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

3 files changed, 95 insertions, 75 deletions

diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 19f16ebaf4fa..54d80fddb739 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -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);
 }
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 2a3806b95831..31b46128a63d 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -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)
diff --git a/arch/x86/lib/copy_page_64.S b/arch/x86/lib/copy_page_64.S
index 6b34d04d096a..176cca67212b 100644
--- a/arch/x86/lib/copy_page_64.S
+++ b/arch/x86/lib/copy_page_64.S
@@ -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
-
-        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     %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
-
+        decl    %ecx
+
+        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, 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"