/*
	Asm versions of Xen pv-ops, suitable for either direct use or inlining.
	The inline versions are the same as the direct-use versions, with the
	pre- and post-amble chopped off.

	This code is encoded for size rather than absolute efficiency,
	with a view to being able to inline as much as possible.

	We only bother with direct forms (ie, vcpu in pda) of the operations
	here; the indirect forms are better handled in C, since they're
	generally too large to inline anyway.
 */

#include <asm/errno.h>
#include <asm/percpu.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>

#include <xen/interface/xen.h>

#include "xen-asm.h"

ENTRY(xen_adjust_exception_frame)
	mov 8+0(%rsp),%rcx
	mov 8+8(%rsp),%r11
	ret $16

hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
/*
	Xen64 iret frame:

	ss
	rsp
	rflags
	cs
	rip		<-- standard iret frame

	flags

	rcx		}
	r11		}<-- pushed by hypercall page
rsp ->	rax		}
 */
ENTRY(xen_iret)
	pushq $0
1:	jmp hypercall_iret
ENDPATCH(xen_iret)
RELOC(xen_iret, 1b+1)

/*
	sysexit is not used for 64-bit processes, so it's
	only ever used to return to 32-bit compat userspace.
 */
ENTRY(xen_sysexit)
	pushq $__USER32_DS
	pushq %rcx
	pushq $X86_EFLAGS_IF
	pushq $__USER32_CS
	pushq %rdx

	pushq $0
1:	jmp hypercall_iret
ENDPATCH(xen_sysexit)
RELOC(xen_sysexit, 1b+1)

ENTRY(xen_sysret64)
	/* We're already on the usermode stack at this point, but still
	   with the kernel gs, so we can easily switch back */
	movq %rsp, PER_CPU_VAR(old_rsp)
	movq PER_CPU_VAR(kernel_stack),%rsp

	pushq $__USER_DS
	pushq PER_CPU_VAR(old_rsp)
	pushq %r11
	pushq $__USER_CS
	pushq %rcx

	pushq $VGCF_in_syscall
1:	jmp hypercall_iret
ENDPATCH(xen_sysret64)
RELOC(xen_sysret64, 1b+1)

ENTRY(xen_sysret32)
	/* We're already on the usermode stack at this point, but still
	   with the kernel gs, so we can easily switch back */
	movq %rsp, PER_CPU_VAR(old_rsp)
	movq PER_CPU_VAR(kernel_stack), %rsp

	pushq $__USER32_DS
	pushq PER_CPU_VAR(old_rsp)
	pushq %r11
	pushq $__USER32_CS
	pushq %rcx

	pushq $VGCF_in_syscall
1:	jmp hypercall_iret
ENDPATCH(xen_sysret32)
RELOC(xen_sysret32, 1b+1)

/*
	Xen handles syscall callbacks much like ordinary exceptions,
	which means we have:
	 - kernel gs
	 - kernel rsp
	 - an iret-like stack frame on the stack (including rcx and r11):
		ss
		rsp
		rflags
		cs
		rip
		r11
	rsp->	rcx

	In all the entrypoints, we undo all that to make it look
	like a CPU-generated syscall/sysenter and jump to the normal
	entrypoint.
 */

.macro undo_xen_syscall
	mov 0*8(%rsp),%rcx
	mov 1*8(%rsp),%r11
	mov 5*8(%rsp),%rsp
.endm

/* Normal 64-bit system call target */
ENTRY(xen_syscall_target)
	undo_xen_syscall
	jmp system_call_after_swapgs
ENDPROC(xen_syscall_target)

#ifdef CONFIG_IA32_EMULATION

/* 32-bit compat syscall target */
ENTRY(xen_syscall32_target)
	undo_xen_syscall
	jmp ia32_cstar_target
ENDPROC(xen_syscall32_target)

/* 32-bit compat sysenter target */
ENTRY(xen_sysenter_target)
	undo_xen_syscall
	jmp ia32_sysenter_target
ENDPROC(xen_sysenter_target)

#else /* !CONFIG_IA32_EMULATION */

ENTRY(xen_syscall32_target)
ENTRY(xen_sysenter_target)
	lea 16(%rsp), %rsp	/* strip %rcx,%r11 */
	mov $-ENOSYS, %rax
	pushq $VGCF_in_syscall
	jmp hypercall_iret
ENDPROC(xen_syscall32_target)
ENDPROC(xen_sysenter_target)

#endif	/* CONFIG_IA32_EMULATION */