Contributors: 11
Author Tokens Token Proportion Commits Commit Proportion
SeongJae Park 1596 70.81% 31 65.96%
Honggyu Kim 481 21.34% 1 2.13%
Matthew Wilcox 76 3.37% 4 8.51%
Kefeng Wang 69 3.06% 3 6.38%
Vishal Moola (Oracle) 12 0.53% 2 4.26%
Xin Hao 5 0.22% 1 2.13%
Hyeongtak Ji 4 0.18% 1 2.13%
Levi Yun 3 0.13% 1 2.13%
Xia Kaixu 3 0.13% 1 2.13%
Ryan Roberts 3 0.13% 1 2.13%
Baolin Wang 2 0.09% 1 2.13%
Total 2254 47 
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541
// SPDX-License-Identifier: GPL-2.0
/*
 * DAMON Primitives for The Physical Address Space
 *
 * Author: SeongJae Park <sj@kernel.org>
 */

#define pr_fmt(fmt) "damon-pa: " fmt

#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
#include <linux/pagemap.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/memory-tiers.h>
#include <linux/migrate.h>
#include <linux/mm_inline.h>

#include "../internal.h"
#include "ops-common.h"

static bool damon_folio_mkold_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long addr, void *arg)
{
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0);

	while (page_vma_mapped_walk(&pvmw)) {
		addr = pvmw.address;
		if (pvmw.pte)
			damon_ptep_mkold(pvmw.pte, vma, addr);
		else
			damon_pmdp_mkold(pvmw.pmd, vma, addr);
	}
	return true;
}

static void damon_folio_mkold(struct folio *folio)
{
	struct rmap_walk_control rwc = {
		.rmap_one = damon_folio_mkold_one,
		.anon_lock = folio_lock_anon_vma_read,
	};
	bool need_lock;

	if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
		folio_set_idle(folio);
		return;
	}

	need_lock = !folio_test_anon(folio) || folio_test_ksm(folio);
	if (need_lock && !folio_trylock(folio))
		return;

	rmap_walk(folio, &rwc);

	if (need_lock)
		folio_unlock(folio);

}

static void damon_pa_mkold(unsigned long paddr)
{
	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));

	if (!folio)
		return;

	damon_folio_mkold(folio);
	folio_put(folio);
}

static void __damon_pa_prepare_access_check(struct damon_region *r)
{
	r->sampling_addr = damon_rand(r->ar.start, r->ar.end);

	damon_pa_mkold(r->sampling_addr);
}

static void damon_pa_prepare_access_checks(struct damon_ctx *ctx)
{
	struct damon_target *t;
	struct damon_region *r;

	damon_for_each_target(t, ctx) {
		damon_for_each_region(r, t)
			__damon_pa_prepare_access_check(r);
	}
}

static bool damon_folio_young_one(struct folio *folio,
		struct vm_area_struct *vma, unsigned long addr, void *arg)
{
	bool *accessed = arg;
	DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, addr, 0);

	*accessed = false;
	while (page_vma_mapped_walk(&pvmw)) {
		addr = pvmw.address;
		if (pvmw.pte) {
			*accessed = pte_young(ptep_get(pvmw.pte)) ||
				!folio_test_idle(folio) ||
				mmu_notifier_test_young(vma->vm_mm, addr);
		} else {
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
			*accessed = pmd_young(pmdp_get(pvmw.pmd)) ||
				!folio_test_idle(folio) ||
				mmu_notifier_test_young(vma->vm_mm, addr);
#else
			WARN_ON_ONCE(1);
#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
		}
		if (*accessed) {
			page_vma_mapped_walk_done(&pvmw);
			break;
		}
	}

	/* If accessed, stop walking */
	return *accessed == false;
}

static bool damon_folio_young(struct folio *folio)
{
	bool accessed = false;
	struct rmap_walk_control rwc = {
		.arg = &accessed,
		.rmap_one = damon_folio_young_one,
		.anon_lock = folio_lock_anon_vma_read,
	};
	bool need_lock;

	if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
		if (folio_test_idle(folio))
			return false;
		else
			return true;
	}

	need_lock = !folio_test_anon(folio) || folio_test_ksm(folio);
	if (need_lock && !folio_trylock(folio))
		return false;

	rmap_walk(folio, &rwc);

	if (need_lock)
		folio_unlock(folio);

	return accessed;
}

static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz)
{
	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));
	bool accessed;

	if (!folio)
		return false;

	accessed = damon_folio_young(folio);
	*folio_sz = folio_size(folio);
	folio_put(folio);
	return accessed;
}

static void __damon_pa_check_access(struct damon_region *r,
		struct damon_attrs *attrs)
{
	static unsigned long last_addr;
	static unsigned long last_folio_sz = PAGE_SIZE;
	static bool last_accessed;

	/* If the region is in the last checked page, reuse the result */
	if (ALIGN_DOWN(last_addr, last_folio_sz) ==
				ALIGN_DOWN(r->sampling_addr, last_folio_sz)) {
		damon_update_region_access_rate(r, last_accessed, attrs);
		return;
	}

	last_accessed = damon_pa_young(r->sampling_addr, &last_folio_sz);
	damon_update_region_access_rate(r, last_accessed, attrs);

	last_addr = r->sampling_addr;
}

static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
{
	struct damon_target *t;
	struct damon_region *r;
	unsigned int max_nr_accesses = 0;

	damon_for_each_target(t, ctx) {
		damon_for_each_region(r, t) {
			__damon_pa_check_access(r, &ctx->attrs);
			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
		}
	}

	return max_nr_accesses;
}

static bool __damos_pa_filter_out(struct damos_filter *filter,
		struct folio *folio)
{
	bool matched = false;
	struct mem_cgroup *memcg;

	switch (filter->type) {
	case DAMOS_FILTER_TYPE_ANON:
		matched = folio_test_anon(folio);
		break;
	case DAMOS_FILTER_TYPE_MEMCG:
		rcu_read_lock();
		memcg = folio_memcg_check(folio);
		if (!memcg)
			matched = false;
		else
			matched = filter->memcg_id == mem_cgroup_id(memcg);
		rcu_read_unlock();
		break;
	case DAMOS_FILTER_TYPE_YOUNG:
		matched = damon_folio_young(folio);
		if (matched)
			damon_folio_mkold(folio);
		break;
	default:
		break;
	}

	return matched == filter->matching;
}

/*
 * damos_pa_filter_out - Return true if the page should be filtered out.
 */
static bool damos_pa_filter_out(struct damos *scheme, struct folio *folio)
{
	struct damos_filter *filter;

	damos_for_each_filter(filter, scheme) {
		if (__damos_pa_filter_out(filter, folio))
			return true;
	}
	return false;
}

static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s)
{
	unsigned long addr, applied;
	LIST_HEAD(folio_list);
	bool install_young_filter = true;
	struct damos_filter *filter;

	/* check access in page level again by default */
	damos_for_each_filter(filter, s) {
		if (filter->type == DAMOS_FILTER_TYPE_YOUNG) {
			install_young_filter = false;
			break;
		}
	}
	if (install_young_filter) {
		filter = damos_new_filter(DAMOS_FILTER_TYPE_YOUNG, true);
		if (!filter)
			return 0;
		damos_add_filter(s, filter);
	}

	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
		struct folio *folio = damon_get_folio(PHYS_PFN(addr));

		if (!folio)
			continue;

		if (damos_pa_filter_out(s, folio))
			goto put_folio;

		folio_clear_referenced(folio);
		folio_test_clear_young(folio);
		if (!folio_isolate_lru(folio))
			goto put_folio;
		if (folio_test_unevictable(folio))
			folio_putback_lru(folio);
		else
			list_add(&folio->lru, &folio_list);
put_folio:
		folio_put(folio);
	}
	if (install_young_filter)
		damos_destroy_filter(filter);
	applied = reclaim_pages(&folio_list);
	cond_resched();
	return applied * PAGE_SIZE;
}

static inline unsigned long damon_pa_mark_accessed_or_deactivate(
		struct damon_region *r, struct damos *s, bool mark_accessed)
{
	unsigned long addr, applied = 0;

	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
		struct folio *folio = damon_get_folio(PHYS_PFN(addr));

		if (!folio)
			continue;

		if (damos_pa_filter_out(s, folio))
			goto put_folio;

		if (mark_accessed)
			folio_mark_accessed(folio);
		else
			folio_deactivate(folio);
		applied += folio_nr_pages(folio);
put_folio:
		folio_put(folio);
	}
	return applied * PAGE_SIZE;
}

static unsigned long damon_pa_mark_accessed(struct damon_region *r,
	struct damos *s)
{
	return damon_pa_mark_accessed_or_deactivate(r, s, true);
}

static unsigned long damon_pa_deactivate_pages(struct damon_region *r,
	struct damos *s)
{
	return damon_pa_mark_accessed_or_deactivate(r, s, false);
}

static unsigned int __damon_pa_migrate_folio_list(
		struct list_head *migrate_folios, struct pglist_data *pgdat,
		int target_nid)
{
	unsigned int nr_succeeded = 0;
	nodemask_t allowed_mask = NODE_MASK_NONE;
	struct migration_target_control mtc = {
		/*
		 * Allocate from 'node', or fail quickly and quietly.
		 * When this happens, 'page' will likely just be discarded
		 * instead of migrated.
		 */
		.gfp_mask = (GFP_HIGHUSER_MOVABLE & ~__GFP_RECLAIM) |
			__GFP_NOWARN | __GFP_NOMEMALLOC | GFP_NOWAIT,
		.nid = target_nid,
		.nmask = &allowed_mask
	};

	if (pgdat->node_id == target_nid || target_nid == NUMA_NO_NODE)
		return 0;

	if (list_empty(migrate_folios))
		return 0;

	/* Migration ignores all cpuset and mempolicy settings */
	migrate_pages(migrate_folios, alloc_migrate_folio, NULL,
		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DAMON,
		      &nr_succeeded);

	return nr_succeeded;
}

static unsigned int damon_pa_migrate_folio_list(struct list_head *folio_list,
						struct pglist_data *pgdat,
						int target_nid)
{
	unsigned int nr_migrated = 0;
	struct folio *folio;
	LIST_HEAD(ret_folios);
	LIST_HEAD(migrate_folios);

	while (!list_empty(folio_list)) {
		struct folio *folio;

		cond_resched();

		folio = lru_to_folio(folio_list);
		list_del(&folio->lru);

		if (!folio_trylock(folio))
			goto keep;

		/* Relocate its contents to another node. */
		list_add(&folio->lru, &migrate_folios);
		folio_unlock(folio);
		continue;
keep:
		list_add(&folio->lru, &ret_folios);
	}
	/* 'folio_list' is always empty here */

	/* Migrate folios selected for migration */
	nr_migrated += __damon_pa_migrate_folio_list(
			&migrate_folios, pgdat, target_nid);
	/*
	 * Folios that could not be migrated are still in @migrate_folios.  Add
	 * those back on @folio_list
	 */
	if (!list_empty(&migrate_folios))
		list_splice_init(&migrate_folios, folio_list);

	try_to_unmap_flush();

	list_splice(&ret_folios, folio_list);

	while (!list_empty(folio_list)) {
		folio = lru_to_folio(folio_list);
		list_del(&folio->lru);
		folio_putback_lru(folio);
	}

	return nr_migrated;
}

static unsigned long damon_pa_migrate_pages(struct list_head *folio_list,
					    int target_nid)
{
	int nid;
	unsigned long nr_migrated = 0;
	LIST_HEAD(node_folio_list);
	unsigned int noreclaim_flag;

	if (list_empty(folio_list))
		return nr_migrated;

	noreclaim_flag = memalloc_noreclaim_save();

	nid = folio_nid(lru_to_folio(folio_list));
	do {
		struct folio *folio = lru_to_folio(folio_list);

		if (nid == folio_nid(folio)) {
			list_move(&folio->lru, &node_folio_list);
			continue;
		}

		nr_migrated += damon_pa_migrate_folio_list(&node_folio_list,
							   NODE_DATA(nid),
							   target_nid);
		nid = folio_nid(lru_to_folio(folio_list));
	} while (!list_empty(folio_list));

	nr_migrated += damon_pa_migrate_folio_list(&node_folio_list,
						   NODE_DATA(nid),
						   target_nid);

	memalloc_noreclaim_restore(noreclaim_flag);

	return nr_migrated;
}

static unsigned long damon_pa_migrate(struct damon_region *r, struct damos *s)
{
	unsigned long addr, applied;
	LIST_HEAD(folio_list);

	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
		struct folio *folio = damon_get_folio(PHYS_PFN(addr));

		if (!folio)
			continue;

		if (damos_pa_filter_out(s, folio))
			goto put_folio;

		if (!folio_isolate_lru(folio))
			goto put_folio;
		list_add(&folio->lru, &folio_list);
put_folio:
		folio_put(folio);
	}
	applied = damon_pa_migrate_pages(&folio_list, s->target_nid);
	cond_resched();
	return applied * PAGE_SIZE;
}


static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
		struct damon_target *t, struct damon_region *r,
		struct damos *scheme)
{
	switch (scheme->action) {
	case DAMOS_PAGEOUT:
		return damon_pa_pageout(r, scheme);
	case DAMOS_LRU_PRIO:
		return damon_pa_mark_accessed(r, scheme);
	case DAMOS_LRU_DEPRIO:
		return damon_pa_deactivate_pages(r, scheme);
	case DAMOS_MIGRATE_HOT:
	case DAMOS_MIGRATE_COLD:
		return damon_pa_migrate(r, scheme);
	case DAMOS_STAT:
		break;
	default:
		/* DAMOS actions that not yet supported by 'paddr'. */
		break;
	}
	return 0;
}

static int damon_pa_scheme_score(struct damon_ctx *context,
		struct damon_target *t, struct damon_region *r,
		struct damos *scheme)
{
	switch (scheme->action) {
	case DAMOS_PAGEOUT:
		return damon_cold_score(context, r, scheme);
	case DAMOS_LRU_PRIO:
		return damon_hot_score(context, r, scheme);
	case DAMOS_LRU_DEPRIO:
		return damon_cold_score(context, r, scheme);
	case DAMOS_MIGRATE_HOT:
		return damon_hot_score(context, r, scheme);
	case DAMOS_MIGRATE_COLD:
		return damon_cold_score(context, r, scheme);
	default:
		break;
	}

	return DAMOS_MAX_SCORE;
}

static int __init damon_pa_initcall(void)
{
	struct damon_operations ops = {
		.id = DAMON_OPS_PADDR,
		.init = NULL,
		.update = NULL,
		.prepare_access_checks = damon_pa_prepare_access_checks,
		.check_accesses = damon_pa_check_accesses,
		.reset_aggregated = NULL,
		.target_valid = NULL,
		.cleanup = NULL,
		.apply_scheme = damon_pa_apply_scheme,
		.get_scheme_score = damon_pa_scheme_score,
	};

	return damon_register_ops(&ops);
};

subsys_initcall(damon_pa_initcall);