Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Subject: [PATCH 5/5] riscv: __asm_to/copy_from_user: Bulk copy when both src,
 dst are aligned
To:     Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        linux-kernel@vger.kernel.org, linux-riscv@lists.infradead.org
References: <5a5c07ac-8c11-79d3-46a3-a255d4148f76@gmail.com>
From:   Akira Tsukamoto <akira.tsukamoto@gmail.com>
Message-ID: <4637f0f2-2da9-1056-37bf-17c0861b6bff@gmail.com>
Date:   Sat, 19 Jun 2021 20:43:06 +0900
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:78.0) Gecko/20100101
 Thunderbird/78.11.0
MIME-Version: 1.0
In-Reply-To: <5a5c07ac-8c11-79d3-46a3-a255d4148f76@gmail.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Precedence: bulk


In the lucky situation that the both source and destination address are on
the aligned boundary, perform load and store with register size to copy the
data.

Without the unrolling, it will reduce the speed since the next store
instruction for the same register using from the load will stall the
pipeline.

Signed-off-by: Akira Tsukamoto <akira.tsukamoto@gmail.com>
---
 arch/riscv/lib/uaccess.S | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/arch/riscv/lib/uaccess.S b/arch/riscv/lib/uaccess.S
index e2e57551fc76..bceb0629e440 100644
--- a/arch/riscv/lib/uaccess.S
+++ b/arch/riscv/lib/uaccess.S
@@ -67,6 +67,39 @@ ENTRY(__asm_copy_from_user)
 	bnez	a3, .Lshift_copy
 
 .Lword_copy:
+        /*
+	 * Both src and dst are aligned, unrolled word copy
+	 *
+	 * a0 - start of aligned dst
+	 * a1 - start of aligned src
+	 * a3 - a1 & mask:(SZREG-1)
+	 * t0 - end of aligned dst
+	 */
+	addi	t0, t0, -(8*SZREG-1) /* not to over run */
+2:
+	fixup REG_L   a4,        0(a1), 10f
+	fixup REG_L   a5,    SZREG(a1), 10f
+	fixup REG_L   a6,  2*SZREG(a1), 10f
+	fixup REG_L   a7,  3*SZREG(a1), 10f
+	fixup REG_L   t1,  4*SZREG(a1), 10f
+	fixup REG_L   t2,  5*SZREG(a1), 10f
+	fixup REG_L   t3,  6*SZREG(a1), 10f
+	fixup REG_L   t4,  7*SZREG(a1), 10f
+	fixup REG_S   a4,        0(a0), 10f
+	fixup REG_S   a5,    SZREG(a0), 10f
+	fixup REG_S   a6,  2*SZREG(a0), 10f
+	fixup REG_S   a7,  3*SZREG(a0), 10f
+	fixup REG_S   t1,  4*SZREG(a0), 10f
+	fixup REG_S   t2,  5*SZREG(a0), 10f
+	fixup REG_S   t3,  6*SZREG(a0), 10f
+	fixup REG_S   t4,  7*SZREG(a0), 10f
+	addi	a0, a0, 8*SZREG
+	addi	a1, a1, 8*SZREG
+	bltu	a0, t0, 2b
+
+	addi	t0, t0, 8*SZREG-1 /* revert to original value */
+	j	.Lbyte_copy_tail
+
 .Lshift_copy:
 
 	/*
-- 
2.17.1