Resguardo inicial

linux-7.2.3/mm/damon/Kconfig

@@ -0,0 +1,124 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menu "Data Access Monitoring"
+
+config DAMON
+	bool "DAMON: Data Access Monitoring Framework"
+	help
+	  This builds a framework that allows kernel subsystems to monitor
+	  access frequency of each memory region. The information can be useful
+	  for performance-centric DRAM level memory management.
+
+	  See https://www.kernel.org/doc/html/latest/mm/damon/index.html for
+	  more information.
+
+config DAMON_DEBUG_SANITY
+	bool "Check sanity of DAMON code"
+	depends on DAMON
+	help
+	  This enables additional DAMON debugging-purpose sanity checks in
+	  DAMON code.  This can be useful for finding bugs, but impose
+	  additional overhead.  This is therefore recommended to be enabled on
+	  only development and test setups.
+
+	  If unsure, say N.
+
+config DAMON_KUNIT_TEST
+	bool "Test for damon" if !KUNIT_ALL_TESTS
+	depends on DAMON && KUNIT=y
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the DAMON Kunit test suite.
+
+	  For more information on KUnit and unit tests in general, please refer
+	  to the KUnit documentation.
+
+	  If unsure, say N.
+
+config DAMON_VADDR
+	bool "Data access monitoring operations for virtual address spaces"
+	depends on DAMON && MMU
+	select PAGE_IDLE_FLAG
+	default DAMON
+	help
+	  This builds the default data access monitoring operations for DAMON
+	  that work for virtual address spaces.
+
+config DAMON_PADDR
+	bool "Data access monitoring operations for the physical address space"
+	depends on DAMON && MMU
+	select PAGE_IDLE_FLAG
+	default DAMON
+	help
+	  This builds the default data access monitoring operations for DAMON
+	  that works for the physical address space.
+
+config DAMON_VADDR_KUNIT_TEST
+	bool "Test for DAMON operations" if !KUNIT_ALL_TESTS
+	depends on DAMON_VADDR && KUNIT=y
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the DAMON virtual addresses operations Kunit test suite.
+
+	  For more information on KUnit and unit tests in general, please refer
+	  to the KUnit documentation.
+
+	  If unsure, say N.
+
+config DAMON_SYSFS
+	bool "DAMON sysfs interface"
+	depends on DAMON && SYSFS
+	default DAMON
+	help
+	  This builds the sysfs interface for DAMON.  The user space can use
+	  the interface for arbitrary data access monitoring.
+
+config DAMON_SYSFS_KUNIT_TEST
+	bool "Test for damon sysfs interface" if !KUNIT_ALL_TESTS
+	depends on DAMON_SYSFS && KUNIT=y
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the DAMON sysfs interface Kunit test suite.
+
+	  For more information on KUnit and unit tests in general, please refer
+	  to the KUnit documentation.
+
+	  If unsure, say N.
+
+config DAMON_RECLAIM
+	bool "Build DAMON-based reclaim (DAMON_RECLAIM)"
+	depends on DAMON_PADDR
+	help
+	  This builds the DAMON-based reclamation subsystem.  It finds pages
+	  that not accessed for a long time (cold) using DAMON and reclaim
+	  those.
+
+	  This is suggested to be used as a proactive and lightweight
+	  reclamation under light memory pressure, while the traditional page
+	  scanning-based reclamation is used for heavy pressure.
+
+config DAMON_LRU_SORT
+	bool "Build DAMON-based LRU-lists sorting (DAMON_LRU_SORT)"
+	depends on DAMON_PADDR
+	help
+	  This builds the DAMON-based LRU-lists sorting subsystem.  It tries to
+	  protect frequently accessed (hot) pages while rarely accessed (cold)
+	  pages reclaimed first under memory pressure.
+
+config DAMON_STAT
+	bool "Build data access monitoring stat (DAMON_STAT)"
+	depends on DAMON_PADDR
+	help
+	  This builds the DAMON-based access monitoring statistics subsystem.
+	  It runs DAMON and expose access monitoring results in simple stat
+	  metrics.
+
+config DAMON_STAT_ENABLED_DEFAULT
+	bool "Enable DAMON_STAT by default"
+	depends on DAMON_STAT
+	default DAMON_STAT
+	help
+	  Whether to enable DAMON_STAT by default.  Users can disable it in
+	  boot or runtime using its 'enabled' parameter.
+
+endmenu

linux-7.2.3/mm/damon/Makefile

@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-y				:= core.o
+obj-$(CONFIG_DAMON_VADDR)	+= ops-common.o vaddr.o
+obj-$(CONFIG_DAMON_PADDR)	+= ops-common.o paddr.o
+obj-$(CONFIG_DAMON_SYSFS)	+= sysfs-common.o sysfs-schemes.o sysfs.o
+obj-$(CONFIG_DAMON_RECLAIM)	+= modules-common.o reclaim.o
+obj-$(CONFIG_DAMON_LRU_SORT)	+= modules-common.o lru_sort.o
+obj-$(CONFIG_DAMON_STAT)	+= modules-common.o stat.o

linux-7.2.3/mm/damon/lru_sort.c

@@ -0,0 +1,562 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON-based LRU-lists Sorting
+ */
+
+#define pr_fmt(fmt) "damon-lru-sort: " fmt
+
+#include <linux/damon.h>
+#include <linux/kstrtox.h>
+#include <linux/module.h>
+
+#include "modules-common.h"
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "damon_lru_sort."
+
+/*
+ * Enable or disable DAMON_LRU_SORT.
+ *
+ * You can enable DAMON_LRU_SORT by setting the value of this parameter as
+ * ``Y``.  Setting it as ``N`` disables DAMON_LRU_SORT.  Note that
+ * DAMON_LRU_SORT could do no real monitoring and LRU-lists sorting due to the
+ * watermarks-based activation condition.  Refer to below descriptions for the
+ * watermarks parameter for this.
+ */
+static bool enabled __read_mostly;
+
+/*
+ * Make DAMON_LRU_SORT reads the input parameters again, except ``enabled``.
+ *
+ * Input parameters that updated while DAMON_LRU_SORT is running are not
+ * applied by default.  Once this parameter is set as ``Y``, DAMON_LRU_SORT
+ * reads values of parameters except ``enabled`` again.  Once the re-reading is
+ * done, this parameter is set as ``N``.  If invalid parameters are found while
+ * the re-reading, DAMON_LRU_SORT will be disabled.
+ */
+static bool commit_inputs __read_mostly;
+
+/*
+ * Desired active to [in]active memory ratio in bp (1/10,000).
+ *
+ * While keeping the caps that set by other quotas, DAMON_LRU_SORT
+ * automatically increases and decreases the effective level of the quota
+ * aiming the LRU [de]prioritizations of the hot and cold memory resulting in
+ * this active to [in]active memory ratio.  Value zero means disabling this
+ * auto-tuning feature.
+ *
+ * Disabled by default.
+ */
+static unsigned long active_mem_bp __read_mostly;
+module_param(active_mem_bp, ulong, 0600);
+
+/*
+ * Auto-tune monitoring intervals.
+ *
+ * If this parameter is set as ``Y``, DAMON_LRU_SORT automatically tunes
+ * DAMON's sampling and aggregation intervals.  The auto-tuning aims to capture
+ * meaningful amount of access events in each DAMON-snapshot, while keeping the
+ * sampling interval 5 milliseconds in minimum, and 10 seconds in maximum.
+ * Setting this as ``N`` disables the auto-tuning.
+ *
+ * Disabled by default.
+ */
+static bool autotune_monitoring_intervals __read_mostly;
+module_param(autotune_monitoring_intervals, bool, 0600);
+
+/*
+ * Filter [non-]young pages accordingly for LRU [de]prioritizations.
+ *
+ * If this is set, check page level access (youngness) once again before each
+ * LRU [de]prioritization operation.  LRU prioritization operation is skipped
+ * if the page has not accessed since the last check (not young).  LRU
+ * deprioritization operation is skipped if the page has accessed since the
+ * last check (young).  The feature is enabled or disabled if this parameter is
+ * set as ``Y`` or ``N``, respectively.
+ *
+ * Disabled by default.
+ */
+static bool filter_young_pages __read_mostly;
+module_param(filter_young_pages, bool, 0600);
+
+/*
+ * Access frequency threshold for hot memory regions identification in permil.
+ *
+ * If a memory region is accessed in frequency of this or higher,
+ * DAMON_LRU_SORT identifies the region as hot, and mark it as accessed on the
+ * LRU list, so that it could not be reclaimed under memory pressure.  50% by
+ * default.
+ */
+static unsigned long hot_thres_access_freq = 500;
+module_param(hot_thres_access_freq, ulong, 0600);
+
+/*
+ * Time threshold for cold memory regions identification in microseconds.
+ *
+ * If a memory region is not accessed for this or longer time, DAMON_LRU_SORT
+ * identifies the region as cold, and mark it as unaccessed on the LRU list, so
+ * that it could be reclaimed first under memory pressure.  120 seconds by
+ * default.
+ */
+static unsigned long cold_min_age __read_mostly = 120000000;
+module_param(cold_min_age, ulong, 0600);
+
+static struct damos_quota damon_lru_sort_quota = {
+	/* Use up to 10 ms per 1 sec, by default */
+	.ms = 10,
+	.sz = 0,
+	.reset_interval = 1000,
+	/* Within the quota, mark hotter regions accessed first. */
+	.weight_sz = 0,
+	.weight_nr_accesses = 1,
+	.weight_age = 1,
+};
+DEFINE_DAMON_MODULES_DAMOS_TIME_QUOTA(damon_lru_sort_quota);
+
+static struct damos_watermarks damon_lru_sort_wmarks = {
+	.metric = DAMOS_WMARK_FREE_MEM_RATE,
+	.interval = 5000000,	/* 5 seconds */
+	.high = 200,		/* 20 percent */
+	.mid = 150,		/* 15 percent */
+	.low = 50,		/* 5 percent */
+};
+DEFINE_DAMON_MODULES_WMARKS_PARAMS(damon_lru_sort_wmarks);
+
+static struct damon_attrs damon_lru_sort_mon_attrs = {
+	.sample_interval = 5000,	/* 5 ms */
+	.aggr_interval = 100000,	/* 100 ms */
+	.ops_update_interval = 0,
+	.min_nr_regions = 10,
+	.max_nr_regions = 1000,
+};
+DEFINE_DAMON_MODULES_MON_ATTRS_PARAMS(damon_lru_sort_mon_attrs);
+
+/*
+ * Start of the target memory region in physical address.
+ *
+ * The start physical address of memory region that DAMON_LRU_SORT will do work
+ * against.  By default, the system's entire physical memory is used as the
+ * region.
+ */
+static unsigned long monitor_region_start __read_mostly;
+module_param(monitor_region_start, ulong, 0600);
+
+/*
+ * End of the target memory region in physical address.
+ *
+ * The end physical address of memory region that DAMON_LRU_SORT will do work
+ * against.  By default, the system's entire physical memory is used as the
+ * region.
+ */
+static unsigned long monitor_region_end __read_mostly;
+module_param(monitor_region_end, ulong, 0600);
+
+/*
+ * Scale factor for DAMON_LRU_SORT to ops address conversion.
+ *
+ * This parameter must not be set to 0.
+ */
+static unsigned long addr_unit __read_mostly = 1;
+
+static struct damos_stat damon_lru_sort_hot_stat;
+DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_hot_stat,
+		lru_sort_tried_hot_regions, lru_sorted_hot_regions,
+		hot_quota_exceeds);
+
+static struct damos_stat damon_lru_sort_cold_stat;
+DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_lru_sort_cold_stat,
+		lru_sort_tried_cold_regions, lru_sorted_cold_regions,
+		cold_quota_exceeds);
+
+static struct damos_access_pattern damon_lru_sort_stub_pattern = {
+	/* Find regions having PAGE_SIZE or larger size */
+	.min_sz_region = PAGE_SIZE,
+	.max_sz_region = ULONG_MAX,
+	/* no matter its access frequency */
+	.min_nr_accesses = 0,
+	.max_nr_accesses = UINT_MAX,
+	/* no matter its age */
+	.min_age_region = 0,
+	.max_age_region = UINT_MAX,
+};
+
+static struct damon_ctx *ctx;
+static struct damon_target *target;
+
+static struct damos *damon_lru_sort_new_scheme(
+		struct damos_access_pattern *pattern, enum damos_action action)
+{
+	struct damos_quota quota = damon_lru_sort_quota;
+
+	/* Use half of total quota for hot/cold pages sorting */
+	quota.ms = quota.ms / 2;
+
+	return damon_new_scheme(
+			/* find the pattern, and */
+			pattern,
+			/* (de)prioritize on LRU-lists */
+			action,
+			/* for each aggregation interval */
+			0,
+			/* under the quota. */
+			&quota,
+			/* (De)activate this according to the watermarks. */
+			&damon_lru_sort_wmarks,
+			NUMA_NO_NODE);
+}
+
+/* Create a DAMON-based operation scheme for hot memory regions */
+static struct damos *damon_lru_sort_new_hot_scheme(unsigned int hot_thres)
+{
+	struct damos_access_pattern pattern = damon_lru_sort_stub_pattern;
+
+	pattern.min_nr_accesses = hot_thres;
+	return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_PRIO);
+}
+
+/* Create a DAMON-based operation scheme for cold memory regions */
+static struct damos *damon_lru_sort_new_cold_scheme(unsigned int cold_thres)
+{
+	struct damos_access_pattern pattern = damon_lru_sort_stub_pattern;
+
+	pattern.max_nr_accesses = 0;
+	pattern.min_age_region = cold_thres;
+	return damon_lru_sort_new_scheme(&pattern, DAMOS_LRU_DEPRIO);
+}
+
+static int damon_lru_sort_add_quota_goals(struct damos *hot_scheme,
+		struct damos *cold_scheme)
+{
+	struct damos_quota_goal *goal;
+
+	if (!active_mem_bp)
+		return 0;
+	if (10000 < active_mem_bp)
+		return -EINVAL;
+	goal = damos_new_quota_goal(DAMOS_QUOTA_ACTIVE_MEM_BP, active_mem_bp);
+	if (!goal)
+		return -ENOMEM;
+	damos_add_quota_goal(&hot_scheme->quota, goal);
+	/* aim 0.2 % goal conflict, to keep little ping pong */
+	goal = damos_new_quota_goal(DAMOS_QUOTA_INACTIVE_MEM_BP,
+			10000 - active_mem_bp + 2);
+	if (!goal)
+		return -ENOMEM;
+	damos_add_quota_goal(&cold_scheme->quota, goal);
+	return 0;
+}
+
+static int damon_lru_sort_add_filters(struct damos *hot_scheme,
+		struct damos *cold_scheme)
+{
+	struct damos_filter *filter;
+
+	if (!filter_young_pages)
+		return 0;
+
+	/* disallow prioritizing not-young pages */
+	filter = damos_new_filter(DAMOS_FILTER_TYPE_YOUNG, false, false);
+	if (!filter)
+		return -ENOMEM;
+	damos_add_filter(hot_scheme, filter);
+
+	/* disabllow de-prioritizing young pages */
+	filter = damos_new_filter(DAMOS_FILTER_TYPE_YOUNG, true, false);
+	if (!filter)
+		return -ENOMEM;
+	damos_add_filter(cold_scheme, filter);
+	return 0;
+}
+
+static int damon_lru_sort_apply_parameters(void)
+{
+	struct damon_ctx *param_ctx;
+	struct damon_target *param_target;
+	struct damon_attrs attrs;
+	struct damos *hot_scheme, *cold_scheme;
+	unsigned int hot_thres, cold_thres;
+	int err;
+
+	err = damon_modules_new_paddr_ctx_target(&param_ctx, &param_target);
+	if (err)
+		return err;
+
+	param_ctx->addr_unit = addr_unit;
+	param_ctx->min_region_sz = max(DAMON_MIN_REGION_SZ / addr_unit, 1);
+
+	if (!is_power_of_2(param_ctx->min_region_sz)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (!damon_lru_sort_mon_attrs.sample_interval) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	attrs = damon_lru_sort_mon_attrs;
+	if (autotune_monitoring_intervals) {
+		attrs.sample_interval = 5000;
+		attrs.aggr_interval = 100000;
+		attrs.intervals_goal.access_bp = 40;
+		attrs.intervals_goal.aggrs = 3;
+		attrs.intervals_goal.min_sample_us = 5000;
+		attrs.intervals_goal.max_sample_us = 10 * 1000 * 1000;
+	}
+	err = damon_set_attrs(param_ctx, &attrs);
+	if (err)
+		goto out;
+
+	err = -ENOMEM;
+	hot_thres = damon_max_nr_accesses(&attrs) *
+		hot_thres_access_freq / 1000;
+	hot_scheme = damon_lru_sort_new_hot_scheme(hot_thres);
+	if (!hot_scheme)
+		goto out;
+
+	cold_thres = cold_min_age / attrs.aggr_interval;
+	cold_scheme = damon_lru_sort_new_cold_scheme(cold_thres);
+	if (!cold_scheme) {
+		damon_destroy_scheme(hot_scheme);
+		goto out;
+	}
+
+	damon_set_schemes(param_ctx, &hot_scheme, 1);
+	damon_add_scheme(param_ctx, cold_scheme);
+
+	err = damon_lru_sort_add_quota_goals(hot_scheme, cold_scheme);
+	if (err)
+		goto out;
+	err = damon_lru_sort_add_filters(hot_scheme, cold_scheme);
+	if (err)
+		goto out;
+
+	err = damon_set_region_system_rams_default(param_target,
+					&monitor_region_start,
+					&monitor_region_end,
+					param_ctx->addr_unit,
+					param_ctx->min_region_sz);
+	if (err)
+		goto out;
+	err = damon_commit_ctx(ctx, param_ctx);
+out:
+	damon_destroy_ctx(param_ctx);
+	return err;
+}
+
+static int damon_lru_sort_commit_inputs_fn(void *arg)
+{
+	return damon_lru_sort_apply_parameters();
+}
+
+static bool damon_lru_sort_damon_has_started;
+
+static int damon_lru_sort_commit_inputs_store(const char *val,
+					      const struct kernel_param *kp)
+{
+	bool commit_inputs_request;
+	int err;
+	struct damon_call_control control = {
+		.fn = damon_lru_sort_commit_inputs_fn,
+	};
+
+	if (!val) {
+		commit_inputs_request = true;
+	} else {
+		err = kstrtobool(val, &commit_inputs_request);
+		if (err)
+			return err;
+	}
+
+	if (!commit_inputs_request)
+		return 0;
+
+	/* Skip damon_call() if ctx has not successfully started. */
+	if (!damon_lru_sort_damon_has_started)
+		return -EINVAL;
+
+	err = damon_call(ctx, &control);
+
+	return err ? err : control.return_code;
+}
+
+static const struct kernel_param_ops commit_inputs_param_ops = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = damon_lru_sort_commit_inputs_store,
+	.get = param_get_bool,
+};
+
+module_param_cb(commit_inputs, &commit_inputs_param_ops, &commit_inputs, 0600);
+
+static int damon_lru_sort_damon_call_fn(void *arg)
+{
+	struct damon_ctx *c = arg;
+	struct damos *s;
+
+	/* update the stats parameter */
+	damon_for_each_scheme(s, c) {
+		if (s->action == DAMOS_LRU_PRIO)
+			damon_lru_sort_hot_stat = s->stat;
+		else if (s->action == DAMOS_LRU_DEPRIO)
+			damon_lru_sort_cold_stat = s->stat;
+	}
+
+	return 0;
+}
+
+static struct damon_call_control call_control = {
+	.fn = damon_lru_sort_damon_call_fn,
+	.repeat = true,
+};
+
+static int damon_lru_sort_turn(bool on)
+{
+	int err;
+
+	if (!on)
+		return damon_stop(&ctx, 1);
+
+	err = damon_lru_sort_apply_parameters();
+	if (err)
+		return err;
+
+	err = damon_start(&ctx, 1, true);
+	if (err)
+		return err;
+	if (!damon_lru_sort_damon_has_started)
+		damon_lru_sort_damon_has_started = true;
+	return damon_call(ctx, &call_control);
+}
+
+static int damon_lru_sort_addr_unit_store(const char *val,
+		const struct kernel_param *kp)
+{
+	unsigned long input_addr_unit;
+	int err = kstrtoul(val, 0, &input_addr_unit);
+
+	if (err)
+		return err;
+	if (!input_addr_unit)
+		return -EINVAL;
+
+	addr_unit = input_addr_unit;
+	return 0;
+}
+
+static const struct kernel_param_ops addr_unit_param_ops = {
+	.set = damon_lru_sort_addr_unit_store,
+	.get = param_get_ulong,
+};
+
+module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600);
+MODULE_PARM_DESC(addr_unit,
+	"Scale factor for DAMON_LRU_SORT to ops address conversion (default: 1)");
+
+static bool damon_lru_sort_enabled(void)
+{
+	if (!ctx)
+		return false;
+	return damon_is_running(ctx);
+}
+
+static int damon_lru_sort_enabled_store(const char *val,
+		const struct kernel_param *kp)
+{
+	int err;
+
+	err = kstrtobool(val, &enabled);
+	if (err)
+		return err;
+
+	if (damon_lru_sort_enabled() == enabled)
+		return 0;
+
+	/* Called before init function.  The function will handle this. */
+	if (!damon_initialized())
+		return 0;
+
+	/* damon_modules_new_paddr_ctx_target() in the init function failed. */
+	if (!ctx)
+		return -ENOMEM;
+
+	return damon_lru_sort_turn(enabled);
+}
+
+static int damon_lru_sort_enabled_load(char *buffer,
+		const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%c\n", damon_lru_sort_enabled() ? 'Y' : 'N');
+}
+
+static const struct kernel_param_ops enabled_param_ops = {
+	.set = damon_lru_sort_enabled_store,
+	.get = damon_lru_sort_enabled_load,
+};
+
+module_param_cb(enabled, &enabled_param_ops, &enabled, 0600);
+MODULE_PARM_DESC(enabled,
+	"Enable or disable DAMON_LRU_SORT (default: disabled)");
+
+static int damon_lru_sort_kdamond_pid_store(const char *val,
+		const struct kernel_param *kp)
+{
+	/*
+	 * kdamond_pid is read-only, but kernel command line could write it.
+	 * Do nothing here.
+	 */
+	return 0;
+}
+
+static int damon_lru_sort_kdamond_pid_load(char *buffer,
+		const struct kernel_param *kp)
+{
+	int kdamond_pid = -1;
+
+	if (ctx) {
+		kdamond_pid = damon_kdamond_pid(ctx);
+		if (kdamond_pid < 0)
+			kdamond_pid = -1;
+	}
+	return sprintf(buffer, "%d\n", kdamond_pid);
+}
+
+static const struct kernel_param_ops kdamond_pid_param_ops = {
+	.set = damon_lru_sort_kdamond_pid_store,
+	.get = damon_lru_sort_kdamond_pid_load,
+};
+
+/*
+ * PID of the DAMON thread
+ *
+ * If DAMON_LRU_SORT is enabled, this becomes the PID of the worker thread.
+ * Else, -1.
+ */
+module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400);
+
+static int __init damon_lru_sort_init(void)
+{
+	int err;
+
+	if (!damon_initialized()) {
+		err = -ENOMEM;
+		goto out;
+	}
+	err = damon_modules_new_paddr_ctx_target(&ctx, &target);
+	if (err)
+		goto out;
+
+	call_control.data = ctx;
+
+	/* 'enabled' has set before this function, probably via command line */
+	if (enabled)
+		err = damon_lru_sort_turn(true);
+
+out:
+	if (err && enabled)
+		enabled = false;
+	return err;
+}
+
+module_init(damon_lru_sort_init);

linux-7.2.3/mm/damon/modules-common.c

@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common Code for DAMON Modules
+ */
+
+#include <linux/damon.h>
+
+#include "modules-common.h"
+
+/*
+ * Allocate, set, and return a DAMON context for the physical address space.
+ * @ctxp:	Pointer to save the point to the newly created context
+ * @targetp:	Pointer to save the point to the newly created target
+ */
+int damon_modules_new_paddr_ctx_target(struct damon_ctx **ctxp,
+		struct damon_target **targetp)
+{
+	struct damon_ctx *ctx;
+	struct damon_target *target;
+
+	ctx = damon_new_ctx();
+	if (!ctx)
+		return -ENOMEM;
+
+	if (damon_select_ops(ctx, DAMON_OPS_PADDR)) {
+		damon_destroy_ctx(ctx);
+		return -EINVAL;
+	}
+
+	target = damon_new_target();
+	if (!target) {
+		damon_destroy_ctx(ctx);
+		return -ENOMEM;
+	}
+	damon_add_target(ctx, target);
+
+	*ctxp = ctx;
+	*targetp = target;
+	return 0;
+}

linux-7.2.3/mm/damon/modules-common.h

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common Code for DAMON Modules
+ */
+
+#include <linux/moduleparam.h>
+
+#define DEFINE_DAMON_MODULES_MON_ATTRS_PARAMS(attrs)			\
+	module_param_named(sample_interval, attrs.sample_interval,	\
+			ulong, 0600);					\
+	module_param_named(aggr_interval, attrs.aggr_interval, ulong,	\
+			0600);						\
+	module_param_named(min_nr_regions, attrs.min_nr_regions, ulong,	\
+			0600);						\
+	module_param_named(max_nr_regions, attrs.max_nr_regions, ulong,	\
+			0600);
+
+#define DEFINE_DAMON_MODULES_DAMOS_TIME_QUOTA(quota)			\
+	module_param_named(quota_ms, quota.ms, ulong, 0600);		\
+	module_param_named(quota_reset_interval_ms,			\
+			quota.reset_interval, ulong, 0600);
+
+#define DEFINE_DAMON_MODULES_DAMOS_QUOTAS(quota)			\
+	DEFINE_DAMON_MODULES_DAMOS_TIME_QUOTA(quota)			\
+	module_param_named(quota_sz, quota.sz, ulong, 0600);
+
+#define DEFINE_DAMON_MODULES_WMARKS_PARAMS(wmarks)			\
+	module_param_named(wmarks_interval, wmarks.interval, ulong,	\
+			0600);						\
+	module_param_named(wmarks_high, wmarks.high, ulong, 0600);	\
+	module_param_named(wmarks_mid, wmarks.mid, ulong, 0600);	\
+	module_param_named(wmarks_low, wmarks.low, ulong, 0600);
+
+#define DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(stat, try_name,		\
+		succ_name, qt_exceed_name)				\
+	module_param_named(nr_##try_name, stat.nr_tried, ulong, 0400);	\
+	module_param_named(bytes_##try_name, stat.sz_tried, ulong,	\
+			0400);						\
+	module_param_named(nr_##succ_name, stat.nr_applied, ulong,	\
+			0400);						\
+	module_param_named(bytes_##succ_name, stat.sz_applied, ulong,	\
+			0400);						\
+	module_param_named(nr_##qt_exceed_name, stat.qt_exceeds, ulong,	\
+			0400);
+
+int damon_modules_new_paddr_ctx_target(struct damon_ctx **ctxp,
+		struct damon_target **targetp);

linux-7.2.3/mm/damon/ops-common.c

@@ -0,0 +1,442 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common Code for Data Access Monitoring
+ */
+
+#include <linux/migrate.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/leafops.h>
+
+#include "../internal.h"
+#include "ops-common.h"
+
+/*
+ * Get an online page for a pfn if it's in the LRU list.  Otherwise, returns
+ * NULL.
+ *
+ * The body of this function is stolen from the 'page_idle_get_folio()'.  We
+ * steal rather than reuse it because the code is quite simple.
+ */
+struct folio *damon_get_folio(unsigned long pfn)
+{
+	struct page *page = pfn_to_online_page(pfn);
+	struct folio *folio;
+
+	if (!page)
+		return NULL;
+
+	folio = page_folio(page);
+	if (!folio_try_get(folio))
+		return NULL;
+	if (unlikely(page_folio(page) != folio) || !folio_test_lru(folio)) {
+		folio_put(folio);
+		folio = NULL;
+	}
+	return folio;
+}
+
+void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr)
+{
+	pte_t pteval = ptep_get(pte);
+	struct folio *folio;
+	bool young = false;
+	unsigned long pfn;
+
+	if (likely(pte_present(pteval)))
+		pfn = pte_pfn(pteval);
+	else
+		pfn = softleaf_to_pfn(softleaf_from_pte(pteval));
+
+	folio = damon_get_folio(pfn);
+	if (!folio)
+		return;
+
+	/*
+	 * PFN swap PTEs, such as device-exclusive ones, that actually map pages
+	 * are "old" from a CPU perspective. The MMU notifier takes care of any
+	 * device aspects.
+	 */
+	if (likely(pte_present(pteval)))
+		young |= ptep_test_and_clear_young(vma, addr, pte);
+	young |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + PAGE_SIZE);
+	if (young)
+		folio_set_young(folio);
+
+	folio_set_idle(folio);
+	folio_put(folio);
+}
+
+void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	pmd_t pmdval = pmdp_get(pmd);
+	struct folio *folio;
+	bool young = false;
+	unsigned long pfn;
+
+	if (likely(pmd_present(pmdval)))
+		pfn = pmd_pfn(pmdval);
+	else
+		pfn = softleaf_to_pfn(softleaf_from_pmd(pmdval));
+
+	folio = damon_get_folio(pfn);
+	if (!folio)
+		return;
+
+	if (likely(pmd_present(pmdval)))
+		young |= pmdp_test_and_clear_young(vma, addr, pmd);
+	young |= mmu_notifier_clear_young(vma->vm_mm, addr, addr + HPAGE_PMD_SIZE);
+	if (young)
+		folio_set_young(folio);
+
+	folio_set_idle(folio);
+	folio_put(folio);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+}
+
+#define DAMON_MAX_SUBSCORE	(100)
+#define DAMON_MAX_AGE_IN_LOG	(32)
+
+int damon_hot_score(struct damon_ctx *c, struct damon_region *r,
+			struct damos *s)
+{
+	int freq_subscore;
+	unsigned int age_in_sec;
+	int age_in_log, age_subscore;
+	unsigned int freq_weight = s->quota.weight_nr_accesses;
+	unsigned int age_weight = s->quota.weight_age;
+	int hotness;
+
+	freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE /
+		damon_max_nr_accesses(&c->attrs);
+
+	age_in_sec = (unsigned long)r->age * c->attrs.aggr_interval / 1000000;
+	if (age_in_sec)
+		age_in_log = min_t(int, ilog2(age_in_sec) + 1,
+				DAMON_MAX_AGE_IN_LOG);
+	else
+		age_in_log = 0;
+
+
+	/* If frequency is 0, higher age means it's colder */
+	if (freq_subscore == 0)
+		age_in_log *= -1;
+
+	/*
+	 * Now age_in_log is in [-DAMON_MAX_AGE_IN_LOG, DAMON_MAX_AGE_IN_LOG].
+	 * Scale it to be in [0, 100] and set it as age subscore.
+	 */
+	age_in_log += DAMON_MAX_AGE_IN_LOG;
+	age_subscore = age_in_log * DAMON_MAX_SUBSCORE /
+		DAMON_MAX_AGE_IN_LOG / 2;
+
+	hotness = (freq_weight * freq_subscore + age_weight * age_subscore);
+	if (freq_weight + age_weight)
+		hotness /= freq_weight + age_weight;
+	/*
+	 * Transform it to fit in [0, DAMOS_MAX_SCORE]
+	 */
+	hotness = hotness * DAMOS_MAX_SCORE / DAMON_MAX_SUBSCORE;
+	hotness = max(min(hotness, DAMOS_MAX_SCORE), 0);
+
+	return hotness;
+}
+
+int damon_cold_score(struct damon_ctx *c, struct damon_region *r,
+			struct damos *s)
+{
+	int hotness = damon_hot_score(c, r, s);
+
+	/* Return coldness of the region */
+	return DAMOS_MAX_SCORE - hotness;
+}
+
+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;
+}
+
+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,
+	};
+
+	if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
+		folio_set_idle(folio);
+		return;
+	}
+
+	if (!folio_trylock(folio))
+		return;
+
+	rmap_walk(folio, &rwc);
+	folio_unlock(folio);
+
+}
+
+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);
+	pte_t pte;
+
+	*accessed = false;
+	while (page_vma_mapped_walk(&pvmw)) {
+		addr = pvmw.address;
+		if (pvmw.pte) {
+			pte = ptep_get(pvmw.pte);
+
+			/*
+			 * PFN swap PTEs, such as device-exclusive ones, that
+			 * actually map pages are "old" from a CPU perspective.
+			 * The MMU notifier takes care of any device aspects.
+			 */
+			*accessed = (pte_present(pte) && pte_young(pte)) ||
+				!folio_test_idle(folio) ||
+				mmu_notifier_test_young(vma->vm_mm, addr);
+		} else {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+			pmd_t pmd = pmdp_get(pvmw.pmd);
+
+			*accessed = (pmd_present(pmd) && pmd_young(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;
+}
+
+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,
+	};
+
+	if (!folio_mapped(folio) || !folio_raw_mapping(folio)) {
+		if (folio_test_idle(folio))
+			return false;
+		else
+			return true;
+	}
+
+	if (!folio_trylock(folio))
+		return false;
+
+	rmap_walk(folio, &rwc);
+	folio_unlock(folio);
+
+	return accessed;
+}
+
+bool damos_folio_filter_match(struct damos_filter *filter, struct folio *folio)
+{
+	bool matched = false;
+	struct mem_cgroup *memcg;
+	size_t folio_sz;
+
+	switch (filter->type) {
+	case DAMOS_FILTER_TYPE_ANON:
+		matched = folio_test_anon(folio);
+		break;
+	case DAMOS_FILTER_TYPE_ACTIVE:
+		matched = folio_test_active(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;
+	case DAMOS_FILTER_TYPE_HUGEPAGE_SIZE:
+		folio_sz = folio_size(folio);
+		matched = filter->sz_range.min <= folio_sz &&
+			  folio_sz <= filter->sz_range.max;
+		break;
+	case DAMOS_FILTER_TYPE_UNMAPPED:
+		matched = !folio_mapped(folio) || !folio_raw_mapping(folio);
+		break;
+	default:
+		break;
+	}
+
+	return matched == filter->matching;
+}
+
+static unsigned int __damon_migrate_folio_list(
+		struct list_head *migrate_folios, struct pglist_data *pgdat,
+		int target_nid)
+{
+	unsigned int nr_succeeded = 0;
+	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_NOMEMALLOC | GFP_NOWAIT,
+		.nid = target_nid,
+	};
+
+	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_migration_target, NULL,
+		      (unsigned long)&mtc, MIGRATE_ASYNC, MR_DAMON,
+		      &nr_succeeded);
+
+	return nr_succeeded;
+}
+
+static unsigned int damon_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_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);
+		node_stat_sub_folio(folio, NR_ISOLATED_ANON +
+				folio_is_file_lru(folio));
+		folio_putback_lru(folio);
+	}
+
+	return nr_migrated;
+}
+
+unsigned long damon_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;
+
+	if (target_nid < 0 || target_nid >= MAX_NUMNODES ||
+			!node_state(target_nid, N_MEMORY)) {
+		while (!list_empty(folio_list)) {
+			struct folio *folio = lru_to_folio(folio_list);
+
+			list_del(&folio->lru);
+			node_stat_sub_folio(folio, NR_ISOLATED_ANON +
+					folio_is_file_lru(folio));
+			folio_putback_lru(folio);
+		}
+		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_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_migrate_folio_list(&node_folio_list,
+						   NODE_DATA(nid),
+						   target_nid);
+
+	memalloc_noreclaim_restore(noreclaim_flag);
+
+	return nr_migrated;
+}
+
+bool damos_ops_has_filter(struct damos *s)
+{
+	struct damos_filter *f;
+
+	damos_for_each_ops_filter(f, s)
+		return true;
+	return false;
+}

linux-7.2.3/mm/damon/ops-common.h

@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common Code for Data Access Monitoring
+ */
+
+#include <linux/damon.h>
+
+struct folio *damon_get_folio(unsigned long pfn);
+
+void damon_ptep_mkold(pte_t *pte, struct vm_area_struct *vma, unsigned long addr);
+void damon_pmdp_mkold(pmd_t *pmd, struct vm_area_struct *vma, unsigned long addr);
+void damon_folio_mkold(struct folio *folio);
+bool damon_folio_young(struct folio *folio);
+
+int damon_cold_score(struct damon_ctx *c, struct damon_region *r,
+			struct damos *s);
+int damon_hot_score(struct damon_ctx *c, struct damon_region *r,
+			struct damos *s);
+
+bool damos_folio_filter_match(struct damos_filter *filter, struct folio *folio);
+unsigned long damon_migrate_pages(struct list_head *folio_list, int target_nid);
+
+bool damos_ops_has_filter(struct damos *s);

linux-7.2.3/mm/damon/paddr.c

@@ -0,0 +1,458 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON Code for The Physical Address Space
+ */
+
+#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/mm_inline.h>
+
+#include "../internal.h"
+#include "ops-common.h"
+
+static phys_addr_t damon_pa_phys_addr(
+		unsigned long addr, unsigned long addr_unit)
+{
+	return (phys_addr_t)addr * addr_unit;
+}
+
+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(phys_addr_t 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,
+		struct damon_ctx *ctx)
+{
+	r->sampling_addr = damon_rand(ctx, r->ar.start, r->ar.end);
+
+	damon_pa_mkold(damon_pa_phys_addr(r->sampling_addr, ctx->addr_unit));
+}
+
+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, ctx);
+	}
+}
+
+static bool damon_pa_young(phys_addr_t 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, unsigned long addr_unit)
+{
+	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(sampling_addr, last_folio_sz)) {
+		damon_update_region_access_rate(r, last_accessed, attrs);
+		return;
+	}
+
+	last_accessed = damon_pa_young(sampling_addr, &last_folio_sz);
+	damon_update_region_access_rate(r, last_accessed, attrs);
+
+	last_addr = 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, ctx->addr_unit);
+			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
+		}
+	}
+
+	return max_nr_accesses;
+}
+
+static bool damon_pa_filter_match(struct damon_filter *filter,
+		struct folio *folio)
+{
+	bool matched = false;
+	struct mem_cgroup *memcg;
+
+	switch (filter->type) {
+	case DAMON_FILTER_TYPE_ANON:
+		if (!folio) {
+			matched = false;
+			break;
+		}
+		matched = folio_test_anon(folio);
+		break;
+	case DAMON_FILTER_TYPE_MEMCG:
+		if (!folio) {
+			matched = false;
+			break;
+		}
+		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;
+	default:
+		break;
+	}
+	return matched == filter->matching;
+}
+
+static bool damon_pa_filter_pass(phys_addr_t pa, struct folio *folio,
+		struct damon_probe *p)
+{
+	struct damon_filter *f;
+	bool pass = true;
+
+	damon_for_each_filter(f, p) {
+		if (damon_pa_filter_match(f, folio)) {
+			pass = f->allow;
+			break;
+		}
+		pass = !f->allow;
+	}
+	return pass;
+}
+
+static void damon_pa_apply_probes(struct damon_ctx *ctx)
+{
+	struct damon_target *t;
+	struct damon_region *r;
+	struct damon_probe *p;
+
+	damon_for_each_target(t, ctx) {
+		damon_for_each_region(r, t) {
+			int i = 0;
+			phys_addr_t pa;
+			struct folio *folio;
+
+			pa = damon_pa_phys_addr(r->sampling_addr,
+					ctx->addr_unit);
+			folio = damon_get_folio(PHYS_PFN(pa));
+			damon_for_each_probe(p, ctx) {
+				if (damon_pa_filter_pass(pa, folio, p))
+					r->probe_hits[i]++;
+				i++;
+			}
+			if (folio)
+				folio_put(folio);
+		}
+	}
+}
+
+/*
+ * 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;
+
+	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,
+		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 = NULL;
+
+	/* 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);
+	}
+
+	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);
+}
+
+static inline unsigned long damon_pa_de_activate(
+		struct damon_region *r, unsigned long addr_unit,
+		struct damos *s, bool activate,
+		unsigned long *sz_filter_passed)
+{
+	phys_addr_t addr, applied = 0;
+	struct folio *folio = NULL;
+
+	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 (activate)
+			folio_activate(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_activate_pages(struct damon_region *r,
+		unsigned long addr_unit, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	return damon_pa_de_activate(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_de_activate(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 = NULL;
+
+	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;
+		node_stat_add_folio(folio, NR_ISOLATED_ANON +
+				folio_is_file_lru(folio));
+		list_add(&folio->lru, &folio_list);
+put_folio:
+		addr += folio_size(folio);
+		folio_put(folio);
+	}
+	applied = damon_migrate_pages(&folio_list, s->target_nid);
+	cond_resched();
+	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 = NULL;
+
+	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_activate_pages(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,
+		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,
+		.apply_probes = damon_pa_apply_probes,
+		.target_valid = NULL,
+		.apply_scheme = damon_pa_apply_scheme,
+		.get_scheme_score = damon_pa_scheme_score,
+	};
+
+	return damon_register_ops(&ops);
+};
+
+subsys_initcall(damon_pa_initcall);

linux-7.2.3/mm/damon/reclaim.c

@@ -0,0 +1,483 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON-based page reclamation
+ */
+
+#define pr_fmt(fmt) "damon-reclaim: " fmt
+
+#include <linux/damon.h>
+#include <linux/kstrtox.h>
+#include <linux/module.h>
+
+#include "modules-common.h"
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "damon_reclaim."
+
+/*
+ * Enable or disable DAMON_RECLAIM.
+ *
+ * You can enable DAMON_RCLAIM by setting the value of this parameter as ``Y``.
+ * Setting it as ``N`` disables DAMON_RECLAIM.  Note that DAMON_RECLAIM could
+ * do no real monitoring and reclamation due to the watermarks-based activation
+ * condition.  Refer to below descriptions for the watermarks parameter for
+ * this.
+ */
+static bool enabled __read_mostly;
+
+/*
+ * Make DAMON_RECLAIM reads the input parameters again, except ``enabled``.
+ *
+ * Input parameters that updated while DAMON_RECLAIM is running are not applied
+ * by default.  Once this parameter is set as ``Y``, DAMON_RECLAIM reads values
+ * of parameters except ``enabled`` again.  Once the re-reading is done, this
+ * parameter is set as ``N``.  If invalid parameters are found while the
+ * re-reading, DAMON_RECLAIM will be disabled.
+ */
+static bool commit_inputs __read_mostly;
+
+/*
+ * Time threshold for cold memory regions identification in microseconds.
+ *
+ * If a memory region is not accessed for this or longer time, DAMON_RECLAIM
+ * identifies the region as cold, and reclaims.  120 seconds by default.
+ */
+static unsigned long min_age __read_mostly = 120000000;
+module_param(min_age, ulong, 0600);
+
+static struct damos_quota damon_reclaim_quota = {
+	/* use up to 10 ms time, reclaim up to 128 MiB per 1 sec by default */
+	.ms = 10,
+	.sz = 128 * 1024 * 1024,
+	.reset_interval = 1000,
+	/* Within the quota, page out older regions first. */
+	.weight_sz = 0,
+	.weight_nr_accesses = 0,
+	.weight_age = 1
+};
+DEFINE_DAMON_MODULES_DAMOS_QUOTAS(damon_reclaim_quota);
+
+/*
+ * Desired level of memory pressure-stall time in microseconds.
+ *
+ * While keeping the caps that set by other quotas, DAMON_RECLAIM automatically
+ * increases and decreases the effective level of the quota aiming this level of
+ * memory pressure is incurred.  System-wide ``some`` memory PSI in microseconds
+ * per quota reset interval (``quota_reset_interval_ms``) is collected and
+ * compared to this value to see if the aim is satisfied.  Value zero means
+ * disabling this auto-tuning feature.
+ *
+ * Disabled by default.
+ */
+static unsigned long quota_mem_pressure_us __read_mostly;
+module_param(quota_mem_pressure_us, ulong, 0600);
+
+/*
+ * User-specifiable feedback for auto-tuning of the effective quota.
+ *
+ * While keeping the caps that set by other quotas, DAMON_RECLAIM automatically
+ * increases and decreases the effective level of the quota aiming receiving this
+ * feedback of value ``10,000`` from the user.  DAMON_RECLAIM assumes the feedback
+ * value and the quota are positively proportional.  Value zero means disabling
+ * this auto-tuning feature.
+ *
+ * Disabled by default.
+ *
+ */
+static unsigned long quota_autotune_feedback __read_mostly;
+module_param(quota_autotune_feedback, ulong, 0600);
+
+/*
+ * Auto-tune monitoring intervals.
+ *
+ * If this parameter is set as ``Y``, DAMON_RECLAIM automatically tunes DAMON's
+ * sampling and aggregation intervals.  The auto-tuning aims to capture
+ * meaningful amount of access events in each DAMON-snapshot, while keeping the
+ * sampling intervals 5 milliseconds in minimum, and 10 seconds in maximum.
+ * Setting this as ``N`` disables the auto-tuning.
+ *
+ * Disabled by default.
+ */
+static bool autotune_monitoring_intervals __read_mostly;
+module_param(autotune_monitoring_intervals, bool, 0600);
+
+static struct damos_watermarks damon_reclaim_wmarks = {
+	.metric = DAMOS_WMARK_FREE_MEM_RATE,
+	.interval = 5000000,	/* 5 seconds */
+	.high = 500,		/* 50 percent */
+	.mid = 400,		/* 40 percent */
+	.low = 200,		/* 20 percent */
+};
+DEFINE_DAMON_MODULES_WMARKS_PARAMS(damon_reclaim_wmarks);
+
+static struct damon_attrs damon_reclaim_mon_attrs = {
+	.sample_interval = 5000,	/* 5 ms */
+	.aggr_interval = 100000,	/* 100 ms */
+	.ops_update_interval = 0,
+	.min_nr_regions = 10,
+	.max_nr_regions = 1000,
+};
+DEFINE_DAMON_MODULES_MON_ATTRS_PARAMS(damon_reclaim_mon_attrs);
+
+/*
+ * Start of the target memory region in physical address.
+ *
+ * The start physical address of memory region that DAMON_RECLAIM will do work
+ * against.  By default, the system's entire physical memory is used as the
+ * region.
+ */
+static unsigned long monitor_region_start __read_mostly;
+module_param(monitor_region_start, ulong, 0600);
+
+/*
+ * End of the target memory region in physical address.
+ *
+ * The end physical address of memory region that DAMON_RECLAIM will do work
+ * against.  By default, the system's entire physical memory is used as the
+ * region.
+ */
+static unsigned long monitor_region_end __read_mostly;
+module_param(monitor_region_end, ulong, 0600);
+
+/*
+ * Scale factor for DAMON_RECLAIM to ops address conversion.
+ *
+ * This parameter must not be set to 0.
+ */
+static unsigned long addr_unit __read_mostly = 1;
+
+/*
+ * Skip anonymous pages reclamation.
+ *
+ * If this parameter is set as ``Y``, DAMON_RECLAIM does not reclaim anonymous
+ * pages.  By default, ``N``.
+ */
+static bool skip_anon __read_mostly;
+module_param(skip_anon, bool, 0600);
+
+static struct damos_stat damon_reclaim_stat;
+DEFINE_DAMON_MODULES_DAMOS_STATS_PARAMS(damon_reclaim_stat,
+		reclaim_tried_regions, reclaimed_regions, quota_exceeds);
+
+static struct damon_ctx *ctx;
+static struct damon_target *target;
+
+static struct damos *damon_reclaim_new_scheme(unsigned long aggr_interval)
+{
+	struct damos_access_pattern pattern = {
+		/* Find regions having PAGE_SIZE or larger size */
+		.min_sz_region = PAGE_SIZE,
+		.max_sz_region = ULONG_MAX,
+		/* and not accessed at all */
+		.min_nr_accesses = 0,
+		.max_nr_accesses = 0,
+		/* for min_age or more micro-seconds */
+		.min_age_region = min_age / aggr_interval,
+		.max_age_region = UINT_MAX,
+	};
+
+	return damon_new_scheme(
+			&pattern,
+			/* page out those, as soon as found */
+			DAMOS_PAGEOUT,
+			/* for each aggregation interval */
+			0,
+			/* under the quota. */
+			&damon_reclaim_quota,
+			/* (De)activate this according to the watermarks. */
+			&damon_reclaim_wmarks,
+			NUMA_NO_NODE);
+}
+
+static int damon_reclaim_apply_parameters(void)
+{
+	struct damon_ctx *param_ctx;
+	struct damon_target *param_target;
+	struct damon_attrs attrs;
+	struct damos *scheme;
+	struct damos_quota_goal *goal;
+	struct damos_filter *filter;
+	int err;
+
+	err = damon_modules_new_paddr_ctx_target(&param_ctx, &param_target);
+	if (err)
+		return err;
+
+	param_ctx->addr_unit = addr_unit;
+	param_ctx->min_region_sz = max(DAMON_MIN_REGION_SZ / addr_unit, 1);
+
+	if (!is_power_of_2(param_ctx->min_region_sz)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (!damon_reclaim_mon_attrs.aggr_interval) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	attrs = damon_reclaim_mon_attrs;
+	if (autotune_monitoring_intervals) {
+		attrs.sample_interval = 5000;
+		attrs.aggr_interval = 100000;
+		attrs.intervals_goal.access_bp = 40;
+		attrs.intervals_goal.aggrs = 3;
+		attrs.intervals_goal.min_sample_us = 5000;
+		attrs.intervals_goal.max_sample_us = 10 * 1000 * 1000;
+	}
+	err = damon_set_attrs(param_ctx, &attrs);
+	if (err)
+		goto out;
+
+	err = -ENOMEM;
+	scheme = damon_reclaim_new_scheme(attrs.aggr_interval);
+	if (!scheme)
+		goto out;
+	damon_set_schemes(param_ctx, &scheme, 1);
+
+	if (quota_mem_pressure_us) {
+		goal = damos_new_quota_goal(DAMOS_QUOTA_SOME_MEM_PSI_US,
+				quota_mem_pressure_us);
+		if (!goal)
+			goto out;
+		damos_add_quota_goal(&scheme->quota, goal);
+	}
+
+	if (quota_autotune_feedback) {
+		goal = damos_new_quota_goal(DAMOS_QUOTA_USER_INPUT, 10000);
+		if (!goal)
+			goto out;
+		goal->current_value = quota_autotune_feedback;
+		damos_add_quota_goal(&scheme->quota, goal);
+	}
+
+	if (skip_anon) {
+		filter = damos_new_filter(DAMOS_FILTER_TYPE_ANON, true, false);
+		if (!filter)
+			goto out;
+		damos_add_filter(scheme, filter);
+	}
+
+	err = damon_set_region_system_rams_default(param_target,
+			&monitor_region_start, &monitor_region_end,
+			param_ctx->addr_unit, param_ctx->min_region_sz);
+	if (err)
+		goto out;
+	err = damon_commit_ctx(ctx, param_ctx);
+out:
+	damon_destroy_ctx(param_ctx);
+	return err;
+}
+
+static int damon_reclaim_commit_inputs_fn(void *arg)
+{
+	return damon_reclaim_apply_parameters();
+}
+
+static bool damon_reclaim_damon_has_started;
+
+static int damon_reclaim_commit_inputs_store(const char *val,
+					     const struct kernel_param *kp)
+{
+	bool commit_inputs_request;
+	int err;
+	struct damon_call_control control = {
+		.fn = damon_reclaim_commit_inputs_fn,
+	};
+
+	if (!val) {
+		commit_inputs_request = true;
+	} else {
+		err = kstrtobool(val, &commit_inputs_request);
+		if (err)
+			return err;
+	}
+
+	if (!commit_inputs_request)
+		return 0;
+
+	/* Skip damon_call() if ctx has not successfully started. */
+	if (!damon_reclaim_damon_has_started)
+		return -EINVAL;
+
+	err = damon_call(ctx, &control);
+
+	return err ? err : control.return_code;
+}
+
+static const struct kernel_param_ops commit_inputs_param_ops = {
+	.flags = KERNEL_PARAM_OPS_FL_NOARG,
+	.set = damon_reclaim_commit_inputs_store,
+	.get = param_get_bool,
+};
+
+module_param_cb(commit_inputs, &commit_inputs_param_ops, &commit_inputs, 0600);
+
+static int damon_reclaim_damon_call_fn(void *arg)
+{
+	struct damon_ctx *c = arg;
+	struct damos *s;
+
+	/* update the stats parameter */
+	damon_for_each_scheme(s, c)
+		damon_reclaim_stat = s->stat;
+
+	return 0;
+}
+
+static struct damon_call_control call_control = {
+	.fn = damon_reclaim_damon_call_fn,
+	.repeat = true,
+};
+
+static int damon_reclaim_turn(bool on)
+{
+	int err;
+
+	if (!on)
+		return damon_stop(&ctx, 1);
+
+	err = damon_reclaim_apply_parameters();
+	if (err)
+		return err;
+
+	err = damon_start(&ctx, 1, true);
+	if (err)
+		return err;
+	if (!damon_reclaim_damon_has_started)
+		damon_reclaim_damon_has_started = true;
+	return damon_call(ctx, &call_control);
+}
+
+static int damon_reclaim_addr_unit_store(const char *val,
+		const struct kernel_param *kp)
+{
+	unsigned long input_addr_unit;
+	int err = kstrtoul(val, 0, &input_addr_unit);
+
+	if (err)
+		return err;
+	if (!input_addr_unit)
+		return -EINVAL;
+
+	addr_unit = input_addr_unit;
+	return 0;
+}
+
+static const struct kernel_param_ops addr_unit_param_ops = {
+	.set = damon_reclaim_addr_unit_store,
+	.get = param_get_ulong,
+};
+
+module_param_cb(addr_unit, &addr_unit_param_ops, &addr_unit, 0600);
+MODULE_PARM_DESC(addr_unit,
+	"Scale factor for DAMON_RECLAIM to ops address conversion (default: 1)");
+
+static bool damon_reclaim_enabled(void)
+{
+	if (!ctx)
+		return false;
+	return damon_is_running(ctx);
+}
+
+static int damon_reclaim_enabled_store(const char *val,
+		const struct kernel_param *kp)
+{
+	int err;
+
+	err = kstrtobool(val, &enabled);
+	if (err)
+		return err;
+
+	if (damon_reclaim_enabled() == enabled)
+		return 0;
+
+	/* Called before init function.  The function will handle this. */
+	if (!damon_initialized())
+		return 0;
+
+	/* damon_modules_new_paddr_ctx_target() in the init function failed. */
+	if (!ctx)
+		return -ENOMEM;
+
+	return damon_reclaim_turn(enabled);
+}
+
+static int damon_reclaim_enabled_load(char *buffer,
+		const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%c\n", damon_reclaim_enabled() ? 'Y' : 'N');
+}
+
+static const struct kernel_param_ops enabled_param_ops = {
+	.set = damon_reclaim_enabled_store,
+	.get = damon_reclaim_enabled_load,
+};
+
+module_param_cb(enabled, &enabled_param_ops, &enabled, 0600);
+MODULE_PARM_DESC(enabled,
+	"Enable or disable DAMON_RECLAIM (default: disabled)");
+
+static int damon_reclaim_kdamond_pid_store(const char *val,
+		const struct kernel_param *kp)
+{
+	/*
+	 * kdamond_pid is read-only, but kernel command line could write it.
+	 * Do nothing here.
+	 */
+	return 0;
+}
+
+static int damon_reclaim_kdamond_pid_load(char *buffer,
+		const struct kernel_param *kp)
+{
+	int kdamond_pid = -1;
+
+	if (ctx) {
+		kdamond_pid = damon_kdamond_pid(ctx);
+		if (kdamond_pid < 0)
+			kdamond_pid = -1;
+	}
+	return sprintf(buffer, "%d\n", kdamond_pid);
+}
+
+static const struct kernel_param_ops kdamond_pid_param_ops = {
+	.set = damon_reclaim_kdamond_pid_store,
+	.get = damon_reclaim_kdamond_pid_load,
+};
+
+/*
+ * PID of the DAMON thread
+ *
+ * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread.
+ * Else, -1.
+ */
+module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400);
+
+static int __init damon_reclaim_init(void)
+{
+	int err;
+
+	if (!damon_initialized()) {
+		err = -ENOMEM;
+		goto out;
+	}
+	err = damon_modules_new_paddr_ctx_target(&ctx, &target);
+	if (err)
+		goto out;
+
+	call_control.data = ctx;
+
+	/* 'enabled' has set before this function, probably via command line */
+	if (enabled)
+		err = damon_reclaim_turn(true);
+
+out:
+	if (err && enabled)
+		enabled = false;
+	return err;
+}
+
+module_init(damon_reclaim_init);

linux-7.2.3/mm/damon/stat.c

@@ -0,0 +1,327 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Shows data access monitoring results in simple metrics.
+ */
+
+#define pr_fmt(fmt) "damon-stat: " fmt
+
+#include <linux/damon.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sort.h>
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "damon_stat."
+
+static int damon_stat_enabled_store(
+		const char *val, const struct kernel_param *kp);
+
+static int damon_stat_enabled_load(char *buffer,
+		const struct kernel_param *kp);
+
+static const struct kernel_param_ops enabled_param_ops = {
+	.set = damon_stat_enabled_store,
+	.get = damon_stat_enabled_load,
+};
+
+static bool enabled __read_mostly = IS_ENABLED(
+	CONFIG_DAMON_STAT_ENABLED_DEFAULT);
+module_param_cb(enabled, &enabled_param_ops, NULL, 0600);
+MODULE_PARM_DESC(enabled, "Enable of disable DAMON_STAT");
+
+static unsigned long estimated_memory_bandwidth __read_mostly;
+module_param(estimated_memory_bandwidth, ulong, 0400);
+MODULE_PARM_DESC(estimated_memory_bandwidth,
+		"Estimated memory bandwidth usage in bytes per second");
+
+static long memory_idle_ms_percentiles[101] = {0,};
+module_param_array(memory_idle_ms_percentiles, long, NULL, 0400);
+MODULE_PARM_DESC(memory_idle_ms_percentiles,
+		"Memory idle time percentiles in milliseconds");
+
+static unsigned long aggr_interval_us;
+module_param(aggr_interval_us, ulong, 0400);
+MODULE_PARM_DESC(aggr_interval_us,
+		"Current tuned aggregation interval in microseconds");
+
+static struct damon_ctx *damon_stat_context;
+
+static unsigned long damon_stat_last_refresh_jiffies;
+
+static void damon_stat_set_estimated_memory_bandwidth(struct damon_ctx *c)
+{
+	struct damon_target *t;
+	struct damon_region *r;
+	unsigned long access_bytes = 0;
+
+	damon_for_each_target(t, c) {
+		damon_for_each_region(r, t)
+			access_bytes += (r->ar.end - r->ar.start) *
+				r->nr_accesses;
+	}
+	estimated_memory_bandwidth = access_bytes * USEC_PER_MSEC *
+		MSEC_PER_SEC / c->attrs.aggr_interval;
+}
+
+static int damon_stat_idletime(const struct damon_region *r)
+{
+	if (r->nr_accesses)
+		return -1 * (r->age + 1);
+	return r->age + 1;
+}
+
+static int damon_stat_cmp_regions(const void *a, const void *b)
+{
+	const struct damon_region *ra = *(const struct damon_region **)a;
+	const struct damon_region *rb = *(const struct damon_region **)b;
+
+	return damon_stat_idletime(ra) - damon_stat_idletime(rb);
+}
+
+static int damon_stat_sort_regions(struct damon_ctx *c,
+		struct damon_region ***sorted_ptr, int *nr_regions_ptr,
+		unsigned long *total_sz_ptr)
+{
+	struct damon_target *t;
+	struct damon_region *r;
+	struct damon_region **region_pointers;
+	unsigned int nr_regions = 0;
+	unsigned long total_sz = 0;
+
+	damon_for_each_target(t, c) {
+		/* there is only one target */
+		region_pointers = kmalloc_objs(*region_pointers,
+					       damon_nr_regions(t));
+		if (!region_pointers)
+			return -ENOMEM;
+		damon_for_each_region(r, t) {
+			region_pointers[nr_regions++] = r;
+			total_sz += r->ar.end - r->ar.start;
+		}
+	}
+	sort(region_pointers, nr_regions, sizeof(*region_pointers),
+			damon_stat_cmp_regions, NULL);
+	*sorted_ptr = region_pointers;
+	*nr_regions_ptr = nr_regions;
+	*total_sz_ptr = total_sz;
+	return 0;
+}
+
+static void damon_stat_set_idletime_percentiles(struct damon_ctx *c)
+{
+	struct damon_region **sorted_regions, *region;
+	int nr_regions;
+	unsigned long total_sz, accounted_bytes = 0;
+	int err, i, next_percentile = 0;
+
+	err = damon_stat_sort_regions(c, &sorted_regions, &nr_regions,
+			&total_sz);
+	if (err)
+		return;
+	for (i = 0; i < nr_regions; i++) {
+		region = sorted_regions[i];
+		accounted_bytes += region->ar.end - region->ar.start;
+		while (next_percentile <= accounted_bytes * 100 / total_sz)
+			memory_idle_ms_percentiles[next_percentile++] =
+				damon_stat_idletime(region) *
+				(long)c->attrs.aggr_interval / USEC_PER_MSEC;
+	}
+	kfree(sorted_regions);
+}
+
+static int damon_stat_damon_call_fn(void *data)
+{
+	struct damon_ctx *c = data;
+
+	/* avoid unnecessarily frequent stat update */
+	if (time_before_eq(jiffies, damon_stat_last_refresh_jiffies +
+				msecs_to_jiffies(5 * MSEC_PER_SEC)))
+		return 0;
+	damon_stat_last_refresh_jiffies = jiffies;
+
+	aggr_interval_us = c->attrs.aggr_interval;
+	damon_stat_set_estimated_memory_bandwidth(c);
+	damon_stat_set_idletime_percentiles(c);
+	return 0;
+}
+
+static struct damon_ctx *damon_stat_build_ctx(void)
+{
+	struct damon_ctx *ctx;
+	struct damon_attrs attrs;
+	struct damon_target *target;
+	unsigned long start = 0, end = 0;
+
+	ctx = damon_new_ctx();
+	if (!ctx)
+		return NULL;
+	attrs = (struct damon_attrs) {
+		.sample_interval = 5 * USEC_PER_MSEC,
+		.aggr_interval = 100 * USEC_PER_MSEC,
+		.ops_update_interval = 60 * USEC_PER_MSEC * MSEC_PER_SEC,
+		.min_nr_regions = 10,
+		.max_nr_regions = 1000,
+	};
+	/*
+	 * auto-tune sampling and aggregation interval aiming 4% DAMON-observed
+	 * accesses ratio, keeping sampling interval in [5ms, 10s] range.
+	 */
+	attrs.intervals_goal = (struct damon_intervals_goal) {
+		.access_bp = 400, .aggrs = 3,
+		.min_sample_us = 5000, .max_sample_us = 10000000,
+	};
+	if (damon_set_attrs(ctx, &attrs))
+		goto free_out;
+
+	if (damon_select_ops(ctx, DAMON_OPS_PADDR))
+		goto free_out;
+
+	target = damon_new_target();
+	if (!target)
+		goto free_out;
+	damon_add_target(ctx, target);
+	if (damon_set_region_system_rams_default(target, &start, &end,
+				ctx->addr_unit, ctx->min_region_sz))
+		goto free_out;
+	return ctx;
+free_out:
+	damon_destroy_ctx(ctx);
+	return NULL;
+}
+
+static struct damon_call_control call_control = {
+	.fn = damon_stat_damon_call_fn,
+	.repeat = true,
+};
+
+static int damon_stat_start(void)
+{
+	int err;
+
+	if (damon_stat_context) {
+		if (damon_is_running(damon_stat_context))
+			return -EAGAIN;
+		damon_destroy_ctx(damon_stat_context);
+	}
+
+	damon_stat_context = damon_stat_build_ctx();
+	if (!damon_stat_context)
+		return -ENOMEM;
+	err = damon_start(&damon_stat_context, 1, true);
+	if (err) {
+		damon_destroy_ctx(damon_stat_context);
+		damon_stat_context = NULL;
+		return err;
+	}
+
+	damon_stat_last_refresh_jiffies = jiffies;
+	call_control.data = damon_stat_context;
+	return damon_call(damon_stat_context, &call_control);
+}
+
+static void damon_stat_stop(void)
+{
+	damon_stop(&damon_stat_context, 1);
+	damon_destroy_ctx(damon_stat_context);
+	damon_stat_context = NULL;
+}
+
+static bool damon_stat_enabled(void)
+{
+	if (!damon_stat_context)
+		return false;
+	return damon_is_running(damon_stat_context);
+}
+
+static int damon_stat_enabled_store(
+		const char *val, const struct kernel_param *kp)
+{
+	int err;
+
+	err = kstrtobool(val, &enabled);
+	if (err)
+		return err;
+
+	if (damon_stat_enabled() == enabled)
+		return 0;
+
+	if (!damon_initialized())
+		/*
+		 * probably called from command line parsing (parse_args()).
+		 * Cannot call damon_new_ctx().  Let damon_stat_init() handle.
+		 */
+		return 0;
+
+	if (enabled)
+		return damon_stat_start();
+	damon_stat_stop();
+	return 0;
+}
+
+static int damon_stat_enabled_load(char *buffer, const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%c\n", damon_stat_enabled() ? 'Y' : 'N');
+}
+
+static int damon_stat_kdamond_pid_store(
+		const char *val, const struct kernel_param *kp)
+{
+	/*
+	 * kdamond_pid is read-only, but kernel command line could write it.
+	 * Do nothing here.
+	 */
+	return 0;
+}
+
+static int damon_stat_kdamond_pid_load(
+		char *buffer, const struct kernel_param *kp)
+{
+	int pid;
+
+	if (!damon_stat_context) {
+		pid = -1;
+	} else {
+		pid = damon_kdamond_pid(damon_stat_context);
+		if (pid < 1)
+			pid = -1;
+	}
+	return sprintf(buffer, "%d\n", pid);
+}
+
+static const struct kernel_param_ops kdamond_pid_param_ops = {
+	.set = damon_stat_kdamond_pid_store,
+	.get = damon_stat_kdamond_pid_load,
+};
+
+/*
+ * PID of the DAMON thread
+ *
+ * If DAMON_STAT is enabled, this becomes the PID of the worker thread.
+ * Else, -1.
+ */
+module_param_cb(kdamond_pid, &kdamond_pid_param_ops, NULL, 0400);
+MODULE_PARM_DESC(kdamond_pid, "pid of the kdamond");
+
+static int __init damon_stat_init(void)
+{
+	int err = 0;
+
+	if (!damon_initialized()) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	/* probably set via command line */
+	if (enabled)
+		err = damon_stat_start();
+
+out:
+	if (err && enabled)
+		enabled = false;
+	return err;
+}
+
+module_init(damon_stat_init);

linux-7.2.3/mm/damon/sysfs-common.c

@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common Code for DAMON Sysfs Interface
+ */
+
+#include <linux/slab.h>
+
+#include "sysfs-common.h"
+
+DEFINE_MUTEX(damon_sysfs_lock);
+
+/*
+ * unsigned long range directory
+ */
+
+struct damon_sysfs_ul_range *damon_sysfs_ul_range_alloc(
+		unsigned long min,
+		unsigned long max)
+{
+	struct damon_sysfs_ul_range *range = kmalloc_obj(*range);
+
+	if (!range)
+		return NULL;
+	range->kobj = (struct kobject){};
+	range->min = min;
+	range->max = max;
+
+	return range;
+}
+
+static ssize_t min_show(struct kobject *kobj, struct kobj_attribute *attr,
+		char *buf)
+{
+	struct damon_sysfs_ul_range *range = container_of(kobj,
+			struct damon_sysfs_ul_range, kobj);
+
+	return sysfs_emit(buf, "%lu\n", range->min);
+}
+
+static ssize_t min_store(struct kobject *kobj, struct kobj_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct damon_sysfs_ul_range *range = container_of(kobj,
+			struct damon_sysfs_ul_range, kobj);
+	unsigned long min;
+	int err;
+
+	err = kstrtoul(buf, 0, &min);
+	if (err)
+		return err;
+
+	range->min = min;
+	return count;
+}
+
+static ssize_t max_show(struct kobject *kobj, struct kobj_attribute *attr,
+		char *buf)
+{
+	struct damon_sysfs_ul_range *range = container_of(kobj,
+			struct damon_sysfs_ul_range, kobj);
+
+	return sysfs_emit(buf, "%lu\n", range->max);
+}
+
+static ssize_t max_store(struct kobject *kobj, struct kobj_attribute *attr,
+		const char *buf, size_t count)
+{
+	struct damon_sysfs_ul_range *range = container_of(kobj,
+			struct damon_sysfs_ul_range, kobj);
+	unsigned long max;
+	int err;
+
+	err = kstrtoul(buf, 0, &max);
+	if (err)
+		return err;
+
+	range->max = max;
+	return count;
+}
+
+void damon_sysfs_ul_range_release(struct kobject *kobj)
+{
+	kfree(container_of(kobj, struct damon_sysfs_ul_range, kobj));
+}
+
+static struct kobj_attribute damon_sysfs_ul_range_min_attr =
+		__ATTR_RW_MODE(min, 0600);
+
+static struct kobj_attribute damon_sysfs_ul_range_max_attr =
+		__ATTR_RW_MODE(max, 0600);
+
+static struct attribute *damon_sysfs_ul_range_attrs[] = {
+	&damon_sysfs_ul_range_min_attr.attr,
+	&damon_sysfs_ul_range_max_attr.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(damon_sysfs_ul_range);
+
+const struct kobj_type damon_sysfs_ul_range_ktype = {
+	.release = damon_sysfs_ul_range_release,
+	.sysfs_ops = &kobj_sysfs_ops,
+	.default_groups = damon_sysfs_ul_range_groups,
+};
+
+
+static bool damon_sysfs_memcg_path_eq(struct mem_cgroup *memcg,
+		char *memcg_path_buf, char *path)
+{
+#ifdef CONFIG_MEMCG
+	cgroup_path(memcg->css.cgroup, memcg_path_buf, PATH_MAX);
+	if (sysfs_streq(memcg_path_buf, path))
+		return true;
+#endif /* CONFIG_MEMCG */
+	return false;
+}
+
+int damon_sysfs_memcg_path_to_id(char *memcg_path, u64 *id)
+{
+	struct mem_cgroup *memcg;
+	char *path;
+	bool found = false;
+
+	if (!memcg_path)
+		return -EINVAL;
+
+	path = kmalloc_array(PATH_MAX, sizeof(*path), GFP_KERNEL);
+	if (!path)
+		return -ENOMEM;
+
+	for (memcg = mem_cgroup_iter(NULL, NULL, NULL); memcg;
+			memcg = mem_cgroup_iter(NULL, memcg, NULL)) {
+		/* skip offlined memcg */
+		if (!mem_cgroup_online(memcg))
+			continue;
+		if (damon_sysfs_memcg_path_eq(memcg, path, memcg_path)) {
+			*id = mem_cgroup_id(memcg);
+			found = true;
+			mem_cgroup_iter_break(NULL, memcg);
+			break;
+		}
+	}
+
+	kfree(path);
+	return found ? 0 : -EINVAL;
+}

linux-7.2.3/mm/damon/sysfs-common.h

@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common Code for DAMON Sysfs Interface
+ */
+
+#include <linux/damon.h>
+#include <linux/kobject.h>
+
+extern struct mutex damon_sysfs_lock;
+
+struct damon_sysfs_ul_range {
+	struct kobject kobj;
+	unsigned long min;
+	unsigned long max;
+};
+
+struct damon_sysfs_ul_range *damon_sysfs_ul_range_alloc(
+		unsigned long min,
+		unsigned long max);
+void damon_sysfs_ul_range_release(struct kobject *kobj);
+
+extern const struct kobj_type damon_sysfs_ul_range_ktype;
+
+/*
+ * schemes directory
+ */
+
+struct damon_sysfs_schemes {
+	struct kobject kobj;
+	struct damon_sysfs_scheme **schemes_arr;
+	int nr;
+};
+
+struct damon_sysfs_schemes *damon_sysfs_schemes_alloc(void);
+void damon_sysfs_schemes_rm_dirs(struct damon_sysfs_schemes *schemes);
+
+extern const struct kobj_type damon_sysfs_schemes_ktype;
+
+int damon_sysfs_add_schemes(struct damon_ctx *ctx,
+		struct damon_sysfs_schemes *sysfs_schemes);
+
+void damon_sysfs_schemes_update_stats(
+		struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx);
+
+void damos_sysfs_populate_region_dir(struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx, struct damon_target *t,
+		struct damon_region *r, struct damos *s,
+		bool total_bytes_only, unsigned long sz_filter_passed);
+
+int damon_sysfs_schemes_clear_regions(
+		struct damon_sysfs_schemes *sysfs_schemes);
+
+int damos_sysfs_set_quota_scores(struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx);
+
+void damos_sysfs_update_effective_quotas(
+		struct damon_sysfs_schemes *sysfs_schemes,
+		struct damon_ctx *ctx);
+
+int damon_sysfs_memcg_path_to_id(char *memcg_path, u64 *id);

linux-7.2.3/mm/damon/tests/.kunitconfig

@@ -0,0 +1,18 @@
+# for DAMON core
+CONFIG_KUNIT=y
+CONFIG_DAMON=y
+CONFIG_DAMON_KUNIT_TEST=y
+
+# for DAMON vaddr ops
+CONFIG_MMU=y
+CONFIG_PAGE_IDLE_FLAG=y
+CONFIG_DAMON_VADDR=y
+CONFIG_DAMON_VADDR_KUNIT_TEST=y
+
+# for DAMON sysfs interface
+CONFIG_SYSFS=y
+CONFIG_DAMON_SYSFS=y
+CONFIG_DAMON_SYSFS_KUNIT_TEST=y
+
+# enable DAMON_DEBUG_SANITY to catch any bug
+CONFIG_DAMON_DEBUG_SANITY=y

linux-7.2.3/mm/damon/tests/sysfs-kunit.h

@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Data Access Monitor Unit Tests
+ */
+
+#ifdef CONFIG_DAMON_SYSFS_KUNIT_TEST
+
+#ifndef _DAMON_SYSFS_TEST_H
+#define _DAMON_SYSFS_TEST_H
+
+#include <kunit/test.h>
+
+static unsigned int nr_damon_targets(struct damon_ctx *ctx)
+{
+	struct damon_target *t;
+	unsigned int nr_targets = 0;
+
+	damon_for_each_target(t, ctx)
+		nr_targets++;
+
+	return nr_targets;
+}
+
+static int __damon_sysfs_test_get_any_pid(int min, int max)
+{
+	struct pid *pid;
+	int i;
+
+	for (i = min; i <= max; i++) {
+		pid = find_get_pid(i);
+		if (pid) {
+			put_pid(pid);
+			return i;
+		}
+	}
+	return -1;
+}
+
+static void damon_sysfs_test_add_targets(struct kunit *test)
+{
+	struct damon_sysfs_targets *sysfs_targets;
+	struct damon_sysfs_target *sysfs_target;
+	struct damon_ctx *ctx;
+
+	sysfs_targets = damon_sysfs_targets_alloc();
+	if (!sysfs_targets)
+		kunit_skip(test, "sysfs_targets alloc fail");
+	sysfs_targets->nr = 1;
+	sysfs_targets->targets_arr = kmalloc_objs(*sysfs_targets->targets_arr,
+						  1);
+	if (!sysfs_targets->targets_arr) {
+		kfree(sysfs_targets);
+		kunit_skip(test, "targets_arr alloc fail");
+	}
+
+	sysfs_target = damon_sysfs_target_alloc();
+	if (!sysfs_target) {
+		kfree(sysfs_targets->targets_arr);
+		kfree(sysfs_targets);
+		kunit_skip(test, "sysfs_target alloc fail");
+	}
+	sysfs_target->pid = __damon_sysfs_test_get_any_pid(12, 100);
+	sysfs_target->regions = damon_sysfs_regions_alloc();
+	if (!sysfs_target->regions) {
+		kfree(sysfs_targets->targets_arr);
+		kfree(sysfs_targets);
+		kfree(sysfs_target);
+		kunit_skip(test, "sysfs_regions alloc fail");
+	}
+
+	sysfs_targets->targets_arr[0] = sysfs_target;
+
+	ctx = damon_new_ctx();
+	if (!ctx) {
+		kfree(sysfs_targets->targets_arr);
+		kfree(sysfs_targets);
+		kfree(sysfs_target->regions);
+		kfree(sysfs_target);
+		kunit_skip(test, "ctx alloc fail");
+	}
+
+	damon_sysfs_add_targets(ctx, sysfs_targets);
+	KUNIT_EXPECT_EQ(test, 1u, nr_damon_targets(ctx));
+
+	sysfs_target->pid = __damon_sysfs_test_get_any_pid(
+			sysfs_target->pid + 1, 200);
+	damon_sysfs_add_targets(ctx, sysfs_targets);
+	KUNIT_EXPECT_EQ(test, 2u, nr_damon_targets(ctx));
+
+	damon_destroy_ctx(ctx);
+	kfree(sysfs_targets->targets_arr);
+	kfree(sysfs_targets);
+	kfree(sysfs_target->regions);
+	kfree(sysfs_target);
+}
+
+static struct kunit_case damon_sysfs_test_cases[] = {
+	KUNIT_CASE(damon_sysfs_test_add_targets),
+	{},
+};
+
+static struct kunit_suite damon_sysfs_test_suite = {
+	.name = "damon-sysfs",
+	.test_cases = damon_sysfs_test_cases,
+};
+kunit_test_suite(damon_sysfs_test_suite);
+
+#endif /* _DAMON_SYSFS_TEST_H */
+
+#endif /* CONFIG_DAMON_SYSFS_KUNIT_TEST */

linux-7.2.3/mm/damon/tests/vaddr-kunit.h

@@ -0,0 +1,281 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Data Access Monitor Unit Tests
+ */
+
+#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
+
+#ifndef _DAMON_VADDR_TEST_H
+#define _DAMON_VADDR_TEST_H
+
+#include <kunit/test.h>
+
+static int __link_vmas(struct maple_tree *mt, struct vm_area_struct *vmas,
+			ssize_t nr_vmas)
+{
+	int i, ret = -ENOMEM;
+	MA_STATE(mas, mt, 0, 0);
+
+	if (!nr_vmas)
+		return 0;
+
+	mas_lock(&mas);
+	for (i = 0; i < nr_vmas; i++) {
+		mas_set_range(&mas, vmas[i].vm_start, vmas[i].vm_end - 1);
+		if (mas_store_gfp(&mas, &vmas[i], GFP_KERNEL))
+			goto failed;
+	}
+
+	ret = 0;
+failed:
+	mas_unlock(&mas);
+	return ret;
+}
+
+/*
+ * Test __damon_va_three_regions() function
+ *
+ * In case of virtual memory address spaces monitoring, DAMON converts the
+ * complex and dynamic memory mappings of each target task to three
+ * discontiguous regions which cover every mapped areas.  However, the three
+ * regions should not include the two biggest unmapped areas in the original
+ * mapping, because the two biggest areas are normally the areas between 1)
+ * heap and the mmap()-ed regions, and 2) the mmap()-ed regions and stack.
+ * Because these two unmapped areas are very huge but obviously never accessed,
+ * covering the region is just a waste.
+ *
+ * '__damon_va_three_regions() receives an address space of a process.  It
+ * first identifies the start of mappings, end of mappings, and the two biggest
+ * unmapped areas.  After that, based on the information, it constructs the
+ * three regions and returns.  For more detail, refer to the comment of
+ * 'damon_init_regions_of()' function definition in 'mm/damon.c' file.
+ *
+ * For example, suppose virtual address ranges of 10-20, 20-25, 200-210,
+ * 210-220, 300-305, and 307-330 (Other comments represent this mappings in
+ * more short form: 10-20-25, 200-210-220, 300-305, 307-330) of a process are
+ * mapped.  To cover every mappings, the three regions should start with 10,
+ * and end with 305.  The process also has three unmapped areas, 25-200,
+ * 220-300, and 305-307.  Among those, 25-200 and 220-300 are the biggest two
+ * unmapped areas, and thus it should be converted to three regions of 10-25,
+ * 200-220, and 300-330.
+ */
+static void damon_test_three_regions_in_vmas(struct kunit *test)
+{
+	static struct mm_struct mm;
+	struct damon_addr_range regions[3] = {0};
+	/* 10-20-25, 200-210-220, 300-305, 307-330 */
+	static struct vm_area_struct vmas[] = {
+		(struct vm_area_struct) {.vm_start = 10, .vm_end = 20},
+		(struct vm_area_struct) {.vm_start = 20, .vm_end = 25},
+		(struct vm_area_struct) {.vm_start = 200, .vm_end = 210},
+		(struct vm_area_struct) {.vm_start = 210, .vm_end = 220},
+		(struct vm_area_struct) {.vm_start = 300, .vm_end = 305},
+		(struct vm_area_struct) {.vm_start = 307, .vm_end = 330},
+	};
+
+	mt_init_flags(&mm.mm_mt, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_USE_RCU);
+	if (__link_vmas(&mm.mm_mt, vmas, ARRAY_SIZE(vmas)))
+		kunit_skip(test, "Failed to create VMA tree");
+
+	__damon_va_three_regions(&mm, regions);
+
+	KUNIT_EXPECT_EQ(test, 10ul, regions[0].start);
+	KUNIT_EXPECT_EQ(test, 25ul, regions[0].end);
+	KUNIT_EXPECT_EQ(test, 200ul, regions[1].start);
+	KUNIT_EXPECT_EQ(test, 220ul, regions[1].end);
+	KUNIT_EXPECT_EQ(test, 300ul, regions[2].start);
+	KUNIT_EXPECT_EQ(test, 330ul, regions[2].end);
+}
+
+static struct damon_region *__nth_region_of(struct damon_target *t, int idx)
+{
+	struct damon_region *r;
+	unsigned int i = 0;
+
+	damon_for_each_region(r, t) {
+		if (i++ == idx)
+			return r;
+	}
+
+	return NULL;
+}
+
+/*
+ * Test 'damon_set_regions()'
+ *
+ * test			kunit object
+ * regions		an array containing start/end addresses of current
+ *			monitoring target regions
+ * nr_regions		the number of the addresses in 'regions'
+ * three_regions	The three regions that need to be applied now
+ * expected		start/end addresses of monitoring target regions that
+ *			'three_regions' are applied
+ * nr_expected		the number of addresses in 'expected'
+ *
+ * The memory mapping of the target processes changes dynamically.  To follow
+ * the change, DAMON periodically reads the mappings, simplifies it to the
+ * three regions, and updates the monitoring target regions to fit in the three
+ * regions.  The update of current target regions is the role of
+ * 'damon_set_regions()'.
+ *
+ * This test passes the given target regions and the new three regions that
+ * need to be applied to the function and check whether it updates the regions
+ * as expected.
+ */
+static void damon_do_test_apply_three_regions(struct kunit *test,
+				unsigned long *regions, int nr_regions,
+				struct damon_addr_range *three_regions,
+				unsigned long *expected, int nr_expected)
+{
+	struct damon_target *t;
+	struct damon_addr_range *ranges;
+	struct damon_region *r;
+	int i;
+
+	t = damon_new_target();
+	if (!t)
+		kunit_skip(test, "target alloc fail");
+
+	ranges = kmalloc_array(nr_regions / 2, sizeof(*ranges), GFP_KERNEL);
+	if (!ranges) {
+		damon_destroy_target(t, NULL);
+		kunit_skip(test, "ranges alloc fail");
+	}
+	for (i = 0; i < nr_regions / 2; i++) {
+		ranges[i].start = regions[i * 2];
+		ranges[i].end = regions[i * 2 + 1];
+	}
+	if (damon_set_regions(t, ranges, nr_regions / 2,
+				DAMON_MIN_REGION_SZ)) {
+		kfree(ranges);
+		damon_destroy_target(t, NULL);
+		kunit_skip(test, "damon_set_regions() fail");
+	}
+	kfree(ranges);
+
+	if (damon_set_regions(t, three_regions, 3, DAMON_MIN_REGION_SZ)) {
+		damon_destroy_target(t, NULL);
+		kunit_skip(test, "second damon_set_regions() fail");
+	}
+
+	for (i = 0; i < nr_expected / 2; i++) {
+		r = __nth_region_of(t, i);
+		KUNIT_EXPECT_EQ(test, r->ar.start, expected[i * 2]);
+		KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
+	}
+
+	damon_destroy_target(t, NULL);
+}
+
+/*
+ * This function test most common case where the three big regions are only
+ * slightly changed.  Target regions should adjust their boundary (10-20-30,
+ * 50-55, 70-80, 90-100) to fit with the new big regions or remove target
+ * regions (57-79) that now out of the three regions.
+ */
+static void damon_test_apply_three_regions1(struct kunit *test)
+{
+	/* 10-20-30, 50-55-57-59, 70-80-90-100 */
+	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+				70, 80, 80, 90, 90, 100};
+	/* 5-27, 45-55, 73-104 */
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 27},
+		(struct damon_addr_range){.start = 45, .end = 55},
+		(struct damon_addr_range){.start = 73, .end = 104} };
+	/* 5-20-27, 45-55, 73-80-90-104 */
+	unsigned long expected[] = {5, 20, 20, 27, 45, 55,
+				73, 80, 80, 90, 90, 104};
+
+	damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+			new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+/*
+ * Test slightly bigger change.  Similar to above, but the second big region
+ * now require two target regions (50-55, 57-59) to be removed.
+ */
+static void damon_test_apply_three_regions2(struct kunit *test)
+{
+	/* 10-20-30, 50-55-57-59, 70-80-90-100 */
+	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+				70, 80, 80, 90, 90, 100};
+	/* 5-27, 56-57, 65-104 */
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 27},
+		(struct damon_addr_range){.start = 56, .end = 57},
+		(struct damon_addr_range){.start = 65, .end = 104} };
+	/* 5-20-27, 56-57, 65-80-90-104 */
+	unsigned long expected[] = {5, 20, 20, 27, 56, 57,
+				65, 80, 80, 90, 90, 104};
+
+	damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+			new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+/*
+ * Test a big change.  The second big region has totally freed and mapped to
+ * different area (50-59 -> 61-63).  The target regions which were in the old
+ * second big region (50-55-57-59) should be removed and new target region
+ * covering the second big region (61-63) should be created.
+ */
+static void damon_test_apply_three_regions3(struct kunit *test)
+{
+	/* 10-20-30, 50-55-57-59, 70-80-90-100 */
+	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+				70, 80, 80, 90, 90, 100};
+	/* 5-27, 61-63, 65-104 */
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 27},
+		(struct damon_addr_range){.start = 61, .end = 63},
+		(struct damon_addr_range){.start = 65, .end = 104} };
+	/* 5-20-27, 61-63, 65-80-90-104 */
+	unsigned long expected[] = {5, 20, 20, 27, 61, 63,
+				65, 80, 80, 90, 90, 104};
+
+	damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+			new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+/*
+ * Test another big change.  Both of the second and third big regions (50-59
+ * and 70-100) has totally freed and mapped to different area (30-32 and
+ * 65-68).  The target regions which were in the old second and third big
+ * regions should now be removed and new target regions covering the new second
+ * and third big regions should be created.
+ */
+static void damon_test_apply_three_regions4(struct kunit *test)
+{
+	/* 10-20-30, 50-55-57-59, 70-80-90-100 */
+	unsigned long regions[] = {10, 20, 20, 30, 50, 55, 55, 57, 57, 59,
+				70, 80, 80, 90, 90, 100};
+	/* 5-7, 30-32, 65-68 */
+	struct damon_addr_range new_three_regions[3] = {
+		(struct damon_addr_range){.start = 5, .end = 7},
+		(struct damon_addr_range){.start = 30, .end = 32},
+		(struct damon_addr_range){.start = 65, .end = 68} };
+	/* expect 5-7, 30-32, 65-68 */
+	unsigned long expected[] = {5, 7, 30, 32, 65, 68};
+
+	damon_do_test_apply_three_regions(test, regions, ARRAY_SIZE(regions),
+			new_three_regions, expected, ARRAY_SIZE(expected));
+}
+
+static struct kunit_case damon_test_cases[] = {
+	KUNIT_CASE(damon_test_three_regions_in_vmas),
+	KUNIT_CASE(damon_test_apply_three_regions1),
+	KUNIT_CASE(damon_test_apply_three_regions2),
+	KUNIT_CASE(damon_test_apply_three_regions3),
+	KUNIT_CASE(damon_test_apply_three_regions4),
+	{},
+};
+
+static struct kunit_suite damon_test_suite = {
+	.name = "damon-operations",
+	.test_cases = damon_test_cases,
+};
+kunit_test_suite(damon_test_suite);
+
+#endif /* _DAMON_VADDR_TEST_H */
+
+#endif	/* CONFIG_DAMON_VADDR_KUNIT_TEST */

linux-7.2.3/mm/damon/vaddr.c

@@ -0,0 +1,989 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON Code for Virtual Address Spaces
+ */
+
+#define pr_fmt(fmt) "damon-va: " fmt
+
+#include <linux/highmem.h>
+#include <linux/hugetlb.h>
+#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/pagewalk.h>
+#include <linux/sched/mm.h>
+
+#include "../internal.h"
+#include "ops-common.h"
+
+#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
+#undef DAMON_MIN_REGION_SZ
+#define DAMON_MIN_REGION_SZ 1
+#endif
+
+/*
+ * 't->pid' should be the pointer to the relevant 'struct pid' having reference
+ * count.  Caller must put the returned task, unless it is NULL.
+ */
+static inline struct task_struct *damon_get_task_struct(struct damon_target *t)
+{
+	return get_pid_task(t->pid, PIDTYPE_PID);
+}
+
+/*
+ * Get the mm_struct of the given target
+ *
+ * Caller _must_ put the mm_struct after use, unless it is NULL.
+ *
+ * Returns the mm_struct of the target on success, NULL on failure
+ */
+static struct mm_struct *damon_get_mm(struct damon_target *t)
+{
+	struct task_struct *task;
+	struct mm_struct *mm;
+
+	task = damon_get_task_struct(t);
+	if (!task)
+		return NULL;
+
+	mm = get_task_mm(task);
+	put_task_struct(task);
+	return mm;
+}
+
+static unsigned long sz_range(struct damon_addr_range *r)
+{
+	return r->end - r->start;
+}
+
+/*
+ * Find three regions separated by two biggest unmapped regions
+ *
+ * vma		the head vma of the target address space
+ * regions	an array of three address ranges that results will be saved
+ *
+ * This function receives an address space and finds three regions in it which
+ * separated by the two biggest unmapped regions in the space.  Please refer to
+ * below comments of '__damon_va_init_regions()' function to know why this is
+ * necessary.
+ *
+ * Returns 0 if success, or negative error code otherwise.
+ */
+static int __damon_va_three_regions(struct mm_struct *mm,
+				       struct damon_addr_range regions[3])
+{
+	struct damon_addr_range first_gap = {0}, second_gap = {0};
+	VMA_ITERATOR(vmi, mm, 0);
+	struct vm_area_struct *vma, *prev = NULL;
+	unsigned long start;
+
+	/*
+	 * Find the two biggest gaps so that first_gap > second_gap > others.
+	 * If this is too slow, it can be optimised to examine the maple
+	 * tree gaps.
+	 */
+	rcu_read_lock();
+	for_each_vma(vmi, vma) {
+		unsigned long gap;
+
+		if (!prev) {
+			start = vma->vm_start;
+			goto next;
+		}
+		gap = vma->vm_start - prev->vm_end;
+
+		if (gap > sz_range(&first_gap)) {
+			second_gap = first_gap;
+			first_gap.start = prev->vm_end;
+			first_gap.end = vma->vm_start;
+		} else if (gap > sz_range(&second_gap)) {
+			second_gap.start = prev->vm_end;
+			second_gap.end = vma->vm_start;
+		}
+next:
+		prev = vma;
+	}
+	rcu_read_unlock();
+
+	if (!sz_range(&second_gap) || !sz_range(&first_gap))
+		return -EINVAL;
+
+	/* Sort the two biggest gaps by address */
+	if (first_gap.start > second_gap.start)
+		swap(first_gap, second_gap);
+
+	/* Store the result */
+	regions[0].start = ALIGN(start, DAMON_MIN_REGION_SZ);
+	regions[0].end = ALIGN(first_gap.start, DAMON_MIN_REGION_SZ);
+	regions[1].start = ALIGN(first_gap.end, DAMON_MIN_REGION_SZ);
+	regions[1].end = ALIGN(second_gap.start, DAMON_MIN_REGION_SZ);
+	regions[2].start = ALIGN(second_gap.end, DAMON_MIN_REGION_SZ);
+	regions[2].end = ALIGN(prev->vm_end, DAMON_MIN_REGION_SZ);
+
+	return 0;
+}
+
+/*
+ * Get the three regions in the given target (task)
+ *
+ * Returns 0 on success, negative error code otherwise.
+ */
+static int damon_va_three_regions(struct damon_target *t,
+				struct damon_addr_range regions[3])
+{
+	struct mm_struct *mm;
+	int rc;
+
+	mm = damon_get_mm(t);
+	if (!mm)
+		return -EINVAL;
+
+	mmap_read_lock(mm);
+	rc = __damon_va_three_regions(mm, regions);
+	mmap_read_unlock(mm);
+
+	mmput(mm);
+	return rc;
+}
+
+/*
+ * Initialize the monitoring target regions for the given target (task)
+ *
+ * t	the given target
+ *
+ * Because only a number of small portions of the entire address space
+ * is actually mapped to the memory and accessed, monitoring the unmapped
+ * regions is wasteful.  That said, because we can deal with small noises,
+ * tracking every mapping is not strictly required but could even incur a high
+ * overhead if the mapping frequently changes or the number of mappings is
+ * high.  The adaptive regions adjustment mechanism will further help to deal
+ * with the noise by simply identifying the unmapped areas as a region that
+ * has no access.  Moreover, applying the real mappings that would have many
+ * unmapped areas inside will make the adaptive mechanism quite complex.  That
+ * said, too huge unmapped areas inside the monitoring target should be removed
+ * to not take the time for the adaptive mechanism.
+ *
+ * For the reason, we convert the complex mappings to three distinct regions
+ * that cover every mapped area of the address space.  Also the two gaps
+ * between the three regions are the two biggest unmapped areas in the given
+ * address space.  In detail, this function first identifies the start and the
+ * end of the mappings and the two biggest unmapped areas of the address space.
+ * Then, it constructs the three regions as below:
+ *
+ *     [mappings[0]->start, big_two_unmapped_areas[0]->start)
+ *     [big_two_unmapped_areas[0]->end, big_two_unmapped_areas[1]->start)
+ *     [big_two_unmapped_areas[1]->end, mappings[nr_mappings - 1]->end)
+ *
+ * As usual memory map of processes is as below, the gap between the heap and
+ * the uppermost mmap()-ed region, and the gap between the lowermost mmap()-ed
+ * region and the stack will be two biggest unmapped regions.  Because these
+ * gaps are exceptionally huge areas in usual address space, excluding these
+ * two biggest unmapped regions will be sufficient to make a trade-off.
+ *
+ *   <heap>
+ *   <BIG UNMAPPED REGION 1>
+ *   <uppermost mmap()-ed region>
+ *   (other mmap()-ed regions and small unmapped regions)
+ *   <lowermost mmap()-ed region>
+ *   <BIG UNMAPPED REGION 2>
+ *   <stack>
+ */
+static void __damon_va_init_regions(struct damon_ctx *ctx,
+				     struct damon_target *t)
+{
+	struct damon_target *ti;
+	struct damon_addr_range regions[3];
+	int tidx = 0;
+
+	if (damon_va_three_regions(t, regions)) {
+		damon_for_each_target(ti, ctx) {
+			if (ti == t)
+				break;
+			tidx++;
+		}
+		pr_debug("Failed to get three regions of %dth target\n", tidx);
+		return;
+	}
+
+	damon_set_regions(t, regions, 3, DAMON_MIN_REGION_SZ);
+}
+
+/* Initialize '->regions_list' of every target (task) */
+static void damon_va_init(struct damon_ctx *ctx)
+{
+	struct damon_target *t;
+
+	damon_for_each_target(t, ctx) {
+		/* the user may set the target regions as they want */
+		if (!damon_nr_regions(t))
+			__damon_va_init_regions(ctx, t);
+	}
+}
+
+/*
+ * Update regions for current memory mappings
+ */
+static void damon_va_update(struct damon_ctx *ctx)
+{
+	struct damon_addr_range three_regions[3];
+	struct damon_target *t;
+
+	damon_for_each_target(t, ctx) {
+		if (damon_va_three_regions(t, three_regions))
+			continue;
+		damon_set_regions(t, three_regions, 3, DAMON_MIN_REGION_SZ);
+	}
+}
+
+static void damon_va_walk_page_range(struct mm_struct *mm, unsigned long start,
+		unsigned long end, struct mm_walk_ops *ops, void *private)
+{
+	struct vm_area_struct *vma;
+
+	vma = lock_vma_under_rcu(mm, start);
+	if (!vma)
+		goto lock_mmap;
+
+	if (end > vma->vm_end) {
+		vma_end_read(vma);
+		goto lock_mmap;
+	}
+
+	if (!(vma->vm_flags & VM_PFNMAP)) {
+		ops->walk_lock = PGWALK_VMA_RDLOCK_VERIFY;
+		walk_page_range_vma(vma, start, end, ops, private);
+	}
+
+	vma_end_read(vma);
+	return;
+
+lock_mmap:
+	mmap_read_lock(mm);
+	ops->walk_lock = PGWALK_RDLOCK;
+	walk_page_range(mm, start, end, ops, private);
+	mmap_read_unlock(mm);
+}
+
+static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
+		unsigned long next, struct mm_walk *walk)
+{
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	ptl = pmd_trans_huge_lock(pmd, walk->vma);
+	if (ptl) {
+		pmd_t pmde = pmdp_get(pmd);
+
+		if (pmd_present(pmde))
+			damon_pmdp_mkold(pmd, walk->vma, addr);
+		spin_unlock(ptl);
+		return 0;
+	}
+
+	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte)
+		return 0;
+	if (!pte_present(ptep_get(pte)))
+		goto out;
+	damon_ptep_mkold(pte, walk->vma, addr);
+out:
+	pte_unmap_unlock(pte, ptl);
+	return 0;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static void damon_hugetlb_mkold(pte_t *pte, struct mm_struct *mm,
+				struct vm_area_struct *vma, unsigned long addr)
+{
+	bool referenced = false;
+	pte_t entry = huge_ptep_get(mm, addr, pte);
+	struct folio *folio = pfn_folio(pte_pfn(entry));
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	folio_get(folio);
+
+	if (pte_young(entry)) {
+		referenced = true;
+		entry = pte_mkold(entry);
+		set_huge_pte_at(mm, addr, pte, entry, psize);
+	}
+
+	if (mmu_notifier_clear_young(mm, addr,
+				     addr + huge_page_size(hstate_vma(vma))))
+		referenced = true;
+
+	if (referenced)
+		folio_set_young(folio);
+
+	folio_set_idle(folio);
+	folio_put(folio);
+}
+
+static int damon_mkold_hugetlb_entry(pte_t *pte, unsigned long hmask,
+				     unsigned long addr, unsigned long end,
+				     struct mm_walk *walk)
+{
+	struct hstate *h = hstate_vma(walk->vma);
+	spinlock_t *ptl;
+	pte_t entry;
+
+	ptl = huge_pte_lock(h, walk->mm, pte);
+	entry = huge_ptep_get(walk->mm, addr, pte);
+	if (!pte_present(entry))
+		goto out;
+
+	damon_hugetlb_mkold(pte, walk->mm, walk->vma, addr);
+
+out:
+	spin_unlock(ptl);
+	return 0;
+}
+#else
+#define damon_mkold_hugetlb_entry NULL
+#endif /* CONFIG_HUGETLB_PAGE */
+
+static void damon_va_mkold(struct mm_struct *mm, unsigned long addr)
+{
+	struct mm_walk_ops damon_mkold_ops = {
+		.pmd_entry = damon_mkold_pmd_entry,
+		.hugetlb_entry = damon_mkold_hugetlb_entry,
+	};
+
+	damon_va_walk_page_range(mm, addr, addr + 1, &damon_mkold_ops, NULL);
+}
+
+/*
+ * Functions for the access checking of the regions
+ */
+
+static void __damon_va_prepare_access_check(struct mm_struct *mm,
+					struct damon_region *r,
+					struct damon_ctx *ctx)
+{
+	r->sampling_addr = damon_rand(ctx, r->ar.start, r->ar.end);
+
+	damon_va_mkold(mm, r->sampling_addr);
+}
+
+static void damon_va_prepare_access_checks(struct damon_ctx *ctx)
+{
+	struct damon_target *t;
+	struct mm_struct *mm;
+	struct damon_region *r;
+
+	damon_for_each_target(t, ctx) {
+		mm = damon_get_mm(t);
+		if (!mm)
+			continue;
+		damon_for_each_region(r, t)
+			__damon_va_prepare_access_check(mm, r, ctx);
+		mmput(mm);
+	}
+}
+
+struct damon_young_walk_private {
+	/* size of the folio for the access checked virtual memory address */
+	unsigned long *folio_sz;
+	bool young;
+};
+
+static int damon_young_pmd_entry(pmd_t *pmd, unsigned long addr,
+		unsigned long next, struct mm_walk *walk)
+{
+	pte_t *pte;
+	pte_t ptent;
+	spinlock_t *ptl;
+	struct folio *folio;
+	struct damon_young_walk_private *priv = walk->private;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	ptl = pmd_trans_huge_lock(pmd, walk->vma);
+	if (ptl) {
+		pmd_t pmde = pmdp_get(pmd);
+
+		if (!pmd_present(pmde))
+			goto huge_out;
+		folio = vm_normal_folio_pmd(walk->vma, addr, pmde);
+		if (!folio)
+			goto huge_out;
+		if (pmd_young(pmde) || !folio_test_idle(folio) ||
+					mmu_notifier_test_young(walk->mm,
+						addr))
+			priv->young = true;
+		*priv->folio_sz = HPAGE_PMD_SIZE;
+huge_out:
+		spin_unlock(ptl);
+		return 0;
+	}
+#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
+
+	pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte)
+		return 0;
+	ptent = ptep_get(pte);
+	if (!pte_present(ptent))
+		goto out;
+	folio = vm_normal_folio(walk->vma, addr, ptent);
+	if (!folio)
+		goto out;
+	if (pte_young(ptent) || !folio_test_idle(folio) ||
+			mmu_notifier_test_young(walk->mm, addr))
+		priv->young = true;
+	*priv->folio_sz = folio_size(folio);
+out:
+	pte_unmap_unlock(pte, ptl);
+	return 0;
+}
+
+#ifdef CONFIG_HUGETLB_PAGE
+static int damon_young_hugetlb_entry(pte_t *pte, unsigned long hmask,
+				     unsigned long addr, unsigned long end,
+				     struct mm_walk *walk)
+{
+	struct damon_young_walk_private *priv = walk->private;
+	struct hstate *h = hstate_vma(walk->vma);
+	struct folio *folio;
+	spinlock_t *ptl;
+	pte_t entry;
+
+	ptl = huge_pte_lock(h, walk->mm, pte);
+	entry = huge_ptep_get(walk->mm, addr, pte);
+	if (!pte_present(entry))
+		goto out;
+
+	folio = pfn_folio(pte_pfn(entry));
+	folio_get(folio);
+
+	if (pte_young(entry) || !folio_test_idle(folio) ||
+	    mmu_notifier_test_young(walk->mm, addr))
+		priv->young = true;
+	*priv->folio_sz = huge_page_size(h);
+
+	folio_put(folio);
+
+out:
+	spin_unlock(ptl);
+	return 0;
+}
+#else
+#define damon_young_hugetlb_entry NULL
+#endif /* CONFIG_HUGETLB_PAGE */
+
+static bool damon_va_young(struct mm_struct *mm, unsigned long addr,
+		unsigned long *folio_sz)
+{
+	struct damon_young_walk_private arg = {
+		.folio_sz = folio_sz,
+		.young = false,
+	};
+
+	struct mm_walk_ops damon_young_ops = {
+		.pmd_entry = damon_young_pmd_entry,
+		.hugetlb_entry = damon_young_hugetlb_entry,
+	};
+
+	damon_va_walk_page_range(mm, addr, addr + 1, &damon_young_ops, &arg);
+	return arg.young;
+}
+
+/*
+ * Check whether the region was accessed after the last preparation
+ *
+ * mm	'mm_struct' for the given virtual address space
+ * r	the region to be checked
+ */
+static void __damon_va_check_access(struct mm_struct *mm,
+				struct damon_region *r, bool same_target,
+				struct damon_attrs *attrs)
+{
+	static unsigned long last_addr;
+	static unsigned long last_folio_sz = PAGE_SIZE;
+	static bool last_accessed;
+
+	if (!mm) {
+		damon_update_region_access_rate(r, false, attrs);
+		return;
+	}
+
+	/* If the region is in the last checked page, reuse the result */
+	if (same_target && (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_va_young(mm, r->sampling_addr, &last_folio_sz);
+	damon_update_region_access_rate(r, last_accessed, attrs);
+
+	last_addr = r->sampling_addr;
+}
+
+static unsigned int damon_va_check_accesses(struct damon_ctx *ctx)
+{
+	struct damon_target *t;
+	struct mm_struct *mm;
+	struct damon_region *r;
+	unsigned int max_nr_accesses = 0;
+	bool same_target;
+
+	damon_for_each_target(t, ctx) {
+		mm = damon_get_mm(t);
+		same_target = false;
+		damon_for_each_region(r, t) {
+			__damon_va_check_access(mm, r, same_target,
+					&ctx->attrs);
+			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
+			same_target = true;
+		}
+		if (mm)
+			mmput(mm);
+	}
+
+	return max_nr_accesses;
+}
+
+static bool damos_va_filter_young_match(struct damos_filter *filter,
+		struct folio *folio, struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep, pmd_t *pmdp)
+{
+	bool young = false;
+
+	if (ptep)
+		young = pte_young(ptep_get(ptep));
+	else if (pmdp)
+		young = pmd_young(pmdp_get(pmdp));
+
+	young = young || !folio_test_idle(folio) ||
+		mmu_notifier_test_young(vma->vm_mm, addr);
+
+	if (young && ptep)
+		damon_ptep_mkold(ptep, vma, addr);
+	else if (young && pmdp)
+		damon_pmdp_mkold(pmdp, vma, addr);
+
+	return young == filter->matching;
+}
+
+static bool damos_va_filter_out(struct damos *scheme, struct folio *folio,
+		struct vm_area_struct *vma, unsigned long addr,
+		pte_t *ptep, pmd_t *pmdp)
+{
+	struct damos_filter *filter;
+	bool matched;
+
+	if (scheme->core_filters_allowed)
+		return false;
+
+	damos_for_each_ops_filter(filter, scheme) {
+		/*
+		 * damos_folio_filter_match checks the young filter by doing an
+		 * rmap on the folio to find its page table. However, being the
+		 * vaddr scheme, we have direct access to the page tables, so
+		 * use that instead.
+		 */
+		if (filter->type == DAMOS_FILTER_TYPE_YOUNG)
+			matched = damos_va_filter_young_match(filter, folio,
+				vma, addr, ptep, pmdp);
+		else
+			matched = damos_folio_filter_match(filter, folio);
+
+		if (matched)
+			return !filter->allow;
+	}
+	return scheme->ops_filters_default_reject;
+}
+
+struct damos_va_migrate_private {
+	struct list_head *migration_lists;
+	struct damos *scheme;
+};
+
+/*
+ * Place the given folio in the migration_list corresponding to where the folio
+ * should be migrated.
+ *
+ * The algorithm used here is similar to weighted_interleave_nid()
+ */
+static void damos_va_migrate_dests_add(struct folio *folio,
+		struct vm_area_struct *vma, unsigned long addr,
+		struct damos_migrate_dests *dests,
+		struct list_head *migration_lists)
+{
+	pgoff_t ilx;
+	int order;
+	unsigned int target;
+	unsigned int weight_total = 0;
+	int i;
+
+	/*
+	 * If dests is empty, there is only one migration list corresponding
+	 * to s->target_nid.
+	 */
+	if (!dests->nr_dests) {
+		i = 0;
+		goto isolate;
+	}
+
+	order = folio_order(folio);
+	ilx = vma->vm_pgoff >> order;
+	ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order);
+
+	for (i = 0; i < dests->nr_dests; i++)
+		weight_total += dests->weight_arr[i];
+
+	/* If the total weights are somehow 0, don't migrate at all */
+	if (!weight_total)
+		return;
+
+	target = ilx % weight_total;
+	for (i = 0; i < dests->nr_dests; i++) {
+		if (target < dests->weight_arr[i])
+			break;
+		target -= dests->weight_arr[i];
+	}
+
+	/* If the folio is already in the right node, don't do anything */
+	if (folio_nid(folio) == dests->node_id_arr[i])
+		return;
+
+isolate:
+	if (!folio_isolate_lru(folio))
+		return;
+	node_stat_add_folio(folio, NR_ISOLATED_ANON +
+			folio_is_file_lru(folio));
+	list_add(&folio->lru, &migration_lists[i]);
+}
+
+static int damos_va_migrate_pmd_entry(pmd_t *pmd, unsigned long addr,
+		unsigned long next, struct mm_walk *walk)
+{
+	struct damos_va_migrate_private *priv = walk->private;
+	struct list_head *migration_lists = priv->migration_lists;
+	struct damos *s = priv->scheme;
+	struct damos_migrate_dests *dests = &s->migrate_dests;
+	struct folio *folio;
+	spinlock_t *ptl;
+	pte_t *start_pte, *pte, ptent;
+	int nr;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	ptl = pmd_trans_huge_lock(pmd, walk->vma);
+	if (ptl) {
+		pmd_t pmde = pmdp_get(pmd);
+
+		if (!pmd_present(pmde))
+			goto huge_out;
+		folio = vm_normal_folio_pmd(walk->vma, addr, pmde);
+		if (!folio)
+			goto huge_out;
+		if (damos_va_filter_out(s, folio, walk->vma, addr, NULL, pmd))
+			goto huge_out;
+		damos_va_migrate_dests_add(folio, walk->vma, addr, dests,
+				migration_lists);
+huge_out:
+		spin_unlock(ptl);
+		return 0;
+	}
+#endif	/* CONFIG_TRANSPARENT_HUGEPAGE */
+
+	start_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
+	if (!pte)
+		return 0;
+
+	for (; addr < next; pte += nr, addr += nr * PAGE_SIZE) {
+		nr = 1;
+		ptent = ptep_get(pte);
+
+		if (pte_none(ptent) || !pte_present(ptent))
+			continue;
+		folio = vm_normal_folio(walk->vma, addr, ptent);
+		if (!folio)
+			continue;
+		if (damos_va_filter_out(s, folio, walk->vma, addr, pte, NULL))
+			continue;
+		damos_va_migrate_dests_add(folio, walk->vma, addr, dests,
+				migration_lists);
+		nr = folio_nr_pages(folio);
+	}
+	pte_unmap_unlock(start_pte, ptl);
+	return 0;
+}
+
+/*
+ * Functions for the target validity check and cleanup
+ */
+
+static bool damon_va_target_valid(struct damon_target *t)
+{
+	struct task_struct *task;
+
+	task = damon_get_task_struct(t);
+	if (task) {
+		put_task_struct(task);
+		return true;
+	}
+
+	return false;
+}
+
+static void damon_va_cleanup_target(struct damon_target *t)
+{
+	put_pid(t->pid);
+}
+
+#ifndef CONFIG_ADVISE_SYSCALLS
+static unsigned long damos_madvise(struct damon_target *target,
+		struct damon_region *r, int behavior)
+{
+	return 0;
+}
+#else
+static unsigned long damos_madvise(struct damon_target *target,
+		struct damon_region *r, int behavior)
+{
+	struct mm_struct *mm;
+	unsigned long start = PAGE_ALIGN(r->ar.start);
+	unsigned long len = PAGE_ALIGN(damon_sz_region(r));
+	unsigned long applied;
+
+	mm = damon_get_mm(target);
+	if (!mm)
+		return 0;
+
+	applied = do_madvise(mm, start, len, behavior) ? 0 : len;
+	mmput(mm);
+
+	return applied;
+}
+#endif	/* CONFIG_ADVISE_SYSCALLS */
+
+static unsigned long damos_va_migrate(struct damon_target *target,
+		struct damon_region *r, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	LIST_HEAD(folio_list);
+	struct damos_va_migrate_private priv;
+	struct mm_struct *mm;
+	int nr_dests;
+	int nid;
+	bool use_target_nid;
+	unsigned long applied = 0;
+	struct damos_migrate_dests *dests = &s->migrate_dests;
+	struct mm_walk_ops walk_ops = {
+		.pmd_entry = damos_va_migrate_pmd_entry,
+		.pte_entry = NULL,
+	};
+
+	use_target_nid = dests->nr_dests == 0;
+	nr_dests = use_target_nid ? 1 : dests->nr_dests;
+	priv.scheme = s;
+	priv.migration_lists = kmalloc_objs(*priv.migration_lists, nr_dests);
+	if (!priv.migration_lists)
+		return 0;
+
+	for (int i = 0; i < nr_dests; i++)
+		INIT_LIST_HEAD(&priv.migration_lists[i]);
+
+
+	mm = damon_get_mm(target);
+	if (!mm)
+		goto free_lists;
+
+	damon_va_walk_page_range(mm, r->ar.start, r->ar.end, &walk_ops, &priv);
+	mmput(mm);
+
+	for (int i = 0; i < nr_dests; i++) {
+		nid = use_target_nid ? s->target_nid : dests->node_id_arr[i];
+		applied += damon_migrate_pages(&priv.migration_lists[i], nid);
+		cond_resched();
+	}
+
+free_lists:
+	kfree(priv.migration_lists);
+	return applied * PAGE_SIZE;
+}
+
+struct damos_va_stat_private {
+	struct damos *scheme;
+	unsigned long *sz_filter_passed;
+};
+
+static inline bool damos_va_invalid_folio(struct folio *folio,
+		struct damos *s)
+{
+	return !folio || folio == s->last_applied;
+}
+
+static int damos_va_stat_pmd_entry(pmd_t *pmd, unsigned long addr,
+		unsigned long next, struct mm_walk *walk)
+{
+	struct damos_va_stat_private *priv = walk->private;
+	struct damos *s = priv->scheme;
+	unsigned long *sz_filter_passed = priv->sz_filter_passed;
+	struct vm_area_struct *vma = walk->vma;
+	struct folio *folio;
+	spinlock_t *ptl;
+	pte_t *start_pte, *pte, ptent;
+	int nr;
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	ptl = pmd_trans_huge_lock(pmd, vma);
+	if (ptl) {
+		pmd_t pmde = pmdp_get(pmd);
+
+		if (!pmd_present(pmde))
+			goto huge_unlock;
+
+		folio = vm_normal_folio_pmd(vma, addr, pmde);
+
+		if (damos_va_invalid_folio(folio, s))
+			goto huge_unlock;
+
+		if (!damos_va_filter_out(s, folio, vma, addr, NULL, pmd))
+			*sz_filter_passed += folio_size(folio);
+		s->last_applied = folio;
+
+huge_unlock:
+		spin_unlock(ptl);
+		return 0;
+	}
+#endif
+	start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	if (!start_pte)
+		return 0;
+
+	for (; addr < next; pte += nr, addr += nr * PAGE_SIZE) {
+		nr = 1;
+		ptent = ptep_get(pte);
+
+		if (pte_none(ptent) || !pte_present(ptent))
+			continue;
+
+		folio = vm_normal_folio(vma, addr, ptent);
+
+		if (damos_va_invalid_folio(folio, s))
+			continue;
+
+		if (!damos_va_filter_out(s, folio, vma, addr, pte, NULL))
+			*sz_filter_passed += folio_size(folio);
+		nr = folio_nr_pages(folio);
+		s->last_applied = folio;
+	}
+	pte_unmap_unlock(start_pte, ptl);
+	return 0;
+}
+
+static unsigned long damos_va_stat(struct damon_target *target,
+		struct damon_region *r, struct damos *s,
+		unsigned long *sz_filter_passed)
+{
+	struct damos_va_stat_private priv;
+	struct mm_struct *mm;
+	struct mm_walk_ops walk_ops = {
+		.pmd_entry = damos_va_stat_pmd_entry,
+	};
+
+	priv.scheme = s;
+	priv.sz_filter_passed = sz_filter_passed;
+
+	if (!damos_ops_has_filter(s))
+		return 0;
+
+	mm = damon_get_mm(target);
+	if (!mm)
+		return 0;
+
+	damon_va_walk_page_range(mm, r->ar.start, r->ar.end, &walk_ops, &priv);
+	mmput(mm);
+	return 0;
+}
+
+static unsigned long damon_va_apply_scheme(struct damon_ctx *ctx,
+		struct damon_target *t, struct damon_region *r,
+		struct damos *scheme, unsigned long *sz_filter_passed)
+{
+	int madv_action;
+
+	switch (scheme->action) {
+	case DAMOS_WILLNEED:
+		madv_action = MADV_WILLNEED;
+		break;
+	case DAMOS_COLD:
+		madv_action = MADV_COLD;
+		break;
+	case DAMOS_PAGEOUT:
+		madv_action = MADV_PAGEOUT;
+		break;
+	case DAMOS_HUGEPAGE:
+		madv_action = MADV_HUGEPAGE;
+		break;
+	case DAMOS_NOHUGEPAGE:
+		madv_action = MADV_NOHUGEPAGE;
+		break;
+	case DAMOS_COLLAPSE:
+		madv_action = MADV_COLLAPSE;
+		break;
+	case DAMOS_MIGRATE_HOT:
+	case DAMOS_MIGRATE_COLD:
+		return damos_va_migrate(t, r, scheme, sz_filter_passed);
+	case DAMOS_STAT:
+		return damos_va_stat(t, r, scheme, sz_filter_passed);
+	default:
+		/*
+		 * DAMOS actions that are not yet supported by 'vaddr'.
+		 */
+		return 0;
+	}
+
+	return damos_madvise(t, r, madv_action);
+}
+
+static int damon_va_scheme_score(struct damon_ctx *context,
+		struct damon_region *r, struct damos *scheme)
+{
+
+	switch (scheme->action) {
+	case DAMOS_PAGEOUT:
+		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_va_initcall(void)
+{
+	struct damon_operations ops = {
+		.id = DAMON_OPS_VADDR,
+		.init = damon_va_init,
+		.update = damon_va_update,
+		.prepare_access_checks = damon_va_prepare_access_checks,
+		.check_accesses = damon_va_check_accesses,
+		.target_valid = damon_va_target_valid,
+		.cleanup_target = damon_va_cleanup_target,
+		.apply_scheme = damon_va_apply_scheme,
+		.get_scheme_score = damon_va_scheme_score,
+	};
+	/* ops for fixed virtual address ranges */
+	struct damon_operations ops_fvaddr = ops;
+	int err;
+
+	/* Don't set the monitoring target regions for the entire mapping */
+	ops_fvaddr.id = DAMON_OPS_FVADDR;
+	ops_fvaddr.init = NULL;
+	ops_fvaddr.update = NULL;
+
+	err = damon_register_ops(&ops);
+	if (err)
+		return err;
+	return damon_register_ops(&ops_fvaddr);
+};
+
+subsys_initcall(damon_va_initcall);
+
+#include "tests/vaddr-kunit.h"