LoongArch: Add alternative runtime patching mechanism

Introduce the "alternative" mechanism from ARM64 and x86 for LoongArch
to apply runtime patching. The main purpose of this patch is to provide
a framework. In future we can use this mechanism (i.e., the ALTERNATIVE
and ALTERNATIVE_2 macros) to optimize hotspot functions according to cpu
features.

Signed-off-by: Jun Yi <yijun@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

arch/loongarch/include/asm/alternative-asm.h

@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ALTERNATIVE_ASM_H
+#define _ASM_ALTERNATIVE_ASM_H
+
+#ifdef __ASSEMBLY__
+
+#include <asm/asm.h>
+
+/*
+ * Issue one struct alt_instr descriptor entry (need to put it into
+ * the section .altinstructions, see below). This entry contains
+ * enough information for the alternatives patching code to patch an
+ * instruction. See apply_alternatives().
+ */
+.macro altinstruction_entry orig alt feature orig_len alt_len
+	.long \orig - .
+	.long \alt - .
+	.short \feature
+	.byte \orig_len
+	.byte \alt_len
+.endm
+
+/*
+ * Define an alternative between two instructions. If @feature is
+ * present, early code in apply_alternatives() replaces @oldinstr with
+ * @newinstr. ".fill" directive takes care of proper instruction padding
+ * in case @newinstr is longer than @oldinstr.
+ */
+.macro ALTERNATIVE oldinstr, newinstr, feature
+140 :
+	\oldinstr
+141 :
+	.fill - (((144f-143f)-(141b-140b)) > 0) * ((144f-143f)-(141b-140b)) / 4, 4, 0x03400000
+142 :
+
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 140b, 143f, \feature, 142b-140b, 144f-143f
+	.popsection
+
+	.subsection 1
+143 :
+	\newinstr
+144 :
+	.previous
+.endm
+
+#define old_len			(141b-140b)
+#define new_len1		(144f-143f)
+#define new_len2		(145f-144f)
+
+#define alt_max_short(a, b)	((a) ^ (((a) ^ (b)) & -(-((a) < (b)))))
+
+/*
+ * Same as ALTERNATIVE macro above but for two alternatives. If CPU
+ * has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
+ * @feature2, it replaces @oldinstr with @feature2.
+ */
+.macro ALTERNATIVE_2 oldinstr, newinstr1, feature1, newinstr2, feature2
+140 :
+	\oldinstr
+141 :
+	.fill - ((alt_max_short(new_len1, new_len2) - (old_len)) > 0) * \
+		(alt_max_short(new_len1, new_len2) - (old_len)) / 4, 4, 0x03400000
+142 :
+
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 140b, 143f, \feature1, 142b-140b, 144f-143f, 142b-141b
+	altinstruction_entry 140b, 144f, \feature2, 142b-140b, 145f-144f, 142b-141b
+	.popsection
+
+	.subsection 1
+143 :
+	\newinstr1
+144 :
+	\newinstr2
+145 :
+	.previous
+.endm
+
+#endif  /*  __ASSEMBLY__  */
+
+#endif /* _ASM_ALTERNATIVE_ASM_H */

arch/loongarch/include/asm/alternative.h

@@ -0,0 +1,111 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_ALTERNATIVE_H
+#define _ASM_ALTERNATIVE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+#include <asm/asm.h>
+
+struct alt_instr {
+	s32 instr_offset;	/* offset to original instruction */
+	s32 replace_offset;	/* offset to replacement instruction */
+	u16 feature;		/* feature bit set for replacement */
+	u8  instrlen;		/* length of original instruction */
+	u8  replacementlen;	/* length of new instruction */
+} __packed;
+
+/*
+ * Debug flag that can be tested to see whether alternative
+ * instructions were patched in already:
+ */
+extern int alternatives_patched;
+extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+
+extern void alternative_instructions(void);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+
+#define b_replacement(num)	"664"#num
+#define e_replacement(num)	"665"#num
+
+#define alt_end_marker		"663"
+#define alt_slen		"662b-661b"
+#define alt_total_slen		alt_end_marker"b-661b"
+#define alt_rlen(num)		e_replacement(num)"f-"b_replacement(num)"f"
+
+#define __OLDINSTR(oldinstr, num)					\
+	"661:\n\t" oldinstr "\n662:\n"					\
+	".fill -(((" alt_rlen(num) ")-(" alt_slen ")) > 0) * "		\
+		"((" alt_rlen(num) ")-(" alt_slen ")) / 4, 4, 0x03400000\n"
+
+#define OLDINSTR(oldinstr, num)						\
+	__OLDINSTR(oldinstr, num)					\
+	alt_end_marker ":\n"
+
+#define alt_max_short(a, b)	"((" a ") ^ (((" a ") ^ (" b ")) & -(-((" a ") < (" b ")))))"
+
+/*
+ * Pad the second replacement alternative with additional NOPs if it is
+ * additionally longer than the first replacement alternative.
+ */
+#define OLDINSTR_2(oldinstr, num1, num2) \
+	"661:\n\t" oldinstr "\n662:\n"								\
+	".fill -((" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) > 0) * "	\
+		"(" alt_max_short(alt_rlen(num1), alt_rlen(num2)) " - (" alt_slen ")) / 4, "	\
+		"4, 0x03400000\n"	\
+	alt_end_marker ":\n"
+
+#define ALTINSTR_ENTRY(feature, num)					      \
+	" .long 661b - .\n"				/* label           */ \
+	" .long " b_replacement(num)"f - .\n"		/* new instruction */ \
+	" .short " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte " alt_total_slen "\n"			/* source len      */ \
+	" .byte " alt_rlen(num) "\n"			/* replacement len */
+
+#define ALTINSTR_REPLACEMENT(newinstr, feature, num)	/* replacement */     \
+	b_replacement(num)":\n\t" newinstr "\n" e_replacement(num) ":\n\t"
+
+/* alternative assembly primitive: */
+#define ALTERNATIVE(oldinstr, newinstr, feature)			\
+	OLDINSTR(oldinstr, 1)						\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature, 1)					\
+	".popsection\n"							\
+	".subsection 1\n" \
+	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
+	".previous\n"
+
+#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
+	OLDINSTR_2(oldinstr, 1, 2)					\
+	".pushsection .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature1, 1)					\
+	ALTINSTR_ENTRY(feature2, 2)					\
+	".popsection\n"							\
+	".subsection 1\n" \
+	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
+	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
+	".previous\n"
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * length of oldinstr must be longer or equal the length of newinstr
+ * It can be padded with nops as needed.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, newinstr, feature)			\
+	(asm volatile (ALTERNATIVE(oldinstr, newinstr, feature) : : : "memory"))
+
+#define alternative_2(oldinstr, newinstr1, feature1, newinstr2, feature2) \
+	(asm volatile(ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2) ::: "memory"))
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_ALTERNATIVE_H */

arch/loongarch/include/asm/bugs.h

@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_BUGS_H
+#define _ASM_BUGS_H
+
+#include <asm/cpu.h>
+#include <asm/cpu-info.h>
+
+extern void check_bugs(void);
+
+#endif /* _ASM_BUGS_H */

arch/loongarch/include/asm/inst.h

@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <asm/asm.h>
 
+#define INSN_NOP		0x03400000
 #define INSN_BREAK		0x002a0000
 
 #define ADDR_IMMMASK_LU52ID	0xFFF0000000000000
@@ -28,13 +29,16 @@ enum reg0i26_op {
 enum reg1i20_op {
 	lu12iw_op	= 0x0a,
 	lu32id_op	= 0x0b,
+	pcaddi_op	= 0x0c,
 	pcaddu12i_op	= 0x0e,
 	pcaddu18i_op	= 0x0f,
 };
 
 enum reg1i21_op {
 	beqz_op		= 0x10,
 	bnez_op		= 0x11,
+	bceqz_op	= 0x12, /* bits[9:8] = 0x00 */
+	bcnez_op	= 0x12, /* bits[9:8] = 0x01 */
 };
 
 enum reg2_op {
@@ -315,6 +319,12 @@ static inline bool is_imm_negative(unsigned long val, unsigned int bit)
 	return val & (1UL << (bit - 1));
 }
 
+static inline bool is_pc_ins(union loongarch_instruction *ip)
+{
+	return ip->reg1i20_format.opcode >= pcaddi_op &&
+			ip->reg1i20_format.opcode <= pcaddu18i_op;
+}
+
 static inline bool is_branch_ins(union loongarch_instruction *ip)
 {
 	return ip->reg1i21_format.opcode >= beqz_op &&
@@ -353,6 +363,14 @@ static inline bool unsigned_imm_check(unsigned long val, unsigned int bit)
 	return val < (1UL << bit);
 }
 
+static inline unsigned long sign_extend(unsigned long val, unsigned int idx)
+{
+	if (!is_imm_negative(val, idx + 1))
+		return ((1UL << idx) - 1) & val;
+	else
+		return ~((1UL << idx) - 1) | val;
+}
+
 #define DEF_EMIT_REG0I26_FORMAT(NAME, OP)				\
 static inline void emit_##NAME(union loongarch_instruction *insn,	\
 			       int offset)				\

arch/loongarch/kernel/Makefile

@@ -8,7 +8,7 @@ extra-y		:= vmlinux.lds
 obj-y		+= head.o cpu-probe.o cacheinfo.o env.o setup.o entry.o genex.o \
 		   traps.o irq.o idle.o process.o dma.o mem.o io.o reset.o switch.o \
 		   elf.o syscall.o signal.o time.o topology.o inst.o ptrace.o vdso.o \
-		   unaligned.o
+		   alternative.o unaligned.o
 
 obj-$(CONFIG_ACPI)		+= acpi.o
 obj-$(CONFIG_EFI) 		+= efi.o