summaryrefslogtreecommitdiffstats
path: root/arch/riscv/mm/fault.c
blob: 523dbfbac03ddedac0709a15102bc4e460b93d1f (plain)
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
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
/*
 * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
 *  Lennox Wu <lennox.wu@sunplusct.com>
 *  Chen Liqin <liqin.chen@sunplusct.com>
 * Copyright (C) 2012 Regents of the University of California
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, see the file COPYING, or write
 * to the Free Software Foundation, Inc.,
 */


#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
#include <linux/perf_event.h>
#include <linux/signal.h>
#include <linux/uaccess.h>

#include <asm/pgalloc.h>
#include <asm/ptrace.h>
#include <asm/tlbflush.h>

/*
 * 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)
{
	struct task_struct *tsk;
	struct vm_area_struct *vma;
	struct mm_struct *mm;
	unsigned long addr, cause;
	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
	int code = SEGV_MAPERR;
	vm_fault_t fault;

	cause = regs->scause;
	addr = regs->sbadaddr;

	tsk = current;
	mm = tsk->mm;

	/*
	 * 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((addr >= VMALLOC_START) && (addr <= VMALLOC_END)))
		goto vmalloc_fault;

	/* Enable interrupts if they were enabled in the parent context. */
	if (likely(regs->sstatus & SR_SPIE))
		local_irq_enable();

	/*
	 * If we're in an interrupt, have no user context, or are running
	 * in an atomic region, then we must not take the fault.
	 */
	if (unlikely(faulthandler_disabled() || !mm))
		goto no_context;

	if (user_mode(regs))
		flags |= FAULT_FLAG_USER;

	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr);

retry:
	down_read(&mm->mmap_sem);
	vma = find_vma(mm, addr);
	if (unlikely(!vma))
		goto bad_area;
	if (likely(vma->vm_start <= addr))
		goto good_area;
	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
		goto bad_area;
	if (unlikely(expand_stack(vma, addr)))
		goto bad_area;

	/*
	 * Ok, we have a good vm_area for this memory access, so
	 * we can handle it.
	 */
good_area:
	code = SEGV_ACCERR;

	switch (cause) {
	case EXC_INST_PAGE_FAULT:
		if (!(vma->vm_flags & VM_EXEC))
			goto bad_area;
		break;
	case EXC_LOAD_PAGE_FAULT:
		if (!(vma->vm_flags & VM_READ))
			goto bad_area;
		break;
	case EXC_STORE_PAGE_FAULT:
		if (!(vma->vm_flags & VM_WRITE))
			goto bad_area;
		flags |= FAULT_FLAG_WRITE;
		break;
	default:
		panic("%s: unhandled cause %lu", __func__, cause);
	}

	/*
	 * If for any reason at all we could not handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
	fault = handle_mm_fault(vma, addr, flags);

	/*
	 * If we need to retry but a fatal signal is pending, handle the
	 * signal first. We do not need to release the mmap_sem because it
	 * would already be released in __lock_page_or_retry in mm/filemap.c.
	 */
	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(tsk))
		return;

	if (unlikely(fault & VM_FAULT_ERROR)) {
		if (fault & VM_FAULT_OOM)
			goto out_of_memory;
		else if (fault & VM_FAULT_SIGBUS)
			goto do_sigbus;
		BUG();
	}

	/*
	 * Major/minor page fault accounting is only done on the
	 * initial attempt. If we go through a retry, it is extremely
	 * likely that the page will be found in page cache at that point.
	 */
	if (flags & FAULT_FLAG_ALLOW_RETRY) {
		if (fault & VM_FAULT_MAJOR) {
			tsk->maj_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ,
				      1, regs, addr);
		} else {
			tsk->min_flt++;
			perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN,
				      1, regs, addr);
		}
		if (fault & VM_FAULT_RETRY) {
			/*
			 * Clear FAULT_FLAG_ALLOW_RETRY to avoid any risk
			 * of starvation.
			 */
			flags &= ~(FAULT_FLAG_ALLOW_RETRY);
			flags |= FAULT_FLAG_TRIED;

			/*
			 * No need to up_read(&mm->mmap_sem) as we would
			 * have already released it in __lock_page_or_retry
			 * in mm/filemap.c.
			 */
			goto retry;
		}
	}

	up_read(&mm->mmap_sem);
	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:
	up_read(&mm->mmap_sem);
	/* User mode accesses just cause a SIGSEGV */
	if (user_mode(regs)) {
		do_trap(regs, SIGSEGV, code, addr, tsk);
		return;
	}

no_context:
	/* 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 %s at virtual address " REG_FMT "\n",
		(addr < PAGE_SIZE) ? "NULL pointer dereference" :
		"paging request", addr);
	die(regs, "Oops");
	do_exit(SIGKILL);

	/*
	 * 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).
	 */
out_of_memory:
	up_read(&mm->mmap_sem);
	if (!user_mode(regs))
		goto no_context;
	pagefault_out_of_memory();
	return;

do_sigbus:
	up_read(&mm->mmap_sem);
	/* Kernel mode? Handle exceptions or die */
	if (!user_mode(regs))
		goto no_context;
	do_trap(regs, SIGBUS, BUS_ADRERR, addr, tsk);
	return;

vmalloc_fault:
	{
		pgd_t *pgd, *pgd_k;
		pud_t *pud, *pud_k;
		p4d_t *p4d, *p4d_k;
		pmd_t *pmd, *pmd_k;
		pte_t *pte_k;
		int index;

		if (user_mode(regs))
			goto bad_area;

		/*
		 * Synchronize this task's top level page-table
		 * with the 'reference' page table.
		 *
		 * Do _not_ use "tsk->active_mm->pgd" here.
		 * We might be inside an interrupt in the middle
		 * of a task switch.
		 *
		 * Note: Use the old spbtr name instead of using the current
		 * satp name to support binutils 2.29 which doesn't know about
		 * the privileged ISA 1.10 yet.
		 */
		index = pgd_index(addr);
		pgd = (pgd_t *)pfn_to_virt(csr_read(sptbr)) + index;
		pgd_k = init_mm.pgd + index;

		if (!pgd_present(*pgd_k))
			goto no_context;
		set_pgd(pgd, *pgd_k);

		p4d = p4d_offset(pgd, addr);
		p4d_k = p4d_offset(pgd_k, addr);
		if (!p4d_present(*p4d_k))
			goto no_context;

		pud = pud_offset(p4d, addr);
		pud_k = pud_offset(p4d_k, addr);
		if (!pud_present(*pud_k))
			goto no_context;

		/*
		 * Since the vmalloc area is global, it is unnecessary
		 * to copy individual PTEs
		 */
		pmd = pmd_offset(pud, addr);
		pmd_k = pmd_offset(pud_k, addr);
		if (!pmd_present(*pmd_k))
			goto no_context;
		set_pmd(pmd, *pmd_k);

		/*
		 * Make sure the actual PTE exists as well to
		 * catch kernel vmalloc-area accesses to non-mapped
		 * addresses. If we don't do this, this will just
		 * silently loop forever.
		 */
		pte_k = pte_offset_kernel(pmd_k, addr);
		if (!pte_present(*pte_k))
			goto no_context;

		/*
		 * The kernel assumes that TLBs don't cache invalid
		 * entries, but in RISC-V, SFENCE.VMA specifies an
		 * ordering constraint, not a cache flush; it is
		 * necessary even after writing invalid entries.
		 * Relying on flush_tlb_fix_spurious_fault would
		 * suffice, but the extra traps reduce
		 * performance. So, eagerly SFENCE.VMA.
		 */
		local_flush_tlb_page(addr);

		return;
	}
}