Merge "arm64: optimize memcpy_{from,to}io() and memset_io()"

#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);

 */

void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)

{

	const unsigned char *f = from;

	void *p = (void __force *)to;

	__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);

 */

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);