[PATCH] lib/genalloc: use try_cmpxchg in {set,clear}_bits_ll

From: Uros Bizjak
Date: Wed Jan 18 2023 - 10:07:26 EST


Use try_cmpxchg instead of cmpxchg (*ptr, old, new) == old in
{set,clear}_bits_ll. 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, try_cmpxchg implicitly assigns old *ptr value to "old"
when cmpxchg fails.

Note that the value from *ptr should be read using READ_ONCE to prevent
the compiler from merging, refetching or reordering the read.

The patch also declares these two functions inline, to ensure inlining.

No functional change intended.

Signed-off-by: Uros Bizjak <ubizjak@xxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
lib/genalloc.c | 18 ++++++++----------
1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/lib/genalloc.c b/lib/genalloc.c
index 00fc50d0a640..0c883d6fbd44 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -40,32 +40,30 @@ static inline size_t chunk_size(const struct gen_pool_chunk *chunk)
return chunk->end_addr - chunk->start_addr + 1;
}

-static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
+static inline int
+set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
{
- unsigned long val, nval;
+ unsigned long val = READ_ONCE(*addr);

- nval = *addr;
do {
- val = nval;
if (val & mask_to_set)
return -EBUSY;
cpu_relax();
- } while ((nval = cmpxchg(addr, val, val | mask_to_set)) != val);
+ } while (!try_cmpxchg(addr, &val, val | mask_to_set));

return 0;
}

-static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
+static inline int
+clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
{
- unsigned long val, nval;
+ unsigned long val = READ_ONCE(*addr);

- nval = *addr;
do {
- val = nval;
if ((val & mask_to_clear) != mask_to_clear)
return -EBUSY;
cpu_relax();
- } while ((nval = cmpxchg(addr, val, val & ~mask_to_clear)) != val);
+ } while (!try_cmpxchg(addr, &val, val & ~mask_to_clear));

return 0;
}
--
2.39.0