1 files changed, 285 insertions, 174 deletions

diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 5e8244f65a1a..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>
  */
@@ -12,65 +12,48 @@
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
+#include <linux/memory-tiers.h>
+#include <linux/mm_inline.h>
 
 #include "../internal.h"
-#include "prmtv-common.h"
+#include "ops-common.h"
 
-static bool __damon_pa_mkold(struct page *page, 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)
 {
-	struct page_vma_mapped_walk pvmw = {
-		.page = page,
-		.vma = vma,
-		.address = addr,
-	};
+	return (phys_addr_t)addr * addr_unit;
+}
 
-	while (page_vma_mapped_walk(&pvmw)) {
-		addr = pvmw.address;
-		if (pvmw.pte)
-			damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
-		else
-			damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
-	}
-	return true;
+static unsigned long damon_pa_core_addr(
+		phys_addr_t pa, unsigned long addr_unit)
+{
+	/*
+	 * 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 page *page = damon_get_page(PHYS_PFN(paddr));
-	struct rmap_walk_control rwc = {
-		.rmap_one = __damon_pa_mkold,
-		.anon_lock = page_lock_anon_vma_read,
-	};
-	bool need_lock;
+	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));
 
-	if (!page)
+	if (!folio)
 		return;
 
-	if (!page_mapped(page) || !page_rmapping(page)) {
-		set_page_idle(page);
-		goto out;
-	}
-
-	need_lock = !PageAnon(page) || PageKsm(page);
-	if (need_lock && !trylock_page(page))
-		goto out;
-
-	rmap_walk(page, &rwc);
-
-	if (need_lock)
-		unlock_page(page);
-
-out:
-	put_page(page);
+	damon_folio_mkold(folio);
+	folio_put(folio);
 }
 
-static void __damon_pa_prepare_access_check(struct damon_ctx *ctx,
-					    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)
@@ -80,116 +63,44 @@ 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(ctx, r);
-	}
-}
-
-struct damon_pa_access_chk_result {
-	unsigned long page_sz;
-	bool accessed;
-};
-
-static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma,
-		unsigned long addr, void *arg)
-{
-	struct damon_pa_access_chk_result *result = arg;
-	struct page_vma_mapped_walk pvmw = {
-		.page = page,
-		.vma = vma,
-		.address = addr,
-	};
-
-	result->accessed = false;
-	result->page_sz = PAGE_SIZE;
-	while (page_vma_mapped_walk(&pvmw)) {
-		addr = pvmw.address;
-		if (pvmw.pte) {
-			result->accessed = pte_young(*pvmw.pte) ||
-				!page_is_idle(page) ||
-				mmu_notifier_test_young(vma->vm_mm, addr);
-		} else {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-			result->accessed = pmd_young(*pvmw.pmd) ||
-				!page_is_idle(page) ||
-				mmu_notifier_test_young(vma->vm_mm, addr);
-			result->page_sz = ((1UL) << HPAGE_PMD_SHIFT);
-#else
-			WARN_ON_ONCE(1);
-#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
-		}
-		if (result->accessed) {
-			page_vma_mapped_walk_done(&pvmw);
-			break;
-		}
+			__damon_pa_prepare_access_check(r, ctx->addr_unit);
 	}
-
-	/* If accessed, stop walking */
-	return !result->accessed;
 }
 
-static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz)
+static bool damon_pa_young(phys_addr_t paddr, unsigned long *folio_sz)
 {
-	struct page *page = damon_get_page(PHYS_PFN(paddr));
-	struct damon_pa_access_chk_result result = {
-		.page_sz = PAGE_SIZE,
-		.accessed = false,
-	};
-	struct rmap_walk_control rwc = {
-		.arg = &result,
-		.rmap_one = __damon_pa_young,
-		.anon_lock = page_lock_anon_vma_read,
-	};
-	bool need_lock;
+	struct folio *folio = damon_get_folio(PHYS_PFN(paddr));
+	bool accessed;
 
-	if (!page)
+	if (!folio)
 		return false;
 
-	if (!page_mapped(page) || !page_rmapping(page)) {
-		if (page_is_idle(page))
-			result.accessed = false;
-		else
-			result.accessed = true;
-		put_page(page);
-		goto out;
-	}
-
-	need_lock = !PageAnon(page) || PageKsm(page);
-	if (need_lock && !trylock_page(page)) {
-		put_page(page);
-		return NULL;
-	}
-
-	rmap_walk(page, &rwc);
-
-	if (need_lock)
-		unlock_page(page);
-	put_page(page);
-
-out:
-	*page_sz = result.page_sz;
-	return result.accessed;
+	accessed = damon_folio_young(folio);
+	*folio_sz = folio_size(folio);
+	folio_put(folio);
+	return accessed;
 }
 
-static void __damon_pa_check_access(struct damon_ctx *ctx,
-				    struct damon_region *r)
+static void __damon_pa_check_access(struct damon_region *r,
+		struct damon_attrs *attrs, unsigned long addr_unit)
 {
-	static unsigned long last_addr;
-	static unsigned long last_page_sz = PAGE_SIZE;
+	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_page_sz) ==
-				ALIGN_DOWN(r->sampling_addr, last_page_sz)) {
-		if (last_accessed)
-			r->nr_accesses++;
+	if (ALIGN_DOWN(last_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_page_sz);
-	if (last_accessed)
-		r->nr_accesses++;
+	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)
@@ -200,7 +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(ctx, r);
+			__damon_pa_check_access(
+					r, &ctx->attrs, ctx->addr_unit);
 			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
 		}
 	}
@@ -208,43 +120,228 @@ static unsigned int damon_pa_check_accesses(struct damon_ctx *ctx)
 	return max_nr_accesses;
 }
 
-bool damon_pa_target_valid(void *t)
+/*
+ * 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)
 {
-	return true;
+	struct damos_filter *filter;
+
+	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 unsigned long damon_pa_apply_scheme(struct damon_ctx *ctx,
-		struct damon_target *t, struct damon_region *r,
-		struct damos *scheme)
+static bool damon_pa_invalid_damos_folio(struct folio *folio, struct damos *s)
 {
-	unsigned long addr, applied;
-	LIST_HEAD(page_list);
-
-	if (scheme->action != DAMOS_PAGEOUT)
-		return 0;
+	if (!folio)
+		return true;
+	if (folio == s->last_applied) {
+		folio_put(folio);
+		return true;
+	}
+	return false;
+}
 
-	for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
-		struct page *page = damon_get_page(PHYS_PFN(addr));
+static unsigned long damon_pa_pageout(struct damon_region *r,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	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_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, false);
+		if (!filter)
+			return 0;
+		damos_add_filter(s, filter);
+	}
 
-		if (!page)
+	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);
+		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:
+		addr += folio_size(folio);
+		folio_put(folio);
+	}
+	if (install_young_filter)
+		damos_destroy_filter(filter);
+	applied = reclaim_pages(&folio_list);
+	cond_resched();
+	s->last_applied = folio;
+	return damon_pa_core_addr(applied * PAGE_SIZE, addr_unit);
+}
 
-		ClearPageReferenced(page);
-		test_and_clear_page_young(page);
-		if (isolate_lru_page(page)) {
-			put_page(page);
+static inline unsigned long damon_pa_mark_accessed_or_deactivate(
+		struct damon_region *r, unsigned long addr_unit,
+		struct damos *s, bool mark_accessed,
+		unsigned long *sz_filter_passed)
+{
+	phys_addr_t addr, applied = 0;
+	struct folio *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 (PageUnevictable(page)) {
-			putback_lru_page(page);
-		} else {
-			list_add(&page->lru, &page_list);
-			put_page(page);
+
+		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);
+		else
+			folio_deactivate(folio);
+		applied += folio_nr_pages(folio);
+put_folio:
+		addr += folio_size(folio);
+		folio_put(folio);
+	}
+	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,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	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,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	return damon_pa_mark_accessed_or_deactivate(r, addr_unit, s, false,
+			sz_filter_passed);
+}
+
+static unsigned long damon_pa_migrate(struct damon_region *r,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	phys_addr_t addr, applied;
+	LIST_HEAD(folio_list);
+	struct folio *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 (!folio_isolate_lru(folio))
+			goto put_folio;
+		list_add(&folio->lru, &folio_list);
+put_folio:
+		addr += folio_size(folio);
+		folio_put(folio);
 	}
-	applied = reclaim_pages(&page_list);
+	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, unsigned long *sz_filter_passed)
+{
+	unsigned long aunit = ctx->addr_unit;
+
+	switch (scheme->action) {
+	case DAMOS_PAGEOUT:
+		return damon_pa_pageout(r, aunit, scheme, sz_filter_passed);
+	case DAMOS_LRU_PRIO:
+		return damon_pa_mark_accessed(r, aunit, scheme,
+				sz_filter_passed);
+	case DAMOS_LRU_DEPRIO:
+		return damon_pa_deactivate_pages(r, aunit, scheme,
+				sz_filter_passed);
+	case DAMOS_MIGRATE_HOT:
+	case DAMOS_MIGRATE_COLD:
+		return damon_pa_migrate(r, aunit, scheme, sz_filter_passed);
+	case DAMOS_STAT:
+		return damon_pa_stat(r, aunit, scheme, sz_filter_passed);
+	default:
+		/* DAMOS actions that not yet supported by 'paddr'. */
+		break;
+	}
+	return 0;
 }
 
 static int damon_pa_scheme_score(struct damon_ctx *context,
@@ -253,7 +350,15 @@ static int damon_pa_scheme_score(struct damon_ctx *context,
 {
 	switch (scheme->action) {
 	case DAMOS_PAGEOUT:
-		return damon_pageout_score(context, r, scheme);
+		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;
 	}
@@ -261,15 +366,21 @@ static int damon_pa_scheme_score(struct damon_ctx *context,
 	return DAMOS_MAX_SCORE;
 }
 
-void damon_pa_set_primitives(struct damon_ctx *ctx)
+static int __init damon_pa_initcall(void)
 {
-	ctx->primitive.init = NULL;
-	ctx->primitive.update = NULL;
-	ctx->primitive.prepare_access_checks = damon_pa_prepare_access_checks;
-	ctx->primitive.check_accesses = damon_pa_check_accesses;
-	ctx->primitive.reset_aggregated = NULL;
-	ctx->primitive.target_valid = damon_pa_target_valid;
-	ctx->primitive.cleanup = NULL;
-	ctx->primitive.apply_scheme = damon_pa_apply_scheme;
-	ctx->primitive.get_scheme_score = damon_pa_scheme_score;
-}
+	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,
+		.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);