[PATCH -next V4] riscv: jump_label: Optimize the code size with compressed instruction

[guoren at kernel.org]

From: Guo Ren <guoren at linux.alibaba.com>

Reduce the size of the static branch instruction and prevent atomic
update problems when CONFIG_RISCV_ISA_C=y. It also reduces the jump
range from 1MB to 4KB, but 4KB is enough for the current riscv
requirement.

Signed-off-by: Guo Ren <guoren at linux.alibaba.com>
Signed-off-by: Guo Ren <guoren at kernel.org>
---
Changelog
v4:
 - Rebase on palmer/for-next (20230324)
 - Separate from "riscv: jump_label: Fixup & Optimization"

v3:
https://lore.kernel.org/linux-riscv/20230126170607.1489141-3-guoren@kernel.org/

v2:
https://lore.kernel.org/linux-riscv/20221210100927.835145-3-guoren@kernel.org/

v1:
https://lore.kernel.org/linux-riscv/20220913094252.3555240-6-andy.chiu@sifive.com/
---
 arch/riscv/include/asm/jump_label.h | 16 +++++++++++----
 arch/riscv/kernel/jump_label.c      | 30 +++++++++++++++++++++++++++--
 2 files changed, 40 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/include/asm/jump_label.h b/arch/riscv/include/asm/jump_label.h
index 14a5ea8d8ef0..afc58c31d02b 100644
--- a/arch/riscv/include/asm/jump_label.h
+++ b/arch/riscv/include/asm/jump_label.h
@@ -12,17 +12,23 @@
 #include <linux/types.h>
 #include <asm/asm.h>
 
+#ifdef CONFIG_RISCV_ISA_C
+#define JUMP_LABEL_NOP_SIZE 2
+#else
 #define JUMP_LABEL_NOP_SIZE 4
+#endif
 
 static __always_inline bool arch_static_branch(struct static_key * const key,
 					       const bool branch)
 {
 	asm_volatile_goto(
-		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
-		"	.option norvc				\n\t"
+#ifdef CONFIG_RISCV_ISA_C
+		"1:	c.nop					\n\t"
+#else
 		"1:	nop					\n\t"
+#endif
 		"	.option pop				\n\t"
 		"	.pushsection	__jump_table, \"aw\"	\n\t"
 		"	.align		" RISCV_LGPTR "		\n\t"
@@ -40,11 +46,13 @@ static __always_inline bool arch_static_branch_jump(struct static_key * const ke
 						    const bool branch)
 {
 	asm_volatile_goto(
-		"	.align		2			\n\t"
 		"	.option push				\n\t"
 		"	.option norelax				\n\t"
-		"	.option norvc				\n\t"
+#ifdef CONFIG_RISCV_ISA_C
+		"1:	c.j		%l[label]		\n\t"
+#else
 		"1:	jal		zero, %l[label]		\n\t"
+#endif
 		"	.option pop				\n\t"
 		"	.pushsection	__jump_table, \"aw\"	\n\t"
 		"	.align		" RISCV_LGPTR "		\n\t"
diff --git a/arch/riscv/kernel/jump_label.c b/arch/riscv/kernel/jump_label.c
index e6694759dbd0..08f42c49e3a0 100644
--- a/arch/riscv/kernel/jump_label.c
+++ b/arch/riscv/kernel/jump_label.c
@@ -11,26 +11,52 @@
 #include <asm/bug.h>
 #include <asm/patch.h>
 
+#ifdef CONFIG_RISCV_ISA_C
+#define RISCV_INSN_NOP 0x0001U
+#define RISCV_INSN_C_J 0xa001U
+#else
 #define RISCV_INSN_NOP 0x00000013U
 #define RISCV_INSN_JAL 0x0000006fU
+#endif
 
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
 	void *addr = (void *)jump_entry_code(entry);
+#ifdef CONFIG_RISCV_ISA_C
+	u16 insn;
+#else
 	u32 insn;
+#endif
 
 	if (type == JUMP_LABEL_JMP) {
 		long offset = jump_entry_target(entry) - jump_entry_code(entry);
-
-		if (WARN_ON(offset & 1 || offset < -524288 || offset >= 524288))
+		if (WARN_ON(offset & 1 || offset < -2048 || offset >= 2048))
 			return;
 
+#ifdef CONFIG_RISCV_ISA_C
+		/*
+		 * 001 | imm[11|4|9:8|10|6|7|3:1|5] 01 - C.J
+		 */
+		insn = RISCV_INSN_C_J |
+			(((u16)offset & GENMASK(5, 5)) >> (5 - 2)) |
+			(((u16)offset & GENMASK(3, 1)) << (3 - 1)) |
+			(((u16)offset & GENMASK(7, 7)) >> (7 - 6)) |
+			(((u16)offset & GENMASK(6, 6)) << (7 - 6)) |
+			(((u16)offset & GENMASK(10, 10)) >> (10 - 8)) |
+			(((u16)offset & GENMASK(9, 8)) << (9 - 8)) |
+			(((u16)offset & GENMASK(4, 4)) << (11 - 4)) |
+			(((u16)offset & GENMASK(11, 11)) << (12 - 11));
+#else
+		/*
+		 * imm[20|10:1|11|19:12] | rd | 1101111 - JAL
+		 */
 		insn = RISCV_INSN_JAL |
 			(((u32)offset & GENMASK(19, 12)) << (12 - 12)) |
 			(((u32)offset & GENMASK(11, 11)) << (20 - 11)) |
 			(((u32)offset & GENMASK(10,  1)) << (21 -  1)) |
 			(((u32)offset & GENMASK(20, 20)) << (31 - 20));
+#endif
 	} else {
 		insn = RISCV_INSN_NOP;
 	}
-- 
2.36.1