#include <asm/dwarf2.h>
#include "irq_vectors.h"
+/*
+ * 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.
+ */
+
#define nr_syscalls ((syscall_table_size)/4)
CF_MASK = 0x00000001
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
ALIGN
RING0_PTREGS_FRAME
ret_from_exception:
- preempt_stop
+ preempt_stop(CLBR_ANY)
ret_from_intr:
GET_THREAD_INFO(%ebp)
check_userspace:
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
#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:
* 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*/
pushl $(__USER_CS)
CFI_ADJUST_CFA_OFFSET 4
/*CFI_REL_OFFSET cs, 0*/
+#ifndef CONFIG_COMPAT_VDSO
/*
* Push current_thread_info()->sysenter_return to the stack.
* A tiny bit of offset fixup is necessary - 4*4 means the 4 words
* pushed above; +8 corresponds to copy_thread's esp0 setting.
*/
pushl (TI_sysenter_return-THREAD_SIZE+8+4*4)(%esp)
+#else
+ pushl $SYSENTER_RETURN
+#endif
CFI_ADJUST_CFA_OFFSET 4
CFI_REL_OFFSET eip, 0
jae syscall_badsys
call *sys_call_table(,%eax,4)
movl %eax,PT_EAX(%esp)
- DISABLE_INTERRUPTS
+ DISABLE_INTERRUPTS(CLBR_ECX|CLBR_EDX)
TRACE_IRQS_OFF
movl TI_flags(%ebp), %ecx
testw $_TIF_ALLWORK_MASK, %cx
call *sys_call_table(,%eax,4)
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
.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
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.
CFI_ADJUST_CFA_OFFSET 4
pushl %eax
CFI_ADJUST_CFA_OFFSET 4
- DISABLE_INTERRUPTS
+ DISABLE_INTERRUPTS(CLBR_EAX)
TRACE_IRQS_OFF
lss (%esp), %esp
CFI_ADJUST_CFA_OFFSET -8
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
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
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:
.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
jmp error_code
CFI_ENDPROC
-#ifdef CONFIG_STACK_UNWIND
-ENTRY(arch_unwind_init_running)
- CFI_STARTPROC
- movl 4(%esp), %edx
- movl (%esp), %ecx
- leal 4(%esp), %eax
- movl %ebx, PT_EBX(%edx)
- xorl %ebx, %ebx
- 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, PT_CS(%edx)
- movl %ebx, PT_EFLAGS(%edx)
- movl %eax, PT_OLDESP(%edx)
- movl 8(%esp), %eax
- movl %ecx, 8(%esp)
- movl PT_EBX(%edx), %ebx
- movl $__KERNEL_DS, PT_OLDSS(%edx)
- jmpl *%eax
- CFI_ENDPROC
-ENDPROC(arch_unwind_init_running)
-#endif
-
ENTRY(kernel_thread_helper)
pushl $0 # fake return address for unwinder
CFI_STARTPROC