[PATCH v1] riscv: skip software algning code for HAVE_EFFICIENT_UNALIGNED_ACCESS

[Andy Chiu]

We can jump straight into the copy loop if the kernel is compiled for a
hardware that natively supports misaligned access. The user copy
bandwidth improvement on K3 and Ascaolon is shown as below:

Misaligned user copy, size: 512B (offset: [0:15] except 0, 8)
BW Improvement	| Write	| Read	|
K3		| 6.19%	| 3.43%	|
Ascalon		| 10.0%	| 11.4%	|

Aligned user copy, size: 512B (offset: 0, 8)
BW Improvement	| Write	| Read	|
K3		| 1.69%	| 0.90%	|
Ascalon		| 1.25%	| 3.32%	|

Suggested-by: Anton Blanchard <antonb at tenstorrent.com>
Signed-off-by: Andy Chiu <tchiu at tenstorrent.com>
---
 arch/riscv/lib/uaccess.S | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index 4efea1b3326c..cf8586a937de 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -76,6 +76,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled)
 	li	a3, 9*SZREG-1 /* size must >= (word_copy stride + SZREG-1) */
 	bltu	a2, a3, .Lbyte_copy_tail
 
+#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 	/*
 	 * Copy first bytes until dst is aligned to word boundary.
 	 * a0 - start of dst
@@ -103,7 +104,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled)
 	/* a1 - start of src */
 	andi	a3, a1, SZREG-1
 	bnez	a3, .Lshift_copy
-
+#endif
 .Lword_copy:
         /*
 	 * Both src and dst are aligned, unrolled word copy
@@ -137,6 +138,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled)
 	addi	t0, t0, 8*SZREG /* revert to original value */
 	j	.Lbyte_copy_tail
 
+#if !defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 .Lshift_copy:
 
 	/*
@@ -189,6 +191,7 @@ SYM_FUNC_START(fallback_scalar_usercopy_sum_enabled)
 
 	/* Revert src to original unaligned value  */
 	add	a1, a1, a3
+#endif
 
 .Lbyte_copy_tail:
 	/*
-- 
2.43.0