powerpc/64: reuse PPC32 static inline flush_dcache_range()

This patch drops the assembly PPC64 version of flush_dcache_range()
and re-uses the PPC32 static inline version.

With GCC 8.1, the following code is generated:

void flush_test(unsigned long start, unsigned long stop)
{
	flush_dcache_range(start, stop);
}

0000000000000130 <.flush_test>:
 130:	3d 22 00 00 	addis   r9,r2,0
			132: R_PPC64_TOC16_HA	.data+0x8
 134:	81 09 00 00 	lwz     r8,0(r9)
			136: R_PPC64_TOC16_LO	.data+0x8
 138:	3d 22 00 00 	addis   r9,r2,0
			13a: R_PPC64_TOC16_HA	.data+0xc
 13c:	80 e9 00 00 	lwz     r7,0(r9)
			13e: R_PPC64_TOC16_LO	.data+0xc
 140:	7d 48 00 d0 	neg     r10,r8
 144:	7d 43 18 38 	and     r3,r10,r3
 148:	7c 00 04 ac 	hwsync
 14c:	4c 00 01 2c 	isync
 150:	39 28 ff ff 	addi    r9,r8,-1
 154:	7c 89 22 14 	add     r4,r9,r4
 158:	7c 83 20 50 	subf    r4,r3,r4
 15c:	7c 89 3c 37 	srd.    r9,r4,r7
 160:	41 82 00 1c 	beq     17c <.flush_test+0x4c>
 164:	7d 29 03 a6 	mtctr   r9
 168:	60 00 00 00 	nop
 16c:	60 00 00 00 	nop
 170:	7c 00 18 ac 	dcbf    0,r3
 174:	7c 63 42 14 	add     r3,r3,r8
 178:	42 00 ff f8 	bdnz    170 <.flush_test+0x40>
 17c:	7c 00 04 ac 	hwsync
 180:	4c 00 01 2c 	isync
 184:	4e 80 00 20 	blr
 188:	60 00 00 00 	nop
 18c:	60 00 00 00 	nop
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/include/asm/cache.h

@@ -54,6 +54,16 @@ struct ppc64_caches {
 };
 
 extern struct ppc64_caches ppc64_caches;
+
+static inline u32 l1_cache_shift(void)
+{
+	return ppc64_caches.l1d.log_block_size;
+}
+
+static inline u32 l1_cache_bytes(void)
+{
+	return ppc64_caches.l1d.block_size;
+}
 #else
 static inline u32 l1_cache_shift(void)
 {

arch/powerpc/include/asm/cacheflush.h

@@ -60,7 +60,6 @@ static inline void __flush_dcache_icache_phys(unsigned long physaddr)
 }
 #endif
 
-#ifdef CONFIG_PPC32
 /*
  * Write any modified data cache blocks out to memory and invalidate them.
  * Does not invalidate the corresponding instruction cache blocks.
@@ -73,9 +72,17 @@ static inline void flush_dcache_range(unsigned long start, unsigned long stop)
 	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
 	unsigned long i;
 
+	if (IS_ENABLED(CONFIG_PPC64)) {
+		mb();	/* sync */
+		isync();
+	}
+
 	for (i = 0; i < size >> shift; i++, addr += bytes)
 		dcbf(addr);
 	mb();	/* sync */
+
+	if (IS_ENABLED(CONFIG_PPC64))
+		isync();
 }
 
 /*
@@ -115,11 +122,6 @@ static inline void invalidate_dcache_range(unsigned long start,
 	mb();	/* sync */
 }
 
-#endif /* CONFIG_PPC32 */
-#ifdef CONFIG_PPC64
-extern void flush_dcache_range(unsigned long start, unsigned long stop);
-#endif
-
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 	do { \
 		memcpy(dst, src, len); \

arch/powerpc/kernel/misc_64.S

@@ -114,35 +114,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE)
 _ASM_NOKPROBE_SYMBOL(flush_icache_range)
 EXPORT_SYMBOL(flush_icache_range)
 
-/*
- * Like above, but only do the D-cache.
- *
- * flush_dcache_range(unsigned long start, unsigned long stop)
- *
- *    flush all bytes from start to stop-1 inclusive
- */
-
-_GLOBAL_TOC(flush_dcache_range)
- 	ld	r10,PPC64_CACHES@toc(r2)
-	lwz	r7,DCACHEL1BLOCKSIZE(r10)	/* Get dcache block size */
-	addi	r5,r7,-1
-	andc	r6,r3,r5		/* round low to line bdy */
-	subf	r8,r6,r4		/* compute length */
-	add	r8,r8,r5		/* ensure we get enough */
-	lwz	r9,DCACHEL1LOGBLOCKSIZE(r10)/* Get log-2 of dcache block size */
-	srw.	r8,r8,r9		/* compute line count */
-	beqlr				/* nothing to do? */
-	sync
-	isync
-	mtctr	r8
-0:	dcbf	0,r6
-	add	r6,r6,r7
-	bdnz	0b
-	sync
-	isync
-	blr
-EXPORT_SYMBOL(flush_dcache_range)
-
 /*
  * Flush a particular page from the data cache to RAM.
  * Note: this is necessary because the instruction cache does *not*