From: Sam Tebbs sam.tebbs@arm.com

mainline inclusion from mainline-v5.14-rc1 commit 758602c04409d8c5a092cef570b2de125ce0f2ae category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XOA CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

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

Note that for simplicity Arm have chosen to contribute this code to Linux under GPLv2 rather than the original MIT license.

Signed-off-by: Sam Tebbs sam.tebbs@arm.com [ rm: update attribution and commit message ] Signed-off-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/0fe90c90b96b569fbdfd46e47bd1298abb02079e.162212852... Signed-off-by: Will Deacon will@kernel.org Signed-off-by: liwei liwei728@huawei.com --- arch/arm64/lib/strcmp.S | 289 +++++++++++++++++----------------------- 1 file changed, 121 insertions(+), 168 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/aarch6... */

#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. */ + +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

-.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(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 - -.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: + b L(start_realigned) + +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: - 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..*/ + 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 - 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. */ + 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, .Lloopcmp_proc + cbz syndrome, L(loop_misaligned) + b L(end)

-.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 +L(done): + sub result, data1, data2 ret + SYM_FUNC_END_PI(strcmp) EXPORT_SYMBOL_NOKASAN(strcmp)

From: Sam Tebbs sam.tebbs@arm.com

mainline inclusion from mainline-v5.14-rc1 commit 020b199bc70d98d92e1bbc6a71358d7293ebc5ea category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XOA CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Import the latest version of the former Cortex Strings - now Arm Optimized Routines - strncmp function based on the upstream code of string/aarch64/strncmp.S at commit e823e3a from https://github.com/ARM-software/optimized-routines

Note that for simplicity Arm have chosen to contribute this code to Linux under GPLv2 rather than the original MIT license.

Signed-off-by: Sam Tebbs sam.tebbs@arm.com [ rm: update attribution and commit message ] Signed-off-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/26110bee02ad360596c9a7536af7eaaf6890d0e8.162212852... Signed-off-by: Will Deacon will@kernel.org Signed-off-by: liwei liwei728@huawei.com --- arch/arm64/lib/strncmp.S | 406 ++++++++++++++++++--------------------- 1 file changed, 184 insertions(+), 222 deletions(-)

diff --git a/arch/arm64/lib/strncmp.S b/arch/arm64/lib/strncmp.S index 2a7ee949ed47..0c0bf5462de0 100644 --- a/arch/arm64/lib/strncmp.S +++ b/arch/arm64/lib/strncmp.S @@ -1,299 +1,261 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Copyright (C) 2013 ARM Ltd. - * Copyright (C) 2013 Linaro. + * Copyright (c) 2013, 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/aarch6... */

#include <linux/linkage.h> #include <asm/assembler.h>

-/* - * compare two strings +/* Assumptions: * - * Parameters: - * x0 - const string 1 pointer - * x1 - const string 2 pointer - * x2 - the maximal length to be compared - * 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 -limit .req x2 -result .req x0 +#define src1 x0 +#define src2 x1 +#define limit x2 +#define result x0

/* Internal variables. */ -data1 .req x3 -data1w .req w3 -data2 .req x4 -data2w .req w4 -has_nul .req x5 -diff .req x6 -syndrome .req x7 -tmp1 .req x8 -tmp2 .req x9 -tmp3 .req x10 -zeroones .req x11 -pos .req x12 -limit_wd .req x13 -mask .req x14 -endloop .req x15 +#define data1 x3 +#define data1w w3 +#define data2 x4 +#define data2w w4 +#define has_nul x5 +#define diff x6 +#define syndrome x7 +#define tmp1 x8 +#define tmp2 x9 +#define tmp3 x10 +#define zeroones x11 +#define pos x12 +#define limit_wd x13 +#define mask x14 +#define endloop x15 +#define count mask

SYM_FUNC_START_WEAK_PI(strncmp) - cbz limit, .Lret0 + cbz limit, L(ret0) eor tmp1, src1, src2 mov zeroones, #REP8_01 tst tmp1, #7 - b.ne .Lmisaligned8 - ands tmp1, src1, #7 - b.ne .Lmutual_align + and count, src1, #7 + b.ne L(misaligned8) + cbnz count, L(mutual_align) /* Calculate the number of full and partial words -1. */ - /* - * when limit is mulitply of 8, if not sub 1, - * the judgement of last dword will wrong. - */ - sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ - lsr limit_wd, limit_wd, #3 /* Convert to Dwords. */ + sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ + lsr limit_wd, limit_wd, #3 /* Convert to Dwords. */

- /* - * 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: + /* 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. */ + .p2align 4 +L(loop_aligned): ldr data1, [src1], #8 ldr data2, [src2], #8 -.Lstart_realigned: +L(start_realigned): subs limit_wd, limit_wd, #1 sub tmp1, data1, zeroones orr tmp2, data1, #REP8_7f - eor diff, data1, data2 /* Non-zero if differences found. */ - csinv endloop, diff, xzr, pl /* Last Dword or differences.*/ - bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ + eor diff, data1, data2 /* Non-zero if differences found. */ + csinv endloop, diff, xzr, pl /* Last Dword or differences. */ + bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ ccmp endloop, #0, #0, eq - b.eq .Lloop_aligned + b.eq L(loop_aligned) + /* End of main loop */

- /*Not reached the limit, must have found the end or a diff. */ - tbz limit_wd, #63, .Lnot_limit + /* Not reached the limit, must have found the end or a diff. */ + tbz limit_wd, #63, L(not_limit)

/* Limit % 8 == 0 => all bytes significant. */ ands limit, limit, #7 - b.eq .Lnot_limit + b.eq L(not_limit)

- lsl limit, limit, #3 /* Bits -> bytes. */ + lsl limit, limit, #3 /* Bits -> bytes. */ mov mask, #~0 -CPU_BE( lsr mask, mask, limit ) -CPU_LE( lsl mask, mask, limit ) +#ifdef __AARCH64EB__ + lsr mask, mask, limit +#else + lsl mask, mask, limit +#endif bic data1, data1, mask bic data2, data2, mask

/* Make sure that the NUL byte is marked in the syndrome. */ orr has_nul, has_nul, mask

-.Lnot_limit: +L(not_limit): orr syndrome, diff, has_nul - b .Lcal_cmpresult

-.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 precede the start point. - * We also need to adjust the limit calculations, but without - * overflowing if the limit is near ULONG_MAX. - */ +#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 precede the start point. + We also need to adjust the limit calculations, but without + overflowing if the limit is near ULONG_MAX. */ bic src1, src1, #7 bic src2, src2, #7 ldr data1, [src1], #8 - neg tmp3, tmp1, lsl #3 /* 64 - bits(bytes beyond align). */ + neg tmp3, count, lsl #3 /* 64 - bits(bytes beyond align). */ ldr data2, [src2], #8 mov tmp2, #~0 - sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ + sub limit_wd, limit, #1 /* limit != 0, so no underflow. */ +#ifdef __AARCH64EB__ /* Big-endian. Early bytes are at MSB. */ -CPU_BE( lsl tmp2, tmp2, tmp3 ) /* Shift (tmp1 & 63). */ + lsl tmp2, tmp2, tmp3 /* Shift (count & 63). */ +#else /* Little-endian. Early bytes are at LSB. */ -CPU_LE( lsr tmp2, tmp2, tmp3 ) /* Shift (tmp1 & 63). */ - + lsr tmp2, tmp2, tmp3 /* Shift (count & 63). */ +#endif and tmp3, limit_wd, #7 lsr limit_wd, limit_wd, #3 - /* Adjust the limit. Only low 3 bits used, so overflow irrelevant.*/ - add limit, limit, tmp1 - add tmp3, tmp3, tmp1 + /* Adjust the limit. Only low 3 bits used, so overflow irrelevant. */ + add limit, limit, count + add tmp3, tmp3, count orr data1, data1, tmp2 orr data2, data2, tmp2 add limit_wd, limit_wd, tmp3, lsr #3 - b .Lstart_realigned + b L(start_realigned) + + .p2align 4 + /* Don't bother with dwords for up to 16 bytes. */ +L(misaligned8): + cmp limit, #16 + b.hs L(try_misaligned_words)

-/*when src1 offset is not equal to src2 offset...*/ -.Lmisaligned8: - cmp limit, #8 - b.lo .Ltiny8proc /*limit < 8... */ - /* - * 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. */ - /* - * Here, limit is not less than 8, so directly run .Ltinycmp - * without checking the limit.*/ - sub limit, limit, pos -.Ltinycmp: +L(byte_loop): + /* Perhaps we can do better than this. */ 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: + subs limit, limit, #1 + ccmp data1w, #1, #0, hi /* NZCV = 0b0000. */ + ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */ + b.eq L(byte_loop) +L(done): sub result, data1, data2 ret - -.Lstart_align: + /* Align the SRC1 to a dword by doing a bytewise compare and then do + the dword loop. */ +L(try_misaligned_words): lsr limit_wd, limit, #3 - cbz limit_wd, .Lremain8 - /*process more leading bytes to make str1 aligned...*/ - ands xzr, src1, #7 - b.eq .Lrecal_offset - add src1, src1, tmp3 /*tmp3 is positive in this branch.*/ - add src2, src2, tmp3 - ldr data1, [src1], #8 - ldr data2, [src2], #8 + cbz count, L(do_misaligned)

- sub limit, limit, tmp3 + neg count, count + and count, count, #7 + sub limit, limit, count lsr limit_wd, limit, #3 - subs limit_wd, limit_wd, #1

- sub tmp1, data1, zeroones - orr tmp2, data1, #REP8_7f - eor diff, data1, data2 /* Non-zero if differences found. */ - csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/ - bics has_nul, tmp1, tmp2 - ccmp endloop, #0, #0, eq /*has_null is ZERO: no null byte*/ - b.ne .Lunequal_proc - /*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 - bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ - eor diff, data1, data2 /* Non-zero if differences found. */ - csinv endloop, diff, xzr, eq - cbnz endloop, .Lunequal_proc +L(page_end_loop): + ldrb data1w, [src1], #1 + ldrb data2w, [src2], #1 + cmp data1w, #1 + ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */ + b.ne L(done) + subs count, count, #1 + b.hi L(page_end_loop) + +L(do_misaligned): + /* Prepare ourselves for the next page crossing. Unlike the aligned + loop, we fetch 1 less dword because we risk crossing bounds on + SRC2. */ + mov count, #8 + subs limit_wd, limit_wd, #1 + b.lo L(done_loop) +L(loop_misaligned): + and tmp2, src2, #0xff8 + eor tmp2, tmp2, #0xff8 + cbz tmp2, L(page_end_loop)

- /*The second part process*/ ldr data1, [src1], #8 ldr data2, [src2], #8 - subs limit_wd, limit_wd, #1 sub tmp1, data1, zeroones orr tmp2, data1, #REP8_7f - eor diff, data1, data2 /* Non-zero if differences found. */ - csinv endloop, diff, xzr, ne/*if limit_wd is 0,will finish the cmp*/ - bics has_nul, tmp1, tmp2 - ccmp endloop, #0, #0, eq /*has_null is ZERO: no null byte*/ - b.eq .Lloopcmp_proc - -.Lunequal_proc: - orr syndrome, diff, has_nul - cbz syndrome, .Lremain8 -.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 can't 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 ) - /* - * 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 - 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 - -.Lremain8: - /* Limit % 8 == 0 => all bytes significant. */ - ands limit, limit, #7 - b.eq .Lret0 -.Ltiny8proc: - ldrb data1w, [src1], #1 - ldrb data2w, [src2], #1 - subs limit, limit, #1 + eor diff, data1, data2 /* Non-zero if differences found. */ + bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ + ccmp diff, #0, #0, eq + b.ne L(not_limit) + subs limit_wd, limit_wd, #1 + b.pl L(loop_misaligned)

- ccmp data1w, #1, #0, ne /* NZCV = 0b0000. */ - ccmp data1w, data2w, #0, cs /* NZCV = 0b0000. */ - b.eq .Ltiny8proc - sub result, data1, data2 - ret +L(done_loop): + /* We found a difference or a NULL before the limit was reached. */ + and limit, limit, #7 + cbz limit, L(not_limit) + /* Read the last word. */ + sub src1, src1, 8 + sub src2, src2, 8 + ldr data1, [src1, limit] + ldr data2, [src2, limit] + sub tmp1, data1, zeroones + orr tmp2, data1, #REP8_7f + eor diff, data1, data2 /* Non-zero if differences found. */ + bics has_nul, tmp1, tmp2 /* Non-zero if NUL terminator. */ + ccmp diff, #0, #0, eq + b.ne L(not_limit)

-.Lret0: +L(ret0): mov result, #0 ret + SYM_FUNC_END_PI(strncmp) EXPORT_SYMBOL_NOKASAN(strncmp)

From: Robin Murphy robin.murphy@arm.com

mainline inclusion from mainline-v5.14-rc1 commit 285133040e6ce0e6f37db962f2b4dad10ea46da0 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XOA CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Import the latest implementation of memcpy(), based on the upstream code of string/aarch64/memcpy.S at commit afd6244 from https://github.com/ARM-software/optimized-routines, and subsuming memmove() in the process.

Note that for simplicity Arm have chosen to contribute this code to Linux under GPLv2 rather than the original MIT license.

Note also that the needs of the usercopy routines vs. regular memcpy() have now diverged so far that we abandon the shared template idea and the damage which that incurred to the tuning of LDP/STP loops. We'll be back to tackle those routines separately in future.

Signed-off-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/3c953af43506581b2422f61952261e76949ba711.162212852... Signed-off-by: Will Deacon will@kernel.org

Conflicts: arch/arm64/lib/Makefile Signed-off-by: liwei liwei728@huawei.com --- arch/arm64/lib/Makefile | 8 +- arch/arm64/lib/memcpy.S | 272 ++++++++++++++++++++++++++++++++------- arch/arm64/lib/memmove.S | 189 --------------------------- 3 files changed, 233 insertions(+), 236 deletions(-) delete mode 100644 arch/arm64/lib/memmove.S

diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile index e2dbef587c9b..98577a2659ec 100644 --- a/arch/arm64/lib/Makefile +++ b/arch/arm64/lib/Makefile @@ -1,8 +1,8 @@ # SPDX-License-Identifier: GPL-2.0 -lib-y := clear_user.o delay.o copy_from_user.o \ - copy_to_user.o copy_in_user.o copy_page.o \ - clear_page.o csum.o memchr.o memcpy.o memcpy_mc.o memmove.o \ - memset.o memcmp.o strcmp.o strncmp.o strlen.o \ +lib-y := clear_user.o delay.o copy_from_user.o \ + copy_to_user.o copy_in_user.o copy_page.o \ + clear_page.o csum.o memchr.o memcpy.o memcpy_mc.o \ + memset.o memcmp.o strcmp.o strncmp.o strlen.o \ strnlen.o strchr.o strrchr.o tishift.o

ifeq ($(CONFIG_KERNEL_MODE_NEON), y) diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S index dc8d2a216a6e..31073a8304fb 100644 --- a/arch/arm64/lib/memcpy.S +++ b/arch/arm64/lib/memcpy.S @@ -1,66 +1,252 @@ /* 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/aarch6... */

#include <linux/linkage.h> #include <asm/assembler.h> -#include <asm/cache.h>

-/* - * Copy a buffer from src to dest (alignment handled by the hardware) +/* Assumptions: + * + * ARMv8-a, AArch64, unaligned accesses. * - * Parameters: - * x0 - dest - * x1 - src - * x2 - n - * Returns: - * x0 - dest */ - .macro ldrb1 reg, ptr, val - ldrb \reg, [\ptr], \val - .endm - - .macro strb1 reg, ptr, val - strb \reg, [\ptr], \val - .endm

- .macro ldrh1 reg, ptr, val - ldrh \reg, [\ptr], \val - .endm +#define L(label) .L ## label

- .macro strh1 reg, ptr, val - strh \reg, [\ptr], \val - .endm +#define dstin x0 +#define src x1 +#define count x2 +#define dst x3 +#define srcend x4 +#define dstend x5 +#define A_l x6 +#define A_lw w6 +#define A_h x7 +#define B_l x8 +#define B_lw w8 +#define B_h x9 +#define C_l x10 +#define C_lw w10 +#define C_h x11 +#define D_l x12 +#define D_h x13 +#define E_l x14 +#define E_h x15 +#define F_l x16 +#define F_h x17 +#define G_l count +#define G_h dst +#define H_l src +#define H_h srcend +#define tmp1 x14

- .macro ldr1 reg, ptr, val - ldr \reg, [\ptr], \val - .endm +/* This implementation handles overlaps and supports both memcpy and memmove + from a single entry point. It uses unaligned accesses and branchless + sequences to keep the code small, simple and improve performance.

- .macro str1 reg, ptr, val - str \reg, [\ptr], \val - .endm + Copies are split into 3 main cases: small copies of up to 32 bytes, medium + copies of up to 128 bytes, and large copies. The overhead of the overlap + check is negligible since it is only required for large copies.

- .macro ldp1 reg1, reg2, ptr, val - ldp \reg1, \reg2, [\ptr], \val - .endm - - .macro stp1 reg1, reg2, ptr, val - stp \reg1, \reg2, [\ptr], \val - .endm + Large copies use a software pipelined loop processing 64 bytes per iteration. + The destination pointer is 16-byte aligned to minimize unaligned accesses. + The loop tail is handled by always copying 64 bytes from the end. +*/

+SYM_FUNC_START_ALIAS(__memmove) +SYM_FUNC_START_WEAK_ALIAS_PI(memmove) SYM_FUNC_START_ALIAS(__memcpy) SYM_FUNC_START_WEAK_PI(memcpy) -#include "copy_template.S" + add srcend, src, count + add dstend, dstin, count + cmp count, 128 + b.hi L(copy_long) + cmp count, 32 + b.hi L(copy32_128) + + /* Small copies: 0..32 bytes. */ + cmp count, 16 + b.lo L(copy16) + ldp A_l, A_h, [src] + ldp D_l, D_h, [srcend, -16] + stp A_l, A_h, [dstin] + stp D_l, D_h, [dstend, -16] + ret + + /* Copy 8-15 bytes. */ +L(copy16): + tbz count, 3, L(copy8) + ldr A_l, [src] + ldr A_h, [srcend, -8] + str A_l, [dstin] + str A_h, [dstend, -8] + ret + + .p2align 3 + /* Copy 4-7 bytes. */ +L(copy8): + tbz count, 2, L(copy4) + ldr A_lw, [src] + ldr B_lw, [srcend, -4] + str A_lw, [dstin] + str B_lw, [dstend, -4] + ret + + /* Copy 0..3 bytes using a branchless sequence. */ +L(copy4): + cbz count, L(copy0) + lsr tmp1, count, 1 + ldrb A_lw, [src] + ldrb C_lw, [srcend, -1] + ldrb B_lw, [src, tmp1] + strb A_lw, [dstin] + strb B_lw, [dstin, tmp1] + strb C_lw, [dstend, -1] +L(copy0): + ret + + .p2align 4 + /* Medium copies: 33..128 bytes. */ +L(copy32_128): + ldp A_l, A_h, [src] + ldp B_l, B_h, [src, 16] + ldp C_l, C_h, [srcend, -32] + ldp D_l, D_h, [srcend, -16] + cmp count, 64 + b.hi L(copy128) + stp A_l, A_h, [dstin] + stp B_l, B_h, [dstin, 16] + stp C_l, C_h, [dstend, -32] + stp D_l, D_h, [dstend, -16] ret + + .p2align 4 + /* Copy 65..128 bytes. */ +L(copy128): + ldp E_l, E_h, [src, 32] + ldp F_l, F_h, [src, 48] + cmp count, 96 + b.ls L(copy96) + ldp G_l, G_h, [srcend, -64] + ldp H_l, H_h, [srcend, -48] + stp G_l, G_h, [dstend, -64] + stp H_l, H_h, [dstend, -48] +L(copy96): + stp A_l, A_h, [dstin] + stp B_l, B_h, [dstin, 16] + stp E_l, E_h, [dstin, 32] + stp F_l, F_h, [dstin, 48] + stp C_l, C_h, [dstend, -32] + stp D_l, D_h, [dstend, -16] + ret + + .p2align 4 + /* Copy more than 128 bytes. */ +L(copy_long): + /* Use backwards copy if there is an overlap. */ + sub tmp1, dstin, src + cbz tmp1, L(copy0) + cmp tmp1, count + b.lo L(copy_long_backwards) + + /* Copy 16 bytes and then align dst to 16-byte alignment. */ + + ldp D_l, D_h, [src] + and tmp1, dstin, 15 + bic dst, dstin, 15 + sub src, src, tmp1 + add count, count, tmp1 /* Count is now 16 too large. */ + ldp A_l, A_h, [src, 16] + stp D_l, D_h, [dstin] + ldp B_l, B_h, [src, 32] + ldp C_l, C_h, [src, 48] + ldp D_l, D_h, [src, 64]! + subs count, count, 128 + 16 /* Test and readjust count. */ + b.ls L(copy64_from_end) + +L(loop64): + stp A_l, A_h, [dst, 16] + ldp A_l, A_h, [src, 16] + stp B_l, B_h, [dst, 32] + ldp B_l, B_h, [src, 32] + stp C_l, C_h, [dst, 48] + ldp C_l, C_h, [src, 48] + stp D_l, D_h, [dst, 64]! + ldp D_l, D_h, [src, 64]! + subs count, count, 64 + b.hi L(loop64) + + /* Write the last iteration and copy 64 bytes from the end. */ +L(copy64_from_end): + ldp E_l, E_h, [srcend, -64] + stp A_l, A_h, [dst, 16] + ldp A_l, A_h, [srcend, -48] + stp B_l, B_h, [dst, 32] + ldp B_l, B_h, [srcend, -32] + stp C_l, C_h, [dst, 48] + ldp C_l, C_h, [srcend, -16] + stp D_l, D_h, [dst, 64] + stp E_l, E_h, [dstend, -64] + stp A_l, A_h, [dstend, -48] + stp B_l, B_h, [dstend, -32] + stp C_l, C_h, [dstend, -16] + ret + + .p2align 4 + + /* Large backwards copy for overlapping copies. + Copy 16 bytes and then align dst to 16-byte alignment. */ +L(copy_long_backwards): + ldp D_l, D_h, [srcend, -16] + and tmp1, dstend, 15 + sub srcend, srcend, tmp1 + sub count, count, tmp1 + ldp A_l, A_h, [srcend, -16] + stp D_l, D_h, [dstend, -16] + ldp B_l, B_h, [srcend, -32] + ldp C_l, C_h, [srcend, -48] + ldp D_l, D_h, [srcend, -64]! + sub dstend, dstend, tmp1 + subs count, count, 128 + b.ls L(copy64_from_start) + +L(loop64_backwards): + stp A_l, A_h, [dstend, -16] + ldp A_l, A_h, [srcend, -16] + stp B_l, B_h, [dstend, -32] + ldp B_l, B_h, [srcend, -32] + stp C_l, C_h, [dstend, -48] + ldp C_l, C_h, [srcend, -48] + stp D_l, D_h, [dstend, -64]! + ldp D_l, D_h, [srcend, -64]! + subs count, count, 64 + b.hi L(loop64_backwards) + + /* Write the last iteration and copy 64 bytes from the start. */ +L(copy64_from_start): + ldp G_l, G_h, [src, 48] + stp A_l, A_h, [dstend, -16] + ldp A_l, A_h, [src, 32] + stp B_l, B_h, [dstend, -32] + ldp B_l, B_h, [src, 16] + stp C_l, C_h, [dstend, -48] + ldp C_l, C_h, [src] + stp D_l, D_h, [dstend, -64] + stp G_l, G_h, [dstin, 48] + stp A_l, A_h, [dstin, 32] + stp B_l, B_h, [dstin, 16] + stp C_l, C_h, [dstin] + ret + SYM_FUNC_END_PI(memcpy) EXPORT_SYMBOL(memcpy) SYM_FUNC_END_ALIAS(__memcpy) EXPORT_SYMBOL(__memcpy) +SYM_FUNC_END_ALIAS_PI(memmove) +EXPORT_SYMBOL(memmove) +SYM_FUNC_END_ALIAS(__memmove) +EXPORT_SYMBOL(__memmove) \ No newline at end of file diff --git a/arch/arm64/lib/memmove.S b/arch/arm64/lib/memmove.S deleted file mode 100644 index 1035dce4bdaf..000000000000 --- a/arch/arm64/lib/memmove.S +++ /dev/null @@ -1,189 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2013 ARM Ltd. - * Copyright (C) 2013 Linaro. - * - * 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/ - */ - -#include <linux/linkage.h> -#include <asm/assembler.h> -#include <asm/cache.h> - -/* - * Move a buffer from src to test (alignment handled by the hardware). - * If dest <= src, call memcpy, otherwise copy in reverse order. - * - * Parameters: - * x0 - dest - * x1 - src - * x2 - n - * Returns: - * x0 - dest - */ -dstin .req x0 -src .req x1 -count .req x2 -tmp1 .req x3 -tmp1w .req w3 -tmp2 .req x4 -tmp2w .req w4 -tmp3 .req x5 -tmp3w .req w5 -dst .req x6 - -A_l .req x7 -A_h .req x8 -B_l .req x9 -B_h .req x10 -C_l .req x11 -C_h .req x12 -D_l .req x13 -D_h .req x14 - -SYM_FUNC_START_ALIAS(__memmove) -SYM_FUNC_START_WEAK_PI(memmove) - cmp dstin, src - b.lo __memcpy - add tmp1, src, count - cmp dstin, tmp1 - b.hs __memcpy /* No overlap. */ - - add dst, dstin, count - add src, src, count - cmp count, #16 - b.lo .Ltail15 /*probably non-alignment accesses.*/ - - ands tmp2, src, #15 /* Bytes to reach alignment. */ - b.eq .LSrcAligned - sub count, count, tmp2 - /* - * process the aligned offset length to make the src aligned firstly. - * those extra instructions' cost is acceptable. It also make the - * coming accesses are based on aligned address. - */ - tbz tmp2, #0, 1f - ldrb tmp1w, [src, #-1]! - strb tmp1w, [dst, #-1]! -1: - tbz tmp2, #1, 2f - ldrh tmp1w, [src, #-2]! - strh tmp1w, [dst, #-2]! -2: - tbz tmp2, #2, 3f - ldr tmp1w, [src, #-4]! - str tmp1w, [dst, #-4]! -3: - tbz tmp2, #3, .LSrcAligned - ldr tmp1, [src, #-8]! - str tmp1, [dst, #-8]! - -.LSrcAligned: - cmp count, #64 - b.ge .Lcpy_over64 - - /* - * Deal with small copies quickly by dropping straight into the - * exit block. - */ -.Ltail63: - /* - * Copy up to 48 bytes of data. At this point we only need the - * bottom 6 bits of count to be accurate. - */ - ands tmp1, count, #0x30 - b.eq .Ltail15 - cmp tmp1w, #0x20 - b.eq 1f - b.lt 2f - ldp A_l, A_h, [src, #-16]! - stp A_l, A_h, [dst, #-16]! -1: - ldp A_l, A_h, [src, #-16]! - stp A_l, A_h, [dst, #-16]! -2: - ldp A_l, A_h, [src, #-16]! - stp A_l, A_h, [dst, #-16]! - -.Ltail15: - tbz count, #3, 1f - ldr tmp1, [src, #-8]! - str tmp1, [dst, #-8]! -1: - tbz count, #2, 2f - ldr tmp1w, [src, #-4]! - str tmp1w, [dst, #-4]! -2: - tbz count, #1, 3f - ldrh tmp1w, [src, #-2]! - strh tmp1w, [dst, #-2]! -3: - tbz count, #0, .Lexitfunc - ldrb tmp1w, [src, #-1] - strb tmp1w, [dst, #-1] - -.Lexitfunc: - ret - -.Lcpy_over64: - subs count, count, #128 - b.ge .Lcpy_body_large - /* - * Less than 128 bytes to copy, so handle 64 bytes here and then jump - * to the tail. - */ - ldp A_l, A_h, [src, #-16] - stp A_l, A_h, [dst, #-16] - ldp B_l, B_h, [src, #-32] - ldp C_l, C_h, [src, #-48] - stp B_l, B_h, [dst, #-32] - stp C_l, C_h, [dst, #-48] - ldp D_l, D_h, [src, #-64]! - stp D_l, D_h, [dst, #-64]! - - tst count, #0x3f - b.ne .Ltail63 - ret - - /* - * Critical loop. Start at a new cache line boundary. Assuming - * 64 bytes per line this ensures the entire loop is in one line. - */ - .p2align L1_CACHE_SHIFT -.Lcpy_body_large: - /* pre-load 64 bytes data. */ - ldp A_l, A_h, [src, #-16] - ldp B_l, B_h, [src, #-32] - ldp C_l, C_h, [src, #-48] - ldp D_l, D_h, [src, #-64]! -1: - /* - * interlace the load of next 64 bytes data block with store of the last - * loaded 64 bytes data. - */ - stp A_l, A_h, [dst, #-16] - ldp A_l, A_h, [src, #-16] - stp B_l, B_h, [dst, #-32] - ldp B_l, B_h, [src, #-32] - stp C_l, C_h, [dst, #-48] - ldp C_l, C_h, [src, #-48] - stp D_l, D_h, [dst, #-64]! - ldp D_l, D_h, [src, #-64]! - subs count, count, #64 - b.ge 1b - stp A_l, A_h, [dst, #-16] - stp B_l, B_h, [dst, #-32] - stp C_l, C_h, [dst, #-48] - stp D_l, D_h, [dst, #-64]! - - tst count, #0x3f - b.ne .Ltail63 - ret -SYM_FUNC_END_PI(memmove) -EXPORT_SYMBOL(memmove) -SYM_FUNC_END_ALIAS(__memmove) -EXPORT_SYMBOL(__memmove)

From: Robin Murphy robin.murphy@arm.com

mainline inclusion from mainline-v5.14-rc1 commit 344323e0428b9911406bede6cff23d1482c19eae category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I94XOA CVE: NA

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

Now that we're always using STTR variants rather than abstracting two different addressing modes, the user_ldst macro here is frankly more obfuscating than helpful. Rewrite __arch_clear_user() with regular USER() annotations so that it's clearer what's going on, and take the opportunity to minimise the branchiness in the most common paths, while also allowing the exception fixup to return an accurate result.

Apparently some folks examine large reads from /dev/zero closely enough to notice the loop being hot, so align it per the other critical loops (presumably around a typical instruction fetch granularity).

Reviewed-by: Mark Rutland mark.rutland@arm.com Signed-off-by: Robin Murphy robin.murphy@arm.com Link: https://lore.kernel.org/r/1cbd78b12c076a8ad4656a345811cfb9425df0b3.162212852... Signed-off-by: Will Deacon will@kernel.org Signed-off-by: liwei liwei728@huawei.com --- arch/arm64/lib/clear_user.S | 47 +++++++++++++++++++++---------------- 1 file changed, 27 insertions(+), 20 deletions(-)

diff --git a/arch/arm64/lib/clear_user.S b/arch/arm64/lib/clear_user.S index 64cdf4ef04a2..438ca547b004 100644 --- a/arch/arm64/lib/clear_user.S +++ b/arch/arm64/lib/clear_user.S @@ -1,12 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * Based on arch/arm/lib/clear_user.S - * - * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2021 Arm Ltd. */ -#include <linux/linkage.h>

-#include <asm/asm-uaccess.h> +#include <linux/linkage.h> #include <asm/assembler.h>

.text @@ -19,28 +16,36 @@ * * Alignment fixed up by hardware. */ + + .p2align 4 + // Alignment is for the loop, but since the prologue (including BTI) + // is also 16 bytes we can keep any padding outside the function SYM_FUNC_START(__arch_clear_user) - mov x2, x1 // save the size for fixup return + add x2, x0, x1 subs x1, x1, #8 b.mi 2f #ifdef CONFIG_ARCH_HISI .align 5 #endif 1: -user_ldst 9f, sttr, xzr, x0, 8 +USER(9f, sttr xzr, [x0]) + add x0, x0, #8 subs x1, x1, #8 - b.pl 1b -2: adds x1, x1, #4 - b.mi 3f -user_ldst 9f, sttr, wzr, x0, 4 - sub x1, x1, #4 -3: adds x1, x1, #2 - b.mi 4f -user_ldst 9f, sttrh, wzr, x0, 2 - sub x1, x1, #2 -4: adds x1, x1, #1 - b.mi 5f -user_ldst 9f, sttrb, wzr, x0, 0 + b.hi 1b +USER(9f, sttr xzr, [x2, #-8]) + mov x0, #0 + ret + +2: tbz x1, #2, 3f +USER(9f, sttr wzr, [x0]) +USER(8f, sttr wzr, [x2, #-4]) + mov x0, #0 + ret + +3: tbz x1, #1, 4f +USER(9f, sttrh wzr, [x0]) +4: tbz x1, #0, 5f +USER(7f, sttrb wzr, [x2, #-1]) 5: mov x0, #0 ret SYM_FUNC_END(__arch_clear_user) @@ -48,6 +53,8 @@ EXPORT_SYMBOL(__arch_clear_user)

.section .fixup,"ax" .align 2 -9: mov x0, x2 // return the original size +7: sub x0, x2, #5 // Adjust for faulting on the final byte... +8: add x0, x0, #4 // ...or the second word of the 4-7 byte case +9: sub x0, x2, x0 ret .previous