linux/bitmap: Force inlining of bitmap weight functions

With this config:

  http://busybox.net/~vda/kernel_config_OPTIMIZE_INLINING_and_Os

gcc-4.7.2 generates many copies of these tiny functions:

	bitmap_weight (55 copies):
	55                      push   %rbp
	48 89 e5                mov    %rsp,%rbp
	e8 3f 3a 8b 00          callq  __bitmap_weight
	5d                      pop    %rbp
	c3                      retq

	hweight_long (23 copies):
	55                      push   %rbp
	e8 b5 65 8e 00          callq  __sw_hweight64
	48 89 e5                mov    %rsp,%rbp
	5d                      pop    %rbp
	c3                      retq

See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66122

This patch fixes this via s/inline/__always_inline/

While at it, replaced two "__inline__" with usual "inline"
(the rest of the source file uses the latter).

	    text     data      bss       dec  filename
	86971357 17195880 36659200 140826437  vmlinux.before
	86971120 17195912 36659200 140826232  vmlinux

Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Graf <tgraf@suug.ch>
Cc: linux-kernel@vger.kernel.org
Link: http://lkml.kernel.org/r/1438697716-28121-1-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index ea17cca9e6852f982b1f98a5a06f863de7324e61..9653fdb76a4273dc21cecc1ddf87ea3b7576668d 100644 (file)
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -295,7 +295,7 @@ static inline int bitmap_full(const unsigned long *src, unsigned int nbits)
        return find_first_zero_bit(src, nbits) == nbits;
 }
 
-static inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
+static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits)
 {
        if (small_const_nbits(nbits))
                return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 297f5bda4fdf66a798eef2b54b43cf3592e9c005..e63553386ae715d387fadd39c4e53650ce3e226e 100644 (file)
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -57,7 +57,7 @@ extern unsigned long __sw_hweight64(__u64 w);
             (bit) < (size);                                    \
             (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
 
-static __inline__ int get_bitmask_order(unsigned int count)
+static inline int get_bitmask_order(unsigned int count)
 {
        int order;
 
@@ -65,7 +65,7 @@ static __inline__ int get_bitmask_order(unsigned int count)
        return order;   /* We could be slightly more clever with -1 here... */
 }
 
-static __inline__ int get_count_order(unsigned int count)
+static inline int get_count_order(unsigned int count)
 {
        int order;
 
@@ -75,7 +75,7 @@ static __inline__ int get_count_order(unsigned int count)
        return order;
 }
 
-static inline unsigned long hweight_long(unsigned long w)
+static __always_inline unsigned long hweight_long(unsigned long w)
 {
        return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
 }