From: Robin Murphy <robin.murphy@arm.com>
To: will@kernel.org, catalin.marinas@arm.com
Cc: linux-arm-kernel@lists.infradead.org, yangyingliang@huawei.com,
shenkai8@huawei.com
Subject: [PATCH 2/8] arm64: Import latest version of Cortex Strings' strcmp
Date: Tue, 11 May 2021 17:12:32 +0100 [thread overview]
Message-ID: <0554ecb0e7411186b5e26c0223a6c1b6030df707.1620738177.git.robin.murphy@arm.com> (raw)
In-Reply-To: <cover.1620738177.git.robin.murphy@arm.com>
From: Sam Tebbs <sam.tebbs@arm.com>
Import the latest version of the former Cortex Strings - now
Arm Optimized Routines - strcmp function based on the upstream
code of string/aarch64/strcmp.S at commit afd6244 from
https://github.com/ARM-software/optimized-routines
Signed-off-by: Sam Tebbs <sam.tebbs@arm.com>
[ rm: update attribution and commit message ]
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
---
arch/arm64/lib/strcmp.S | 295 +++++++++++++++++-----------------------
1 file changed, 124 insertions(+), 171 deletions(-)
diff --git a/arch/arm64/lib/strcmp.S b/arch/arm64/lib/strcmp.S
index 4e79566726c8..e82ccb6c2f93 100644
--- a/arch/arm64/lib/strcmp.S
+++ b/arch/arm64/lib/strcmp.S
@@ -1,84 +1,123 @@
/* SPDX-License-Identifier: GPL-2.0-only */
/*
- * Copyright (C) 2013 ARM Ltd.
- * Copyright (C) 2013 Linaro.
+ * Copyright (c) 2012-2020, Arm Limited.
*
- * This code is based on glibc cortex strings work originally authored by Linaro
- * be found @
- *
- * http://bazaar.launchpad.net/~linaro-toolchain-dev/cortex-strings/trunk/
- * files/head:/src/aarch64/
+ * Adapted from the original at:
+ * https://github.com/ARM-software/optimized-routines/blob/master/string/aarch64/strcmp.S
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
-/*
- * compare two strings
+/* Assumptions:
*
- * Parameters:
- * x0 - const string 1 pointer
- * x1 - const string 2 pointer
- * Returns:
- * x0 - an integer less than, equal to, or greater than zero
- * if s1 is found, respectively, to be less than, to match,
- * or be greater than s2.
+ * ARMv8-a, AArch64
*/
+#define L(label) .L ## label
+
#define REP8_01 0x0101010101010101
#define REP8_7f 0x7f7f7f7f7f7f7f7f
#define REP8_80 0x8080808080808080
/* Parameters and result. */
-src1 .req x0
-src2 .req x1
-result .req x0
+#define src1 x0
+#define src2 x1
+#define result x0
/* Internal variables. */
-data1 .req x2
-data1w .req w2
-data2 .req x3
-data2w .req w3
-has_nul .req x4
-diff .req x5
-syndrome .req x6
-tmp1 .req x7
-tmp2 .req x8
-tmp3 .req x9
-zeroones .req x10
-pos .req x11
+#define data1 x2
+#define data1w w2
+#define data2 x3
+#define data2w w3
+#define has_nul x4
+#define diff x5
+#define syndrome x6
+#define tmp1 x7
+#define tmp2 x8
+#define tmp3 x9
+#define zeroones x10
+#define pos x11
+ /* Start of performance-critical section -- one 64B cache line. */
+ .align 6
SYM_FUNC_START_WEAK_PI(strcmp)
eor tmp1, src1, src2
mov zeroones, #REP8_01
tst tmp1, #7
- b.ne .Lmisaligned8
+ b.ne L(misaligned8)
ands tmp1, src1, #7
- b.ne .Lmutual_align
-
- /*
- * NUL detection works on the principle that (X - 1) & (~X) & 0x80
- * (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
- * can be done in parallel across the entire word.
- */
-.Lloop_aligned:
+ b.ne L(mutual_align)
+ /* NUL detection works on the principle that (X - 1) & (~X) & 0x80
+ (=> (X - 1) & ~(X | 0x7f)) is non-zero iff a byte is zero, and
+ can be done in parallel across the entire word. */
+L(loop_aligned):
ldr data1, [src1], #8
ldr data2, [src2], #8
-.Lstart_realigned:
+L(start_realigned):
sub tmp1, data1, zeroones
orr tmp2, data1, #REP8_7f
eor diff, data1, data2 /* Non-zero if differences found. */
bic has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */
orr syndrome, diff, has_nul
- cbz syndrome, .Lloop_aligned
- b .Lcal_cmpresult
+ cbz syndrome, L(loop_aligned)
+ /* End of performance-critical section -- one 64B cache line. */
-.Lmutual_align:
- /*
- * Sources are mutually aligned, but are not currently at an
- * alignment boundary. Round down the addresses and then mask off
- * the bytes that preceed the start point.
- */
+L(end):
+#ifndef __AARCH64EB__
+ rev syndrome, syndrome
+ rev data1, data1
+ /* The MS-non-zero bit of the syndrome marks either the first bit
+ that is different, or the top bit of the first zero byte.
+ Shifting left now will bring the critical information into the
+ top bits. */
+ clz pos, syndrome
+ rev data2, data2
+ lsl data1, data1, pos
+ lsl data2, data2, pos
+ /* But we need to zero-extend (char is unsigned) the value and then
+ perform a signed 32-bit subtraction. */
+ lsr data1, data1, #56
+ sub result, data1, data2, lsr #56
+ ret
+#else
+ /* For big-endian we cannot use the trick with the syndrome value
+ as carry-propagation can corrupt the upper bits if the trailing
+ bytes in the string contain 0x01. */
+ /* However, if there is no NUL byte in the dword, we can generate
+ the result directly. We can't just subtract the bytes as the
+ MSB might be significant. */
+ cbnz has_nul, 1f
+ cmp data1, data2
+ cset result, ne
+ cneg result, result, lo
+ ret
+1:
+ /* Re-compute the NUL-byte detection, using a byte-reversed value. */
+ rev tmp3, data1
+ sub tmp1, tmp3, zeroones
+ orr tmp2, tmp3, #REP8_7f
+ bic has_nul, tmp1, tmp2
+ rev has_nul, has_nul
+ orr syndrome, diff, has_nul
+ clz pos, syndrome
+ /* The MS-non-zero bit of the syndrome marks either the first bit
+ that is different, or the top bit of the first zero byte.
+ Shifting left now will bring the critical information into the
+ top bits. */
+ lsl data1, data1, pos
+ lsl data2, data2, pos
+ /* But we need to zero-extend (char is unsigned) the value and then
+ perform a signed 32-bit subtraction. */
+ lsr data1, data1, #56
+ sub result, data1, data2, lsr #56
+ ret
+#endif
+
+L(mutual_align):
+ /* Sources are mutually aligned, but are not currently at an
+ alignment boundary. Round down the addresses and then mask off
+ the bytes that preceed the start point. */
bic src1, src1, #7
bic src2, src2, #7
lsl tmp1, tmp1, #3 /* Bytes beyond alignment -> bits. */
@@ -86,138 +125,52 @@ SYM_FUNC_START_WEAK_PI(strcmp)
neg tmp1, tmp1 /* Bits to alignment -64. */
ldr data2, [src2], #8
mov tmp2, #~0
+#ifdef __AARCH64EB__
/* Big-endian. Early bytes are at MSB. */
-CPU_BE( lsl tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */
+ lsl tmp2, tmp2, tmp1 /* Shift (tmp1 & 63). */
+#else
/* Little-endian. Early bytes are at LSB. */
-CPU_LE( lsr tmp2, tmp2, tmp1 ) /* Shift (tmp1 & 63). */
-
+ lsr tmp2, tmp2, tmp1 /* Shift (tmp1 & 63). */
+#endif
orr data1, data1, tmp2
orr data2, data2, tmp2
- b .Lstart_realigned
+ b L(start_realigned)
-.Lmisaligned8:
- /*
- * Get the align offset length to compare per byte first.
- * After this process, one string's address will be aligned.
- */
- and tmp1, src1, #7
- neg tmp1, tmp1
- add tmp1, tmp1, #8
- and tmp2, src2, #7
- neg tmp2, tmp2
- add tmp2, tmp2, #8
- subs tmp3, tmp1, tmp2
- csel pos, tmp1, tmp2, hi /*Choose the maximum. */
-.Ltinycmp:
+L(misaligned8):
+ /* Align SRC1 to 8 bytes and then compare 8 bytes at a time, always
+ checking to make sure that we don't access beyond page boundary in
+ SRC2. */
+ tst src1, #7
+ b.eq L(loop_misaligned)
+L(do_misaligned):
ldrb data1w, [src1], #1
ldrb data2w, [src2], #1
- subs pos, pos, #1
- ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */
- ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */
- b.eq .Ltinycmp
- cbnz pos, 1f /*find the null or unequal...*/
cmp data1w, #1
- ccmp data1w, data2w, #0, cs
- b.eq .Lstart_align /*the last bytes are equal....*/
-1:
+ ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */
+ b.ne L(done)
+ tst src1, #7
+ b.ne L(do_misaligned)
+
+L(loop_misaligned):
+ /* Test if we are within the last dword of the end of a 4K page. If
+ yes then jump back to the misaligned loop to copy a byte at a time. */
+ and tmp1, src2, #0xff8
+ eor tmp1, tmp1, #0xff8
+ cbz tmp1, L(do_misaligned)
+ ldr data1, [src1], #8
+ ldr data2, [src2], #8
+
+ sub tmp1, data1, zeroones
+ orr tmp2, data1, #REP8_7f
+ eor diff, data1, data2 /* Non-zero if differences found. */
+ bic has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */
+ orr syndrome, diff, has_nul
+ cbz syndrome, L(loop_misaligned)
+ b L(end)
+
+L(done):
sub result, data1, data2
ret
-.Lstart_align:
- ands xzr, src1, #7
- b.eq .Lrecal_offset
- /*process more leading bytes to make str1 aligned...*/
- add src1, src1, tmp3
- add src2, src2, tmp3
- /*load 8 bytes from aligned str1 and non-aligned str2..*/
- ldr data1, [src1], #8
- ldr data2, [src2], #8
-
- sub tmp1, data1, zeroones
- orr tmp2, data1, #REP8_7f
- bic has_nul, tmp1, tmp2
- eor diff, data1, data2 /* Non-zero if differences found. */
- orr syndrome, diff, has_nul
- cbnz syndrome, .Lcal_cmpresult
- /*How far is the current str2 from the alignment boundary...*/
- and tmp3, tmp3, #7
-.Lrecal_offset:
- neg pos, tmp3
-.Lloopcmp_proc:
- /*
- * Divide the eight bytes into two parts. First,backwards the src2
- * to an alignment boundary,load eight bytes from the SRC2 alignment
- * boundary,then compare with the relative bytes from SRC1.
- * If all 8 bytes are equal,then start the second part's comparison.
- * Otherwise finish the comparison.
- * This special handle can garantee all the accesses are in the
- * thread/task space in avoid to overrange access.
- */
- ldr data1, [src1,pos]
- ldr data2, [src2,pos]
- sub tmp1, data1, zeroones
- orr tmp2, data1, #REP8_7f
- bic has_nul, tmp1, tmp2
- eor diff, data1, data2 /* Non-zero if differences found. */
- orr syndrome, diff, has_nul
- cbnz syndrome, .Lcal_cmpresult
-
- /*The second part process*/
- ldr data1, [src1], #8
- ldr data2, [src2], #8
- sub tmp1, data1, zeroones
- orr tmp2, data1, #REP8_7f
- bic has_nul, tmp1, tmp2
- eor diff, data1, data2 /* Non-zero if differences found. */
- orr syndrome, diff, has_nul
- cbz syndrome, .Lloopcmp_proc
-
-.Lcal_cmpresult:
- /*
- * reversed the byte-order as big-endian,then CLZ can find the most
- * significant zero bits.
- */
-CPU_LE( rev syndrome, syndrome )
-CPU_LE( rev data1, data1 )
-CPU_LE( rev data2, data2 )
-
- /*
- * For big-endian we cannot use the trick with the syndrome value
- * as carry-propagation can corrupt the upper bits if the trailing
- * bytes in the string contain 0x01.
- * However, if there is no NUL byte in the dword, we can generate
- * the result directly. We cannot just subtract the bytes as the
- * MSB might be significant.
- */
-CPU_BE( cbnz has_nul, 1f )
-CPU_BE( cmp data1, data2 )
-CPU_BE( cset result, ne )
-CPU_BE( cneg result, result, lo )
-CPU_BE( ret )
-CPU_BE( 1: )
- /*Re-compute the NUL-byte detection, using a byte-reversed value. */
-CPU_BE( rev tmp3, data1 )
-CPU_BE( sub tmp1, tmp3, zeroones )
-CPU_BE( orr tmp2, tmp3, #REP8_7f )
-CPU_BE( bic has_nul, tmp1, tmp2 )
-CPU_BE( rev has_nul, has_nul )
-CPU_BE( orr syndrome, diff, has_nul )
-
- clz pos, syndrome
- /*
- * The MS-non-zero bit of the syndrome marks either the first bit
- * that is different, or the top bit of the first zero byte.
- * Shifting left now will bring the critical information into the
- * top bits.
- */
- lsl data1, data1, pos
- lsl data2, data2, pos
- /*
- * But we need to zero-extend (char is unsigned) the value and then
- * perform a signed 32-bit subtraction.
- */
- lsr data1, data1, #56
- sub result, data1, data2, lsr #56
- ret
SYM_FUNC_END_PI(strcmp)
EXPORT_SYMBOL_NOKASAN(strcmp)
--
2.21.0.dirty
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2021-05-11 16:19 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-05-11 16:12 [PATCH 0/8] arm64: String function updates Robin Murphy
2021-05-11 16:12 ` [PATCH 1/8] arm64: Import latest version of Cortex Strings' memcmp Robin Murphy
2021-05-12 13:28 ` Mark Rutland
2021-05-12 13:38 ` Robin Murphy
2021-05-12 14:51 ` Szabolcs Nagy
2021-05-26 10:17 ` Mark Rutland
2021-05-11 16:12 ` Robin Murphy [this message]
2021-05-11 16:12 ` [PATCH 3/8] arm64: Import updated version of Cortex Strings' strlen Robin Murphy
2021-05-11 16:12 ` [PATCH 4/8] arm64: Import latest version of Cortex Strings' strncmp Robin Murphy
2021-05-11 16:12 ` [PATCH 5/8] arm64: Add assembly annotations for weak-PI-alias madness Robin Murphy
2021-05-11 16:12 ` [PATCH 6/8] arm64: Import latest memcpy()/memmove() implementation Robin Murphy
2021-05-11 16:12 ` [PATCH 7/8] arm64: Better optimised memchr() Robin Murphy
2021-05-14 14:55 ` Catalin Marinas
2021-05-14 18:38 ` Robin Murphy
2021-05-11 16:12 ` [PATCH 8/8] arm64: Rewrite __arch_clear_user() Robin Murphy
2021-05-12 10:48 ` Mark Rutland
2021-05-12 11:31 ` Robin Murphy
2021-05-12 13:06 ` Mark Rutland
2021-05-12 13:51 ` Robin Murphy
2021-05-14 11:57 ` [PATCH v2] " Robin Murphy
2021-05-26 11:15 ` Mark Rutland
2021-05-27 13:24 ` Robin Murphy
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=0554ecb0e7411186b5e26c0223a6c1b6030df707.1620738177.git.robin.murphy@arm.com \
--to=robin.murphy@arm.com \
--cc=catalin.marinas@arm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=shenkai8@huawei.com \
--cc=will@kernel.org \
--cc=yangyingliang@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).