1 files changed, 141 insertions, 296 deletions

diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index a9ff35341d65..07a8aead439e 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * DAMON Primitives for The Physical Address Space
+ * DAMON Code for The Physical Address Space
  *
  * Author: SeongJae Park <sj@kernel.org>
  */
@@ -13,52 +13,31 @@
 #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)
+static phys_addr_t damon_pa_phys_addr(
+		unsigned long addr, unsigned long addr_unit)
 {
-	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;
+	return (phys_addr_t)addr * addr_unit;
 }
 
-static void damon_folio_mkold(struct folio *folio)
+static unsigned long damon_pa_core_addr(
+		phys_addr_t pa, unsigned long addr_unit)
 {
-	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);
-
+	/*
+	 * Use div_u64() for avoiding linking errors related with __udivdi3,
+	 * __aeabi_uldivmod, or similar problems.  This should also improve the
+	 * performance optimization (read div_u64() comment for the detail).
+	 */
+	if (sizeof(pa) == 8 && sizeof(addr_unit) == 4)
+		return div_u64(pa, addr_unit);
+	return pa / addr_unit;
 }
 
-static void damon_pa_mkold(unsigned long paddr)
+static void damon_pa_mkold(phys_addr_t paddr)
 {
 	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));
 
@@ -69,11 +48,12 @@ static void damon_pa_mkold(unsigned long paddr)
 	folio_put(folio);
 }
 
-static void __damon_pa_prepare_access_check(struct damon_region *r)
+static void __damon_pa_prepare_access_check(struct damon_region *r,
+		unsigned long addr_unit)
 {
 	r->sampling_addr = damon_rand(r->ar.start, r->ar.end);
 
-	damon_pa_mkold(r->sampling_addr);
+	damon_pa_mkold(damon_pa_phys_addr(r->sampling_addr, addr_unit));
 }
 
 static void damon_pa_prepare_access_checks(struct damon_ctx *ctx)
@@ -83,72 +63,11 @@ static void damon_pa_prepare_access_checks(struct damon_ctx *ctx)
 
 	damon_for_each_target(t, ctx) {
 		damon_for_each_region(r, t)
-			__damon_pa_prepare_access_check(r);
+			__damon_pa_prepare_access_check(r, ctx->addr_unit);
 	}
 }
 
-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)
+static bool damon_pa_young(phys_addr_t paddr, unsigned long *folio_sz)
 {
 	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));
 	bool accessed;
@@ -163,23 +82,25 @@ static bool damon_pa_young(unsigned long paddr, unsigned long *folio_sz)
 }
 
 static void __damon_pa_check_access(struct damon_region *r,
-		struct damon_attrs *attrs)
+		struct damon_attrs *attrs, unsigned long addr_unit)
 {
-	static unsigned long last_addr;
+	static phys_addr_t last_addr;
 	static unsigned long last_folio_sz = PAGE_SIZE;
 	static bool last_accessed;
+	phys_addr_t sampling_addr = damon_pa_phys_addr(
+			r->sampling_addr, addr_unit);
 
 	/* 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)) {
+				ALIGN_DOWN(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);
+	last_accessed = damon_pa_young(sampling_addr, &last_folio_sz);
 	damon_update_region_access_rate(r, last_accessed, attrs);
 
-	last_addr = r->sampling_addr;
+	last_addr = sampling_addr;
 }
 
 static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
@@ -190,7 +111,8 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
 
 	damon_for_each_target(t, ctx) {
 		damon_for_each_region(r, t) {
-			__damon_pa_check_access(r, &ctx->attrs);
+			__damon_pa_check_access(
+					r, &ctx->attrs, ctx->addr_unit);
 			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
 		}
 	}
@@ -198,37 +120,6 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
 	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.
  */
@@ -236,42 +127,64 @@ 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;
+	if (scheme->core_filters_allowed)
+		return false;
+
+	damos_for_each_ops_filter(filter, scheme) {
+		if (damos_folio_filter_match(filter, folio))
+			return !filter->allow;
+	}
+	return scheme->ops_filters_default_reject;
+}
+
+static bool damon_pa_invalid_damos_folio(struct folio *folio, struct damos *s)
+{
+	if (!folio)
+		return true;
+	if (folio == s->last_applied) {
+		folio_put(folio);
+		return true;
 	}
 	return false;
 }
 
-static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s)
+static unsigned long damon_pa_pageout(struct damon_region *r,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
 {
-	unsigned long addr, applied;
+	phys_addr_t addr, applied;
 	LIST_HEAD(folio_list);
 	bool install_young_filter = true;
 	struct damos_filter *filter;
+	struct folio *folio;
 
 	/* check access in page level again by default */
-	damos_for_each_filter(filter, s) {
+	damos_for_each_ops_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);
+		filter = damos_new_filter(
+				DAMOS_FILTER_TYPE_YOUNG, true, false);
 		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)
+	addr = damon_pa_phys_addr(r->ar.start, addr_unit);
+	while (addr < damon_pa_phys_addr(r->ar.end, addr_unit)) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
+			addr += PAGE_SIZE;
 			continue;
+		}
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
+		else
+			*sz_filter_passed += folio_size(folio) / addr_unit;
 
 		folio_clear_referenced(folio);
 		folio_test_clear_young(folio);
@@ -282,28 +195,37 @@ static unsigned long damon_pa_pageout(struct damon_region *r, struct damos *s)
 		else
 			list_add(&folio->lru, &folio_list);
 put_folio:
+		addr += folio_size(folio);
 		folio_put(folio);
 	}
 	if (install_young_filter)
 		damos_destroy_filter(filter);
 	applied = reclaim_pages(&folio_list);
 	cond_resched();
-	return applied * PAGE_SIZE;
+	s->last_applied = folio;
+	return damon_pa_core_addr(applied * PAGE_SIZE, addr_unit);
 }
 
 static inline unsigned long damon_pa_mark_accessed_or_deactivate(
-		struct damon_region *r, struct damos *s, bool mark_accessed)
+		struct damon_region *r, unsigned long addr_unit,
+		struct damos *s, bool mark_accessed,
+		unsigned long *sz_filter_passed)
 {
-	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));
+	phys_addr_t addr, applied = 0;
+	struct folio *folio;
 
-		if (!folio)
+	addr = damon_pa_phys_addr(r->ar.start, addr_unit);
+	while (addr < damon_pa_phys_addr(r->ar.end, addr_unit)) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
+			addr += PAGE_SIZE;
 			continue;
+		}
 
 		if (damos_pa_filter_out(s, folio))
 			goto put_folio;
+		else
+			*sz_filter_passed += folio_size(folio) / addr_unit;
 
 		if (mark_accessed)
 			folio_mark_accessed(folio);
@@ -311,186 +233,110 @@ static inline unsigned long damon_pa_mark_accessed_or_deactivate(
 			folio_deactivate(folio);
 		applied += folio_nr_pages(folio);
 put_folio:
+		addr += folio_size(folio);
 		folio_put(folio);
 	}
-	return applied * PAGE_SIZE;
+	s->last_applied = folio;
+	return damon_pa_core_addr(applied * PAGE_SIZE, addr_unit);
 }
 
 static unsigned long damon_pa_mark_accessed(struct damon_region *r,
-	struct damos *s)
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
 {
-	return damon_pa_mark_accessed_or_deactivate(r, s, true);
+	return damon_pa_mark_accessed_or_deactivate(r, addr_unit, s, true,
+			sz_filter_passed);
 }
 
 static unsigned long damon_pa_deactivate_pages(struct damon_region *r,
-	struct damos *s)
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
 {
-	return damon_pa_mark_accessed_or_deactivate(r, s, false);
+	return damon_pa_mark_accessed_or_deactivate(r, addr_unit, s, false,
+			sz_filter_passed);
 }
 
-static unsigned int __damon_pa_migrate_folio_list(
-		struct list_head *migrate_folios, struct pglist_data *pgdat,
-		int target_nid)
+static unsigned long damon_pa_migrate(struct damon_region *r,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
 {
-	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;
+	phys_addr_t addr, applied;
+	LIST_HEAD(folio_list);
 	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);
+	addr = damon_pa_phys_addr(r->ar.start, addr_unit);
+	while (addr < damon_pa_phys_addr(r->ar.end, addr_unit)) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
+			addr += PAGE_SIZE;
 			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;
+		else
+			*sz_filter_passed += folio_size(folio) / addr_unit;
 
 		if (!folio_isolate_lru(folio))
 			goto put_folio;
 		list_add(&folio->lru, &folio_list);
 put_folio:
+		addr += folio_size(folio);
 		folio_put(folio);
 	}
-	applied = damon_pa_migrate_pages(&folio_list, s->target_nid);
+	applied = damon_migrate_pages(&folio_list, s->target_nid);
 	cond_resched();
-	return applied * PAGE_SIZE;
+	s->last_applied = folio;
+	return damon_pa_core_addr(applied * PAGE_SIZE, addr_unit);
 }
 
+static unsigned long damon_pa_stat(struct damon_region *r,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	phys_addr_t addr;
+	struct folio *folio;
+
+	if (!damos_ops_has_filter(s))
+		return 0;
+
+	addr = damon_pa_phys_addr(r->ar.start, addr_unit);
+	while (addr < damon_pa_phys_addr(r->ar.end, addr_unit)) {
+		folio = damon_get_folio(PHYS_PFN(addr));
+		if (damon_pa_invalid_damos_folio(folio, s)) {
+			addr += PAGE_SIZE;
+			continue;
+		}
+
+		if (!damos_pa_filter_out(s, folio))
+			*sz_filter_passed += folio_size(folio) / addr_unit;
+		addr += folio_size(folio);
+		folio_put(folio);
+	}
+	s->last_applied = folio;
+	return 0;
+}
 
 static unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
 		struct damon_target *t, struct damon_region *r,
-		struct damos *scheme)
+		struct damos *scheme, unsigned long *sz_filter_passed)
 {
+	unsigned long aunit = ctx->addr_unit;
+
 	switch (scheme->action) {
 	case DAMOS_PAGEOUT:
-		return damon_pa_pageout(r, scheme);
+		return damon_pa_pageout(r, aunit, scheme, sz_filter_passed);
 	case DAMOS_LRU_PRIO:
-		return damon_pa_mark_accessed(r, scheme);
+		return damon_pa_mark_accessed(r, aunit, scheme,
+				sz_filter_passed);
 	case DAMOS_LRU_DEPRIO:
-		return damon_pa_deactivate_pages(r, scheme);
+		return damon_pa_deactivate_pages(r, aunit, scheme,
+				sz_filter_passed);
 	case DAMOS_MIGRATE_HOT:
 	case DAMOS_MIGRATE_COLD:
-		return damon_pa_migrate(r, scheme);
+		return damon_pa_migrate(r, aunit, scheme, sz_filter_passed);
 	case DAMOS_STAT:
-		break;
+		return damon_pa_stat(r, aunit, scheme, sz_filter_passed);
 	default:
 		/* DAMOS actions that not yet supported by 'paddr'. */
 		break;
@@ -528,7 +374,6 @@ static int __init damon_pa_initcall(void)
 		.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,