From: SeongJae Park <sjpark@xxxxxxxxx>
This commit implements DAMON's basic access check and region based
sampling mechanisms. This change would seems make no sense, mainly
because it is only a part of the DAMON's logics. Following two commits
will make more sense.
Basic Access Check
------------------
DAMON basically reports what pages are how frequently accessed. Note
that the frequency is not an absolute number of accesses, but a relative
frequency among the pages of the target workloads.
Users can control the resolution of the reports by setting two time
intervals, ``sampling interval`` and ``aggregation interval``. In
detail, DAMON checks access to each page per ``sampling interval``,
aggregates the results (counts the number of the accesses to each page),
and reports the aggregated results per ``aggregation interval``. For
the access check of each page, DAMON uses the Accessed bits of PTEs.
This is thus similar to common periodic access checks based access
tracking mechanisms, which overhead is increasing as the size of the
target process grows.
Region Based Sampling
---------------------
To avoid the unbounded increase of the overhead, DAMON groups a number
of adjacent pages that assumed to have same access frequencies into a
region. As long as the assumption (pages in a region have same access
frequencies) is kept, only one page in the region is required to be
checked. Thus, for each ``sampling interval``, DAMON randomly picks one
page in each region and clears its Accessed bit. After one more
``sampling interval``, DAMON reads the Accessed bit of the page and
increases the access frequency of the region if the bit has set
meanwhile. Therefore, the monitoring overhead is controllable by
setting the number of regions.
Nonetheless, this scheme cannot preserve the quality of the output if
the assumption is not kept. Following commit will introduce how we can
make the guarantee with best effort.
Signed-off-by: SeongJae Park <sjpark@xxxxxxxxx>
Reviewed-by: Leonard Foerster <foersleo@xxxxxxxxx>
---
include/linux/damon.h | 48 +++-
mm/damon.c | 615 +++++++++++++++++++++++++++++++++++++++++-
2 files changed, 660 insertions(+), 3 deletions(-)
diff --git a/include/linux/damon.h b/include/linux/damon.h
index 135633334929..f0fe4520a4e9 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -11,6 +11,8 @@
#define _DAMON_H_
#include <linux/random.h>
+#include <linux/mutex.h>
+#include <linux/time64.h>
#include <linux/types.h>
/**
@@ -44,11 +46,55 @@ 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.
*/
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 */
};
+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
diff --git a/mm/damon.c b/mm/damon.c
index 170e8a694dbe..fa14ff7dd31a 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -9,18 +9,29 @@
* This file is constructed in below parts.
*
* - Functions and macros for DAMON data structures
+ * - Functions for the initial monitoring target regions construction
+ * - Functions for the access checking of the regions
+ * - 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 +178,606 @@ static unsigned int nr_damon_regions(struct damon_task *t)
return nr_regions;
}
+/*
+ * Get the mm_struct of the given task
+ *
+ * Caller _must_ put the mm_struct after use, unless it is NULL.
+ *
+ * Returns the mm_struct of the task on success, NULL on failure
+ */
+static struct mm_struct *damon_get_mm(struct damon_task *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;
+}
+
+/*
+ * Functions for the initial monitoring target regions construction
+ */
+
+/*
+ * Size-evenly split a region into 'nr_pieces' small regions
+ *
+ * Returns 0 on success, or negative error code otherwise.
+ */
+static int damon_split_region_evenly(struct damon_ctx *ctx,
+ struct damon_region *r, unsigned int nr_pieces)
+{
+ unsigned long sz_orig, sz_piece, orig_end;
+ struct damon_region *n = NULL, *next;
+ unsigned long start;
+
+ if (!r || !nr_pieces)
+ return -EINVAL;
+
+ orig_end = r->vm_end;
+ sz_orig = r->vm_end - r->vm_start;
+ sz_piece = ALIGN_DOWN(sz_orig / nr_pieces, MIN_REGION);
+
+ if (!sz_piece)
+ return -EINVAL;
+
+ r->vm_end = r->vm_start + sz_piece;
+ next = damon_next_region(r);
+ for (start = r->vm_end; start + sz_piece <= orig_end;
+ start += sz_piece) {
+ n = damon_new_region(ctx, start, start + sz_piece);
+ if (!n)
+ return -ENOMEM;
+ damon_insert_region(n, r, next);
+ r = n;
+ }
+ /* complement last region for possible rounding error */
+ if (n)
+ n->vm_end = orig_end;
+
+ return 0;
+}
+
+struct region {
+ unsigned long start;
+ unsigned long end;
+};
+
+static unsigned long sz_region(struct region *r)
+{
+ return r->end - r->start;
+}
+
+static void swap_regions(struct region *r1, struct region *r2)
+{
+ struct region tmp;
+
+ tmp = *r1;
+ *r1 = *r2;
+ *r2 = tmp;
+}
+
+/*
+ * Find three regions separated by two biggest unmapped regions
+ *
+ * vma the head vma of the target address space
+ * regions an array of three 'struct region's 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_init_regions_of()' function to know why this is
+ * necessary.
+ *
+ * Returns 0 if success, or negative error code otherwise.
+ */
+static int damon_three_regions_in_vmas(struct vm_area_struct *vma,
+ struct region regions[3])
+{
+ struct region gap = {0}, first_gap = {0}, second_gap = {0};
+ struct vm_area_struct *last_vma = NULL;
+ unsigned long start = 0;
+
+ /* Find two biggest gaps so that first_gap > second_gap > others */
+ for (; vma; vma = vma->vm_next) {
+ if (!last_vma) {
+ start = vma->vm_start;
+ last_vma = vma;
+ continue;
+ }
+ gap.start = last_vma->vm_end;
+ gap.end = vma->vm_start;
+ if (sz_region(&gap) > sz_region(&second_gap)) {
+ swap_regions(&gap, &second_gap);
+ if (sz_region(&second_gap) > sz_region(&first_gap))
+ swap_regions(&second_gap, &first_gap);
+ }
+ last_vma = vma;
+ }
+
+ if (!sz_region(&second_gap) || !sz_region(&first_gap))
+ return -EINVAL;
+
+ /* Sort the two biggest gaps by address */
+ if (first_gap.start > second_gap.start)
+ swap_regions(&first_gap, &second_gap);
+
+ /* Store the result */
+ regions[0].start = ALIGN(start, MIN_REGION);
+ regions[0].end = ALIGN(first_gap.start, MIN_REGION);
+ regions[1].start = ALIGN(first_gap.end, MIN_REGION);
+ regions[1].end = ALIGN(second_gap.start, MIN_REGION);
+ regions[2].start = ALIGN(second_gap.end, MIN_REGION);
+ regions[2].end = ALIGN(last_vma->vm_end, MIN_REGION);
+
+ return 0;
+}
+
+/*
+ * Get the three regions in the given task
+ *
+ * Returns 0 on success, negative error code otherwise.
+ */
+static int damon_three_regions_of(struct damon_task *t,
+ struct region regions[3])
+{
+ struct mm_struct *mm;
+ int rc;
+
+ mm = damon_get_mm(t);
+ if (!mm)
+ return -EINVAL;
+
+ down_read(&mm->mmap_sem);
+ rc = damon_three_regions_in_vmas(mm->mmap, regions);
+ up_read(&mm->mmap_sem);
+
+ mmput(mm);
+ return rc;
+}
+
+/*
+ * Initialize the monitoring target regions for the given task
+ *
+ * t the given target task
+ *
+ * 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. Nonetheless, this may seems very weird. DAMON's dynamic regions
+ * adjustment mechanism, which will be implemented with following commit will
+ * make this more sense.
+ *
+ * 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_init_regions_of(struct damon_ctx *c, struct damon_task *t)
+{
+ struct damon_region *r, *m = NULL;
+ struct region regions[3];
+ int i;
+
+ if (damon_three_regions_of(t, regions)) {
+ pr_err("Failed to get three regions of task %d\n", t->pid);
+ return;
+ }
+
+ /* Set the initial three regions of the task */
+ for (i = 0; i < 3; i++) {
+ r = damon_new_region(c, regions[i].start, regions[i].end);
+ if (!r) {
+ pr_err("%d'th init region creation failed\n", i);
+ return;
+ }
+ damon_add_region(r, t);
+ if (i == 1)
+ m = r;
+ }
+
+ /* Split the middle region into 'min_nr_regions - 2' regions */
+ if (damon_split_region_evenly(c, m, c->min_nr_regions - 2))
+ pr_warn("Init middle region failed to be split\n");
+}
+
+/* Initialize '->regions_list' of every task */
+static void kdamond_init_regions(struct damon_ctx *ctx)
+{
+ struct damon_task *t;
+
+ damon_for_each_task(t, ctx)
+ damon_init_regions_of(ctx, t);
+}
+
+/*
+ * Functions for the access checking of the regions
+ */
+
+static void damon_mkold(struct mm_struct *mm, unsigned long addr)
+{
+ pte_t *pte = NULL;
+ pmd_t *pmd = NULL;
+ spinlock_t *ptl;
+
+ if (follow_pte_pmd(mm, addr, NULL, &pte, &pmd, &ptl))
+ return;
+
+ if (pte) {
+ if (pte_young(*pte)) {
+ clear_page_idle(pte_page(*pte));
+ set_page_young(pte_page(*pte));
+ }
+ *pte = pte_mkold(*pte);
+ pte_unmap_unlock(pte, ptl);
+ return;
+ }
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ if (pmd_young(*pmd)) {
+ clear_page_idle(pmd_page(*pmd));
+ set_page_young(pmd_page(*pmd));
+ }
+ *pmd = pmd_mkold(*pmd);
+ spin_unlock(ptl);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+}
+
+static void damon_prepare_access_check(struct damon_ctx *ctx,
+ struct mm_struct *mm, struct damon_region *r)
+{
+ r->sampling_addr = damon_rand(r->vm_start, r->vm_end);
+
+ damon_mkold(mm, r->sampling_addr);
+}
+
+static void kdamond_prepare_access_checks(struct damon_ctx *ctx)
+{
+ struct damon_task *t;
+ struct mm_struct *mm;
+ struct damon_region *r;
+
+ damon_for_each_task(t, ctx) {
+ mm = damon_get_mm(t);
+ if (!mm)
+ continue;
+ damon_for_each_region(r, t)
+ damon_prepare_access_check(ctx, mm, r);
+ mmput(mm);
+ }
+}
+
+static bool damon_young(struct mm_struct *mm, unsigned long addr,
+ unsigned long *page_sz)
+{
+ pte_t *pte = NULL;
+ pmd_t *pmd = NULL;
+ spinlock_t *ptl;
+ bool young = false;
+
+ if (follow_pte_pmd(mm, addr, NULL, &pte, &pmd, &ptl))
+ return false;
+
+ *page_sz = PAGE_SIZE;
+ if (pte) {
+ young = pte_young(*pte);
+ pte_unmap_unlock(pte, ptl);
+ return young;
+ }
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ young = pmd_young(*pmd);
+ spin_unlock(ptl);
+ *page_sz = ((1UL) << HPAGE_PMD_SHIFT);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+ return 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_check_access(struct damon_ctx *ctx,
+ struct mm_struct *mm, struct damon_region *r)
+{
+ static struct mm_struct *last_mm;
+ 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 (mm == last_mm && (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_young(mm, r->sampling_addr, &last_page_sz);
+ if (last_accessed)
+ r->nr_accesses++;
+
+ last_mm = mm;
+ last_addr = r->sampling_addr;
+}
+
+static void kdamond_check_accesses(struct damon_ctx *ctx)
+{
+ struct damon_task *t;
+ struct mm_struct *mm;
+ struct damon_region *r;
+
+ damon_for_each_task(t, ctx) {
+ mm = damon_get_mm(t);
+ if (!mm)
+ continue;
+ damon_for_each_region(r, t)
+ damon_check_access(ctx, mm, r);
+ mmput(mm);
+ }
+}
+
+/*
+ * 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) {
+ 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);
+ kdamond_init_regions(ctx);
+ while (!kdamond_need_stop(ctx)) {
+ kdamond_prepare_access_checks(ctx);
+
+ usleep_range(ctx->sample_interval, ctx->sample_interval + 1);
+
+ kdamond_check_accesses(ctx);
+
+ if (kdamond_aggregate_interval_passed(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
*/
--
2.17.1
