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
|
// SPDX-License-Identifier: GPL-2.0-only
/* Page Fault Handling for ARC (TLB Miss / ProtV)
*
* Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
*/
#include <linux/signal.h>
#include <linux/interrupt.h>
#include <linux/sched/signal.h>
#include <linux/errno.h>
#include <linux/ptrace.h>
#include <linux/uaccess.h>
#include <linux/kdebug.h>
#include <linux/perf_event.h>
#include <linux/mm_types.h>
#include <asm/mmu.h>
/*
* kernel virtual address is required to implement vmalloc/pkmap/fixmap
* Refer to asm/processor.h for System Memory Map
*
* It simply copies the PMD entry (pointer to 2nd level page table or hugepage)
* from swapper pgdir to task pgdir. The 2nd level table/page is thus shared
*/
noinline static int handle_kernel_vaddr_fault(unsigned long address)
{
/*
* Synchronize this task's top level page-table
* with the 'reference' page table.
*/
pgd_t *pgd, *pgd_k;
p4d_t *p4d, *p4d_k;
pud_t *pud, *pud_k;
pmd_t *pmd, *pmd_k;
pgd = pgd_offset(current->active_mm, address);
pgd_k = pgd_offset_k(address);
if (pgd_none (*pgd_k))
goto bad_area;
if (!pgd_present(*pgd))
set_pgd(pgd, *pgd_k);
p4d = p4d_offset(pgd, address);
p4d_k = p4d_offset(pgd_k, address);
if (p4d_none(*p4d_k))
goto bad_area;
if (!p4d_present(*p4d))
set_p4d(p4d, *p4d_k);
pud = pud_offset(p4d, address);
pud_k = pud_offset(p4d_k, address);
if (pud_none(*pud_k))
goto bad_area;
if (!pud_present(*pud))
set_pud(pud, *pud_k);
pmd = pmd_offset(pud, address);
pmd_k = pmd_offset(pud_k, address);
if (pmd_none(*pmd_k))
goto bad_area;
if (!pmd_present(*pmd))
set_pmd(pmd, *pmd_k);
/* XXX: create the TLB entry here */
return 0;
bad_area:
return 1;
}
void do_page_fault(unsigned long address, struct pt_regs *regs)
{
struct vm_area_struct *vma = NULL;
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
int sig, si_code = SEGV_MAPERR;
unsigned int write = 0, exec = 0, mask;
vm_fault_t fault = VM_FAULT_SIGSEGV; /* handle_mm_fault() output */
unsigned int flags; /* handle_mm_fault() input */
/*
* 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 >= VMALLOC_START && !user_mode(regs)) {
if (unlikely(handle_kernel_vaddr_fault(address)))
goto no_context;
else
return;
}
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (faulthandler_disabled() || !mm)
goto no_context;
if (regs->ecr_cause & ECR_C_PROTV_STORE) /* ST/EX */
write = 1;
else if ((regs->ecr_vec == ECR_V_PROTV) &&
(regs->ecr_cause == ECR_C_PROTV_INST_FETCH))
exec = 1;
flags = FAULT_FLAG_DEFAULT;
if (user_mode(regs))
flags |= FAULT_FLAG_USER;
if (write)
flags |= FAULT_FLAG_WRITE;
perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
retry:
mmap_read_lock(mm);
vma = find_vma(mm, address);
if (!vma)
goto bad_area;
if (unlikely(address < vma->vm_start)) {
if (!(vma->vm_flags & VM_GROWSDOWN) || expand_stack(vma, address))
goto bad_area;
}
/*
* vm_area is good, now check permissions for this memory access
*/
mask = VM_READ;
if (write)
mask = VM_WRITE;
if (exec)
mask = VM_EXEC;
if (!(vma->vm_flags & mask)) {
si_code = SEGV_ACCERR;
goto bad_area;
}
fault = handle_mm_fault(vma, address, flags, regs);
/* Quick path to respond to signals */
if (fault_signal_pending(fault, regs)) {
if (!user_mode(regs))
goto no_context;
return;
}
/* The fault is fully completed (including releasing mmap lock) */
if (fault & VM_FAULT_COMPLETED)
return;
/*
* Fault retry nuances, mmap_lock already relinquished by core mm
*/
if (unlikely(fault & VM_FAULT_RETRY)) {
flags |= FAULT_FLAG_TRIED;
goto retry;
}
bad_area:
mmap_read_unlock(mm);
/*
* Major/minor page fault accounting
* (in case of retry we only land here once)
*/
if (likely(!(fault & VM_FAULT_ERROR)))
/* Normal return path: fault Handled Gracefully */
return;
if (!user_mode(regs))
goto no_context;
if (fault & VM_FAULT_OOM) {
pagefault_out_of_memory();
return;
}
if (fault & VM_FAULT_SIGBUS) {
sig = SIGBUS;
si_code = BUS_ADRERR;
}
else {
sig = SIGSEGV;
}
tsk->thread.fault_address = address;
force_sig_fault(sig, si_code, (void __user *)address);
return;
no_context:
if (fixup_exception(regs))
return;
die("Oops", regs, address);
}
|
