[PATCH] x86_64: Clean up copy_*_user
- Remove optimization for old B stepping Opteron - Make the fast path for copies with a multiple of eight length faster. - Minor instruction rearrangement to hopefully avoid a pipeline stall or two. - Add comment about errata to consider. Signed-off-by: Andi Kleen <ak@suse.de> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This commit is contained in:
Andi Kleen
Linus Torvalds
parent
17a941d854
commit
2cbc9ee35c
|
|
@ -4,12 +4,9 @@
|
|||
* Functions to copy from and to user space.
|
||||
*/
|
||||
|
||||
#define FIX_ALIGNMENT 1
|
||||
|
||||
#include <asm/current.h>
|
||||
#include <asm/asm-offsets.h>
|
||||
#include <asm/thread_info.h>
|
||||
#include <asm/cpufeature.h>
|
||||
|
||||
/* Standard copy_to_user with segment limit checking */
|
||||
.globl copy_to_user
|
||||
|
|
@ -21,23 +18,7 @@ copy_to_user:
|
|||
jc bad_to_user
|
||||
cmpq threadinfo_addr_limit(%rax),%rcx
|
||||
jae bad_to_user
|
||||
2:
|
||||
.byte 0xe9 /* 32bit jump */
|
||||
.long .Lcug-1f
|
||||
1:
|
||||
|
||||
.section .altinstr_replacement,"ax"
|
||||
3: .byte 0xe9 /* replacement jmp with 8 bit immediate */
|
||||
.long copy_user_generic_c-1b /* offset */
|
||||
.previous
|
||||
.section .altinstructions,"a"
|
||||
.align 8
|
||||
.quad 2b
|
||||
.quad 3b
|
||||
.byte X86_FEATURE_K8_C
|
||||
.byte 5
|
||||
.byte 5
|
||||
.previous
|
||||
jmp copy_user_generic
|
||||
|
||||
/* Standard copy_from_user with segment limit checking */
|
||||
.globl copy_from_user
|
||||
|
|
@ -72,223 +53,44 @@ bad_to_user:
|
|||
* rsi source
|
||||
* rdx count
|
||||
*
|
||||
* 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.
|
||||
*
|
||||
* Output:
|
||||
* eax uncopied bytes or 0 if successful.
|
||||
*/
|
||||
.globl copy_user_generic
|
||||
.p2align 4
|
||||
copy_user_generic:
|
||||
.byte 0x66,0x66,0x90 /* 5 byte nop for replacement jump */
|
||||
.byte 0x66,0x90
|
||||
1:
|
||||
.section .altinstr_replacement,"ax"
|
||||
2: .byte 0xe9 /* near jump with 32bit immediate */
|
||||
.long copy_user_generic_c-1b /* offset */
|
||||
.previous
|
||||
.section .altinstructions,"a"
|
||||
.align 8
|
||||
.quad copy_user_generic
|
||||
.quad 2b
|
||||
.byte X86_FEATURE_K8_C
|
||||
.byte 5
|
||||
.byte 5
|
||||
.previous
|
||||
.Lcug:
|
||||
pushq %rbx
|
||||
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
|
||||
|
||||
.Lende:
|
||||
popq %rbx
|
||||
ret
|
||||
|
||||
#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:
|
||||
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
|
||||
|
||||
/* C stepping K8 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
|
||||
*
|
||||
* Output:
|
||||
* eax uncopied bytes or 0 if successfull.
|
||||
*/
|
||||
copy_user_generic_c:
|
||||
.globl copy_user_generic
|
||||
copy_user_generic:
|
||||
movl %edx,%ecx
|
||||
shrl $3,%ecx
|
||||
andl $7,%edx
|
||||
jz 5f
|
||||
1: rep
|
||||
movsq
|
||||
movl %edx,%ecx
|
||||
xor %eax,%eax
|
||||
2: rep
|
||||
movsb
|
||||
4: movl %ecx,%eax
|
||||
ret
|
||||
/* align here? */
|
||||
5: xorl %eax,%eax
|
||||
6: rep movsq
|
||||
ret
|
||||
|
||||
.section .fixup,"ax"
|
||||
3: lea (%rdx,%rcx,8),%rax
|
||||
ret
|
||||
|
||||
4: movl %ecx,%eax
|
||||
ret
|
||||
.previous
|
||||
|
||||
.section __ex_table,"a"
|
||||
.quad 1b,3b
|
||||
.quad 2b,4b
|
||||
.quad 6b,4b
|
||||
.previous
|
||||
|
|
|
|||
Loading…
Reference in New Issue