Merge tag 'loongarch-kvm-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.11

1. Add ParaVirt steal time support.
2. Add some VM migration enhancement.
3. Add perf kvm-stat support for loongarch.

29 files changed, 551 insertions, 110 deletions

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index e38139c576ee..b81d0eba5c7e 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -143,7 +143,7 @@ config LOONGARCH
 	select HAVE_LIVEPATCH
 	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
-	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS
+	select HAVE_OBJTOOL if AS_HAS_EXPLICIT_RELOCS && AS_HAS_THIN_ADD_SUB && !CC_IS_CLANG
 	select HAVE_PCI
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
@@ -261,6 +261,9 @@ config AS_HAS_EXPLICIT_RELOCS
 config AS_HAS_FCSR_CLASS
 	def_bool $(as-instr,movfcsr2gr \$t0$(comma)\$fcsr0)
 
+config AS_HAS_THIN_ADD_SUB
+	def_bool $(cc-option,-Wa$(comma)-mthin-add-sub)
+
 config AS_HAS_LSX_EXTENSION
 	def_bool $(as-instr,vld \$vr0$(comma)\$a0$(comma)0)
 
@@ -646,6 +649,17 @@ config PARAVIRT
 	  over full virtualization.  However, when run without a hypervisor
 	  the kernel is theoretically slower and slightly larger.
 
+config PARAVIRT_TIME_ACCOUNTING
+	bool "Paravirtual steal time accounting"
+	depends on PARAVIRT
+	help
+	  Select this option to enable fine granularity task steal time
+	  accounting. Time spent executing other tasks in parallel with
+	  the current vCPU is discounted from the vCPU power. To account for
+	  that, there can be a small performance impact.
+
+	  If in doubt, say N here.
+
 endmenu
 
 config ARCH_SELECT_MEMORY_MODEL
diff --git a/arch/loongarch/Kconfig.debug b/arch/loongarch/Kconfig.debug
index 98d60630c3d4..8b2ce5b5d43e 100644
--- a/arch/loongarch/Kconfig.debug
+++ b/arch/loongarch/Kconfig.debug
@@ -28,6 +28,7 @@ config UNWINDER_PROLOGUE
 
 config UNWINDER_ORC
 	bool "ORC unwinder"
+	depends on HAVE_OBJTOOL
 	select OBJTOOL
 	help
 	  This option enables the ORC (Oops Rewind Capability) unwinder for
diff --git a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
index 8aefb0c12672..a34734a6c3ce 100644
--- a/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k0500-ref.dts
@@ -44,14 +44,14 @@
 &gmac0 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	bus_id = <0x0>;
 };
 
 &gmac1 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	bus_id = <0x1>;
 };
 
diff --git a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
index 8463fe035386..23cf26cc3e5f 100644
--- a/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k1000-ref.dts
@@ -43,7 +43,7 @@
 &gmac0 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy0>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
@@ -58,7 +58,7 @@
 &gmac1 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy1>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
diff --git a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
index 74b99bd234cc..ea9e6985d0e9 100644
--- a/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
+++ b/arch/loongarch/boot/dts/loongson-2k2000-ref.dts
@@ -92,7 +92,7 @@
 &gmac2 {
 	status = "okay";
 
-	phy-mode = "rgmii";
+	phy-mode = "rgmii-id";
 	phy-handle = <&phy2>;
 	mdio {
 		compatible = "snps,dwmac-mdio";
diff --git a/arch/loongarch/include/asm/hw_breakpoint.h b/arch/loongarch/include/asm/hw_breakpoint.h
index 21447fb1efc7..d78330916bd1 100644
--- a/arch/loongarch/include/asm/hw_breakpoint.h
+++ b/arch/loongarch/include/asm/hw_breakpoint.h
@@ -75,6 +75,8 @@ do {								\
 #define CSR_MWPC_NUM		0x3f
 
 #define CTRL_PLV_ENABLE		0x1e
+#define CTRL_PLV0_ENABLE	0x02
+#define CTRL_PLV3_ENABLE	0x10
 
 #define MWPnCFG3_LoadEn		8
 #define MWPnCFG3_StoreEn	9
@@ -101,7 +103,7 @@ struct perf_event;
 struct perf_event_attr;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-				  int *gen_len, int *gen_type, int *offset);
+				  int *gen_len, int *gen_type);
 extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_arch_parse(struct perf_event *bp,
 				    const struct perf_event_attr *attr,
diff --git a/arch/loongarch/include/asm/kvm_host.h b/arch/loongarch/include/asm/kvm_host.h
index c87b6ea0ec47..fe38f98eeff8 100644
--- a/arch/loongarch/include/asm/kvm_host.h
+++ b/arch/loongarch/include/asm/kvm_host.h
@@ -30,12 +30,17 @@
 #define KVM_PRIVATE_MEM_SLOTS		0
 
 #define KVM_HALT_POLL_NS_DEFAULT	500000
+#define KVM_REQ_TLB_FLUSH_GPA		KVM_ARCH_REQ(0)
+#define KVM_REQ_STEAL_UPDATE		KVM_ARCH_REQ(1)
 
 #define KVM_GUESTDBG_SW_BP_MASK		\
 	(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP)
 #define KVM_GUESTDBG_VALID_MASK		\
 	(KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_SW_BP | KVM_GUESTDBG_SINGLESTEP)
 
+#define KVM_DIRTY_LOG_MANUAL_CAPS	\
+	(KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | KVM_DIRTY_LOG_INITIALLY_SET)
+
 struct kvm_vm_stat {
 	struct kvm_vm_stat_generic generic;
 	u64 pages;
@@ -190,6 +195,7 @@ struct kvm_vcpu_arch {
 
 	/* vcpu's vpid */
 	u64 vpid;
+	gpa_t flush_gpa;
 
 	/* Frequency of stable timer in Hz */
 	u64 timer_mhz;
@@ -201,6 +207,13 @@ struct kvm_vcpu_arch {
 	struct kvm_mp_state mp_state;
 	/* cpucfg */
 	u32 cpucfg[KVM_MAX_CPUCFG_REGS];
+
+	/* paravirt steal time */
+	struct {
+		u64 guest_addr;
+		u64 last_steal;
+		struct gfn_to_hva_cache cache;
+	} st;
 };
 
 static inline unsigned long readl_sw_gcsr(struct loongarch_csrs *csr, int reg)
diff --git a/arch/loongarch/include/asm/kvm_para.h b/arch/loongarch/include/asm/kvm_para.h
index 4ba2312e5f8c..335fb86778e2 100644
--- a/arch/loongarch/include/asm/kvm_para.h
+++ b/arch/loongarch/include/asm/kvm_para.h
@@ -14,6 +14,7 @@
 
 #define KVM_HCALL_SERVICE		HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SERVICE)
 #define  KVM_HCALL_FUNC_IPI		1
+#define  KVM_HCALL_FUNC_NOTIFY		2
 
 #define KVM_HCALL_SWDBG			HYPERCALL_ENCODE(HYPERVISOR_KVM, KVM_HCALL_CODE_SWDBG)
 
@@ -24,6 +25,16 @@
 #define KVM_HCALL_INVALID_CODE		-1UL
 #define KVM_HCALL_INVALID_PARAMETER	-2UL
 
+#define KVM_STEAL_PHYS_VALID		BIT_ULL(0)
+#define KVM_STEAL_PHYS_MASK		GENMASK_ULL(63, 6)
+
+struct kvm_steal_time {
+	__u64 steal;
+	__u32 version;
+	__u32 flags;
+	__u32 pad[12];
+};
+
 /*
  * Hypercall interface for KVM hypervisor
  *
diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
index 590a92cb5416..c416cb7125c0 100644
--- a/arch/loongarch/include/asm/kvm_vcpu.h
+++ b/arch/loongarch/include/asm/kvm_vcpu.h
@@ -120,4 +120,9 @@ static inline void kvm_write_reg(struct kvm_vcpu *vcpu, int num, unsigned long v
 	vcpu->arch.gprs[num] = val;
 }
 
+static inline bool kvm_pvtime_supported(void)
+{
+	return !!sched_info_on();
+}
+
 #endif /* __ASM_LOONGARCH_KVM_VCPU_H__ */
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index eb09adda54b7..7a4633ef284b 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -169,6 +169,7 @@
 #define  KVM_SIGNATURE			"KVM\0"
 #define CPUCFG_KVM_FEATURE		(CPUCFG_KVM_BASE + 4)
 #define  KVM_FEATURE_IPI		BIT(1)
+#define  KVM_FEATURE_STEAL_TIME		BIT(2)
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/loongarch/include/asm/numa.h b/arch/loongarch/include/asm/numa.h
index 27f319b49862..b5f9de9f102e 100644
--- a/arch/loongarch/include/asm/numa.h
+++ b/arch/loongarch/include/asm/numa.h
@@ -56,6 +56,7 @@ extern int early_cpu_to_node(int cpu);
 static inline void early_numa_add_cpu(int cpuid, s16 node)	{ }
 static inline void numa_add_cpu(unsigned int cpu)		{ }
 static inline void numa_remove_cpu(unsigned int cpu)		{ }
+static inline void set_cpuid_to_node(int cpuid, s16 node)	{ }
 
 static inline int early_cpu_to_node(int cpu)
 {
diff --git a/arch/loongarch/include/asm/paravirt.h b/arch/loongarch/include/asm/paravirt.h
index 0965710f47f2..dddec49671ae 100644
--- a/arch/loongarch/include/asm/paravirt.h
+++ b/arch/loongarch/include/asm/paravirt.h
@@ -18,6 +18,7 @@ static inline u64 paravirt_steal_clock(int cpu)
 }
 
 int __init pv_ipi_init(void);
+int __init pv_time_init(void);
 
 #else
 
@@ -26,5 +27,9 @@ static inline int pv_ipi_init(void)
 	return 0;
 }
 
+static inline int pv_time_init(void)
+{
+	return 0;
+}
 #endif // CONFIG_PARAVIRT
 #endif
diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 45b507a7b06f..d9eafd3ee3d1 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -42,7 +42,7 @@
 	.macro JUMP_VIRT_ADDR temp1 temp2
 	li.d	\temp1, CACHE_BASE
 	pcaddi	\temp2, 0
-	or	\temp1, \temp1, \temp2
+	bstrins.d  \temp1, \temp2, (DMW_PABITS - 1), 0
 	jirl	zero, \temp1, 0xc
 	.endm
 
diff --git a/arch/loongarch/include/uapi/asm/kvm.h b/arch/loongarch/include/uapi/asm/kvm.h
index f9abef382317..ddc5cab0ffd0 100644
--- a/arch/loongarch/include/uapi/asm/kvm.h
+++ b/arch/loongarch/include/uapi/asm/kvm.h
@@ -81,7 +81,11 @@ 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)
+
+/* Device Control API on vcpu fd */
 #define KVM_LOONGARCH_VCPU_CPUCFG	0
+#define KVM_LOONGARCH_VCPU_PVTIME_CTRL	1
+#define  KVM_LOONGARCH_VCPU_PVTIME_GPA	0
 
 struct kvm_debug_exit_arch {
 };
diff --git a/arch/loongarch/kernel/head.S b/arch/loongarch/kernel/head.S
index c4f7de2e2805..4677ea8fa8e9 100644
--- a/arch/loongarch/kernel/head.S
+++ b/arch/loongarch/kernel/head.S
@@ -22,7 +22,7 @@
 _head:
 	.word	MZ_MAGIC		/* "MZ", MS-DOS header */
 	.org	0x8
-	.dword	kernel_entry		/* Kernel entry point */
+	.dword	_kernel_entry		/* Kernel entry point (physical address) */
 	.dword	_kernel_asize		/* Kernel image effective size */
 	.quad	PHYS_LINK_KADDR		/* Kernel image load offset from start of RAM */
 	.org	0x38			/* 0x20 ~ 0x37 reserved */
diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c
index fc55c4de2a11..621ad7634df7 100644
--- a/arch/loongarch/kernel/hw_breakpoint.c
+++ b/arch/loongarch/kernel/hw_breakpoint.c
@@ -174,11 +174,21 @@ void flush_ptrace_hw_breakpoint(struct task_struct *tsk)
 static int hw_breakpoint_control(struct perf_event *bp,
 				 enum hw_breakpoint_ops ops)
 {
-	u32 ctrl;
+	u32 ctrl, privilege;
 	int i, max_slots, enable;
+	struct pt_regs *regs;
 	struct perf_event **slots;
 	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
+	if (arch_check_bp_in_kernelspace(info))
+		privilege = CTRL_PLV0_ENABLE;
+	else
+		privilege = CTRL_PLV3_ENABLE;
+
+	/*  Whether bp belongs to a task. */
+	if (bp->hw.target)
+		regs = task_pt_regs(bp->hw.target);
+
 	if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		slots = this_cpu_ptr(bp_on_reg);
@@ -197,31 +207,38 @@ static int hw_breakpoint_control(struct perf_event *bp,
 	switch (ops) {
 	case HW_BREAKPOINT_INSTALL:
 		/* Set the FWPnCFG/MWPnCFG 1~4 register. */
-		write_wb_reg(CSR_CFG_ADDR, i, 0, info->address);
-		write_wb_reg(CSR_CFG_ADDR, i, 1, info->address);
-		write_wb_reg(CSR_CFG_MASK, i, 0, info->mask);
-		write_wb_reg(CSR_CFG_MASK, i, 1, info->mask);
-		write_wb_reg(CSR_CFG_ASID, i, 0, 0);
-		write_wb_reg(CSR_CFG_ASID, i, 1, 0);
 		if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
-			write_wb_reg(CSR_CFG_CTRL, i, 0, CTRL_PLV_ENABLE);
+			write_wb_reg(CSR_CFG_ADDR, i, 0, info->address);
+			write_wb_reg(CSR_CFG_MASK, i, 0, info->mask);
+			write_wb_reg(CSR_CFG_ASID, i, 0, 0);
+			write_wb_reg(CSR_CFG_CTRL, i, 0, privilege);
 		} else {
+			write_wb_reg(CSR_CFG_ADDR, i, 1, info->address);
+			write_wb_reg(CSR_CFG_MASK, i, 1, info->mask);
+			write_wb_reg(CSR_CFG_ASID, i, 1, 0);
 			ctrl = encode_ctrl_reg(info->ctrl);
-			write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | CTRL_PLV_ENABLE);
+			write_wb_reg(CSR_CFG_CTRL, i, 1, ctrl | privilege);
 		}
 		enable = csr_read64(LOONGARCH_CSR_CRMD);
 		csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD);
+		if (bp->hw.target)
+			regs->csr_prmd |= CSR_PRMD_PWE;
 		break;
 	case HW_BREAKPOINT_UNINSTALL:
 		/* Reset the FWPnCFG/MWPnCFG 1~4 register. */
-		write_wb_reg(CSR_CFG_ADDR, i, 0, 0);
-		write_wb_reg(CSR_CFG_ADDR, i, 1, 0);
-		write_wb_reg(CSR_CFG_MASK, i, 0, 0);
-		write_wb_reg(CSR_CFG_MASK, i, 1, 0);
-		write_wb_reg(CSR_CFG_CTRL, i, 0, 0);
-		write_wb_reg(CSR_CFG_CTRL, i, 1, 0);
-		write_wb_reg(CSR_CFG_ASID, i, 0, 0);
-		write_wb_reg(CSR_CFG_ASID, i, 1, 0);
+		if (info->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
+			write_wb_reg(CSR_CFG_ADDR, i, 0, 0);
+			write_wb_reg(CSR_CFG_MASK, i, 0, 0);
+			write_wb_reg(CSR_CFG_CTRL, i, 0, 0);
+			write_wb_reg(CSR_CFG_ASID, i, 0, 0);
+		} else {
+			write_wb_reg(CSR_CFG_ADDR, i, 1, 0);
+			write_wb_reg(CSR_CFG_MASK, i, 1, 0);
+			write_wb_reg(CSR_CFG_CTRL, i, 1, 0);
+			write_wb_reg(CSR_CFG_ASID, i, 1, 0);
+		}
+		if (bp->hw.target)
+			regs->csr_prmd &= ~CSR_PRMD_PWE;
 		break;
 	}
 
@@ -283,7 +300,7 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
  * to generic breakpoint descriptions.
  */
 int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-			   int *gen_len, int *gen_type, int *offset)
+			   int *gen_len, int *gen_type)
 {
 	/* Type */
 	switch (ctrl.type) {
@@ -303,11 +320,6 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 		return -EINVAL;
 	}
 
-	if (!ctrl.len)
-		return -EINVAL;
-
-	*offset = __ffs(ctrl.len);
-
 	/* Len */
 	switch (ctrl.len) {
 	case LOONGARCH_BREAKPOINT_LEN_1:
@@ -386,21 +398,17 @@ int hw_breakpoint_arch_parse(struct perf_event *bp,
 			     struct arch_hw_breakpoint *hw)
 {
 	int ret;
-	u64 alignment_mask, offset;
+	u64 alignment_mask;
 
 	/* Build the arch_hw_breakpoint. */
 	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
-	if (hw->ctrl.type != LOONGARCH_BREAKPOINT_EXECUTE)
-		alignment_mask = 0x7;
-	else
+	if (hw->ctrl.type == LOONGARCH_BREAKPOINT_EXECUTE) {
 		alignment_mask = 0x3;
-	offset = hw->address & alignment_mask;
-
-	hw->address &= ~alignment_mask;
-	hw->ctrl.len <<= offset;
+		hw->address &= ~alignment_mask;
+	}
 
 	return 0;
 }
@@ -471,12 +479,15 @@ void breakpoint_handler(struct pt_regs *regs)
 	slots = this_cpu_ptr(bp_on_reg);
 
 	for (i = 0; i < boot_cpu_data.watch_ireg_count; ++i) {
-		bp = slots[i];
-		if (bp == NULL)
-			continue;
-		perf_bp_event(bp, regs);
+		if ((csr_read32(LOONGARCH_CSR_FWPS) & (0x1 << i))) {
+			bp = slots[i];
+			if (bp == NULL)
+				continue;
+			perf_bp_event(bp, regs);
+			csr_write32(0x1 << i, LOONGARCH_CSR_FWPS);
+			update_bp_registers(regs, 0, 0);
+		}
 	}
-	update_bp_registers(regs, 0, 0);
 }
 NOKPROBE_SYMBOL(breakpoint_handler);
 
@@ -488,12 +499,15 @@ void watchpoint_handler(struct pt_regs *regs)
 	slots = this_cpu_ptr(wp_on_reg);
 
 	for (i = 0; i < boot_cpu_data.watch_dreg_count; ++i) {
-		wp = slots[i];
-		if (wp == NULL)
-			continue;
-		perf_bp_event(wp, regs);
+		if ((csr_read32(LOONGARCH_CSR_MWPS) & (0x1 << i))) {
+			wp = slots[i];
+			if (wp == NULL)
+				continue;
+			perf_bp_event(wp, regs);
+			csr_write32(0x1 << i, LOONGARCH_CSR_MWPS);
+			update_bp_registers(regs, 0, 1);
+		}
 	}
-	update_bp_registers(regs, 0, 1);
 }
 NOKPROBE_SYMBOL(watchpoint_handler);
 
diff --git a/arch/loongarch/kernel/paravirt.c b/arch/loongarch/kernel/paravirt.c
index 1633ed4f692f..9abe8b71aa48 100644
--- a/arch/loongarch/kernel/paravirt.c
+++ b/arch/loongarch/kernel/paravirt.c
@@ -4,11 +4,14 @@
 #include <linux/interrupt.h>
 #include <linux/jump_label.h>
 #include <linux/kvm_para.h>
+#include <linux/reboot.h>
 #include <linux/static_call.h>
 #include <asm/paravirt.h>
 
+static int has_steal_clock;
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
+static DEFINE_PER_CPU(struct kvm_steal_time, steal_time) __aligned(64);
 
 static u64 native_steal_clock(int cpu)
 {
@@ -17,6 +20,34 @@ static u64 native_steal_clock(int cpu)
 
 DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
 
+static bool steal_acc = true;
+
+static int __init parse_no_stealacc(char *arg)
+{
+	steal_acc = false;
+	return 0;
+}
+early_param("no-steal-acc", parse_no_stealacc);
+
+static u64 paravt_steal_clock(int cpu)
+{
+	int version;
+	u64 steal;
+	struct kvm_steal_time *src;
+
+	src = &per_cpu(steal_time, cpu);
+	do {
+
+		version = src->version;
+		virt_rmb(); /* Make sure that the version is read before the steal */
+		steal = src->steal;
+		virt_rmb(); /* Make sure that the steal is read before the next version */
+
+	} while ((version & 1) || (version != src->version));
+
+	return steal;
+}
+
 #ifdef CONFIG_SMP
 static void pv_send_ipi_single(int cpu, unsigned int action)
 {
@@ -149,3 +180,117 @@ int __init pv_ipi_init(void)
 
 	return 0;
 }
+
+static int pv_enable_steal_time(void)
+{
+	int cpu = smp_processor_id();
+	unsigned long addr;
+	struct kvm_steal_time *st;
+
+	if (!has_steal_clock)
+		return -EPERM;
+
+	st = &per_cpu(steal_time, cpu);
+	addr = per_cpu_ptr_to_phys(st);
+
+	/* The whole structure kvm_steal_time should be in one page */
+	if (PFN_DOWN(addr) != PFN_DOWN(addr + sizeof(*st))) {
+		pr_warn("Illegal PV steal time addr %lx\n", addr);
+		return -EFAULT;
+	}
+
+	addr |= KVM_STEAL_PHYS_VALID;
+	kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, KVM_FEATURE_STEAL_TIME, addr);
+
+	return 0;
+}
+
+static void pv_disable_steal_time(void)
+{
+	if (has_steal_clock)
+		kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, KVM_FEATURE_STEAL_TIME, 0);
+}
+
+#ifdef CONFIG_SMP
+static int pv_time_cpu_online(unsigned int cpu)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	pv_enable_steal_time();
+	local_irq_restore(flags);
+
+	return 0;
+}
+
+static int pv_time_cpu_down_prepare(unsigned int cpu)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	pv_disable_steal_time();
+	local_irq_restore(flags);
+
+	return 0;
+}
+#endif
+
+static void pv_cpu_reboot(void *unused)
+{
+	pv_disable_steal_time();
+}
+
+static int pv_reboot_notify(struct notifier_block *nb, unsigned long code, void *unused)
+{
+	on_each_cpu(pv_cpu_reboot, NULL, 1);
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block pv_reboot_nb = {
+	.notifier_call  = pv_reboot_notify,
+};
+
+int __init pv_time_init(void)
+{
+	int r, feature;
+
+	if (!cpu_has_hypervisor)
+		return 0;
+	if (!kvm_para_available())
+		return 0;
+
+	feature = read_cpucfg(CPUCFG_KVM_FEATURE);
+	if (!(feature & KVM_FEATURE_STEAL_TIME))
+		return 0;
+
+	has_steal_clock = 1;
+	r = pv_enable_steal_time();
+	if (r < 0) {
+		has_steal_clock = 0;
+		return 0;
+	}
+	register_reboot_notifier(&pv_reboot_nb);
+
+#ifdef CONFIG_SMP
+	r = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+				      "loongarch/pv_time:online",
+				      pv_time_cpu_online, pv_time_cpu_down_prepare);
+	if (r < 0) {
+		has_steal_clock = 0;
+		pr_err("Failed to install cpu hotplug callbacks\n");
+		return r;
+	}
+#endif
+
+	static_call_update(pv_steal_clock, paravt_steal_clock);
+
+	static_key_slow_inc(&paravirt_steal_enabled);
+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
+	if (steal_acc)
+		static_key_slow_inc(&paravirt_steal_rq_enabled);
+#endif
+
+	pr_info("Using paravirt steal-time\n");
+
+	return 0;
+}
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index c114c5ef1332..200109de1971 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -494,28 +494,14 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 				     struct arch_hw_breakpoint_ctrl ctrl,
 				     struct perf_event_attr *attr)
 {
-	int err, len, type, offset;
+	int err, len, type;
 
-	err = arch_bp_generic_fields(ctrl, &len, &type, &offset);
+	err = arch_bp_generic_fields(ctrl, &len, &type);
 	if (err)
 		return err;
 
-	switch (note_type) {
-	case NT_LOONGARCH_HW_BREAK:
-		if ((type & HW_BREAKPOINT_X) != type)
-			return -EINVAL;
-		break;
-	case NT_LOONGARCH_HW_WATCH:
-		if ((type & HW_BREAKPOINT_RW) != type)
-			return -EINVAL;
-		break;
-	default:
-		return -EINVAL;
-	}
-
 	attr->bp_len	= len;
 	attr->bp_type	= type;
-	attr->bp_addr	+= offset;
 
 	return 0;
 }
@@ -609,10 +595,27 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
 		return PTR_ERR(bp);
 
 	attr = bp->attr;
-	decode_ctrl_reg(uctrl, &ctrl);
-	err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr);
-	if (err)
-		return err;
+
+	switch (note_type) {
+	case NT_LOONGARCH_HW_BREAK:
+		ctrl.type = LOONGARCH_BREAKPOINT_EXECUTE;
+		ctrl.len = LOONGARCH_BREAKPOINT_LEN_4;
+		break;
+	case NT_LOONGARCH_HW_WATCH:
+		decode_ctrl_reg(uctrl, &ctrl);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (uctrl & CTRL_PLV_ENABLE) {
+		err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr);
+		if (err)
+			return err;
+		attr.disabled = 0;
+	} else {
+		attr.disabled = 1;
+	}
 
 	return modify_user_hw_breakpoint(bp, &attr);
 }
@@ -643,6 +646,10 @@ static int ptrace_hbp_set_addr(unsigned int note_type,
 	struct perf_event *bp;
 	struct perf_event_attr attr;
 
+	/* Kernel-space address cannot be monitored by user-space */
+	if ((unsigned long)addr >= XKPRANGE)
+		return -EINVAL;
+
 	bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx);
 	if (IS_ERR(bp))
 		return PTR_ERR(bp);
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index 60e0fe97f61a..3d048f1be143 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -282,7 +282,7 @@ static void __init fdt_setup(void)
 		return;
 
 	/* Prefer to use built-in dtb, checking its legality first. */
-	if (!fdt_check_header(__dtb_start))
+	if (IS_ENABLED(CONFIG_BUILTIN_DTB) && !fdt_check_header(__dtb_start))
 		fdt_pointer = __dtb_start;
 	else
 		fdt_pointer = efi_fdt_pointer(); /* Fallback to firmware dtb */
@@ -351,10 +351,8 @@ void __init platform_init(void)
 	arch_reserve_vmcore();
 	arch_reserve_crashkernel();
 
-#ifdef CONFIG_ACPI_TABLE_UPGRADE
-	acpi_table_upgrade();
-#endif
 #ifdef CONFIG_ACPI
+	acpi_table_upgrade();
 	acpi_gbl_use_default_register_widths = false;
 	acpi_boot_table_init();
 #endif
diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index 0dfe2388ef41..1436d2465939 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -273,7 +273,6 @@ static void __init fdt_smp_setup(void)
 
 		if (cpuid == loongson_sysconf.boot_cpu_id) {
 			cpu = 0;
-			numa_add_cpu(cpu);
 		} else {
 			cpu = cpumask_next_zero(-1, cpu_present_mask);
 		}
@@ -283,6 +282,9 @@ static void __init fdt_smp_setup(void)
 		set_cpu_present(cpu, true);
 		__cpu_number_map[cpuid] = cpu;
 		__cpu_logical_map[cpu] = cpuid;
+
+		early_numa_add_cpu(cpu, 0);
+		set_cpuid_to_node(cpuid, 0);
 	}
 
 	loongson_sysconf.nr_cpus = num_processors;
@@ -468,6 +470,7 @@ void smp_prepare_boot_cpu(void)
 	set_cpu_possible(0, true);
 	set_cpu_online(0, true);
 	set_my_cpu_offset(per_cpu_offset(0));
+	numa_add_cpu(0);
 
 	rr_node = first_node(node_online_map);
 	for_each_possible_cpu(cpu) {
diff --git a/arch/loongarch/kernel/syscall.c b/arch/loongarch/kernel/syscall.c
index b4c5acd7aa3b..8801611143ab 100644
--- a/arch/loongarch/kernel/syscall.c
+++ b/arch/loongarch/kernel/syscall.c
@@ -22,7 +22,7 @@
 #define __SYSCALL(nr, call)	[nr] = (call),
 
 SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len, unsigned long,
-		prot, unsigned long, flags, unsigned long, fd, off_t, offset)
+		prot, unsigned long, flags, unsigned long, fd, unsigned long, offset)
 {
 	if (offset & ~PAGE_MASK)
 		return -EINVAL;
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index fd5354f9be7c..46d7d40c87e3 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -15,6 +15,7 @@
 
 #include <asm/cpu-features.h>
 #include <asm/loongarch.h>
+#include <asm/paravirt.h>
 #include <asm/time.h>
 
 u64 cpu_clock_freq;
@@ -214,4 +215,5 @@ void __init time_init(void)
 
 	constant_clockevent_init();
 	constant_clocksource_init();
+	pv_time_init();
 }
diff --git a/arch/loongarch/kernel/vmlinux.lds.S b/arch/loongarch/kernel/vmlinux.lds.S
index e8e97dbf9ca4..3c7595342730 100644
--- a/arch/loongarch/kernel/vmlinux.lds.S
+++ b/arch/loongarch/kernel/vmlinux.lds.S
@@ -6,6 +6,7 @@
 
 #define PAGE_SIZE _PAGE_SIZE
 #define RO_EXCEPTION_TABLE_ALIGN	4
+#define PHYSADDR_MASK			0xffffffffffff /* 48-bit */
 
 /*
  * Put .bss..swapper_pg_dir as the first thing in .bss. This will
@@ -142,10 +143,11 @@ SECTIONS
 
 #ifdef CONFIG_EFI_STUB
 	/* header symbols */
-	_kernel_asize = _end - _text;
-	_kernel_fsize = _edata - _text;
-	_kernel_vsize = _end - __initdata_begin;
-	_kernel_rsize = _edata - __initdata_begin;
+	_kernel_entry = ABSOLUTE(kernel_entry & PHYSADDR_MASK);
+	_kernel_asize = ABSOLUTE(_end - _text);
+	_kernel_fsize = ABSOLUTE(_edata - _text);
+	_kernel_vsize = ABSOLUTE(_end - __initdata_begin);
+	_kernel_rsize = ABSOLUTE(_edata - __initdata_begin);
 #endif
 
 	.gptab.sdata : {
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index c4ef2b4d9797..248744b4d086 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
 	select KVM_MMIO
 	select HAVE_KVM_READONLY_MEM
 	select KVM_XFER_TO_GUEST_WORK
+	select SCHED_INFO
 	help
 	  Support hosting virtualized guest machines using
 	  hardware virtualization extensions. You will need
diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index c86e099af5ca..ea73f9dc2cc6 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -24,7 +24,7 @@
 static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst)
 {
 	int rd, rj;
-	unsigned int index;
+	unsigned int index, ret;
 
 	if (inst.reg2_format.opcode != cpucfg_op)
 		return EMULATE_FAIL;
@@ -50,7 +50,10 @@ static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst)
 		vcpu->arch.gprs[rd] = *(unsigned int *)KVM_SIGNATURE;
 		break;
 	case CPUCFG_KVM_FEATURE:
-		vcpu->arch.gprs[rd] = KVM_FEATURE_IPI;
+		ret = KVM_FEATURE_IPI;
+		if (kvm_pvtime_supported())
+			ret |= KVM_FEATURE_STEAL_TIME;
+		vcpu->arch.gprs[rd] = ret;
 		break;
 	default:
 		vcpu->arch.gprs[rd] = 0;
@@ -687,6 +690,34 @@ static int kvm_handle_fpu_disabled(struct kvm_vcpu *vcpu)
 	return RESUME_GUEST;
 }
 
+static long kvm_save_notify(struct kvm_vcpu *vcpu)
+{
+	unsigned long id, data;
+
+	id   = kvm_read_reg(vcpu, LOONGARCH_GPR_A1);
+	data = kvm_read_reg(vcpu, LOONGARCH_GPR_A2);
+	switch (id) {
+	case KVM_FEATURE_STEAL_TIME:
+		if (!kvm_pvtime_supported())
+			return KVM_HCALL_INVALID_CODE;
+
+		if (data & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID))
+			return KVM_HCALL_INVALID_PARAMETER;
+
+		vcpu->arch.st.guest_addr = data;
+		if (!(data & KVM_STEAL_PHYS_VALID))
+			break;
+
+		vcpu->arch.st.last_steal = current->sched_info.run_delay;
+		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+		break;
+	default:
+		break;
+	};
+
+	return 0;
+};
+
 /*
  * kvm_handle_lsx_disabled() - Guest used LSX while disabled in root.
  * @vcpu:      Virtual CPU context.
@@ -758,10 +789,13 @@ static void kvm_handle_service(struct kvm_vcpu *vcpu)
 		kvm_send_pv_ipi(vcpu);
 		ret = KVM_HCALL_SUCCESS;
 		break;
+	case KVM_HCALL_FUNC_NOTIFY:
+		ret = kvm_save_notify(vcpu);
+		break;
 	default:
 		ret = KVM_HCALL_INVALID_CODE;
 		break;
-	};
+	}
 
 	kvm_write_reg(vcpu, LOONGARCH_GPR_A0, ret);
 }
diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index 86a2f2d0cb27..844736b99d38 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -242,6 +242,7 @@ void kvm_check_vpid(struct kvm_vcpu *vcpu)
 		kvm_update_vpid(vcpu, cpu);
 		trace_kvm_vpid_change(vcpu, vcpu->arch.vpid);
 		vcpu->cpu = cpu;
+		kvm_clear_request(KVM_REQ_TLB_FLUSH_GPA, vcpu);
 	}
 
 	/* Restore GSTAT(0x50).vpid */
diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
index 98883aa23ab8..2634a9e8d82c 100644
--- a/arch/loongarch/kvm/mmu.c
+++ b/arch/loongarch/kvm/mmu.c
@@ -163,6 +163,7 @@ static kvm_pte_t *kvm_populate_gpa(struct kvm *kvm,
 
 			child = kvm_mmu_memory_cache_alloc(cache);
 			_kvm_pte_init(child, ctx.invalid_ptes[ctx.level - 1]);
+			smp_wmb(); /* Make pte visible before pmd */
 			kvm_set_pte(entry, __pa(child));
 		} else if (kvm_pte_huge(*entry)) {
 			return entry;
@@ -444,6 +445,17 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				   enum kvm_mr_change change)
 {
 	int needs_flush;
+	u32 old_flags = old ? old->flags : 0;
+	u32 new_flags = new ? new->flags : 0;
+	bool log_dirty_pages = new_flags & KVM_MEM_LOG_DIRTY_PAGES;
+
+	/* Only track memslot flags changed */
+	if (change != KVM_MR_FLAGS_ONLY)
+		return;
+
+	/* Discard dirty page tracking on readonly memslot */
+	if ((old_flags & new_flags) & KVM_MEM_READONLY)
+		return;
 
 	/*
 	 * If dirty page logging is enabled, write protect all pages in the slot
@@ -454,9 +466,14 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	 * MOVE/DELETE:	The old mappings will already have been cleaned up by
 	 *		kvm_arch_flush_shadow_memslot()
 	 */
-	if (change == KVM_MR_FLAGS_ONLY &&
-	    (!(old->flags & KVM_MEM_LOG_DIRTY_PAGES) &&
-	     new->flags & KVM_MEM_LOG_DIRTY_PAGES)) {
+	if (!(old_flags & KVM_MEM_LOG_DIRTY_PAGES) && log_dirty_pages) {
+		/*
+		 * Initially-all-set does not require write protecting any page
+		 * because they're all assumed to be dirty.
+		 */
+		if (kvm_dirty_log_manual_protect_and_init_set(kvm))
+			return;
+
 		spin_lock(&kvm->mmu_lock);
 		/* Write protect GPA page table entries */
 		needs_flush = kvm_mkclean_gpa_pt(kvm, new->base_gfn,
@@ -540,6 +557,7 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_memory_slot *slot;
+	struct page *page;
 
 	spin_lock(&kvm->mmu_lock);
 
@@ -551,10 +569,8 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ
 	}
 
 	/* Track access to pages marked old */
-	new = *ptep;
-	if (!kvm_pte_young(new))
-		new = kvm_pte_mkyoung(new);
-		/* call kvm_set_pfn_accessed() after unlock */
+	new = kvm_pte_mkyoung(*ptep);
+	/* call kvm_set_pfn_accessed() after unlock */
 
 	if (write && !kvm_pte_dirty(new)) {
 		if (!kvm_pte_write(new)) {
@@ -582,19 +598,22 @@ static int kvm_map_page_fast(struct kvm_vcpu *vcpu, unsigned long gpa, bool writ
 	if (changed) {
 		kvm_set_pte(ptep, new);
 		pfn = kvm_pte_pfn(new);
+		page = kvm_pfn_to_refcounted_page(pfn);
+		if (page)
+			get_page(page);
 	}
 	spin_unlock(&kvm->mmu_lock);
 
-	/*
-	 * Fixme: pfn may be freed after mmu_lock
-	 * kvm_try_get_pfn(pfn)/kvm_release_pfn pair to prevent this?
-	 */
-	if (kvm_pte_young(changed))
-		kvm_set_pfn_accessed(pfn);
+	if (changed) {
+		if (kvm_pte_young(changed))
+			kvm_set_pfn_accessed(pfn);
 
-	if (kvm_pte_dirty(changed)) {
-		mark_page_dirty(kvm, gfn);
-		kvm_set_pfn_dirty(pfn);
+		if (kvm_pte_dirty(changed)) {
+			mark_page_dirty(kvm, gfn);
+			kvm_set_pfn_dirty(pfn);
+		}
+		if (page)
+			put_page(page);
 	}
 	return ret;
 out:
@@ -737,6 +756,7 @@ static kvm_pte_t *kvm_split_huge(struct kvm_vcpu *vcpu, kvm_pte_t *ptep, gfn_t g
 		val += PAGE_SIZE;
 	}
 
+	smp_wmb(); /* Make pte visible before pmd */
 	/* The later kvm_flush_tlb_gpa() will flush hugepage tlb */
 	kvm_set_pte(ptep, __pa(child));
 
@@ -858,11 +878,21 @@ retry:
 
 	/* Disable dirty logging on HugePages */
 	level = 0;
-	if (!fault_supports_huge_mapping(memslot, hva, write)) {
-		level = 0;
-	} else {
+	if (fault_supports_huge_mapping(memslot, hva, write)) {
+		/* Check page level about host mmu*/
 		level = host_pfn_mapping_level(kvm, gfn, memslot);
 		if (level == 1) {
+			/*
+			 * Check page level about secondary mmu
+			 * Disable hugepage if it is normal page on
+			 * secondary mmu already
+			 */
+			ptep = kvm_populate_gpa(kvm, NULL, gpa, 0);
+			if (ptep && !kvm_pte_huge(*ptep))
+				level = 0;
+		}
+
+		if (level == 1) {
 			gfn = gfn & ~(PTRS_PER_PTE - 1);
 			pfn = pfn & ~(PTRS_PER_PTE - 1);
 		}
@@ -892,7 +922,6 @@ retry:
 		kvm_set_pfn_dirty(pfn);
 	}
 
-	kvm_set_pfn_accessed(pfn);
 	kvm_release_pfn_clean(pfn);
 out:
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
@@ -908,7 +937,8 @@ int kvm_handle_mm_fault(struct kvm_vcpu *vcpu, unsigned long gpa, bool write)
 		return ret;
 
 	/* Invalidate this entry in the TLB */
-	kvm_flush_tlb_gpa(vcpu, gpa);
+	vcpu->arch.flush_gpa = gpa;
+	kvm_make_request(KVM_REQ_TLB_FLUSH_GPA, vcpu);
 
 	return 0;
 }
diff --git a/arch/loongarch/kvm/tlb.c b/arch/loongarch/kvm/tlb.c
index 02535df6b51f..ebdbe9264e9c 100644
--- a/arch/loongarch/kvm/tlb.c
+++ b/arch/loongarch/kvm/tlb.c
@@ -23,10 +23,7 @@ void kvm_flush_tlb_all(void)
 
 void kvm_flush_tlb_gpa(struct kvm_vcpu *vcpu, unsigned long gpa)
 {
-	unsigned long flags;
-
-	local_irq_save(flags);
+	lockdep_assert_irqs_disabled();
 	gpa &= (PAGE_MASK << 1);
 	invtlb(INVTLB_GID_ADDR, read_csr_gstat() & CSR_GSTAT_GID, gpa);
-	local_irq_restore(flags);
 }
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 9e8030d45129..bdfb1a910e27 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -31,6 +31,50 @@ const struct kvm_stats_header kvm_vcpu_stats_header = {
 		       sizeof(kvm_vcpu_stats_desc),
 };
 
+static void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+	u32 version;
+	u64 steal;
+	gpa_t gpa;
+	struct kvm_memslots *slots;
+	struct kvm_steal_time __user *st;
+	struct gfn_to_hva_cache *ghc;
+
+	ghc = &vcpu->arch.st.cache;
+	gpa = vcpu->arch.st.guest_addr;
+	if (!(gpa & KVM_STEAL_PHYS_VALID))
+		return;
+
+	gpa &= KVM_STEAL_PHYS_MASK;
+	slots = kvm_memslots(vcpu->kvm);
+	if (slots->generation != ghc->generation || gpa != ghc->gpa) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st))) {
+			ghc->gpa = INVALID_GPA;
+			return;
+		}
+	}
+
+	st = (struct kvm_steal_time __user *)ghc->hva;
+	unsafe_get_user(version, &st->version, out);
+	if (version & 1)
+		version += 1; /* first time write, random junk */
+
+	version += 1;
+	unsafe_put_user(version, &st->version, out);
+	smp_wmb();
+
+	unsafe_get_user(steal, &st->steal, out);
+	steal += current->sched_info.run_delay - vcpu->arch.st.last_steal;
+	vcpu->arch.st.last_steal = current->sched_info.run_delay;
+	unsafe_put_user(steal, &st->steal, out);
+
+	smp_wmb();
+	version += 1;
+	unsafe_put_user(version, &st->version, out);
+out:
+	mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
+}
+
 /*
  * kvm_check_requests - check and handle pending vCPU requests
  *
@@ -48,9 +92,22 @@ static int kvm_check_requests(struct kvm_vcpu *vcpu)
 	if (kvm_dirty_ring_check_request(vcpu))
 		return RESUME_HOST;
 
+	if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
+		kvm_update_stolen_time(vcpu);
+
 	return RESUME_GUEST;
 }
 
+static void kvm_late_check_requests(struct kvm_vcpu *vcpu)
+{
+	lockdep_assert_irqs_disabled();
+	if (kvm_check_request(KVM_REQ_TLB_FLUSH_GPA, vcpu))
+		if (vcpu->arch.flush_gpa != INVALID_GPA) {
+			kvm_flush_tlb_gpa(vcpu, vcpu->arch.flush_gpa);
+			vcpu->arch.flush_gpa = INVALID_GPA;
+		}
+}
+
 /*
  * Check and handle pending signal and vCPU requests etc
  * Run with irq enabled and preempt enabled
@@ -101,6 +158,13 @@ static int kvm_pre_enter_guest(struct kvm_vcpu *vcpu)
 		/* Make sure the vcpu mode has been written */
 		smp_store_mb(vcpu->mode, IN_GUEST_MODE);
 		kvm_check_vpid(vcpu);
+
+		/*
+		 * Called after function kvm_check_vpid()
+		 * Since it updates CSR.GSTAT used by kvm_flush_tlb_gpa(),
+		 * and it may also clear KVM_REQ_TLB_FLUSH_GPA pending bit
+		 */
+		kvm_late_check_requests(vcpu);
 		vcpu->arch.host_eentry = csr_read64(LOONGARCH_CSR_EENTRY);
 		/* Clear KVM_LARCH_SWCSR_LATEST as CSR will change when enter guest */
 		vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
@@ -354,6 +418,17 @@ static int _kvm_getcsr(struct kvm_vcpu *vcpu, unsigned int id, u64 *val)
 		return -EINVAL;
 
 	if (id == LOONGARCH_CSR_ESTAT) {
+		preempt_disable();
+		vcpu_load(vcpu);
+		/*
+		 * Sync pending interrupts into ESTAT so that interrupt
+		 * remains during VM migration stage
+		 */
+		kvm_deliver_intr(vcpu);
+		vcpu->arch.aux_inuse &= ~KVM_LARCH_SWCSR_LATEST;
+		vcpu_put(vcpu);
+		preempt_enable();
+
 		/* ESTAT IP0~IP7 get from GINTC */
 		gintc = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_GINTC) & 0xff;
 		*val = kvm_read_sw_gcsr(csr, LOONGARCH_CSR_ESTAT) | (gintc << 2);
@@ -662,6 +737,16 @@ static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu,
 	return -ENXIO;
 }
 
+static int kvm_loongarch_pvtime_has_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	if (!kvm_pvtime_supported() ||
+			attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+		return -ENXIO;
+
+	return 0;
+}
+
 static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
 				       struct kvm_device_attr *attr)
 {
@@ -671,6 +756,9 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
 	case KVM_LOONGARCH_VCPU_CPUCFG:
 		ret = kvm_loongarch_cpucfg_has_attr(vcpu, attr);
 		break;
+	case KVM_LOONGARCH_VCPU_PVTIME_CTRL:
+		ret = kvm_loongarch_pvtime_has_attr(vcpu, attr);
+		break;
 	default:
 		break;
 	}
@@ -678,7 +766,7 @@ static int kvm_loongarch_vcpu_has_attr(struct kvm_vcpu *vcpu,
 	return ret;
 }
 
-static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
+static int kvm_loongarch_cpucfg_get_attr(struct kvm_vcpu *vcpu,
 					 struct kvm_device_attr *attr)
 {
 	int ret = 0;
@@ -694,6 +782,23 @@ static int kvm_loongarch_get_cpucfg_attr(struct kvm_vcpu *vcpu,
 	return ret;
 }
 
+static int kvm_loongarch_pvtime_get_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	u64 gpa;
+	u64 __user *user = (u64 __user *)attr->addr;
+
+	if (!kvm_pvtime_supported() ||
+			attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+		return -ENXIO;
+
+	gpa = vcpu->arch.st.guest_addr;
+	if (put_user(gpa, user))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
 				       struct kvm_device_attr *attr)
 {
@@ -701,7 +806,10 @@ static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
 
 	switch (attr->group) {
 	case KVM_LOONGARCH_VCPU_CPUCFG:
-		ret = kvm_loongarch_get_cpucfg_attr(vcpu, attr);
+		ret = kvm_loongarch_cpucfg_get_attr(vcpu, attr);
+		break;
+	case KVM_LOONGARCH_VCPU_PVTIME_CTRL:
+		ret = kvm_loongarch_pvtime_get_attr(vcpu, attr);
 		break;
 	default:
 		break;
@@ -716,6 +824,43 @@ static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu,
 	return -ENXIO;
 }
 
+static int kvm_loongarch_pvtime_set_attr(struct kvm_vcpu *vcpu,
+					 struct kvm_device_attr *attr)
+{
+	int idx, ret = 0;
+	u64 gpa, __user *user = (u64 __user *)attr->addr;
+	struct kvm *kvm = vcpu->kvm;
+
+	if (!kvm_pvtime_supported() ||
+			attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+		return -ENXIO;
+
+	if (get_user(gpa, user))
+		return -EFAULT;
+
+	if (gpa & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID))
+		return -EINVAL;
+
+	if (!(gpa & KVM_STEAL_PHYS_VALID)) {
+		vcpu->arch.st.guest_addr = gpa;
+		return 0;
+	}
+
+	/* Check the address is in a valid memslot */
+	idx = srcu_read_lock(&kvm->srcu);
+	if (kvm_is_error_hva(gfn_to_hva(kvm, gpa >> PAGE_SHIFT)))
+		ret = -EINVAL;
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	if (!ret) {
+		vcpu->arch.st.guest_addr = gpa;
+		vcpu->arch.st.last_steal = current->sched_info.run_delay;
+		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
+	}
+
+	return ret;
+}
+
 static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu,
 				       struct kvm_device_attr *attr)
 {
@@ -725,6 +870,9 @@ static int kvm_loongarch_vcpu_set_attr(struct kvm_vcpu *vcpu,
 	case KVM_LOONGARCH_VCPU_CPUCFG:
 		ret = kvm_loongarch_cpucfg_set_attr(vcpu, attr);
 		break;
+	case KVM_LOONGARCH_VCPU_PVTIME_CTRL:
+		ret = kvm_loongarch_pvtime_set_attr(vcpu, attr);
+		break;
 	default:
 		break;
 	}
@@ -994,6 +1142,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	struct loongarch_csrs *csr;
 
 	vcpu->arch.vpid = 0;
+	vcpu->arch.flush_gpa = INVALID_GPA;
 
 	hrtimer_init(&vcpu->arch.swtimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	vcpu->arch.swtimer.function = kvm_swtimer_wakeup;
@@ -1084,6 +1233,7 @@ static int _kvm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Control guest page CCA attribute */
 	change_csr_gcfg(CSR_GCFG_MATC_MASK, CSR_GCFG_MATC_ROOT);
+	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 
 	/* Don't bother restoring registers multiple times unless necessary */
 	if (vcpu->arch.aux_inuse & KVM_LARCH_HWCSR_USABLE)