Merge branch 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6

* 'for-linus' of git://one.firstfloor.org/home/andi/git/linux-2.6: (156 commits)
  [PATCH] x86-64: Export smp_call_function_single
  [PATCH] i386: Clean up smp_tune_scheduling()
  [PATCH] unwinder: move .eh_frame to RODATA
  [PATCH] unwinder: fully support linker generated .eh_frame_hdr section
  [PATCH] x86-64: don't use set_irq_regs()
  [PATCH] x86-64: check vector in setup_ioapic_dest to verify if need setup_IO_APIC_irq
  [PATCH] x86-64: Make ix86 default to HIGHMEM4G instead of NOHIGHMEM
  [PATCH] i386: replace kmalloc+memset with kzalloc
  [PATCH] x86-64: remove remaining pc98 code
  [PATCH] x86-64: remove unused variable
  [PATCH] x86-64: Fix constraints in atomic_add_return()
  [PATCH] x86-64: fix asm constraints in i386 atomic_add_return
  [PATCH] x86-64: Correct documentation for bzImage protocol v2.05
  [PATCH] x86-64: replace kmalloc+memset with kzalloc in MTRR code
  [PATCH] x86-64: Fix numaq build error
  [PATCH] x86-64: include/asm-x86_64/cpufeature.h isn't a userspace header
  [PATCH] unwinder: Add debugging output to the Dwarf2 unwinder
  [PATCH] x86-64: Clarify error message in GART code
  [PATCH] x86-64: Fix interrupt race in idle callback (3rd try)
  [PATCH] x86-64: Remove unwind stack pointer alignment forcing again
  ...

Fixed conflict in include/linux/uaccess.h manually

Signed-off-by: Linus Torvalds <torvalds@osdl.org>

1 files changed, 184 insertions, 147 deletions

diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 5a63d6fdb70..de34b7fed3c 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -30,12 +30,13 @@
  *	18(%esp) - %eax
  *	1C(%esp) - %ds
  *	20(%esp) - %es
- *	24(%esp) - orig_eax
- *	28(%esp) - %eip
- *	2C(%esp) - %cs
- *	30(%esp) - %eflags
- *	34(%esp) - %oldesp
- *	38(%esp) - %oldss
+ *	24(%esp) - %gs
+ *	28(%esp) - orig_eax
+ *	2C(%esp) - %eip
+ *	30(%esp) - %cs
+ *	34(%esp) - %eflags
+ *	38(%esp) - %oldesp
+ *	3C(%esp) - %oldss
  *
  * "current" is in register %ebx during any slow entries.
  */
@@ -48,26 +49,24 @@
 #include <asm/smp.h>
 #include <asm/page.h>
 #include <asm/desc.h>
+#include <asm/percpu.h>
 #include <asm/dwarf2.h>
 #include "irq_vectors.h"
 
-#define nr_syscalls ((syscall_table_size)/4)
+/*
+ * We use macros for low-level operations which need to be overridden
+ * for paravirtualization.  The following will never clobber any registers:
+ *   INTERRUPT_RETURN (aka. "iret")
+ *   GET_CR0_INTO_EAX (aka. "movl %cr0, %eax")
+ *   ENABLE_INTERRUPTS_SYSEXIT (aka "sti; sysexit").
+ *
+ * For DISABLE_INTERRUPTS/ENABLE_INTERRUPTS (aka "cli"/"sti"), you must
+ * specify what registers can be overwritten (CLBR_NONE, CLBR_EAX/EDX/ECX/ANY).
+ * Allowing a register to be clobbered can shrink the paravirt replacement
+ * enough to patch inline, increasing performance.
+ */
 
-EBX		= 0x00
-ECX		= 0x04
-EDX		= 0x08
-ESI		= 0x0C
-EDI		= 0x10
-EBP		= 0x14
-EAX		= 0x18
-DS		= 0x1C
-ES		= 0x20
-ORIG_EAX	= 0x24
-EIP		= 0x28
-CS		= 0x2C
-EFLAGS		= 0x30
-OLDESP		= 0x34
-OLDSS		= 0x38
+#define nr_syscalls ((syscall_table_size)/4)
 
 CF_MASK		= 0x00000001
 TF_MASK		= 0x00000100
@@ -76,23 +75,16 @@ DF_MASK		= 0x00000400
 NT_MASK		= 0x00004000
 VM_MASK		= 0x00020000
 
-/* These are replaces for paravirtualization */
-#define DISABLE_INTERRUPTS		cli
-#define ENABLE_INTERRUPTS		sti
-#define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit
-#define INTERRUPT_RETURN		iret
-#define GET_CR0_INTO_EAX		movl %cr0, %eax
-
 #ifdef CONFIG_PREEMPT
-#define preempt_stop		DISABLE_INTERRUPTS; TRACE_IRQS_OFF
+#define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
 #else
-#define preempt_stop
+#define preempt_stop(clobbers)
 #define resume_kernel		restore_nocheck
 #endif
 
 .macro TRACE_IRQS_IRET
 #ifdef CONFIG_TRACE_IRQFLAGS
-	testl $IF_MASK,EFLAGS(%esp)     # interrupts off?
+	testl $IF_MASK,PT_EFLAGS(%esp)     # interrupts off?
 	jz 1f
 	TRACE_IRQS_ON
 1:
@@ -107,6 +99,9 @@ VM_MASK		= 0x00020000
 
 #define SAVE_ALL \
 	cld; \
+	pushl %gs; \
+	CFI_ADJUST_CFA_OFFSET 4;\
+	/*CFI_REL_OFFSET gs, 0;*/\
 	pushl %es; \
 	CFI_ADJUST_CFA_OFFSET 4;\
 	/*CFI_REL_OFFSET es, 0;*/\
@@ -136,7 +131,9 @@ VM_MASK		= 0x00020000
 	CFI_REL_OFFSET ebx, 0;\
 	movl $(__USER_DS), %edx; \
 	movl %edx, %ds; \
-	movl %edx, %es;
+	movl %edx, %es; \
+	movl $(__KERNEL_PDA), %edx; \
+	movl %edx, %gs
 
 #define RESTORE_INT_REGS \
 	popl %ebx;	\
@@ -169,17 +166,22 @@ VM_MASK		= 0x00020000
 2:	popl %es;	\
 	CFI_ADJUST_CFA_OFFSET -4;\
 	/*CFI_RESTORE es;*/\
-.section .fixup,"ax";	\
-3:	movl $0,(%esp);	\
-	jmp 1b;		\
+3:	popl %gs;	\
+	CFI_ADJUST_CFA_OFFSET -4;\
+	/*CFI_RESTORE gs;*/\
+.pushsection .fixup,"ax";	\
 4:	movl $0,(%esp);	\
+	jmp 1b;		\
+5:	movl $0,(%esp);	\
 	jmp 2b;		\
-.previous;		\
+6:	movl $0,(%esp);	\
+	jmp 3b;		\
 .section __ex_table,"a";\
 	.align 4;	\
-	.long 1b,3b;	\
-	.long 2b,4b;	\
-.previous
+	.long 1b,4b;	\
+	.long 2b,5b;	\
+	.long 3b,6b;	\
+.popsection
 
 #define RING0_INT_FRAME \
 	CFI_STARTPROC simple;\
@@ -198,18 +200,18 @@ VM_MASK		= 0x00020000
 #define RING0_PTREGS_FRAME \
 	CFI_STARTPROC simple;\
 	CFI_SIGNAL_FRAME;\
-	CFI_DEF_CFA esp, OLDESP-EBX;\
-	/*CFI_OFFSET cs, CS-OLDESP;*/\
-	CFI_OFFSET eip, EIP-OLDESP;\
-	/*CFI_OFFSET es, ES-OLDESP;*/\
-	/*CFI_OFFSET ds, DS-OLDESP;*/\
-	CFI_OFFSET eax, EAX-OLDESP;\
-	CFI_OFFSET ebp, EBP-OLDESP;\
-	CFI_OFFSET edi, EDI-OLDESP;\
-	CFI_OFFSET esi, ESI-OLDESP;\
-	CFI_OFFSET edx, EDX-OLDESP;\
-	CFI_OFFSET ecx, ECX-OLDESP;\
-	CFI_OFFSET ebx, EBX-OLDESP
+	CFI_DEF_CFA esp, PT_OLDESP-PT_EBX;\
+	/*CFI_OFFSET cs, PT_CS-PT_OLDESP;*/\
+	CFI_OFFSET eip, PT_EIP-PT_OLDESP;\
+	/*CFI_OFFSET es, PT_ES-PT_OLDESP;*/\
+	/*CFI_OFFSET ds, PT_DS-PT_OLDESP;*/\
+	CFI_OFFSET eax, PT_EAX-PT_OLDESP;\
+	CFI_OFFSET ebp, PT_EBP-PT_OLDESP;\
+	CFI_OFFSET edi, PT_EDI-PT_OLDESP;\
+	CFI_OFFSET esi, PT_ESI-PT_OLDESP;\
+	CFI_OFFSET edx, PT_EDX-PT_OLDESP;\
+	CFI_OFFSET ecx, PT_ECX-PT_OLDESP;\
+	CFI_OFFSET ebx, PT_EBX-PT_OLDESP
 
 ENTRY(ret_from_fork)
 	CFI_STARTPROC
@@ -237,17 +239,18 @@ ENTRY(ret_from_fork)
 	ALIGN
 	RING0_PTREGS_FRAME
 ret_from_exception:
-	preempt_stop
+	preempt_stop(CLBR_ANY)
 ret_from_intr:
 	GET_THREAD_INFO(%ebp)
 check_userspace:
-	movl EFLAGS(%esp), %eax		# mix EFLAGS and CS
-	movb CS(%esp), %al
+	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS and CS
+	movb PT_CS(%esp), %al
 	andl $(VM_MASK | SEGMENT_RPL_MASK), %eax
 	cmpl $USER_RPL, %eax
 	jb resume_kernel		# not returning to v8086 or userspace
+
 ENTRY(resume_userspace)
- 	DISABLE_INTERRUPTS		# make sure we don't miss an interrupt
+ 	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
 					# between sampling and the iret
 	movl TI_flags(%ebp), %ecx
@@ -258,14 +261,14 @@ ENTRY(resume_userspace)
 
 #ifdef CONFIG_PREEMPT
 ENTRY(resume_kernel)
-	DISABLE_INTERRUPTS
+	DISABLE_INTERRUPTS(CLBR_ANY)
 	cmpl $0,TI_preempt_count(%ebp)	# non-zero preempt_count ?
 	jnz restore_nocheck
 need_resched:
 	movl TI_flags(%ebp), %ecx	# need_resched set ?
 	testb $_TIF_NEED_RESCHED, %cl
 	jz restore_all
-	testl $IF_MASK,EFLAGS(%esp)     # interrupts off (exception path) ?
+	testl $IF_MASK,PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz restore_all
 	call preempt_schedule_irq
 	jmp need_resched
@@ -287,7 +290,7 @@ sysenter_past_esp:
 	 * No need to follow this irqs on/off section: the syscall
 	 * disabled irqs and here we enable it straight after entry:
 	 */
-	ENABLE_INTERRUPTS
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushl $(__USER_DS)
 	CFI_ADJUST_CFA_OFFSET 4
 	/*CFI_REL_OFFSET ss, 0*/
@@ -331,20 +334,27 @@ sysenter_past_esp:
 	cmpl $(nr_syscalls), %eax
 	jae syscall_badsys
 	call *sys_call_table(,%eax,4)
-	movl %eax,EAX(%esp)
-	DISABLE_INTERRUPTS
+	movl %eax,PT_EAX(%esp)
+	DISABLE_INTERRUPTS(CLBR_ECX|CLBR_EDX)
 	TRACE_IRQS_OFF
 	movl TI_flags(%ebp), %ecx
 	testw $_TIF_ALLWORK_MASK, %cx
 	jne syscall_exit_work
 /* if something modifies registers it must also disable sysexit */
-	movl EIP(%esp), %edx
-	movl OLDESP(%esp), %ecx
+	movl PT_EIP(%esp), %edx
+	movl PT_OLDESP(%esp), %ecx
 	xorl %ebp,%ebp
 	TRACE_IRQS_ON
+1:	mov  PT_GS(%esp), %gs
 	ENABLE_INTERRUPTS_SYSEXIT
 	CFI_ENDPROC
-
+.pushsection .fixup,"ax"
+2:	movl $0,PT_GS(%esp)
+	jmp 1b
+.section __ex_table,"a"
+	.align 4
+	.long 1b,2b
+.popsection
 
 	# system call handler stub
 ENTRY(system_call)
@@ -353,7 +363,7 @@ ENTRY(system_call)
 	CFI_ADJUST_CFA_OFFSET 4
 	SAVE_ALL
 	GET_THREAD_INFO(%ebp)
-	testl $TF_MASK,EFLAGS(%esp)
+	testl $TF_MASK,PT_EFLAGS(%esp)
 	jz no_singlestep
 	orl $_TIF_SINGLESTEP,TI_flags(%ebp)
 no_singlestep:
@@ -365,9 +375,9 @@ no_singlestep:
 	jae syscall_badsys
 syscall_call:
 	call *sys_call_table(,%eax,4)
-	movl %eax,EAX(%esp)		# store the return value
+	movl %eax,PT_EAX(%esp)		# store the return value
 syscall_exit:
-	DISABLE_INTERRUPTS		# make sure we don't miss an interrupt
+	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
 					# between sampling and the iret
 	TRACE_IRQS_OFF
@@ -376,12 +386,12 @@ syscall_exit:
 	jne syscall_exit_work
 
 restore_all:
-	movl EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
-	# Warning: OLDSS(%esp) contains the wrong/random values if we
+	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
+	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
 	# are returning to the kernel.
 	# See comments in process.c:copy_thread() for details.
-	movb OLDSS(%esp), %ah
-	movb CS(%esp), %al
+	movb PT_OLDSS(%esp), %ah
+	movb PT_CS(%esp), %al
 	andl $(VM_MASK | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
 	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
@@ -390,13 +400,13 @@ restore_nocheck:
 	TRACE_IRQS_IRET
 restore_nocheck_notrace:
 	RESTORE_REGS
-	addl $4, %esp
+	addl $4, %esp			# skip orig_eax/error_code
 	CFI_ADJUST_CFA_OFFSET -4
 1:	INTERRUPT_RETURN
 .section .fixup,"ax"
 iret_exc:
 	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	pushl $0			# no error code
 	pushl $do_iret_error
 	jmp error_code
@@ -408,33 +418,42 @@ iret_exc:
 
 	CFI_RESTORE_STATE
 ldt_ss:
-	larl OLDSS(%esp), %eax
+	larl PT_OLDSS(%esp), %eax
 	jnz restore_nocheck
 	testl $0x00400000, %eax		# returning to 32bit stack?
 	jnz restore_nocheck		# allright, normal return
+
+#ifdef CONFIG_PARAVIRT
+	/*
+	 * The kernel can't run on a non-flat stack if paravirt mode
+	 * is active.  Rather than try to fixup the high bits of
+	 * ESP, bypass this code entirely.  This may break DOSemu
+	 * and/or Wine support in a paravirt VM, although the option
+	 * is still available to implement the setting of the high
+	 * 16-bits in the INTERRUPT_RETURN paravirt-op.
+	 */
+	cmpl $0, paravirt_ops+PARAVIRT_enabled
+	jne restore_nocheck
+#endif
+
 	/* If returning to userspace with 16bit stack,
 	 * try to fix the higher word of ESP, as the CPU
 	 * won't restore it.
 	 * This is an "official" bug of all the x86-compatible
 	 * CPUs, which we can try to work around to make
 	 * dosemu and wine happy. */
-	subl $8, %esp		# reserve space for switch16 pointer
-	CFI_ADJUST_CFA_OFFSET 8
-	DISABLE_INTERRUPTS
+	movl PT_OLDESP(%esp), %eax
+	movl %esp, %edx
+	call patch_espfix_desc
+	pushl $__ESPFIX_SS
+	CFI_ADJUST_CFA_OFFSET 4
+	pushl %eax
+	CFI_ADJUST_CFA_OFFSET 4
+	DISABLE_INTERRUPTS(CLBR_EAX)
 	TRACE_IRQS_OFF
-	movl %esp, %eax
-	/* Set up the 16bit stack frame with switch32 pointer on top,
-	 * and a switch16 pointer on top of the current frame. */
-	call setup_x86_bogus_stack
-	CFI_ADJUST_CFA_OFFSET -8	# frame has moved
-	TRACE_IRQS_IRET
-	RESTORE_REGS
-	lss 20+4(%esp), %esp	# switch to 16bit stack
-1:	INTERRUPT_RETURN
-.section __ex_table,"a"
-	.align 4
-	.long 1b,iret_exc
-.previous
+	lss (%esp), %esp
+	CFI_ADJUST_CFA_OFFSET -8
+	jmp restore_nocheck
 	CFI_ENDPROC
 
 	# perform work that needs to be done immediately before resumption
@@ -445,7 +464,7 @@ work_pending:
 	jz work_notifysig
 work_resched:
 	call schedule
-	DISABLE_INTERRUPTS		# make sure we don't miss an interrupt
+	DISABLE_INTERRUPTS(CLBR_ANY)	# make sure we don't miss an interrupt
 					# setting need_resched or sigpending
 					# between sampling and the iret
 	TRACE_IRQS_OFF
@@ -458,7 +477,8 @@ work_resched:
 
 work_notifysig:				# deal with pending signals and
 					# notify-resume requests
-	testl $VM_MASK, EFLAGS(%esp)
+#ifdef CONFIG_VM86
+	testl $VM_MASK, PT_EFLAGS(%esp)
 	movl %esp, %eax
 	jne work_notifysig_v86		# returning to kernel-space or
 					# vm86-space
@@ -468,29 +488,30 @@ work_notifysig:				# deal with pending signals and
 
 	ALIGN
 work_notifysig_v86:
-#ifdef CONFIG_VM86
 	pushl %ecx			# save ti_flags for do_notify_resume
 	CFI_ADJUST_CFA_OFFSET 4
 	call save_v86_state		# %eax contains pt_regs pointer
 	popl %ecx
 	CFI_ADJUST_CFA_OFFSET -4
 	movl %eax, %esp
+#else
+	movl %esp, %eax
+#endif
 	xorl %edx, %edx
 	call do_notify_resume
 	jmp resume_userspace_sig
-#endif
 
 	# perform syscall exit tracing
 	ALIGN
 syscall_trace_entry:
-	movl $-ENOSYS,EAX(%esp)
+	movl $-ENOSYS,PT_EAX(%esp)
 	movl %esp, %eax
 	xorl %edx,%edx
 	call do_syscall_trace
 	cmpl $0, %eax
 	jne resume_userspace		# ret != 0 -> running under PTRACE_SYSEMU,
 					# so must skip actual syscall
-	movl ORIG_EAX(%esp), %eax
+	movl PT_ORIG_EAX(%esp), %eax
 	cmpl $(nr_syscalls), %eax
 	jnae syscall_call
 	jmp syscall_exit
@@ -501,7 +522,7 @@ syscall_exit_work:
 	testb $(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|_TIF_SINGLESTEP), %cl
 	jz work_pending
 	TRACE_IRQS_ON
-	ENABLE_INTERRUPTS		# could let do_syscall_trace() call
+	ENABLE_INTERRUPTS(CLBR_ANY)	# could let do_syscall_trace() call
 					# schedule() instead
 	movl %esp, %eax
 	movl $1, %edx
@@ -515,39 +536,38 @@ syscall_fault:
 	CFI_ADJUST_CFA_OFFSET 4
 	SAVE_ALL
 	GET_THREAD_INFO(%ebp)
-	movl $-EFAULT,EAX(%esp)
+	movl $-EFAULT,PT_EAX(%esp)
 	jmp resume_userspace
 
 syscall_badsys:
-	movl $-ENOSYS,EAX(%esp)
+	movl $-ENOSYS,PT_EAX(%esp)
 	jmp resume_userspace
 	CFI_ENDPROC
 
 #define FIXUP_ESPFIX_STACK \
-	movl %esp, %eax; \
-	/* switch to 32bit stack using the pointer on top of 16bit stack */ \
-	lss %ss:CPU_16BIT_STACK_SIZE-8, %esp; \
-	/* copy data from 16bit stack to 32bit stack */ \
-	call fixup_x86_bogus_stack; \
-	/* put ESP to the proper location */ \
-	movl %eax, %esp;
-#define UNWIND_ESPFIX_STACK \
+	/* since we are on a wrong stack, we cant make it a C code :( */ \
+	movl %gs:PDA_cpu, %ebx; \
+	PER_CPU(cpu_gdt_descr, %ebx); \
+	movl GDS_address(%ebx), %ebx; \
+	GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah); \
+	addl %esp, %eax; \
+	pushl $__KERNEL_DS; \
+	CFI_ADJUST_CFA_OFFSET 4; \
 	pushl %eax; \
 	CFI_ADJUST_CFA_OFFSET 4; \
+	lss (%esp), %esp; \
+	CFI_ADJUST_CFA_OFFSET -8;
+#define UNWIND_ESPFIX_STACK \
 	movl %ss, %eax; \
-	/* see if on 16bit stack */ \
+	/* see if on espfix stack */ \
 	cmpw $__ESPFIX_SS, %ax; \
-	je 28f; \
-27:	popl %eax; \
-	CFI_ADJUST_CFA_OFFSET -4; \
-.section .fixup,"ax"; \
-28:	movl $__KERNEL_DS, %eax; \
+	jne 27f; \
+	movl $__KERNEL_DS, %eax; \
 	movl %eax, %ds; \
 	movl %eax, %es; \
-	/* switch to 32bit stack */ \
+	/* switch to normal stack */ \
 	FIXUP_ESPFIX_STACK; \
-	jmp 27b; \
-.previous
+27:;
 
 /*
  * Build the entry stubs and pointer table with
@@ -608,13 +628,16 @@ KPROBE_ENTRY(page_fault)
 	CFI_ADJUST_CFA_OFFSET 4
 	ALIGN
 error_code:
+	/* the function address is in %gs's slot on the stack */
+	pushl %es
+	CFI_ADJUST_CFA_OFFSET 4
+	/*CFI_REL_OFFSET es, 0*/
 	pushl %ds
 	CFI_ADJUST_CFA_OFFSET 4
 	/*CFI_REL_OFFSET ds, 0*/
 	pushl %eax
 	CFI_ADJUST_CFA_OFFSET 4
 	CFI_REL_OFFSET eax, 0
-	xorl %eax, %eax
 	pushl %ebp
 	CFI_ADJUST_CFA_OFFSET 4
 	CFI_REL_OFFSET ebp, 0
@@ -627,7 +650,6 @@ error_code:
 	pushl %edx
 	CFI_ADJUST_CFA_OFFSET 4
 	CFI_REL_OFFSET edx, 0
-	decl %eax			# eax = -1
 	pushl %ecx
 	CFI_ADJUST_CFA_OFFSET 4
 	CFI_REL_OFFSET ecx, 0
@@ -635,18 +657,20 @@ error_code:
 	CFI_ADJUST_CFA_OFFSET 4
 	CFI_REL_OFFSET ebx, 0
 	cld
-	pushl %es
+	pushl %gs
 	CFI_ADJUST_CFA_OFFSET 4
-	/*CFI_REL_OFFSET es, 0*/
+	/*CFI_REL_OFFSET gs, 0*/
+	movl $(__KERNEL_PDA), %ecx
+	movl %ecx, %gs
 	UNWIND_ESPFIX_STACK
 	popl %ecx
 	CFI_ADJUST_CFA_OFFSET -4
 	/*CFI_REGISTER es, ecx*/
-	movl ES(%esp), %edi		# get the function address
-	movl ORIG_EAX(%esp), %edx	# get the error code
-	movl %eax, ORIG_EAX(%esp)
-	movl %ecx, ES(%esp)
-	/*CFI_REL_OFFSET es, ES*/
+	movl PT_GS(%esp), %edi		# get the function address
+	movl PT_ORIG_EAX(%esp), %edx	# get the error code
+	movl $-1, PT_ORIG_EAX(%esp)	# no syscall to restart
+	mov  %ecx, PT_GS(%esp)
+	/*CFI_REL_OFFSET gs, ES*/
 	movl $(__USER_DS), %ecx
 	movl %ecx, %ds
 	movl %ecx, %es
@@ -682,7 +706,7 @@ ENTRY(device_not_available)
 	GET_CR0_INTO_EAX
 	testl $0x4, %eax		# EM (math emulation bit)
 	jne device_not_available_emulate
-	preempt_stop
+	preempt_stop(CLBR_ANY)
 	call math_state_restore
 	jmp ret_from_exception
 device_not_available_emulate:
@@ -754,7 +778,7 @@ KPROBE_ENTRY(nmi)
 	cmpw $__ESPFIX_SS, %ax
 	popl %eax
 	CFI_ADJUST_CFA_OFFSET -4
-	je nmi_16bit_stack
+	je nmi_espfix_stack
 	cmpl $sysenter_entry,(%esp)
 	je nmi_stack_fixup
 	pushl %eax
@@ -797,7 +821,7 @@ nmi_debug_stack_check:
 	FIX_STACK(24,nmi_stack_correct, 1)
 	jmp nmi_stack_correct
 
-nmi_16bit_stack:
+nmi_espfix_stack:
 	/* We have a RING0_INT_FRAME here.
 	 *
 	 * create the pointer to lss back
@@ -806,7 +830,6 @@ nmi_16bit_stack:
 	CFI_ADJUST_CFA_OFFSET 4
 	pushl %esp
 	CFI_ADJUST_CFA_OFFSET 4
-	movzwl %sp, %esp
 	addw $4, (%esp)
 	/* copy the iret frame of 12 bytes */
 	.rept 3
@@ -817,11 +840,11 @@ nmi_16bit_stack:
 	CFI_ADJUST_CFA_OFFSET 4
 	SAVE_ALL
 	FIXUP_ESPFIX_STACK		# %eax == %esp
-	CFI_ADJUST_CFA_OFFSET -20	# the frame has now moved
 	xorl %edx,%edx			# zero error code
 	call do_nmi
 	RESTORE_REGS
-	lss 12+4(%esp), %esp		# back to 16bit stack
+	lss 12+4(%esp), %esp		# back to espfix stack
+	CFI_ADJUST_CFA_OFFSET -24
 1:	INTERRUPT_RETURN
 	CFI_ENDPROC
 .section __ex_table,"a"
@@ -830,6 +853,19 @@ nmi_16bit_stack:
 .previous
 KPROBE_END(nmi)
 
+#ifdef CONFIG_PARAVIRT
+ENTRY(native_iret)
+1:	iret
+.section __ex_table,"a"
+	.align 4
+	.long 1b,iret_exc
+.previous
+
+ENTRY(native_irq_enable_sysexit)
+	sti
+	sysexit
+#endif
+
 KPROBE_ENTRY(int3)
 	RING0_INT_FRAME
 	pushl $-1			# mark this as an int
@@ -949,26 +985,27 @@ ENTRY(arch_unwind_init_running)
 	movl	4(%esp), %edx
 	movl	(%esp), %ecx
 	leal	4(%esp), %eax
-	movl	%ebx, EBX(%edx)
+	movl	%ebx, PT_EBX(%edx)
 	xorl	%ebx, %ebx
-	movl	%ebx, ECX(%edx)
-	movl	%ebx, EDX(%edx)
-	movl	%esi, ESI(%edx)
-	movl	%edi, EDI(%edx)
-	movl	%ebp, EBP(%edx)
-	movl	%ebx, EAX(%edx)
-	movl	$__USER_DS, DS(%edx)
-	movl	$__USER_DS, ES(%edx)
-	movl	%ebx, ORIG_EAX(%edx)
-	movl	%ecx, EIP(%edx)
+	movl	%ebx, PT_ECX(%edx)
+	movl	%ebx, PT_EDX(%edx)
+	movl	%esi, PT_ESI(%edx)
+	movl	%edi, PT_EDI(%edx)
+	movl	%ebp, PT_EBP(%edx)
+	movl	%ebx, PT_EAX(%edx)
+	movl	$__USER_DS, PT_DS(%edx)
+	movl	$__USER_DS, PT_ES(%edx)
+	movl	$0, PT_GS(%edx)
+	movl	%ebx, PT_ORIG_EAX(%edx)
+	movl	%ecx, PT_EIP(%edx)
 	movl	12(%esp), %ecx
-	movl	$__KERNEL_CS, CS(%edx)
-	movl	%ebx, EFLAGS(%edx)
-	movl	%eax, OLDESP(%edx)
+	movl	$__KERNEL_CS, PT_CS(%edx)
+	movl	%ebx, PT_EFLAGS(%edx)
+	movl	%eax, PT_OLDESP(%edx)
 	movl	8(%esp), %eax
 	movl	%ecx, 8(%esp)
-	movl	EBX(%edx), %ebx
-	movl	$__KERNEL_DS, OLDSS(%edx)
+	movl	PT_EBX(%edx), %ebx
+	movl	$__KERNEL_DS, PT_OLDSS(%edx)
 	jmpl	*%eax
 	CFI_ENDPROC
 ENDPROC(arch_unwind_init_running)