Merge tag 'loongarch-kvm-6.8' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.8

1. Optimization for memslot hugepage checking.
2. Cleanup and fix some HW/SW timer issues.
3. Add LSX/LASX (128bit/256bit SIMD) support.

26 files changed, 595 insertions, 193 deletions

diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index 9eeb0c05f3f4..4ba8d67ddb09 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -68,6 +68,7 @@ LDFLAGS_vmlinux			+= -static -n -nostdlib
 ifdef CONFIG_AS_HAS_EXPLICIT_RELOCS
 cflags-y			+= $(call cc-option,-mexplicit-relocs)
 KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-mdirect-extern-access)
+KBUILD_CFLAGS_KERNEL		+= $(call cc-option,-fdirect-access-external-data)
 KBUILD_AFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
 KBUILD_CFLAGS_MODULE		+= $(call cc-option,-fno-direct-access-external-data)
 KBUILD_AFLAGS_MODULE		+= $(call cc-option,-mno-relax) $(call cc-option,-Wa$(comma)-mno-relax)
@@ -82,7 +83,7 @@ endif
 
 ifeq ($(CONFIG_RELOCATABLE),y)
 KBUILD_CFLAGS_KERNEL		+= -fPIE
-LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext
+LDFLAGS_vmlinux			+= -static -pie --no-dynamic-linker -z notext $(call ld-option, --apply-dynamic-relocs)
 endif
 
 cflags-y += $(call cc-option, -mno-check-zero-division)
@@ -142,6 +143,8 @@ vdso-install-y += arch/loongarch/vdso/vdso.so.dbg
 
 all:	$(notdir $(KBUILD_IMAGE))
 
+vmlinuz.efi: vmlinux.efi
+
 vmlinux.elf vmlinux.efi vmlinuz.efi: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(bootvars-y) $(boot)/$@
 
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index c9544f358c33..655db7d7a427 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -609,8 +609,7 @@
 	lu32i.d	\reg, 0
 	lu52i.d	\reg, \reg, 0
 	.pushsection ".la_abs", "aw", %progbits
-	768:
-	.dword	768b-766b
+	.dword	766b
 	.dword	\sym
 	.popsection
 #endif
diff --git a/arch/loongarch/include/asm/efi.h b/arch/loongarch/include/asm/efi.h
index 091897d40b03..91d81f9730ab 100644
--- a/arch/loongarch/include/asm/efi.h
+++ b/arch/loongarch/include/asm/efi.h
@@ -32,6 +32,6 @@ static inline unsigned long efi_get_kimg_min_align(void)
 
 #define EFI_KIMG_PREFERRED_ADDRESS	PHYSADDR(VMLINUX_LOAD_ADDRESS)
 
-unsigned long kernel_entry_address(void);
+unsigned long kernel_entry_address(unsigned long kernel_addr);
 
 #endif /* _ASM_LOONGARCH_EFI_H */
diff --git a/arch/loongarch/include/asm/elf.h b/arch/loongarch/include/asm/elf.h
index b9a4ab54285c..9b16a3b8e706 100644
--- a/arch/loongarch/include/asm/elf.h
+++ b/arch/loongarch/include/asm/elf.h
@@ -293,7 +293,7 @@ extern const char *__elf_platform;
 #define ELF_PLAT_INIT(_r, load_addr)	do { \
 	_r->regs[1] = _r->regs[2] = _r->regs[3] = _r->regs[4] = 0;	\
 	_r->regs[5] = _r->regs[6] = _r->regs[7] = _r->regs[8] = 0;	\
-	_r->regs[9] = _r->regs[10] = _r->regs[11] = _r->regs[12] = 0;	\
+	_r->regs[9] = _r->regs[10] /* syscall n */ = _r->regs[12] = 0;	\
 	_r->regs[13] = _r->regs[14] = _r->regs[15] = _r->regs[16] = 0;	\
 	_r->regs[17] = _r->regs[18] = _r->regs[19] = _r->regs[20] = 0;	\
 	_r->regs[21] = _r->regs[22] = _r->regs[23] = _r->regs[24] = 0;	\
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index b108301c2e5a..2d62f7b0d377 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -45,7 +45,10 @@ struct kvm_vcpu_stat {
 	u64 signal_exits;
 };
 
+#define KVM_MEM_HUGEPAGE_CAPABLE	(1UL << 0)
+#define KVM_MEM_HUGEPAGE_INCAPABLE	(1UL << 1)
 struct kvm_arch_memory_slot {
+	unsigned long flags;
 };
 
 struct kvm_context {
@@ -92,8 +95,10 @@ enum emulation_result {
 };
 
 #define KVM_LARCH_FPU		(0x1 << 0)
-#define KVM_LARCH_SWCSR_LATEST	(0x1 << 1)
-#define KVM_LARCH_HWCSR_USABLE	(0x1 << 2)
+#define KVM_LARCH_LSX		(0x1 << 1)
+#define KVM_LARCH_LASX		(0x1 << 2)
+#define KVM_LARCH_SWCSR_LATEST	(0x1 << 3)
+#define KVM_LARCH_HWCSR_USABLE	(0x1 << 4)
 
 struct kvm_vcpu_arch {
 	/*
@@ -175,6 +180,21 @@ static inline void writel_sw_gcsr(struct loongarch_csrs *csr, int reg, unsigned
 	csr->csrs[reg] = val;
 }
 
+static inline bool kvm_guest_has_fpu(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_FP;
+}
+
+static inline bool kvm_guest_has_lsx(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_LSX;
+}
+
+static inline bool kvm_guest_has_lasx(struct kvm_vcpu_arch *arch)
+{
+	return arch->cpucfg[2] & CPUCFG2_LASX;
+}
+
 /* Debug: dump vcpu state */
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
 
diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index 553cfa2b2b1c..e71ceb88f29e 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -55,7 +55,26 @@ void kvm_save_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fpu(struct loongarch_fpu *fpu);
 void kvm_restore_fcsr(struct loongarch_fpu *fpu);
 
-void kvm_acquire_timer(struct kvm_vcpu *vcpu);
+#ifdef CONFIG_CPU_HAS_LSX
+int kvm_own_lsx(struct kvm_vcpu *vcpu);
+void kvm_save_lsx(struct loongarch_fpu *fpu);
+void kvm_restore_lsx(struct loongarch_fpu *fpu);
+#else
+static inline int kvm_own_lsx(struct kvm_vcpu *vcpu) { }
+static inline void kvm_save_lsx(struct loongarch_fpu *fpu) { }
+static inline void kvm_restore_lsx(struct loongarch_fpu *fpu) { }
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+int kvm_own_lasx(struct kvm_vcpu *vcpu);
+void kvm_save_lasx(struct loongarch_fpu *fpu);
+void kvm_restore_lasx(struct loongarch_fpu *fpu);
+#else
+static inline int kvm_own_lasx(struct kvm_vcpu *vcpu) { }
+static inline void kvm_save_lasx(struct loongarch_fpu *fpu) { }
+static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
+#endif
+
 void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
 void kvm_reset_timer(struct kvm_vcpu *vcpu);
 void kvm_save_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 9b4957cefa8a..46366e783c84 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -1098,12 +1098,11 @@
 
 static __always_inline u64 drdtime(void)
 {
-	int rID = 0;
 	u64 val = 0;
 
 	__asm__ __volatile__(
-		"rdtime.d %0, %1 \n\t"
-		: "=r"(val), "=r"(rID)
+		"rdtime.d %0, $zero\n\t"
+		: "=r"(val)
 		:
 		);
 	return val;
diff --git a/arch/loongarch/include/asm/percpu.h b/arch/loongarch/include/asm/percpu.h
index ed5da02b1cf6..9b36ac003f89 100644
--- a/arch/loongarch/include/asm/percpu.h
+++ b/arch/loongarch/include/asm/percpu.h
@@ -40,13 +40,13 @@ static __always_inline unsigned long __percpu_##op(void *ptr,		\
 	switch (size) {							\
 	case 4:								\
 		__asm__ __volatile__(					\
-		"am"#asm_op".w"	" %[ret], %[val], %[ptr]	\n"		\
+		"am"#asm_op".w"	" %[ret], %[val], %[ptr]	\n"	\
 		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u32 *)ptr)		\
 		: [val] "r" (val));					\
 		break;							\
 	case 8:								\
 		__asm__ __volatile__(					\
-		"am"#asm_op".d" " %[ret], %[val], %[ptr]	\n"		\
+		"am"#asm_op".d" " %[ret], %[val], %[ptr]	\n"	\
 		: [ret] "=&r" (ret), [ptr] "+ZB"(*(u64 *)ptr)		\
 		: [val] "r" (val));					\
 		break;							\
@@ -63,7 +63,7 @@ PERCPU_OP(and, and, &)
 PERCPU_OP(or, or, |)
 #undef PERCPU_OP
 
-static __always_inline unsigned long __percpu_read(void *ptr, int size)
+static __always_inline unsigned long __percpu_read(void __percpu *ptr, int size)
 {
 	unsigned long ret;
 
@@ -100,7 +100,7 @@ static __always_inline unsigned long __percpu_read(void *ptr, int size)
 	return ret;
 }
 
-static __always_inline void __percpu_write(void *ptr, unsigned long val, int size)
+static __always_inline void __percpu_write(void __percpu *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
@@ -132,8 +132,7 @@ static __always_inline void __percpu_write(void *ptr, unsigned long val, int siz
 	}
 }
 
-static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val,
-						   int size)
+static __always_inline unsigned long __percpu_xchg(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
diff --git a/arch/loongarch/include/asm/setup.h b/arch/loongarch/include/asm/setup.h
index a0bc159ce8bd..ee52fb1e9963 100644
--- a/arch/loongarch/include/asm/setup.h
+++ b/arch/loongarch/include/asm/setup.h
@@ -25,7 +25,7 @@ extern void set_merr_handler(unsigned long offset, void *addr, unsigned long len
 #ifdef CONFIG_RELOCATABLE
 
 struct rela_la_abs {
-	long offset;
+	long pc;
 	long symvalue;
 };
 
diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h
index c6ad2ee6106c..923d0bd38294 100644
--- a/arch/loongarch/include/uapi/asm/kvm.h
+++ b/arch/loongarch/include/uapi/asm/kvm.h
@@ -79,6 +79,7 @@ struct kvm_fpu {
 #define LOONGARCH_REG_64(TYPE, REG)	(TYPE | KVM_REG_SIZE_U64 | (REG << LOONGARCH_REG_SHIFT))
 #define KVM_IOC_CSRID(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CSR, REG)
 #define KVM_IOC_CPUCFG(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG)
+#define KVM_LOONGARCH_VCPU_CPUCFG	0
 
 struct kvm_debug_exit_arch {
 };
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 4fcc168f0732..3c808c680370 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -57,7 +57,7 @@ obj-$(CONFIG_MAGIC_SYSRQ)	+= sysrq.o
 
 obj-$(CONFIG_RELOCATABLE)	+= relocate.o
 
-obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
+obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o relocate_kernel.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 
 obj-$(CONFIG_UNWINDER_GUESS)	+= unwind_guess.o
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index d53ab10f4644..4382e36ae3d4 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -349,6 +349,7 @@ SYM_FUNC_START(_restore_lsx_upper)
 	lsx_restore_all_upper a0 t0 t1
 	jr	ra
 SYM_FUNC_END(_restore_lsx_upper)
+EXPORT_SYMBOL(_restore_lsx_upper)
 
 SYM_FUNC_START(_init_lsx_upper)
 	lsx_init_all_upper t1
@@ -384,6 +385,7 @@ SYM_FUNC_START(_restore_lasx_upper)
 	lasx_restore_all_upper a0 t0 t1
 	jr	ra
 SYM_FUNC_END(_restore_lasx_upper)
+EXPORT_SYMBOL(_restore_lasx_upper)
 
 SYM_FUNC_START(_init_lasx_upper)
 	lasx_init_all_upper t1
diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c
index 6c3eff9af9fb..1acfa704c8d0 100644
--- a/arch/loongarch/kernel/relocate.c
+++ b/arch/loongarch/kernel/relocate.c
@@ -52,7 +52,7 @@ static inline void __init relocate_absolute(long random_offset)
 	for (p = begin; (void *)p < end; p++) {
 		long v = p->symvalue;
 		uint32_t lu12iw, ori, lu32id, lu52id;
-		union loongarch_instruction *insn = (void *)p - p->offset;
+		union loongarch_instruction *insn = (void *)p->pc;
 
 		lu12iw = (v >> 12) & 0xfffff;
 		ori    = v & 0xfff;
@@ -102,6 +102,14 @@ static inline __init unsigned long get_random_boot(void)
 	return hash;
 }
 
+static int __init nokaslr(char *p)
+{
+	pr_info("KASLR is disabled.\n");
+
+	return 0; /* Print a notice and silence the boot warning */
+}
+early_param("nokaslr", nokaslr);
+
 static inline __init bool kaslr_disabled(void)
 {
 	char *str;
diff --git a/arch/loongarch/kernel/stacktrace.c b/arch/loongarch/kernel/stacktrace.c
index 92270f14db94..f623feb2129f 100644
--- a/arch/loongarch/kernel/stacktrace.c
+++ b/arch/loongarch/kernel/stacktrace.c
@@ -32,7 +32,7 @@ void arch_stack_walk(stack_trace_consume_fn consume_entry, void *cookie,
 	}
 
 	for (unwind_start(&state, task, regs);
-	     !unwind_done(&state) && !unwind_error(&state); unwind_next_frame(&state)) {
+	     !unwind_done(&state); unwind_next_frame(&state)) {
 		addr = unwind_get_return_address(&state);
 		if (!addr || !consume_entry(cookie, addr))
 			break;
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index 3064af94db9c..e7015f7b70e3 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -58,14 +58,16 @@ static int constant_set_state_oneshot(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_oneshot_stopped(struct clock_event_device *evt)
+static int constant_set_state_periodic(struct clock_event_device *evt)
 {
+	unsigned long period;
 	unsigned long timer_config;
 
 	raw_spin_lock(&state_lock);
 
-	timer_config = csr_read64(LOONGARCH_CSR_TCFG);
-	timer_config &= ~CSR_TCFG_EN;
+	period = const_clock_freq / HZ;
+	timer_config = period & CSR_TCFG_VAL;
+	timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN);
 	csr_write64(timer_config, LOONGARCH_CSR_TCFG);
 
 	raw_spin_unlock(&state_lock);
@@ -73,16 +75,14 @@ static int constant_set_state_oneshot_stopped(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_periodic(struct clock_event_device *evt)
+static int constant_set_state_shutdown(struct clock_event_device *evt)
 {
-	unsigned long period;
 	unsigned long timer_config;
 
 	raw_spin_lock(&state_lock);
 
-	period = const_clock_freq / HZ;
-	timer_config = period & CSR_TCFG_VAL;
-	timer_config |= (CSR_TCFG_PERIOD | CSR_TCFG_EN);
+	timer_config = csr_read64(LOONGARCH_CSR_TCFG);
+	timer_config &= ~CSR_TCFG_EN;
 	csr_write64(timer_config, LOONGARCH_CSR_TCFG);
 
 	raw_spin_unlock(&state_lock);
@@ -90,11 +90,6 @@ static int constant_set_state_periodic(struct clock_event_device *evt)
 	return 0;
 }
 
-static int constant_set_state_shutdown(struct clock_event_device *evt)
-{
-	return 0;
-}
-
 static int constant_timer_next_event(unsigned long delta, struct clock_event_device *evt)
 {
 	unsigned long timer_config;
@@ -161,7 +156,7 @@ int constant_clockevent_init(void)
 	cd->rating = 320;
 	cd->cpumask = cpumask_of(cpu);
 	cd->set_state_oneshot = constant_set_state_oneshot;
-	cd->set_state_oneshot_stopped = constant_set_state_oneshot_stopped;
+	cd->set_state_oneshot_stopped = constant_set_state_shutdown;
 	cd->set_state_periodic = constant_set_state_periodic;
 	cd->set_state_shutdown = constant_set_state_shutdown;
 	cd->set_next_event = constant_timer_next_event;
diff --git a/arch/loongarch/kernel/unwind.c b/arch/loongarch/kernel/unwind.c
index ba324ba76fa1..a463d6961344 100644
--- a/arch/loongarch/kernel/unwind.c
+++ b/arch/loongarch/kernel/unwind.c
@@ -28,6 +28,5 @@ bool default_next_frame(struct unwind_state *state)
 
 	} while (!get_stack_info(state->sp, state->task, info));
 
-	state->error = true;
 	return false;
 }
diff --git a/arch/loongarch/kernel/unwind_prologue.c b/arch/loongarch/kernel/unwind_prologue.c
index 55afc27320e1..929ae240280a 100644
--- a/arch/loongarch/kernel/unwind_prologue.c
+++ b/arch/loongarch/kernel/unwind_prologue.c
@@ -227,7 +227,7 @@ static bool next_frame(struct unwind_state *state)
 	} while (!get_stack_info(state->sp, state->task, info));
 
 out:
-	state->error = true;
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
 }
 
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index ce8de3fa472c..ed1d89d53e2e 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -200,17 +200,8 @@ int kvm_emu_idle(struct kvm_vcpu *vcpu)
 	++vcpu->stat.idle_exits;
 	trace_kvm_exit_idle(vcpu, KVM_TRACE_EXIT_IDLE);
 
-	if (!kvm_arch_vcpu_runnable(vcpu)) {
-		/*
-		 * Switch to the software timer before halt-polling/blocking as
-		 * the guest's timer may be a break event for the vCPU, and the
-		 * hypervisor timer runs only when the CPU is in guest mode.
-		 * Switch before halt-polling so that KVM recognizes an expired
-		 * timer before blocking.
-		 */
-		kvm_save_timer(vcpu);
-		kvm_vcpu_block(vcpu);
-	}
+	if (!kvm_arch_vcpu_runnable(vcpu))
+		kvm_vcpu_halt(vcpu);
 
 	return EMULATE_DONE;
 }
@@ -643,6 +634,11 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
 {
 	struct kvm_run *run = vcpu->run;
 
+	if (!kvm_guest_has_fpu(&vcpu->arch)) {
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+		return RESUME_GUEST;
+	}
+
 	/*
 	 * If guest FPU not present, the FPU operation should have been
 	 * treated as a reserved instruction!
@@ -660,6 +656,36 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
 }
 
 /*
+ * kvm_handle_lsx_disabled() - Guest used LSX while disabled in root.
+ * @vcpu:      Virtual CPU context.
+ *
+ * Handle when the guest attempts to use LSX when it is disabled in the root
+ * context.
+ */
+static int kvm_handle_lsx_disabled(struct kvm_vcpu *vcpu)
+{
+	if (kvm_own_lsx(vcpu))
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+
+	return RESUME_GUEST;
+}
+
+/*
+ * kvm_handle_lasx_disabled() - Guest used LASX while disabled in root.
+ * @vcpu:	Virtual CPU context.
+ *
+ * Handle when the guest attempts to use LASX when it is disabled in the root
+ * context.
+ */
+static int kvm_handle_lasx_disabled(struct kvm_vcpu *vcpu)
+{
+	if (kvm_own_lasx(vcpu))
+		kvm_queue_exception(vcpu, EXCCODE_INE, 0);
+
+	return RESUME_GUEST;
+}
+
+/*
  * LoongArch KVM callback handling for unimplemented guest exiting
  */
 static int kvm_fault_ni(struct kvm_vcpu *vcpu)
@@ -687,6 +713,8 @@ static exit_handle_fn kvm_fault_tables[EXCCODE_INT_START] = {
 	[EXCCODE_TLBS]			= kvm_handle_write_fault,
 	[EXCCODE_TLBM]			= kvm_handle_write_fault,
 	[EXCCODE_FPDIS]			= kvm_handle_fpu_disabled,
+	[EXCCODE_LSXDIS]		= kvm_handle_lsx_disabled,
+	[EXCCODE_LASXDIS]		= kvm_handle_lasx_disabled,
 	[EXCCODE_GSPR]			= kvm_handle_gspr,
 };
 
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index 1c1d5199500e..86a2f2d0cb27 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -287,7 +287,6 @@ int kvm_arch_hardware_enable(void)
 	if (env & CSR_GCFG_MATC_ROOT)
 		gcfg |= CSR_GCFG_MATC_ROOT;
 
-	gcfg |= CSR_GCFG_TIT;
 	write_csr_gcfg(gcfg);
 
 	kvm_flush_tlb_all();
diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
index 80480df5f550..915f17527893 100644
--- a/arch/loongarch/kvm/mmu.c
+++ b/arch/loongarch/kvm/mmu.c
@@ -13,6 +13,16 @@
 #include <asm/tlb.h>
 #include <asm/kvm_mmu.h>
 
+static inline bool kvm_hugepage_capable(struct kvm_memory_slot *slot)
+{
+	return slot->arch.flags & KVM_MEM_HUGEPAGE_CAPABLE;
+}
+
+static inline bool kvm_hugepage_incapable(struct kvm_memory_slot *slot)
+{
+	return slot->arch.flags & KVM_MEM_HUGEPAGE_INCAPABLE;
+}
+
 static inline void kvm_ptw_prepare(struct kvm *kvm, kvm_ptw_ctx *ctx)
 {
 	ctx->level = kvm->arch.root_level;
@@ -365,6 +375,69 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 	kvm_ptw_top(kvm->arch.pgd, start << PAGE_SHIFT, end << PAGE_SHIFT, &ctx);
 }
 
+int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old,
+				   struct kvm_memory_slot *new, enum kvm_mr_change change)
+{
+	gpa_t gpa_start;
+	hva_t hva_start;
+	size_t size, gpa_offset, hva_offset;
+
+	if ((change != KVM_MR_MOVE) && (change != KVM_MR_CREATE))
+		return 0;
+	/*
+	 * Prevent userspace from creating a memory region outside of the
+	 * VM GPA address space
+	 */
+	if ((new->base_gfn + new->npages) > (kvm->arch.gpa_size >> PAGE_SHIFT))
+		return -ENOMEM;
+
+	new->arch.flags = 0;
+	size = new->npages * PAGE_SIZE;
+	gpa_start = new->base_gfn << PAGE_SHIFT;
+	hva_start = new->userspace_addr;
+	if (IS_ALIGNED(size, PMD_SIZE) && IS_ALIGNED(gpa_start, PMD_SIZE)
+			&& IS_ALIGNED(hva_start, PMD_SIZE))
+		new->arch.flags |= KVM_MEM_HUGEPAGE_CAPABLE;
+	else {
+		/*
+		 * Pages belonging to memslots that don't have the same
+		 * alignment within a PMD for userspace and GPA cannot be
+		 * mapped with PMD entries, because we'll end up mapping
+		 * the wrong pages.
+		 *
+		 * Consider a layout like the following:
+		 *
+		 *    memslot->userspace_addr:
+		 *    +-----+--------------------+--------------------+---+
+		 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
+		 *    +-----+--------------------+--------------------+---+
+		 *
+		 *    memslot->base_gfn << PAGE_SIZE:
+		 *      +---+--------------------+--------------------+-----+
+		 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
+		 *      +---+--------------------+--------------------+-----+
+		 *
+		 * If we create those stage-2 blocks, we'll end up with this
+		 * incorrect mapping:
+		 *   d -> f
+		 *   e -> g
+		 *   f -> h
+		 */
+		gpa_offset = gpa_start & (PMD_SIZE - 1);
+		hva_offset = hva_start & (PMD_SIZE - 1);
+		if (gpa_offset != hva_offset) {
+			new->arch.flags |= KVM_MEM_HUGEPAGE_INCAPABLE;
+		} else {
+			if (gpa_offset == 0)
+				gpa_offset = PMD_SIZE;
+			if ((size + gpa_offset) < (PMD_SIZE * 2))
+				new->arch.flags |= KVM_MEM_HUGEPAGE_INCAPABLE;
+		}
+	}
+
+	return 0;
+}
+
 void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   struct kvm_memory_slot *old,
 				   const struct kvm_memory_slot *new,
@@ -562,47 +635,23 @@ out:
 }
 
 static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
-				unsigned long hva, unsigned long map_size, bool write)
+				unsigned long hva, bool write)
 {
-	size_t size;
-	gpa_t gpa_start;
-	hva_t uaddr_start, uaddr_end;
+	hva_t start, end;
 
 	/* Disable dirty logging on HugePages */
 	if (kvm_slot_dirty_track_enabled(memslot) && write)
 		return false;
 
-	size = memslot->npages * PAGE_SIZE;
-	gpa_start = memslot->base_gfn << PAGE_SHIFT;
-	uaddr_start = memslot->userspace_addr;
-	uaddr_end = uaddr_start + size;
+	if (kvm_hugepage_capable(memslot))
+		return true;
 
-	/*
-	 * Pages belonging to memslots that don't have the same alignment
-	 * within a PMD for userspace and GPA cannot be mapped with stage-2
-	 * PMD entries, because we'll end up mapping the wrong pages.
-	 *
-	 * Consider a layout like the following:
-	 *
-	 *    memslot->userspace_addr:
-	 *    +-----+--------------------+--------------------+---+
-	 *    |abcde|fgh  Stage-1 block  |    Stage-1 block tv|xyz|
-	 *    +-----+--------------------+--------------------+---+
-	 *
-	 *    memslot->base_gfn << PAGE_SIZE:
-	 *      +---+--------------------+--------------------+-----+
-	 *      |abc|def  Stage-2 block  |    Stage-2 block   |tvxyz|
-	 *      +---+--------------------+--------------------+-----+
-	 *
-	 * If we create those stage-2 blocks, we'll end up with this incorrect
-	 * mapping:
-	 *   d -> f
-	 *   e -> g
-	 *   f -> h
-	 */
-	if ((gpa_start & (map_size - 1)) != (uaddr_start & (map_size - 1)))
+	if (kvm_hugepage_incapable(memslot))
 		return false;
 
+	start = memslot->userspace_addr;
+	end = start + memslot->npages * PAGE_SIZE;
+
 	/*
 	 * Next, let's make sure we're not trying to map anything not covered
 	 * by the memslot. This means we have to prohibit block size mappings
@@ -615,8 +664,7 @@ static bool fault_supports_huge_mapping(struct kvm_memory_slot *memslot,
 	 * userspace_addr or the base_gfn, as both are equally aligned (per
 	 * the check above) and equally sized.
 	 */
-	return (hva & ~(map_size - 1)) >= uaddr_start &&
-		(hva & ~(map_size - 1)) + map_size <= uaddr_end;
+	return (hva >= ALIGN(start, PMD_SIZE)) && (hva < ALIGN_DOWN(end, PMD_SIZE));
 }
 
 /*
@@ -842,7 +890,7 @@ retry:
 
 	/* Disable dirty logging on HugePages */
 	level = 0;
-	if (!fault_supports_huge_mapping(memslot, hva, PMD_SIZE, write)) {
+	if (!fault_supports_huge_mapping(memslot, hva, write)) {
 		level = 0;
 	} else {
 		level = host_pfn_mapping_level(kvm, gfn, memslot);
@@ -901,12 +949,6 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
 {
 }
 
-int kvm_arch_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old,
-				   struct kvm_memory_slot *new, enum kvm_mr_change change)
-{
-	return 0;
-}
-
 void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
 					const struct kvm_memory_slot *memslot)
 {
diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
index 0ed9040307b7..ba976509bfe8 100644
--- a/arch/loongarch/kvm/switch.S
+++ b/arch/loongarch/kvm/switch.S
@@ -245,6 +245,37 @@ SYM_FUNC_START(kvm_restore_fpu)
 	jr                 ra
 SYM_FUNC_END(kvm_restore_fpu)
 
+#ifdef CONFIG_CPU_HAS_LSX
+SYM_FUNC_START(kvm_save_lsx)
+	fpu_save_csr    a0 t1
+	fpu_save_cc     a0 t1 t2
+	lsx_save_data   a0 t1
+	jr              ra
+SYM_FUNC_END(kvm_save_lsx)
+
+SYM_FUNC_START(kvm_restore_lsx)
+	lsx_restore_data a0 t1
+	fpu_restore_cc   a0 t1 t2
+	fpu_restore_csr  a0 t1 t2
+	jr               ra
+SYM_FUNC_END(kvm_restore_lsx)
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+SYM_FUNC_START(kvm_save_lasx)
+	fpu_save_csr    a0 t1
+	fpu_save_cc     a0 t1 t2
+	lasx_save_data  a0 t1
+	jr              ra
+SYM_FUNC_END(kvm_save_lasx)
+
+SYM_FUNC_START(kvm_restore_lasx)
+	lasx_restore_data a0 t1
+	fpu_restore_cc    a0 t1 t2
+	fpu_restore_csr   a0 t1 t2
+	jr                ra
+SYM_FUNC_END(kvm_restore_lasx)
+#endif
 	.section ".rodata"
 SYM_DATA(kvm_exception_size, .quad kvm_exc_entry_end - kvm_exc_entry)
 SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)
diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
index 284bf553fefe..111328f60872 100644
--- a/arch/loongarch/kvm/timer.c
+++ b/arch/loongarch/kvm/timer.c
@@ -65,40 +65,23 @@ void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long timer_hz)
 }
 
 /*
- * Restore hard timer state and enable guest to access timer registers
- * without trap, should be called with irq disabled
- */
-void kvm_acquire_timer(struct kvm_vcpu *vcpu)
-{
-	unsigned long cfg;
-
-	cfg = read_csr_gcfg();
-	if (!(cfg & CSR_GCFG_TIT))
-		return;
-
-	/* Enable guest access to hard timer */
-	write_csr_gcfg(cfg & ~CSR_GCFG_TIT);
-
-	/*
-	 * Freeze the soft-timer and sync the guest stable timer with it. We do
-	 * this with interrupts disabled to avoid latency.
-	 */
-	hrtimer_cancel(&vcpu->arch.swtimer);
-}
-
-/*
  * Restore soft timer state from saved context.
  */
 void kvm_restore_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long cfg, delta, period;
+	unsigned long cfg, estat;
+	unsigned long ticks, delta, period;
 	ktime_t expire, now;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
 	/*
 	 * Set guest stable timer cfg csr
+	 * Disable timer before restore estat CSR register, avoid to
+	 * get invalid timer interrupt for old timer cfg
 	 */
 	cfg = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG);
+
+	write_gcsr_timercfg(0);
 	kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
 	kvm_restore_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
 	if (!(cfg & CSR_TCFG_EN)) {
@@ -108,23 +91,55 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
 	}
 
 	/*
+	 * Freeze the soft-timer and sync the guest stable timer with it.
+	 */
+	hrtimer_cancel(&vcpu->arch.swtimer);
+
+	/*
+	 * From LoongArch Reference Manual Volume 1 Chapter 7.6.2
+	 * If oneshot timer is fired, CSR TVAL will be -1, there are two
+	 * conditions:
+	 *  1) timer is fired during exiting to host
+	 *  2) timer is fired and vm is doing timer irq, and then exiting to
+	 *     host. Host should not inject timer irq to avoid spurious
+	 *     timer interrupt again
+	 */
+	ticks = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TVAL);
+	estat = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_ESTAT);
+	if (!(cfg & CSR_TCFG_PERIOD) && (ticks > cfg)) {
+		/*
+		 * Writing 0 to LOONGARCH_CSR_TVAL will inject timer irq
+		 * and set CSR TVAL with -1
+		 */
+		write_gcsr_timertick(0);
+
+		/*
+		 * Writing CSR_TINTCLR_TI to LOONGARCH_CSR_TINTCLR will clear
+		 * timer interrupt, and CSR TVAL keeps unchanged with -1, it
+		 * avoids spurious timer interrupt
+		 */
+		if (!(estat & CPU_TIMER))
+			gcsr_write(CSR_TINTCLR_TI, LOONGARCH_CSR_TINTCLR);
+		return;
+	}
+
+	/*
 	 * Set remainder tick value if not expired
 	 */
+	delta = 0;
 	now = ktime_get();
 	expire = vcpu->arch.expire;
 	if (ktime_before(now, expire))
 		delta = ktime_to_tick(vcpu, ktime_sub(expire, now));
-	else {
-		if (cfg & CSR_TCFG_PERIOD) {
-			period = cfg & CSR_TCFG_VAL;
-			delta = ktime_to_tick(vcpu, ktime_sub(now, expire));
-			delta = period - (delta % period);
-		} else
-			delta = 0;
+	else if (cfg & CSR_TCFG_PERIOD) {
+		period = cfg & CSR_TCFG_VAL;
+		delta = ktime_to_tick(vcpu, ktime_sub(now, expire));
+		delta = period - (delta % period);
+
 		/*
 		 * Inject timer here though sw timer should inject timer
 		 * interrupt async already, since sw timer may be cancelled
-		 * during injecting intr async in function kvm_acquire_timer
+		 * during injecting intr async
 		 */
 		kvm_queue_irq(vcpu, INT_TI);
 	}
@@ -139,27 +154,41 @@ void kvm_restore_timer(struct kvm_vcpu *vcpu)
  */
 static void _kvm_save_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long ticks, delta;
+	unsigned long ticks, delta, cfg;
 	ktime_t expire;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
+	cfg = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG);
 	ticks = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TVAL);
-	delta = tick_to_ns(vcpu, ticks);
-	expire = ktime_add_ns(ktime_get(), delta);
-	vcpu->arch.expire = expire;
-	if (ticks) {
+
+	/*
+	 * From LoongArch Reference Manual Volume 1 Chapter 7.6.2
+	 * If period timer is fired, CSR TVAL will be reloaded from CSR TCFG
+	 * If oneshot timer is fired, CSR TVAL will be -1
+	 * Here judge one-shot timer fired by checking whether TVAL is larger
+	 * than TCFG
+	 */
+	if (ticks < cfg) {
+		delta = tick_to_ns(vcpu, ticks);
+		expire = ktime_add_ns(ktime_get(), delta);
+		vcpu->arch.expire = expire;
+
 		/*
-		 * Update hrtimer to use new timeout
 		 * HRTIMER_MODE_PINNED is suggested since vcpu may run in
 		 * the same physical cpu in next time
 		 */
-		hrtimer_cancel(&vcpu->arch.swtimer);
 		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
-	} else
+	} else if (vcpu->stat.generic.blocking) {
 		/*
-		 * Inject timer interrupt so that hall polling can dectect and exit
+		 * Inject timer interrupt so that halt polling can dectect and exit.
+		 * VCPU is scheduled out already and sleeps in rcuwait queue and
+		 * will not poll pending events again. kvm_queue_irq() is not enough,
+		 * hrtimer swtimer should be used here.
 		 */
-		kvm_queue_irq(vcpu, INT_TI);
+		expire = ktime_add_ns(ktime_get(), 10);
+		vcpu->arch.expire = expire;
+		hrtimer_start(&vcpu->arch.swtimer, expire, HRTIMER_MODE_ABS_PINNED);
+	}
 }
 
 /*
@@ -168,21 +197,15 @@ static void _kvm_save_timer(struct kvm_vcpu *vcpu)
  */
 void kvm_save_timer(struct kvm_vcpu *vcpu)
 {
-	unsigned long cfg;
 	struct loongarch_csrs *csr = vcpu->arch.csr;
 
 	preempt_disable();
-	cfg = read_csr_gcfg();
-	if (!(cfg & CSR_GCFG_TIT)) {
-		/* Disable guest use of hard timer */
-		write_csr_gcfg(cfg | CSR_GCFG_TIT);
-
-		/* Save hard timer state */
-		kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
-		kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TVAL);
-		if (kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG) & CSR_TCFG_EN)
-			_kvm_save_timer(vcpu);
-	}
+
+	/* Save hard timer state */
+	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TCFG);
+	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_TVAL);
+	if (kvm_read_sw_gcsr(csr, LOONGARCH_CSR_TCFG) & CSR_TCFG_EN)
+		_kvm_save_timer(vcpu);
 
 	/* Save timer-related state to vCPU context */
 	kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
diff --git a/arch/loongarch/kvm/trace.h b/arch/loongarch/kvm/trace.h
index a1e35d655418..c2484ad4cffa 100644
--- a/arch/loongarch/kvm/trace.h
+++ b/arch/loongarch/kvm/trace.h
@@ -102,6 +102,8 @@ TRACE_EVENT(kvm_exit_gspr,
 #define KVM_TRACE_AUX_DISCARD		4
 
 #define KVM_TRACE_AUX_FPU		1
+#define KVM_TRACE_AUX_LSX		2
+#define KVM_TRACE_AUX_LASX		3
 
 #define kvm_trace_symbol_aux_op				\
 	{ KVM_TRACE_AUX_SAVE,		"save" },	\
@@ -111,7 +113,9 @@ TRACE_EVENT(kvm_exit_gspr,
 	{ KVM_TRACE_AUX_DISCARD,	"discard" }
 
 #define kvm_trace_symbol_aux_state			\
-	{ KVM_TRACE_AUX_FPU,     "FPU" }
+	{ KVM_TRACE_AUX_FPU,     "FPU" },		\
+	{ KVM_TRACE_AUX_LSX,     "LSX" },		\
+	{ KVM_TRACE_AUX_LASX,    "LASX" }
 
 TRACE_EVENT(kvm_aux,
 	    TP_PROTO(struct kvm_vcpu *vcpu, unsigned int op,
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 73d0c2b9c1a5..27701991886d 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -95,7 +95,6 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
 		 * check vmid before vcpu enter guest
 		 */
 		local_irq_disable();
-		kvm_acquire_timer(vcpu);
 		kvm_deliver_intr(vcpu);
 		kvm_deliver_exception(vcpu);
 		/* Make sure the vcpu mode has been written */
@@ -187,8 +186,15 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 {
-	return kvm_pending_timer(vcpu) ||
+	int ret;
+
+	/* Protect from TOD sync and vcpu_load/put() */
+	preempt_disable();
+	ret = kvm_pending_timer(vcpu) ||
 		kvm_read_hw_gcsr(LOONGARCH_CSR_ESTAT) & (1 << INT_TI);
+	preempt_enable();
+
+	return ret;
 }
 
 int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu)
@@ -244,23 +250,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
-/**
- * kvm_migrate_count() - Migrate timer.
- * @vcpu:       Virtual CPU.
- *
- * Migrate hrtimer to the current CPU by cancelling and restarting it
- * if the hrtimer is active.
- *
- * Must be called when the vCPU is migrated to a different CPU, so that
- * the timer can interrupt the guest at the new CPU, and the timer irq can
- * be delivered to the vCPU.
- */
-static void kvm_migrate_count(struct kvm_vcpu *vcpu)
-{
-	if (hrtimer_cancel(&vcpu->arch.swtimer))
-		hrtimer_restart(&vcpu->arch.swtimer);
-}
-
 static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val)
 {
 	unsigned long gintc;
@@ -309,6 +298,76 @@ static int _kvm_setcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 val)
 	return ret;
 }
 
+static int _kvm_get_cpucfg(int id, u64 *v)
+{
+	int ret = 0;
+
+	if (id < 0 && id >= KVM_MAX_CPUCFG_REGS)
+		return -EINVAL;
+
+	switch (id) {
+	case 2:
+		/* Return CPUCFG2 features which have been supported by KVM */
+		*v = CPUCFG2_FP     | CPUCFG2_FPSP  | CPUCFG2_FPDP     |
+		     CPUCFG2_FPVERS | CPUCFG2_LLFTP | CPUCFG2_LLFTPREV |
+		     CPUCFG2_LAM;
+		/*
+		 * If LSX is supported by CPU, it is also supported by KVM,
+		 * as we implement it.
+		 */
+		if (cpu_has_lsx)
+			*v |= CPUCFG2_LSX;
+		/*
+		 * if LASX is supported by CPU, it is also supported by KVM,
+		 * as we implement it.
+		 */
+		if (cpu_has_lasx)
+			*v |= CPUCFG2_LASX;
+
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+static int kvm_check_cpucfg(int id, u64 val)
+{
+	u64 mask;
+	int ret = 0;
+
+	if (id < 0 && id >= KVM_MAX_CPUCFG_REGS)
+		return -EINVAL;
+
+	if (_kvm_get_cpucfg(id, &mask))
+		return ret;
+
+	switch (id) {
+	case 2:
+		/* CPUCFG2 features checking */
+		if (val & ~mask)
+			/* The unsupported features should not be set */
+			ret = -EINVAL;
+		else if (!(val & CPUCFG2_LLFTP))
+			/* The LLFTP must be set, as guest must has a constant timer */
+			ret = -EINVAL;
+		else if ((val & CPUCFG2_FP) && (!(val & CPUCFG2_FPSP) || !(val & CPUCFG2_FPDP)))
+			/* Single and double float point must both be set when enable FP */
+			ret = -EINVAL;
+		else if ((val & CPUCFG2_LSX) && !(val & CPUCFG2_FP))
+			/* FP should be set when enable LSX */
+			ret = -EINVAL;
+		else if ((val & CPUCFG2_LASX) && !(val & CPUCFG2_LSX))
+			/* LSX, FP should be set when enable LASX, and FP has been checked before. */
+			ret = -EINVAL;
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
 static int kvm_get_one_reg(struct kvm_vcpu *vcpu,
 		const struct kvm_one_reg *reg, u64 *v)
 {
@@ -378,10 +437,10 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
 		break;
 	case KVM_REG_LOONGARCH_CPUCFG:
 		id = KVM_GET_IOC_CPUCFG_IDX(reg->id);
-		if (id >= 0 && id < KVM_MAX_CPUCFG_REGS)
-			vcpu->arch.cpucfg[id] = (u32)v;
-		else
-			ret = -EINVAL;
+		ret = kvm_check_cpucfg(id, v);
+		if (ret)
+			break;
+		vcpu->arch.cpucfg[id] = (u32)v;
 		break;
 	case KVM_REG_LOONGARCH_KVM:
 		switch (reg->id) {
@@ -471,10 +530,94 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 	return -EINVAL;
 }
 
+static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	switch (attr->attr) {
+	case 2:
+		return 0;
+	default:
+		return -ENXIO;
+	}
+
+	return -ENXIO;
+}
+
+static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_cpucfg_has_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	int ret = 0;
+	uint64_t val;
+	uint64_t __user *uaddr = (uint64_t __user *)attr->addr;
+
+	ret = _kvm_get_cpucfg(attr->attr, &val);
+	if (ret)
+		return ret;
+
+	put_user(val, uaddr);
+
+	return ret;
+}
+
+static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_get_cpucfg_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	return -ENXIO;
+}
+
+static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu,
+				       struct kvm_device_attr *attr)
+{
+	int ret = -ENXIO;
+
+	switch (attr->group) {
+	case KVM_LOONGARCH_VCPU_CPUCFG:
+		ret = kvm_loongarch_cpucfg_set_attr(vcpu, attr);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
 	long r;
+	struct kvm_device_attr attr;
 	void __user *argp = (void __user *)arg;
 	struct kvm_vcpu *vcpu = filp->private_data;
 
@@ -514,6 +657,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_enable_cap(vcpu, &cap);
 		break;
 	}
+	case KVM_HAS_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_has_attr(vcpu, &attr);
+		break;
+	}
+	case KVM_GET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_get_attr(vcpu, &attr);
+		break;
+	}
+	case KVM_SET_DEVICE_ATTR: {
+		r = -EFAULT;
+		if (copy_from_user(&attr, argp, sizeof(attr)))
+			break;
+		r = kvm_loongarch_vcpu_set_attr(vcpu, &attr);
+		break;
+	}
 	default:
 		r = -ENOIOCTLCMD;
 		break;
@@ -561,12 +725,96 @@ void kvm_own_fpu(struct kvm_vcpu *vcpu)
 	preempt_enable();
 }
 
+#ifdef CONFIG_CPU_HAS_LSX
+/* Enable LSX and restore context */
+int kvm_own_lsx(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_guest_has_fpu(&vcpu->arch) || !kvm_guest_has_lsx(&vcpu->arch))
+		return -EINVAL;
+
+	preempt_disable();
+
+	/* Enable LSX for guest */
+	set_csr_euen(CSR_EUEN_LSXEN | CSR_EUEN_FPEN);
+	switch (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
+	case KVM_LARCH_FPU:
+		/*
+		 * Guest FPU state already loaded,
+		 * only restore upper LSX state
+		 */
+		_restore_lsx_upper(&vcpu->arch.fpu);
+		break;
+	default:
+		/* Neither FP or LSX already active,
+		 * restore full LSX state
+		 */
+		kvm_restore_lsx(&vcpu->arch.fpu);
+		break;
+	}
+
+	trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_LSX);
+	vcpu->arch.aux_inuse |= KVM_LARCH_LSX | KVM_LARCH_FPU;
+	preempt_enable();
+
+	return 0;
+}
+#endif
+
+#ifdef CONFIG_CPU_HAS_LASX
+/* Enable LASX and restore context */
+int kvm_own_lasx(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_guest_has_fpu(&vcpu->arch) || !kvm_guest_has_lsx(&vcpu->arch) || !kvm_guest_has_lasx(&vcpu->arch))
+		return -EINVAL;
+
+	preempt_disable();
+
+	set_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN | CSR_EUEN_LASXEN);
+	switch (vcpu->arch.aux_inuse & (KVM_LARCH_FPU | KVM_LARCH_LSX)) {
+	case KVM_LARCH_LSX:
+	case KVM_LARCH_LSX | KVM_LARCH_FPU:
+		/* Guest LSX state already loaded, only restore upper LASX state */
+		_restore_lasx_upper(&vcpu->arch.fpu);
+		break;
+	case KVM_LARCH_FPU:
+		/* Guest FP state already loaded, only restore upper LSX & LASX state */
+		_restore_lsx_upper(&vcpu->arch.fpu);
+		_restore_lasx_upper(&vcpu->arch.fpu);
+		break;
+	default:
+		/* Neither FP or LSX already active, restore full LASX state */
+		kvm_restore_lasx(&vcpu->arch.fpu);
+		break;
+	}
+
+	trace_kvm_aux(vcpu, KVM_TRACE_AUX_RESTORE, KVM_TRACE_AUX_LASX);
+	vcpu->arch.aux_inuse |= KVM_LARCH_LASX | KVM_LARCH_LSX | KVM_LARCH_FPU;
+	preempt_enable();
+
+	return 0;
+}
+#endif
+
 /* Save context and disable FPU */
 void kvm_lose_fpu(struct kvm_vcpu *vcpu)
 {
 	preempt_disable();
 
-	if (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
+	if (vcpu->arch.aux_inuse & KVM_LARCH_LASX) {
+		kvm_save_lasx(&vcpu->arch.fpu);
+		vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU | KVM_LARCH_LASX);
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_LASX);
+
+		/* Disable LASX & LSX & FPU */
+		clear_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN | CSR_EUEN_LASXEN);
+	} else if (vcpu->arch.aux_inuse & KVM_LARCH_LSX) {
+		kvm_save_lsx(&vcpu->arch.fpu);
+		vcpu->arch.aux_inuse &= ~(KVM_LARCH_LSX | KVM_LARCH_FPU);
+		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_LSX);
+
+		/* Disable LSX & FPU */
+		clear_csr_euen(CSR_EUEN_FPEN | CSR_EUEN_LSXEN);
+	} else if (vcpu->arch.aux_inuse & KVM_LARCH_FPU) {
 		kvm_save_fpu(&vcpu->arch.fpu);
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_FPU;
 		trace_kvm_aux(vcpu, KVM_TRACE_AUX_SAVE, KVM_TRACE_AUX_FPU);
@@ -789,17 +1037,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	if (vcpu->arch.last_sched_cpu != cpu) {
-		kvm_debug("[%d->%d]KVM vCPU[%d] switch\n",
-				vcpu->arch.last_sched_cpu, cpu, vcpu->vcpu_id);
-		/*
-		 * Migrate the timer interrupt to the current CPU so that it
-		 * always interrupts the guest and synchronously triggers a
-		 * guest timer interrupt.
-		 */
-		kvm_migrate_count(vcpu);
-	}
-
 	/* Restore guest state to registers */
 	_kvm_vcpu_load(vcpu, cpu);
 	local_irq_restore(flags);
diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
index 71d0539e2d0b..2aae72e63871 100644
--- a/arch/loongarch/mm/pgtable.c
+++ b/arch/loongarch/mm/pgtable.c
@@ -13,13 +13,13 @@ struct page *dmw_virt_to_page(unsigned long kaddr)
 {
 	return pfn_to_page(virt_to_pfn(kaddr));
 }
-EXPORT_SYMBOL_GPL(dmw_virt_to_page);
+EXPORT_SYMBOL(dmw_virt_to_page);
 
 struct page *tlb_virt_to_page(unsigned long kaddr)
 {
 	return pfn_to_page(pte_pfn(*virt_to_kpte(kaddr)));
 }
-EXPORT_SYMBOL_GPL(tlb_virt_to_page);
+EXPORT_SYMBOL(tlb_virt_to_page);
 
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
diff --git a/arch/loongarch/net/bpf_jit.c b/arch/loongarch/net/bpf_jit.c
index 169ff8b3915e..4fcd6cd6da23 100644
--- a/arch/loongarch/net/bpf_jit.c
+++ b/arch/loongarch/net/bpf_jit.c
@@ -480,10 +480,12 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 		case 8:
 			move_reg(ctx, t1, src);
 			emit_insn(ctx, extwb, dst, t1);
+			emit_zext_32(ctx, dst, is32);
 			break;
 		case 16:
 			move_reg(ctx, t1, src);
 			emit_insn(ctx, extwh, dst, t1);
+			emit_zext_32(ctx, dst, is32);
 			break;
 		case 32:
 			emit_insn(ctx, addw, dst, src, LOONGARCH_GPR_ZERO);
@@ -772,8 +774,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 			break;
 		case 32:
 			emit_insn(ctx, revb2w, dst, dst);
-			/* zero-extend 32 bits into 64 bits */
-			emit_zext_32(ctx, dst, is32);
+			/* clear the upper 32 bits */
+			emit_zext_32(ctx, dst, true);
 			break;
 		case 64:
 			emit_insn(ctx, revbd, dst, dst);
@@ -911,8 +913,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 
 	/* function return */
 	case BPF_JMP | BPF_EXIT:
-		emit_sext_32(ctx, regmap[BPF_REG_0], true);
-
 		if (i == ctx->prog->len - 1)
 			break;
 
@@ -988,14 +988,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx, bool ext
 			}
 			break;
 		case BPF_DW:
-			if (is_signed_imm12(off)) {
-				emit_insn(ctx, ldd, dst, src, off);
-			} else if (is_signed_imm14(off)) {
-				emit_insn(ctx, ldptrd, dst, src, off);
-			} else {
-				move_imm(ctx, t1, off, is32);
-				emit_insn(ctx, ldxd, dst, src, t1);
-			}
+			move_imm(ctx, t1, off, is32);
+			emit_insn(ctx, ldxd, dst, src, t1);
 			break;
 		}