summaryrefslogtreecommitdiff
path: root/lib/cpumask.c
diff options
context:
space:
mode:
authorAlexey Dobriyan <adobriyan@gmail.com>2017-09-09 02:17:15 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2017-09-09 04:26:51 +0300
commitf22ef333c32cc683922d7e3361a83ebc31b2ac6d (patch)
tree57173374d87f88a280e80a6b7b8ee3eb237d2c0b /lib/cpumask.c
parent0ce2c2029312ed78e37b56b08fa0f59ba97ef50b (diff)
downloadlinux-f22ef333c32cc683922d7e3361a83ebc31b2ac6d.tar.xz
cpumask: make cpumask_next() out-of-line
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. Link: http://lkml.kernel.org/r/20170824230010.GA1593@avx2 Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'lib/cpumask.c')
-rw-r--r--lib/cpumask.c16
1 files changed, 16 insertions, 0 deletions
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 4731a0895760..8b1a1bd77539 100644
--- 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