Every for_each_XXX_cpu() invocation calls cpumask_next() which is an inline
function:
static inline unsigned int cpumask_next(int n, const struct cpumask
*srcp)
{
/* -1 is a legal arg here. */
if (n != -1)
cpumask_check(n);
return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n +
1);
}
However!
find_next_bit() is regular out-of-line function which means "nr_cpu_ids" load
and
increment happen at the caller resulting in a lot of bloat
x86_64 defconfig:
add/remove: 3/0 grow/shrink: 8/373 up/down: 155/-5668 (-5513)
x86_64 allyesconfig-ish:
add/remove: 3/1 grow/shrink: 57/634 up/down: 3515/-28177 (-24662) !!!
Some archs redefine find_next_bit() but it is OK:
m68k inline but SMP is not supported
arm out-of-line
unicore32 out-of-line
Function call will happen anyway, so move load and increment into callee.
Signed-off-by: Alexey Dobriyan <[email protected]>
---
include/linux/cpumask.h | 15 +--------------
lib/cpumask.c | 16 ++++++++++++++++
2 files changed, 17 insertions(+), 14 deletions(-)
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -178,20 +178,7 @@ static inline unsigned int cpumask_first(const struct
cpumask *srcp)
return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits);
}
-/**
- * cpumask_next - get the next cpu in a cpumask
- * @n: the cpu prior to the place to search (ie. return will be > @n)
- * @srcp: the cpumask pointer
- *
- * Returns >= nr_cpu_ids if no further cpus set.
- */
-static inline unsigned int cpumask_next(int n, const struct cpumask *srcp)
-{
- /* -1 is a legal arg here. */
- if (n != -1)
- cpumask_check(n);
- return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1);
-}
+unsigned int cpumask_next(int n, const struct cpumask *srcp);
/**
* cpumask_next_zero - get the next unset cpu in a cpumask
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -6,6 +6,22 @@
#include <linux/bootmem.h>
/**
+ * cpumask_next - get the next cpu in a cpumask
+ * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @srcp: the cpumask pointer
+ *
+ * Returns >= nr_cpu_ids if no further cpus set.
+ */
+unsigned int cpumask_next(int n, const struct cpumask *srcp)
+{
+ /* -1 is a legal arg here. */
+ if (n != -1)
+ cpumask_check(n);
+ return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
+}
+EXPORT_SYMBOL(cpumask_next);
+
+/**
* cpumask_next_and - get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (ie. return will be > @n)
* @src1p: the first cpumask pointer
