[PATCH] powerpc: implement clear_bit_unlock_is_negative_byte()

[Nicholas Piggin]

Commit b91e1302ad9b8 ("mm: optimize PageWaiters bit use for
unlock_page()") added a special bitop function to speed up
unlock_page(). Implement this for powerpc.

This improves the unlock_page() core code from this:

        li      9,1
        lwsync
1:      ldarx   10,0,3,0
        andc    10,10,9
        stdcx.  10,0,3
        bne-    1b
        ori     2,2,0
        ld      9,0(3)
        andi.   10,9,0x80
        beqlr
        li      4,0
        b       wake_up_page_bit

To this:

        li      10,1
        lwsync
1:      ldarx   9,0,3,0
        andc    9,9,10
        stdcx.  9,0,3
        bne-    1b
        andi.   10,9,0x80
        beqlr
        li      4,0
        b       wake_up_page_bit

In a test of elapsed time for dd writing into 16GB of already-dirty
pagecache on a POWER8 with 4K pages, which has one unlock_page per 4kB
this patch reduced overhead by 1.1%:

    N           Min           Max        Median           Avg        Stddev
x  19         2.578         2.619         2.594         2.595         0.011
+  19         2.552         2.592         2.564         2.565         0.008
Difference at 95.0% confidence
        -0.030  +/- 0.006
        -1.142% +/- 0.243%

Signed-off-by: Nicholas Piggin <npig...@gmail.com>
---
 arch/powerpc/include/asm/bitops.h | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/arch/powerpc/include/asm/bitops.h 
b/arch/powerpc/include/asm/bitops.h
index 59abc620f8e8..9add12ee13dd 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -154,6 +154,31 @@ static __inline__ int test_and_change_bit(unsigned long nr,
        return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
 }
 
+static __inline__ unsigned long clear_bit_unlock_return_word(int nr,
+                                               volatile unsigned long *addr)
+{
+       unsigned long old, t;
+       unsigned long *p = (unsigned long *)addr + BIT_WORD(nr);
+       unsigned long mask = BIT_MASK(nr);
+
+       __asm__ __volatile__ (
+       PPC_RELEASE_BARRIER
+"1:"   PPC_LLARX(%0,0,%3,0) "\n"
+       "andc %1,%0,%2\n"
+       PPC405_ERR77(0,%3)
+       PPC_STLCX "%1,0,%3\n"
+       "bne- 1b\n"
+       : "=&r" (old), "=&r" (t)
+       : "r" (mask), "r" (p)
+       : "cc", "memory");
+
+       return old;
+}
+
+/* This is a special function for mm/filemap.c */
+#define clear_bit_unlock_is_negative_byte(nr, addr)                    \
+       (clear_bit_unlock_return_word(nr, addr) & BIT_MASK(PG_waiters))
+
 #include <asm-generic/bitops/non-atomic.h>
 
 static __inline__ void __clear_bit_unlock(int nr, volatile unsigned long *addr)
-- 
2.11.0