powerpc/memcpy: Add memcpy_mcsafe for pmem
The pmem infrastructure uses memcpy_mcsafe in the pmem layer so as to convert machine check exceptions into a return value on failure in case a machine check exception is encountered during the memcpy. The return value is the number of bytes remaining to be copied. This patch largely borrows from the copyuser_power7 logic and does not add the VMX optimizations, largely to keep the patch simple. If needed those optimizations can be folded in. Signed-off-by: Balbir Singh <bsingharora@gmail.com> [arbab@linux.ibm.com: Added symbol export] Co-developed-by: Santosh Sivaraj <santosh@fossix.org> Signed-off-by: Santosh Sivaraj <santosh@fossix.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190820081352.8641-7-santosh@fossix.org
This commit is contained in:
Balbir Singh
Michael Ellerman
parent
895e3dceeb
commit
4d4a273854
|
|
@ -53,7 +53,9 @@ void *__memmove(void *to, const void *from, __kernel_size_t n);
|
|||
#ifndef CONFIG_KASAN
|
||||
#define __HAVE_ARCH_MEMSET32
|
||||
#define __HAVE_ARCH_MEMSET64
|
||||
#define __HAVE_ARCH_MEMCPY_MCSAFE
|
||||
|
||||
extern int memcpy_mcsafe(void *dst, const void *src, __kernel_size_t sz);
|
||||
extern void *__memset16(uint16_t *, uint16_t v, __kernel_size_t);
|
||||
extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
|
||||
extern void *__memset64(uint64_t *, uint64_t v, __kernel_size_t);
|
||||
|
|
|
|||
|
|
@ -39,7 +39,7 @@ obj-$(CONFIG_PPC_BOOK3S_64) += copyuser_power7.o copypage_power7.o \
|
|||
memcpy_power7.o
|
||||
|
||||
obj64-y += copypage_64.o copyuser_64.o mem_64.o hweight_64.o \
|
||||
memcpy_64.o
|
||||
memcpy_64.o memcpy_mcsafe_64.o
|
||||
|
||||
obj64-$(CONFIG_SMP) += locks.o
|
||||
obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
|
||||
|
|
|
|||
|
|
@ -0,0 +1,242 @@
|
|||
/* SPDX-License-Identifier: GPL-2.0 */
|
||||
/*
|
||||
* Copyright (C) IBM Corporation, 2011
|
||||
* Derived from copyuser_power7.s by Anton Blanchard <anton@au.ibm.com>
|
||||
* Author - Balbir Singh <bsingharora@gmail.com>
|
||||
*/
|
||||
#include <asm/ppc_asm.h>
|
||||
#include <asm/errno.h>
|
||||
#include <asm/export.h>
|
||||
|
||||
.macro err1
|
||||
100:
|
||||
EX_TABLE(100b,.Ldo_err1)
|
||||
.endm
|
||||
|
||||
.macro err2
|
||||
200:
|
||||
EX_TABLE(200b,.Ldo_err2)
|
||||
.endm
|
||||
|
||||
.macro err3
|
||||
300: EX_TABLE(300b,.Ldone)
|
||||
.endm
|
||||
|
||||
.Ldo_err2:
|
||||
ld r22,STK_REG(R22)(r1)
|
||||
ld r21,STK_REG(R21)(r1)
|
||||
ld r20,STK_REG(R20)(r1)
|
||||
ld r19,STK_REG(R19)(r1)
|
||||
ld r18,STK_REG(R18)(r1)
|
||||
ld r17,STK_REG(R17)(r1)
|
||||
ld r16,STK_REG(R16)(r1)
|
||||
ld r15,STK_REG(R15)(r1)
|
||||
ld r14,STK_REG(R14)(r1)
|
||||
addi r1,r1,STACKFRAMESIZE
|
||||
.Ldo_err1:
|
||||
/* Do a byte by byte copy to get the exact remaining size */
|
||||
mtctr r7
|
||||
46:
|
||||
err3; lbz r0,0(r4)
|
||||
addi r4,r4,1
|
||||
err3; stb r0,0(r3)
|
||||
addi r3,r3,1
|
||||
bdnz 46b
|
||||
li r3,0
|
||||
blr
|
||||
|
||||
.Ldone:
|
||||
mfctr r3
|
||||
blr
|
||||
|
||||
|
||||
_GLOBAL(memcpy_mcsafe)
|
||||
mr r7,r5
|
||||
cmpldi r5,16
|
||||
blt .Lshort_copy
|
||||
|
||||
.Lcopy:
|
||||
/* Get the source 8B aligned */
|
||||
neg r6,r4
|
||||
mtocrf 0x01,r6
|
||||
clrldi r6,r6,(64-3)
|
||||
|
||||
bf cr7*4+3,1f
|
||||
err1; lbz r0,0(r4)
|
||||
addi r4,r4,1
|
||||
err1; stb r0,0(r3)
|
||||
addi r3,r3,1
|
||||
subi r7,r7,1
|
||||
|
||||
1: bf cr7*4+2,2f
|
||||
err1; lhz r0,0(r4)
|
||||
addi r4,r4,2
|
||||
err1; sth r0,0(r3)
|
||||
addi r3,r3,2
|
||||
subi r7,r7,2
|
||||
|
||||
2: bf cr7*4+1,3f
|
||||
err1; lwz r0,0(r4)
|
||||
addi r4,r4,4
|
||||
err1; stw r0,0(r3)
|
||||
addi r3,r3,4
|
||||
subi r7,r7,4
|
||||
|
||||
3: sub r5,r5,r6
|
||||
cmpldi r5,128
|
||||
blt 5f
|
||||
|
||||
mflr r0
|
||||
stdu r1,-STACKFRAMESIZE(r1)
|
||||
std r14,STK_REG(R14)(r1)
|
||||
std r15,STK_REG(R15)(r1)
|
||||
std r16,STK_REG(R16)(r1)
|
||||
std r17,STK_REG(R17)(r1)
|
||||
std r18,STK_REG(R18)(r1)
|
||||
std r19,STK_REG(R19)(r1)
|
||||
std r20,STK_REG(R20)(r1)
|
||||
std r21,STK_REG(R21)(r1)
|
||||
std r22,STK_REG(R22)(r1)
|
||||
std r0,STACKFRAMESIZE+16(r1)
|
||||
|
||||
srdi r6,r5,7
|
||||
mtctr r6
|
||||
|
||||
/* Now do cacheline (128B) sized loads and stores. */
|
||||
.align 5
|
||||
4:
|
||||
err2; ld r0,0(r4)
|
||||
err2; ld r6,8(r4)
|
||||
err2; ld r8,16(r4)
|
||||
err2; ld r9,24(r4)
|
||||
err2; ld r10,32(r4)
|
||||
err2; ld r11,40(r4)
|
||||
err2; ld r12,48(r4)
|
||||
err2; ld r14,56(r4)
|
||||
err2; ld r15,64(r4)
|
||||
err2; ld r16,72(r4)
|
||||
err2; ld r17,80(r4)
|
||||
err2; ld r18,88(r4)
|
||||
err2; ld r19,96(r4)
|
||||
err2; ld r20,104(r4)
|
||||
err2; ld r21,112(r4)
|
||||
err2; ld r22,120(r4)
|
||||
addi r4,r4,128
|
||||
err2; std r0,0(r3)
|
||||
err2; std r6,8(r3)
|
||||
err2; std r8,16(r3)
|
||||
err2; std r9,24(r3)
|
||||
err2; std r10,32(r3)
|
||||
err2; std r11,40(r3)
|
||||
err2; std r12,48(r3)
|
||||
err2; std r14,56(r3)
|
||||
err2; std r15,64(r3)
|
||||
err2; std r16,72(r3)
|
||||
err2; std r17,80(r3)
|
||||
err2; std r18,88(r3)
|
||||
err2; std r19,96(r3)
|
||||
err2; std r20,104(r3)
|
||||
err2; std r21,112(r3)
|
||||
err2; std r22,120(r3)
|
||||
addi r3,r3,128
|
||||
subi r7,r7,128
|
||||
bdnz 4b
|
||||
|
||||
clrldi r5,r5,(64-7)
|
||||
|
||||
/* Up to 127B to go */
|
||||
5: srdi r6,r5,4
|
||||
mtocrf 0x01,r6
|
||||
|
||||
6: bf cr7*4+1,7f
|
||||
err2; ld r0,0(r4)
|
||||
err2; ld r6,8(r4)
|
||||
err2; ld r8,16(r4)
|
||||
err2; ld r9,24(r4)
|
||||
err2; ld r10,32(r4)
|
||||
err2; ld r11,40(r4)
|
||||
err2; ld r12,48(r4)
|
||||
err2; ld r14,56(r4)
|
||||
addi r4,r4,64
|
||||
err2; std r0,0(r3)
|
||||
err2; std r6,8(r3)
|
||||
err2; std r8,16(r3)
|
||||
err2; std r9,24(r3)
|
||||
err2; std r10,32(r3)
|
||||
err2; std r11,40(r3)
|
||||
err2; std r12,48(r3)
|
||||
err2; std r14,56(r3)
|
||||
addi r3,r3,64
|
||||
subi r7,r7,64
|
||||
|
||||
7: ld r14,STK_REG(R14)(r1)
|
||||
ld r15,STK_REG(R15)(r1)
|
||||
ld r16,STK_REG(R16)(r1)
|
||||
ld r17,STK_REG(R17)(r1)
|
||||
ld r18,STK_REG(R18)(r1)
|
||||
ld r19,STK_REG(R19)(r1)
|
||||
ld r20,STK_REG(R20)(r1)
|
||||
ld r21,STK_REG(R21)(r1)
|
||||
ld r22,STK_REG(R22)(r1)
|
||||
addi r1,r1,STACKFRAMESIZE
|
||||
|
||||
/* Up to 63B to go */
|
||||
bf cr7*4+2,8f
|
||||
err1; ld r0,0(r4)
|
||||
err1; ld r6,8(r4)
|
||||
err1; ld r8,16(r4)
|
||||
err1; ld r9,24(r4)
|
||||
addi r4,r4,32
|
||||
err1; std r0,0(r3)
|
||||
err1; std r6,8(r3)
|
||||
err1; std r8,16(r3)
|
||||
err1; std r9,24(r3)
|
||||
addi r3,r3,32
|
||||
subi r7,r7,32
|
||||
|
||||
/* Up to 31B to go */
|
||||
8: bf cr7*4+3,9f
|
||||
err1; ld r0,0(r4)
|
||||
err1; ld r6,8(r4)
|
||||
addi r4,r4,16
|
||||
err1; std r0,0(r3)
|
||||
err1; std r6,8(r3)
|
||||
addi r3,r3,16
|
||||
subi r7,r7,16
|
||||
|
||||
9: clrldi r5,r5,(64-4)
|
||||
|
||||
/* Up to 15B to go */
|
||||
.Lshort_copy:
|
||||
mtocrf 0x01,r5
|
||||
bf cr7*4+0,12f
|
||||
err1; lwz r0,0(r4) /* Less chance of a reject with word ops */
|
||||
err1; lwz r6,4(r4)
|
||||
addi r4,r4,8
|
||||
err1; stw r0,0(r3)
|
||||
err1; stw r6,4(r3)
|
||||
addi r3,r3,8
|
||||
subi r7,r7,8
|
||||
|
||||
12: bf cr7*4+1,13f
|
||||
err1; lwz r0,0(r4)
|
||||
addi r4,r4,4
|
||||
err1; stw r0,0(r3)
|
||||
addi r3,r3,4
|
||||
subi r7,r7,4
|
||||
|
||||
13: bf cr7*4+2,14f
|
||||
err1; lhz r0,0(r4)
|
||||
addi r4,r4,2
|
||||
err1; sth r0,0(r3)
|
||||
addi r3,r3,2
|
||||
subi r7,r7,2
|
||||
|
||||
14: bf cr7*4+3,15f
|
||||
err1; lbz r0,0(r4)
|
||||
err1; stb r0,0(r3)
|
||||
|
||||
15: li r3,0
|
||||
blr
|
||||
|
||||
EXPORT_SYMBOL_GPL(memcpy_mcsafe);
|
||||
Loading…
Reference in New Issue