@@ -11,6 +11,8 @@
#define _DAMON_H_
#include <linux/random.h>
+#include <linux/mutex.h>
+#include <linux/time64.h>
#include <linux/types.h>
/**
@@ -53,11 +55,87 @@ struct damon_task {
};
/**
- * struct damon_ctx - Represents a context for each monitoring.
+ * struct damon_ctx - Represents a context for each monitoring. This is the
+ * main interface that allows users to set the attributes and get the results
+ * of the monitoring.
+ *
+ * For each monitoring request (damon_start()), a kernel thread for the
+ * monitoring is created. The pointer to the thread is stored in @kdamond.
+ *
+ * @sample_interval: The time between access samplings.
+ * @aggr_interval: The time between monitor results aggregations.
+ * @min_nr_regions: The number of initial monitoring regions.
+ *
+ * For each @sample_interval, DAMON checks whether each region is accessed or
+ * not. It aggregates and keeps the access information (number of accesses to
+ * each region) for @aggr_interval time. All time intervals are in
+ * micro-seconds.
+ *
+ * @kdamond: Kernel thread who does the monitoring.
+ * @kdamond_stop: Notifies whether kdamond should stop.
+ * @kdamond_lock: Mutex for the synchronizations with @kdamond.
+ *
+ * The monitoring thread sets @kdamond to NULL when it terminates. Therefore,
+ * users can know whether the monitoring is ongoing or terminated by reading
+ * @kdamond. Also, users can ask @kdamond to be terminated by writing non-zero
+ * to @kdamond_stop. Reads and writes to @kdamond and @kdamond_stop from
+ * outside of the monitoring thread must be protected by @kdamond_lock.
+ *
+ * Note that the monitoring thread protects only @kdamond and @kdamond_stop via
+ * @kdamond_lock. Accesses to other fields must be protected by themselves.
+ *
* @tasks_list: Head of monitoring target tasks (&damon_task) list.
+ *
+ * @init_target_regions: Constructs initial monitoring target regions.
+ * @prepare_access_checks: Prepares next access check of target regions.
+ * @check_accesses: Checks the access of target regions.
+ * @sample_cb: Called for each sampling interval.
+ * @aggregate_cb: Called for each aggregation interval.
+ *
+ * DAMON can be extended for various address spaces by users. For this, users
+ * can register the target address space dependent low level functions for
+ * their usecases via the callback pointers of the context. The monitoring
+ * thread calls @init_target_regions before starting the monitoring, and
+ * @prepare_access_checks and @check_accesses for each @sample_interval.
+ *
+ * @init_target_regions should construct proper monitoring target regions and
+ * link those to the DAMON context struct.
+ * @prepare_access_checks should manipulate the monitoring regions to be
+ * prepare for the next access check.
+ * @check_accesses should check the accesses to each region that made after the
+ * last preparation and update the `->nr_accesses` of each region.
+ *
+ * @sample_cb and @aggregate_cb are called from @kdamond for each of the
+ * sampling intervals and aggregation intervals, respectively. Therefore,
+ * users can safely access to the monitoring results via @tasks_list without
+ * additional protection of @kdamond_lock. For the reason, users are
+ * recommended to use these callback for the accesses to the results.
*/
struct damon_ctx {
+ unsigned long sample_interval;
+ unsigned long aggr_interval;
+ unsigned long min_nr_regions;
+
+ struct timespec64 last_aggregation;
+
+ struct task_struct *kdamond;
+ bool kdamond_stop;
+ struct mutex kdamond_lock;
+
struct list_head tasks_list; /* 'damon_task' objects */
+
+ /* callbacks */
+ void (*init_target_regions)(struct damon_ctx *context);
+ void (*prepare_access_checks)(struct damon_ctx *context);
+ unsigned int (*check_accesses)(struct damon_ctx *context);
+ void (*sample_cb)(struct damon_ctx *context);
+ void (*aggregate_cb)(struct damon_ctx *context);
};
+int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids);
+int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
+ unsigned long aggr_int, unsigned long min_nr_reg);
+int damon_start(struct damon_ctx *ctx);
+int damon_stop(struct damon_ctx *ctx);
+
#endif
@@ -9,18 +9,27 @@
* This file is constructed in below parts.
*
* - Functions and macros for DAMON data structures
+ * - Functions for DAMON core logics and features
+ * - Functions for the DAMON programming interface
* - Functions for the module loading/unloading
- *
- * The core parts are not implemented yet.
*/
#define pr_fmt(fmt) "damon: " fmt
#include <linux/damon.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
#include <linux/mm.h>
#include <linux/module.h>
+#include <linux/page_idle.h>
+#include <linux/random.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/task.h>
#include <linux/slab.h>
+/* Minimal region size. Every damon_region is aligned by this. */
+#define MIN_REGION PAGE_SIZE
+
/*
* Functions and macros for DAMON data structures
*/
@@ -167,6 +176,251 @@ static unsigned int nr_damon_regions(struct damon_task *t)
return nr_regions;
}
+/*
+ * Functions for DAMON core logics and features
+ */
+
+/*
+ * damon_check_reset_time_interval() - Check if a time interval is elapsed.
+ * @baseline: the time to check whether the interval has elapsed since
+ * @interval: the time interval (microseconds)
+ *
+ * See whether the given time interval has passed since the given baseline
+ * time. If so, it also updates the baseline to current time for next check.
+ *
+ * Return: true if the time interval has passed, or false otherwise.
+ */
+static bool damon_check_reset_time_interval(struct timespec64 *baseline,
+ unsigned long interval)
+{
+ struct timespec64 now;
+
+ ktime_get_coarse_ts64(&now);
+ if ((timespec64_to_ns(&now) - timespec64_to_ns(baseline)) <
+ interval * 1000)
+ return false;
+ *baseline = now;
+ return true;
+}
+
+/*
+ * Check whether it is time to flush the aggregated information
+ */
+static bool kdamond_aggregate_interval_passed(struct damon_ctx *ctx)
+{
+ return damon_check_reset_time_interval(&ctx->last_aggregation,
+ ctx->aggr_interval);
+}
+
+/*
+ * Reset the aggregated monitoring results
+ */
+static void kdamond_reset_aggregated(struct damon_ctx *c)
+{
+ struct damon_task *t;
+ struct damon_region *r;
+
+ damon_for_each_task(t, c) {
+ damon_for_each_region(r, t)
+ r->nr_accesses = 0;
+ }
+}
+
+/*
+ * Check whether current monitoring should be stopped
+ *
+ * The monitoring is stopped when either the user requested to stop, or all
+ * monitoring target tasks are dead.
+ *
+ * Returns true if need to stop current monitoring.
+ */
+static bool kdamond_need_stop(struct damon_ctx *ctx)
+{
+ struct damon_task *t;
+ struct task_struct *task;
+ bool stop;
+
+ mutex_lock(&ctx->kdamond_lock);
+ stop = ctx->kdamond_stop;
+ mutex_unlock(&ctx->kdamond_lock);
+ if (stop)
+ return true;
+
+ damon_for_each_task(t, ctx) {
+ /* -1 is reserved for non-process bounded monitoring */
+ if (t->pid == -1)
+ return false;
+
+ task = damon_get_task_struct(t);
+ if (task) {
+ put_task_struct(task);
+ return false;
+ }
+ }
+
+ return true;
+}
+
+/*
+ * The monitoring daemon that runs as a kernel thread
+ */
+static int kdamond_fn(void *data)
+{
+ struct damon_ctx *ctx = (struct damon_ctx *)data;
+ struct damon_task *t;
+ struct damon_region *r, *next;
+
+ pr_info("kdamond (%d) starts\n", ctx->kdamond->pid);
+ if (ctx->init_target_regions)
+ ctx->init_target_regions(ctx);
+ while (!kdamond_need_stop(ctx)) {
+ if (ctx->prepare_access_checks)
+ ctx->prepare_access_checks(ctx);
+ if (ctx->sample_cb)
+ ctx->sample_cb(ctx);
+
+ usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+
+ if (ctx->check_accesses)
+ ctx->check_accesses(ctx);
+
+ if (kdamond_aggregate_interval_passed(ctx)) {
+ if (ctx->aggregate_cb)
+ ctx->aggregate_cb(ctx);
+ kdamond_reset_aggregated(ctx);
+ }
+
+ }
+ damon_for_each_task(t, ctx) {
+ damon_for_each_region_safe(r, next, t)
+ damon_destroy_region(r);
+ }
+ pr_debug("kdamond (%d) finishes\n", ctx->kdamond->pid);
+ mutex_lock(&ctx->kdamond_lock);
+ ctx->kdamond = NULL;
+ mutex_unlock(&ctx->kdamond_lock);
+
+ do_exit(0);
+}
+
+/*
+ * Functions for the DAMON programming interface
+ */
+
+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;
+}
+
+/**
+ * damon_start() - Starts monitoring with given context.
+ * @ctx: monitoring context
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_start(struct damon_ctx *ctx)
+{
+ int err = -EBUSY;
+
+ mutex_lock(&ctx->kdamond_lock);
+ if (!ctx->kdamond) {
+ err = 0;
+ ctx->kdamond_stop = false;
+ ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond");
+ if (IS_ERR(ctx->kdamond))
+ err = PTR_ERR(ctx->kdamond);
+ }
+ mutex_unlock(&ctx->kdamond_lock);
+
+ return err;
+}
+
+/**
+ * damon_stop() - Stops monitoring of given context.
+ * @ctx: monitoring context
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_stop(struct damon_ctx *ctx)
+{
+ mutex_lock(&ctx->kdamond_lock);
+ if (ctx->kdamond) {
+ ctx->kdamond_stop = true;
+ mutex_unlock(&ctx->kdamond_lock);
+ while (damon_kdamond_running(ctx))
+ usleep_range(ctx->sample_interval,
+ ctx->sample_interval * 2);
+ return 0;
+ }
+ mutex_unlock(&ctx->kdamond_lock);
+
+ return -EPERM;
+}
+
+/**
+ * damon_set_pids() - Set monitoring target processes.
+ * @ctx: monitoring context
+ * @pids: array of target processes pids
+ * @nr_pids: number of entries in @pids
+ *
+ * This function should not be called while the kdamond is running.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_set_pids(struct damon_ctx *ctx, int *pids, ssize_t nr_pids)
+{
+ ssize_t i;
+ struct damon_task *t, *next;
+
+ damon_for_each_task_safe(t, next, ctx)
+ damon_destroy_task(t);
+
+ for (i = 0; i < nr_pids; i++) {
+ t = damon_new_task(pids[i]);
+ if (!t) {
+ pr_err("Failed to alloc damon_task\n");
+ return -ENOMEM;
+ }
+ damon_add_task(ctx, t);
+ }
+
+ return 0;
+}
+
+/**
+ * damon_set_attrs() - Set attributes for the monitoring.
+ * @ctx: monitoring context
+ * @sample_int: time interval between samplings
+ * @aggr_int: time interval between aggregations
+ * @min_nr_reg: minimal number of regions
+ *
+ * This function should not be called while the kdamond is running.
+ * Every time interval is in micro-seconds.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
+ unsigned long aggr_int, unsigned long min_nr_reg)
+{
+ if (min_nr_reg < 3) {
+ pr_err("min_nr_regions (%lu) must be at least 3\n",
+ min_nr_reg);
+ return -EINVAL;
+ }
+
+ ctx->sample_interval = sample_int;
+ ctx->aggr_interval = aggr_int;
+ ctx->min_nr_regions = min_nr_reg;
+
+ return 0;
+}
+
/*
* Functions for the module loading/unloading
*/