riscv: __asm_copy_to-from_user: Fix: overrun copy

There were two causes for the overrun memory access.

The threshold size was too small.
The aligning dst require one SZREG and unrolling word copy requires
8*SZREG, total have to be at least 9*SZREG.

Inside the unrolling copy, the subtracting -(8*SZREG-1) would make
iteration happening one extra loop. Proper value is -(8*SZREG).
Signed-off-by: Akira Tsukamoto <akira.tsukamoto@gmail.com>
Fixes: ca6eaaa2 ("riscv: __asm_copy_to-from_user: Optimize unaligned memory access and pipeline stall")
Signed-off-by: Palmer Dabbelt <palmerdabbelt@google.com>

arch/riscv/lib/uaccess.S

@@ -35,7 +35,7 @@ ENTRY(__asm_copy_from_user)
 	/*
 	 * Use byte copy only if too small.
 	 */
-	li	a3, 8*SZREG /* size must be larger than size in word_copy */
+	li	a3, 9*SZREG /* size must be larger than size in word_copy */
 	bltu	a2, a3, .Lbyte_copy_tail
 
 	/*
@@ -75,7 +75,7 @@ ENTRY(__asm_copy_from_user)
 	 * a3 - a1 & mask:(SZREG-1)
 	 * t0 - end of aligned dst
 	 */
-	addi	t0, t0, -(8*SZREG-1) /* not to over run */
+	addi	t0, t0, -(8*SZREG) /* not to over run */
 2:
 	fixup REG_L   a4,        0(a1), 10f
 	fixup REG_L   a5,    SZREG(a1), 10f
@@ -97,7 +97,7 @@ ENTRY(__asm_copy_from_user)
 	addi	a1, a1, 8*SZREG
 	bltu	a0, t0, 2b
 
-	addi	t0, t0, 8*SZREG-1 /* revert to original value */
+	addi	t0, t0, 8*SZREG /* revert to original value */
 	j	.Lbyte_copy_tail
 
 .Lshift_copy: