21 files changed, 127 insertions, 91 deletions

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 36061f4732b7..1c5544401530 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -63,7 +63,8 @@ config RISCV
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
-	select ARCH_SUPPORTS_CFI_CLANG
+	# clang >= 17: https://github.com/llvm/llvm-project/commit/62fa708ceb027713b386c7e0efda994f8bdc27e2
+	select ARCH_SUPPORTS_CFI_CLANG if CLANG_VERSION >= 170000
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC if MMU
 	select ARCH_SUPPORTS_HUGE_PFNMAP if TRANSPARENT_HUGEPAGE
 	select ARCH_SUPPORTS_HUGETLBFS if MMU
@@ -97,6 +98,7 @@ config RISCV
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select CPU_PM if CPU_IDLE || HIBERNATION || SUSPEND
+	select DYNAMIC_FTRACE if FUNCTION_TRACER
 	select EDAC_SUPPORT
 	select FRAME_POINTER if PERF_EVENTS || (FUNCTION_TRACER && !DYNAMIC_FTRACE)
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
@@ -161,7 +163,7 @@ config RISCV
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_FUNCTION_GRAPH_FREGS
-	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && HAVE_DYNAMIC_FTRACE
 	select HAVE_EBPF_JIT if MMU
 	select HAVE_GUP_FAST if MMU
 	select HAVE_FUNCTION_ARG_ACCESS_API
diff --git a/arch/riscv/include/asm/kvm_aia.h b/arch/riscv/include/asm/kvm_aia.h
index 3b643b9efc07..5acce285e56e 100644
--- a/arch/riscv/include/asm/kvm_aia.h
+++ b/arch/riscv/include/asm/kvm_aia.h
@@ -87,6 +87,9 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
 
 extern struct kvm_device_ops kvm_riscv_aia_device_ops;
 
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu);
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu);
 int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu);
 
@@ -161,7 +164,6 @@ void kvm_riscv_aia_destroy_vm(struct kvm *kvm);
 int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner,
 			     void __iomem **hgei_va, phys_addr_t *hgei_pa);
 void kvm_riscv_aia_free_hgei(int cpu, int hgei);
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable);
 
 void kvm_riscv_aia_enable(void);
 void kvm_riscv_aia_disable(void);
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index 85cfebc32e4c..bcbf8b1ec115 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -306,6 +306,9 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
 	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
 }
 
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index a11816bbf9e7..5bd5aae60d53 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -1028,7 +1028,7 @@ static inline pud_t pud_modify(pud_t pud, pgprot_t newprot)
 #define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
 #define __swp_entry_to_pte(x)	((pte_t) { (x).val })
 
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
 {
 	return pte_val(pte) & _PAGE_SWP_EXCLUSIVE;
 }
@@ -1075,7 +1075,6 @@ static inline pte_t pte_swp_clear_exclusive(pte_t pte)
  */
 #ifdef CONFIG_64BIT
 #define TASK_SIZE_64	(PGDIR_SIZE * PTRS_PER_PGD / 2)
-#define TASK_SIZE_MAX	LONG_MAX
 
 #ifdef CONFIG_COMPAT
 #define TASK_SIZE_32	(_AC(0x80000000, UL) - PAGE_SIZE)
diff --git a/arch/riscv/include/asm/runtime-const.h b/arch/riscv/include/asm/runtime-const.h
index 451fd76b8811..d766e2b9e6df 100644
--- a/arch/riscv/include/asm/runtime-const.h
+++ b/arch/riscv/include/asm/runtime-const.h
@@ -206,7 +206,7 @@ static inline void __runtime_fixup_32(__le16 *lui_parcel, __le16 *addi_parcel, u
 		addi_insn_mask &= 0x07fff;
 	}
 
-	if (lower_immediate & 0x00000fff) {
+	if (lower_immediate & 0x00000fff || lui_insn == RISCV_INSN_NOP4) {
 		/* replace upper 12 bits of addi with lower 12 bits of val */
 		addi_insn &= addi_insn_mask;
 		addi_insn |= (lower_immediate & 0x00000fff) << 20;
diff --git a/arch/riscv/include/asm/uaccess.h b/arch/riscv/include/asm/uaccess.h
index d472da4450e6..b88a6218b7f2 100644
--- a/arch/riscv/include/asm/uaccess.h
+++ b/arch/riscv/include/asm/uaccess.h
@@ -127,6 +127,7 @@ do {								\
 
 #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 #define __get_user_8(x, ptr, label)				\
+do {								\
 	u32 __user *__ptr = (u32 __user *)(ptr);		\
 	u32 __lo, __hi;						\
 	asm_goto_output(					\
@@ -141,7 +142,7 @@ do {								\
 		: : label);                                     \
 	(x) = (__typeof__(x))((__typeof__((x) - (x)))(		\
 		(((u64)__hi << 32) | __lo)));			\
-
+} while (0)
 #else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
 #define __get_user_8(x, ptr, label)				\
 do {								\
@@ -310,8 +311,8 @@ do {								\
 do {								\
 	if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) &&	\
 	    !IS_ALIGNED((uintptr_t)__gu_ptr, sizeof(*__gu_ptr))) {	\
-		__inttype(x) val = (__inttype(x))x;			\
-		if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(val), sizeof(*__gu_ptr))) \
+		__inttype(x) ___val = (__inttype(x))x;			\
+		if (__asm_copy_to_user_sum_enabled(__gu_ptr, &(___val), sizeof(*__gu_ptr))) \
 			goto label;				\
 		break;						\
 	}							\
diff --git a/arch/riscv/include/asm/vdso/getrandom.h b/arch/riscv/include/asm/vdso/getrandom.h
index 8dc92441702a..c6d66895c1f5 100644
--- a/arch/riscv/include/asm/vdso/getrandom.h
+++ b/arch/riscv/include/asm/vdso/getrandom.h
@@ -18,7 +18,7 @@ static __always_inline ssize_t getrandom_syscall(void *_buffer, size_t _len, uns
 	register unsigned int flags asm("a2") = _flags;
 
 	asm volatile ("ecall\n"
-		      : "+r" (ret)
+		      : "=r" (ret)
 		      : "r" (nr), "r" (buffer), "r" (len), "r" (flags)
 		      : "memory");
 
diff --git a/arch/riscv/include/asm/vector.h b/arch/riscv/include/asm/vector.h
index 45c9b426fcc5..b61786d43c20 100644
--- a/arch/riscv/include/asm/vector.h
+++ b/arch/riscv/include/asm/vector.h
@@ -205,11 +205,11 @@ static inline void __riscv_v_vstate_save(struct __riscv_v_ext_state *save_to,
 			THEAD_VSETVLI_T4X0E8M8D1
 			THEAD_VSB_V_V0T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V8T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V16T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VSB_V_V0T0
+			THEAD_VSB_V_V24T0
 			: : "r" (datap) : "memory", "t0", "t4");
 	} else {
 		asm volatile (
@@ -241,11 +241,11 @@ static inline void __riscv_v_vstate_restore(struct __riscv_v_ext_state *restore_
 			THEAD_VSETVLI_T4X0E8M8D1
 			THEAD_VLB_V_V0T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V8T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V16T0
 			"add		t0, t0, t4\n\t"
-			THEAD_VLB_V_V0T0
+			THEAD_VLB_V_V24T0
 			: : "r" (datap) : "memory", "t0", "t4");
 	} else {
 		asm volatile (
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index e6fbaaf54956..87d655944803 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -18,10 +18,10 @@ const struct cpu_operations cpu_ops_sbi;
 
 /*
  * Ordered booting via HSM brings one cpu at a time. However, cpu hotplug can
- * be invoked from multiple threads in parallel. Define a per cpu data
+ * be invoked from multiple threads in parallel. Define an array of boot data
  * to handle that.
  */
-static DEFINE_PER_CPU(struct sbi_hart_boot_data, boot_data);
+static struct sbi_hart_boot_data boot_data[NR_CPUS];
 
 static int sbi_hsm_hart_start(unsigned long hartid, unsigned long saddr,
 			      unsigned long priv)
@@ -67,7 +67,7 @@ static int sbi_cpu_start(unsigned int cpuid, struct task_struct *tidle)
 	unsigned long boot_addr = __pa_symbol(secondary_start_sbi);
 	unsigned long hartid = cpuid_to_hartid_map(cpuid);
 	unsigned long hsm_data;
-	struct sbi_hart_boot_data *bdata = &per_cpu(boot_data, cpuid);
+	struct sbi_hart_boot_data *bdata = &boot_data[cpuid];
 
 	/* Make sure tidle is updated */
 	smp_mb();
diff --git a/arch/riscv/kernel/ftrace.c b/arch/riscv/kernel/ftrace.c
index 4c6c24380cfd..8d18d6727f0f 100644
--- a/arch/riscv/kernel/ftrace.c
+++ b/arch/riscv/kernel/ftrace.c
@@ -14,6 +14,18 @@
 #include <asm/text-patching.h>
 
 #ifdef CONFIG_DYNAMIC_FTRACE
+void ftrace_arch_code_modify_prepare(void)
+	__acquires(&text_mutex)
+{
+	mutex_lock(&text_mutex);
+}
+
+void ftrace_arch_code_modify_post_process(void)
+	__releases(&text_mutex)
+{
+	mutex_unlock(&text_mutex);
+}
+
 unsigned long ftrace_call_adjust(unsigned long addr)
 {
 	if (IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS))
@@ -29,10 +41,8 @@ unsigned long arch_ftrace_get_symaddr(unsigned long fentry_ip)
 
 void arch_ftrace_update_code(int command)
 {
-	mutex_lock(&text_mutex);
 	command |= FTRACE_MAY_SLEEP;
 	ftrace_modify_all_code(command);
-	mutex_unlock(&text_mutex);
 	flush_icache_all();
 }
 
@@ -149,6 +159,8 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 	unsigned int nops[2], offset;
 	int ret;
 
+	guard(mutex)(&text_mutex);
+
 	ret = ftrace_rec_set_nop_ops(rec);
 	if (ret)
 		return ret;
@@ -157,9 +169,7 @@ int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 	nops[0] = to_auipc_t0(offset);
 	nops[1] = RISCV_INSN_NOP4;
 
-	mutex_lock(&text_mutex);
 	ret = patch_insn_write((void *)pc, nops, 2 * MCOUNT_INSN_SIZE);
-	mutex_unlock(&text_mutex);
 
 	return ret;
 }
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f7c9a1caa83e..14888e5ea19a 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -50,6 +50,7 @@ atomic_t hart_lottery __section(".sdata")
 #endif
 ;
 unsigned long boot_cpu_hartid;
+EXPORT_SYMBOL_GPL(boot_cpu_hartid);
 
 /*
  * Place kernel memory regions on the resource tree so that
diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index 9c83848797a7..80230de167de 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -6,6 +6,7 @@
 #include <linux/cpu.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/irqflags.h>
 #include <linux/randomize_kstack.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
@@ -151,7 +152,9 @@ asmlinkage __visible __trap_section void name(struct pt_regs *regs)		\
 {										\
 	if (user_mode(regs)) {							\
 		irqentry_enter_from_user_mode(regs);				\
+		local_irq_enable();						\
 		do_trap_error(regs, signo, code, regs->epc, "Oops - " str);	\
+		local_irq_disable();						\
 		irqentry_exit_to_user_mode(regs);				\
 	} else {								\
 		irqentry_state_t state = irqentry_nmi_enter(regs);		\
@@ -173,17 +176,14 @@ asmlinkage __visible __trap_section void do_trap_insn_illegal(struct pt_regs *re
 
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
-
 		local_irq_enable();
 
 		handled = riscv_v_first_use_handler(regs);
-
-		local_irq_disable();
-
 		if (!handled)
 			do_trap_error(regs, SIGILL, ILL_ILLOPC, regs->epc,
 				      "Oops - illegal instruction");
 
+		local_irq_disable();
 		irqentry_exit_to_user_mode(regs);
 	} else {
 		irqentry_state_t state = irqentry_nmi_enter(regs);
@@ -308,9 +308,11 @@ asmlinkage __visible __trap_section void do_trap_break(struct pt_regs *regs)
 {
 	if (user_mode(regs)) {
 		irqentry_enter_from_user_mode(regs);
+		local_irq_enable();
 
 		handle_break(regs);
 
+		local_irq_disable();
 		irqentry_exit_to_user_mode(regs);
 	} else {
 		irqentry_state_t state = irqentry_nmi_enter(regs);
diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
index dd8e4af6583f..f760e4fcc052 100644
--- a/arch/riscv/kernel/traps_misaligned.c
+++ b/arch/riscv/kernel/traps_misaligned.c
@@ -454,14 +454,14 @@ static int handle_scalar_misaligned_load(struct pt_regs *regs)
 
 	val.data_u64 = 0;
 	if (user_mode(regs)) {
-		if (copy_from_user_nofault(&val, (u8 __user *)addr, len))
+		if (copy_from_user(&val, (u8 __user *)addr, len))
 			return -1;
 	} else {
 		memcpy(&val, (u8 *)addr, len);
 	}
 
 	if (!fp)
-		SET_RD(insn, regs, val.data_ulong << shift >> shift);
+		SET_RD(insn, regs, (long)(val.data_ulong << shift) >> shift);
 	else if (len == 8)
 		set_f64_rd(insn, regs, val.data_u64);
 	else
@@ -555,7 +555,7 @@ static int handle_scalar_misaligned_store(struct pt_regs *regs)
 		return -EOPNOTSUPP;
 
 	if (user_mode(regs)) {
-		if (copy_to_user_nofault((u8 __user *)addr, &val, len))
+		if (copy_to_user((u8 __user *)addr, &val, len))
 			return -1;
 	} else {
 		memcpy((u8 *)addr, &val, len);
diff --git a/arch/riscv/kernel/vdso/vdso.lds.S b/arch/riscv/kernel/vdso/vdso.lds.S
index 7c15b0f4ee3b..c29ef12a63bb 100644
--- a/arch/riscv/kernel/vdso/vdso.lds.S
+++ b/arch/riscv/kernel/vdso/vdso.lds.S
@@ -30,7 +30,7 @@ SECTIONS
 		*(.data .data.* .gnu.linkonce.d.*)
 		*(.dynbss)
 		*(.bss .bss.* .gnu.linkonce.b.*)
-	}
+	}						:text
 
 	.note		: { *(.note.*) }		:text	:note
 
diff --git a/arch/riscv/kernel/vendor_extensions/sifive.c b/arch/riscv/kernel/vendor_extensions/sifive.c
index 1411337dc1e6..8fcf67e8c07f 100644
--- a/arch/riscv/kernel/vendor_extensions/sifive.c
+++ b/arch/riscv/kernel/vendor_extensions/sifive.c
@@ -8,7 +8,7 @@
 #include <linux/types.h>
 
 /* All SiFive vendor extensions supported in Linux */
-const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = {
+static const struct riscv_isa_ext_data riscv_isa_vendor_ext_sifive[] = {
 	__RISCV_ISA_EXT_DATA(xsfvfnrclipxfqf, RISCV_ISA_VENDOR_EXT_XSFVFNRCLIPXFQF),
 	__RISCV_ISA_EXT_DATA(xsfvfwmaccqqq, RISCV_ISA_VENDOR_EXT_XSFVFWMACCQQQ),
 	__RISCV_ISA_EXT_DATA(xsfvqmaccdod, RISCV_ISA_VENDOR_EXT_XSFVQMACCDOD),
diff --git a/arch/riscv/kvm/aia.c b/arch/riscv/kvm/aia.c
index 19afd1f23537..dad318185660 100644
--- a/arch/riscv/kvm/aia.c
+++ b/arch/riscv/kvm/aia.c
@@ -30,28 +30,6 @@ unsigned int kvm_riscv_aia_nr_hgei;
 unsigned int kvm_riscv_aia_max_ids;
 DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
 
-static int aia_find_hgei(struct kvm_vcpu *owner)
-{
-	int i, hgei;
-	unsigned long flags;
-	struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei);
-
-	raw_spin_lock_irqsave(&hgctrl->lock, flags);
-
-	hgei = -1;
-	for (i = 1; i <= kvm_riscv_aia_nr_hgei; i++) {
-		if (hgctrl->owners[i] == owner) {
-			hgei = i;
-			break;
-		}
-	}
-
-	raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
-
-	put_cpu_ptr(&aia_hgei);
-	return hgei;
-}
-
 static inline unsigned long aia_hvictl_value(bool ext_irq_pending)
 {
 	unsigned long hvictl;
@@ -95,7 +73,6 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
 
 bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 {
-	int hgei;
 	unsigned long seip;
 
 	if (!kvm_riscv_aia_available())
@@ -114,11 +91,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 	if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip)
 		return false;
 
-	hgei = aia_find_hgei(vcpu);
-	if (hgei > 0)
-		return !!(ncsr_read(CSR_HGEIP) & BIT(hgei));
-
-	return false;
+	return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu);
 }
 
 void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu)
@@ -164,6 +137,9 @@ void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu)
 		csr_write(CSR_HVIPRIO2H, csr->hviprio2h);
 #endif
 	}
+
+	if (kvm_riscv_aia_initialized(vcpu->kvm))
+		kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu);
 }
 
 void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
@@ -174,6 +150,9 @@ void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
 	if (!kvm_riscv_aia_available())
 		return;
 
+	if (kvm_riscv_aia_initialized(vcpu->kvm))
+		kvm_riscv_vcpu_aia_imsic_put(vcpu);
+
 	if (kvm_riscv_nacl_available()) {
 		nsh = nacl_shmem();
 		csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT);
@@ -472,22 +451,6 @@ void kvm_riscv_aia_free_hgei(int cpu, int hgei)
 	raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
 }
 
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable)
-{
-	int hgei;
-
-	if (!kvm_riscv_aia_available())
-		return;
-
-	hgei = aia_find_hgei(owner);
-	if (hgei > 0) {
-		if (enable)
-			csr_set(CSR_HGEIE, BIT(hgei));
-		else
-			csr_clear(CSR_HGEIE, BIT(hgei));
-	}
-}
-
 static irqreturn_t hgei_interrupt(int irq, void *dev_id)
 {
 	int i;
diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index 29ef9c2133a9..2ff865943ebb 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -676,6 +676,48 @@ static void imsic_swfile_update(struct kvm_vcpu *vcpu,
 	imsic_swfile_extirq_update(vcpu);
 }
 
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+	unsigned long flags;
+	bool ret = false;
+
+	/*
+	 * The IMSIC SW-file directly injects interrupt via hvip so
+	 * only check for interrupt when IMSIC VS-file is being used.
+	 */
+
+	read_lock_irqsave(&imsic->vsfile_lock, flags);
+	if (imsic->vsfile_cpu > -1)
+		ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+
+	return ret;
+}
+
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	/*
+	 * No need to explicitly clear HGEIE CSR bits because the
+	 * hgei interrupt handler (aka hgei_interrupt()) will always
+	 * clear it for us.
+	 */
+}
+
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu)
+{
+	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+	unsigned long flags;
+
+	if (!kvm_vcpu_is_blocking(vcpu))
+		return;
+
+	read_lock_irqsave(&imsic->vsfile_lock, flags);
+	if (imsic->vsfile_cpu > -1)
+		csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei));
+	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+}
+
 void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
@@ -781,6 +823,9 @@ int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu)
 	 * producers to the new IMSIC VS-file.
 	 */
 
+	/* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */
+	csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei));
+
 	/* Zero-out new IMSIC VS-file */
 	imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix);
 
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index e0a01af426ff..0462863206ca 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -207,16 +207,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvm_riscv_vcpu_timer_pending(vcpu);
 }
 
-void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
-{
-	kvm_riscv_aia_wakeon_hgei(vcpu, true);
-}
-
-void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
-	kvm_riscv_aia_wakeon_hgei(vcpu, false);
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&
diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 5fbf3f94f1e8..b17fad091bab 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -103,7 +103,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 		kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_FENCE_I_SENT);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA:
-		if (cp->a2 == 0 && cp->a3 == 0)
+		if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL)
 			kvm_riscv_hfence_vvma_all(vcpu->kvm, hbase, hmask);
 		else
 			kvm_riscv_hfence_vvma_gva(vcpu->kvm, hbase, hmask,
@@ -111,7 +111,7 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 		kvm_riscv_vcpu_pmu_incr_fw(vcpu, SBI_PMU_FW_HFENCE_VVMA_SENT);
 		break;
 	case SBI_EXT_RFENCE_REMOTE_SFENCE_VMA_ASID:
-		if (cp->a2 == 0 && cp->a3 == 0)
+		if ((cp->a2 == 0 && cp->a3 == 0) || cp->a3 == -1UL)
 			kvm_riscv_hfence_vvma_asid_all(vcpu->kvm,
 						       hbase, hmask, cp->a4);
 		else
@@ -127,9 +127,9 @@ static int kvm_sbi_ext_rfence_handler(struct kvm_vcpu *vcpu, struct kvm_run *run
 	case SBI_EXT_RFENCE_REMOTE_HFENCE_VVMA_ASID:
 		/*
 		 * Until nested virtualization is implemented, the
-		 * SBI HFENCE calls should be treated as NOPs
+		 * SBI HFENCE calls should return not supported
+		 * hence fallthrough.
 		 */
-		break;
 	default:
 		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 	}
diff --git a/arch/riscv/kvm/vcpu_timer.c b/arch/riscv/kvm/vcpu_timer.c
index ff672fa71fcc..85a7262115e1 100644
--- a/arch/riscv/kvm/vcpu_timer.c
+++ b/arch/riscv/kvm/vcpu_timer.c
@@ -345,8 +345,24 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
 	/*
 	 * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
 	 * upon every VM exit so no need to save here.
+	 *
+	 * If VS-timer expires when no VCPU running on a host CPU then
+	 * WFI executed by such host CPU will be effective NOP resulting
+	 * in no power savings. This is because as-per RISC-V Privileged
+	 * specificaiton: "WFI is also required to resume execution for
+	 * locally enabled interrupts pending at any privilege level,
+	 * regardless of the global interrupt enable at each privilege
+	 * level."
+	 *
+	 * To address the above issue, vstimecmp CSR must be set to -1UL
+	 * over here when VCPU is scheduled-out or exits to user space.
 	 */
 
+	csr_write(CSR_VSTIMECMP, -1UL);
+#if defined(CONFIG_32BIT)
+	csr_write(CSR_VSTIMECMPH, -1UL);
+#endif
+
 	/* timer should be enabled for the remaining operations */
 	if (unlikely(!t->init_done))
 		return;
diff --git a/arch/riscv/tools/relocs_check.sh b/arch/riscv/tools/relocs_check.sh
index baeb2e7b2290..742993e6a8cb 100755
--- a/arch/riscv/tools/relocs_check.sh
+++ b/arch/riscv/tools/relocs_check.sh
@@ -14,7 +14,9 @@ bad_relocs=$(
 ${srctree}/scripts/relocs_check.sh "$@" |
 	# These relocations are okay
 	#	R_RISCV_RELATIVE
-	grep -F -w -v 'R_RISCV_RELATIVE'
+	#	R_RISCV_NONE
+	grep -F -w -v 'R_RISCV_RELATIVE
+R_RISCV_NONE'
 )
 
 if [ -z "$bad_relocs" ]; then