Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm changes from Ingo Molnar:
 "Two fixlets and a cleanup."

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86_32: Return actual stack when requesting sp from regs
  x86: Don't clobber top of pt_regs in nested NMI
  x86/asm: Clean up copy_page_*() comments and code
This commit is contained in:
Linus Torvalds 2012-12-11 19:55:20 -08:00
commit 0019fab355
3 changed files with 92 additions and 72 deletions

View File

@ -239,6 +239,15 @@ static inline unsigned long regs_get_register(struct pt_regs *regs,
{
if (unlikely(offset > MAX_REG_OFFSET))
return 0;
#ifdef CONFIG_X86_32
/*
* Traps from the kernel do not save sp and ss.
* Use the helper function to retrieve sp.
*/
if (offset == offsetof(struct pt_regs, sp) &&
regs->cs == __KERNEL_CS)
return kernel_stack_pointer(regs);
#endif
return *(unsigned long *)((unsigned long)regs + offset);
}

View File

@ -1699,9 +1699,10 @@ nested_nmi:
1:
/* Set up the interrupted NMIs stack to jump to repeat_nmi */
leaq -6*8(%rsp), %rdx
leaq -1*8(%rsp), %rdx
movq %rdx, %rsp
CFI_ADJUST_CFA_OFFSET 6*8
CFI_ADJUST_CFA_OFFSET 1*8
leaq -10*8(%rsp), %rdx
pushq_cfi $__KERNEL_DS
pushq_cfi %rdx
pushfq_cfi
@ -1709,8 +1710,8 @@ nested_nmi:
pushq_cfi $repeat_nmi
/* Put stack back */
addq $(11*8), %rsp
CFI_ADJUST_CFA_OFFSET -11*8
addq $(6*8), %rsp
CFI_ADJUST_CFA_OFFSET -6*8
nested_nmi_out:
popq_cfi %rdx
@ -1736,18 +1737,18 @@ first_nmi:
* +-------------------------+
* | NMI executing variable |
* +-------------------------+
* | Saved SS |
* | Saved Return RSP |
* | Saved RFLAGS |
* | Saved CS |
* | Saved RIP |
* +-------------------------+
* | copied SS |
* | copied Return RSP |
* | copied RFLAGS |
* | copied CS |
* | copied RIP |
* +-------------------------+
* | Saved SS |
* | Saved Return RSP |
* | Saved RFLAGS |
* | Saved CS |
* | Saved RIP |
* +-------------------------+
* | pt_regs |
* +-------------------------+
*
@ -1763,9 +1764,14 @@ first_nmi:
/* Set the NMI executing variable on the stack. */
pushq_cfi $1
/*
* Leave room for the "copied" frame
*/
subq $(5*8), %rsp
/* Copy the stack frame to the Saved frame */
.rept 5
pushq_cfi 6*8(%rsp)
pushq_cfi 11*8(%rsp)
.endr
CFI_DEF_CFA_OFFSET SS+8-RIP
@ -1786,12 +1792,15 @@ repeat_nmi:
* is benign for the non-repeat case, where 1 was pushed just above
* to this very stack slot).
*/
movq $1, 5*8(%rsp)
movq $1, 10*8(%rsp)
/* Make another copy, this one may be modified by nested NMIs */
addq $(10*8), %rsp
CFI_ADJUST_CFA_OFFSET -10*8
.rept 5
pushq_cfi 4*8(%rsp)
pushq_cfi -6*8(%rsp)
.endr
subq $(5*8), %rsp
CFI_DEF_CFA_OFFSET SS+8-RIP
end_repeat_nmi:
@ -1842,8 +1851,12 @@ nmi_swapgs:
SWAPGS_UNSAFE_STACK
nmi_restore:
RESTORE_ALL 8
/* Pop the extra iret frame */
addq $(5*8), %rsp
/* Clear the NMI executing stack variable */
movq $0, 10*8(%rsp)
movq $0, 5*8(%rsp)
jmp irq_return
CFI_ENDPROC
END(nmi)

View File

@ -5,91 +5,89 @@
#include <asm/alternative-asm.h>
ALIGN
copy_page_c:
copy_page_rep:
CFI_STARTPROC
movl $4096/8,%ecx
rep movsq
movl $4096/8, %ecx
rep movsq
ret
CFI_ENDPROC
ENDPROC(copy_page_c)
ENDPROC(copy_page_rep)
/* Don't use streaming store because it's better when the target
ends up in cache. */
/* Could vary the prefetch distance based on SMP/UP */
/*
* Don't use streaming copy unless the CPU indicates X86_FEATURE_REP_GOOD.
* Could vary the prefetch distance based on SMP/UP.
*/
ENTRY(copy_page)
CFI_STARTPROC
subq $2*8,%rsp
subq $2*8, %rsp
CFI_ADJUST_CFA_OFFSET 2*8
movq %rbx,(%rsp)
movq %rbx, (%rsp)
CFI_REL_OFFSET rbx, 0
movq %r12,1*8(%rsp)
movq %r12, 1*8(%rsp)
CFI_REL_OFFSET r12, 1*8
movl $(4096/64)-5,%ecx
movl $(4096/64)-5, %ecx
.p2align 4
.Loop64:
dec %rcx
movq (%rsi), %rax
movq 8 (%rsi), %rbx
movq 16 (%rsi), %rdx
movq 24 (%rsi), %r8
movq 32 (%rsi), %r9
movq 40 (%rsi), %r10
movq 48 (%rsi), %r11
movq 56 (%rsi), %r12
dec %rcx
movq 0x8*0(%rsi), %rax
movq 0x8*1(%rsi), %rbx
movq 0x8*2(%rsi), %rdx
movq 0x8*3(%rsi), %r8
movq 0x8*4(%rsi), %r9
movq 0x8*5(%rsi), %r10
movq 0x8*6(%rsi), %r11
movq 0x8*7(%rsi), %r12
prefetcht0 5*64(%rsi)
movq %rax, (%rdi)
movq %rbx, 8 (%rdi)
movq %rdx, 16 (%rdi)
movq %r8, 24 (%rdi)
movq %r9, 32 (%rdi)
movq %r10, 40 (%rdi)
movq %r11, 48 (%rdi)
movq %r12, 56 (%rdi)
movq %rax, 0x8*0(%rdi)
movq %rbx, 0x8*1(%rdi)
movq %rdx, 0x8*2(%rdi)
movq %r8, 0x8*3(%rdi)
movq %r9, 0x8*4(%rdi)
movq %r10, 0x8*5(%rdi)
movq %r11, 0x8*6(%rdi)
movq %r12, 0x8*7(%rdi)
leaq 64 (%rsi), %rsi
leaq 64 (%rdi), %rdi
leaq 64 (%rsi), %rsi
leaq 64 (%rdi), %rdi
jnz .Loop64
jnz .Loop64
movl $5,%ecx
movl $5, %ecx
.p2align 4
.Loop2:
decl %ecx
decl %ecx
movq (%rsi), %rax
movq 8 (%rsi), %rbx
movq 16 (%rsi), %rdx
movq 24 (%rsi), %r8
movq 32 (%rsi), %r9
movq 40 (%rsi), %r10
movq 48 (%rsi), %r11
movq 56 (%rsi), %r12
movq 0x8*0(%rsi), %rax
movq 0x8*1(%rsi), %rbx
movq 0x8*2(%rsi), %rdx
movq 0x8*3(%rsi), %r8
movq 0x8*4(%rsi), %r9
movq 0x8*5(%rsi), %r10
movq 0x8*6(%rsi), %r11
movq 0x8*7(%rsi), %r12
movq %rax, (%rdi)
movq %rbx, 8 (%rdi)
movq %rdx, 16 (%rdi)
movq %r8, 24 (%rdi)
movq %r9, 32 (%rdi)
movq %r10, 40 (%rdi)
movq %r11, 48 (%rdi)
movq %r12, 56 (%rdi)
leaq 64(%rdi),%rdi
leaq 64(%rsi),%rsi
movq %rax, 0x8*0(%rdi)
movq %rbx, 0x8*1(%rdi)
movq %rdx, 0x8*2(%rdi)
movq %r8, 0x8*3(%rdi)
movq %r9, 0x8*4(%rdi)
movq %r10, 0x8*5(%rdi)
movq %r11, 0x8*6(%rdi)
movq %r12, 0x8*7(%rdi)
leaq 64(%rdi), %rdi
leaq 64(%rsi), %rsi
jnz .Loop2
movq (%rsp),%rbx
movq (%rsp), %rbx
CFI_RESTORE rbx
movq 1*8(%rsp),%r12
movq 1*8(%rsp), %r12
CFI_RESTORE r12
addq $2*8,%rsp
addq $2*8, %rsp
CFI_ADJUST_CFA_OFFSET -2*8
ret
.Lcopy_page_end:
@ -103,7 +101,7 @@ ENDPROC(copy_page)
.section .altinstr_replacement,"ax"
1: .byte 0xeb /* jmp <disp8> */
.byte (copy_page_c - copy_page) - (2f - 1b) /* offset */
.byte (copy_page_rep - copy_page) - (2f - 1b) /* offset */
2:
.previous
.section .altinstructions,"a"