[tip: x86/core] x86/word-at-a-time: Remove .fixup usage

[tip-bot2 for Peter Zijlstra]

The following commit has been merged into the x86/core branch of tip:

Commit-ID:     b7760780257354bb14de62abed868405b844fa13
Gitweb:        https://git.kernel.org/tip/b7760780257354bb14de62abed868405b844fa13
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Wed, 10 Nov 2021 11:01:23 +01:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Sat, 11 Dec 2021 09:09:50 +01:00

x86/word-at-a-time: Remove .fixup usage

Rewrite load_unaligned_zeropad() to not require .fixup text.

This is easiest done using asm-goto-output, where we can stick a C
label in the exception table entry. The fallback version isn't nearly
so nice but should work.

Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Reviewed-by: Josh Poimboeuf <jpoimboe@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20211110101326.141775772@xxxxxxxxxxxxx
---
 arch/x86/include/asm/word-at-a-time.h | 66 ++++++++++++++++++--------
 1 file changed, 47 insertions(+), 19 deletions(-)

diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
index 06006b0..8338b04 100644
--- a/arch/x86/include/asm/word-at-a-time.h
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -77,30 +77,58 @@ 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 ret, dummy;
+	unsigned long offset, data;
+	unsigned long ret;
+
+	asm_volatile_goto(
+		"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;
+}
 
-	asm(
-		"1:\tmov %2,%0\n"
+#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"
-		".section .fixup,\"ax\"\n"
-		"3:\t"
-		"lea %2,%1\n\t"
-		"and %3,%1\n\t"
-		"mov (%1),%0\n\t"
-		"leal %2,%%ecx\n\t"
-		"andl %4,%%ecx\n\t"
-		"shll $3,%%ecx\n\t"
-		"shr %%cl,%0\n\t"
-		"jmp 2b\n"
-		".previous\n"
-		_ASM_EXTABLE(1b, 3b)
-		:"=&r" (ret),"=&c" (dummy)
-		:"m" (*(unsigned long *)addr),
-		 "i" (-sizeof(unsigned long)),
-		 "i" (sizeof(unsigned long)-1));
+
+		_ASM_EXTABLE_FAULT(1b, 2b)
+
+		: [ret] "=&r" (ret), "+a" (err)
+		: [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 */