page_owner.c 6.7 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12
#include <linux/debugfs.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/bootmem.h>
#include <linux/stacktrace.h>
#include <linux/page_owner.h>
#include "internal.h"

static bool page_owner_disabled = true;
bool page_owner_inited __read_mostly;

13 14
static void init_early_allocated_pages(void);

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
static int early_page_owner_param(char *buf)
{
	if (!buf)
		return -EINVAL;

	if (strcmp(buf, "on") == 0)
		page_owner_disabled = false;

	return 0;
}
early_param("page_owner", early_page_owner_param);

static bool need_page_owner(void)
{
	if (page_owner_disabled)
		return false;

	return true;
}

static void init_page_owner(void)
{
	if (page_owner_disabled)
		return;

	page_owner_inited = true;
41
	init_early_allocated_pages();
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
}

struct page_ext_operations page_owner_ops = {
	.need = need_page_owner,
	.init = init_page_owner,
};

void __reset_page_owner(struct page *page, unsigned int order)
{
	int i;
	struct page_ext *page_ext;

	for (i = 0; i < (1 << order); i++) {
		page_ext = lookup_page_ext(page + i);
		__clear_bit(PAGE_EXT_OWNER, &page_ext->flags);
	}
}

void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask)
{
62 63 64 65 66 67 68
	struct page_ext *page_ext = lookup_page_ext(page);
	struct stack_trace trace = {
		.nr_entries = 0,
		.max_entries = ARRAY_SIZE(page_ext->trace_entries),
		.entries = &page_ext->trace_entries[0],
		.skip = 3,
	};
69

70
	save_stack_trace(&trace);
71 72 73

	page_ext->order = order;
	page_ext->gfp_mask = gfp_mask;
74
	page_ext->nr_entries = trace.nr_entries;
75 76 77 78

	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
}

79 80 81 82 83 84 85
gfp_t __get_page_owner_gfp(struct page *page)
{
	struct page_ext *page_ext = lookup_page_ext(page);

	return page_ext->gfp_mask;
}

86 87 88 89 90 91 92
static ssize_t
print_page_owner(char __user *buf, size_t count, unsigned long pfn,
		struct page *page, struct page_ext *page_ext)
{
	int ret;
	int pageblock_mt, page_mt;
	char *kbuf;
93 94 95 96
	struct stack_trace trace = {
		.nr_entries = page_ext->nr_entries,
		.entries = &page_ext->trace_entries[0],
	};
97 98 99 100 101 102

	kbuf = kmalloc(count, GFP_KERNEL);
	if (!kbuf)
		return -ENOMEM;

	ret = snprintf(kbuf, count,
103 104 105
			"Page allocated via order %u, mask %#x(%pGg)\n",
			page_ext->order, page_ext->gfp_mask,
			&page_ext->gfp_mask);
106 107 108 109 110 111 112 113

	if (ret >= count)
		goto err;

	/* Print information relevant to grouping pages by mobility */
	pageblock_mt = get_pfnblock_migratetype(page, pfn);
	page_mt  = gfpflags_to_migratetype(page_ext->gfp_mask);
	ret += snprintf(kbuf + ret, count - ret,
114
			"PFN %lu type %s Block %lu type %s Flags %#lx(%pGp)\n",
115
			pfn,
116
			migratetype_names[page_mt],
117
			pfn >> pageblock_order,
118 119
			migratetype_names[pageblock_mt],
			page->flags, &page->flags);
120 121 122 123

	if (ret >= count)
		goto err;

124
	ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0);
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
	if (ret >= count)
		goto err;

	ret += snprintf(kbuf + ret, count - ret, "\n");
	if (ret >= count)
		goto err;

	if (copy_to_user(buf, kbuf, ret))
		ret = -EFAULT;

	kfree(kbuf);
	return ret;

err:
	kfree(kbuf);
	return -ENOMEM;
}

static ssize_t
read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos)
{
	unsigned long pfn;
	struct page *page;
	struct page_ext *page_ext;

	if (!page_owner_inited)
		return -EINVAL;

	page = NULL;
	pfn = min_low_pfn + *ppos;

	/* Find a valid PFN or the start of a MAX_ORDER_NR_PAGES area */
	while (!pfn_valid(pfn) && (pfn & (MAX_ORDER_NR_PAGES - 1)) != 0)
		pfn++;

	drain_all_pages(NULL);

	/* Find an allocated page */
	for (; pfn < max_pfn; pfn++) {
		/*
		 * If the new page is in a new MAX_ORDER_NR_PAGES area,
		 * validate the area as existing, skip it if not
		 */
		if ((pfn & (MAX_ORDER_NR_PAGES - 1)) == 0 && !pfn_valid(pfn)) {
			pfn += MAX_ORDER_NR_PAGES - 1;
			continue;
		}

		/* Check for holes within a MAX_ORDER area */
		if (!pfn_valid_within(pfn))
			continue;

		page = pfn_to_page(pfn);
		if (PageBuddy(page)) {
			unsigned long freepage_order = page_order_unsafe(page);

			if (freepage_order < MAX_ORDER)
				pfn += (1UL << freepage_order) - 1;
			continue;
		}

		page_ext = lookup_page_ext(page);

		/*
189 190
		 * Some pages could be missed by concurrent allocation or free,
		 * because we don't hold the zone lock.
191 192 193 194 195 196 197 198 199 200 201 202 203
		 */
		if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags))
			continue;

		/* Record the next PFN to read in the file offset */
		*ppos = (pfn - min_low_pfn) + 1;

		return print_page_owner(buf, count, pfn, page, page_ext);
	}

	return 0;
}

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
static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone)
{
	struct page *page;
	struct page_ext *page_ext;
	unsigned long pfn = zone->zone_start_pfn, block_end_pfn;
	unsigned long end_pfn = pfn + zone->spanned_pages;
	unsigned long count = 0;

	/* Scan block by block. First and last block may be incomplete */
	pfn = zone->zone_start_pfn;

	/*
	 * Walk the zone in pageblock_nr_pages steps. If a page block spans
	 * a zone boundary, it will be double counted between zones. This does
	 * not matter as the mixed block count will still be correct
	 */
	for (; pfn < end_pfn; ) {
		if (!pfn_valid(pfn)) {
			pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES);
			continue;
		}

		block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
		block_end_pfn = min(block_end_pfn, end_pfn);

		page = pfn_to_page(pfn);

		for (; pfn < block_end_pfn; pfn++) {
			if (!pfn_valid_within(pfn))
				continue;

			page = pfn_to_page(pfn);

			/*
			 * We are safe to check buddy flag and order, because
			 * this is init stage and only single thread runs.
			 */
			if (PageBuddy(page)) {
				pfn += (1UL << page_order(page)) - 1;
				continue;
			}

			if (PageReserved(page))
				continue;

			page_ext = lookup_page_ext(page);

			/* Maybe overraping zone */
			if (test_bit(PAGE_EXT_OWNER, &page_ext->flags))
				continue;

			/* Found early allocated page */
			set_page_owner(page, 0, 0);
			count++;
		}
	}

	pr_info("Node %d, zone %8s: page owner found early allocated %lu pages\n",
		pgdat->node_id, zone->name, count);
}

static void init_zones_in_node(pg_data_t *pgdat)
{
	struct zone *zone;
	struct zone *node_zones = pgdat->node_zones;
	unsigned long flags;

	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
		if (!populated_zone(zone))
			continue;

		spin_lock_irqsave(&zone->lock, flags);
		init_pages_in_zone(pgdat, zone);
		spin_unlock_irqrestore(&zone->lock, flags);
	}
}

static void init_early_allocated_pages(void)
{
	pg_data_t *pgdat;

	drain_all_pages(NULL);
	for_each_online_pgdat(pgdat)
		init_zones_in_node(pgdat);
}

290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309
static const struct file_operations proc_page_owner_operations = {
	.read		= read_page_owner,
};

static int __init pageowner_init(void)
{
	struct dentry *dentry;

	if (!page_owner_inited) {
		pr_info("page_owner is disabled\n");
		return 0;
	}

	dentry = debugfs_create_file("page_owner", S_IRUSR, NULL,
			NULL, &proc_page_owner_operations);
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);

	return 0;
}
310
late_initcall(pageowner_init)