(cpu, &cpus);
+
+			cpumask_clear_cpu(cpu, &one_cpu);
+		}
+	}
+
+	if (clear_all)
+		cpumask_clear(&cpus);
+
+	ret = copy_to_user(cpus_user, &cpus, cpusetsize);
+	if (ret)
+		return -EFAULT;
+
+	return 0;
+}
+
+static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
+			    size_t pair_count, size_t cpusetsize,
+			    unsigned long __user *cpus_user,
+			    unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return hwprobe_get_cpus(pairs, pair_count, cpusetsize,
+					cpus_user, flags);
+
+	return hwprobe_get_values(pairs, pair_count, cpusetsize,
+				  cpus_user, flags);
+}
+
+#ifdef CONFIG_MMU
+
+static int __init init_hwprobe_vdso_data(void)
+{
+	struct vdso_data *vd = __arch_get_k_vdso_data();
+	struct arch_vdso_data *avd = &vd->arch_data;
+	u64 id_bitsmash = 0;
+	struct riscv_hwprobe pair;
+	int key;
+
+	/*
+	 * Initialize vDSO data with the answers for the "all CPUs" case, to
+	 * save a syscall in the common case.
+	 */
+	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
+		pair.key = key;
+		hwprobe_one_pair(&pair, cpu_online_mask);
+
+		WARN_ON_ONCE(pair.key < 0);
+
+		avd->all_cpu_hwprobe_values[key] = pair.value;
+		/*
+		 * Smash together the vendor, arch, and impl IDs to see if
+		 * they're all 0 or any negative.
+		 */
+		if (key <= RISCV_HWPROBE_KEY_MIMPID)
+			id_bitsmash |= pair.value;
+	}
+
+	/*
+	 * If the arch, vendor, and implementation ID are all the same across
+	 * all harts, then assume all CPUs are the same, and allow the vDSO to
+	 * answer queries for arbitrary masks. However if all values are 0 (not
+	 * populated) or any value returns -1 (varies across CPUs), then the
+	 * vDSO should defer to the kernel for exotic cpu masks.
+	 */
+	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
+	return 0;
+}
+
+arch_initcall_sync(init_hwprobe_vdso_data);
+
+#endif /* CONFIG_MMU */
+
+SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
+		size_t, pair_count, size_t, cpusetsize, unsigned long __user *,
+		cpus, unsigned int, flags)
+{
+	return do_riscv_hwprobe(pairs, pair_count, cpusetsize,
+				cpus, flags);
+}
diff --git a/arch/riscv/kernel/sys_riscv.c b/arch/riscv/kernel/sys_riscv.c
index a2ca5b7756..f1c1416a9f 100644
--- a/arch/riscv/kernel/sys_riscv.c
+++ b/arch/riscv/kernel/sys_riscv.c
@@ -7,15 +7,7 @@
 
 #include <linux/syscalls.h>
 #include <asm/cacheflush.h>
-#include <asm/cpufeature.h>
-#include <asm/hwprobe.h>
-#include <asm/sbi.h>
-#include <asm/vector.h>
-#include <asm/switch_to.h>
-#include <asm/uaccess.h>
-#include <asm/unistd.h>
 #include <asm-generic/mman-common.h>
-#include <vdso/vsyscall.h>
 
 static long riscv_sys_mmap(unsigned long addr, unsigned long len,
 			   unsigned long prot, unsigned long flags,
@@ -77,283 +69,6 @@ SYSCALL_DEFINE3(riscv_flush_icache, uintptr_t, start, uintptr_t, end,
 	return 0;
 }
 
-/*
- * The hwprobe interface, for allowing userspace to probe to see which features
- * are supported by the hardware.  See Documentation/arch/riscv/hwprobe.rst for more
- * details.
- */
-static void hwprobe_arch_id(struct riscv_hwprobe *pair,
-			    const struct cpumask *cpus)
-{
-	u64 id = -1ULL;
-	bool first = true;
-	int cpu;
-
-	for_each_cpu(cpu, cpus) {
-		u64 cpu_id;
-
-		switch (pair->key) {
-		case RISCV_HWPROBE_KEY_MVENDORID:
-			cpu_id = riscv_cached_mvendorid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MIMPID:
-			cpu_id = riscv_cached_mimpid(cpu);
-			break;
-		case RISCV_HWPROBE_KEY_MARCHID:
-			cpu_id = riscv_cached_marchid(cpu);
-			break;
-		}
-
-		if (first) {
-			id = cpu_id;
-			first = false;
-		}
-
-		/*
-		 * If there's a mismatch for the given set, return -1 in the
-		 * value.
-		 */
-		if (id != cpu_id) {
-			id = -1ULL;
-			break;
-		}
-	}
-
-	pair->value = id;
-}
-
-static void hwprobe_isa_ext0(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	int cpu;
-	u64 missing = 0;
-
-	pair->value = 0;
-	if (has_fpu())
-		pair->value |= RISCV_HWPROBE_IMA_FD;
-
-	if (riscv_isa_extension_available(NULL, c))
-		pair->value |= RISCV_HWPROBE_IMA_C;
-
-	if (has_vector())
-		pair->value |= RISCV_HWPROBE_IMA_V;
-
-	/*
-	 * Loop through and record extensions that 1) anyone has, and 2) anyone
-	 * doesn't have.
-	 */
-	for_each_cpu(cpu, cpus) {
-		struct riscv_isainfo *isainfo = &hart_isa[cpu];
-
-#define EXT_KEY(ext)									\
-	do {										\
-		if (__riscv_isa_extension_available(isainfo->isa, RISCV_ISA_EXT_##ext))	\
-			pair->value |= RISCV_HWPROBE_EXT_##ext;				\
-		else									\
-			missing |= RISCV_HWPROBE_EXT_##ext;				\
-	} while (false)
-
-		/*
-		 * Only use EXT_KEY() for extensions which can be exposed to userspace,
-		 * regardless of the kernel's configuration, as no other checks, besides
-		 * presence in the hart_isa bitmap, are made.
-		 */
-		EXT_KEY(ZBA);
-		EXT_KEY(ZBB);
-		EXT_KEY(ZBS);
-		EXT_KEY(ZICBOZ);
-#undef EXT_KEY
-	}
-
-	/* Now turn off reporting features if any CPU is missing it. */
-	pair->value &= ~missing;
-}
-
-static bool hwprobe_ext0_has(const struct cpumask *cpus, u64 ext)
-{
-	struct riscv_hwprobe pair;
-
-	hwprobe_isa_ext0(&pair, cpus);
-	return (pair.value & ext);
-}
-
-static u64 hwprobe_misaligned(const struct cpumask *cpus)
-{
-	int cpu;
-	u64 perf = -1ULL;
-
-	for_each_cpu(cpu, cpus) {
-		int this_perf = per_cpu(misaligned_access_speed, cpu);
-
-		if (perf == -1ULL)
-			perf = this_perf;
-
-		if (perf != this_perf) {
-			perf = RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-			break;
-		}
-	}
-
-	if (perf == -1ULL)
-		return RISCV_HWPROBE_MISALIGNED_UNKNOWN;
-
-	return perf;
-}
-
-static void hwprobe_one_pair(struct riscv_hwprobe *pair,
-			     const struct cpumask *cpus)
-{
-	switch (pair->key) {
-	case RISCV_HWPROBE_KEY_MVENDORID:
-	case RISCV_HWPROBE_KEY_MARCHID:
-	case RISCV_HWPROBE_KEY_MIMPID:
-		hwprobe_arch_id(pair, cpus);
-		break;
-	/*
-	 * The kernel already assumes that the base single-letter ISA
-	 * extensions are supported on all harts, and only supports the
-	 * IMA base, so just cheat a bit here and tell that to
-	 * userspace.
-	 */
-	case RISCV_HWPROBE_KEY_BASE_BEHAVIOR:
-		pair->value = RISCV_HWPROBE_BASE_BEHAVIOR_IMA;
-		break;
-
-	case RISCV_HWPROBE_KEY_IMA_EXT_0:
-		hwprobe_isa_ext0(pair, cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_CPUPERF_0:
-		pair->value = hwprobe_misaligned(cpus);
-		break;
-
-	case RISCV_HWPROBE_KEY_ZICBOZ_BLOCK_SIZE:
-		pair->value = 0;
-		if (hwprobe_ext0_has(cpus, RISCV_HWPROBE_EXT_ZICBOZ))
-			pair->value = riscv_cboz_block_size;
-		break;
-
-	/*
-	 * For forward compatibility, unknown keys don't fail the whole
-	 * call, but get their element key set to -1 and value set to 0
-	 * indicating they're unrecognized.
-	 */
-	default:
-		pair->key = -1;
-		pair->value = 0;
-		break;
-	}
-}
-
-static int do_riscv_hwprobe(struct riscv_hwprobe __user *pairs,
-			    size_t pair_count, size_t cpu_count,
-			    unsigned long __user *cpus_user,
-			    unsigned int flags)
-{
-	size_t out;
-	int ret;
-	cpumask_t cpus;
-
-	/* Check the reserved flags. */
-	if (flags != 0)
-		return -EINVAL;
-
-	/*
-	 * The interface supports taking in a CPU mask, and returns values that
-	 * are consistent across that mask. Allow userspace to specify NULL and
-	 * 0 as a shortcut to all online CPUs.
-	 */
-	cpumask_clear(&cpus);
-	if (!cpu_count && !cpus_user) {
-		cpumask_copy(&cpus, cpu_online_mask);
-	} else {
-		if (cpu_count > cpumask_size())
-			cpu_count = cpumask_size();
-
-		ret = copy_from_user(&cpus, cpus_user, cpu_count);
-		if (ret)
-			return -EFAULT;
-
-		/*
-		 * Userspace must provide at least one online CPU, without that
-		 * there's no way to define what is supported.
-		 */
-		cpumask_and(&cpus, &cpus, cpu_online_mask);
-		if (cpumask_empty(&cpus))
-			return -EINVAL;
-	}
-
-	for (out = 0; out < pair_count; out++, pairs++) {
-		struct riscv_hwprobe pair;
-
-		if (get_user(pair.key, &pairs->key))
-			return -EFAULT;
-
-		pair.value = 0;
-		hwprobe_one_pair(&pair, &cpus);
-		ret = put_user(pair.key, &pairs->key);
-		if (ret == 0)
-			ret = put_user(pair.value, &pairs->value);
-
-		if (ret)
-			return -EFAULT;
-	}
-
-	return 0;
-}
-
-#ifdef CONFIG_MMU
-
-static int __init init_hwprobe_vdso_data(void)
-{
-	struct vdso_data *vd = __arch_get_k_vdso_data();
-	struct arch_vdso_data *avd = &vd->arch_data;
-	u64 id_bitsmash = 0;
-	struct riscv_hwprobe pair;
-	int key;
-
-	/*
-	 * Initialize vDSO data with the answers for the "all CPUs" case, to
-	 * save a syscall in the common case.
-	 */
-	for (key = 0; key <= RISCV_HWPROBE_MAX_KEY; key++) {
-		pair.key = key;
-		hwprobe_one_pair(&pair, cpu_online_mask);
-
-		WARN_ON_ONCE(pair.key < 0);
-
-		avd->all_cpu_hwprobe_values[key] = pair.value;
-		/*
-		 * Smash together the vendor, arch, and impl IDs to see if
-		 * they're all 0 or any negative.
-		 */
-		if (key <= RISCV_HWPROBE_KEY_MIMPID)
-			id_bitsmash |= pair.value;
-	}
-
-	/*
-	 * If the arch, vendor, and implementation ID are all the same across
-	 * all harts, then assume all CPUs are the same, and allow the vDSO to
-	 * answer queries for arbitrary masks. However if all values are 0 (not
-	 * populated) or any value returns -1 (varies across CPUs), then the
-	 * vDSO should defer to the kernel for exotic cpu masks.
-	 */
-	avd->homogeneous_cpus = id_bitsmash != 0 && id_bitsmash != -1;
-	return 0;
-}
-
-arch_initcall_sync(init_hwprobe_vdso_data);
-
-#endif /* CONFIG_MMU */
-
-SYSCALL_DEFINE5(riscv_hwprobe, struct riscv_hwprobe __user *, pairs,
-		size_t, pair_count, size_t, cpu_count, unsigned long __user *,
-		cpus, unsigned int, flags)
-{
-	return do_riscv_hwprobe(pairs, pair_count, cpu_count,
-				cpus, flags);
-}
-
 /* Not defined using SYSCALL_DEFINE0 to avoid error injection */
 asmlinkage long __riscv_sys_ni_syscall(const struct pt_regs *__unused)
 {
diff --git a/arch/riscv/kernel/time.c b/arch/riscv/kernel/time.c
index 23641e82a9..ba34771977 100644
--- a/arch/riscv/kernel/time.c
+++ b/arch/riscv/kernel/time.c
@@ -12,6 +12,7 @@
 #include <asm/sbi.h>
 #include <asm/processor.h>
 #include <asm/timex.h>
+#include <asm/paravirt.h>
 
 unsigned long riscv_timebase __ro_after_init;
 EXPORT_SYMBOL_GPL(riscv_timebase);
@@ -45,4 +46,6 @@ void __init time_init(void)
 	timer_probe();
 
 	tick_setup_hrtimer_broadcast();
+
+	pv_time_init();
 }
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index a1b9be3c43..142f5f5168 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -121,7 +121,7 @@ void do_trap(struct pt_regs *regs, int signo, int code, unsigned long addr)
 		print_vma_addr(KERN_CONT " in ", instruction_pointer(regs));
 		pr_cont("\n");
 		__show_regs(regs);
-		dump_instr(KERN_EMERG, regs);
+		dump_instr(KERN_INFO, regs);
 	}
 
 	force_sig_fault(signo, code, (void __user *)addr);
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index 1ed769c87a..c2ed4e689b 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -319,7 +319,7 @@ static inline int get_insn(struct pt_regs *regs, ulong mepc, ulong *r_insn)
 static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 {
 	if (user_mode(regs)) {
-		return __get_user(*r_val, addr);
+		return __get_user(*r_val, (u8 __user *)addr);
 	} else {
 		*r_val = *addr;
 		return 0;
@@ -329,7 +329,7 @@ static inline int load_u8(struct pt_regs *regs, const u8 *addr, u8 *r_val)
 static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 {
 	if (user_mode(regs)) {
-		return __put_user(val, addr);
+		return __put_user(val, (u8 __user *)addr);
 	} else {
 		*addr = val;
 		return 0;
@@ -343,7 +343,7 @@ static inline int store_u8(struct pt_regs *regs, u8 *addr, u8 val)
 	if (user_mode(regs)) {				\
 		__ret = __get_user(insn, insn_addr);	\
 	} else {					\
-		insn = *insn_addr;			\
+		insn = *(__force u16 *)insn_addr;	\
 		__ret = 0;				\
 	}						\
 							\
diff --git a/arch/riscv/kernel/vdso/Makefile b/arch/riscv/kernel/vdso/Makefile
index 9b517fe1b8..272c431ac5 100644
--- a/arch/riscv/kernel/vdso/Makefile
+++ b/arch/riscv/kernel/vdso/Makefile
@@ -37,6 +37,7 @@ endif
 
 # Disable -pg to prevent insert call site
 CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
+CFLAGS_REMOVE_hwprobe.o = $(CC_FLAGS_FTRACE) $(CC_FLAGS_SCS)
 
 # Disable profiling and instrumentation for VDSO code
 GCOV_PROFILE := n
diff --git a/arch/riscv/kernel/vdso/hwprobe.c b/arch/riscv/kernel/vdso/hwprobe.c
index cadf725ef7..1e926e4b58 100644
--- a/arch/riscv/kernel/vdso/hwprobe.c
+++ b/arch/riscv/kernel/vdso/hwprobe.c
@@ -3,26 +3,22 @@
  * Copyright 2023 Rivos, Inc
  */
 
+#include <linux/string.h>
 #include <linux/types.h>
 #include <vdso/datapage.h>
 #include <vdso/helpers.h>
 
 extern int riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
+			 size_t cpusetsize, unsigned long *cpus,
 			 unsigned int flags);
 
-/* Add a prototype to avoid -Wmissing-prototypes warning. */
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
-			 unsigned int flags);
-
-int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
-			 size_t cpu_count, unsigned long *cpus,
-			 unsigned int flags)
+static int riscv_vdso_get_values(struct riscv_hwprobe *pairs, size_t pair_count,
+				 size_t cpusetsize, unsigned long *cpus,
+				 unsigned int flags)
 {
 	const struct vdso_data *vd = __arch_get_vdso_data();
 	const struct arch_vdso_data *avd = &vd->arch_data;
-	bool all_cpus = !cpu_count && !cpus;
+	bool all_cpus = !cpusetsize && !cpus;
 	struct riscv_hwprobe *p = pairs;
 	struct riscv_hwprobe *end = pairs + pair_count;
 
@@ -33,7 +29,7 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 	 * masks.
 	 */
 	if ((flags != 0) || (!all_cpus && !avd->homogeneous_cpus))
-		return riscv_hwprobe(pairs, pair_count, cpu_count, cpus, flags);
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
 
 	/* This is something we can handle, fill out the pairs. */
 	while (p < end) {
@@ -50,3 +46,71 @@ int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
 
 	return 0;
 }
+
+static int riscv_vdso_get_cpus(struct riscv_hwprobe *pairs, size_t pair_count,
+			       size_t cpusetsize, unsigned long *cpus,
+			       unsigned int flags)
+{
+	const struct vdso_data *vd = __arch_get_vdso_data();
+	const struct arch_vdso_data *avd = &vd->arch_data;
+	struct riscv_hwprobe *p = pairs;
+	struct riscv_hwprobe *end = pairs + pair_count;
+	unsigned char *c = (unsigned char *)cpus;
+	bool empty_cpus = true;
+	bool clear_all = false;
+	int i;
+
+	if (!cpusetsize || !cpus)
+		return -EINVAL;
+
+	for (i = 0; i < cpusetsize; i++) {
+		if (c[i]) {
+			empty_cpus = false;
+			break;
+		}
+	}
+
+	if (empty_cpus || flags != RISCV_HWPROBE_WHICH_CPUS || !avd->homogeneous_cpus)
+		return riscv_hwprobe(pairs, pair_count, cpusetsize, cpus, flags);
+
+	while (p < end) {
+		if (riscv_hwprobe_key_is_valid(p->key)) {
+			struct riscv_hwprobe t = {
+				.key = p->key,
+				.value = avd->all_cpu_hwprobe_values[p->key],
+			};
+
+			if (!riscv_hwprobe_pair_cmp(&t, p))
+				clear_all = true;
+		} else {
+			clear_all = true;
+			p->key = -1;
+			p->value = 0;
+		}
+		p++;
+	}
+
+	if (clear_all) {
+		for (i = 0; i < cpusetsize; i++)
+			c[i] = 0;
+	}
+
+	return 0;
+}
+
+/* Add a prototype to avoid -Wmissing-prototypes warning. */
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags);
+
+int __vdso_riscv_hwprobe(struct riscv_hwprobe *pairs, size_t pair_count,
+			 size_t cpusetsize, unsigned long *cpus,
+			 unsigned int flags)
+{
+	if (flags & RISCV_HWPROBE_WHICH_CPUS)
+		return riscv_vdso_get_cpus(pairs, pair_count, cpusetsize,
+					   cpus, flags);
+
+	return riscv_vdso_get_values(pairs, pair_count, cpusetsize,
+				     cpus, flags);
+}
diff --git a/arch/riscv/kernel/vdso/vgettimeofday.c b/arch/riscv/kernel/vdso/vgettimeofday.c
index cc0d80699c..b350578025 100644
--- a/arch/riscv/kernel/vdso/vgettimeofday.c
+++ b/arch/riscv/kernel/vdso/vgettimeofday.c
@@ -8,23 +8,18 @@
 
 #include <linux/time.h>
 #include <linux/types.h>
+#include <vdso/gettime.h>
 
-extern
-int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts);
 int __vdso_clock_gettime(clockid_t clock, struct __kernel_timespec *ts)
 {
 	return __cvdso_clock_gettime(clock, ts);
 }
 
-extern
-int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz);
 int __vdso_gettimeofday(struct __kernel_old_timeval *tv, struct timezone *tz)
 {
 	return __cvdso_gettimeofday(tv, tz);
 }
 
-extern
-int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res);
 int __vdso_clock_getres(clockid_t clock_id, struct __kernel_timespec *res)
 {
 	return __cvdso_clock_getres(clock_id, res);
diff --git a/arch/riscv/kernel/vector.c b/arch/riscv/kernel/vector.c
index 578b629248..6727d1d3b8 100644
--- a/arch/riscv/kernel/vector.c
+++ b/arch/riscv/kernel/vector.c
@@ -21,6 +21,10 @@
 #include <asm/bug.h>
 
 static bool riscv_v_implicit_uacc = IS_ENABLED(CONFIG_RISCV_ISA_V_DEFAULT_ENABLE);
+static struct kmem_cache *riscv_v_user_cachep;
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+static struct kmem_cache *riscv_v_kernel_cachep;
+#endif
 
 unsigned long riscv_v_vsize __read_mostly;
 EXPORT_SYMBOL_GPL(riscv_v_vsize);
@@ -47,6 +51,21 @@ int riscv_v_setup_vsize(void)
 	return 0;
 }
 
+void __init riscv_v_setup_ctx_cache(void)
+{
+	if (!has_vector())
+		return;
+
+	riscv_v_user_cachep = kmem_cache_create_usercopy("riscv_vector_ctx",
+							 riscv_v_vsize, 16, SLAB_PANIC,
+							 0, riscv_v_vsize, NULL);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_kernel_cachep = kmem_cache_create("riscv_vector_kctx",
+						  riscv_v_vsize, 16,
+						  SLAB_PANIC, NULL);
+#endif
+}
+
 static bool insn_is_vector(u32 insn_buf)
 {
 	u32 opcode = insn_buf & __INSN_OPCODE_MASK;
@@ -80,20 +99,37 @@ static bool insn_is_vector(u32 insn_buf)
 	return false;
 }
 
-static int riscv_v_thread_zalloc(void)
+static int riscv_v_thread_zalloc(struct kmem_cache *cache,
+				 struct __riscv_v_ext_state *ctx)
 {
 	void *datap;
 
-	datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	datap = kmem_cache_zalloc(cache, GFP_KERNEL);
 	if (!datap)
 		return -ENOMEM;
 
-	current->thread.vstate.datap = datap;
-	memset(&current->thread.vstate, 0, offsetof(struct __riscv_v_ext_state,
-						    datap));
+	ctx->datap = datap;
+	memset(ctx, 0, offsetof(struct __riscv_v_ext_state, datap));
 	return 0;
 }
 
+void riscv_v_thread_alloc(struct task_struct *tsk)
+{
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	riscv_v_thread_zalloc(riscv_v_kernel_cachep, &tsk->thread.kernel_vstate);
+#endif
+}
+
+void riscv_v_thread_free(struct task_struct *tsk)
+{
+	if (tsk->thread.vstate.datap)
+		kmem_cache_free(riscv_v_user_cachep, tsk->thread.vstate.datap);
+#ifdef CONFIG_RISCV_ISA_V_PREEMPTIVE
+	if (tsk->thread.kernel_vstate.datap)
+		kmem_cache_free(riscv_v_kernel_cachep, tsk->thread.kernel_vstate.datap);
+#endif
+}
+
 #define VSTATE_CTRL_GET_CUR(x) ((x) & PR_RISCV_V_VSTATE_CTRL_CUR_MASK)
 #define VSTATE_CTRL_GET_NEXT(x) (((x) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK) >> 2)
 #define VSTATE_CTRL_MAKE_NEXT(x) (((x) << 2) & PR_RISCV_V_VSTATE_CTRL_NEXT_MASK)
@@ -122,7 +158,8 @@ static inline void riscv_v_ctrl_set(struct task_struct *tsk, int cur, int nxt,
 	ctrl |= VSTATE_CTRL_MAKE_NEXT(nxt);
 	if (inherit)
 		ctrl |= PR_RISCV_V_VSTATE_CTRL_INHERIT;
-	tsk->thread.vstate_ctrl = ctrl;
+	tsk->thread.vstate_ctrl &= ~PR_RISCV_V_VSTATE_CTRL_MASK;
+	tsk->thread.vstate_ctrl |= ctrl;
 }
 
 bool riscv_v_vstate_ctrl_user_allowed(void)
@@ -162,12 +199,12 @@ bool riscv_v_first_use_handler(struct pt_regs *regs)
 	 * context where VS has been off. So, try to allocate the user's V
 	 * context and resume execution.
 	 */
-	if (riscv_v_thread_zalloc()) {
+	if (riscv_v_thread_zalloc(riscv_v_user_cachep, &current->thread.vstate)) {
 		force_sig(SIGBUS);
 		return true;
 	}
 	riscv_v_vstate_on(regs);
-	riscv_v_vstate_restore(current, regs);
+	riscv_v_vstate_set_restore(current, regs);
 	return true;
 }