[PATCH v4 2/5] m68k/bitops: use __builtin_{clz,ctzl,ffs} to evaluate constant expressions

From: Vincent Mailhol
Date: Sun Jan 28 2024 - 00:06:52 EST


The compiler is not able to do constant folding on "asm volatile" code.

Evaluate whether or not the function argument is a constant expression
and if this is the case, return an equivalent builtin expression.

On linux 6.7 with an allyesconfig and GCC 13.2.1, it saves roughly 11 KB.

$ size --format=GNU vmlinux.before vmlinux.after
text data bss total filename
60457964 70953697 2288644 133700305 vmlinux.before
60441196 70957057 2290724 133688977 vmlinux.after

Reference: commit fdb6649ab7c1 ("x86/asm/bitops: Use __builtin_ctzl() to evaluate constant expressions")
Link: https://git.kernel.org/torvalds/c/fdb6649ab7c1

Reviewed-by: Geert Uytterhoeven <geert@xxxxxxxxxxxxxx>
Signed-off-by: Vincent Mailhol <mailhol.vincent@xxxxxxxxxx>
---
arch/m68k/include/asm/bitops.h | 12 ++++++++++++
1 file changed, 12 insertions(+)

diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index a8b23f897f24..02ec8a193b96 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -469,6 +469,9 @@ static __always_inline unsigned long ffz(unsigned long word)
{
int res;

+ if (__builtin_constant_p(word))
+ return __builtin_ctzl(~word);
+
__asm__ __volatile__ ("bfffo %1{#0,#0},%0"
: "=d" (res) : "d" (~word & -~word));
return res ^ 31;
@@ -490,6 +493,9 @@ static __always_inline unsigned long ffz(unsigned long word)
!defined(CONFIG_M68000)
static __always_inline unsigned long __ffs(unsigned long x)
{
+ if (__builtin_constant_p(x))
+ return __builtin_ctzl(x);
+
__asm__ __volatile__ ("bitrev %0; ff1 %0"
: "=d" (x)
: "0" (x));
@@ -522,6 +528,9 @@ static __always_inline int ffs(int x)
{
int cnt;

+ if (__builtin_constant_p(x))
+ return __builtin_ffs(x);
+
__asm__ ("bfffo %1{#0:#0},%0"
: "=d" (cnt)
: "dm" (x & -x));
@@ -540,6 +549,9 @@ static __always_inline int fls(unsigned int x)
{
int cnt;

+ if (__builtin_constant_p(x))
+ return x ? BITS_PER_TYPE(x) - __builtin_clz(x) : 0;
+
__asm__ ("bfffo %1{#0,#0},%0"
: "=d" (cnt)
: "dm" (x));
--
2.43.0