s390/preempt: Optimize __preempt_count_dec_and_test()

Provide an inline assembly using alternatives to avoid the need of a
base register due to relocatable lowcore when adding or subtracting
small constants from preempt_count.

Main user is preempt_enable(), which subtracts one from preempt_count
and tests if the result is zero.

With this the generated code changes from

  1000b8:       a7 19 00 00             lghi    %r1,0
  1000bc:       eb ff 13 a8 00 6e       alsi    936(%r1),-1
  1000c2:       a7 54 00 05             jnhe    1000cc <__rcu_read_unlock+0x14>

to something like this:

  1000b8:       eb ff 03 a8 00 6e       alsi    936,-1
  1000be:       a7 54 00 05             jnhe    1000c8 <__rcu_read_unlock+0x10>

Kernel image size is reduced by 45kb (bloat-o-meter -t, defconfig, gcc15).

Reviewed-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>

diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index ef6ea3163c27e77a51b82f045a9afa7c4357cb1b..6e5821bb047e28465634250989138d319676ab1d 100644 (file)
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -113,7 +113,22 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
+#ifdef __HAVE_ASM_FLAG_OUTPUTS__
+       unsigned long lc_preempt;
+       int cc;
+
+       lc_preempt = offsetof(struct lowcore, preempt_count);
+       asm_inline(
+               ALTERNATIVE("alsi       %[offzero](%%r0),%[val]\n",
+                           "alsi       %[offalt](%%r0),%[val]\n",
+                           ALT_FEATURE(MFEATURE_LOWCORE))
+               : "=@cc" (cc), "+m" (((struct lowcore *)0)->preempt_count)
+               : [offzero] "i" (lc_preempt), [val] "i" (-1),
+               [offalt] "i" (lc_preempt + LOWCORE_ALT_ADDRESS));
+       return (cc == 0) || (cc == 2);
+#else
        return __atomic_add_const_and_test(-1, &get_lowcore()->preempt_count);
+#endif
 }
 
 /*