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
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
|
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
#include <linux/signal.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/version.h>
#include <linux/vt_kern.h>
#include <linux/extable.h>
#include <linux/uaccess.h>
#include <linux/perf_event.h>
#include <linux/kprobes.h>
#include <asm/hardirq.h>
#include <asm/mmu_context.h>
#include <asm/traps.h>
#include <asm/page.h>
int fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *fixup;
fixup = search_exception_tables(instruction_pointer(regs));
if (fixup) {
regs->pc = fixup->nextinsn;
return 1;
}
return 0;
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long write,
unsigned long mmu_meh)
{
struct vm_area_struct *vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
int si_code;
int fault;
unsigned long address = mmu_meh & PAGE_MASK;
if (kprobe_page_fault(regs, tsk->thread.trap_no))
return;
si_code = SEGV_MAPERR;
#ifndef CONFIG_CPU_HAS_TLBI
/*
* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*
* NOTE! We MUST NOT take any locks for this case. We may
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
*/
if (unlikely(address >= VMALLOC_START) &&
unlikely(address <= VMALLOC_END)) {
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
*
* Do _not_ use "tsk" here. We might be inside
* an interrupt in the middle of a task switch..
*/
int offset = pgd_index(address);
pgd_t *pgd, *pgd_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pte_t *pte_k;
unsigned long pgd_base;
pgd_base = (unsigned long)__va(get_pgd());
pgd = (pgd_t *)pgd_base + offset;
pgd_k = init_mm.pgd + offset;
if (!pgd_present(*pgd_k))
goto no_context;
set_pgd(pgd, *pgd_k);
pud = (pud_t *)pgd;
pud_k = (pud_t *)pgd_k;
if (!pud_present(*pud_k))
goto no_context;
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
goto no_context;
set_pmd(pmd, *pmd_k);
pte_k = pte_offset_kernel(pmd_k, address);
if (!pte_present(*pte_k))
goto no_context;
return;
}
#endif
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (in_atomic() || !mm)
goto bad_area_nosemaphore;
mmap_read_lock(mm);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (vma->vm_start <= address)
goto good_area;
if (!(vma->vm_flags & VM_GROWSDOWN))
goto bad_area;
if (expand_stack(vma, address))
goto bad_area;
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
si_code = SEGV_ACCERR;
if (write) {
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
} else {
if (unlikely(!vma_is_accessible(vma)))
goto bad_area;
}
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
fault = handle_mm_fault(vma, address, write ? FAULT_FLAG_WRITE : 0);
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
else if (fault & VM_FAULT_SIGSEGV)
goto bad_area;
BUG();
}
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, regs,
address);
} else {
tsk->min_flt++;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, regs,
address);
}
mmap_read_unlock(mm);
return;
/*
* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
bad_area:
mmap_read_unlock(mm);
bad_area_nosemaphore:
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs)) {
tsk->thread.trap_no = trap_no(regs);
force_sig_fault(SIGSEGV, si_code, (void __user *)address);
return;
}
no_context:
tsk->thread.trap_no = trap_no(regs);
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs))
return;
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
bust_spinlocks(1);
pr_alert("Unable to handle kernel paging request at virtual "
"address 0x%08lx, pc: 0x%08lx\n", address, regs->pc);
die(regs, "Oops");
out_of_memory:
tsk->thread.trap_no = trap_no(regs);
/*
* We ran out of memory, call the OOM killer, and return the userspace
* (which will retry the fault, or kill us if we got oom-killed).
*/
pagefault_out_of_memory();
return;
do_sigbus:
tsk->thread.trap_no = trap_no(regs);
mmap_read_unlock(mm);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs))
goto no_context;
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
}
|
