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

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86: Include probe_roms.h in probe_roms.c
  x86/32: Print control and debug registers for kerenel context
  x86: Tighten dependencies of CPU_SUP_*_32
  x86/numa: Improve internode cache alignment
  x86: Fix the NMI nesting comments
  x86-64: Improve insn scheduling in SAVE_ARGS_IRQ
  x86-64: Fix CFI annotations for NMI nesting code
  bitops: Add missing parentheses to new get_order macro
  bitops: Optimise get_order()
  bitops: Adjust the comment on get_order() to describe the size==0 case
  x86/spinlocks: Eliminate TICKET_MASK
  x86-64: Handle byte-wise tail copying in memcpy() without a loop
  x86-64: Fix memcpy() to support sizes of 4Gb and above
  x86-64: Fix memset() to support sizes of 4Gb and above
  x86-64: Slightly shorten copy_page()

arch/x86/kernel/dumpstack_32.c

@@ -87,7 +87,7 @@ void show_registers(struct pt_regs *regs)
 	int i;
 
 	print_modules();
-	__show_regs(regs, 0);
+	__show_regs(regs, !user_mode_vm(regs));
 
 	printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n",
 		TASK_COMM_LEN, current->comm, task_pid_nr(current),

arch/x86/kernel/entry_64.S

@@ -320,7 +320,7 @@ ENDPROC(native_usergs_sysret64)
 	movq %rsp, %rsi
 
 	leaq -RBP(%rsp),%rdi	/* arg1 for handler */
-	testl $3, CS(%rdi)
+	testl $3, CS-RBP(%rsi)
 	je 1f
 	SWAPGS
 	/*
@@ -330,11 +330,10 @@ ENDPROC(native_usergs_sysret64)
 	 * moving irq_enter into assembly, which would be too much work)
 	 */
 1:	incl PER_CPU_VAR(irq_count)
-	jne 2f
-	mov PER_CPU_VAR(irq_stack_ptr),%rsp
+	cmovzq PER_CPU_VAR(irq_stack_ptr),%rsp
 	CFI_DEF_CFA_REGISTER	rsi
 
-2:	/* Store previous stack value */
+	/* Store previous stack value */
 	pushq %rsi
 	CFI_ESCAPE	0x0f /* DW_CFA_def_cfa_expression */, 6, \
 			0x77 /* DW_OP_breg7 */, 0, \
@@ -1530,6 +1529,7 @@ ENTRY(nmi)
 
 	/* Use %rdx as out temp variable throughout */
 	pushq_cfi %rdx
+	CFI_REL_OFFSET rdx, 0
 
 	/*
 	 * If %cs was not the kernel segment, then the NMI triggered in user
@@ -1554,6 +1554,7 @@ ENTRY(nmi)
 	 */
 	lea 6*8(%rsp), %rdx
 	test_in_nmi rdx, 4*8(%rsp), nested_nmi, first_nmi
+	CFI_REMEMBER_STATE
 
 nested_nmi:
 	/*
@@ -1585,10 +1586,12 @@ nested_nmi:
 
 nested_nmi_out:
 	popq_cfi %rdx
+	CFI_RESTORE rdx
 
 	/* No need to check faults here */
 	INTERRUPT_RETURN
 
+	CFI_RESTORE_STATE
 first_nmi:
 	/*
 	 * Because nested NMIs will use the pushed location that we
@@ -1620,10 +1623,15 @@ first_nmi:
 	 * | pt_regs                 |
 	 * +-------------------------+
 	 *
-	 * The saved RIP is used to fix up the copied RIP that a nested
-	 * NMI may zero out. The original stack frame and the temp storage
+	 * The saved stack frame is used to fix up the copied stack frame
+	 * that a nested NMI may change to make the interrupted NMI iret jump
+	 * to the repeat_nmi. The original stack frame and the temp storage
 	 * is also used by nested NMIs and can not be trusted on exit.
 	 */
+	/* Do not pop rdx, nested NMIs will corrupt that part of the stack */
+	movq (%rsp), %rdx
+	CFI_RESTORE rdx
+
 	/* Set the NMI executing variable on the stack. */
 	pushq_cfi $1
 
@@ -1631,22 +1639,39 @@ first_nmi:
 	.rept 5
 	pushq_cfi 6*8(%rsp)
 	.endr
+	CFI_DEF_CFA_OFFSET SS+8-RIP
+
+	/* Everything up to here is safe from nested NMIs */
+
+	/*
+	 * If there was a nested NMI, the first NMI's iret will return
+	 * here. But NMIs are still enabled and we can take another
+	 * nested NMI. The nested NMI checks the interrupted RIP to see
+	 * if it is between repeat_nmi and end_repeat_nmi, and if so
+	 * it will just return, as we are about to repeat an NMI anyway.
+	 * This makes it safe to copy to the stack frame that a nested
+	 * NMI will update.
+	 */
+repeat_nmi:
+	/*
+	 * Update the stack variable to say we are still in NMI (the update
+	 * is benign for the non-repeat case, where 1 was pushed just above
+	 * to this very stack slot).
+	 */
+	movq $1, 5*8(%rsp)
 
 	/* Make another copy, this one may be modified by nested NMIs */
 	.rept 5
 	pushq_cfi 4*8(%rsp)
 	.endr
-
-	/* Do not pop rdx, nested NMIs will corrupt it */
-	movq 11*8(%rsp), %rdx
+	CFI_DEF_CFA_OFFSET SS+8-RIP
+end_repeat_nmi:
 
 	/*
 	 * Everything below this point can be preempted by a nested
-	 * NMI if the first NMI took an exception. Repeated NMIs
-	 * caused by an exception and nested NMI will start here, and
-	 * can still be preempted by another NMI.
+	 * NMI if the first NMI took an exception and reset our iret stack
+	 * so that we repeat another NMI.
 	 */
-restart_nmi:
 	pushq_cfi $-1		/* ORIG_RAX: no syscall to restart */
 	subq $ORIG_RAX-R15, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15
@@ -1675,26 +1700,6 @@ nmi_restore:
 	CFI_ENDPROC
 END(nmi)
 
-	/*
-	 * If an NMI hit an iret because of an exception or breakpoint,
-	 * it can lose its NMI context, and a nested NMI may come in.
-	 * In that case, the nested NMI will change the preempted NMI's
-	 * stack to jump to here when it does the final iret.
-	 */
-repeat_nmi:
-	INTR_FRAME
-	/* Update the stack variable to say we are still in NMI */
-	movq $1, 5*8(%rsp)
-
-	/* copy the saved stack back to copy stack */
-	.rept 5
-	pushq_cfi 4*8(%rsp)
-	.endr
-
-	jmp restart_nmi
-	CFI_ENDPROC
-end_repeat_nmi:
-
 ENTRY(ignore_sysret)
 	CFI_STARTPROC
 	mov $-ENOSYS,%eax

arch/x86/kernel/probe_roms.c

@@ -12,6 +12,7 @@
 #include <linux/pci.h>
 #include <linux/export.h>
 
+#include <asm/probe_roms.h>
 #include <asm/pci-direct.h>
 #include <asm/e820.h>
 #include <asm/mmzone.h>