LoongArch: Add Loongson Binary Translation (LBT) extension support

Loongson Binary Translation (LBT) is used to accelerate binary translation,
which contains 4 scratch registers (scr0 to scr3), x86/ARM eflags (eflags)
and x87 fpu stack pointer (ftop).

This patch support kernel to save/restore these registers, handle the LBT
exception and maintain sigcontext.

Signed-off-by: Qi Hu <huqi@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

19 files changed, 693 insertions, 31 deletions

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 465759f6b0edd6..21cc2e2d1f27db 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -254,6 +254,9 @@ config AS_HAS_LSX_EXTENSION
 config AS_HAS_LASX_EXTENSION
 	def_bool $(as-instr,xvld \$xr0$(comma)\$a0$(comma)0)
 
+config AS_HAS_LBT_EXTENSION
+	def_bool $(as-instr,movscr2gr \$a0$(comma)\$scr0)
+
 menu "Kernel type and options"
 
 source "kernel/Kconfig.hz"
@@ -534,6 +537,18 @@ config CPU_HAS_LASX
 
 	  If unsure, say Y.
 
+config CPU_HAS_LBT
+	bool "Support for the Loongson Binary Translation Extension"
+	depends on AS_HAS_LBT_EXTENSION
+	help
+	  Loongson Binary Translation (LBT) introduces 4 scratch registers (SCR0
+	  to SCR3), x86/ARM eflags (eflags) and x87 fpu stack pointer (ftop).
+	  Enabling this option allows the kernel to allocate and switch registers
+	  specific to LBT.
+
+	  If you want to use this feature, such as the Loongson Architecture
+	  Translator (LAT), say Y.
+
 config CPU_HAS_PREFETCH
 	bool
 	default y
diff --git a/arch/loongarch/include/asm/asm-prototypes.h b/arch/loongarch/include/asm/asm-prototypes.h
index ed06d399742083..cf8e1a4e7c19da 100644
--- a/arch/loongarch/include/asm/asm-prototypes.h
+++ b/arch/loongarch/include/asm/asm-prototypes.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/uaccess.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/mmu_context.h>
 #include <asm/page.h>
 #include <asm/ftrace.h>
diff --git a/arch/loongarch/include/asm/asmmacro.h b/arch/loongarch/include/asm/asmmacro.h
index af542a8d847f67..c9544f358c3399 100644
--- a/arch/loongarch/include/asm/asmmacro.h
+++ b/arch/loongarch/include/asm/asmmacro.h
@@ -41,12 +41,51 @@
 
 	.macro fpu_save_csr thread tmp
 	movfcsr2gr	\tmp, fcsr0
-	stptr.w	\tmp, \thread, THREAD_FCSR
+	stptr.w		\tmp, \thread, THREAD_FCSR
+#ifdef CONFIG_CPU_HAS_LBT
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp, \tmp, FPU_CSR_TM
+	beqz		\tmp, 1f
+	/* Save FTOP */
+	x86mftop	\tmp
+	stptr.w		\tmp, \thread, THREAD_FTOP
+	/* Turn off TM to ensure the order of FPR in memory independent of TM */
+	x86clrtm
+1:
+#endif
 	.endm
 
-	.macro fpu_restore_csr thread tmp
-	ldptr.w	\tmp, \thread, THREAD_FCSR
-	movgr2fcsr	fcsr0, \tmp
+	.macro fpu_restore_csr thread tmp0 tmp1
+	ldptr.w		\tmp0, \thread, THREAD_FCSR
+	movgr2fcsr	fcsr0, \tmp0
+#ifdef CONFIG_CPU_HAS_LBT
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp0, \tmp0, FPU_CSR_TM
+	beqz		\tmp0, 2f
+	/* Restore FTOP */
+	ldptr.w		\tmp0, \thread, THREAD_FTOP
+	andi		\tmp0, \tmp0, 0x7
+	la.pcrel	\tmp1, 1f
+	alsl.d		\tmp1, \tmp0, \tmp1, 3
+	jr		\tmp1
+1:
+	x86mttop	0
+	b	2f
+	x86mttop	1
+	b	2f
+	x86mttop	2
+	b	2f
+	x86mttop	3
+	b	2f
+	x86mttop	4
+	b	2f
+	x86mttop	5
+	b	2f
+	x86mttop	6
+	b	2f
+	x86mttop	7
+2:
+#endif
 	.endm
 
 	.macro fpu_save_cc thread tmp0 tmp1
@@ -246,7 +285,7 @@
 	.macro	lsx_restore_all	thread tmp0 tmp1
 	lsx_restore_data	\thread, \tmp0
 	fpu_restore_cc		\thread, \tmp0, \tmp1
-	fpu_restore_csr		\thread, \tmp0
+	fpu_restore_csr		\thread, \tmp0, \tmp1
 	.endm
 
 	.macro	lsx_save_upper vd base tmp off
@@ -456,7 +495,7 @@
 	.macro	lasx_restore_all thread tmp0 tmp1
 	lasx_restore_data	\thread, \tmp0
 	fpu_restore_cc		\thread, \tmp0, \tmp1
-	fpu_restore_csr		\thread, \tmp0
+	fpu_restore_csr		\thread, \tmp0, \tmp1
 	.endm
 
 	.macro	lasx_save_upper xd base tmp off
diff --git a/arch/loongarch/include/asm/lbt.h b/arch/loongarch/include/asm/lbt.h
new file mode 100644
index 00000000000000..e671978bf5523f
--- /dev/null
+++ b/arch/loongarch/include/asm/lbt.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Qi Hu <huqi@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_LBT_H
+#define _ASM_LBT_H
+
+#include <asm/cpu.h>
+#include <asm/current.h>
+#include <asm/loongarch.h>
+#include <asm/processor.h>
+
+extern void _init_lbt(void);
+extern void _save_lbt(struct loongarch_lbt *);
+extern void _restore_lbt(struct loongarch_lbt *);
+
+static inline int is_lbt_enabled(void)
+{
+	if (!cpu_has_lbt)
+		return 0;
+
+	return (csr_read32(LOONGARCH_CSR_EUEN) & CSR_EUEN_LBTEN) ?
+		1 : 0;
+}
+
+static inline int is_lbt_owner(void)
+{
+	return test_thread_flag(TIF_USEDLBT);
+}
+
+#ifdef CONFIG_CPU_HAS_LBT
+
+static inline void enable_lbt(void)
+{
+	if (cpu_has_lbt)
+		csr_xchg32(CSR_EUEN_LBTEN, CSR_EUEN_LBTEN, LOONGARCH_CSR_EUEN);
+}
+
+static inline void disable_lbt(void)
+{
+	if (cpu_has_lbt)
+		csr_xchg32(0, CSR_EUEN_LBTEN, LOONGARCH_CSR_EUEN);
+}
+
+static inline void __own_lbt(void)
+{
+	enable_lbt();
+	set_thread_flag(TIF_USEDLBT);
+	KSTK_EUEN(current) |= CSR_EUEN_LBTEN;
+}
+
+static inline void own_lbt_inatomic(int restore)
+{
+	if (cpu_has_lbt && !is_lbt_owner()) {
+		__own_lbt();
+		if (restore)
+			_restore_lbt(&current->thread.lbt);
+	}
+}
+
+static inline void own_lbt(int restore)
+{
+	preempt_disable();
+	own_lbt_inatomic(restore);
+	preempt_enable();
+}
+
+static inline void lose_lbt_inatomic(int save, struct task_struct *tsk)
+{
+	if (cpu_has_lbt && is_lbt_owner()) {
+		if (save)
+			_save_lbt(&tsk->thread.lbt);
+
+		disable_lbt();
+		clear_tsk_thread_flag(tsk, TIF_USEDLBT);
+	}
+	KSTK_EUEN(tsk) &= ~(CSR_EUEN_LBTEN);
+}
+
+static inline void lose_lbt(int save)
+{
+	preempt_disable();
+	lose_lbt_inatomic(save, current);
+	preempt_enable();
+}
+
+static inline void init_lbt(void)
+{
+	__own_lbt();
+	_init_lbt();
+}
+#else
+static inline void own_lbt_inatomic(int restore) {}
+static inline void lose_lbt_inatomic(int save, struct task_struct *tsk) {}
+static inline void init_lbt(void) {}
+static inline void lose_lbt(int save) {}
+#endif
+
+static inline int thread_lbt_context_live(void)
+{
+	if (!cpu_has_lbt)
+		return 0;
+
+	return test_thread_flag(TIF_LBT_CTX_LIVE);
+}
+
+#endif /* _ASM_LBT_H */
diff --git a/arch/loongarch/include/asm/loongarch.h b/arch/loongarch/include/asm/loongarch.h
index a500efe0fd9288..33531d432b492d 100644
--- a/arch/loongarch/include/asm/loongarch.h
+++ b/arch/loongarch/include/asm/loongarch.h
@@ -1410,6 +1410,10 @@ __BUILD_CSR_OP(tlbidx)
 #define FPU_CSR_RU	0x200	/* towards +Infinity */
 #define FPU_CSR_RD	0x300	/* towards -Infinity */
 
+/* Bit 6 of FPU Status Register specify the LBT TOP simulation mode */
+#define FPU_CSR_TM_SHIFT	0x6
+#define FPU_CSR_TM		(_ULCAST_(1) << FPU_CSR_TM_SHIFT)
+
 #define read_fcsr(source)	\
 ({	\
 	unsigned int __res;	\
diff --git a/arch/loongarch/include/asm/processor.h b/arch/loongarch/include/asm/processor.h
index 636e1c66398c17..c3bc44b5f5b30b 100644
--- a/arch/loongarch/include/asm/processor.h
+++ b/arch/loongarch/include/asm/processor.h
@@ -80,11 +80,22 @@ BUILD_FPR_ACCESS(32)
 BUILD_FPR_ACCESS(64)
 
 struct loongarch_fpu {
-	unsigned int	fcsr;
 	uint64_t	fcc;	/* 8x8 */
+	uint32_t	fcsr;
+	uint32_t	ftop;
 	union fpureg	fpr[NUM_FPU_REGS];
 };
 
+struct loongarch_lbt {
+	/* Scratch registers */
+	unsigned long scr0;
+	unsigned long scr1;
+	unsigned long scr2;
+	unsigned long scr3;
+	/* Eflags register */
+	unsigned long eflags;
+};
+
 #define INIT_CPUMASK { \
 	{0,} \
 }
@@ -113,15 +124,6 @@ struct thread_struct {
 	unsigned long csr_ecfg;
 	unsigned long csr_badvaddr;	/* Last user fault */
 
-	/* Scratch registers */
-	unsigned long scr0;
-	unsigned long scr1;
-	unsigned long scr2;
-	unsigned long scr3;
-
-	/* Eflags register */
-	unsigned long eflags;
-
 	/* Other stuff associated with the thread. */
 	unsigned long trap_nr;
 	unsigned long error_code;
@@ -133,6 +135,7 @@ struct thread_struct {
 	 * context because they are conditionally copied at fork().
 	 */
 	struct loongarch_fpu fpu FPU_ALIGN;
+	struct loongarch_lbt lbt; /* Also conditionally copied */
 
 	/* Hardware breakpoints pinned to this task. */
 	struct perf_event *hbp_break[LOONGARCH_MAX_BRP];
@@ -174,8 +177,9 @@ struct thread_struct {
 	 * FPU & vector registers				\
 	 */							\
 	.fpu			= {				\
-		.fcsr		= 0,				\
 		.fcc		= 0,				\
+		.fcsr		= 0,				\
+		.ftop		= 0,				\
 		.fpr		= {{{0,},},},			\
 	},							\
 	.hbp_break		= {0},				\
diff --git a/arch/loongarch/include/asm/switch_to.h b/arch/loongarch/include/asm/switch_to.h
index 24e3094bebab16..5b225aff3ba21a 100644
--- a/arch/loongarch/include/asm/switch_to.h
+++ b/arch/loongarch/include/asm/switch_to.h
@@ -7,6 +7,7 @@
 
 #include <asm/cpu-features.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 
 struct task_struct;
 
@@ -34,6 +35,7 @@ extern asmlinkage struct task_struct *__switch_to(struct task_struct *prev,
 #define switch_to(prev, next, last)						\
 do {										\
 	lose_fpu_inatomic(1, prev);						\
+	lose_lbt_inatomic(1, prev);						\
 	hw_breakpoint_thread_switch(next);					\
 	(last) = __switch_to(prev, next, task_thread_info(next),		\
 		 __builtin_return_address(0), __builtin_frame_address(0));	\
diff --git a/arch/loongarch/include/asm/thread_info.h b/arch/loongarch/include/asm/thread_info.h
index 1a3354ca056e9a..8cb653d49a5434 100644
--- a/arch/loongarch/include/asm/thread_info.h
+++ b/arch/loongarch/include/asm/thread_info.h
@@ -84,6 +84,8 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define TIF_SINGLESTEP		16	/* Single Step */
 #define TIF_LSX_CTX_LIVE	17	/* LSX context must be preserved */
 #define TIF_LASX_CTX_LIVE	18	/* LASX context must be preserved */
+#define TIF_USEDLBT		19	/* LBT was used by this task this quantum (SMP) */
+#define TIF_LBT_CTX_LIVE	20	/* LBT context must be preserved */
 
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
@@ -101,6 +103,8 @@ register unsigned long current_stack_pointer __asm__("$sp");
 #define _TIF_SINGLESTEP		(1<<TIF_SINGLESTEP)
 #define _TIF_LSX_CTX_LIVE	(1<<TIF_LSX_CTX_LIVE)
 #define _TIF_LASX_CTX_LIVE	(1<<TIF_LASX_CTX_LIVE)
+#define _TIF_USEDLBT		(1<<TIF_USEDLBT)
+#define _TIF_LBT_CTX_LIVE	(1<<TIF_LBT_CTX_LIVE)
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_THREAD_INFO_H */
diff --git a/arch/loongarch/include/uapi/asm/ptrace.h b/arch/loongarch/include/uapi/asm/ptrace.h
index 06e3be52cb0427..ac915f84165053 100644
--- a/arch/loongarch/include/uapi/asm/ptrace.h
+++ b/arch/loongarch/include/uapi/asm/ptrace.h
@@ -56,6 +56,12 @@ struct user_lasx_state {
 	uint64_t vregs[32*4];
 };
 
+struct user_lbt_state {
+	uint64_t scr[4];
+	uint32_t eflags;
+	uint32_t ftop;
+};
+
 struct user_watch_state {
 	uint64_t dbg_info;
 	struct {
diff --git a/arch/loongarch/include/uapi/asm/sigcontext.h b/arch/loongarch/include/uapi/asm/sigcontext.h
index 4cd7d16f703775..6c22f616b8f15d 100644
--- a/arch/loongarch/include/uapi/asm/sigcontext.h
+++ b/arch/loongarch/include/uapi/asm/sigcontext.h
@@ -59,4 +59,14 @@ struct lasx_context {
 	__u32	fcsr;
 };
 
+/* LBT context */
+#define LBT_CTX_MAGIC		0x42540001
+#define LBT_CTX_ALIGN		8
+struct lbt_context {
+	__u64	regs[4];
+	__u32	eflags;
+	__u32	ftop;
+};
+
+
 #endif /* _UAPI_ASM_SIGCONTEXT_H */
diff --git a/arch/loongarch/kernel/Makefile b/arch/loongarch/kernel/Makefile
index 8e279f04f9e7a8..5341dcf15a171f 100644
--- a/arch/loongarch/kernel/Makefile
+++ b/arch/loongarch/kernel/Makefile
@@ -15,6 +15,8 @@ obj-$(CONFIG_EFI) 		+= efi.o
 
 obj-$(CONFIG_CPU_HAS_FPU)	+= fpu.o kfpu.o
 
+obj-$(CONFIG_CPU_HAS_LBT)	+= lbt.o
+
 obj-$(CONFIG_ARCH_STRICT_ALIGN)	+= unaligned.o
 
 ifdef CONFIG_FUNCTION_TRACER
diff --git a/arch/loongarch/kernel/asm-offsets.c b/arch/loongarch/kernel/asm-offsets.c
index 505e4bf5960314..8da0726777edb4 100644
--- a/arch/loongarch/kernel/asm-offsets.c
+++ b/arch/loongarch/kernel/asm-offsets.c
@@ -118,13 +118,6 @@ void output_thread_defines(void)
 	OFFSET(THREAD_CSRECFG, task_struct,
 	       thread.csr_ecfg);
 
-	OFFSET(THREAD_SCR0, task_struct, thread.scr0);
-	OFFSET(THREAD_SCR1, task_struct, thread.scr1);
-	OFFSET(THREAD_SCR2, task_struct, thread.scr2);
-	OFFSET(THREAD_SCR3, task_struct, thread.scr3);
-
-	OFFSET(THREAD_EFLAGS, task_struct, thread.eflags);
-
 	OFFSET(THREAD_FPU, task_struct, thread.fpu);
 
 	OFFSET(THREAD_BVADDR, task_struct, \
@@ -172,6 +165,17 @@ void output_thread_fpu_defines(void)
 
 	OFFSET(THREAD_FCSR, loongarch_fpu, fcsr);
 	OFFSET(THREAD_FCC,  loongarch_fpu, fcc);
+	OFFSET(THREAD_FTOP, loongarch_fpu, ftop);
+	BLANK();
+}
+
+void output_thread_lbt_defines(void)
+{
+	OFFSET(THREAD_SCR0,  loongarch_lbt, scr0);
+	OFFSET(THREAD_SCR1,  loongarch_lbt, scr1);
+	OFFSET(THREAD_SCR2,  loongarch_lbt, scr2);
+	OFFSET(THREAD_SCR3,  loongarch_lbt, scr3);
+	OFFSET(THREAD_EFLAGS, loongarch_lbt, eflags);
 	BLANK();
 }
 
diff --git a/arch/loongarch/kernel/cpu-probe.c b/arch/loongarch/kernel/cpu-probe.c
index e925579c7a71ea..55320813ee0819 100644
--- a/arch/loongarch/kernel/cpu-probe.c
+++ b/arch/loongarch/kernel/cpu-probe.c
@@ -144,6 +144,20 @@ static void cpu_probe_common(struct cpuinfo_loongarch *c)
 		c->options |= LOONGARCH_CPU_LVZ;
 		elf_hwcap |= HWCAP_LOONGARCH_LVZ;
 	}
+#ifdef CONFIG_CPU_HAS_LBT
+	if (config & CPUCFG2_X86BT) {
+		c->options |= LOONGARCH_CPU_LBT_X86;
+		elf_hwcap |= HWCAP_LOONGARCH_LBT_X86;
+	}
+	if (config & CPUCFG2_ARMBT) {
+		c->options |= LOONGARCH_CPU_LBT_ARM;
+		elf_hwcap |= HWCAP_LOONGARCH_LBT_ARM;
+	}
+	if (config & CPUCFG2_MIPSBT) {
+		c->options |= LOONGARCH_CPU_LBT_MIPS;
+		elf_hwcap |= HWCAP_LOONGARCH_LBT_MIPS;
+	}
+#endif
 
 	config = read_cpucfg(LOONGARCH_CPUCFG6);
 	if (config & CPUCFG6_PMP)
diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
index 80dccf8e39a747..d53ab10f464465 100644
--- a/arch/loongarch/kernel/fpu.S
+++ b/arch/loongarch/kernel/fpu.S
@@ -138,6 +138,13 @@
 	.macro sc_save_fcsr base, tmp0
 	movfcsr2gr	\tmp0, fcsr0
 	EX	st.w	\tmp0, \base, 0
+#if defined(CONFIG_CPU_HAS_LBT)
+	/* TM bit is always 0 if LBT not supported */
+	andi		\tmp0, \tmp0, FPU_CSR_TM
+	beqz		\tmp0, 1f
+	x86clrtm
+1:
+#endif
 	.endm
 
 	.macro sc_restore_fcsr base, tmp0
@@ -309,7 +316,7 @@ EXPORT_SYMBOL(_save_fp)
  */
 SYM_FUNC_START(_restore_fp)
 	fpu_restore_double	a0 t1		# clobbers t1
-	fpu_restore_csr		a0 t1
+	fpu_restore_csr		a0 t1 t2
 	fpu_restore_cc		a0 t1 t2	# clobbers t1, t2
 	jr			ra
 SYM_FUNC_END(_restore_fp)
diff --git a/arch/loongarch/kernel/lbt.S b/arch/loongarch/kernel/lbt.S
new file mode 100644
index 00000000000000..9c75120a26d836
--- /dev/null
+++ b/arch/loongarch/kernel/lbt.S
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Qi Hu <huqi@loongson.cn>
+ *         Huacai Chen <chenhuacai@loongson.cn>
+ *
+ * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
+ */
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/asm-extable.h>
+#include <asm/asm-offsets.h>
+#include <asm/errno.h>
+#include <asm/regdef.h>
+
+#define SCR_REG_WIDTH 8
+
+	.macro	EX insn, reg, src, offs
+.ex\@:	\insn	\reg, \src, \offs
+	_asm_extable .ex\@, .L_lbt_fault
+	.endm
+
+/*
+ * Save a thread's lbt context.
+ */
+SYM_FUNC_START(_save_lbt)
+	movscr2gr	t1, $scr0		# save scr
+	stptr.d		t1, a0, THREAD_SCR0
+	movscr2gr	t1, $scr1
+	stptr.d		t1, a0, THREAD_SCR1
+	movscr2gr	t1, $scr2
+	stptr.d		t1, a0, THREAD_SCR2
+	movscr2gr	t1, $scr3
+	stptr.d		t1, a0, THREAD_SCR3
+
+	x86mfflag	t1, 0x3f		# save eflags
+	stptr.d		t1, a0, THREAD_EFLAGS
+	jr		ra
+SYM_FUNC_END(_save_lbt)
+EXPORT_SYMBOL(_save_lbt)
+
+/*
+ * Restore a thread's lbt context.
+ */
+SYM_FUNC_START(_restore_lbt)
+	ldptr.d		t1, a0, THREAD_SCR0	# restore scr
+	movgr2scr	$scr0, t1
+	ldptr.d		t1, a0, THREAD_SCR1
+	movgr2scr	$scr1, t1
+	ldptr.d		t1, a0, THREAD_SCR2
+	movgr2scr	$scr2, t1
+	ldptr.d		t1, a0, THREAD_SCR3
+	movgr2scr	$scr3, t1
+
+	ldptr.d		t1, a0, THREAD_EFLAGS	# restore eflags
+	x86mtflag	t1, 0x3f
+	jr		ra
+SYM_FUNC_END(_restore_lbt)
+EXPORT_SYMBOL(_restore_lbt)
+
+/*
+ * Load scr/eflag with zero.
+ */
+SYM_FUNC_START(_init_lbt)
+	movgr2scr	$scr0, zero
+	movgr2scr	$scr1, zero
+	movgr2scr	$scr2, zero
+	movgr2scr	$scr3, zero
+
+	x86mtflag	zero, 0x3f
+	jr		ra
+SYM_FUNC_END(_init_lbt)
+
+/*
+ * a0: scr
+ * a1: eflag
+ */
+SYM_FUNC_START(_save_lbt_context)
+	movscr2gr	t1, $scr0		# save scr
+	EX	st.d	t1, a0, (0 * SCR_REG_WIDTH)
+	movscr2gr	t1, $scr1
+	EX	st.d	t1, a0, (1 * SCR_REG_WIDTH)
+	movscr2gr	t1, $scr2
+	EX	st.d	t1, a0, (2 * SCR_REG_WIDTH)
+	movscr2gr	t1, $scr3
+	EX	st.d	t1, a0, (3 * SCR_REG_WIDTH)
+
+	x86mfflag	t1, 0x3f		# save eflags
+	EX 	st.w	t1, a1, 0
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_save_lbt_context)
+
+/*
+ * a0: scr
+ * a1: eflag
+ */
+SYM_FUNC_START(_restore_lbt_context)
+	EX	ld.d	t1, a0, (0 * SCR_REG_WIDTH)	# restore scr
+	movgr2scr	$scr0, t1
+	EX	ld.d	t1, a0, (1 * SCR_REG_WIDTH)
+	movgr2scr	$scr1, t1
+	EX	ld.d	t1, a0, (2 * SCR_REG_WIDTH)
+	movgr2scr	$scr2, t1
+	EX	ld.d	t1, a0, (3 * SCR_REG_WIDTH)
+	movgr2scr	$scr3, t1
+
+	EX 	ld.w	t1, a1, 0			# restore eflags
+	x86mtflag	t1, 0x3f
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_restore_lbt_context)
+
+/*
+ * a0: ftop
+ */
+SYM_FUNC_START(_save_ftop_context)
+	x86mftop	t1
+	st.w		t1, a0, 0
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_save_ftop_context)
+
+/*
+ * a0: ftop
+ */
+SYM_FUNC_START(_restore_ftop_context)
+	ld.w		t1, a0, 0
+	andi		t1, t1, 0x7
+	la.pcrel	a0, 1f
+	alsl.d		a0, t1, a0, 3
+	jr		a0
+1:
+	x86mttop	0
+	b	2f
+	x86mttop	1
+	b	2f
+	x86mttop	2
+	b	2f
+	x86mttop	3
+	b	2f
+	x86mttop	4
+	b	2f
+	x86mttop	5
+	b	2f
+	x86mttop	6
+	b	2f
+	x86mttop	7
+2:
+	li.w		a0, 0			# success
+	jr		ra
+SYM_FUNC_END(_restore_ftop_context)
+
+.L_lbt_fault:
+	li.w		a0, -EFAULT		# failure
+	jr		ra
diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c
index 4ee1e9d6a65f1b..91ccedd9db6ac7 100644
--- a/arch/loongarch/kernel/process.c
+++ b/arch/loongarch/kernel/process.c
@@ -38,6 +38,7 @@
 #include <asm/cpu.h>
 #include <asm/elf.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
@@ -82,9 +83,11 @@ void start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp)
 	euen = regs->csr_euen & ~(CSR_EUEN_FPEN);
 	regs->csr_euen = euen;
 	lose_fpu(0);
+	lose_lbt(0);
 
 	clear_thread_flag(TIF_LSX_CTX_LIVE);
 	clear_thread_flag(TIF_LASX_CTX_LIVE);
+	clear_thread_flag(TIF_LBT_CTX_LIVE);
 	clear_used_math();
 	regs->csr_era = pc;
 	regs->regs[3] = sp;
@@ -121,10 +124,14 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 
 	preempt_enable();
 
-	if (used_math())
-		memcpy(dst, src, sizeof(struct task_struct));
-	else
+	if (!used_math())
 		memcpy(dst, src, offsetof(struct task_struct, thread.fpu.fpr));
+	else
+		memcpy(dst, src, offsetof(struct task_struct, thread.lbt.scr0));
+
+#ifdef CONFIG_CPU_HAS_LBT
+	memcpy(&dst->thread.lbt, &src->thread.lbt, sizeof(struct loongarch_lbt));
+#endif
 
 	return 0;
 }
@@ -189,8 +196,10 @@ out:
 	ptrace_hw_copy_thread(p);
 	clear_tsk_thread_flag(p, TIF_USEDFPU);
 	clear_tsk_thread_flag(p, TIF_USEDSIMD);
+	clear_tsk_thread_flag(p, TIF_USEDLBT);
 	clear_tsk_thread_flag(p, TIF_LSX_CTX_LIVE);
 	clear_tsk_thread_flag(p, TIF_LASX_CTX_LIVE);
+	clear_tsk_thread_flag(p, TIF_LBT_CTX_LIVE);
 
 	return 0;
 }
diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
index f72adbf530c646..c114c5ef13325a 100644
--- a/arch/loongarch/kernel/ptrace.c
+++ b/arch/loongarch/kernel/ptrace.c
@@ -38,6 +38,7 @@
 #include <asm/cpu.h>
 #include <asm/cpu-info.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/loongarch.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -338,6 +339,46 @@ static int simd_set(struct task_struct *target,
 
 #endif /* CONFIG_CPU_HAS_LSX */
 
+#ifdef CONFIG_CPU_HAS_LBT
+static int lbt_get(struct task_struct *target,
+		   const struct user_regset *regset,
+		   struct membuf to)
+{
+	int r;
+
+	r = membuf_write(&to, &target->thread.lbt.scr0, sizeof(target->thread.lbt.scr0));
+	r = membuf_write(&to, &target->thread.lbt.scr1, sizeof(target->thread.lbt.scr1));
+	r = membuf_write(&to, &target->thread.lbt.scr2, sizeof(target->thread.lbt.scr2));
+	r = membuf_write(&to, &target->thread.lbt.scr3, sizeof(target->thread.lbt.scr3));
+	r = membuf_write(&to, &target->thread.lbt.eflags, sizeof(u32));
+	r = membuf_write(&to, &target->thread.fpu.ftop, sizeof(u32));
+
+	return r;
+}
+
+static int lbt_set(struct task_struct *target,
+		   const struct user_regset *regset,
+		   unsigned int pos, unsigned int count,
+		   const void *kbuf, const void __user *ubuf)
+{
+	int err = 0;
+	const int eflags_start = 4 * sizeof(target->thread.lbt.scr0);
+	const int ftop_start = eflags_start + sizeof(u32);
+
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.lbt.scr0,
+				  0, 4 * sizeof(target->thread.lbt.scr0));
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.lbt.eflags,
+				  eflags_start, ftop_start);
+	err |= user_regset_copyin(&pos, &count, &kbuf, &ubuf,
+				  &target->thread.fpu.ftop,
+				  ftop_start, ftop_start + sizeof(u32));
+
+	return err;
+}
+#endif /* CONFIG_CPU_HAS_LBT */
+
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 
 /*
@@ -802,6 +843,9 @@ enum loongarch_regset {
 #ifdef CONFIG_CPU_HAS_LASX
 	REGSET_LASX,
 #endif
+#ifdef CONFIG_CPU_HAS_LBT
+	REGSET_LBT,
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	REGSET_HW_BREAK,
 	REGSET_HW_WATCH,
@@ -853,6 +897,16 @@ static const struct user_regset loongarch64_regsets[] = {
 		.set		= simd_set,
 	},
 #endif
+#ifdef CONFIG_CPU_HAS_LBT
+	[REGSET_LBT] = {
+		.core_note_type	= NT_LOONGARCH_LBT,
+		.n		= 5,
+		.size		= sizeof(u64),
+		.align		= sizeof(u64),
+		.regset_get	= lbt_get,
+		.set		= lbt_set,
+	},
+#endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	[REGSET_HW_BREAK] = {
 		.core_note_type = NT_LOONGARCH_HW_BREAK,
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index ceb899366c0a7b..504fdfe852030f 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -32,6 +32,7 @@
 #include <asm/cacheflush.h>
 #include <asm/cpu-features.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/ucontext.h>
 #include <asm/vdso.h>
 
@@ -44,6 +45,9 @@
 /* Make sure we will not lose FPU ownership */
 #define lock_fpu_owner()	({ preempt_disable(); pagefault_disable(); })
 #define unlock_fpu_owner()	({ pagefault_enable(); preempt_enable(); })
+/* Make sure we will not lose LBT ownership */
+#define lock_lbt_owner()	({ preempt_disable(); pagefault_disable(); })
+#define unlock_lbt_owner()	({ pagefault_enable(); preempt_enable(); })
 
 /* Assembly functions to move context to/from the FPU */
 extern asmlinkage int
@@ -59,6 +63,13 @@ _save_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 extern asmlinkage int
 _restore_lasx_context(void __user *fpregs, void __user *fcc, void __user *fcsr);
 
+#ifdef CONFIG_CPU_HAS_LBT
+extern asmlinkage int _save_lbt_context(void __user *regs, void __user *eflags);
+extern asmlinkage int _restore_lbt_context(void __user *regs, void __user *eflags);
+extern asmlinkage int _save_ftop_context(void __user *ftop);
+extern asmlinkage int _restore_ftop_context(void __user *ftop);
+#endif
+
 struct rt_sigframe {
 	struct siginfo rs_info;
 	struct ucontext rs_uctx;
@@ -75,6 +86,7 @@ struct extctx_layout {
 	struct _ctx_layout fpu;
 	struct _ctx_layout lsx;
 	struct _ctx_layout lasx;
+	struct _ctx_layout lbt;
 	struct _ctx_layout end;
 };
 
@@ -215,6 +227,52 @@ static int copy_lasx_from_sigcontext(struct lasx_context __user *ctx)
 	return err;
 }
 
+#ifdef CONFIG_CPU_HAS_LBT
+static int copy_lbt_to_sigcontext(struct lbt_context __user *ctx)
+{
+	int err = 0;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	err |= __put_user(current->thread.lbt.scr0, &regs[0]);
+	err |= __put_user(current->thread.lbt.scr1, &regs[1]);
+	err |= __put_user(current->thread.lbt.scr2, &regs[2]);
+	err |= __put_user(current->thread.lbt.scr3, &regs[3]);
+	err |= __put_user(current->thread.lbt.eflags, eflags);
+
+	return err;
+}
+
+static int copy_lbt_from_sigcontext(struct lbt_context __user *ctx)
+{
+	int err = 0;
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	err |= __get_user(current->thread.lbt.scr0, &regs[0]);
+	err |= __get_user(current->thread.lbt.scr1, &regs[1]);
+	err |= __get_user(current->thread.lbt.scr2, &regs[2]);
+	err |= __get_user(current->thread.lbt.scr3, &regs[3]);
+	err |= __get_user(current->thread.lbt.eflags, eflags);
+
+	return err;
+}
+
+static int copy_ftop_to_sigcontext(struct lbt_context __user *ctx)
+{
+	uint32_t  __user *ftop	= &ctx->ftop;
+
+	return __put_user(current->thread.fpu.ftop, ftop);
+}
+
+static int copy_ftop_from_sigcontext(struct lbt_context __user *ctx)
+{
+	uint32_t  __user *ftop	= &ctx->ftop;
+
+	return __get_user(current->thread.fpu.ftop, ftop);
+}
+#endif
+
 /*
  * Wrappers for the assembly _{save,restore}_fp_context functions.
  */
@@ -272,6 +330,41 @@ static int restore_hw_lasx_context(struct lasx_context __user *ctx)
 	return _restore_lasx_context(regs, fcc, fcsr);
 }
 
+/*
+ * Wrappers for the assembly _{save,restore}_lbt_context functions.
+ */
+#ifdef CONFIG_CPU_HAS_LBT
+static int save_hw_lbt_context(struct lbt_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	return _save_lbt_context(regs, eflags);
+}
+
+static int restore_hw_lbt_context(struct lbt_context __user *ctx)
+{
+	uint64_t __user *regs	= (uint64_t *)&ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&ctx->eflags;
+
+	return _restore_lbt_context(regs, eflags);
+}
+
+static int save_hw_ftop_context(struct lbt_context __user *ctx)
+{
+	uint32_t __user *ftop	= &ctx->ftop;
+
+	return _save_ftop_context(ftop);
+}
+
+static int restore_hw_ftop_context(struct lbt_context __user *ctx)
+{
+	uint32_t __user *ftop	= &ctx->ftop;
+
+	return _restore_ftop_context(ftop);
+}
+#endif
+
 static int fcsr_pending(unsigned int __user *fcsr)
 {
 	int err, sig = 0;
@@ -519,6 +612,77 @@ static int protected_restore_lasx_context(struct extctx_layout *extctx)
 	return err ?: sig;
 }
 
+#ifdef CONFIG_CPU_HAS_LBT
+static int protected_save_lbt_context(struct extctx_layout *extctx)
+{
+	int err = 0;
+	struct sctx_info __user *info = extctx->lbt.addr;
+	struct lbt_context __user *lbt_ctx =
+		(struct lbt_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lbt_ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&lbt_ctx->eflags;
+
+	while (1) {
+		lock_lbt_owner();
+		if (is_lbt_owner())
+			err |= save_hw_lbt_context(lbt_ctx);
+		else
+			err |= copy_lbt_to_sigcontext(lbt_ctx);
+		if (is_fpu_owner())
+			err |= save_hw_ftop_context(lbt_ctx);
+		else
+			err |= copy_ftop_to_sigcontext(lbt_ctx);
+		unlock_lbt_owner();
+
+		err |= __put_user(LBT_CTX_MAGIC, &info->magic);
+		err |= __put_user(extctx->lbt.size, &info->size);
+
+		if (likely(!err))
+			break;
+		/* Touch the LBT context and try again */
+		err = __put_user(0, &regs[0]) | __put_user(0, eflags);
+
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+
+static int protected_restore_lbt_context(struct extctx_layout *extctx)
+{
+	int err = 0, tmp __maybe_unused;
+	struct sctx_info __user *info = extctx->lbt.addr;
+	struct lbt_context __user *lbt_ctx =
+		(struct lbt_context *)get_ctx_through_ctxinfo(info);
+	uint64_t __user *regs	= (uint64_t *)&lbt_ctx->regs;
+	uint32_t __user *eflags	= (uint32_t *)&lbt_ctx->eflags;
+
+	while (1) {
+		lock_lbt_owner();
+		if (is_lbt_owner())
+			err |= restore_hw_lbt_context(lbt_ctx);
+		else
+			err |= copy_lbt_from_sigcontext(lbt_ctx);
+		if (is_fpu_owner())
+			err |= restore_hw_ftop_context(lbt_ctx);
+		else
+			err |= copy_ftop_from_sigcontext(lbt_ctx);
+		unlock_lbt_owner();
+
+		if (likely(!err))
+			break;
+		/* Touch the LBT context and try again */
+		err = __get_user(tmp, &regs[0]) | __get_user(tmp, eflags);
+
+		if (err)
+			return err;
+	}
+
+	return err;
+}
+#endif
+
 static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 			    struct extctx_layout *extctx)
 {
@@ -539,6 +703,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	else if (extctx->fpu.addr)
 		err |= protected_save_fpu_context(extctx);
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (extctx->lbt.addr)
+		err |= protected_save_lbt_context(extctx);
+#endif
+
 	/* Set the "end" magic */
 	info = (struct sctx_info *)extctx->end.addr;
 	err |= __put_user(0, &info->magic);
@@ -584,6 +753,13 @@ static int parse_extcontext(struct sigcontext __user *sc, struct extctx_layout *
 			extctx->lasx.addr = info;
 			break;
 
+		case LBT_CTX_MAGIC:
+			if (size < (sizeof(struct sctx_info) +
+				    sizeof(struct lbt_context)))
+				goto invalid;
+			extctx->lbt.addr = info;
+			break;
+
 		default:
 			goto invalid;
 		}
@@ -636,6 +812,11 @@ static int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc
 	else if (extctx.fpu.addr)
 		err |= protected_restore_fpu_context(&extctx);
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (extctx.lbt.addr)
+		err |= protected_restore_lbt_context(&extctx);
+#endif
+
 bad:
 	return err;
 }
@@ -700,6 +881,13 @@ static unsigned long setup_extcontext(struct extctx_layout *extctx, unsigned lon
 			  sizeof(struct fpu_context), FPU_CTX_ALIGN, new_sp);
 	}
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (cpu_has_lbt && thread_lbt_context_live()) {
+		new_sp = extframe_alloc(extctx, &extctx->lbt,
+			  sizeof(struct lbt_context), LBT_CTX_ALIGN, new_sp);
+	}
+#endif
+
 	return new_sp;
 }
 
diff --git a/arch/loongarch/kernel/traps.c b/arch/loongarch/kernel/traps.c
index 89699db45cec17..7ed01a7b254254 100644
--- a/arch/loongarch/kernel/traps.c
+++ b/arch/loongarch/kernel/traps.c
@@ -36,6 +36,7 @@
 #include <asm/break.h>
 #include <asm/cpu.h>
 #include <asm/fpu.h>
+#include <asm/lbt.h>
 #include <asm/inst.h>
 #include <asm/loongarch.h>
 #include <asm/mmu_context.h>
@@ -966,13 +967,47 @@ out:
 	irqentry_exit(regs, state);
 }
 
+static void init_restore_lbt(void)
+{
+	if (!thread_lbt_context_live()) {
+		/* First time LBT context user */
+		init_lbt();
+		set_thread_flag(TIF_LBT_CTX_LIVE);
+	} else {
+		if (!is_lbt_owner())
+			own_lbt_inatomic(1);
+	}
+
+	BUG_ON(!is_lbt_enabled());
+}
+
 asmlinkage void noinstr do_lbt(struct pt_regs *regs)
 {
 	irqentry_state_t state = irqentry_enter(regs);
 
-	local_irq_enable();
-	force_sig(SIGILL);
-	local_irq_disable();
+	/*
+	 * BTD (Binary Translation Disable exception) can be triggered
+	 * during FP save/restore if TM (Top Mode) is on, which may
+	 * cause irq_enable during 'switch_to'. To avoid this situation
+	 * (including the user using 'MOVGR2GCSR' to turn on TM, which
+	 * will not trigger the BTE), we need to check PRMD first.
+	 */
+	if (regs->csr_prmd & CSR_PRMD_PIE)
+		local_irq_enable();
+
+	if (!cpu_has_lbt) {
+		force_sig(SIGILL);
+		goto out;
+	}
+	BUG_ON(is_lbt_enabled());
+
+	preempt_disable();
+	init_restore_lbt();
+	preempt_enable();
+
+out:
+	if (regs->csr_prmd & CSR_PRMD_PIE)
+		local_irq_disable();
 
 	irqentry_exit(regs, state);
 }