flush/clean/invalidate _dcache_range() functions are all very
similar and are quite short. They are mainly used in __dma_sync()
perf_event locate them in the top 3 consumming functions during
heavy ethernet activity

They are good candidate for inlining, as __dma_sync() does
almost nothing but calling them

Signed-off-by: Christophe Leroy <redacted>
---
New in v2

 arch/powerpc/include/asm/cacheflush.h | 55 +++++++++++++++++++++++++++--
 arch/powerpc/kernel/misc_32.S         | 65 -----------------------------------
 arch/powerpc/kernel/ppc_ksyms.c       |  2 ++
 3 files changed, 54 insertions(+), 68 deletions(-)

diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 6229e6b..6169604 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h

@@ -47,12 +47,61 @@ static inline void __flush_dcache_icache_phys(unsigned long physaddr)
 }
 #endif
 
-extern void flush_dcache_range(unsigned long start, unsigned long stop);
 #ifdef CONFIG_PPC32
-extern void clean_dcache_range(unsigned long start, unsigned long stop);
-extern void invalidate_dcache_range(unsigned long start, unsigned long stop);
+/*
+ * Write any modified data cache blocks out to memory and invalidate them.
+ * Does not invalidate the corresponding instruction cache blocks.
+ */
+static inline void flush_dcache_range(unsigned long start, unsigned long stop)
+{
+	void *addr = (void *)(start & ~(L1_CACHE_BYTES - 1));
+	unsigned int size = stop - (unsigned long)addr + (L1_CACHE_BYTES - 1);
+	unsigned int i;
+
+	for (i = 0; i < size >> L1_CACHE_SHIFT; i++, addr += L1_CACHE_BYTES)
+		dcbf(addr);
+	if (i)
+		mb();	/* sync */
+}