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 <[email protected]>
Signed-off-by: Huacai Chen <[email protected]>

Author: specialpointcentral

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

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>

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

arch/loongarch/include/asm/lbt.h

@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Author: Qi Hu <[email protected]>
+ *         Huacai Chen <[email protected]>
+ * 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 */

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;	\

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},				\

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));	\

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 */

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 {

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 */