Merge tag 'loongarch-kvm-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.7

Add LoongArch's KVM support. Loongson 3A5000/3A6000 supports hardware
assisted virtualization. With cpu virtualization, there are separate
hw-supported user mode and kernel mode in guest mode. With memory
virtualization, there are two-level hw mmu table for guest mode and host
mode. Also there is separate hw cpu timer with consant frequency in
guest mode, so that vm can migrate between hosts with different freq.
Currently, we are able to boot LoongArch Linux Guests.

Few key aspects of KVM LoongArch added by this series are:
1. Enable kvm hardware function when kvm module is loaded.
2. Implement VM and vcpu related ioctl interface such as vcpu create,
   vcpu run etc. GET_ONE_REG/SET_ONE_REG ioctl commands are use to
   get general registers one by one.
3. Hardware access about MMU, timer and csr are emulated in kernel.
4. Hardwares such as mmio and iocsr device are emulated in user space
   such as IPI, irqchips, pci devices etc.

27 files changed, 4902 insertions, 14 deletions

diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
index 21a7578142a1..edc682a94ca4 100644
--- a/Documentation/virt/kvm/api.rst
+++ b/Documentation/virt/kvm/api.rst
@@ -416,6 +416,13 @@ Reads the general purpose registers from the vcpu.
 	__u64 pc;
   };
 
+  /* LoongArch */
+  struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	unsigned long gpr[32];
+	unsigned long pc;
+  };
+
 
 4.12 KVM_SET_REGS
 -----------------
@@ -506,7 +513,7 @@ translation mode.
 ------------------
 
 :Capability: basic
-:Architectures: x86, ppc, mips, riscv
+:Architectures: x86, ppc, mips, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_interrupt (in)
 :Returns: 0 on success, negative on failure.
@@ -592,6 +599,14 @@ b) KVM_INTERRUPT_UNSET
 
 This is an asynchronous vcpu ioctl and can be invoked from any thread.
 
+LOONGARCH:
+^^^^^^^^^^
+
+Queues an external interrupt to be injected into the virtual CPU. A negative
+interrupt number dequeues the interrupt.
+
+This is an asynchronous vcpu ioctl and can be invoked from any thread.
+
 
 4.17 KVM_DEBUG_GUEST
 --------------------
@@ -737,7 +752,7 @@ signal mask.
 ----------------
 
 :Capability: basic
-:Architectures: x86
+:Architectures: x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_fpu (out)
 :Returns: 0 on success, -1 on error
@@ -746,7 +761,7 @@ Reads the floating point state from the vcpu.
 
 ::
 
-  /* for KVM_GET_FPU and KVM_SET_FPU */
+  /* x86: for KVM_GET_FPU and KVM_SET_FPU */
   struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
@@ -761,12 +776,21 @@ Reads the floating point state from the vcpu.
 	__u32 pad2;
   };
 
+  /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
+	__u32 fcsr;
+	__u64 fcc;
+	struct kvm_fpureg {
+		__u64 val64[4];
+	}fpr[32];
+  };
+
 
 4.23 KVM_SET_FPU
 ----------------
 
 :Capability: basic
-:Architectures: x86
+:Architectures: x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_fpu (in)
 :Returns: 0 on success, -1 on error
@@ -775,7 +799,7 @@ Writes the floating point state to the vcpu.
 
 ::
 
-  /* for KVM_GET_FPU and KVM_SET_FPU */
+  /* x86: for KVM_GET_FPU and KVM_SET_FPU */
   struct kvm_fpu {
 	__u8  fpr[8][16];
 	__u16 fcw;
@@ -790,6 +814,15 @@ Writes the floating point state to the vcpu.
 	__u32 pad2;
   };
 
+  /* LoongArch: for KVM_GET_FPU and KVM_SET_FPU */
+  struct kvm_fpu {
+	__u32 fcsr;
+	__u64 fcc;
+	struct kvm_fpureg {
+		__u64 val64[4];
+	}fpr[32];
+  };
+
 
 4.24 KVM_CREATE_IRQCHIP
 -----------------------
@@ -1387,7 +1420,7 @@ documentation when it pops into existence).
 -------------------
 
 :Capability: KVM_CAP_ENABLE_CAP
-:Architectures: mips, ppc, s390, x86
+:Architectures: mips, ppc, s390, x86, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_enable_cap (in)
 :Returns: 0 on success; -1 on error
@@ -1442,7 +1475,7 @@ for vm-wide capabilities.
 ---------------------
 
 :Capability: KVM_CAP_MP_STATE
-:Architectures: x86, s390, arm64, riscv
+:Architectures: x86, s390, arm64, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_mp_state (out)
 :Returns: 0 on success; -1 on error
@@ -1460,7 +1493,7 @@ Possible values are:
 
    ==========================    ===============================================
    KVM_MP_STATE_RUNNABLE         the vcpu is currently running
-                                 [x86,arm64,riscv]
+                                 [x86,arm64,riscv,loongarch]
    KVM_MP_STATE_UNINITIALIZED    the vcpu is an application processor (AP)
                                  which has not yet received an INIT signal [x86]
    KVM_MP_STATE_INIT_RECEIVED    the vcpu has received an INIT signal, and is
@@ -1516,11 +1549,14 @@ For riscv:
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu is paused or not.
 
+On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect
+whether the vcpu is runnable.
+
 4.39 KVM_SET_MP_STATE
 ---------------------
 
 :Capability: KVM_CAP_MP_STATE
-:Architectures: x86, s390, arm64, riscv
+:Architectures: x86, s390, arm64, riscv, loongarch
 :Type: vcpu ioctl
 :Parameters: struct kvm_mp_state (in)
 :Returns: 0 on success; -1 on error
@@ -1538,6 +1574,9 @@ For arm64/riscv:
 The only states that are valid are KVM_MP_STATE_STOPPED and
 KVM_MP_STATE_RUNNABLE which reflect if the vcpu should be paused or not.
 
+On LoongArch, only the KVM_MP_STATE_RUNNABLE state is used to reflect
+whether the vcpu is runnable.
+
 4.40 KVM_SET_IDENTITY_MAP_ADDR
 ------------------------------
 
@@ -2841,6 +2880,19 @@ Following are the RISC-V D-extension registers:
   0x8020 0000 0600 0020 fcsr      Floating point control and status register
 ======================= ========= =============================================
 
+LoongArch registers are mapped using the lower 32 bits. The upper 16 bits of
+that is the register group type.
+
+LoongArch csr registers are used to control guest cpu or get status of guest
+cpu, and they have the following id bit patterns::
+
+  0x9030 0000 0001 00 <reg:5> <sel:3>   (64-bit)
+
+LoongArch KVM control registers are used to implement some new defined functions
+such as set vcpu counter or reset vcpu, and they have the following id bit patterns::
+
+  0x9030 0000 0002 <reg:16>
+
 
 4.69 KVM_GET_ONE_REG
 --------------------
diff --git a/MAINTAINERS b/MAINTAINERS
index dd5de540ec0b..7f0d7cc0e693 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11522,6 +11522,18 @@ F:	include/kvm/arm_*
 F:	tools/testing/selftests/kvm/*/aarch64/
 F:	tools/testing/selftests/kvm/aarch64/
 
+KERNEL VIRTUAL MACHINE FOR LOONGARCH (KVM/LoongArch)
+M:	Tianrui Zhao <zhaotianrui@loongson.cn>
+M:	Bibo Mao <maobibo@loongson.cn>
+M:	Huacai Chen <chenhuacai@kernel.org>
+L:	kvm@vger.kernel.org
+L:	loongarch@lists.linux.dev
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
+F:	arch/loongarch/include/asm/kvm*
+F:	arch/loongarch/include/uapi/asm/kvm*
+F:	arch/loongarch/kvm/
+
 KERNEL VIRTUAL MACHINE FOR MIPS (KVM/mips)
 M:	Huacai Chen <chenhuacai@kernel.org>
 L:	linux-mips@vger.kernel.org
diff --git a/arch/loongarch/Kbuild b/arch/loongarch/Kbuild
index b01f5cdb27e0..beb8499dd8ed 100644
--- a/arch/loongarch/Kbuild
+++ b/arch/loongarch/Kbuild
@@ -3,5 +3,7 @@ obj-y += mm/
 obj-y += net/
 obj-y += vdso/
 
+obj-$(CONFIG_KVM) += kvm/
+
 # for cleaning
 subdir- += boot
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index e14396a2ddcb..d889a0b97bc1 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -129,6 +129,7 @@ config LOONGARCH
 	select HAVE_KPROBES
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_KRETPROBES
+	select HAVE_KVM
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_PCI
@@ -263,6 +264,9 @@ config AS_HAS_LASX_EXTENSION
 config AS_HAS_LBT_EXTENSION
 	def_bool $(as-instr,movscr2gr \$a0$(comma)\$scr0)
 
+config AS_HAS_LVZ_EXTENSION
+	def_bool $(as-instr,hvcl 0)
+
 menu "Kernel type and options"
 
 source "kernel/Kconfig.hz"
@@ -676,3 +680,5 @@ source "kernel/power/Kconfig"
 source "drivers/acpi/Kconfig"
 
 endmenu
+
+source "arch/loongarch/kvm/Kconfig"
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index a3b52aaa83b3..33795e4a5bd6 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -66,6 +66,8 @@ CONFIG_EFI_ZBOOT=y
 CONFIG_EFI_GENERIC_STUB_INITRD_CMDLINE_LOADER=y
 CONFIG_EFI_CAPSULE_LOADER=m
 CONFIG_EFI_TEST=m
+CONFIG_VIRTUALIZATION=y
+CONFIG_KVM=m
 CONFIG_JUMP_LABEL=y
 CONFIG_MODULES=y
 CONFIG_MODULE_FORCE_LOAD=y
diff --git a/arch/loongarch/include/asm/inst.h b/arch/loongarch/include/asm/inst.h
index 71e1ed4165c8..008a88ead60d 100644
--- a/arch/loongarch/include/asm/inst.h
+++ b/arch/loongarch/include/asm/inst.h
@@ -65,6 +65,14 @@ enum reg2_op {
 	revbd_op	= 0x0f,
 	revh2w_op	= 0x10,
 	revhd_op	= 0x11,
+	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 +326,13 @@ 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 +361,7 @@ 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;
 };
diff --git a/arch/loongarch/include/asm/kvm_csr.h b/arch/loongarch/include/asm/kvm_csr.h
new file mode 100644
index 000000000000..724ca8b7b401
--- /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 000000000000..11328700d4fa
--- /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 000000000000..099bafc6f797
--- /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