1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
|
/*
* safe-syscall.inc.S : host-specific assembly fragment
* to handle signals occurring at the same time as system calls.
* This is intended to be included by common-user/safe-syscall.S
*
* Written by Richard Henderson <rth@twiddle.net>
* Copyright (C) 2016 Red Hat, Inc.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
.global safe_syscall_base
.global safe_syscall_start
.global safe_syscall_end
.type safe_syscall_base, @function
/* This is the entry point for making a system call. The calling
* convention here is that of a C varargs function with the
* first argument an 'int *' to the signal_pending flag, the
* second one the system call number (as a 'long'), and all further
* arguments being syscall arguments (also 'long').
*/
safe_syscall_base:
.cfi_startproc
push %ebp
.cfi_adjust_cfa_offset 4
.cfi_rel_offset ebp, 0
push %esi
.cfi_adjust_cfa_offset 4
.cfi_rel_offset esi, 0
push %edi
.cfi_adjust_cfa_offset 4
.cfi_rel_offset edi, 0
push %ebx
.cfi_adjust_cfa_offset 4
.cfi_rel_offset ebx, 0
/* The syscall calling convention isn't the same as the C one:
* we enter with 0(%esp) == return address
* 4(%esp) == &signal_pending
* 8(%esp) == syscall number
* 12(%esp) ... 32(%esp) == syscall arguments
* and return the result in eax
* and the syscall instruction needs
* eax == syscall number
* ebx, ecx, edx, esi, edi, ebp == syscall arguments
* and returns the result in eax
* Shuffle everything around appropriately.
* Note the 16 bytes that we pushed to save registers.
*/
mov 12+16(%esp), %ebx /* the syscall arguments */
mov 16+16(%esp), %ecx
mov 20+16(%esp), %edx
mov 24+16(%esp), %esi
mov 28+16(%esp), %edi
mov 32+16(%esp), %ebp
/* This next sequence of code works in conjunction with the
* rewind_if_safe_syscall_function(). If a signal is taken
* and the interrupted PC is anywhere between 'safe_syscall_start'
* and 'safe_syscall_end' then we rewind it to 'safe_syscall_start'.
* The code sequence must therefore be able to cope with this, and
* the syscall instruction must be the final one in the sequence.
*/
safe_syscall_start:
/* if signal_pending is non-zero, don't do the call */
mov 4+16(%esp), %eax /* signal_pending */
cmpl $0, (%eax)
jnz 2f
mov 8+16(%esp), %eax /* syscall number */
int $0x80
safe_syscall_end:
/* code path for having successfully executed the syscall */
#if defined(__linux__)
/* Linux kernel returns (small) negative errno. */
cmp $-4095, %eax
jae 0f
#elif defined(__FreeBSD__)
/* FreeBSD kernel returns positive errno and C bit set. */
jc 1f
#else
#error "unsupported os"
#endif
pop %ebx
.cfi_remember_state
.cfi_adjust_cfa_offset -4
.cfi_restore ebx
pop %edi
.cfi_adjust_cfa_offset -4
.cfi_restore edi
pop %esi
.cfi_adjust_cfa_offset -4
.cfi_restore esi
pop %ebp
.cfi_adjust_cfa_offset -4
.cfi_restore ebp
ret
.cfi_restore_state
#if defined(__linux__)
0: neg %eax
jmp 1f
#endif
/* code path when we didn't execute the syscall */
2: mov $QEMU_ERESTARTSYS, %eax
/* code path setting errno */
1: pop %ebx
.cfi_adjust_cfa_offset -4
.cfi_restore ebx
pop %edi
.cfi_adjust_cfa_offset -4
.cfi_restore edi
pop %esi
.cfi_adjust_cfa_offset -4
.cfi_restore esi
pop %ebp
.cfi_adjust_cfa_offset -4
.cfi_restore ebp
jmp safe_syscall_set_errno_tail
.cfi_endproc
.size safe_syscall_base, .-safe_syscall_base
|
