All new accounts created on Gitlab now require administrator approval. If you invite any collaborators, please let Flux staff know so they can approve the accounts.

dump.c 7.61 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
/*
 * Copyright (c) 2014, The Linux Foundation. All rights reserved.
 * Debug helper to dump the current kernel pagetables of the system
 * so that we can see what the various memory ranges are set to.
 *
 * Derived from x86 and arm implementation:
 * (C) Copyright 2008 Intel Corporation
 *
 * Author: Arjan van de Ven <arjan@linux.intel.com>
 *
 * 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; version 2
 * of the License.
 */
#include <linux/debugfs.h>
17
#include <linux/errno.h>
18
#include <linux/fs.h>
19
#include <linux/io.h>
20
#include <linux/init.h>
21 22 23 24 25
#include <linux/mm.h>
#include <linux/sched.h>
#include <linux/seq_file.h>

#include <asm/fixmap.h>
26
#include <asm/kasan.h>
27
#include <asm/memory.h>
28
#include <asm/pgtable.h>
29
#include <asm/pgtable-hwdef.h>
30 31 32 33 34 35

struct addr_marker {
	unsigned long start_address;
	const char *name;
};

36
static const struct addr_marker address_markers[] = {
37 38 39 40
#ifdef CONFIG_KASAN
	{ KASAN_SHADOW_START,		"Kasan shadow start" },
	{ KASAN_SHADOW_END,		"Kasan shadow end" },
#endif
41 42 43 44 45 46 47 48
	{ MODULES_VADDR,		"Modules start" },
	{ MODULES_END,			"Modules end" },
	{ VMALLOC_START,		"vmalloc() Area" },
	{ VMALLOC_END,			"vmalloc() End" },
	{ FIXADDR_START,		"Fixmap start" },
	{ FIXADDR_TOP,			"Fixmap end" },
	{ PCI_IO_START,			"PCI I/O start" },
	{ PCI_IO_END,			"PCI I/O end" },
49
#ifdef CONFIG_SPARSEMEM_VMEMMAP
50 51
	{ VMEMMAP_START,		"vmemmap start" },
	{ VMEMMAP_START + VMEMMAP_SIZE,	"vmemmap end" },
52
#endif
53 54
	{ PAGE_OFFSET,			"Linear Mapping" },
	{ -1,				NULL },
55 56
};

57 58 59 60 61 62
/*
 * The page dumper groups page table entries of the same type into a single
 * description. It uses pg_state to track the range information while
 * iterating over the pte entries. When the continuity is broken it then
 * dumps out a description of the range.
 */
63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79
struct pg_state {
	struct seq_file *seq;
	const struct addr_marker *marker;
	unsigned long start_address;
	unsigned level;
	u64 current_prot;
};

struct prot_bits {
	u64		mask;
	u64		val;
	const char	*set;
	const char	*clear;
};

static const struct prot_bits pte_bits[] = {
	{
80 81 82 83 84
		.mask	= PTE_VALID,
		.val	= PTE_VALID,
		.set	= " ",
		.clear	= "F",
	}, {
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
		.mask	= PTE_USER,
		.val	= PTE_USER,
		.set	= "USR",
		.clear	= "   ",
	}, {
		.mask	= PTE_RDONLY,
		.val	= PTE_RDONLY,
		.set	= "ro",
		.clear	= "RW",
	}, {
		.mask	= PTE_PXN,
		.val	= PTE_PXN,
		.set	= "NX",
		.clear	= "x ",
	}, {
		.mask	= PTE_SHARED,
		.val	= PTE_SHARED,
		.set	= "SHD",
		.clear	= "   ",
	}, {
		.mask	= PTE_AF,
		.val	= PTE_AF,
		.set	= "AF",
		.clear	= "  ",
	}, {
		.mask	= PTE_NG,
		.val	= PTE_NG,
		.set	= "NG",
		.clear	= "  ",
114 115 116 117 118 119 120 121 122 123
	}, {
		.mask	= PTE_CONT,
		.val	= PTE_CONT,
		.set	= "CON",
		.clear	= "   ",
	}, {
		.mask	= PTE_TABLE_BIT,
		.val	= PTE_TABLE_BIT,
		.set	= "   ",
		.clear	= "BLK",
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
	}, {
		.mask	= PTE_UXN,
		.val	= PTE_UXN,
		.set	= "UXN",
	}, {
		.mask	= PTE_ATTRINDX_MASK,
		.val	= PTE_ATTRINDX(MT_DEVICE_nGnRnE),
		.set	= "DEVICE/nGnRnE",
	}, {
		.mask	= PTE_ATTRINDX_MASK,
		.val	= PTE_ATTRINDX(MT_DEVICE_nGnRE),
		.set	= "DEVICE/nGnRE",
	}, {
		.mask	= PTE_ATTRINDX_MASK,
		.val	= PTE_ATTRINDX(MT_DEVICE_GRE),
		.set	= "DEVICE/GRE",
	}, {
		.mask	= PTE_ATTRINDX_MASK,
		.val	= PTE_ATTRINDX(MT_NORMAL_NC),
		.set	= "MEM/NORMAL-NC",
	}, {
		.mask	= PTE_ATTRINDX_MASK,
		.val	= PTE_ATTRINDX(MT_NORMAL),
		.set	= "MEM/NORMAL",
	}
};

struct pg_level {
	const struct prot_bits *bits;
Mark Rutland's avatar
Mark Rutland committed
153
	const char *name;
154 155 156 157 158 159 160
	size_t num;
	u64 mask;
};

static struct pg_level pg_level[] = {
	{
	}, { /* pgd */
Mark Rutland's avatar
Mark Rutland committed
161
		.name	= "PGD",
162 163 164
		.bits	= pte_bits,
		.num	= ARRAY_SIZE(pte_bits),
	}, { /* pud */
Mark Rutland's avatar
Mark Rutland committed
165
		.name	= (CONFIG_PGTABLE_LEVELS > 3) ? "PUD" : "PGD",
166 167 168
		.bits	= pte_bits,
		.num	= ARRAY_SIZE(pte_bits),
	}, { /* pmd */
Mark Rutland's avatar
Mark Rutland committed
169
		.name	= (CONFIG_PGTABLE_LEVELS > 2) ? "PMD" : "PGD",
170 171 172
		.bits	= pte_bits,
		.num	= ARRAY_SIZE(pte_bits),
	}, { /* pte */
Mark Rutland's avatar
Mark Rutland committed
173
		.name	= "PTE",
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
		.bits	= pte_bits,
		.num	= ARRAY_SIZE(pte_bits),
	},
};

static void dump_prot(struct pg_state *st, const struct prot_bits *bits,
			size_t num)
{
	unsigned i;

	for (i = 0; i < num; i++, bits++) {
		const char *s;

		if ((st->current_prot & bits->mask) == bits->val)
			s = bits->set;
		else
			s = bits->clear;

		if (s)
			seq_printf(st->seq, " %s", s);
	}
}

static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
				u64 val)
{
	static const char units[] = "KMGTPE";
	u64 prot = val & pg_level[level].mask;

	if (!st->level) {
		st->level = level;
		st->current_prot = prot;
		st->start_address = addr;
		seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
	} else if (prot != st->current_prot || level != st->level ||
		   addr >= st->marker[1].start_address) {
		const char *unit = units;
		unsigned long delta;

		if (st->current_prot) {
214
			seq_printf(st->seq, "0x%016lx-0x%016lx   ",
215 216 217 218 219 220 221
				   st->start_address, addr);

			delta = (addr - st->start_address) >> 10;
			while (!(delta & 1023) && unit[1]) {
				delta >>= 10;
				unit++;
			}
Mark Rutland's avatar
Mark Rutland committed
222 223
			seq_printf(st->seq, "%9lu%c %s", delta, *unit,
				   pg_level[st->level].name);
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
			if (pg_level[st->level].bits)
				dump_prot(st, pg_level[st->level].bits,
					  pg_level[st->level].num);
			seq_puts(st->seq, "\n");
		}

		if (addr >= st->marker[1].start_address) {
			st->marker++;
			seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
		}

		st->start_address = addr;
		st->current_prot = prot;
		st->level = level;
	}

	if (addr >= st->marker[1].start_address) {
		st->marker++;
		seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
	}

}

static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start)
{
	pte_t *pte = pte_offset_kernel(pmd, 0);
	unsigned long addr;
	unsigned i;

	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
		addr = start + i * PAGE_SIZE;
		note_page(st, addr, 4, pte_val(*pte));
	}
}

static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
{
	pmd_t *pmd = pmd_offset(pud, 0);
	unsigned long addr;
	unsigned i;

	for (i = 0; i < PTRS_PER_PMD; i++, pmd++) {
		addr = start + i * PMD_SIZE;
267
		if (pmd_none(*pmd) || pmd_sect(*pmd)) {
268
			note_page(st, addr, 3, pmd_val(*pmd));
269 270
		} else {
			BUG_ON(pmd_bad(*pmd));
271
			walk_pte(st, pmd, addr);
272
		}
273 274 275 276 277 278 279 280 281 282 283
	}
}

static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
{
	pud_t *pud = pud_offset(pgd, 0);
	unsigned long addr;
	unsigned i;

	for (i = 0; i < PTRS_PER_PUD; i++, pud++) {
		addr = start + i * PUD_SIZE;
284
		if (pud_none(*pud) || pud_sect(*pud)) {
285
			note_page(st, addr, 2, pud_val(*pud));
286 287
		} else {
			BUG_ON(pud_bad(*pud));
288
			walk_pmd(st, pud, addr);
289
		}
290 291 292 293 294
	}
}

static void walk_pgd(struct pg_state *st, struct mm_struct *mm, unsigned long start)
{
295
	pgd_t *pgd = pgd_offset(mm, 0UL);
296 297 298 299 300
	unsigned i;
	unsigned long addr;

	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
		addr = start + i * PGDIR_SIZE;
301
		if (pgd_none(*pgd)) {
302
			note_page(st, addr, 1, pgd_val(*pgd));
303 304
		} else {
			BUG_ON(pgd_bad(*pgd));
305
			walk_pud(st, pgd, addr);
306
		}
307 308 309 310 311 312 313 314 315 316
	}
}

static int ptdump_show(struct seq_file *m, void *v)
{
	struct pg_state st = {
		.seq = m,
		.marker = address_markers,
	};

317
	walk_pgd(&st, &init_mm, VA_START);
318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349

	note_page(&st, 0, 0, 0);
	return 0;
}

static int ptdump_open(struct inode *inode, struct file *file)
{
	return single_open(file, ptdump_show, NULL);
}

static const struct file_operations ptdump_fops = {
	.open		= ptdump_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release,
};

static int ptdump_init(void)
{
	struct dentry *pe;
	unsigned i, j;

	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
		if (pg_level[i].bits)
			for (j = 0; j < pg_level[i].num; j++)
				pg_level[i].mask |= pg_level[i].bits[j].mask;

	pe = debugfs_create_file("kernel_page_tables", 0400, NULL, NULL,
				 &ptdump_fops);
	return pe ? 0 : -ENOMEM;
}
device_initcall(ptdump_init);