[PATCH 3/5] riscv: __asm_to/copy_from_user: Copy until dst is aligned

[Akira Tsukamoto <akira.tsukamoto@gmail.com>]

First copy in bytes until reaches the first word aligned boundary in
destination memory address.

For speeding up the copy, trying to avoid both the unaligned memory access
and byte access are the key. This is the preparation before the bulk
aligned word copy.

Signed-off-by: Akira Tsukamoto <akira.tsukamoto@gmail.com>
---
 arch/riscv/lib/uaccess.S | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index be1810077f9a..4906b5ca91c3 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -32,6 +32,34 @@ ENTRY(__asm_copy_from_user)
 	add	t0, a0, a2
 	bgtu	a0, t0, 5f
 
+	/*
+	 * Use byte copy only if too small.
+	 */
+	li	a3, 8*SZREG /* size must be larger than size in word_copy */
+	bltu	a2, a3, .Lbyte_copy_tail
+
+	/*
+	 * Copy first bytes until dst is align to word boundary.
+	 * a0 - start of dst
+	 * t1 - start of aligned dst
+	 */
+	addi	t1, a0, SZREG-1
+	andi	t1, t1, ~(SZREG-1)
+	/* dst is already aligned, skip */
+	beq	a0, t1, .Lskip_first_bytes
+1:
+	/* a5 - one byte for copying data */
+	fixup lb      a5, 0(a1), 10f
+	addi	a1, a1, 1	/* src */
+	fixup sb      a5, 0(a0), 10f
+	addi	a0, a0, 1	/* dst */
+	bltu	a0, t1, 1b	/* t1 - start of aligned dst */
+
+.Lskip_first_bytes:
+
+.Lword_copy:
+.Lshift_copy:
+
 .Lbyte_copy_tail:
 	/*
 	 * Byte copy anything left.
-- 
2.17.1