alpha: implement xor_unlock_is_negative_byte

Inspired by the alpha clear_bit() and arch_atomic_add_return(), this will
surely be more efficient than the generic one defined in filemap.c.

Link: https://lkml.kernel.org/r/20231004165317.1061855-9-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

arch/alpha/include/asm/bitops.h

@@ -286,6 +286,27 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 #define arch_test_bit generic_test_bit
 #define arch_test_bit_acquire generic_test_bit_acquire
 
+static inline bool xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+	unsigned long temp, old;
+
+	__asm__ __volatile__(
+	"1:	ldl_l %0,%4\n"
+	"	mov %0,%2\n"
+	"	xor %0,%3,%0\n"
+	"	stl_c %0,%1\n"
+	"	beq %0,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (*p), "=&r" (old)
+	:"Ir" (mask), "m" (*p));
+
+	return (old & BIT(7)) != 0;
+}
+#define xor_unlock_is_negative_byte xor_unlock_is_negative_byte
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..