linux-sg2042/arch/x86/lib/copy_user_64.S

355 lines
7.2 KiB
ArmAsm

/* Copyright 2002 Andi Kleen, SuSE Labs.
* Subject to the GNU Public License v2.
*
* Functions to copy from and to user space.
*/
#include <linux/linkage.h>
#include <asm/dwarf2.h>
#define FIX_ALIGNMENT 1
#include <asm/current.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
#include <asm/cpufeature.h>
.macro ALTERNATIVE_JUMP feature,orig,alt
0:
.byte 0xe9 /* 32bit jump */
.long \orig-1f /* by default jump to orig */
1:
.section .altinstr_replacement,"ax"
2: .byte 0xe9 /* near jump with 32bit immediate */
.long \alt-1b /* offset */ /* or alternatively to alt */
.previous
.section .altinstructions,"a"
.align 8
.quad 0b
.quad 2b
.byte \feature /* when feature is set */
.byte 5
.byte 5
.previous
.endm
/* Standard copy_to_user with segment limit checking */
ENTRY(copy_to_user)
CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rdi,%rcx
addq %rdx,%rcx
jc bad_to_user
cmpq threadinfo_addr_limit(%rax),%rcx
jae bad_to_user
xorl %eax,%eax /* clear zero flag */
ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
CFI_ENDPROC
ENTRY(copy_user_generic)
CFI_STARTPROC
movl $1,%ecx /* set zero flag */
ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
CFI_ENDPROC
ENTRY(__copy_from_user_inatomic)
CFI_STARTPROC
xorl %ecx,%ecx /* clear zero flag */
ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
CFI_ENDPROC
/* Standard copy_from_user with segment limit checking */
ENTRY(copy_from_user)
CFI_STARTPROC
GET_THREAD_INFO(%rax)
movq %rsi,%rcx
addq %rdx,%rcx
jc bad_from_user
cmpq threadinfo_addr_limit(%rax),%rcx
jae bad_from_user
movl $1,%ecx /* set zero flag */
ALTERNATIVE_JUMP X86_FEATURE_REP_GOOD,copy_user_generic_unrolled,copy_user_generic_string
CFI_ENDPROC
ENDPROC(copy_from_user)
.section .fixup,"ax"
/* must zero dest */
bad_from_user:
CFI_STARTPROC
movl %edx,%ecx
xorl %eax,%eax
rep
stosb
bad_to_user:
movl %edx,%eax
ret
CFI_ENDPROC
END(bad_from_user)
.previous
/*
* copy_user_generic_unrolled - memory copy with exception handling.
* This version is for CPUs like P4 that don't have efficient micro code for rep movsq
*
* Input:
* rdi destination
* rsi source
* rdx count
* ecx zero flag -- if true zero destination on error
*
* Output:
* eax uncopied bytes or 0 if successful.
*/
ENTRY(copy_user_generic_unrolled)
CFI_STARTPROC
pushq %rbx
CFI_ADJUST_CFA_OFFSET 8
CFI_REL_OFFSET rbx, 0
pushq %rcx
CFI_ADJUST_CFA_OFFSET 8
CFI_REL_OFFSET rcx, 0
xorl %eax,%eax /*zero for the exception handler */
#ifdef FIX_ALIGNMENT
/* check for bad alignment of destination */
movl %edi,%ecx
andl $7,%ecx
jnz .Lbad_alignment
.Lafter_bad_alignment:
#endif
movq %rdx,%rcx
movl $64,%ebx
shrq $6,%rdx
decq %rdx
js .Lhandle_tail
.p2align 4
.Lloop:
.Ls1: movq (%rsi),%r11
.Ls2: movq 1*8(%rsi),%r8
.Ls3: movq 2*8(%rsi),%r9
.Ls4: movq 3*8(%rsi),%r10
.Ld1: movq %r11,(%rdi)
.Ld2: movq %r8,1*8(%rdi)
.Ld3: movq %r9,2*8(%rdi)
.Ld4: movq %r10,3*8(%rdi)
.Ls5: movq 4*8(%rsi),%r11
.Ls6: movq 5*8(%rsi),%r8
.Ls7: movq 6*8(%rsi),%r9
.Ls8: movq 7*8(%rsi),%r10
.Ld5: movq %r11,4*8(%rdi)
.Ld6: movq %r8,5*8(%rdi)
.Ld7: movq %r9,6*8(%rdi)
.Ld8: movq %r10,7*8(%rdi)
decq %rdx
leaq 64(%rsi),%rsi
leaq 64(%rdi),%rdi
jns .Lloop
.p2align 4
.Lhandle_tail:
movl %ecx,%edx
andl $63,%ecx
shrl $3,%ecx
jz .Lhandle_7
movl $8,%ebx
.p2align 4
.Lloop_8:
.Ls9: movq (%rsi),%r8
.Ld9: movq %r8,(%rdi)
decl %ecx
leaq 8(%rdi),%rdi
leaq 8(%rsi),%rsi
jnz .Lloop_8
.Lhandle_7:
movl %edx,%ecx
andl $7,%ecx
jz .Lende
.p2align 4
.Lloop_1:
.Ls10: movb (%rsi),%bl
.Ld10: movb %bl,(%rdi)
incq %rdi
incq %rsi
decl %ecx
jnz .Lloop_1
CFI_REMEMBER_STATE
.Lende:
popq %rcx
CFI_ADJUST_CFA_OFFSET -8
CFI_RESTORE rcx
popq %rbx
CFI_ADJUST_CFA_OFFSET -8
CFI_RESTORE rbx
ret
CFI_RESTORE_STATE
#ifdef FIX_ALIGNMENT
/* align destination */
.p2align 4
.Lbad_alignment:
movl $8,%r9d
subl %ecx,%r9d
movl %r9d,%ecx
cmpq %r9,%rdx
jz .Lhandle_7
js .Lhandle_7
.Lalign_1:
.Ls11: movb (%rsi),%bl
.Ld11: movb %bl,(%rdi)
incq %rsi
incq %rdi
decl %ecx
jnz .Lalign_1
subq %r9,%rdx
jmp .Lafter_bad_alignment
#endif
/* table sorted by exception address */
.section __ex_table,"a"
.align 8
.quad .Ls1,.Ls1e
.quad .Ls2,.Ls2e
.quad .Ls3,.Ls3e
.quad .Ls4,.Ls4e
.quad .Ld1,.Ls1e
.quad .Ld2,.Ls2e
.quad .Ld3,.Ls3e
.quad .Ld4,.Ls4e
.quad .Ls5,.Ls5e
.quad .Ls6,.Ls6e
.quad .Ls7,.Ls7e
.quad .Ls8,.Ls8e
.quad .Ld5,.Ls5e
.quad .Ld6,.Ls6e
.quad .Ld7,.Ls7e
.quad .Ld8,.Ls8e
.quad .Ls9,.Le_quad
.quad .Ld9,.Le_quad
.quad .Ls10,.Le_byte
.quad .Ld10,.Le_byte
#ifdef FIX_ALIGNMENT
.quad .Ls11,.Lzero_rest
.quad .Ld11,.Lzero_rest
#endif
.quad .Le5,.Le_zero
.previous
/* compute 64-offset for main loop. 8 bytes accuracy with error on the
pessimistic side. this is gross. it would be better to fix the
interface. */
/* eax: zero, ebx: 64 */
.Ls1e: addl $8,%eax
.Ls2e: addl $8,%eax
.Ls3e: addl $8,%eax
.Ls4e: addl $8,%eax
.Ls5e: addl $8,%eax
.Ls6e: addl $8,%eax
.Ls7e: addl $8,%eax
.Ls8e: addl $8,%eax
addq %rbx,%rdi /* +64 */
subq %rax,%rdi /* correct destination with computed offset */
shlq $6,%rdx /* loop counter * 64 (stride length) */
addq %rax,%rdx /* add offset to loopcnt */
andl $63,%ecx /* remaining bytes */
addq %rcx,%rdx /* add them */
jmp .Lzero_rest
/* exception on quad word loop in tail handling */
/* ecx: loopcnt/8, %edx: length, rdi: correct */
.Le_quad:
shll $3,%ecx
andl $7,%edx
addl %ecx,%edx
/* edx: bytes to zero, rdi: dest, eax:zero */
.Lzero_rest:
cmpl $0,(%rsp)
jz .Le_zero
movq %rdx,%rcx
.Le_byte:
xorl %eax,%eax
.Le5: rep
stosb
/* when there is another exception while zeroing the rest just return */
.Le_zero:
movq %rdx,%rax
jmp .Lende
CFI_ENDPROC
ENDPROC(copy_user_generic)
/* Some CPUs run faster using the string copy instructions.
This is also a lot simpler. Use them when possible.
Patch in jmps to this code instead of copying it fully
to avoid unwanted aliasing in the exception tables. */
/* rdi destination
* rsi source
* rdx count
* ecx zero flag
*
* Output:
* eax uncopied bytes or 0 if successfull.
*
* Only 4GB of copy is supported. This shouldn't be a problem
* because the kernel normally only writes from/to page sized chunks
* even if user space passed a longer buffer.
* And more would be dangerous because both Intel and AMD have
* errata with rep movsq > 4GB. If someone feels the need to fix
* this please consider this.
*/
ENTRY(copy_user_generic_string)
CFI_STARTPROC
movl %ecx,%r8d /* save zero flag */
movl %edx,%ecx
shrl $3,%ecx
andl $7,%edx
jz 10f
1: rep
movsq
movl %edx,%ecx
2: rep
movsb
9: movl %ecx,%eax
ret
/* multiple of 8 byte */
10: rep
movsq
xor %eax,%eax
ret
/* exception handling */
3: lea (%rdx,%rcx,8),%rax /* exception on quad loop */
jmp 6f
5: movl %ecx,%eax /* exception on byte loop */
/* eax: left over bytes */
6: testl %r8d,%r8d /* zero flag set? */
jz 7f
movl %eax,%ecx /* initialize x86 loop counter */
push %rax
xorl %eax,%eax
8: rep
stosb /* zero the rest */
11: pop %rax
7: ret
CFI_ENDPROC
END(copy_user_generic_c)
.section __ex_table,"a"
.quad 1b,3b
.quad 2b,5b
.quad 8b,11b
.quad 10b,3b
.previous