x86: simplify load_unaligned_zeropad() implementation

The exception for the "unaligned access at the end of the page, next
page not mapped" never happens, but the fixup code ends up causing
trouble for compilers to optimize well.

clang in particular ends up seeing it being in the middle of a loop, and
tries desperately to optimize the exception fixup code that is never
really reached.

The simple solution is to just move all the fixups into the exception
handler itself, which moves it all out of the hot case code, and means
that the compiler never sees it or needs to worry about it.

Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 5 insertions, 43 deletions

diff --git a/arch/x86/include/asm/extable_fixup_types.h b/arch/x86/include/asm/extable_fixup_types.h
index 503622627400..991e31cfde94 100644
--- a/arch/x86/include/asm/extable_fixup_types.h
+++ b/arch/x86/include/asm/extable_fixup_types.h
@@ -64,4 +64,6 @@
 #define	EX_TYPE_UCOPY_LEN4		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(4))
 #define	EX_TYPE_UCOPY_LEN8		(EX_TYPE_UCOPY_LEN | EX_DATA_IMM(8))
 
+#define EX_TYPE_ZEROPAD			20 /* longword load with zeropad on fault */
+
 #endif
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 8338b0432b50..46b4f1f7f354 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -77,58 +77,18 @@ static inline unsigned long find_zero(unsigned long mask)
  * and the next page not being mapped, take the exception and
  * return zeroes in the non-existing part.
  */
-#ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT
-
 static inline unsigned long load_unaligned_zeropad(const void *addr)
 {
-	unsigned long offset, data;
 	unsigned long ret;
 
-	asm_volatile_goto(
+	asm volatile(
 		"1:	mov %[mem], %[ret]\n"
-
-		_ASM_EXTABLE(1b, %l[do_exception])
-
-		: [ret] "=r" (ret)
-		: [mem] "m" (*(unsigned long *)addr)
-		: : do_exception);
-
-	return ret;
-
-do_exception:
-	offset = (unsigned long)addr & (sizeof(long) - 1);
-	addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
-	data = *(unsigned long *)addr;
-	ret = data >> offset * 8;
-
-	return ret;
-}
-
-#else /* !CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
-static inline unsigned long load_unaligned_zeropad(const void *addr)
-{
-	unsigned long offset, data;
-	unsigned long ret, err = 0;
-
-	asm(	"1:	mov %[mem], %[ret]\n"
 		"2:\n"
-
-		_ASM_EXTABLE_FAULT(1b, 2b)
-
-		: [ret] "=&r" (ret), "+a" (err)
+		_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_ZEROPAD)
+		: [ret] "=r" (ret)
 		: [mem] "m" (*(unsigned long *)addr));
 
-	if (unlikely(err)) {
-		offset = (unsigned long)addr & (sizeof(long) - 1);
-		addr = (void *)((unsigned long)addr & ~(sizeof(long) - 1));
-		data = *(unsigned long *)addr;
-		ret = data >> offset * 8;
-	}
-
 	return ret;
 }
 
-#endif /* CONFIG_CC_HAS_ASM_GOTO_OUTPUT */
-
 #endif /* _ASM_WORD_AT_A_TIME_H */