public inbox for linux-arm-kernel@lists.infradead.org 
 help / color / mirror / Atom feed
From: Shuai Xue <xueshuai@linux•alibaba.com>
To: Ruidong Tian <tianruidong@linux•alibaba.com>,
	catalin.marinas@arm•com, will@kernel•org, rafael@kernel•org,
	tony.luck@intel•com, guohanjun@huawei•com, mchehab@kernel•org,
	tongtiangen@huawei•com, james.morse@arm•com,
	robin.murphy@arm•com, andreyknvl@gmail•com, dvyukov@google•com,
	vincenzo.frascino@arm•com, mpe@ellerman•id.au, npiggin@gmail•com,
	ryabinin.a.a@gmail•com, glider@google•com,
	christophe.leroy@csgroup•eu, aneesh.kumar@kernel•org,
	naveen.n.rao@linux•ibm.com, tglx@linutronix•de, mingo@redhat•com
Cc: linux-arm-kernel@lists•infradead.org, linux-mm@kvack•org,
	linuxppc-dev@lists•ozlabs.org, linux-kernel@vger•kernel.org,
	kasan-dev@googlegroups•com
Subject: Re: [PATCH v14 7/8] arm64: introduce copy_mc_to_kernel() implementation
Date: Thu, 28 May 2026 11:10:40 +0800	[thread overview]
Message-ID: <05accd00-bcb8-4f23-bd2c-d5eb3bf408f3@linux.alibaba.com> (raw)
In-Reply-To: <20260518084956.2538442-8-tianruidong@linux.alibaba.com>



On 5/18/26 4:49 PM, Ruidong Tian wrote:
> From: Tong Tiangen <tongtiangen@huawei•com>
> 
> The copy_mc_to_kernel() helper is memory copy implementation that handles
> source exceptions. It can be used in memory copy scenarios that tolerate
> hardware memory errors(e.g: pmem_read/dax_copy_to_iter).
> 
> Currently, only x86 and ppc support this helper, Add this for ARM64 as
> well, if ARCH_HAS_COPY_MC is defined, by implementing copy_mc_to_kernel()
> and memcpy_mc() functions.
> 
> Because there is no caller-saved GPR is available for saving "bytes not
> copied" in memcpy(), the memcpy_mc() is referenced to the implementation
> of copy_from_user(). In addition, the fixup of MOPS insn is not considered
> at present.
> 
> [Ruidong: refactor memcpy_mc on top of the new memcpy implementation.]
> 
> Signed-off-by: Tong Tiangen <tongtiangen@huawei•com>
> Signed-off-by: Ruidong Tian <tianruidong@linux•alibaba.com>
> ---
>   arch/arm64/include/asm/string.h  |   5 +
>   arch/arm64/include/asm/uaccess.h |  17 +++
>   arch/arm64/lib/Makefile          |   2 +-
>   arch/arm64/lib/memcpy.S          | 253 +++----------------------------
>   arch/arm64/lib/memcpy_mc.S       |  56 +++++++
>   arch/arm64/lib/memcpy_template.S | 249 ++++++++++++++++++++++++++++++
>   mm/kasan/shadow.c                |  12 ++
>   7 files changed, 359 insertions(+), 235 deletions(-)
>   create mode 100644 arch/arm64/lib/memcpy_mc.S
>   create mode 100644 arch/arm64/lib/memcpy_template.S
> 
> diff --git a/arch/arm64/include/asm/string.h b/arch/arm64/include/asm/string.h
> index 3a3264ff47b9..23eca4fb24fa 100644
> --- a/arch/arm64/include/asm/string.h
> +++ b/arch/arm64/include/asm/string.h
> @@ -35,6 +35,10 @@ extern void *memchr(const void *, int, __kernel_size_t);
>   extern void *memcpy(void *, const void *, __kernel_size_t);
>   extern void *__memcpy(void *, const void *, __kernel_size_t);
>   
> +#define __HAVE_ARCH_MEMCPY_MC
> +extern int memcpy_mc(void *, const void *, __kernel_size_t);
> +extern int __memcpy_mc(void *, const void *, __kernel_size_t);
> +
>   #define __HAVE_ARCH_MEMMOVE
>   extern void *memmove(void *, const void *, __kernel_size_t);
>   extern void *__memmove(void *, const void *, __kernel_size_t);
> @@ -57,6 +61,7 @@ void memcpy_flushcache(void *dst, const void *src, size_t cnt);
>    */
>   
>   #define memcpy(dst, src, len) __memcpy(dst, src, len)
> +#define memcpy_mc(dst, src, len) __memcpy_mc(dst, src, len)
>   #define memmove(dst, src, len) __memmove(dst, src, len)
>   #define memset(s, c, n) __memset(s, c, n)
>   
> diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
> index b0c83a08dda9..93277eca2268 100644
> --- a/arch/arm64/include/asm/uaccess.h
> +++ b/arch/arm64/include/asm/uaccess.h
> @@ -499,5 +499,22 @@ static inline size_t probe_subpage_writeable(const char __user *uaddr,
>   }
>   
>   #endif /* CONFIG_ARCH_HAS_SUBPAGE_FAULTS */
> +#ifdef CONFIG_ARCH_HAS_COPY_MC
> +/**
> + * copy_mc_to_kernel - memory copy that handles source exceptions
> + *
> + * @to:		destination address
> + * @from:	source address
> + * @size:	number of bytes to copy
> + *
> + * Return 0 for success, or bytes not copied.
> + */
> +static inline unsigned long __must_check
> +copy_mc_to_kernel(void *to, const void *from, unsigned long size)
> +{
> +	return memcpy_mc(to, from, size);
> +}
> +#define copy_mc_to_kernel copy_mc_to_kernel
> +#endif
>   
>   #endif /* __ASM_UACCESS_H */
> diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
> index 1f4c3f743a20..a5820e6c33d4 100644
> --- a/arch/arm64/lib/Makefile
> +++ b/arch/arm64/lib/Makefile
> @@ -7,7 +7,7 @@ lib-y		:= clear_user.o delay.o copy_from_user.o		\
>   
>   lib-$(CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE) += uaccess_flushcache.o
>   
> -lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc_page.o
> +lib-$(CONFIG_ARCH_HAS_COPY_MC) += copy_mc_page.o memcpy_mc.o
>   
>   obj-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
>   
> diff --git a/arch/arm64/lib/memcpy.S b/arch/arm64/lib/memcpy.S
> index 9b99106fb95f..ef6aea2de9b4 100644
> --- a/arch/arm64/lib/memcpy.S
> +++ b/arch/arm64/lib/memcpy.S
> @@ -15,247 +15,32 @@
>    *
>    */
>   
> -#define L(label) .L ## label
> +	.macro ldrb1 reg, addr:vararg
> +		ldrb  \reg, \addr
> +	.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, addr:vararg
> +		ldr   \reg, \addr
> +	.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 ldp1 reg1, reg2, addr:vararg
> +		ldp   \reg1, \reg2, \addr
> +	.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 ret1
> +		ret
> +	.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.
> -*/
> +	.macro cpy1 dst, src, count
> +		.arch_extension mops
> +		cpyp [\dst]!, [\src]!, \count!
> +		cpym [\dst]!, [\src]!, \count!
> +		cpye [\dst]!, [\src]!, \count!
> +	.endm
>   
> -SYM_FUNC_START_LOCAL(__pi_memcpy_generic)
> -	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_generic)
> -
> -#ifdef CONFIG_AS_HAS_MOPS
> -	.arch_extension mops
>   SYM_FUNC_START(__pi_memcpy)
> -alternative_if_not ARM64_HAS_MOPS
> -	b	__pi_memcpy_generic
> -alternative_else_nop_endif
> -
> -	mov	dst, dstin
> -	cpyp	[dst]!, [src]!, count!
> -	cpym	[dst]!, [src]!, count!
> -	cpye	[dst]!, [src]!, count!
> -	ret
> +#include "memcpy_template.S"
>   SYM_FUNC_END(__pi_memcpy)
> -#else
> -SYM_FUNC_ALIAS(__pi_memcpy, __pi_memcpy_generic)
> -#endif
>   
>   SYM_FUNC_ALIAS(__memcpy, __pi_memcpy)
>   EXPORT_SYMBOL(__memcpy)
> diff --git a/arch/arm64/lib/memcpy_mc.S b/arch/arm64/lib/memcpy_mc.S
> new file mode 100644
> index 000000000000..90624d35af4b
> --- /dev/null
> +++ b/arch/arm64/lib/memcpy_mc.S
> @@ -0,0 +1,56 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +/*
> + * Copyright (c) 2012-2021, Arm Limited.
> + *
> + * Adapted from the original at:
> + * https://github.com/ARM-software/optimized-routines/blob/afd6244a1f8d9229/string/aarch64/memcpy.S
> + */
> +
> +#include <linux/linkage.h>
> +#include <asm/assembler.h>
> +#include <asm/asm-uaccess.h>
> +
> +/* Assumptions:
> + *
> + * ARMv8-a, AArch64, unaligned accesses.
> + *
> + */
> +
> +	.macro ldrb1 reg, addr:vararg
> +		KERNEL_MEM_ERR(9998f, ldrb  \reg, \addr)
> +	.endm
> +
> +	.macro ldr1 reg, addr:vararg
> +		KERNEL_MEM_ERR(9998f, ldr   \reg, \addr)
> +	.endm
> +
> +	.macro ldp1 reg1, reg2, addr:vararg
> +		KERNEL_MEM_ERR(9998f, ldp   \reg1, \reg2, \addr)
> +	.endm
> +
> +	.macro ret1
> +		mov	x0, #0
> +		ret
> +	.endm
> +
> +	.macro cpy1 dst, src, count
> +	.arch_extension mops
> +	USER_CPY(9998f, 0, cpyp [\dst]!, [\src]!, \count!)
> +	USER_CPY(9996f, 0, cpym [\dst]!, [\src]!, \count!)
> +	USER_CPY(9996f, 0, cpye [\dst]!, [\src]!, \count!)

memcpy_mc.S annotates kernel-to-kernel MOPS with USER_CPY, registering
EX_TYPE_UACCESS_CPY entries. fixup_exception_me() then routes those
through ex_handler_uaccess_cpy(...., esr=0), whose
cpy_faulted_on_uaccess() applies page-fault read/write match
semantics. It only happens to work today because uaccess_is_write=0
matches a hard-coded fault_on_write=0; any tightening (e.g. real esr
threading) immediately breaks recovery.

Please fix this in conjunction with patch 3:
   (a) introduce KERNEL_CPY / EX_TYPE_KACCESS_CPY_MC, or
   (b) give EX_TYPE_UACCESS_CPY a separate MC handler in
       fixup_exception_me() that just redirects PC.

> +	.endm
> +
> +SYM_FUNC_START(__memcpy_mc)
> +#include "memcpy_template.S"
> +
> +	// Exception fixups
> +9996:	b.cs	9998f
> +	// Registers are in Option A format
> +	add	dst, dst, count
> +9998:	sub	x0, dstend, dstin			// bytes not copied


The MOPS branch in memcpy_template.S executes cpy1 *before* the
no_mops block runs `add dstend, dstin, count`. So if the cpy1 takes
an SEA, control jumps to the 9998 fixup in memcpy_mc.S:

     9998: sub x0, dstend, dstin            // bytes not copied
           ret

with dstend uninitialised. The "bytes not copied" return value is
arbitrary garbage in this case, and copy_mc_to_kernel() will pass
that to its caller (dax/pmem), which will then re-touch dst[0..ret]
based on a bogus boundary. Please initialise srcend/dstend before
the cpy1, or save the original count to a callee-saved register and
return it directly


> +	ret
> +SYM_FUNC_END(__memcpy_mc)
> +
> +EXPORT_SYMBOL(__memcpy_mc)
> +SYM_FUNC_ALIAS_WEAK(memcpy_mc, __memcpy_mc)
> +EXPORT_SYMBOL(memcpy_mc)
> diff --git a/arch/arm64/lib/memcpy_template.S b/arch/arm64/lib/memcpy_template.S
> new file mode 100644
> index 000000000000..205516c6e076
> --- /dev/null
> +++ b/arch/arm64/lib/memcpy_template.S
> @@ -0,0 +1,249 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +/*
> + * Copyright (c) 2012-2021, Arm Limited.
> + *
> + * Adapted from the original at:
> + * https://github.com/ARM-software/optimized-routines/blob/afd6244a1f8d9229/string/aarch64/memcpy.S
> + */
> +
> +#include <linux/linkage.h>
> +#include <asm/assembler.h>
> +
> +/* Assumptions:
> + *
> + * ARMv8-a, AArch64, unaligned accesses.
> + *
> + */
> +
> +#define L(label) .L ## label
> +
> +#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
> +
> +/* 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.
> +
> +   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.
> +
> +   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.
> +*/
> +
> +#ifdef CONFIG_AS_HAS_MOPS
> +alternative_if_not ARM64_HAS_MOPS
> +	b	L(no_mops):

Trailing colon. Should be:

     b   L(no_mops)

GNU as either rejects this outright or accepts it as nonsense. Either
way, FEAT_MOPS-capable toolchain builds (binutils >= 2.39, recent LLVM)
will fail or produce broken code. Please verify v2 with both
CONFIG_AS_HAS_MOPS=y and =n.


> +alternative_else_nop_endif
> +
> +	cpy1	dst, src, count

Does this execute the hardware copy instruction using an uninitialized
dst (x3) register?

Before the refactoring, memcpy.S had:

     mov  dst, dstin          ; x3 = x0 (preserve x0 as return value)
     cpyp [dst]!, [src]!, count!
     cpym [dst]!, [src]!, count!
     cpye [dst]!, [src]!, count!
     ret                      ; x0 still holds original dest

After: the template jumps straight to `cpy1 dst, src, count` which
expands to `cpyp [x3]!, [x1]!, x2!` with x3 uninitialised. On any
CPU with FEAT_MOPS (Cortex-X3/X4, A720, etc.) this writes src data to
whatever garbage address x3 held at function entry -- silent memory
corruption or an immediate abort, depending on luck.

This affects both plain memcpy() (through memcpy.S -> memcpy_template.S)
and memcpy_mc() (through memcpy_mc.S -> memcpy_template.S).


> +	ret1
> +#endif
> +
> +L(no_mops):
> +	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)
> +	ldp1	A_l, A_h, [src]
> +	ldp1	D_l, D_h, [srcend, -16]
> +	stp	A_l, A_h, [dstin]
> +	stp	D_l, D_h, [dstend, -16]
> +	ret1
> +
> +	/* Copy 8-15 bytes.  */
> +L(copy16):
> +	tbz	count, 3, L(copy8)
> +	ldr1	A_l, [src]
> +	ldr1	A_h, [srcend, -8]
> +	str	A_l, [dstin]
> +	str	A_h, [dstend, -8]
> +	ret1
> +
> +	.p2align 3
> +	/* Copy 4-7 bytes.  */
> +L(copy8):
> +	tbz	count, 2, L(copy4)
> +	ldr1	A_lw, [src]
> +	ldr1	B_lw, [srcend, -4]
> +	str	A_lw, [dstin]
> +	str	B_lw, [dstend, -4]
> +	ret1
> +
> +	/* Copy 0..3 bytes using a branchless sequence.  */
> +L(copy4):
> +	cbz	count, L(copy0)
> +	lsr	tmp1, count, 1
> +	ldrb1	A_lw, [src]
> +	ldrb1	C_lw, [srcend, -1]
> +	ldrb1	B_lw, [src, tmp1]
> +	strb	A_lw, [dstin]
> +	strb	B_lw, [dstin, tmp1]
> +	strb	C_lw, [dstend, -1]
> +L(copy0):
> +	ret1
> +
> +	.p2align 4
> +	/* Medium copies: 33..128 bytes.  */
> +L(copy32_128):
> +	ldp1	A_l, A_h, [src]
> +	ldp1	B_l, B_h, [src, 16]
> +	ldp1	C_l, C_h, [srcend, -32]
> +	ldp1	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]
> +	ret1
> +
> +	.p2align 4
> +	/* Copy 65..128 bytes.  */
> +L(copy128):
> +	ldp1	E_l, E_h, [src, 32]
> +	ldp1	F_l, F_h, [src, 48]
> +	cmp	count, 96
> +	b.ls	L(copy96)
> +	ldp1	G_l, G_h, [srcend, -64]
> +	ldp1	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]
> +	ret1
> +
> +	.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.  */
> +
> +	ldp1	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.  */
> +	ldp1	A_l, A_h, [src, 16]
> +	stp	D_l, D_h, [dstin]
> +	ldp1	B_l, B_h, [src, 32]
> +	ldp1	C_l, C_h, [src, 48]
> +	ldp1	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]
> +	ldp1	A_l, A_h, [src, 16]
> +	stp	B_l, B_h, [dst, 32]
> +	ldp1	B_l, B_h, [src, 32]
> +	stp	C_l, C_h, [dst, 48]
> +	ldp1	C_l, C_h, [src, 48]
> +	stp	D_l, D_h, [dst, 64]!
> +	ldp1	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):
> +	ldp1	E_l, E_h, [srcend, -64]
> +	stp	A_l, A_h, [dst, 16]
> +	ldp1	A_l, A_h, [srcend, -48]
> +	stp	B_l, B_h, [dst, 32]
> +	ldp1	B_l, B_h, [srcend, -32]
> +	stp	C_l, C_h, [dst, 48]
> +	ldp1	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]
> +	ret1
> +
> +	.p2align 4
> +
> +	/* Large backwards copy for overlapping copies.
> +	   Copy 16 bytes and then align dst to 16-byte alignment.  */
> +L(copy_long_backwards):
> +	ldp1	D_l, D_h, [srcend, -16]
> +	and	tmp1, dstend, 15
> +	sub	srcend, srcend, tmp1
> +	sub	count, count, tmp1
> +	ldp1	A_l, A_h, [srcend, -16]
> +	stp	D_l, D_h, [dstend, -16]
> +	ldp1	B_l, B_h, [srcend, -32]
> +	ldp1	C_l, C_h, [srcend, -48]
> +	ldp1	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]
> +	ldp1	A_l, A_h, [srcend, -16]
> +	stp	B_l, B_h, [dstend, -32]
> +	ldp1	B_l, B_h, [srcend, -32]
> +	stp	C_l, C_h, [dstend, -48]
> +	ldp1	C_l, C_h, [srcend, -48]
> +	stp	D_l, D_h, [dstend, -64]!
> +	ldp1	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):
> +	ldp1	G_l, G_h, [src, 48]
> +	stp	A_l, A_h, [dstend, -16]
> +	ldp1	A_l, A_h, [src, 32]
> +	stp	B_l, B_h, [dstend, -32]
> +	ldp1	B_l, B_h, [src, 16]
> +	stp	C_l, C_h, [dstend, -48]
> +	ldp1	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]
> +	ret1
> diff --git a/mm/kasan/shadow.c b/mm/kasan/shadow.c
> index d286e0a04543..3128f0d9cc46 100644
> --- a/mm/kasan/shadow.c
> +++ b/mm/kasan/shadow.c
> @@ -79,6 +79,18 @@ void *memcpy(void *dest, const void *src, size_t len)
>   }
>   #endif
>   
> +#ifdef __HAVE_ARCH_MEMCPY_MC
> +#undef memcpy_mc
> +int memcpy_mc(void *dest, const void *src, size_t len)
> +{
> +	if (!kasan_check_range(src, len, false, _RET_IP_) ||
> +	    !kasan_check_range(dest, len, true, _RET_IP_))
> +		return (int)len;
> +
> +	return __memcpy_mc(dest, src, len);
> +}

memcpy_mc() is declared `int` while copy_mc_to_kernel() returns
unsigned long, and the asm side returns the full 64-bit (dstend - dstin).
For len >= 2GiB (real on dax_copy_to_iter over large NVDIMM regions)
the int truncation produces garbage "bytes not copied". Please use
unsigned long throughout:

     extern unsigned long memcpy_mc(void *, const void *,
                                    __kernel_size_t);
     extern unsigned long __memcpy_mc(void *, const void *,
                                      __kernel_size_t);

and in mm/kasan/shadow.c drop the `(int)len` cast accordingly:

     unsigned long memcpy_mc(...)
     {
         ...
             return len;          /* not (int)len */
         return __memcpy_mc(...);
     }


Thanks.
Shuai


  reply	other threads:[~2026-05-28  3:11 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-18  8:49 [PATCH v14 0/8] arm64: add ARCH_HAS_COPY_MC support Ruidong Tian
2026-05-18  8:49 ` [PATCH v14 1/8] uaccess: add generic fallback version of copy_mc_to_user() Ruidong Tian
2026-05-27  9:16   ` Shuai Xue
2026-05-18  8:49 ` [PATCH v14 2/8] ACPI: APEI: GHES: use exception context to gate SIGBUS on poison consumption Ruidong Tian
2026-05-27  9:34   ` Shuai Xue
2026-05-18  8:49 ` [PATCH v14 3/8] arm64: add support for ARCH_HAS_COPY_MC Ruidong Tian
2026-05-27 11:35   ` Shuai Xue
2026-06-04  8:10     ` Ruidong Tian
2026-05-18  8:49 ` [PATCH v14 4/8] mm/hwpoison: return -EFAULT when copy fail in copy_mc_[user]_highpage() Ruidong Tian
2026-05-27 11:44   ` Shuai Xue
2026-05-18  8:49 ` [PATCH v14 5/8] arm64: support copy_mc_[user]_highpage() Ruidong Tian
2026-05-27 12:11   ` Shuai Xue
2026-05-18  8:49 ` [PATCH v14 6/8] lib/test: memcpy_kunit: add copy_page() and copy_mc_page() tests Ruidong Tian
2026-05-27 13:43   ` Shuai Xue
2026-05-18  8:49 ` [PATCH v14 7/8] arm64: introduce copy_mc_to_kernel() implementation Ruidong Tian
2026-05-28  3:10   ` Shuai Xue [this message]
2026-05-18  8:49 ` [PATCH v14 8/8] lib/tests: memcpy_kunit: add memcpy_mc() and memcpy_mc_large() test Ruidong Tian
2026-05-28  3:17   ` Shuai Xue
2026-05-18 15:05 ` [PATCH v14 0/8] arm64: add ARCH_HAS_COPY_MC support Kefeng Wang
2026-06-05  7:33   ` Ruidong Tian

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=05accd00-bcb8-4f23-bd2c-d5eb3bf408f3@linux.alibaba.com \
    --to=xueshuai@linux$(echo .)alibaba.com \
    --cc=andreyknvl@gmail$(echo .)com \
    --cc=aneesh.kumar@kernel$(echo .)org \
    --cc=catalin.marinas@arm$(echo .)com \
    --cc=christophe.leroy@csgroup$(echo .)eu \
    --cc=dvyukov@google$(echo .)com \
    --cc=glider@google$(echo .)com \
    --cc=guohanjun@huawei$(echo .)com \
    --cc=james.morse@arm$(echo .)com \
    --cc=kasan-dev@googlegroups$(echo .)com \
    --cc=linux-arm-kernel@lists$(echo .)infradead.org \
    --cc=linux-kernel@vger$(echo .)kernel.org \
    --cc=linux-mm@kvack$(echo .)org \
    --cc=linuxppc-dev@lists$(echo .)ozlabs.org \
    --cc=mchehab@kernel$(echo .)org \
    --cc=mingo@redhat$(echo .)com \
    --cc=mpe@ellerman$(echo .)id.au \
    --cc=naveen.n.rao@linux$(echo .)ibm.com \
    --cc=npiggin@gmail$(echo .)com \
    --cc=rafael@kernel$(echo .)org \
    --cc=robin.murphy@arm$(echo .)com \
    --cc=ryabinin.a.a@gmail$(echo .)com \
    --cc=tglx@linutronix$(echo .)de \
    --cc=tianruidong@linux$(echo .)alibaba.com \
    --cc=tongtiangen@huawei$(echo .)com \
    --cc=tony.luck@intel$(echo .)com \
    --cc=vincenzo.frascino@arm$(echo .)com \
    --cc=will@kernel$(echo .)org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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