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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
|
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 2020-2022 Loongson Technology Corporation Limited
*
* Derived from MIPS:
* Copyright (C) 1995 - 2000 by Ralf Baechle
*/
#include <linux/context_tracking.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/entry-common.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/ratelimit.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/kdebug.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <linux/kfence.h>
#include <asm/branch.h>
#include <asm/exception.h>
#include <asm/mmu_context.h>
#include <asm/ptrace.h>
int show_unhandled_signals = 1;
static void __kprobes no_context(struct pt_regs *regs,
unsigned long write, unsigned long address)
{
const int field = sizeof(unsigned long) * 2;
/* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs))
return;
if (kfence_handle_page_fault(address, write, 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("CPU %d Unable to handle kernel paging request at "
"virtual address %0*lx, era == %0*lx, ra == %0*lx\n",
raw_smp_processor_id(), field, address, field, regs->csr_era,
field, regs->regs[1]);
die("Oops", regs);
}
static void __kprobes do_out_of_memory(struct pt_regs *regs,
unsigned long write, unsigned long address)
{
/*
* 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).
*/
if (!user_mode(regs)) {
no_context(regs, write, address);
return;
}
pagefault_out_of_memory();
}
static void __kprobes do_sigbus(struct pt_regs *regs,
unsigned long write, unsigned long address, int si_code)
{
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs)) {
no_context(regs, write, address);
return;
}
/*
* Send a sigbus, regardless of whether we were in kernel
* or user mode.
*/
current->thread.csr_badvaddr = address;
current->thread.trap_nr = read_csr_excode();
force_sig_fault(SIGBUS, BUS_ADRERR, (void __user *)address);
}
static void __kprobes do_sigsegv(struct pt_regs *regs,
unsigned long write, unsigned long address, int si_code)
{
const int field = sizeof(unsigned long) * 2;
static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
/* Kernel mode? Handle exceptions or die */
if (!user_mode(regs)) {
no_context(regs, write, address);
return;
}
/* User mode accesses just cause a SIGSEGV */
current->thread.csr_badvaddr = address;
if (!write)
current->thread.error_code = 1;
else
current->thread.error_code = 2;
current->thread.trap_nr = read_csr_excode();
if (show_unhandled_signals &&
unhandled_signal(current, SIGSEGV) && __ratelimit(&ratelimit_state)) {
pr_info("do_page_fault(): sending SIGSEGV to %s for invalid %s %0*lx\n",
current->comm,
write ? "write access to" : "read access from",
field, address);
pr_info("era = %0*lx in", field,
(unsigned long) regs->csr_era);
print_vma_addr(KERN_CONT " ", regs->csr_era);
pr_cont("\n");
pr_info("ra = %0*lx in", field,
(unsigned long) regs->regs[1]);
print_vma_addr(KERN_CONT " ", regs->regs[1]);
pr_cont("\n");
}
force_sig_fault(SIGSEGV, si_code, (void __user *)address);
}
/*
* This routine handles page faults. It determines the address,
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
static void __kprobes __do_page_fault(struct pt_regs *regs,
unsigned long write, unsigned long address)
{
int si_code = SEGV_MAPERR;
unsigned int flags = FAULT_FLAG_DEFAULT;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
struct vm_area_struct *vma = NULL;
vm_fault_t fault;
if (kprobe_page_fault(regs, current->thread.trap_nr))
return;
/*
* 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 (address & __UA_LIMIT) {
if (!user_mode(regs))
no_context(regs, write, address);
else
do_sigsegv(regs, write, address, si_code);
return;
}
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm) {
do_sigsegv(regs, write, address, si_code);
return;
}
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
retry:
vma = lock_mm_and_find_vma(mm, address, regs);
if (unlikely(!vma))
goto bad_area_nosemaphore;
goto good_area;
/*
* 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:
do_sigsegv(regs, write, address, si_code);
return;
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
si_code = SEGV_ACCERR;
if (write) {
flags |= FAULT_FLAG_WRITE;
if (!(vma->vm_flags & VM_WRITE))
goto bad_area;
} else {
if (!(vma->vm_flags & VM_READ) && address != exception_era(regs))
goto bad_area;
if (!(vma->vm_flags & VM_EXEC) && address == exception_era(regs))
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, flags, regs);
if (fault_signal_pending(fault, regs)) {
if (!user_mode(regs))
no_context(regs, write, address);
return;
}
/* The fault is fully completed (including releasing mmap lock) */
if (fault & VM_FAULT_COMPLETED)
return;
if (unlikely(fault & VM_FAULT_RETRY)) {
flags |= FAULT_FLAG_TRIED;
/*
* No need to mmap_read_unlock(mm) as we would
* have already released it in __lock_page_or_retry
* in mm/filemap.c.
*/
goto retry;
}
if (unlikely(fault & VM_FAULT_ERROR)) {
mmap_read_unlock(mm);
if (fault & VM_FAULT_OOM) {
do_out_of_memory(regs, write, address);
return;
} else if (fault & VM_FAULT_SIGSEGV) {
do_sigsegv(regs, write, address, si_code);
return;
} else if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE)) {
do_sigbus(regs, write, address, si_code);
return;
}
BUG();
}
mmap_read_unlock(mm);
}
asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
unsigned long write, unsigned long address)
{
irqentry_state_t state = irqentry_enter(regs);
/* Enable interrupt if enabled in parent context */
if (likely(regs->csr_prmd & CSR_PRMD_PIE))
local_irq_enable();
__do_page_fault(regs, write, address);
local_irq_disable();
irqentry_exit(regs, state);
}
|
