sbitmap: Use atomic_long_try_cmpxchg in __sbitmap_queue_get_batch

Use atomic_long_try_cmpxchg instead of
atomic_long_cmpxchg (*ptr, old, new) == old in __sbitmap_queue_get_batch.
x86 CMPXCHG instruction returns success in ZF flag, so this change
saves a compare after cmpxchg (and related move instruction in front
of cmpxchg).

Also, atomic_long_cmpxchg implicitly assigns old *ptr value to "old"
when cmpxchg fails, enabling further code simplifications, e.g.
an extra memory read can be avoided in the loop.

No functional change intended.

Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/r/20220908151200.9993-1-ubizjak@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index 47cd8fb894baee9b02660c1b0df40fca455c00c0..cbfd2e677d871f37d4adffe8df36d8b9cd01bf38 100644 (file)
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -533,16 +533,16 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
                nr = find_first_zero_bit(&map->word, map_depth);
                if (nr + nr_tags <= map_depth) {
                        atomic_long_t *ptr = (atomic_long_t *) &map->word;
-                       unsigned long val, ret;
+                       unsigned long val;
 
                        get_mask = ((1UL << nr_tags) - 1) << nr;
+                       val = READ_ONCE(map->word);
                        do {
-                               val = READ_ONCE(map->word);
                                if ((val & ~get_mask) != val)
                                        goto next;
-                               ret = atomic_long_cmpxchg(ptr, val, get_mask | val);
-                       } while (ret != val);
-                       get_mask = (get_mask & ~ret) >> nr;
+                       } while (!atomic_long_try_cmpxchg(ptr, &val,
+                                                         get_mask | val));
+                       get_mask = (get_mask & ~val) >> nr;
                        if (get_mask) {
                                *offset = nr + (index << sb->shift);
                                update_alloc_hint_after_get(sb, depth, hint,