[PATCH] arm64: optimize memcpy_{from,to}io() and memset_io()

[Joonwoo Park]

Optimize memcpy_{from,to}io() and memset_io() by transferring in 64 bit
as much as possible with minimized barrier usage.  This simplest optimization
brings faster throughput compare to current byte-by-byte read and write with
barrier in the loop.  Code's skeleton is taken from the powerpc.

Signed-off-by: Joonwoo Park <joonwoop at codeaurora.org>
Acked-by: Trilok Soni <tsoni at codeaurora.org>
---
 arch/arm64/kernel/io.c | 72 +++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 62 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kernel/io.c b/arch/arm64/kernel/io.c
index 7d37ead..c0e3ab1 100644
--- a/arch/arm64/kernel/io.c
+++ b/arch/arm64/kernel/io.c
@@ -20,18 +20,34 @@
 #include <linux/types.h>
 #include <linux/io.h>
 
+#define IO_CHECK_ALIGN(v, a) ((((unsigned long)(v)) & ((a) - 1)) == 0)
+
 /*
  * Copy data from IO memory space to "real" memory space.
  */
 void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
 {
-	unsigned char *t = to;
-	while (count) {
+	while (count && (!IO_CHECK_ALIGN(from, 8) || !IO_CHECK_ALIGN(to, 8))) {
+		*(u8 *)to = readb_relaxed(from);
+		from++;
+		to++;
 		count--;
-		*t = readb(from);
-		t++;
+	}
+
+	while (count >= 8) {
+		*(u64 *)to = readq_relaxed(from);
+		from += 8;
+		to += 8;
+		count -= 8;
+	}
+
+	while (count) {
+		*(u8 *)to = readb_relaxed(from);
 		from++;
+		to++;
+		count--;
 	}
+	__iormb();
 }
 EXPORT_SYMBOL(__memcpy_fromio);
 
@@ -40,12 +56,28 @@ EXPORT_SYMBOL(__memcpy_fromio);
  */
 void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
 {
-	const unsigned char *f = from;
+	void *p = (void __force *)from;
+
+	__iowmb();
+	while (count && (!IO_CHECK_ALIGN(p, 8) || !IO_CHECK_ALIGN(from, 8))) {
+		writeb_relaxed(*(volatile u8 *)from, p);
+		from++;
+		p++;
+		count--;
+	}
+
+	while (count >= 8) {
+		writeq_relaxed(*(volatile u64 *)from, p);
+		from += 8;
+		p += 8;
+		count -= 8;
+	}
+
 	while (count) {
+		writeb_relaxed(*(volatile u8 *)from, p);
+		from++;
+		p++;
 		count--;
-		writeb(*f, to);
-		f++;
-		to++;
 	}
 }
 EXPORT_SYMBOL(__memcpy_toio);
@@ -55,10 +87,30 @@ EXPORT_SYMBOL(__memcpy_toio);
  */
 void __memset_io(volatile void __iomem *dst, int c, size_t count)
 {
+	void *p = (void __force *)dst;
+	u64 qc = c;
+
+	qc |= qc << 8;
+	qc |= qc << 16;
+	qc |= qc << 32;
+
+	__iowmb();
+	while (count && !IO_CHECK_ALIGN(p, 8)) {
+		writeb_relaxed(c, p);
+		p++;
+		count--;
+	}
+
+	while (count >= 8) {
+		writeq_relaxed(c, p);
+		p += 8;
+		count -= 8;
+	}
+
 	while (count) {
+		writeb_relaxed(c, p);
+		p++;
 		count--;
-		writeb(c, dst);
-		dst++;
 	}
 }
 EXPORT_SYMBOL(__memset_io);
-- 
The Qualcomm Innovation Center, Inc. is a member of the Code Aurora Forum,
hosted by The Linux Foundation