FROMLIST: arm64: Avoid aligning normal memory pointers in __memcpy_{to,from}io

(cherry picked from arm64/for-next/core commit 9ca255bf041ddc7698b6906dbd846c0ba64b1fe1)

__memcpy_{to,from}io fall back to byte-at-a-time copying if both the
source and destination pointers are not 8-byte aligned. Since one of the
pointers always points at normal memory, this is unnecessary and
detrimental to performance, so only do byte copying until we hit an 8-byte
boundary for the device pointer.

This change was motivated by performance issues in the pstore driver.
On a test platform, measuring probe time for pstore, console buffer
size of 1/4MB and pmsg of 1/2MB, was in the 90-107ms region. Change
managed to reduce it to 10-25ms, an improvement in boot time.

Cc: Kees Cook <keescook@chromium.org>
Cc: Anton Vorontsov <anton@enomsg.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Anton Vorontsov <anton@enomsg.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Bug: 63716230
Change-Id: I245545e8243a54b44d30fbb0d0c71a9b8a77ef63

Author: salyzyn

arch/arm64/kernel/io.c

@@ -25,8 +25,7 @@
  */
 void __memcpy_fromio(void *to, const volatile void __iomem *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)from, 8) ||
-			 !IS_ALIGNED((unsigned long)to, 8))) {
+	while (count && !IS_ALIGNED((unsigned long)from, 8)) {
 		*(u8 *)to = __raw_readb(from);
 		from++;
 		to++;
@@ -54,23 +53,22 @@ EXPORT_SYMBOL(__memcpy_fromio);
  */
 void __memcpy_toio(volatile void __iomem *to, const void *from, size_t count)
 {
-	while (count && (!IS_ALIGNED((unsigned long)to, 8) ||
-			 !IS_ALIGNED((unsigned long)from, 8))) {
-		__raw_writeb(*(volatile u8 *)from, to);
+	while (count && !IS_ALIGNED((unsigned long)to, 8)) {
+		__raw_writeb(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;
 	}
 
 	while (count >= 8) {
-		__raw_writeq(*(volatile u64 *)from, to);
+		__raw_writeq(*(u64 *)from, to);
 		from += 8;
 		to += 8;
 		count -= 8;
 	}
 
 	while (count) {
-		__raw_writeb(*(volatile u8 *)from, to);
+		__raw_writeb(*(u8 *)from, to);
 		from++;
 		to++;
 		count--;