page_idle.c 5.48 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0
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
#include <linux/init.h>
#include <linux/bootmem.h>
#include <linux/fs.h>
#include <linux/sysfs.h>
#include <linux/kobject.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/mmu_notifier.h>
#include <linux/page_ext.h>
#include <linux/page_idle.h>

#define BITMAP_CHUNK_SIZE	sizeof(u64)
#define BITMAP_CHUNK_BITS	(BITMAP_CHUNK_SIZE * BITS_PER_BYTE)

/*
 * Idle page tracking only considers user memory pages, for other types of
 * pages the idle flag is always unset and an attempt to set it is silently
 * ignored.
 *
 * We treat a page as a user memory page if it is on an LRU list, because it is
 * always safe to pass such a page to rmap_walk(), which is essential for idle
 * page tracking. With such an indicator of user pages we can skip isolated
 * pages, but since there are not usually many of them, it will hardly affect
 * the overall result.
 *
 * This function tries to get a user memory page by pfn as described above.
 */
static struct page *page_idle_get_page(unsigned long pfn)
{
	struct page *page;
	struct zone *zone;

	if (!pfn_valid(pfn))
		return NULL;

	page = pfn_to_page(pfn);
	if (!page || !PageLRU(page) ||
	    !get_page_unless_zero(page))
		return NULL;

	zone = page_zone(page);
45
	spin_lock_irq(zone_lru_lock(zone));
46 47 48 49
	if (unlikely(!PageLRU(page))) {
		put_page(page);
		page = NULL;
	}
50
	spin_unlock_irq(zone_lru_lock(zone));
51 52 53
	return page;
}

54
static bool page_idle_clear_pte_refs_one(struct page *page,
55 56 57
					struct vm_area_struct *vma,
					unsigned long addr, void *arg)
{
58 59 60 61 62
	struct page_vma_mapped_walk pvmw = {
		.page = page,
		.vma = vma,
		.address = addr,
	};
63 64
	bool referenced = false;

65 66 67
	while (page_vma_mapped_walk(&pvmw)) {
		addr = pvmw.address;
		if (pvmw.pte) {
68 69 70 71 72 73
			/*
			 * For PTE-mapped THP, one sub page is referenced,
			 * the whole THP is referenced.
			 */
			if (ptep_clear_young_notify(vma, addr, pvmw.pte))
				referenced = true;
74
		} else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) {
75 76
			if (pmdp_clear_young_notify(vma, addr, pvmw.pmd))
				referenced = true;
77 78 79 80
		} else {
			/* unexpected pmd-mapped page? */
			WARN_ON_ONCE(1);
		}
81
	}
82

83 84 85 86 87 88 89 90 91
	if (referenced) {
		clear_page_idle(page);
		/*
		 * We cleared the referenced bit in a mapping to this page. To
		 * avoid interference with page reclaim, mark it young so that
		 * page_referenced() will return > 0.
		 */
		set_page_young(page);
	}
92
	return true;
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
}

static void page_idle_clear_pte_refs(struct page *page)
{
	/*
	 * Since rwc.arg is unused, rwc is effectively immutable, so we
	 * can make it static const to save some cycles and stack.
	 */
	static const struct rmap_walk_control rwc = {
		.rmap_one = page_idle_clear_pte_refs_one,
		.anon_lock = page_lock_anon_vma_read,
	};
	bool need_lock;

	if (!page_mapped(page) ||
	    !page_rmapping(page))
		return;

	need_lock = !PageAnon(page) || PageKsm(page);
	if (need_lock && !trylock_page(page))
		return;

	rmap_walk(page, (struct rmap_walk_control *)&rwc);

	if (need_lock)
		unlock_page(page);
}

static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj,
				     struct bin_attribute *attr, char *buf,
				     loff_t pos, size_t count)
{
	u64 *out = (u64 *)buf;
	struct page *page;
	unsigned long pfn, end_pfn;
	int bit;

	if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
		return -EINVAL;

	pfn = pos * BITS_PER_BYTE;
	if (pfn >= max_pfn)
		return 0;

	end_pfn = pfn + count * BITS_PER_BYTE;
	if (end_pfn > max_pfn)
139
		end_pfn = max_pfn;
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

	for (; pfn < end_pfn; pfn++) {
		bit = pfn % BITMAP_CHUNK_BITS;
		if (!bit)
			*out = 0ULL;
		page = page_idle_get_page(pfn);
		if (page) {
			if (page_is_idle(page)) {
				/*
				 * The page might have been referenced via a
				 * pte, in which case it is not idle. Clear
				 * refs and recheck.
				 */
				page_idle_clear_pte_refs(page);
				if (page_is_idle(page))
					*out |= 1ULL << bit;
			}
			put_page(page);
		}
		if (bit == BITMAP_CHUNK_BITS - 1)
			out++;
		cond_resched();
	}
	return (char *)out - buf;
}

static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj,
				      struct bin_attribute *attr, char *buf,
				      loff_t pos, size_t count)
{
	const u64 *in = (u64 *)buf;
	struct page *page;
	unsigned long pfn, end_pfn;
	int bit;

	if (pos % BITMAP_CHUNK_SIZE || count % BITMAP_CHUNK_SIZE)
		return -EINVAL;

	pfn = pos * BITS_PER_BYTE;
	if (pfn >= max_pfn)
		return -ENXIO;

	end_pfn = pfn + count * BITS_PER_BYTE;
	if (end_pfn > max_pfn)
184
		end_pfn = max_pfn;
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

	for (; pfn < end_pfn; pfn++) {
		bit = pfn % BITMAP_CHUNK_BITS;
		if ((*in >> bit) & 1) {
			page = page_idle_get_page(pfn);
			if (page) {
				page_idle_clear_pte_refs(page);
				set_page_idle(page);
				put_page(page);
			}
		}
		if (bit == BITMAP_CHUNK_BITS - 1)
			in++;
		cond_resched();
	}
	return (char *)in - buf;
}

static struct bin_attribute page_idle_bitmap_attr =
		__BIN_ATTR(bitmap, S_IRUSR | S_IWUSR,
			   page_idle_bitmap_read, page_idle_bitmap_write, 0);

static struct bin_attribute *page_idle_bin_attrs[] = {
	&page_idle_bitmap_attr,
	NULL,
};

212
static const struct attribute_group page_idle_attr_group = {
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
	.bin_attrs = page_idle_bin_attrs,
	.name = "page_idle",
};

#ifndef CONFIG_64BIT
static bool need_page_idle(void)
{
	return true;
}
struct page_ext_operations page_idle_ops = {
	.need = need_page_idle,
};
#endif

static int __init page_idle_init(void)
{
	int err;

	err = sysfs_create_group(mm_kobj, &page_idle_attr_group);
	if (err) {
		pr_err("page_idle: register sysfs failed\n");
		return err;
	}
	return 0;
}
subsys_initcall(page_idle_init);