FAILED: patch "[PATCH] riscv: Fix build with CONFIG_CC_OPTIMIZE_FOR_SIZE=y" failed to apply to 6.1-stable tree

The patch below does not apply to the 6.1-stable tree.
If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <[email protected]>.

Possible dependencies:

0b1d60d6dd9e ("riscv: Fix build with CONFIG_CC_OPTIMIZE_FOR_SIZE=y")

thanks,

greg k-h

------------------ original commit in Linus's tree ------------------

From 0b1d60d6dd9e2e867cc6e4277d73ea5a7ff2d4d0 Mon Sep 17 00:00:00 2001
From: Samuel Holland <[email protected]>
Date: Thu, 22 Sep 2022 01:09:58 -0500
Subject: [PATCH] riscv: Fix build with CONFIG_CC_OPTIMIZE_FOR_SIZE=y

commit 8eb060e10185 ("arch/riscv: add Zihintpause support") broke building with CONFIG_CC_OPTIMIZE_FOR_SIZE enabled (gcc 11.1.0):

CC arch/riscv/kernel/vdso/vgettimeofday.o
In file included from <command-line>:
./arch/riscv/include/asm/jump_label.h: In function 'cpu_relax':
././include/linux/compiler_types.h:285:33: warning: 'asm' operand 0 probably does not match constraints
285 | #define asm_volatile_goto(x...) asm goto(x)
| ^~~
./arch/riscv/include/asm/jump_label.h:41:9: note: in expansion of macro 'asm_volatile_goto'

   41 |         asm_volatile_goto(
      |         ^~~~~~~~~~~~~~~~~

././include/linux/compiler_types.h:285:33: error: impossible constraint in 'asm'
285 | #define asm_volatile_goto(x...) asm goto(x)
| ^~~
./arch/riscv/include/asm/jump_label.h:41:9: note: in expansion of macro 'asm_volatile_goto'

   41 |         asm_volatile_goto(
      |         ^~~~~~~~~~~~~~~~~

make[1]: *** [scripts/Makefile.build:249: arch/riscv/kernel/vdso/vgettimeofday.o] Error 1
make: *** [arch/riscv/Makefile:128: vdso_prepare] Error 2

Having a static branch in cpu_relax() is problematic because that function is widely inlined, including in some quite complex functions like in the VDSO. A quick measurement shows this static branch is responsible by itself for around 40% of the jump table.

Drop the static branch, which ends up being the same number of instructions anyway. If Zihintpause is supported, we trade the nop from the static branch for a div. If Zihintpause is unsupported, we trade the jump from the static branch for (what gets interpreted as) a nop.

index 3c8a5ca95c72..3bf10a8e665a 100644
@@ -67,7 +67,6 @@ enum riscv_isa_ext_id {
  */
 enum riscv_isa_ext_key {
 	RISCV_ISA_EXT_KEY_FPU,		/* For 'F' and 'D' */
-	RISCV_ISA_EXT_KEY_ZIHINTPAUSE,
 	RISCV_ISA_EXT_KEY_MAX,
 };
 

@@ -87,8 +86,6 @@ static __always_inline int riscv_isa_ext2key(int num)
 		return RISCV_ISA_EXT_KEY_FPU;
 	case RISCV_ISA_EXT_d:
 		return RISCV_ISA_EXT_KEY_FPU;
-	case RISCV_ISA_EXT_ZIHINTPAUSE:
-		return RISCV_ISA_EXT_KEY_ZIHINTPAUSE;
 	default:
 		return -EINVAL;
 	}

index 1e4f8b4aef79..789bdb8211a2 100644
@@ -4,30 +4,25 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/jump_label.h>
 #include <asm/barrier.h>
-#include <asm/hwcap.h>
 
 static inline void cpu_relax(void)
 {
-	if (!static_branch_likely(&riscv_isa_ext_keys[RISCV_ISA_EXT_KEY_ZIHINTPAUSE])) {
 #ifdef __riscv_muldiv
-		int dummy;
-		/* In lieu of a halt instruction, induce a long-latency stall. */
-		__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
+	int dummy;
+	/* In lieu of a halt instruction, induce a long-latency stall. */
+	__asm__ __volatile__ ("div %0, %0, zero" : "=r" (dummy));
 #endif
-	} else {
-		/*
-		 * Reduce instruction retirement.
-		 * This assumes the PC changes.
-		 */
+	/*
+	 * Reduce instruction retirement.
+	 * This assumes the PC changes.
+	 */
 #ifdef __riscv_zihintpause
-		__asm__ __volatile__ ("pause");
+	__asm__ __volatile__ ("pause");
 #else
-		/* Encoding of the pause instruction */
-		__asm__ __volatile__ (".4byte 0x100000F");
+	/* Encoding of the pause instruction */
+	__asm__ __volatile__ (".4byte 0x100000F");
 #endif
-	}
 	barrier();
 }