summaryrefslogtreecommitdiff
path: root/mm/damon
diff options
context:
space:
mode:
Diffstat (limited to 'mm/damon')
-rw-r--r--mm/damon/Kconfig24
-rw-r--r--mm/damon/Makefile4
-rw-r--r--mm/damon/core.c446
-rw-r--r--mm/damon/dbgfs-test.h54
-rw-r--r--mm/damon/dbgfs.c430
-rw-r--r--mm/damon/paddr.c273
-rw-r--r--mm/damon/prmtv-common.c133
-rw-r--r--mm/damon/prmtv-common.h20
-rw-r--r--mm/damon/reclaim.c356
-rw-r--r--mm/damon/vaddr-test.h2
-rw-r--r--mm/damon/vaddr.c167
11 files changed, 1737 insertions, 172 deletions
diff --git a/mm/damon/Kconfig b/mm/damon/Kconfig
index 37024798a97c..5bcf05851ad0 100644
--- a/mm/damon/Kconfig
+++ b/mm/damon/Kconfig
@@ -30,7 +30,15 @@ config DAMON_VADDR
select PAGE_IDLE_FLAG
help
This builds the default data access monitoring primitives for DAMON
- that works for virtual address spaces.
+ that work for virtual address spaces.
+
+config DAMON_PADDR
+ bool "Data access monitoring primitives for the physical address space"
+ depends on DAMON && MMU
+ select PAGE_IDLE_FLAG
+ help
+ This builds the default data access monitoring primitives for DAMON
+ that works for the physical address space.
config DAMON_VADDR_KUNIT_TEST
bool "Test for DAMON primitives" if !KUNIT_ALL_TESTS
@@ -46,7 +54,7 @@ config DAMON_VADDR_KUNIT_TEST
config DAMON_DBGFS
bool "DAMON debugfs interface"
- depends on DAMON_VADDR && DEBUG_FS
+ depends on DAMON_VADDR && DAMON_PADDR && DEBUG_FS
help
This builds the debugfs interface for DAMON. The user space admins
can use the interface for arbitrary data access monitoring.
@@ -65,4 +73,16 @@ config DAMON_DBGFS_KUNIT_TEST
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.
+
endmenu
diff --git a/mm/damon/Makefile b/mm/damon/Makefile
index fed4be3bace3..f7d5ac377a2b 100644
--- a/mm/damon/Makefile
+++ b/mm/damon/Makefile
@@ -1,5 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_DAMON) := core.o
-obj-$(CONFIG_DAMON_VADDR) += vaddr.o
+obj-$(CONFIG_DAMON_VADDR) += prmtv-common.o vaddr.o
+obj-$(CONFIG_DAMON_PADDR) += prmtv-common.o paddr.o
obj-$(CONFIG_DAMON_DBGFS) += dbgfs.o
+obj-$(CONFIG_DAMON_RECLAIM) += reclaim.o
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 30e9211f494a..c381b3c525d0 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -10,8 +10,10 @@
#include <linux/damon.h>
#include <linux/delay.h>
#include <linux/kthread.h>
+#include <linux/mm.h>
#include <linux/random.h>
#include <linux/slab.h>
+#include <linux/string.h>
#define CREATE_TRACE_POINTS
#include <trace/events/damon.h>
@@ -45,6 +47,9 @@ struct damon_region *damon_new_region(unsigned long start, unsigned long end)
region->nr_accesses = 0;
INIT_LIST_HEAD(&region->list);
+ region->age = 0;
+ region->last_nr_accesses = 0;
+
return region;
}
@@ -82,6 +87,74 @@ void damon_destroy_region(struct damon_region *r, struct damon_target *t)
damon_free_region(r);
}
+struct damos *damon_new_scheme(
+ unsigned long min_sz_region, unsigned long max_sz_region,
+ unsigned int min_nr_accesses, unsigned int max_nr_accesses,
+ unsigned int min_age_region, unsigned int max_age_region,
+ enum damos_action action, struct damos_quota *quota,
+ struct damos_watermarks *wmarks)
+{
+ struct damos *scheme;
+
+ scheme = kmalloc(sizeof(*scheme), GFP_KERNEL);
+ if (!scheme)
+ return NULL;
+ scheme->min_sz_region = min_sz_region;
+ scheme->max_sz_region = max_sz_region;
+ scheme->min_nr_accesses = min_nr_accesses;
+ scheme->max_nr_accesses = max_nr_accesses;
+ scheme->min_age_region = min_age_region;
+ scheme->max_age_region = max_age_region;
+ scheme->action = action;
+ scheme->stat_count = 0;
+ scheme->stat_sz = 0;
+ INIT_LIST_HEAD(&scheme->list);
+
+ scheme->quota.ms = quota->ms;
+ scheme->quota.sz = quota->sz;
+ scheme->quota.reset_interval = quota->reset_interval;
+ scheme->quota.weight_sz = quota->weight_sz;
+ scheme->quota.weight_nr_accesses = quota->weight_nr_accesses;
+ scheme->quota.weight_age = quota->weight_age;
+ scheme->quota.total_charged_sz = 0;
+ scheme->quota.total_charged_ns = 0;
+ scheme->quota.esz = 0;
+ scheme->quota.charged_sz = 0;
+ scheme->quota.charged_from = 0;
+ scheme->quota.charge_target_from = NULL;
+ scheme->quota.charge_addr_from = 0;
+
+ scheme->wmarks.metric = wmarks->metric;
+ scheme->wmarks.interval = wmarks->interval;
+ scheme->wmarks.high = wmarks->high;
+ scheme->wmarks.mid = wmarks->mid;
+ scheme->wmarks.low = wmarks->low;
+ scheme->wmarks.activated = true;
+
+ return scheme;
+}
+
+void damon_add_scheme(struct damon_ctx *ctx, struct damos *s)
+{
+ list_add_tail(&s->list, &ctx->schemes);
+}
+
+static void damon_del_scheme(struct damos *s)
+{
+ list_del(&s->list);
+}
+
+static void damon_free_scheme(struct damos *s)
+{
+ kfree(s);
+}
+
+void damon_destroy_scheme(struct damos *s)
+{
+ damon_del_scheme(s);
+ damon_free_scheme(s);
+}
+
/*
* Construct a damon_target struct
*
@@ -107,6 +180,11 @@ void damon_add_target(struct damon_ctx *ctx, struct damon_target *t)
list_add_tail(&t->list, &ctx->adaptive_targets);
}
+bool damon_targets_empty(struct damon_ctx *ctx)
+{
+ return list_empty(&ctx->adaptive_targets);
+}
+
static void damon_del_target(struct damon_target *t)
{
list_del(&t->list);
@@ -153,6 +231,7 @@ struct damon_ctx *damon_new_ctx(void)
ctx->max_nr_regions = 1000;
INIT_LIST_HEAD(&ctx->adaptive_targets);
+ INIT_LIST_HEAD(&ctx->schemes);
return ctx;
}
@@ -172,7 +251,13 @@ static void damon_destroy_targets(struct damon_ctx *ctx)
void damon_destroy_ctx(struct damon_ctx *ctx)
{
+ struct damos *s, *next_s;
+
damon_destroy_targets(ctx);
+
+ damon_for_each_scheme_safe(s, next_s, ctx)
+ damon_destroy_scheme(s);
+
kfree(ctx);
}
@@ -248,6 +333,30 @@ int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
}
/**
+ * damon_set_schemes() - Set data access monitoring based operation schemes.
+ * @ctx: monitoring context
+ * @schemes: array of the schemes
+ * @nr_schemes: number of entries in @schemes
+ *
+ * This function should not be called while the kdamond of the context is
+ * running.
+ *
+ * Return: 0 if success, or negative error code otherwise.
+ */
+int damon_set_schemes(struct damon_ctx *ctx, struct damos **schemes,
+ ssize_t nr_schemes)
+{
+ struct damos *s, *next;
+ ssize_t i;
+
+ damon_for_each_scheme_safe(s, next, ctx)
+ damon_destroy_scheme(s);
+ for (i = 0; i < nr_schemes; i++)
+ damon_add_scheme(ctx, schemes[i]);
+ return 0;
+}
+
+/**
* damon_nr_running_ctxs() - Return number of currently running contexts.
*/
int damon_nr_running_ctxs(void)
@@ -281,17 +390,6 @@ static unsigned long damon_region_sz_limit(struct damon_ctx *ctx)
return sz;
}
-static bool damon_kdamond_running(struct damon_ctx *ctx)
-{
- bool running;
-
- mutex_lock(&ctx->kdamond_lock);
- running = ctx->kdamond != NULL;
- mutex_unlock(&ctx->kdamond_lock);
-
- return running;
-}
-
static int kdamond_fn(void *data);
/*
@@ -309,12 +407,11 @@ static int __damon_start(struct damon_ctx *ctx)
mutex_lock(&ctx->kdamond_lock);
if (!ctx->kdamond) {
err = 0;
- ctx->kdamond_stop = false;
ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d",
nr_running_ctxs);
if (IS_ERR(ctx->kdamond)) {
err = PTR_ERR(ctx->kdamond);
- ctx->kdamond = 0;
+ ctx->kdamond = NULL;
}
}
mutex_unlock(&ctx->kdamond_lock);
@@ -365,13 +462,15 @@ int damon_start(struct damon_ctx **ctxs, int nr_ctxs)
*/
static int __damon_stop(struct damon_ctx *ctx)
{
+ struct task_struct *tsk;
+
mutex_lock(&ctx->kdamond_lock);
- if (ctx->kdamond) {
- ctx->kdamond_stop = true;
+ tsk = ctx->kdamond;
+ if (tsk) {
+ get_task_struct(tsk);
mutex_unlock(&ctx->kdamond_lock);
- while (damon_kdamond_running(ctx))
- usleep_range(ctx->sample_interval,
- ctx->sample_interval * 2);
+ kthread_stop(tsk);
+ put_task_struct(tsk);
return 0;
}
mutex_unlock(&ctx->kdamond_lock);
@@ -444,11 +543,203 @@ static void kdamond_reset_aggregated(struct damon_ctx *c)
damon_for_each_region(r, t) {
trace_damon_aggregated(t, r, damon_nr_regions(t));
+ r->last_nr_accesses = r->nr_accesses;
r->nr_accesses = 0;
}
}
}
+static void damon_split_region_at(struct damon_ctx *ctx,
+ struct damon_target *t, struct damon_region *r,
+ unsigned long sz_r);
+
+static bool __damos_valid_target(struct damon_region *r, struct damos *s)
+{
+ unsigned long sz;
+
+ sz = r->ar.end - r->ar.start;
+ return s->min_sz_region <= sz && sz <= s->max_sz_region &&
+ s->min_nr_accesses <= r->nr_accesses &&
+ r->nr_accesses <= s->max_nr_accesses &&
+ s->min_age_region <= r->age && r->age <= s->max_age_region;
+}
+
+static bool damos_valid_target(struct damon_ctx *c, struct damon_target *t,
+ struct damon_region *r, struct damos *s)
+{
+ bool ret = __damos_valid_target(r, s);
+
+ if (!ret || !s->quota.esz || !c->primitive.get_scheme_score)
+ return ret;
+
+ return c->primitive.get_scheme_score(c, t, r, s) >= s->quota.min_score;
+}
+
+static void damon_do_apply_schemes(struct damon_ctx *c,
+ struct damon_target *t,
+ struct damon_region *r)
+{
+ struct damos *s;
+
+ damon_for_each_scheme(s, c) {
+ struct damos_quota *quota = &s->quota;
+ unsigned long sz = r->ar.end - r->ar.start;
+ struct timespec64 begin, end;
+
+ if (!s->wmarks.activated)
+ continue;
+
+ /* Check the quota */
+ if (quota->esz && quota->charged_sz >= quota->esz)
+ continue;
+
+ /* Skip previously charged regions */
+ if (quota->charge_target_from) {
+ if (t != quota->charge_target_from)
+ continue;
+ if (r == damon_last_region(t)) {
+ quota->charge_target_from = NULL;
+ quota->charge_addr_from = 0;
+ continue;
+ }
+ if (quota->charge_addr_from &&
+ r->ar.end <= quota->charge_addr_from)
+ continue;
+
+ if (quota->charge_addr_from && r->ar.start <
+ quota->charge_addr_from) {
+ sz = ALIGN_DOWN(quota->charge_addr_from -
+ r->ar.start, DAMON_MIN_REGION);
+ if (!sz) {
+ if (r->ar.end - r->ar.start <=
+ DAMON_MIN_REGION)
+ continue;
+ sz = DAMON_MIN_REGION;
+ }
+ damon_split_region_at(c, t, r, sz);
+ r = damon_next_region(r);
+ sz = r->ar.end - r->ar.start;
+ }
+ quota->charge_target_from = NULL;
+ quota->charge_addr_from = 0;
+ }
+
+ if (!damos_valid_target(c, t, r, s))
+ continue;
+
+ /* Apply the scheme */
+ if (c->primitive.apply_scheme) {
+ if (quota->esz &&
+ quota->charged_sz + sz > quota->esz) {
+ sz = ALIGN_DOWN(quota->esz - quota->charged_sz,
+ DAMON_MIN_REGION);
+ if (!sz)
+ goto update_stat;
+ damon_split_region_at(c, t, r, sz);
+ }
+ ktime_get_coarse_ts64(&begin);
+ c->primitive.apply_scheme(c, t, r, s);
+ ktime_get_coarse_ts64(&end);
+ quota->total_charged_ns += timespec64_to_ns(&end) -
+ timespec64_to_ns(&begin);
+ quota->charged_sz += sz;
+ if (quota->esz && quota->charged_sz >= quota->esz) {
+ quota->charge_target_from = t;
+ quota->charge_addr_from = r->ar.end + 1;
+ }
+ }
+ if (s->action != DAMOS_STAT)
+ r->age = 0;
+
+update_stat:
+ s->stat_count++;
+ s->stat_sz += sz;
+ }
+}
+
+/* Shouldn't be called if quota->ms and quota->sz are zero */
+static void damos_set_effective_quota(struct damos_quota *quota)
+{
+ unsigned long throughput;
+ unsigned long esz;
+
+ if (!quota->ms) {
+ quota->esz = quota->sz;
+ return;
+ }
+
+ if (quota->total_charged_ns)
+ throughput = quota->total_charged_sz * 1000000 /
+ quota->total_charged_ns;
+ else
+ throughput = PAGE_SIZE * 1024;
+ esz = throughput * quota->ms;
+
+ if (quota->sz && quota->sz < esz)
+ esz = quota->sz;
+ quota->esz = esz;
+}
+
+static void kdamond_apply_schemes(struct damon_ctx *c)
+{
+ struct damon_target *t;
+ struct damon_region *r, *next_r;
+ struct damos *s;
+
+ damon_for_each_scheme(s, c) {
+ struct damos_quota *quota = &s->quota;
+ unsigned long cumulated_sz;
+ unsigned int score, max_score = 0;
+
+ if (!s->wmarks.activated)
+ continue;
+
+ if (!quota->ms && !quota->sz)
+ continue;
+
+ /* New charge window starts */
+ if (time_after_eq(jiffies, quota->charged_from +
+ msecs_to_jiffies(
+ quota->reset_interval))) {
+ quota->total_charged_sz += quota->charged_sz;
+ quota->charged_from = jiffies;
+ quota->charged_sz = 0;
+ damos_set_effective_quota(quota);
+ }
+
+ if (!c->primitive.get_scheme_score)
+ continue;
+
+ /* Fill up the score histogram */
+ memset(quota->histogram, 0, sizeof(quota->histogram));
+ damon_for_each_target(t, c) {
+ damon_for_each_region(r, t) {
+ if (!__damos_valid_target(r, s))
+ continue;
+ score = c->primitive.get_scheme_score(
+ c, t, r, s);
+ quota->histogram[score] +=
+ r->ar.end - r->ar.start;
+ if (score > max_score)
+ max_score = score;
+ }
+ }
+
+ /* Set the min score limit */
+ for (cumulated_sz = 0, score = max_score; ; score--) {
+ cumulated_sz += quota->histogram[score];
+ if (cumulated_sz >= quota->esz || !score)
+ break;
+ }
+ quota->min_score = score;
+ }
+
+ damon_for_each_target(t, c) {
+ damon_for_each_region_safe(r, next_r, t)
+ damon_do_apply_schemes(c, t, r);
+ }
+}
+
#define sz_damon_region(r) (r->ar.end - r->ar.start)
/*
@@ -461,6 +752,7 @@ static void damon_merge_two_regions(struct damon_target *t,
l->nr_accesses = (l->nr_accesses * sz_l + r->nr_accesses * sz_r) /
(sz_l + sz_r);
+ l->age = (l->age * sz_l + r->age * sz_r) / (sz_l + sz_r);
l->ar.end = r->ar.end;
damon_destroy_region(r, t);
}
@@ -480,6 +772,11 @@ static void damon_merge_regions_of(struct damon_target *t, unsigned int thres,
struct damon_region *r, *prev = NULL, *next;
damon_for_each_region_safe(r, next, t) {
+ if (diff_of(r->nr_accesses, r->last_nr_accesses) > thres)
+ r->age = 0;
+ else
+ r->age++;
+
if (prev && prev->ar.end == r->ar.start &&
diff_of(prev->nr_accesses, r->nr_accesses) <= thres &&
sz_damon_region(prev) + sz_damon_region(r) <= sz_limit)
@@ -527,6 +824,9 @@ static void damon_split_region_at(struct damon_ctx *ctx,
r->ar.end = new->ar.start;
+ new->age = r->age;
+ new->last_nr_accesses = r->last_nr_accesses;
+
damon_insert_region(new, r, damon_next_region(r), t);
}
@@ -615,12 +915,8 @@ static bool kdamond_need_update_primitive(struct damon_ctx *ctx)
static bool kdamond_need_stop(struct damon_ctx *ctx)
{
struct damon_target *t;
- bool stop;
- mutex_lock(&ctx->kdamond_lock);
- stop = ctx->kdamond_stop;
- mutex_unlock(&ctx->kdamond_lock);
- if (stop)
+ if (kthread_should_stop())
return true;
if (!ctx->primitive.target_valid)
@@ -634,11 +930,81 @@ static bool kdamond_need_stop(struct damon_ctx *ctx)
return true;
}
-static void set_kdamond_stop(struct damon_ctx *ctx)
+static unsigned long damos_wmark_metric_value(enum damos_wmark_metric metric)
{
- mutex_lock(&ctx->kdamond_lock);
- ctx->kdamond_stop = true;
- mutex_unlock(&ctx->kdamond_lock);
+ struct sysinfo i;
+
+ switch (metric) {
+ case DAMOS_WMARK_FREE_MEM_RATE:
+ si_meminfo(&i);
+ return i.freeram * 1000 / i.totalram;
+ default:
+ break;
+ }
+ return -EINVAL;
+}
+
+/*
+ * Returns zero if the scheme is active. Else, returns time to wait for next
+ * watermark check in micro-seconds.
+ */
+static unsigned long damos_wmark_wait_us(struct damos *scheme)
+{
+ unsigned long metric;
+
+ if (scheme->wmarks.metric == DAMOS_WMARK_NONE)
+ return 0;
+
+ metric = damos_wmark_metric_value(scheme->wmarks.metric);
+ /* higher than high watermark or lower than low watermark */
+ if (metric > scheme->wmarks.high || scheme->wmarks.low > metric) {
+ if (scheme->wmarks.activated)
+ pr_debug("deactivate a scheme (%d) for %s wmark\n",
+ scheme->action,
+ metric > scheme->wmarks.high ?
+ "high" : "low");
+ scheme->wmarks.activated = false;
+ return scheme->wmarks.interval;
+ }
+
+ /* inactive and higher than middle watermark */
+ if ((scheme->wmarks.high >= metric && metric >= scheme->wmarks.mid) &&
+ !scheme->wmarks.activated)
+ return scheme->wmarks.interval;
+
+ if (!scheme->wmarks.activated)
+ pr_debug("activate a scheme (%d)\n", scheme->action);
+ scheme->wmarks.activated = true;
+ return 0;
+}
+
+static void kdamond_usleep(unsigned long usecs)
+{
+ if (usecs > 100 * 1000)
+ schedule_timeout_interruptible(usecs_to_jiffies(usecs));
+ else
+ usleep_range(usecs, usecs + 1);
+}
+
+/* Returns negative error code if it's not activated but should return */
+static int kdamond_wait_activation(struct damon_ctx *ctx)
+{
+ struct damos *s;
+ unsigned long wait_time;
+ unsigned long min_wait_time = 0;
+
+ while (!kdamond_need_stop(ctx)) {
+ damon_for_each_scheme(s, ctx) {
+ wait_time = damos_wmark_wait_us(s);
+ if (!min_wait_time || wait_time < min_wait_time)
+ min_wait_time = wait_time;
+ }
+ if (!min_wait_time)
+ return 0;
+
+ kdamond_usleep(min_wait_time);
+ }
+ return -EBUSY;
}
/*
@@ -651,24 +1017,26 @@ static int kdamond_fn(void *data)
struct damon_region *r, *next;
unsigned int max_nr_accesses = 0;
unsigned long sz_limit = 0;
+ bool done = false;
- mutex_lock(&ctx->kdamond_lock);
- pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
- mutex_unlock(&ctx->kdamond_lock);
+ pr_debug("kdamond (%d) starts\n", current->pid);
if (ctx->primitive.init)
ctx->primitive.init(ctx);
if (ctx->callback.before_start && ctx->callback.before_start(ctx))
- set_kdamond_stop(ctx);
+ done = true;
sz_limit = damon_region_sz_limit(ctx);
- while (!kdamond_need_stop(ctx)) {
+ while (!kdamond_need_stop(ctx) && !done) {
+ if (kdamond_wait_activation(ctx))
+ continue;
+
if (ctx->primitive.prepare_access_checks)
ctx->primitive.prepare_access_checks(ctx);
if (ctx->callback.after_sampling &&
ctx->callback.after_sampling(ctx))
- set_kdamond_stop(ctx);
+ done = true;
usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
@@ -681,7 +1049,8 @@ static int kdamond_fn(void *data)
sz_limit);
if (ctx->callback.after_aggregation &&
ctx->callback.after_aggregation(ctx))
- set_kdamond_stop(ctx);
+ done = true;
+ kdamond_apply_schemes(ctx);
kdamond_reset_aggregated(ctx);
kdamond_split_regions(ctx);
if (ctx->primitive.reset_aggregated)
@@ -699,13 +1068,12 @@ static int kdamond_fn(void *data)
damon_destroy_region(r, t);
}
- if (ctx->callback.before_terminate &&
- ctx->callback.before_terminate(ctx))
- set_kdamond_stop(ctx);
+ if (ctx->callback.before_terminate)
+ ctx->callback.before_terminate(ctx);
if (ctx->primitive.cleanup)
ctx->primitive.cleanup(ctx);
- pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid);
+ pr_debug("kdamond (%d) finishes\n", current->pid);
mutex_lock(&ctx->kdamond_lock);
ctx->kdamond = NULL;
mutex_unlock(&ctx->kdamond_lock);
@@ -714,7 +1082,7 @@ static int kdamond_fn(void *data)
nr_running_ctxs--;
mutex_unlock(&damon_lock);
- do_exit(0);
+ return 0;
}
#include "core-test.h"
diff --git a/mm/damon/dbgfs-test.h b/mm/damon/dbgfs-test.h
index 4eddcfa73996..86b9f9528231 100644
--- a/mm/damon/dbgfs-test.h
+++ b/mm/damon/dbgfs-test.h
@@ -109,9 +109,63 @@ static void damon_dbgfs_test_set_targets(struct kunit *test)
dbgfs_destroy_ctx(ctx);
}
+static void damon_dbgfs_test_set_init_regions(struct kunit *test)
+{
+ struct damon_ctx *ctx = damon_new_ctx();
+ unsigned long ids[] = {1, 2, 3};
+ /* Each line represents one region in ``<target id> <start> <end>`` */
+ char * const valid_inputs[] = {"2 10 20\n 2 20 30\n2 35 45",
+ "2 10 20\n",
+ "2 10 20\n1 39 59\n1 70 134\n 2 20 25\n",
+ ""};
+ /* Reading the file again will show sorted, clean output */
+ char * const valid_expects[] = {"2 10 20\n2 20 30\n2 35 45\n",
+ "2 10 20\n",
+ "1 39 59\n1 70 134\n2 10 20\n2 20 25\n",
+ ""};
+ char * const invalid_inputs[] = {"4 10 20\n", /* target not exists */
+ "2 10 20\n 2 14 26\n", /* regions overlap */
+ "1 10 20\n2 30 40\n 1 5 8"}; /* not sorted by address */
+ char *input, *expect;
+ int i, rc;
+ char buf[256];
+
+ damon_set_targets(ctx, ids, 3);
+
+ /* Put valid inputs and check the results */
+ for (i = 0; i < ARRAY_SIZE(valid_inputs); i++) {
+ input = valid_inputs[i];
+ expect = valid_expects[i];
+
+ rc = set_init_regions(ctx, input, strnlen(input, 256));
+ KUNIT_EXPECT_EQ(test, rc, 0);
+
+ memset(buf, 0, 256);
+ sprint_init_regions(ctx, buf, 256);
+
+ KUNIT_EXPECT_STREQ(test, (char *)buf, expect);
+ }
+ /* Put invalid inputs and check the return error code */
+ for (i = 0; i < ARRAY_SIZE(invalid_inputs); i++) {
+ input = invalid_inputs[i];
+ pr_info("input: %s\n", input);
+ rc = set_init_regions(ctx, input, strnlen(input, 256));
+ KUNIT_EXPECT_EQ(test, rc, -EINVAL);
+
+ memset(buf, 0, 256);
+ sprint_init_regions(ctx, buf, 256);
+
+ KUNIT_EXPECT_STREQ(test, (char *)buf, "");
+ }
+
+ damon_set_targets(ctx, NULL, 0);
+ damon_destroy_ctx(ctx);
+}
+
static struct kunit_case damon_test_cases[] = {
KUNIT_CASE(damon_dbgfs_test_str_to_target_ids),
KUNIT_CASE(damon_dbgfs_test_set_targets),
+ KUNIT_CASE(damon_dbgfs_test_set_init_regions),
{},
};
diff --git a/mm/damon/dbgfs.c b/mm/damon/dbgfs.c
index faee070977d8..eccc14b34901 100644
--- a/mm/damon/dbgfs.c
+++ b/mm/damon/dbgfs.c
@@ -69,8 +69,7 @@ static ssize_t dbgfs_attrs_write(struct file *file,
struct damon_ctx *ctx = file->private_data;
unsigned long s, a, r, minr, maxr;
char *kbuf;
- ssize_t ret = count;
- int err;
+ ssize_t ret;
kbuf = user_input_str(buf, count, ppos);
if (IS_ERR(kbuf))
@@ -88,11 +87,182 @@ static ssize_t dbgfs_attrs_write(struct file *file,
goto unlock_out;
}
- err = damon_set_attrs(ctx, s, a, r, minr, maxr);
- if (err)
- ret = err;
+ ret = damon_set_attrs(ctx, s, a, r, minr, maxr);
+ if (!ret)
+ ret = count;
+unlock_out:
+ mutex_unlock(&ctx->kdamond_lock);
+out:
+ kfree(kbuf);
+ return ret;
+}
+
+static ssize_t sprint_schemes(struct damon_ctx *c, char *buf, ssize_t len)
+{
+ struct damos *s;
+ int written = 0;
+ int rc;
+
+ damon_for_each_scheme(s, c) {
+ rc = scnprintf(&buf[written], len - written,
+ "%lu %lu %u %u %u %u %d %lu %lu %lu %u %u %u %d %lu %lu %lu %lu %lu %lu\n",
+ s->min_sz_region, s->max_sz_region,
+ s->min_nr_accesses, s->max_nr_accesses,
+ s->min_age_region, s->max_age_region,
+ s->action,
+ s->quota.ms, s->quota.sz,
+ s->quota.reset_interval,
+ s->quota.weight_sz,
+ s->quota.weight_nr_accesses,
+ s->quota.weight_age,
+ s->wmarks.metric, s->wmarks.interval,
+ s->wmarks.high, s->wmarks.mid, s->wmarks.low,
+ s->stat_count, s->stat_sz);
+ if (!rc)
+ return -ENOMEM;
+
+ written += rc;
+ }
+ return written;
+}
+
+static ssize_t dbgfs_schemes_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ char *kbuf;
+ ssize_t len;
+
+ kbuf = kmalloc(count, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ mutex_lock(&ctx->kdamond_lock);
+ len = sprint_schemes(ctx, kbuf, count);
+ mutex_unlock(&ctx->kdamond_lock);
+ if (len < 0)
+ goto out;
+ len = simple_read_from_buffer(buf, count, ppos, kbuf, len);
+
+out:
+ kfree(kbuf);
+ return len;
+}
+
+static void free_schemes_arr(struct damos **schemes, ssize_t nr_schemes)
+{
+ ssize_t i;
+
+ for (i = 0; i < nr_schemes; i++)
+ kfree(schemes[i]);
+ kfree(schemes);
+}
+
+static bool damos_action_valid(int action)
+{
+ switch (action) {
+ case DAMOS_WILLNEED:
+ case DAMOS_COLD:
+ case DAMOS_PAGEOUT:
+ case DAMOS_HUGEPAGE:
+ case DAMOS_NOHUGEPAGE:
+ case DAMOS_STAT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+/*
+ * Converts a string into an array of struct damos pointers
+ *
+ * Returns an array of struct damos pointers that converted if the conversion
+ * success, or NULL otherwise.
+ */
+static struct damos **str_to_schemes(const char *str, ssize_t len,
+ ssize_t *nr_schemes)
+{
+ struct damos *scheme, **schemes;
+ const int max_nr_schemes = 256;
+ int pos = 0, parsed, ret;
+ unsigned long min_sz, max_sz;
+ unsigned int min_nr_a, max_nr_a, min_age, max_age;
+ unsigned int action;
+
+ schemes = kmalloc_array(max_nr_schemes, sizeof(scheme),
+ GFP_KERNEL);
+ if (!schemes)
+ return NULL;
+
+ *nr_schemes = 0;
+ while (pos < len && *nr_schemes < max_nr_schemes) {
+ struct damos_quota quota = {};
+ struct damos_watermarks wmarks;
+
+ ret = sscanf(&str[pos],
+ "%lu %lu %u %u %u %u %u %lu %lu %lu %u %u %u %u %lu %lu %lu %lu%n",
+ &min_sz, &max_sz, &min_nr_a, &max_nr_a,
+ &min_age, &max_age, &action, &quota.ms,
+ &quota.sz, &quota.reset_interval,
+ &quota.weight_sz, &quota.weight_nr_accesses,
+ &quota.weight_age, &wmarks.metric,
+ &wmarks.interval, &wmarks.high, &wmarks.mid,
+ &wmarks.low, &parsed);
+ if (ret != 18)
+ break;
+ if (!damos_action_valid(action)) {
+ pr_err("wrong action %d\n", action);
+ goto fail;
+ }
+
+ pos += parsed;
+ scheme = damon_new_scheme(min_sz, max_sz, min_nr_a, max_nr_a,
+ min_age, max_age, action, &quota, &wmarks);
+ if (!scheme)
+ goto fail;
+
+ schemes[*nr_schemes] = scheme;
+ *nr_schemes += 1;
+ }
+ return schemes;
+fail:
+ free_schemes_arr(schemes, *nr_schemes);
+ return NULL;
+}
+
+static ssize_t dbgfs_schemes_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ char *kbuf;
+ struct damos **schemes;
+ ssize_t nr_schemes = 0, ret;
+
+ kbuf = user_input_str(buf, count, ppos);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+
+ schemes = str_to_schemes(kbuf, count, &nr_schemes);
+ if (!schemes) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond) {
+ ret = -EBUSY;
+ goto unlock_out;
+ }
+
+ ret = damon_set_schemes(ctx, schemes, nr_schemes);
+ if (!ret) {
+ ret = count;
+ nr_schemes = 0;
+ }
+
unlock_out:
mutex_unlock(&ctx->kdamond_lock);
+ free_schemes_arr(schemes, nr_schemes);
out:
kfree(kbuf);
return ret;
@@ -185,26 +355,31 @@ static ssize_t dbgfs_target_ids_write(struct file *file,
const char __user *buf, size_t count, loff_t *ppos)
{
struct damon_ctx *ctx = file->private_data;
+ bool id_is_pid = true;
char *kbuf, *nrs;
unsigned long *targets;
ssize_t nr_targets;
- ssize_t ret = count;
+ ssize_t ret;
int i;
- int err;
kbuf = user_input_str(buf, count, ppos);
if (IS_ERR(kbuf))
return PTR_ERR(kbuf);
nrs = kbuf;
+ if (!strncmp(kbuf, "paddr\n", count)) {
+ id_is_pid = false;
+ /* target id is meaningless here, but we set it just for fun */
+ scnprintf(kbuf, count, "42 ");
+ }
- targets = str_to_target_ids(nrs, ret, &nr_targets);
+ targets = str_to_target_ids(nrs, count, &nr_targets);
if (!targets) {
ret = -ENOMEM;
goto out;
}
- if (targetid_is_pid(ctx)) {
+ if (id_is_pid) {
for (i = 0; i < nr_targets; i++) {
targets[i] = (unsigned long)find_get_pid(
(int)targets[i]);
@@ -218,17 +393,27 @@ static ssize_t dbgfs_target_ids_write(struct file *file,
mutex_lock(&ctx->kdamond_lock);
if (ctx->kdamond) {
- if (targetid_is_pid(ctx))
+ if (id_is_pid)
dbgfs_put_pids(targets, nr_targets);
ret = -EBUSY;
goto unlock_out;
}
- err = damon_set_targets(ctx, targets, nr_targets);
- if (err) {
- if (targetid_is_pid(ctx))
+ /* remove targets with previously-set primitive */
+ damon_set_targets(ctx, NULL, 0);
+
+ /* Configure the context for the address space type */
+ if (id_is_pid)
+ damon_va_set_primitives(ctx);
+ else
+ damon_pa_set_primitives(ctx);
+
+ ret = damon_set_targets(ctx, targets, nr_targets);
+ if (ret) {
+ if (id_is_pid)
dbgfs_put_pids(targets, nr_targets);
- ret = err;
+ } else {
+ ret = count;
}
unlock_out:
@@ -240,6 +425,152 @@ out:
return ret;
}
+static ssize_t sprint_init_regions(struct damon_ctx *c, char *buf, ssize_t len)
+{
+ struct damon_target *t;
+ struct damon_region *r;
+ int written = 0;
+ int rc;
+
+ damon_for_each_target(t, c) {
+ damon_for_each_region(r, t) {
+ rc = scnprintf(&buf[written], len - written,
+ "%lu %lu %lu\n",
+ t->id, r->ar.start, r->ar.end);
+ if (!rc)
+ return -ENOMEM;
+ written += rc;
+ }
+ }
+ return written;
+}
+
+static ssize_t dbgfs_init_regions_read(struct file *file, char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ char *kbuf;
+ ssize_t len;
+
+ kbuf = kmalloc(count, GFP_KERNEL);
+ if (!kbuf)
+ return -ENOMEM;
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond) {
+ mutex_unlock(&ctx->kdamond_lock);
+ len = -EBUSY;
+ goto out;
+ }
+
+ len = sprint_init_regions(ctx, kbuf, count);
+ mutex_unlock(&ctx->kdamond_lock);
+ if (len < 0)
+ goto out;
+ len = simple_read_from_buffer(buf, count, ppos, kbuf, len);
+
+out:
+ kfree(kbuf);
+ return len;
+}
+
+static int add_init_region(struct damon_ctx *c,
+ unsigned long target_id, struct damon_addr_range *ar)
+{
+ struct damon_target *t;
+ struct damon_region *r, *prev;
+ unsigned long id;
+ int rc = -EINVAL;
+
+ if (ar->start >= ar->end)
+ return -EINVAL;
+
+ damon_for_each_target(t, c) {
+ id = t->id;
+ if (targetid_is_pid(c))
+ id = (unsigned long)pid_vnr((struct pid *)id);
+ if (id == target_id) {
+ r = damon_new_region(ar->start, ar->end);
+ if (!r)
+ return -ENOMEM;
+ damon_add_region(r, t);
+ if (damon_nr_regions(t) > 1) {
+ prev = damon_prev_region(r);
+ if (prev->ar.end > r->ar.start) {
+ damon_destroy_region(r, t);
+ return -EINVAL;
+ }
+ }
+ rc = 0;
+ }
+ }
+ return rc;
+}
+
+static int set_init_regions(struct damon_ctx *c, const char *str, ssize_t len)
+{
+ struct damon_target *t;
+ struct damon_region *r, *next;
+ int pos = 0, parsed, ret;
+ unsigned long target_id;
+ struct damon_addr_range ar;
+ int err;
+
+ damon_for_each_target(t, c) {
+ damon_for_each_region_safe(r, next, t)
+ damon_destroy_region(r, t);
+ }
+
+ while (pos < len) {
+ ret = sscanf(&str[pos], "%lu %lu %lu%n",
+ &target_id, &ar.start, &ar.end, &parsed);
+ if (ret != 3)
+ break;
+ err = add_init_region(c, target_id, &ar);
+ if (err)
+ goto fail;
+ pos += parsed;
+ }
+
+ return 0;
+
+fail:
+ damon_for_each_target(t, c) {
+ damon_for_each_region_safe(r, next, t)
+ damon_destroy_region(r, t);
+ }
+ return err;
+}
+
+static ssize_t dbgfs_init_regions_write(struct file *file,
+ const char __user *buf, size_t count,
+ loff_t *ppos)
+{
+ struct damon_ctx *ctx = file->private_data;
+ char *kbuf;
+ ssize_t ret = count;
+ int err;
+
+ kbuf = user_input_str(buf, count, ppos);
+ if (IS_ERR(kbuf))
+ return PTR_ERR(kbuf);
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond) {
+ ret = -EBUSY;
+ goto unlock_out;
+ }
+
+ err = set_init_regions(ctx, kbuf, ret);
+ if (err)
+ ret = err;
+
+unlock_out:
+ mutex_unlock(&ctx->kdamond_lock);
+ kfree(kbuf);
+ return ret;
+}
+
static ssize_t dbgfs_kdamond_pid_read(struct file *file,
char __user *buf, size_t count, loff_t *ppos)
{
@@ -279,12 +610,24 @@ static const struct file_operations attrs_fops = {
.write = dbgfs_attrs_write,
};
+static const struct file_operations schemes_fops = {
+ .open = damon_dbgfs_open,
+ .read = dbgfs_schemes_read,
+ .write = dbgfs_schemes_write,
+};
+
static const struct file_operations target_ids_fops = {
.open = damon_dbgfs_open,
.read = dbgfs_target_ids_read,
.write = dbgfs_target_ids_write,
};
+static const struct file_operations init_regions_fops = {
+ .open = damon_dbgfs_open,
+ .read = dbgfs_init_regions_read,
+ .write = dbgfs_init_regions_write,
+};
+
static const struct file_operations kdamond_pid_fops = {
.open = damon_dbgfs_open,
.read = dbgfs_kdamond_pid_read,
@@ -292,28 +635,27 @@ static const struct file_operations kdamond_pid_fops = {
static void dbgfs_fill_ctx_dir(struct dentry *dir, struct damon_ctx *ctx)
{
- const char * const file_names[] = {"attrs", "target_ids",
- "kdamond_pid"};
- const struct file_operations *fops[] = {&attrs_fops, &target_ids_fops,
- &kdamond_pid_fops};
+ const char * const file_names[] = {"attrs", "schemes", "target_ids",
+ "init_regions", "kdamond_pid"};
+ const struct file_operations *fops[] = {&attrs_fops, &schemes_fops,
+ &target_ids_fops, &init_regions_fops, &kdamond_pid_fops};
int i;
for (i = 0; i < ARRAY_SIZE(file_names); i++)
debugfs_create_file(file_names[i], 0600, dir, ctx, fops[i]);
}
-static int dbgfs_before_terminate(struct damon_ctx *ctx)
+static void dbgfs_before_terminate(struct damon_ctx *ctx)
{
struct damon_target *t, *next;
if (!targetid_is_pid(ctx))
- return 0;
+ return;
damon_for_each_target_safe(t, next, ctx) {
put_pid((struct pid *)t->id);
damon_destroy_target(t);
}
- return 0;
}
static struct damon_ctx *dbgfs_new_ctx(void)
@@ -388,8 +730,7 @@ static ssize_t dbgfs_mk_context_write(struct file *file,
{
char *kbuf;
char *ctx_name;
- ssize_t ret = count;
- int err;
+ ssize_t ret;
kbuf = user_input_str(buf, count, ppos);
if (IS_ERR(kbuf))
@@ -407,9 +748,9 @@ static ssize_t dbgfs_mk_context_write(struct file *file,
}
mutex_lock(&damon_dbgfs_lock);
- err = dbgfs_mk_context(ctx_name);
- if (err)
- ret = err;
+ ret = dbgfs_mk_context(ctx_name);
+ if (!ret)
+ ret = count;
mutex_unlock(&damon_dbgfs_lock);
out:
@@ -478,8 +819,7 @@ static ssize_t dbgfs_rm_context_write(struct file *file,
const char __user *buf, size_t count, loff_t *ppos)
{
char *kbuf;
- ssize_t ret = count;
- int err;
+ ssize_t ret;
char *ctx_name;
kbuf = user_input_str(buf, count, ppos);
@@ -498,9 +838,9 @@ static ssize_t dbgfs_rm_context_write(struct file *file,
}
mutex_lock(&damon_dbgfs_lock);
- err = dbgfs_rm_context(ctx_name);
- if (err)
- ret = err;
+ ret = dbgfs_rm_context(ctx_name);
+ if (!ret)
+ ret = count;
mutex_unlock(&damon_dbgfs_lock);
out:
@@ -524,9 +864,8 @@ static ssize_t dbgfs_monitor_on_read(struct file *file,
static ssize_t dbgfs_monitor_on_write(struct file *file,
const char __user *buf, size_t count, loff_t *ppos)
{
- ssize_t ret = count;
+ ssize_t ret;
char *kbuf;
- int err;
kbuf = user_input_str(buf, count, ppos);
if (IS_ERR(kbuf))
@@ -538,15 +877,24 @@ static ssize_t dbgfs_monitor_on_write(struct file *file,
return -EINVAL;
}
- if (!strncmp(kbuf, "on", count))
- err = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs);
- else if (!strncmp(kbuf, "off", count))
- err = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs);
- else
- err = -EINVAL;
+ if (!strncmp(kbuf, "on", count)) {
+ int i;
- if (err)
- ret = err;
+ for (i = 0; i < dbgfs_nr_ctxs; i++) {
+ if (damon_targets_empty(dbgfs_ctxs[i])) {
+ kfree(kbuf);
+ return -EINVAL;
+ }
+ }
+ ret = damon_start(dbgfs_ctxs, dbgfs_nr_ctxs);
+ } else if (!strncmp(kbuf, "off", count)) {
+ ret = damon_stop(dbgfs_ctxs, dbgfs_nr_ctxs);
+ } else {
+ ret = -EINVAL;
+ }
+
+ if (!ret)
+ ret = count;
kfree(kbuf);
return ret;
}
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
new file mode 100644
index 000000000000..a496d6f203d6
--- /dev/null
+++ b/mm/damon/paddr.c
@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON Primitives for The Physical Address Space
+ *
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#define pr_fmt(fmt) "damon-pa: " fmt
+
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+
+#include "../internal.h"
+#include "prmtv-common.h"
+
+static bool __damon_pa_mkold(struct page *page, struct vm_area_struct *vma,
+ unsigned long addr, void *arg)
+{
+ struct page_vma_mapped_walk pvmw = {
+ .page = page,
+ .vma = vma,
+ .address = addr,
+ };
+
+ while (page_vma_mapped_walk(&pvmw)) {
+ addr = pvmw.address;
+ if (pvmw.pte)
+ damon_ptep_mkold(pvmw.pte, vma->vm_mm, addr);
+ else
+ damon_pmdp_mkold(pvmw.pmd, vma->vm_mm, addr);
+ }
+ return true;
+}
+
+static void damon_pa_mkold(unsigned long paddr)
+{
+ struct page *page = damon_get_page(PHYS_PFN(paddr));
+ struct rmap_walk_control rwc = {
+ .rmap_one = __damon_pa_mkold,
+ .anon_lock = page_lock_anon_vma_read,
+ };
+ bool need_lock;
+
+ if (!page)
+ return;
+
+ if (!page_mapped(page) || !page_rmapping(page)) {
+ set_page_idle(page);
+ goto out;
+ }
+
+ need_lock = !PageAnon(page) || PageKsm(page);
+ if (need_lock && !trylock_page(page))
+ goto out;
+
+ rmap_walk(page, &rwc);
+
+ if (need_lock)
+ unlock_page(page);
+
+out:
+ put_page(page);
+}
+
+static void __damon_pa_prepare_access_check(struct damon_ctx *ctx,
+ struct damon_region *r)
+{
+ r->sampling_addr = damon_rand(r->ar.start, r->ar.end);
+
+ damon_pa_mkold(r->sampling_addr);
+}
+
+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(ctx, r);
+ }
+}
+
+struct damon_pa_access_chk_result {
+ unsigned long page_sz;
+ bool accessed;
+};
+
+static bool __damon_pa_young(struct page *page, struct vm_area_struct *vma,
+ unsigned long addr, void *arg)
+{
+ struct damon_pa_access_chk_result *result = arg;
+ struct page_vma_mapped_walk pvmw = {
+ .page = page,
+ .vma = vma,
+ .address = addr,
+ };
+
+ result->accessed = false;
+ result->page_sz = PAGE_SIZE;
+ while (page_vma_mapped_walk(&pvmw)) {
+ addr = pvmw.address;
+ if (pvmw.pte) {
+ result->accessed = pte_young(*pvmw.pte) ||
+ !page_is_idle(page) ||
+ mmu_notifier_test_young(vma->vm_mm, addr);
+ } else {
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ result->accessed = pmd_young(*pvmw.pmd) ||
+ !page_is_idle(page) ||
+ mmu_notifier_test_young(vma->vm_mm, addr);
+ result->page_sz = ((1UL) << HPAGE_PMD_SHIFT);
+#else
+ WARN_ON_ONCE(1);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+ }
+ if (result->accessed) {
+ page_vma_mapped_walk_done(&pvmw);
+ break;
+ }
+ }
+
+ /* If accessed, stop walking */
+ return !result->accessed;
+}
+
+static bool damon_pa_young(unsigned long paddr, unsigned long *page_sz)
+{
+ struct page *page = damon_get_page(PHYS_PFN(paddr));
+ struct damon_pa_access_chk_result result = {
+ .page_sz = PAGE_SIZE,
+ .accessed = false,
+ };
+ struct rmap_walk_control rwc = {
+ .arg = &result,
+ .rmap_one = __damon_pa_young,
+ .anon_lock = page_lock_anon_vma_read,
+ };
+ bool need_lock;
+
+ if (!page)
+ return false;
+
+ if (!page_mapped(page) || !page_rmapping(page)) {
+ if (page_is_idle(page))
+ result.accessed = false;
+ else
+ result.accessed = true;
+ put_page(page);
+ goto out;
+ }
+
+ need_lock = !PageAnon(page) || PageKsm(page);
+ if (need_lock && !trylock_page(page)) {
+ put_page(page);
+ return NULL;
+ }
+
+ rmap_walk(page, &rwc);
+
+ if (need_lock)
+ unlock_page(page);
+ put_page(page);
+
+out:
+ *page_sz = result.page_sz;
+ return result.accessed;
+}
+
+static void __damon_pa_check_access(struct damon_ctx *ctx,
+ struct damon_region *r)
+{
+ static unsigned long last_addr;
+ static unsigned long last_page_sz = PAGE_SIZE;
+ static bool last_accessed;
+
+ /* If the region is in the last checked page, reuse the result */
+ if (ALIGN_DOWN(last_addr, last_page_sz) ==
+ ALIGN_DOWN(r->sampling_addr, last_page_sz)) {
+ if (last_accessed)
+ r->nr_accesses++;
+ return;
+ }
+
+ last_accessed = damon_pa_young(r->sampling_addr, &last_page_sz);
+ if (last_accessed)
+ r->nr_accesses++;
+
+ last_addr = r->sampling_addr;
+}
+
+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(ctx, r);
+ max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
+ }
+ }
+
+ return max_nr_accesses;
+}
+
+bool damon_pa_target_valid(void *t)
+{
+ return true;
+}
+
+int damon_pa_apply_scheme(struct damon_ctx *ctx, struct damon_target *t,
+ struct damon_region *r, struct damos *scheme)
+{
+ unsigned long addr;
+ LIST_HEAD(page_list);
+
+ if (scheme->action != DAMOS_PAGEOUT)
+ return -EINVAL;
+
+ for (addr = r->ar.start; addr < r->ar.end; addr += PAGE_SIZE) {
+ struct page *page = damon_get_page(PHYS_PFN(addr));
+
+ if (!page)
+ continue;
+
+ ClearPageReferenced(page);
+ test_and_clear_page_young(page);
+ if (isolate_lru_page(page)) {
+ put_page(page);
+ continue;
+ }
+ if (PageUnevictable(page)) {
+ putback_lru_page(page);
+ } else {
+ list_add(&page->lru, &page_list);
+ put_page(page);
+ }
+ }
+ reclaim_pages(&page_list);
+ cond_resched();
+ return 0;
+}
+
+int damon_pa_scheme_score(struct damon_ctx *context, struct damon_target *t,
+ struct damon_region *r, struct damos *scheme)
+{
+ switch (scheme->action) {
+ case DAMOS_PAGEOUT:
+ return damon_pageout_score(context, r, scheme);
+ default:
+ break;
+ }
+
+ return DAMOS_MAX_SCORE;
+}
+
+void damon_pa_set_primitives(struct damon_ctx *ctx)
+{
+ ctx->primitive.init = NULL;
+ ctx->primitive.update = NULL;
+ ctx->primitive.prepare_access_checks = damon_pa_prepare_access_checks;
+ ctx->primitive.check_accesses = damon_pa_check_accesses;
+ ctx->primitive.reset_aggregated = NULL;
+ ctx->primitive.target_valid = damon_pa_target_valid;
+ ctx->primitive.cleanup = NULL;
+ ctx->primitive.apply_scheme = damon_pa_apply_scheme;
+ ctx->primitive.get_scheme_score = damon_pa_scheme_score;
+}
diff --git a/mm/damon/prmtv-common.c b/mm/damon/prmtv-common.c
new file mode 100644
index 000000000000..92a04f5831d6
--- /dev/null
+++ b/mm/damon/prmtv-common.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Common Primitives for Data Access Monitoring
+ *
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#include <linux/mmu_notifier.h>
+#include <linux/page_idle.h>
+#include <linux/pagemap.h>
+#include <linux/rmap.h>
+
+#include "prmtv-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_page()'. We
+ * steal rather than reuse it because the code is quite simple.
+ */
+struct page *damon_get_page(unsigned long pfn)
+{
+ struct page *page = pfn_to_online_page(pfn);
+
+ if (!page || !PageLRU(page) || !get_page_unless_zero(page))
+ return NULL;
+
+ if (unlikely(!PageLRU(page))) {
+ put_page(page);
+ page = NULL;
+ }
+ return page;
+}
+
+void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr)
+{
+ bool referenced = false;
+ struct page *page = damon_get_page(pte_pfn(*pte));
+
+ if (!page)
+ return;
+
+ if (pte_young(*pte)) {
+ referenced = true;
+ *pte = pte_mkold(*pte);
+ }
+
+#ifdef CONFIG_MMU_NOTIFIER
+ if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
+ referenced = true;
+#endif /* CONFIG_MMU_NOTIFIER */
+
+ if (referenced)
+ set_page_young(page);
+
+ set_page_idle(page);
+ put_page(page);
+}
+
+void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ bool referenced = false;
+ struct page *page = damon_get_page(pmd_pfn(*pmd));
+
+ if (!page)
+ return;
+
+ if (pmd_young(*pmd)) {
+ referenced = true;
+ *pmd = pmd_mkold(*pmd);
+ }
+
+#ifdef CONFIG_MMU_NOTIFIER
+ if (mmu_notifier_clear_young(mm, addr,
+ addr + ((1UL) << HPAGE_PMD_SHIFT)))
+ referenced = true;
+#endif /* CONFIG_MMU_NOTIFIER */
+
+ if (referenced)
+ set_page_young(page);
+
+ set_page_idle(page);
+ put_page(page);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+}
+
+#define DAMON_MAX_SUBSCORE (100)
+#define DAMON_MAX_AGE_IN_LOG (32)
+
+int damon_pageout_score(struct damon_ctx *c, struct damon_region *r,
+ struct damos *s)
+{
+ unsigned int max_nr_accesses;
+ 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;
+
+ max_nr_accesses = c->aggr_interval / c->sample_interval;
+ freq_subscore = r->nr_accesses * DAMON_MAX_SUBSCORE / max_nr_accesses;
+
+ age_in_sec = (unsigned long)r->age * c->aggr_interval / 1000000;
+ for (age_in_log = 0; age_in_log < DAMON_MAX_AGE_IN_LOG && age_in_sec;
+ age_in_log++, age_in_sec >>= 1)
+ ;
+
+ /* 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;
+
+ /* Return coldness of the region */
+ return DAMOS_MAX_SCORE - hotness;
+}
diff --git a/mm/damon/prmtv-common.h b/mm/damon/prmtv-common.h
new file mode 100644
index 000000000000..61f27037603e
--- /dev/null
+++ b/mm/damon/prmtv-common.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common Primitives for Data Access Monitoring
+ *
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#include <linux/damon.h>
+#include <linux/random.h>
+
+/* Get a random number in [l, r) */
+#define damon_rand(l, r) (l + prandom_u32_max(r - l))
+
+struct page *damon_get_page(unsigned long pfn);
+
+void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm, unsigned long addr);
+void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm, unsigned long addr);
+
+int damon_pageout_score(struct damon_ctx *c, struct damon_region *r,
+ struct damos *s);
diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c
new file mode 100644
index 000000000000..dc1485044eaf
--- /dev/null
+++ b/mm/damon/reclaim.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DAMON-based page reclamation
+ *
+ * Author: SeongJae Park <sj@kernel.org>
+ */
+
+#define pr_fmt(fmt) "damon-reclaim: " fmt
+
+#include <linux/damon.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/workqueue.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;
+module_param(enabled, bool, 0600);
+
+/*
+ * 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);
+
+/*
+ * Limit of time for trying the reclamation in milliseconds.
+ *
+ * DAMON_RECLAIM tries to use only up to this time within a time window
+ * (quota_reset_interval_ms) for trying reclamation of cold pages. This can be
+ * used for limiting CPU consumption of DAMON_RECLAIM. If the value is zero,
+ * the limit is disabled.
+ *
+ * 10 ms by default.
+ */
+static unsigned long quota_ms __read_mostly = 10;
+module_param(quota_ms, ulong, 0600);
+
+/*
+ * Limit of size of memory for the reclamation in bytes.
+ *
+ * DAMON_RECLAIM charges amount of memory which it tried to reclaim within a
+ * time window (quota_reset_interval_ms) and makes no more than this limit is
+ * tried. This can be used for limiting consumption of CPU and IO. If this
+ * value is zero, the limit is disabled.
+ *
+ * 128 MiB by default.
+ */
+static unsigned long quota_sz __read_mostly = 128 * 1024 * 1024;
+module_param(quota_sz, ulong, 0600);
+
+/*
+ * The time/size quota charge reset interval in milliseconds.
+ *
+ * The charge reset interval for the quota of time (quota_ms) and size
+ * (quota_sz). That is, DAMON_RECLAIM does not try reclamation for more than
+ * quota_ms milliseconds or quota_sz bytes within quota_reset_interval_ms
+ * milliseconds.
+ *
+ * 1 second by default.
+ */
+static unsigned long quota_reset_interval_ms __read_mostly = 1000;
+module_param(quota_reset_interval_ms, ulong, 0600);
+
+/*
+ * The watermarks check time interval in microseconds.
+ *
+ * Minimal time to wait before checking the watermarks, when DAMON_RECLAIM is
+ * enabled but inactive due to its watermarks rule. 5 seconds by default.
+ */
+static unsigned long wmarks_interval __read_mostly = 5000000;
+module_param(wmarks_interval, ulong, 0600);
+
+/*
+ * Free memory rate (per thousand) for the high watermark.
+ *
+ * If free memory of the system in bytes per thousand bytes is higher than
+ * this, DAMON_RECLAIM becomes inactive, so it does nothing but periodically
+ * checks the watermarks. 500 (50%) by default.
+ */
+static unsigned long wmarks_high __read_mostly = 500;
+module_param(wmarks_high, ulong, 0600);
+
+/*
+ * Free memory rate (per thousand) for the middle watermark.
+ *
+ * If free memory of the system in bytes per thousand bytes is between this and
+ * the low watermark, DAMON_RECLAIM becomes active, so starts the monitoring
+ * and the reclaiming. 400 (40%) by default.
+ */
+static unsigned long wmarks_mid __read_mostly = 400;
+module_param(wmarks_mid, ulong, 0600);
+
+/*
+ * Free memory rate (per thousand) for the low watermark.
+ *
+ * If free memory of the system in bytes per thousand bytes is lower than this,
+ * DAMON_RECLAIM becomes inactive, so it does nothing but periodically checks
+ * the watermarks. In the case, the system falls back to the LRU-based page
+ * granularity reclamation logic. 200 (20%) by default.
+ */
+static unsigned long wmarks_low __read_mostly = 200;
+module_param(wmarks_low, ulong, 0600);
+
+/*
+ * Sampling interval for the monitoring in microseconds.
+ *
+ * The sampling interval of DAMON for the cold memory monitoring. Please refer
+ * to the DAMON documentation for more detail. 5 ms by default.
+ */
+static unsigned long sample_interval __read_mostly = 5000;
+module_param(sample_interval, ulong, 0600);
+
+/*
+ * Aggregation interval for the monitoring in microseconds.
+ *
+ * The aggregation interval of DAMON for the cold memory monitoring. Please
+ * refer to the DAMON documentation for more detail. 100 ms by default.
+ */
+static unsigned long aggr_interval __read_mostly = 100000;
+module_param(aggr_interval, ulong, 0600);
+
+/*
+ * Minimum number of monitoring regions.
+ *
+ * The minimal number of monitoring regions of DAMON for the cold memory
+ * monitoring. This can be used to set lower-bound of the monitoring quality.
+ * But, setting this too high could result in increased monitoring overhead.
+ * Please refer to the DAMON documentation for more detail. 10 by default.
+ */
+static unsigned long min_nr_regions __read_mostly = 10;
+module_param(min_nr_regions, ulong, 0600);
+
+/*
+ * Maximum number of monitoring regions.
+ *
+ * The maximum number of monitoring regions of DAMON for the cold memory
+ * monitoring. This can be used to set upper-bound of the monitoring overhead.
+ * However, setting this too low could result in bad monitoring quality.
+ * Please refer to the DAMON documentation for more detail. 1000 by default.
+ */
+static unsigned long max_nr_regions __read_mostly = 1000;
+module_param(max_nr_regions, ulong, 0600);
+
+/*
+ * 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, biggest System RAM 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, biggest System RAM is used as the region.
+ */
+static unsigned long monitor_region_end __read_mostly;
+module_param(monitor_region_end, ulong, 0600);
+
+/*
+ * PID of the DAMON thread
+ *
+ * If DAMON_RECLAIM is enabled, this becomes the PID of the worker thread.
+ * Else, -1.
+ */
+static int kdamond_pid __read_mostly = -1;
+module_param(kdamond_pid, int, 0400);
+
+static struct damon_ctx *ctx;
+static struct damon_target *target;
+
+struct damon_reclaim_ram_walk_arg {
+ unsigned long start;
+ unsigned long end;
+};
+
+static int walk_system_ram(struct resource *res, void *arg)
+{
+ struct damon_reclaim_ram_walk_arg *a = arg;
+
+ if (a->end - a->start < res->end - res->start) {
+ a->start = res->start;
+ a->end = res->end;
+ }
+ return 0;
+}
+
+/*
+ * Find biggest 'System RAM' resource and store its start and end address in
+ * @start and @end, respectively. If no System RAM is found, returns false.
+ */
+static bool get_monitoring_region(unsigned long *start, unsigned long *end)
+{
+ struct damon_reclaim_ram_walk_arg arg = {};
+
+ walk_system_ram_res(0, ULONG_MAX, &arg, walk_system_ram);
+ if (arg.end <= arg.start)
+ return false;
+
+ *start = arg.start;
+ *end = arg.end;
+ return true;
+}
+
+static struct damos *damon_reclaim_new_scheme(void)
+{
+ struct damos_watermarks wmarks = {
+ .metric = DAMOS_WMARK_FREE_MEM_RATE,
+ .interval = wmarks_interval,
+ .high = wmarks_high,
+ .mid = wmarks_mid,
+ .low = wmarks_low,
+ };
+ struct damos_quota quota = {
+ /*
+ * Do not try reclamation for more than quota_ms milliseconds
+ * or quota_sz bytes within quota_reset_interval_ms.
+ */
+ .ms = quota_ms,
+ .sz = quota_sz,
+ .reset_interval = quota_reset_interval_ms,
+ /* Within the quota, page out older regions first. */
+ .weight_sz = 0,
+ .weight_nr_accesses = 0,
+ .weight_age = 1
+ };
+ struct damos *scheme = damon_new_scheme(
+ /* Find regions having PAGE_SIZE or larger size */
+ PAGE_SIZE, ULONG_MAX,
+ /* and not accessed at all */
+ 0, 0,
+ /* for min_age or more micro-seconds, and */
+ min_age / aggr_interval, UINT_MAX,
+ /* page out those, as soon as found */
+ DAMOS_PAGEOUT,
+ /* under the quota. */
+ &quota,
+ /* (De)activate this according to the watermarks. */
+ &wmarks);
+
+ return scheme;
+}
+
+static int damon_reclaim_turn(bool on)
+{
+ struct damon_region *region;
+ struct damos *scheme;
+ int err;
+
+ if (!on) {
+ err = damon_stop(&ctx, 1);
+ if (!err)
+ kdamond_pid = -1;
+ return err;
+ }
+
+ err = damon_set_attrs(ctx, sample_interval, aggr_interval, 0,
+ min_nr_regions, max_nr_regions);
+ if (err)
+ return err;
+
+ if (monitor_region_start > monitor_region_end)
+ return -EINVAL;
+ if (!monitor_region_start && !monitor_region_end &&
+ !get_monitoring_region(&monitor_region_start,
+ &monitor_region_end))
+ return -EINVAL;
+ /* DAMON will free this on its own when finish monitoring */
+ region = damon_new_region(monitor_region_start, monitor_region_end);
+ if (!region)
+ return -ENOMEM;
+ damon_add_region(region, target);
+
+ /* Will be freed by 'damon_set_schemes()' below */
+ scheme = damon_reclaim_new_scheme();
+ if (!scheme) {
+ err = -ENOMEM;
+ goto free_region_out;
+ }
+ err = damon_set_schemes(ctx, &scheme, 1);
+ if (err)
+ goto free_scheme_out;
+
+ err = damon_start(&ctx, 1);
+ if (!err) {
+ kdamond_pid = ctx->kdamond->pid;
+ return 0;
+ }
+
+free_scheme_out:
+ damon_destroy_scheme(scheme);
+free_region_out:
+ damon_destroy_region(region, target);
+ return err;
+}
+
+#define ENABLE_CHECK_INTERVAL_MS 1000
+static struct delayed_work damon_reclaim_timer;
+static void damon_reclaim_timer_fn(struct work_struct *work)
+{
+ static bool last_enabled;
+ bool now_enabled;
+
+ now_enabled = enabled;
+ if (last_enabled != now_enabled) {
+ if (!damon_reclaim_turn(now_enabled))
+ last_enabled = now_enabled;
+ else
+ enabled = last_enabled;
+ }
+
+ schedule_delayed_work(&damon_reclaim_timer,
+ msecs_to_jiffies(ENABLE_CHECK_INTERVAL_MS));
+}
+static DECLARE_DELAYED_WORK(damon_reclaim_timer, damon_reclaim_timer_fn);
+
+static int __init damon_reclaim_init(void)
+{
+ ctx = damon_new_ctx();
+ if (!ctx)
+ return -ENOMEM;
+
+ damon_pa_set_primitives(ctx);
+
+ /* 4242 means nothing but fun */
+ target = damon_new_target(4242);
+ if (!target) {
+ damon_destroy_ctx(ctx);
+ return -ENOMEM;
+ }
+ damon_add_target(ctx, target);
+
+ schedule_delayed_work(&damon_reclaim_timer, 0);
+ return 0;
+}
+
+module_init(damon_reclaim_init);
diff --git a/mm/damon/vaddr-test.h b/mm/damon/vaddr-test.h
index 1f5c13257dba..ecfd0b2ed222 100644
--- a/mm/damon/vaddr-test.h
+++ b/mm/damon/vaddr-test.h
@@ -233,7 +233,7 @@ static void damon_test_apply_three_regions3(struct kunit *test)
* 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 crated.
+ * and third big regions should be created.
*/
static void damon_test_apply_three_regions4(struct kunit *test)
{
diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
index 58c1fb2aafa9..35fe49080ee9 100644
--- a/mm/damon/vaddr.c
+++ b/mm/damon/vaddr.c
@@ -7,25 +7,20 @@
#define pr_fmt(fmt) "damon-va: " fmt
-#include <linux/damon.h>
+#include <asm-generic/mman-common.h>
+#include <linux/highmem.h>
#include <linux/hugetlb.h>
-#include <linux/mm.h>
#include <linux/mmu_notifier.h>
-#include <linux/highmem.h>
#include <linux/page_idle.h>
#include <linux/pagewalk.h>
-#include <linux/random.h>
-#include <linux/sched/mm.h>
-#include <linux/slab.h>
+
+#include "prmtv-common.h"
#ifdef CONFIG_DAMON_VADDR_KUNIT_TEST
#undef DAMON_MIN_REGION
#define DAMON_MIN_REGION 1
#endif
-/* Get a random number in [l, r) */
-#define damon_rand(l, r) (l + prandom_u32_max(r - l))
-
/*
* 't->id' should be the pointer to the relevant 'struct pid' having reference
* count. Caller must put the returned task, unless it is NULL.
@@ -311,7 +306,7 @@ static void damon_va_apply_three_regions(struct damon_target *t,
struct damon_addr_range bregions[3])
{
struct damon_region *r, *next;
- unsigned int i = 0;
+ unsigned int i;
/* Remove regions which are not in the three big regions now */
damon_for_each_region_safe(r, next, t) {
@@ -372,82 +367,6 @@ void damon_va_update(struct damon_ctx *ctx)
}
}
-/*
- * 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_page()'. We
- * steal rather than reuse it because the code is quite simple.
- */
-static struct page *damon_get_page(unsigned long pfn)
-{
- struct page *page = pfn_to_online_page(pfn);
-
- if (!page || !PageLRU(page) || !get_page_unless_zero(page))
- return NULL;
-
- if (unlikely(!PageLRU(page))) {
- put_page(page);
- page = NULL;
- }
- return page;
-}
-
-static void damon_ptep_mkold(pte_t *pte, struct mm_struct *mm,
- unsigned long addr)
-{
- bool referenced = false;
- struct page *page = damon_get_page(pte_pfn(*pte));
-
- if (!page)
- return;
-
- if (pte_young(*pte)) {
- referenced = true;
- *pte = pte_mkold(*pte);
- }
-
-#ifdef CONFIG_MMU_NOTIFIER
- if (mmu_notifier_clear_young(mm, addr, addr + PAGE_SIZE))
- referenced = true;
-#endif /* CONFIG_MMU_NOTIFIER */
-
- if (referenced)
- set_page_young(page);
-
- set_page_idle(page);
- put_page(page);
-}
-
-static void damon_pmdp_mkold(pmd_t *pmd, struct mm_struct *mm,
- unsigned long addr)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- bool referenced = false;
- struct page *page = damon_get_page(pmd_pfn(*pmd));
-
- if (!page)
- return;
-
- if (pmd_young(*pmd)) {
- referenced = true;
- *pmd = pmd_mkold(*pmd);
- }
-
-#ifdef CONFIG_MMU_NOTIFIER
- if (mmu_notifier_clear_young(mm, addr,
- addr + ((1UL) << HPAGE_PMD_SHIFT)))
- referenced = true;
-#endif /* CONFIG_MMU_NOTIFIER */
-
- if (referenced)
- set_page_young(page);
-
- set_page_idle(page);
- put_page(page);
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-}
-
static int damon_mkold_pmd_entry(pmd_t *pmd, unsigned long addr,
unsigned long next, struct mm_walk *walk)
{
@@ -475,7 +394,7 @@ out:
return 0;
}
-static struct mm_walk_ops damon_mkold_ops = {
+static const struct mm_walk_ops damon_mkold_ops = {
.pmd_entry = damon_mkold_pmd_entry,
};
@@ -571,7 +490,7 @@ out:
return 0;
}
-static struct mm_walk_ops damon_young_ops = {
+static const struct mm_walk_ops damon_young_ops = {
.pmd_entry = damon_young_pmd_entry,
};
@@ -658,6 +577,76 @@ bool damon_va_target_valid(void *target)
return false;
}
+#ifndef CONFIG_ADVISE_SYSCALLS
+static int damos_madvise(struct damon_target *target, struct damon_region *r,
+ int behavior)
+{
+ return -EINVAL;
+}
+#else
+static int damos_madvise(struct damon_target *target, struct damon_region *r,
+ int behavior)
+{
+ struct mm_struct *mm;
+ int ret = -ENOMEM;
+
+ mm = damon_get_mm(target);
+ if (!mm)
+ goto out;
+
+ ret = do_madvise(mm, PAGE_ALIGN(r->ar.start),
+ PAGE_ALIGN(r->ar.end - r->ar.start), behavior);
+ mmput(mm);
+out:
+ return ret;
+}
+#endif /* CONFIG_ADVISE_SYSCALLS */
+
+int damon_va_apply_scheme(struct damon_ctx *ctx, struct damon_target *t,
+ struct damon_region *r, struct damos *scheme)
+{
+ 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_STAT:
+ return 0;
+ default:
+ pr_warn("Wrong action %d\n", scheme->action);
+ return -EINVAL;
+ }
+
+ return damos_madvise(t, r, madv_action);
+}
+
+int damon_va_scheme_score(struct damon_ctx *context, struct damon_target *t,
+ struct damon_region *r, struct damos *scheme)
+{
+
+ switch (scheme->action) {
+ case DAMOS_PAGEOUT:
+ return damon_pageout_score(context, r, scheme);
+ default:
+ break;
+ }
+
+ return DAMOS_MAX_SCORE;
+}
+
void damon_va_set_primitives(struct damon_ctx *ctx)
{
ctx->primitive.init = damon_va_init;
@@ -667,6 +656,8 @@ void damon_va_set_primitives(struct damon_ctx *ctx)
ctx->primitive.reset_aggregated = NULL;
ctx->primitive.target_valid = damon_va_target_valid;
ctx->primitive.cleanup = NULL;
+ ctx->primitive.apply_scheme = damon_va_apply_scheme;
+ ctx->primitive.get_scheme_score = damon_va_scheme_score;
}
#include "vaddr-test.h"
generated by cgit v1.2.3 (git 2.39.1) at 2024-07-11 21:39:47 +0000