Merging upstream version 6.7.7.

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

13 files changed, 831 insertions, 48 deletions

diff --git a/arch/loongarch/include/asm/acpi.h b/arch/loongarch/include/asm/acpi.h
index 8de6c4b83a..49e29b2999 100644
--- a/arch/loongarch/include/asm/acpi.h
+++ b/arch/loongarch/include/asm/acpi.h
@@ -32,8 +32,10 @@ static inline bool acpi_has_cpu_in_madt(void)
 	return true;
 }
 
+#define MAX_CORE_PIC 256
+
 extern struct list_head acpi_wakeup_device_list;
-extern struct acpi_madt_core_pic acpi_core_pic[NR_CPUS];
+extern struct acpi_madt_core_pic acpi_core_pic[MAX_CORE_PIC];
 
 extern int __init parse_acpi_topology(void);
 
diff --git a/arch/loongarch/include/asm/atomic.h b/arch/loongarch/include/asm/atomic.h
index e27f0c72d3..99af8b3160 100644
--- a/arch/loongarch/include/asm/atomic.h
+++ b/arch/loongarch/include/asm/atomic.h
@@ -36,19 +36,19 @@
 static inline void arch_atomic_##op(int i, atomic_t *v)			\
 {									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.w" " $zero, %1, %0	\n"			\
+	"am"#asm_op".w" " $zero, %1, %0	\n"				\
 	: "+ZB" (v->counter)						\
 	: "r" (I)							\
 	: "memory");							\
 }
 
-#define ATOMIC_OP_RETURN(op, I, asm_op, c_op)				\
-static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v)	\
+#define ATOMIC_OP_RETURN(op, I, asm_op, c_op, mb, suffix)		\
+static inline int arch_atomic_##op##_return##suffix(int i, atomic_t *v)	\
 {									\
 	int result;							\
 									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.w" " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".w" " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)				\
 	: "r" (I)							\
 	: "memory");							\
@@ -56,13 +56,13 @@ static inline int arch_atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 	return result c_op I;						\
 }
 
-#define ATOMIC_FETCH_OP(op, I, asm_op)					\
-static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
+#define ATOMIC_FETCH_OP(op, I, asm_op, mb, suffix)			\
+static inline int arch_atomic_fetch_##op##suffix(int i, atomic_t *v)	\
 {									\
 	int result;							\
 									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.w" " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".w" " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)				\
 	: "r" (I)							\
 	: "memory");							\
@@ -72,29 +72,53 @@ static inline int arch_atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 
 #define ATOMIC_OPS(op, I, asm_op, c_op)					\
 	ATOMIC_OP(op, I, asm_op)					\
-	ATOMIC_OP_RETURN(op, I, asm_op, c_op)				\
-	ATOMIC_FETCH_OP(op, I, asm_op)
+	ATOMIC_OP_RETURN(op, I, asm_op, c_op, _db,         )		\
+	ATOMIC_OP_RETURN(op, I, asm_op, c_op,    , _relaxed)		\
+	ATOMIC_FETCH_OP(op, I, asm_op, _db,         )			\
+	ATOMIC_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC_OPS(add, i, add, +)
 ATOMIC_OPS(sub, -i, add, +)
 
+#define arch_atomic_add_return		arch_atomic_add_return
+#define arch_atomic_add_return_acquire	arch_atomic_add_return
+#define arch_atomic_add_return_release	arch_atomic_add_return
 #define arch_atomic_add_return_relaxed	arch_atomic_add_return_relaxed
+#define arch_atomic_sub_return		arch_atomic_sub_return
+#define arch_atomic_sub_return_acquire	arch_atomic_sub_return
+#define arch_atomic_sub_return_release	arch_atomic_sub_return
 #define arch_atomic_sub_return_relaxed	arch_atomic_sub_return_relaxed
+#define arch_atomic_fetch_add		arch_atomic_fetch_add
+#define arch_atomic_fetch_add_acquire	arch_atomic_fetch_add
+#define arch_atomic_fetch_add_release	arch_atomic_fetch_add
 #define arch_atomic_fetch_add_relaxed	arch_atomic_fetch_add_relaxed
+#define arch_atomic_fetch_sub		arch_atomic_fetch_sub
+#define arch_atomic_fetch_sub_acquire	arch_atomic_fetch_sub
+#define arch_atomic_fetch_sub_release	arch_atomic_fetch_sub
 #define arch_atomic_fetch_sub_relaxed	arch_atomic_fetch_sub_relaxed
 
 #undef ATOMIC_OPS
 
 #define ATOMIC_OPS(op, I, asm_op)					\
 	ATOMIC_OP(op, I, asm_op)					\
-	ATOMIC_FETCH_OP(op, I, asm_op)
+	ATOMIC_FETCH_OP(op, I, asm_op, _db,         )			\
+	ATOMIC_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC_OPS(and, i, and)
 ATOMIC_OPS(or, i, or)
 ATOMIC_OPS(xor, i, xor)
 
+#define arch_atomic_fetch_and		arch_atomic_fetch_and
+#define arch_atomic_fetch_and_acquire	arch_atomic_fetch_and
+#define arch_atomic_fetch_and_release	arch_atomic_fetch_and
 #define arch_atomic_fetch_and_relaxed	arch_atomic_fetch_and_relaxed
+#define arch_atomic_fetch_or		arch_atomic_fetch_or
+#define arch_atomic_fetch_or_acquire	arch_atomic_fetch_or
+#define arch_atomic_fetch_or_release	arch_atomic_fetch_or
 #define arch_atomic_fetch_or_relaxed	arch_atomic_fetch_or_relaxed
+#define arch_atomic_fetch_xor		arch_atomic_fetch_xor
+#define arch_atomic_fetch_xor_acquire	arch_atomic_fetch_xor
+#define arch_atomic_fetch_xor_release	arch_atomic_fetch_xor
 #define arch_atomic_fetch_xor_relaxed	arch_atomic_fetch_xor_relaxed
 
 #undef ATOMIC_OPS
@@ -172,18 +196,18 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 static inline void arch_atomic64_##op(long i, atomic64_t *v)		\
 {									\
 	__asm__ __volatile__(						\
-	"am"#asm_op"_db.d " " $zero, %1, %0	\n"			\
+	"am"#asm_op".d " " $zero, %1, %0	\n"			\
 	: "+ZB" (v->counter)						\
 	: "r" (I)							\
 	: "memory");							\
 }
 
-#define ATOMIC64_OP_RETURN(op, I, asm_op, c_op)					\
-static inline long arch_atomic64_##op##_return_relaxed(long i, atomic64_t *v)	\
+#define ATOMIC64_OP_RETURN(op, I, asm_op, c_op, mb, suffix)			\
+static inline long arch_atomic64_##op##_return##suffix(long i, atomic64_t *v)	\
 {										\
 	long result;								\
 	__asm__ __volatile__(							\
-	"am"#asm_op"_db.d " " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".d " " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)					\
 	: "r" (I)								\
 	: "memory");								\
@@ -191,13 +215,13 @@ static inline long arch_atomic64_##op##_return_relaxed(long i, atomic64_t *v)	\
 	return result c_op I;							\
 }
 
-#define ATOMIC64_FETCH_OP(op, I, asm_op)					\
-static inline long arch_atomic64_fetch_##op##_relaxed(long i, atomic64_t *v)	\
+#define ATOMIC64_FETCH_OP(op, I, asm_op, mb, suffix)				\
+static inline long arch_atomic64_fetch_##op##suffix(long i, atomic64_t *v)	\
 {										\
 	long result;								\
 										\
 	__asm__ __volatile__(							\
-	"am"#asm_op"_db.d " " %1, %2, %0		\n"			\
+	"am"#asm_op#mb".d " " %1, %2, %0		\n"			\
 	: "+ZB" (v->counter), "=&r" (result)					\
 	: "r" (I)								\
 	: "memory");								\
@@ -207,29 +231,53 @@ static inline long arch_atomic64_fetch_##op##_relaxed(long i, atomic64_t *v)	\
 
 #define ATOMIC64_OPS(op, I, asm_op, c_op)				      \
 	ATOMIC64_OP(op, I, asm_op)					      \
-	ATOMIC64_OP_RETURN(op, I, asm_op, c_op)				      \
-	ATOMIC64_FETCH_OP(op, I, asm_op)
+	ATOMIC64_OP_RETURN(op, I, asm_op, c_op, _db,         )		      \
+	ATOMIC64_OP_RETURN(op, I, asm_op, c_op,    , _relaxed)		      \
+	ATOMIC64_FETCH_OP(op, I, asm_op, _db,         )			      \
+	ATOMIC64_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC64_OPS(add, i, add, +)
 ATOMIC64_OPS(sub, -i, add, +)
 
+#define arch_atomic64_add_return		arch_atomic64_add_return
+#define arch_atomic64_add_return_acquire	arch_atomic64_add_return
+#define arch_atomic64_add_return_release	arch_atomic64_add_return
 #define arch_atomic64_add_return_relaxed	arch_atomic64_add_return_relaxed
+#define arch_atomic64_sub_return		arch_atomic64_sub_return
+#define arch_atomic64_sub_return_acquire	arch_atomic64_sub_return
+#define arch_atomic64_sub_return_release	arch_atomic64_sub_return
 #define arch_atomic64_sub_return_relaxed	arch_atomic64_sub_return_relaxed
+#define arch_atomic64_fetch_add			arch_atomic64_fetch_add
+#define arch_atomic64_fetch_add_acquire		arch_atomic64_fetch_add
+#define arch_atomic64_fetch_add_release		arch_atomic64_fetch_add
 #define arch_atomic64_fetch_add_relaxed		arch_atomic64_fetch_add_relaxed
+#define arch_atomic64_fetch_sub			arch_atomic64_fetch_sub
+#define arch_atomic64_fetch_sub_acquire		arch_atomic64_fetch_sub
+#define arch_atomic64_fetch_sub_release		arch_atomic64_fetch_sub
 #define arch_atomic64_fetch_sub_relaxed		arch_atomic64_fetch_sub_relaxed
 
 #undef ATOMIC64_OPS
 
 #define ATOMIC64_OPS(op, I, asm_op)					      \
 	ATOMIC64_OP(op, I, asm_op)					      \
-	ATOMIC64_FETCH_OP(op, I, asm_op)
+	ATOMIC64_FETCH_OP(op, I, asm_op, _db,         )			      \
+	ATOMIC64_FETCH_OP(op, I, asm_op,    , _relaxed)
 
 ATOMIC64_OPS(and, i, and)
 ATOMIC64_OPS(or, i, or)
 ATOMIC64_OPS(xor, i, xor)
 
+#define arch_atomic64_fetch_and		arch_atomic64_fetch_and
+#define arch_atomic64_fetch_and_acquire	arch_atomic64_fetch_and
+#define arch_atomic64_fetch_and_release	arch_atomic64_fetch_and
 #define arch_atomic64_fetch_and_relaxed	arch_atomic64_fetch_and_relaxed
+#define arch_atomic64_fetch_or		arch_atomic64_fetch_or
+#define arch_atomic64_fetch_or_acquire	arch_atomic64_fetch_or
+#define arch_atomic64_fetch_or_release	arch_atomic64_fetch_or
 #define arch_atomic64_fetch_or_relaxed	arch_atomic64_fetch_or_relaxed
+#define arch_atomic64_fetch_xor		arch_atomic64_fetch_xor
+#define arch_atomic64_fetch_xor_acquire	arch_atomic64_fetch_xor
+#define arch_atomic64_fetch_xor_release	arch_atomic64_fetch_xor
 #define arch_atomic64_fetch_xor_relaxed	arch_atomic64_fetch_xor_relaxed
 
 #undef ATOMIC64_OPS
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index 71e1ed4165..d8f637f9e4 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -65,6 +65,16 @@ enum reg2_op {
 	revbd_op	= 0x0f,
 	revh2w_op	= 0x10,
 	revhd_op	= 0x11,
+	extwh_op	= 0x16,
+	extwb_op	= 0x17,
+	iocsrrdb_op     = 0x19200,
+	iocsrrdh_op     = 0x19201,
+	iocsrrdw_op     = 0x19202,
+	iocsrrdd_op     = 0x19203,
+	iocsrwrb_op     = 0x19204,
+	iocsrwrh_op     = 0x19205,
+	iocsrwrw_op     = 0x19206,
+	iocsrwrd_op     = 0x19207,
 };
 
 enum reg2i5_op {
@@ -318,6 +328,13 @@ struct reg2bstrd_format {
 	unsigned int opcode : 10;
 };
 
+struct reg2csr_format {
+	unsigned int rd : 5;
+	unsigned int rj : 5;
+	unsigned int csr : 14;
+	unsigned int opcode : 8;
+};
+
 struct reg3_format {
 	unsigned int rd : 5;
 	unsigned int rj : 5;
@@ -346,6 +363,7 @@ union loongarch_instruction {
 	struct reg2i14_format	reg2i14_format;
 	struct reg2i16_format	reg2i16_format;
 	struct reg2bstrd_format	reg2bstrd_format;
+	struct reg2csr_format   reg2csr_format;
 	struct reg3_format	reg3_format;
 	struct reg3sa2_format	reg3sa2_format;
 };
@@ -556,6 +574,8 @@ static inline void emit_##NAME(union loongarch_instruction *insn,	\
 DEF_EMIT_REG2_FORMAT(revb2h, revb2h_op)
 DEF_EMIT_REG2_FORMAT(revb2w, revb2w_op)
 DEF_EMIT_REG2_FORMAT(revbd, revbd_op)
+DEF_EMIT_REG2_FORMAT(extwh, extwh_op)
+DEF_EMIT_REG2_FORMAT(extwb, extwb_op)
 
 #define DEF_EMIT_REG2I5_FORMAT(NAME, OP)				\
 static inline void emit_##NAME(union loongarch_instruction *insn,	\
@@ -607,6 +627,9 @@ DEF_EMIT_REG2I12_FORMAT(lu52id, lu52id_op)
 DEF_EMIT_REG2I12_FORMAT(andi, andi_op)
 DEF_EMIT_REG2I12_FORMAT(ori, ori_op)
 DEF_EMIT_REG2I12_FORMAT(xori, xori_op)
+DEF_EMIT_REG2I12_FORMAT(ldb, ldb_op)
+DEF_EMIT_REG2I12_FORMAT(ldh, ldh_op)
+DEF_EMIT_REG2I12_FORMAT(ldw, ldw_op)
 DEF_EMIT_REG2I12_FORMAT(ldbu, ldbu_op)
 DEF_EMIT_REG2I12_FORMAT(ldhu, ldhu_op)
 DEF_EMIT_REG2I12_FORMAT(ldwu, ldwu_op)
@@ -685,9 +708,12 @@ static inline void emit_##NAME(union loongarch_instruction *insn,	\
 	insn->reg3_format.rk = rk;					\
 }
 
+DEF_EMIT_REG3_FORMAT(addw, addw_op)
 DEF_EMIT_REG3_FORMAT(addd, addd_op)
 DEF_EMIT_REG3_FORMAT(subd, subd_op)
 DEF_EMIT_REG3_FORMAT(muld, muld_op)
+DEF_EMIT_REG3_FORMAT(divd, divd_op)
+DEF_EMIT_REG3_FORMAT(modd, modd_op)
 DEF_EMIT_REG3_FORMAT(divdu, divdu_op)
 DEF_EMIT_REG3_FORMAT(moddu, moddu_op)
 DEF_EMIT_REG3_FORMAT(and, and_op)
@@ -699,6 +725,9 @@ DEF_EMIT_REG3_FORMAT(srlw, srlw_op)
 DEF_EMIT_REG3_FORMAT(srld, srld_op)
 DEF_EMIT_REG3_FORMAT(sraw, sraw_op)
 DEF_EMIT_REG3_FORMAT(srad, srad_op)
+DEF_EMIT_REG3_FORMAT(ldxb, ldxb_op)
+DEF_EMIT_REG3_FORMAT(ldxh, ldxh_op)
+DEF_EMIT_REG3_FORMAT(ldxw, ldxw_op)
 DEF_EMIT_REG3_FORMAT(ldxbu, ldxbu_op)
 DEF_EMIT_REG3_FORMAT(ldxhu, ldxhu_op)
 DEF_EMIT_REG3_FORMAT(ldxwu, ldxwu_op)
diff --git a/arch/loongarch/include/asm/jump_label.h b/arch/loongarch/include/asm/jump_label.h
index 3cea299a5e..29acfe3de3 100644
--- a/arch/loongarch/include/asm/jump_label.h
+++ b/arch/loongarch/include/asm/jump_label.h
@@ -22,7 +22,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	nop			\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
@@ -35,7 +35,7 @@ l_yes:
 
 static __always_inline bool arch_static_branch_jump(struct static_key * const key, const bool branch)
 {
-	asm_volatile_goto(
+	asm goto(
 		"1:	b	%l[l_yes]	\n\t"
 		JUMP_TABLE_ENTRY
 		:  :  "i"(&((char *)key)[branch]) :  : l_yes);
diff --git a/arch/loongarch/include/asm/kvm_csr.h b/arch/loongarch/include/asm/kvm_csr.h
new file mode 100644
index 0000000000..724ca8b7b4
--- /dev/null
+++ b/arch/loongarch/include/asm/kvm_csr.h
@@ -0,0 +1,211 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __ASM_LOONGARCH_KVM_CSR_H__
+#define __ASM_LOONGARCH_KVM_CSR_H__
+
+#include <linux/uaccess.h>
+#include <linux/kvm_host.h>
+#include <asm/loongarch.h>
+#include <asm/kvm_vcpu.h>
+
+#define gcsr_read(csr)						\
+({								\
+	register unsigned long __v;				\
+	__asm__ __volatile__(					\
+		" gcsrrd %[val], %[reg]\n\t"			\
+		: [val] "=r" (__v)				\
+		: [reg] "i" (csr)				\
+		: "memory");					\
+	__v;							\
+})
+
+#define gcsr_write(v, csr)					\
+({								\
+	register unsigned long __v = v;				\
+	__asm__ __volatile__ (					\
+		" gcsrwr %[val], %[reg]\n\t"			\
+		: [val] "+r" (__v)				\
+		: [reg] "i" (csr)				\
+		: "memory");					\
+})
+
+#define gcsr_xchg(v, m, csr)					\
+({								\
+	register unsigned long __v = v;				\
+	__asm__ __volatile__(					\
+		" gcsrxchg %[val], %[mask], %[reg]\n\t"		\
+		: [val] "+r" (__v)				\
+		: [mask] "r" (m), [reg] "i" (csr)		\
+		: "memory");					\
+	__v;							\
+})
+
+/* Guest CSRS read and write */
+#define read_gcsr_crmd()		gcsr_read(LOONGARCH_CSR_CRMD)
+#define write_gcsr_crmd(val)		gcsr_write(val, LOONGARCH_CSR_CRMD)
+#define read_gcsr_prmd()		gcsr_read(LOONGARCH_CSR_PRMD)
+#define write_gcsr_prmd(val)		gcsr_write(val, LOONGARCH_CSR_PRMD)
+#define read_gcsr_euen()		gcsr_read(LOONGARCH_CSR_EUEN)
+#define write_gcsr_euen(val)		gcsr_write(val, LOONGARCH_CSR_EUEN)
+#define read_gcsr_misc()		gcsr_read(LOONGARCH_CSR_MISC)
+#define write_gcsr_misc(val)		gcsr_write(val, LOONGARCH_CSR_MISC)
+#define read_gcsr_ecfg()		gcsr_read(LOONGARCH_CSR_ECFG)
+#define write_gcsr_ecfg(val)		gcsr_write(val, LOONGARCH_CSR_ECFG)
+#define read_gcsr_estat()		gcsr_read(LOONGARCH_CSR_ESTAT)
+#define write_gcsr_estat(val)		gcsr_write(val, LOONGARCH_CSR_ESTAT)
+#define read_gcsr_era()			gcsr_read(LOONGARCH_CSR_ERA)
+#define write_gcsr_era(val)		gcsr_write(val, LOONGARCH_CSR_ERA)
+#define read_gcsr_badv()		gcsr_read(LOONGARCH_CSR_BADV)
+#define write_gcsr_badv(val)		gcsr_write(val, LOONGARCH_CSR_BADV)
+#define read_gcsr_badi()		gcsr_read(LOONGARCH_CSR_BADI)
+#define write_gcsr_badi(val)		gcsr_write(val, LOONGARCH_CSR_BADI)
+#define read_gcsr_eentry()		gcsr_read(LOONGARCH_CSR_EENTRY)
+#define write_gcsr_eentry(val)		gcsr_write(val, LOONGARCH_CSR_EENTRY)
+
+#define read_gcsr_asid()		gcsr_read(LOONGARCH_CSR_ASID)
+#define write_gcsr_asid(val)		gcsr_write(val, LOONGARCH_CSR_ASID)
+#define read_gcsr_pgdl()		gcsr_read(LOONGARCH_CSR_PGDL)
+#define write_gcsr_pgdl(val)		gcsr_write(val, LOONGARCH_CSR_PGDL)
+#define read_gcsr_pgdh()		gcsr_read(LOONGARCH_CSR_PGDH)
+#define write_gcsr_pgdh(val)		gcsr_write(val, LOONGARCH_CSR_PGDH)
+#define write_gcsr_pgd(val)		gcsr_write(val, LOONGARCH_CSR_PGD)
+#define read_gcsr_pgd()			gcsr_read(LOONGARCH_CSR_PGD)
+#define read_gcsr_pwctl0()		gcsr_read(LOONGARCH_CSR_PWCTL0)
+#define write_gcsr_pwctl0(val)		gcsr_write(val, LOONGARCH_CSR_PWCTL0)
+#define read_gcsr_pwctl1()		gcsr_read(LOONGARCH_CSR_PWCTL1)
+#define write_gcsr_pwctl1(val)		gcsr_write(val, LOONGARCH_CSR_PWCTL1)
+#define read_gcsr_stlbpgsize()		gcsr_read(LOONGARCH_CSR_STLBPGSIZE)
+#define write_gcsr_stlbpgsize(val)	gcsr_write(val, LOONGARCH_CSR_STLBPGSIZE)
+#define read_gcsr_rvacfg()		gcsr_read(LOONGARCH_CSR_RVACFG)
+#define write_gcsr_rvacfg(val)		gcsr_write(val, LOONGARCH_CSR_RVACFG)
+
+#define read_gcsr_cpuid()		gcsr_read(LOONGARCH_CSR_CPUID)
+#define write_gcsr_cpuid(val)		gcsr_write(val, LOONGARCH_CSR_CPUID)
+#define read_gcsr_prcfg1()		gcsr_read(LOONGARCH_CSR_PRCFG1)
+#define write_gcsr_prcfg1(val)		gcsr_write(val, LOONGARCH_CSR_PRCFG1)
+#define read_gcsr_prcfg2()		gcsr_read(LOONGARCH_CSR_PRCFG2)
+#define write_gcsr_prcfg2(val)		gcsr_write(val, LOONGARCH_CSR_PRCFG2)
+#define read_gcsr_prcfg3()		gcsr_read(LOONGARCH_CSR_PRCFG3)
+#define write_gcsr_prcfg3(val)		gcsr_write(val, LOONGARCH_CSR_PRCFG3)
+
+#define read_gcsr_kscratch0()		gcsr_read(LOONGARCH_CSR_KS0)
+#define write_gcsr_kscratch0(val)	gcsr_write(val, LOONGARCH_CSR_KS0)
+#define read_gcsr_kscratch1()		gcsr_read(LOONGARCH_CSR_KS1)
+#define write_gcsr_kscratch1(val)	gcsr_write(val, LOONGARCH_CSR_KS1)
+#define read_gcsr_kscratch2()		gcsr_read(LOONGARCH_CSR_KS2)
+#define write_gcsr_kscratch2(val)	gcsr_write(val, LOONGARCH_CSR_KS2)
+#define read_gcsr_kscratch3()		gcsr_read(LOONGARCH_CSR_KS3)
+#define write_gcsr_kscratch3(val)	gcsr_write(val, LOONGARCH_CSR_KS3)
+#define read_gcsr_kscratch4()		gcsr_read(LOONGARCH_CSR_KS4)
+#define write_gcsr_kscratch4(val)	gcsr_write(val, LOONGARCH_CSR_KS4)
+#define read_gcsr_kscratch5()		gcsr_read(LOONGARCH_CSR_KS5)
+#define write_gcsr_kscratch5(val)	gcsr_write(val, LOONGARCH_CSR_KS5)
+#define read_gcsr_kscratch6()		gcsr_read(LOONGARCH_CSR_KS6)
+#define write_gcsr_kscratch6(val)	gcsr_write(val, LOONGARCH_CSR_KS6)
+#define read_gcsr_kscratch7()		gcsr_read(LOONGARCH_CSR_KS7)
+#define write_gcsr_kscratch7(val)	gcsr_write(val, LOONGARCH_CSR_KS7)
+
+#define read_gcsr_timerid()		gcsr_read(LOONGARCH_CSR_TMID)
+#define write_gcsr_timerid(val)		gcsr_write(val, LOONGARCH_CSR_TMID)
+#define read_gcsr_timercfg()		gcsr_read(LOONGARCH_CSR_TCFG)
+#define write_gcsr_timercfg(val)	gcsr_write(val, LOONGARCH_CSR_TCFG)
+#define read_gcsr_timertick()		gcsr_read(LOONGARCH_CSR_TVAL)
+#define write_gcsr_timertick(val)	gcsr_write(val, LOONGARCH_CSR_TVAL)
+#define read_gcsr_timeroffset()		gcsr_read(LOONGARCH_CSR_CNTC)
+#define write_gcsr_timeroffset(val)	gcsr_write(val, LOONGARCH_CSR_CNTC)
+
+#define read_gcsr_llbctl()		gcsr_read(LOONGARCH_CSR_LLBCTL)
+#define write_gcsr_llbctl(val)		gcsr_write(val, LOONGARCH_CSR_LLBCTL)
+
+#define read_gcsr_tlbidx()		gcsr_read(LOONGARCH_CSR_TLBIDX)
+#define write_gcsr_tlbidx(val)		gcsr_write(val, LOONGARCH_CSR_TLBIDX)
+#define read_gcsr_tlbrentry()		gcsr_read(LOONGARCH_CSR_TLBRENTRY)
+#define write_gcsr_tlbrentry(val)	gcsr_write(val, LOONGARCH_CSR_TLBRENTRY)
+#define read_gcsr_tlbrbadv()		gcsr_read(LOONGARCH_CSR_TLBRBADV)
+#define write_gcsr_tlbrbadv(val)	gcsr_write(val, LOONGARCH_CSR_TLBRBADV)
+#define read_gcsr_tlbrera()		gcsr_read(LOONGARCH_CSR_TLBRERA)
+#define write_gcsr_tlbrera(val)		gcsr_write(val, LOONGARCH_CSR_TLBRERA)
+#define read_gcsr_tlbrsave()		gcsr_read(LOONGARCH_CSR_TLBRSAVE)
+#define write_gcsr_tlbrsave(val)	gcsr_write(val, LOONGARCH_CSR_TLBRSAVE)
+#define read_gcsr_tlbrelo0()		gcsr_read(LOONGARCH_CSR_TLBRELO0)
+#define write_gcsr_tlbrelo0(val)	gcsr_write(val, LOONGARCH_CSR_TLBRELO0)
+#define read_gcsr_tlbrelo1()		gcsr_read(LOONGARCH_CSR_TLBRELO1)
+#define write_gcsr_tlbrelo1(val)	gcsr_write(val, LOONGARCH_CSR_TLBRELO1)
+#define read_gcsr_tlbrehi()		gcsr_read(LOONGARCH_CSR_TLBREHI)
+#define write_gcsr_tlbrehi(val)		gcsr_write(val, LOONGARCH_CSR_TLBREHI)
+#define read_gcsr_tlbrprmd()		gcsr_read(LOONGARCH_CSR_TLBRPRMD)
+#define write_gcsr_tlbrprmd(val)	gcsr_write(val, LOONGARCH_CSR_TLBRPRMD)
+
+#define read_gcsr_directwin0()		gcsr_read(LOONGARCH_CSR_DMWIN0)
+#define write_gcsr_directwin0(val)	gcsr_write(val, LOONGARCH_CSR_DMWIN0)
+#define read_gcsr_directwin1()		gcsr_read(LOONGARCH_CSR_DMWIN1)
+#define write_gcsr_directwin1(val)	gcsr_write(val, LOONGARCH_CSR_DMWIN1)
+#define read_gcsr_directwin2()		gcsr_read(LOONGARCH_CSR_DMWIN2)
+#define write_gcsr_directwin2(val)	gcsr_write(val, LOONGARCH_CSR_DMWIN2)
+#define read_gcsr_directwin3()		gcsr_read(LOONGARCH_CSR_DMWIN3)
+#define write_gcsr_directwin3(val)	gcsr_write(val, LOONGARCH_CSR_DMWIN3)
+
+/* Guest related CSRs */
+#define read_csr_gtlbc()		csr_read64(LOONGARCH_CSR_GTLBC)
+#define write_csr_gtlbc(val)		csr_write64(val, LOONGARCH_CSR_GTLBC)
+#define read_csr_trgp()			csr_read64(LOONGARCH_CSR_TRGP)
+#define read_csr_gcfg()			csr_read64(LOONGARCH_CSR_GCFG)
+#define write_csr_gcfg(val)		csr_write64(val, LOONGARCH_CSR_GCFG)
+#define read_csr_gstat()		csr_read64(LOONGARCH_CSR_GSTAT)
+#define write_csr_gstat(val)		csr_write64(val, LOONGARCH_CSR_GSTAT)
+#define read_csr_gintc()		csr_read64(LOONGARCH_CSR_GINTC)
+#define write_csr_gintc(val)		csr_write64(val, LOONGARCH_CSR_GINTC)
+#define read_csr_gcntc()		csr_read64(LOONGARCH_CSR_GCNTC)
+#define write_csr_gcntc(val)		csr_write64(val, LOONGARCH_CSR_GCNTC)
+
+#define __BUILD_GCSR_OP(name)		__BUILD_CSR_COMMON(gcsr_##name)
+
+__BUILD_CSR_OP(gcfg)
+__BUILD_CSR_OP(gstat)
+__BUILD_CSR_OP(gtlbc)
+__BUILD_CSR_OP(gintc)
+__BUILD_GCSR_OP(llbctl)
+__BUILD_GCSR_OP(tlbidx)
+
+#define set_gcsr_estat(val)	\
+	gcsr_xchg(val, val, LOONGARCH_CSR_ESTAT)
+#define clear_gcsr_estat(val)	\
+	gcsr_xchg(~(val), val, LOONGARCH_CSR_ESTAT)
+
+#define kvm_read_hw_gcsr(id)		gcsr_read(id)
+#define kvm_write_hw_gcsr(id, val)	gcsr_write(val, id)
+
+#define kvm_save_hw_gcsr(csr, gid)	(csr->csrs[gid] = gcsr_read(gid))
+#define kvm_restore_hw_gcsr(csr, gid)	(gcsr_write(csr->csrs[gid], gid))
+
+int kvm_emu_iocsr(larch_inst inst, struct kvm_run *run, struct kvm_vcpu *vcpu);
+
+static __always_inline unsigned long kvm_read_sw_gcsr(struct loongarch_csrs *csr, int gid)
+{
+	return csr->csrs[gid];
+}
+
+static __always_inline void kvm_write_sw_gcsr(struct loongarch_csrs *csr, int gid, unsigned long val)
+{
+	csr->csrs[gid] = val;
+}
+
+static __always_inline void kvm_set_sw_gcsr(struct loongarch_csrs *csr,
+					    int gid, unsigned long val)
+{
+	csr->csrs[gid] |= val;
+}
+
+static __always_inline void kvm_change_sw_gcsr(struct loongarch_csrs *csr,
+					       int gid, unsigned long mask, unsigned long val)
+{
+	unsigned long _mask = mask;
+
+	csr->csrs[gid] &= ~_mask;
+	csr->csrs[gid] |= val & _mask;
+}
+
+#endif	/* __ASM_LOONGARCH_KVM_CSR_H__ */
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
new file mode 100644
index 0000000000..11328700d4
--- /dev/null
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __ASM_LOONGARCH_KVM_HOST_H__
+#define __ASM_LOONGARCH_KVM_HOST_H__
+
+#include <linux/cpumask.h>
+#include <linux/hrtimer.h>
+#include <linux/interrupt.h>
+#include <linux/kvm.h>
+#include <linux/kvm_types.h>
+#include <linux/mutex.h>
+#include <linux/spinlock.h>
+#include <linux/threads.h>
+#include <linux/types.h>
+
+#include <asm/inst.h>
+#include <asm/kvm_mmu.h>
+#include <asm/loongarch.h>
+
+/* Loongarch KVM register ids */
+#define KVM_GET_IOC_CSR_IDX(id)		((id & KVM_CSR_IDX_MASK) >> LOONGARCH_REG_SHIFT)
+#define KVM_GET_IOC_CPUCFG_IDX(id)	((id & KVM_CPUCFG_IDX_MASK) >> LOONGARCH_REG_SHIFT)
+
+#define KVM_MAX_VCPUS			256
+#define KVM_MAX_CPUCFG_REGS		21
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS		0
+
+#define KVM_HALT_POLL_NS_DEFAULT	500000
+
+struct kvm_vm_stat {
+	struct kvm_vm_stat_generic generic;
+	u64 pages;
+	u64 hugepages;
+};
+
+struct kvm_vcpu_stat {
+	struct kvm_vcpu_stat_generic generic;
+	u64 int_exits;
+	u64 idle_exits;
+	u64 cpucfg_exits;
+	u64 signal_exits;
+};
+
+struct kvm_arch_memory_slot {
+};
+
+struct kvm_context {
+	unsigned long vpid_cache;
+	struct kvm_vcpu *last_vcpu;
+};
+
+struct kvm_world_switch {
+	int (*exc_entry)(void);
+	int (*enter_guest)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+	unsigned long page_order;
+};
+
+#define MAX_PGTABLE_LEVELS	4
+
+struct kvm_arch {
+	/* Guest physical mm */
+	kvm_pte_t *pgd;
+	unsigned long gpa_size;
+	unsigned long invalid_ptes[MAX_PGTABLE_LEVELS];
+	unsigned int  pte_shifts[MAX_PGTABLE_LEVELS];
+	unsigned int  root_level;
+
+	s64 time_offset;
+	struct kvm_context __percpu *vmcs;
+};
+
+#define CSR_MAX_NUMS		0x800
+
+struct loongarch_csrs {
+	unsigned long csrs[CSR_MAX_NUMS];
+};
+
+/* Resume Flags */
+#define RESUME_HOST		0
+#define RESUME_GUEST		1
+
+enum emulation_result {
+	EMULATE_DONE,		/* no further processing */
+	EMULATE_DO_MMIO,	/* kvm_run filled with MMIO request */
+	EMULATE_DO_IOCSR,	/* handle IOCSR request */
+	EMULATE_FAIL,		/* can't emulate this instruction */
+	EMULATE_EXCEPT,		/* A guest exception has been generated */
+};
+
+#define KVM_LARCH_FPU		(0x1 << 0)
+#define KVM_LARCH_SWCSR_LATEST	(0x1 << 1)
+#define KVM_LARCH_HWCSR_USABLE	(0x1 << 2)
+
+struct kvm_vcpu_arch {
+	/*
+	 * Switch pointer-to-function type to unsigned long
+	 * for loading the value into register directly.
+	 */
+	unsigned long host_eentry;
+	unsigned long guest_eentry;
+
+	/* Pointers stored here for easy accessing from assembly code */
+	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+
+	/* Host registers preserved across guest mode execution */
+	unsigned long host_sp;
+	unsigned long host_tp;
+	unsigned long host_pgd;
+
+	/* Host CSRs are used when handling exits from guest */
+	unsigned long badi;
+	unsigned long badv;
+	unsigned long host_ecfg;
+	unsigned long host_estat;
+	unsigned long host_percpu;
+
+	/* GPRs */
+	unsigned long gprs[32];
+	unsigned long pc;
+
+	/* Which auxiliary state is loaded (KVM_LARCH_*) */
+	unsigned int aux_inuse;
+
+	/* FPU state */
+	struct loongarch_fpu fpu FPU_ALIGN;
+
+	/* CSR state */
+	struct loongarch_csrs *csr;
+
+	/* GPR used as IO source/target */
+	u32 io_gpr;
+
+	/* KVM register to control count timer */
+	u32 count_ctl;
+	struct hrtimer swtimer;
+
+	/* Bitmask of intr that are pending */
+	unsigned long irq_pending;
+	/* Bitmask of pending intr to be cleared */
+	unsigned long irq_clear;
+
+	/* Bitmask of exceptions that are pending */
+	unsigned long exception_pending;
+	unsigned int  esubcode;
+
+	/* Cache for pages needed inside spinlock regions */
+	struct kvm_mmu_memory_cache mmu_page_cache;
+
+	/* vcpu's vpid */
+	u64 vpid;
+
+	/* Frequency of stable timer in Hz */
+	u64 timer_mhz;
+	ktime_t expire;
+
+	/* Last CPU the vCPU state was loaded on */
+	int last_sched_cpu;
+	/* mp state */
+	struct kvm_mp_state mp_state;
+	/* cpucfg */
+	u32 cpucfg[KVM_MAX_CPUCFG_REGS];
+};
+
+static inline unsigned long readl_sw_gcsr(struct loongarch_csrs *csr, int reg)
+{
+	return csr->csrs[reg];
+}
+
+static inline void writel_sw_gcsr(struct loongarch_csrs *csr, int reg, unsigned long val)
+{
+	csr->csrs[reg] = val;
+}
+
+/* Debug: dump vcpu state */
+int kvm_arch_vcpu_dump_regs(struct kvm_vcpu *vcpu);
+
+/* MMU handling */
+void kvm_flush_tlb_all(void);
+void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa);
+int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long badv, bool write);
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+int kvm_unmap_hva_range(struct kvm *kvm, unsigned long start, unsigned long end, bool blockable);
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+
+static inline void update_pc(struct kvm_vcpu_arch *arch)
+{
+	arch->pc += 4;
+}
+
+/*
+ * kvm_is_ifetch_fault() - Find whether a TLBL exception is due to ifetch fault.
+ * @vcpu:	Virtual CPU.
+ *
+ * Returns:	Whether the TLBL exception was likely due to an instruction
+ *		fetch fault rather than a data load fault.
+ */
+static inline bool kvm_is_ifetch_fault(struct kvm_vcpu_arch *arch)
+{
+	return arch->pc == arch->badv;
+}
+
+/* Misc */
+static inline void kvm_arch_hardware_unsetup(void) {}
+static inline void kvm_arch_sync_events(struct kvm *kvm) {}
+static inline void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen) {}
+static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) {}
+void kvm_check_vpid(struct kvm_vcpu *vcpu);
+enum hrtimer_restart kvm_swtimer_wakeup(struct hrtimer *timer);
+void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot);
+void kvm_init_vmcs(struct kvm *kvm);
+void kvm_exc_entry(void);
+int  kvm_enter_guest(struct kvm_run *run, struct kvm_vcpu *vcpu);
+
+extern unsigned long vpid_mask;
+extern const unsigned long kvm_exception_size;
+extern const unsigned long kvm_enter_guest_size;
+extern struct kvm_world_switch *kvm_loongarch_ops;
+
+#define SW_GCSR		(1 << 0)
+#define HW_GCSR		(1 << 1)
+#define INVALID_GCSR	(1 << 2)
+
+int get_gcsr_flag(int csr);
+void set_hw_gcsr(int csr_id, unsigned long val);
+
+#endif /* __ASM_LOONGARCH_KVM_HOST_H__ */
diff --git a/arch/loongarch/include/asm/kvm_mmu.h b/arch/loongarch/include/asm/kvm_mmu.h
new file mode 100644
index 0000000000..099bafc6f7
--- /dev/null
+++ b/arch/loongarch/include/asm/kvm_mmu.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __ASM_LOONGARCH_KVM_MMU_H__
+#define __ASM_LOONGARCH_KVM_MMU_H__
+
+#include <linux/kvm_host.h>
+#include <asm/pgalloc.h>
+#include <asm/tlb.h>
+
+/*
+ * KVM_MMU_CACHE_MIN_PAGES is the number of GPA page table translation levels
+ * for which pages need to be cached.
+ */
+#define KVM_MMU_CACHE_MIN_PAGES	(CONFIG_PGTABLE_LEVELS - 1)
+
+#define _KVM_FLUSH_PGTABLE	0x1
+#define _KVM_HAS_PGMASK		0x2
+#define kvm_pfn_pte(pfn, prot)	(((pfn) << PFN_PTE_SHIFT) | pgprot_val(prot))
+#define kvm_pte_pfn(x)		((phys_addr_t)((x & _PFN_MASK) >> PFN_PTE_SHIFT))
+
+typedef unsigned long kvm_pte_t;
+typedef struct kvm_ptw_ctx kvm_ptw_ctx;
+typedef int (*kvm_pte_ops)(kvm_pte_t *pte, phys_addr_t addr, kvm_ptw_ctx *ctx);
+
+struct kvm_ptw_ctx {
+	kvm_pte_ops     ops;
+	unsigned long   flag;
+
+	/* for kvm_arch_mmu_enable_log_dirty_pt_masked use */
+	unsigned long   mask;
+	unsigned long   gfn;
+
+	/* page walk mmu info */
+	unsigned int    level;
+	unsigned long   pgtable_shift;
+	unsigned long   invalid_entry;
+	unsigned long   *invalid_ptes;
+	unsigned int    *pte_shifts;
+	void		*opaque;
+
+	/* free pte table page list */
+	struct list_head list;
+};
+
+kvm_pte_t *kvm_pgd_alloc(void);
+
+static inline void kvm_set_pte(kvm_pte_t *ptep, kvm_pte_t val)
+{
+	WRITE_ONCE(*ptep, val);
+}
+
+static inline int kvm_pte_write(kvm_pte_t pte) { return pte & _PAGE_WRITE; }
+static inline int kvm_pte_dirty(kvm_pte_t pte) { return pte & _PAGE_DIRTY; }
+static inline int kvm_pte_young(kvm_pte_t pte) { return pte & _PAGE_ACCESSED; }
+static inline int kvm_pte_huge(kvm_pte_t pte) { return pte & _PAGE_HUGE; }
+
+static inline kvm_pte_t kvm_pte_mkyoung(kvm_pte_t pte)
+{
+	return pte | _PAGE_ACCESSED;
+}
+
+static inline kvm_pte_t kvm_pte_mkold(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_ACCESSED;
+}
+
+static inline kvm_pte_t kvm_pte_mkdirty(kvm_pte_t pte)
+{
+	return pte | _PAGE_DIRTY;
+}
+
+static inline kvm_pte_t kvm_pte_mkclean(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_DIRTY;
+}
+
+static inline kvm_pte_t kvm_pte_mkhuge(kvm_pte_t pte)
+{
+	return pte | _PAGE_HUGE;
+}
+
+static inline kvm_pte_t kvm_pte_mksmall(kvm_pte_t pte)
+{
+	return pte & ~_PAGE_HUGE;
+}
+
+static inline int kvm_need_flush(kvm_ptw_ctx *ctx)
+{
+	return ctx->flag & _KVM_FLUSH_PGTABLE;
+}
+
+static inline kvm_pte_t *kvm_pgtable_offset(kvm_ptw_ctx *ctx, kvm_pte_t *table,
+					phys_addr_t addr)
+{
+
+	return table + ((addr >> ctx->pgtable_shift) & (PTRS_PER_PTE - 1));
+}
+
+static inline phys_addr_t kvm_pgtable_addr_end(kvm_ptw_ctx *ctx,
+				phys_addr_t addr, phys_addr_t end)
+{
+	phys_addr_t boundary, size;
+
+	size = 0x1UL << ctx->pgtable_shift;
+	boundary = (addr + size) & ~(size - 1);
+	return (boundary - 1 < end - 1) ? boundary : end;
+}
+
+static inline int kvm_pte_present(kvm_ptw_ctx *ctx, kvm_pte_t *entry)
+{
+	if (!ctx || ctx->level == 0)
+		return !!(*entry & _PAGE_PRESENT);
+
+	return *entry != ctx->invalid_entry;
+}
+
+static inline int kvm_pte_none(kvm_ptw_ctx *ctx, kvm_pte_t *entry)
+{
+	return *entry == ctx->invalid_entry;
+}
+
+static inline void kvm_ptw_enter(kvm_ptw_ctx *ctx)
+{
+	ctx->level--;
+	ctx->pgtable_shift = ctx->pte_shifts[ctx->level];
+	ctx->invalid_entry = ctx->invalid_ptes[ctx->level];
+}
+
+static inline void kvm_ptw_exit(kvm_ptw_ctx *ctx)
+{
+	ctx->level++;
+	ctx->pgtable_shift = ctx->pte_shifts[ctx->level];
+	ctx->invalid_entry = ctx->invalid_ptes[ctx->level];
+}
+
+#endif /* __ASM_LOONGARCH_KVM_MMU_H__ */
diff --git a/arch/loongarch/include/asm/kvm_types.h b/arch/loongarch/include/asm/kvm_types.h
new file mode 100644
index 0000000000..2fe1d4bdff
--- /dev/null
+++ b/arch/loongarch/include/asm/kvm_types.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef _ASM_LOONGARCH_KVM_TYPES_H
+#define _ASM_LOONGARCH_KVM_TYPES_H
+
+#define KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE	40
+
+#endif /* _ASM_LOONGARCH_KVM_TYPES_H */
diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
new file mode 100644
index 0000000000..553cfa2b2b
--- /dev/null
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -0,0 +1,93 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+
+#ifndef __ASM_LOONGARCH_KVM_VCPU_H__
+#define __ASM_LOONGARCH_KVM_VCPU_H__
+
+#include <linux/kvm_host.h>
+#include <asm/loongarch.h>
+
+/* Controlled by 0x5 guest estat */
+#define CPU_SIP0			(_ULCAST_(1))
+#define CPU_SIP1			(_ULCAST_(1) << 1)
+#define CPU_PMU				(_ULCAST_(1) << 10)
+#define CPU_TIMER			(_ULCAST_(1) << 11)
+#define CPU_IPI				(_ULCAST_(1) << 12)
+
+/* Controlled by 0x52 guest exception VIP aligned to estat bit 5~12 */
+#define CPU_IP0				(_ULCAST_(1))
+#define CPU_IP1				(_ULCAST_(1) << 1)
+#define CPU_IP2				(_ULCAST_(1) << 2)
+#define CPU_IP3				(_ULCAST_(1) << 3)
+#define CPU_IP4				(_ULCAST_(1) << 4)
+#define CPU_IP5				(_ULCAST_(1) << 5)
+#define CPU_IP6				(_ULCAST_(1) << 6)
+#define CPU_IP7				(_ULCAST_(1) << 7)
+
+#define MNSEC_PER_SEC			(NSEC_PER_SEC >> 20)
+
+/* KVM_IRQ_LINE irq field index values */
+#define KVM_LOONGSON_IRQ_TYPE_SHIFT	24
+#define KVM_LOONGSON_IRQ_TYPE_MASK	0xff
+#define KVM_LOONGSON_IRQ_VCPU_SHIFT	16
+#define KVM_LOONGSON_IRQ_VCPU_MASK	0xff
+#define KVM_LOONGSON_IRQ_NUM_SHIFT	0
+#define KVM_LOONGSON_IRQ_NUM_MASK	0xffff
+
+typedef union loongarch_instruction  larch_inst;
+typedef int (*exit_handle_fn)(struct kvm_vcpu *);
+
+int  kvm_emu_mmio_read(struct kvm_vcpu *vcpu, larch_inst inst);
+int  kvm_emu_mmio_write(struct kvm_vcpu *vcpu, larch_inst inst);
+int  kvm_complete_mmio_read(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int  kvm_complete_iocsr_read(struct kvm_vcpu *vcpu, struct kvm_run *run);
+int  kvm_emu_idle(struct kvm_vcpu *vcpu);
+int  kvm_pending_timer(struct kvm_vcpu *vcpu);
+int  kvm_handle_fault(struct kvm_vcpu *vcpu, int fault);
+void kvm_deliver_intr(struct kvm_vcpu *vcpu);
+void kvm_deliver_exception(struct kvm_vcpu *vcpu);
+
+void kvm_own_fpu(struct kvm_vcpu *vcpu);
+void kvm_lose_fpu(struct kvm_vcpu *vcpu);
+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);
+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);
+void kvm_restore_timer(struct kvm_vcpu *vcpu);
+
+int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu, struct kvm_interrupt *irq);
+
+/*
+ * Loongarch KVM guest interrupt handling
+ */
+static inline void kvm_queue_irq(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	set_bit(irq, &vcpu->arch.irq_pending);
+	clear_bit(irq, &vcpu->arch.irq_clear);
+}
+
+static inline void kvm_dequeue_irq(struct kvm_vcpu *vcpu, unsigned int irq)
+{
+	clear_bit(irq, &vcpu->arch.irq_pending);
+	set_bit(irq, &vcpu->arch.irq_clear);
+}
+
+static inline int kvm_queue_exception(struct kvm_vcpu *vcpu,
+			unsigned int code, unsigned int subcode)
+{
+	/* only one exception can be injected */
+	if (!vcpu->arch.exception_pending) {
+		set_bit(code, &vcpu->arch.exception_pending);
+		vcpu->arch.esubcode = subcode;
+		return 0;
+	} else
+		return -1;
+}
+
+#endif /* __ASM_LOONGARCH_KVM_VCPU_H__ */
diff --git a/arch/loongarch/include/asm/local.h b/arch/loongarch/include/asm/local.h
index c49675852b..f53ea653af 100644
--- a/arch/loongarch/include/asm/local.h
+++ b/arch/loongarch/include/asm/local.h
@@ -70,22 +70,27 @@ static inline bool local_try_cmpxchg(local_t *l, long *old, long new)
 #define local_xchg(l, n) (atomic_long_xchg((&(l)->a), (n)))
 
 /**
- * local_add_unless - add unless the number is a given value
+ * local_add_unless - add unless the number is already a given value
  * @l: pointer of type local_t
  * @a: the amount to add to l...
  * @u: ...unless l is equal to u.
  *
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
+ * Atomically adds @a to @l, if @v was not already @u.
+ * Returns true if the addition was done.
  */
-#define local_add_unless(l, a, u)				\
-({								\
-	long c, old;						\
-	c = local_read(l);					\
-	while (c != (u) && (old = local_cmpxchg((l), c, c + (a))) != c) \
-		c = old;					\
-	c != (u);						\
-})
+static inline bool
+local_add_unless(local_t *l, long a, long u)
+{
+	long c = local_read(l);
+
+	do {
+		if (unlikely(c == u))
+			return false;
+	} while (!local_try_cmpxchg(l, &c, c + a));
+
+	return true;
+}
+
 #define local_inc_not_zero(l) local_add_unless((l), 1, 0)
 
 #define local_dec_return(l) local_sub_return(1, (l))
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index 33531d432b..46366e783c 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -226,6 +226,7 @@
 #define LOONGARCH_CSR_ECFG		0x4	/* Exception config */
 #define  CSR_ECFG_VS_SHIFT		16
 #define  CSR_ECFG_VS_WIDTH		3
+#define  CSR_ECFG_VS_SHIFT_END		(CSR_ECFG_VS_SHIFT + CSR_ECFG_VS_WIDTH - 1)
 #define  CSR_ECFG_VS			(_ULCAST_(0x7) << CSR_ECFG_VS_SHIFT)
 #define  CSR_ECFG_IM_SHIFT		0
 #define  CSR_ECFG_IM_WIDTH		14
@@ -314,13 +315,14 @@
 #define  CSR_TLBLO1_V			(_ULCAST_(0x1) << CSR_TLBLO1_V_SHIFT)
 
 #define LOONGARCH_CSR_GTLBC		0x15	/* Guest TLB control */
-#define  CSR_GTLBC_RID_SHIFT		16
-#define  CSR_GTLBC_RID_WIDTH		8
-#define  CSR_GTLBC_RID			(_ULCAST_(0xff) << CSR_GTLBC_RID_SHIFT)
+#define  CSR_GTLBC_TGID_SHIFT		16
+#define  CSR_GTLBC_TGID_WIDTH		8
+#define  CSR_GTLBC_TGID_SHIFT_END	(CSR_GTLBC_TGID_SHIFT + CSR_GTLBC_TGID_WIDTH - 1)
+#define  CSR_GTLBC_TGID			(_ULCAST_(0xff) << CSR_GTLBC_TGID_SHIFT)
 #define  CSR_GTLBC_TOTI_SHIFT		13
 #define  CSR_GTLBC_TOTI			(_ULCAST_(0x1) << CSR_GTLBC_TOTI_SHIFT)
-#define  CSR_GTLBC_USERID_SHIFT		12
-#define  CSR_GTLBC_USERID		(_ULCAST_(0x1) << CSR_GTLBC_USERID_SHIFT)
+#define  CSR_GTLBC_USETGID_SHIFT	12
+#define  CSR_GTLBC_USETGID		(_ULCAST_(0x1) << CSR_GTLBC_USETGID_SHIFT)
 #define  CSR_GTLBC_GMTLBSZ_SHIFT	0
 #define  CSR_GTLBC_GMTLBSZ_WIDTH	6
 #define  CSR_GTLBC_GMTLBSZ		(_ULCAST_(0x3f) << CSR_GTLBC_GMTLBSZ_SHIFT)
@@ -475,6 +477,7 @@
 #define LOONGARCH_CSR_GSTAT		0x50	/* Guest status */
 #define  CSR_GSTAT_GID_SHIFT		16
 #define  CSR_GSTAT_GID_WIDTH		8
+#define  CSR_GSTAT_GID_SHIFT_END	(CSR_GSTAT_GID_SHIFT + CSR_GSTAT_GID_WIDTH - 1)
 #define  CSR_GSTAT_GID			(_ULCAST_(0xff) << CSR_GSTAT_GID_SHIFT)
 #define  CSR_GSTAT_GIDBIT_SHIFT		4
 #define  CSR_GSTAT_GIDBIT_WIDTH		6
@@ -525,6 +528,12 @@
 #define  CSR_GCFG_MATC_GUEST		(_ULCAST_(0x0) << CSR_GCFG_MATC_SHITF)
 #define  CSR_GCFG_MATC_ROOT		(_ULCAST_(0x1) << CSR_GCFG_MATC_SHITF)
 #define  CSR_GCFG_MATC_NEST		(_ULCAST_(0x2) << CSR_GCFG_MATC_SHITF)
+#define  CSR_GCFG_MATP_NEST_SHIFT	2
+#define  CSR_GCFG_MATP_NEST		(_ULCAST_(0x1) << CSR_GCFG_MATP_NEST_SHIFT)
+#define  CSR_GCFG_MATP_ROOT_SHIFT	1
+#define  CSR_GCFG_MATP_ROOT		(_ULCAST_(0x1) << CSR_GCFG_MATP_ROOT_SHIFT)
+#define  CSR_GCFG_MATP_GUEST_SHIFT	0
+#define  CSR_GCFG_MATP_GUEST		(_ULCAST_(0x1) << CSR_GCFG_MATP_GUEST_SHIFT)
 
 #define LOONGARCH_CSR_GINTC		0x52	/* Guest interrupt control */
 #define  CSR_GINTC_HC_SHIFT		16
@@ -1089,12 +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 ed5da02b1c..9b36ac003f 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/pgalloc.h b/arch/loongarch/include/asm/pgalloc.h
index 79470f0b4f..4e2d6b7ca2 100644
--- a/arch/loongarch/include/asm/pgalloc.h
+++ b/arch/loongarch/include/asm/pgalloc.h
@@ -84,6 +84,7 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 
 	if (!ptdesc)
 		return NULL;
+	pagetable_pud_ctor(ptdesc);
 	pud = ptdesc_address(ptdesc);
 
 	pud_init(pud);