linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: SeongJae Park <sjpark@amazon.com>
To: <akpm@linux-foundation.org>
Cc: SeongJae Park <sjpark@amazon.de>, <Jonathan.Cameron@Huawei.com>,
	<aarcange@redhat.com>, <acme@kernel.org>,
	<alexander.shishkin@linux.intel.com>, <amit@kernel.org>,
	<benh@kernel.crashing.org>, <brendan.d.gregg@gmail.com>,
	<brendanhiggins@google.com>, <cai@lca.pw>,
	<colin.king@canonical.com>, <corbet@lwn.net>, <david@redhat.com>,
	<dwmw@amazon.com>, <fan.du@intel.com>, <foersleo@amazon.de>,
	<gthelen@google.com>, <irogers@google.com>, <jolsa@redhat.com>,
	<kirill@shutemov.name>, <mark.rutland@arm.com>, <mgorman@suse.de>,
	<minchan@kernel.org>, <mingo@redhat.com>, <namhyung@kernel.org>,
	<peterz@infradead.org>, <rdunlap@infradead.org>,
	<riel@surriel.com>, <rientjes@google.com>, <rostedt@goodmis.org>,
	<rppt@kernel.org>, <sblbir@amazon.com>, <shakeelb@google.com>,
	<shuah@kernel.org>, <sj38.park@gmail.com>, <snu@amazon.de>,
	<vbabka@suse.cz>, <vdavydov.dev@gmail.com>,
	<yang.shi@linux.alibaba.com>, <ying.huang@intel.com>,
	<zgf574564920@gmail.com>, <linux-damon@amazon.com>,
	<linux-mm@kvack.org>, <linux-doc@vger.kernel.org>,
	<linux-kernel@vger.kernel.org>
Subject: [RFC v8 06/10] mm/damon: Implement callbacks for physical memory monitoring
Date: Mon, 31 Aug 2020 12:47:26 +0200	[thread overview]
Message-ID: <20200831104730.28970-7-sjpark@amazon.com> (raw)
In-Reply-To: <20200831104730.28970-1-sjpark@amazon.com>

From: SeongJae Park <sjpark@amazon.de>

This commit implements the four callbacks (->init_target_regions,
->update_target_regions, ->prepare_access_check, and ->check_accesses)
for the basic access monitoring of the physical memory address space.
By setting the callback pointers to point those, users can easily
monitor the accesses to the physical memory.

Internally, it uses the PTE Accessed bit, as similar to that of the
virtual memory support.  Also, it supports only user memory pages, as
idle page tracking also does, for the same reason.  If the monitoring
target physical memory address range contains non-user memory pages,
access check of the pages will do nothing but simply treat the pages as
not accessed.

Users who want to use other access check primitives and/or monitor the
non-user memory regions could implement and use their own callbacks.

Signed-off-by: SeongJae Park <sjpark@amazon.de>
---
 include/linux/damon.h |   6 ++
 mm/damon.c            | 214 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 220 insertions(+)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 0e790af9c23a..306fa221ceae 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -242,6 +242,12 @@ unsigned int kdamond_check_vm_accesses(struct damon_ctx *ctx);
 bool kdamond_vm_target_valid(struct damon_target *t);
 void kdamond_vm_cleanup(struct damon_ctx *ctx);
 
+/* Reference callback implementations for physical memory */
+void kdamond_init_phys_regions(struct damon_ctx *ctx);
+void kdamond_update_phys_regions(struct damon_ctx *ctx);
+void kdamond_prepare_phys_access_checks(struct damon_ctx *ctx);
+unsigned int kdamond_check_phys_accesses(struct damon_ctx *ctx);
+
 int damon_set_targets(struct damon_ctx *ctx,
 		unsigned long *ids, ssize_t nr_ids);
 int damon_set_attrs(struct damon_ctx *ctx, unsigned long sample_int,
diff --git a/mm/damon.c b/mm/damon.c
index 9815d22fc4de..464209039bf8 100644
--- a/mm/damon.c
+++ b/mm/damon.c
@@ -26,11 +26,14 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
+#include <linux/memory_hotplug.h>
 #include <linux/mm.h>
 #include <linux/mmu_notifier.h>
 #include <linux/module.h>
 #include <linux/page_idle.h>
+#include <linux/pagemap.h>
 #include <linux/random.h>
+#include <linux/rmap.h>
 #include <linux/sched/mm.h>
 #include <linux/sched/task.h>
 #include <linux/slab.h>
@@ -547,6 +550,18 @@ void kdamond_init_vm_regions(struct damon_ctx *ctx)
 	}
 }
 
+/*
+ * The initial regions construction function for the physical address space.
+ *
+ * This default version does nothing in actual.  Users should set the initial
+ * regions by themselves before passing their damon_ctx to 'damon_start()', or
+ * implement their version of this and set '->init_target_regions' of their
+ * damon_ctx to point it.
+ */
+void kdamond_init_phys_regions(struct damon_ctx *ctx)
+{
+}
+
 /*
  * Functions for the dynamic monitoring target regions update
  */
@@ -630,6 +645,19 @@ void kdamond_update_vm_regions(struct damon_ctx *ctx)
 	}
 }
 
+/*
+ * The dynamic monitoring target regions update function for the physical
+ * address space.
+ *
+ * This default version does nothing in actual.  Users should update the
+ * regions in other callbacks such as '->aggregate_cb', or implement their
+ * version of this and set the '->init_target_regions' of their damon_ctx to
+ * point it.
+ */
+void kdamond_update_phys_regions(struct damon_ctx *ctx)
+{
+}
+
 /*
  * Functions for the access checking of the regions
  */
@@ -805,6 +833,192 @@ unsigned int kdamond_check_vm_accesses(struct damon_ctx *ctx)
 	return max_nr_accesses;
 }
 
+/* access check functions for physical address based regions */
+
+/*
+ * Get a page by pfn if it is in the LRU list.  Otherwise, returns NULL.
+ *
+ * The body of this function is stollen from the 'page_idle_get_page()'.  We
+ * steal rather than reuse it because the code is quite simple.
+ */
+static struct page *damon_phys_get_page(unsigned long pfn)
+{
+	struct page *page = pfn_to_online_page(pfn);
+	pg_data_t *pgdat;
+
+	if (!page || !PageLRU(page) ||
+	    !get_page_unless_zero(page))
+		return NULL;
+
+	pgdat = page_pgdat(page);
+	spin_lock_irq(&pgdat->lru_lock);
+	if (unlikely(!PageLRU(page))) {
+		put_page(page);
+		page = NULL;
+	}
+	spin_unlock_irq(&pgdat->lru_lock);
+	return page;
+}
+
+static bool damon_page_mkold(struct page *page, struct vm_area_struct *vma,
+		unsigned long addr, void *arg)
+{
+	damon_mkold(vma->vm_mm, addr);
+	return true;
+}
+
+static void damon_phys_mkold(unsigned long paddr)
+{
+	struct page *page = damon_phys_get_page(PHYS_PFN(paddr));
+	struct rmap_walk_control rwc = {
+		.rmap_one = damon_page_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);
+		put_page(page);
+		return;
+	}
+
+	need_lock = !PageAnon(page) || PageKsm(page);
+	if (need_lock && !trylock_page(page)) {
+		put_page(page);
+		return;
+	}
+
+	rmap_walk(page, &rwc);
+
+	if (need_lock)
+		unlock_page(page);
+	put_page(page);
+}
+
+static void damon_prepare_phys_access_check(struct damon_ctx *ctx,
+					    struct damon_region *r)
+{
+	r->sampling_addr = damon_rand(r->ar.start, r->ar.end);
+
+	damon_phys_mkold(r->sampling_addr);
+}
+
+void kdamond_prepare_phys_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_prepare_phys_access_check(ctx, r);
+	}
+}
+
+struct damon_phys_access_chk_result {
+	unsigned long page_sz;
+	bool accessed;
+};
+
+static bool damon_page_accessed(struct page *page, struct vm_area_struct *vma,
+		unsigned long addr, void *arg)
+{
+	struct damon_phys_access_chk_result *result = arg;
+
+	result->accessed = damon_young(vma->vm_mm, addr, &result->page_sz);
+
+	/* If accessed, stop walking */
+	return !result->accessed;
+}
+
+static bool damon_phys_young(unsigned long paddr, unsigned long *page_sz)
+{
+	struct page *page = damon_phys_get_page(PHYS_PFN(paddr));
+	struct damon_phys_access_chk_result result = {
+		.page_sz = PAGE_SIZE,
+		.accessed = false,
+	};
+	struct rmap_walk_control rwc = {
+		.arg = &result,
+		.rmap_one = damon_page_accessed,
+		.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;
+}
+
+/*
+ * Check whether the region was accessed after the last preparation
+ *
+ * mm	'mm_struct' for the given virtual address space
+ * r	the region of physical address space that needs to be checked
+ */
+static void damon_check_phys_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_phys_young(r->sampling_addr, &last_page_sz);
+	if (last_accessed)
+		r->nr_accesses++;
+
+	last_addr = r->sampling_addr;
+}
+
+unsigned int kdamond_check_phys_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_check_phys_access(ctx, r);
+			max_nr_accesses = max(r->nr_accesses, max_nr_accesses);
+		}
+	}
+
+	return max_nr_accesses;
+}
 
 /*
  * Functions for the target validity check and cleanup
-- 
2.17.1



  parent reply	other threads:[~2020-08-31 10:49 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-31 10:47 [RFC v8 00/10] DAMON: Support Physical Memory Address Space Monitoring SeongJae Park
2020-08-31 10:47 ` [RFC v8 01/10] mm/damon/debugfs: Allow users to set initial monitoring target regions SeongJae Park
2020-08-31 18:08   ` Marco Elver
2020-09-01  6:35     ` SeongJae Park
2020-08-31 10:47 ` [RFC v8 02/10] tools/damon: Support init target regions specification SeongJae Park
2020-08-31 10:47 ` [RFC v8 03/10] mm/damon-test: Add more unit tests for 'init_regions' SeongJae Park
2020-08-31 10:47 ` [RFC v8 04/10] selftests/damon/_chk_record: Do not check number of gaps SeongJae Park
2020-08-31 10:47 ` [RFC v8 05/10] Docs/admin-guide/mm/damon: Document 'init_regions' feature SeongJae Park
2020-08-31 10:47 ` SeongJae Park [this message]
2020-08-31 10:47 ` [RFC v8 07/10] mm/damon/debugfs: Support physical memory monitoring SeongJae Park
2020-08-31 10:47 ` [RFC v8 08/10] tools/damon/record: " SeongJae Park
2020-08-31 10:47 ` [RFC v8 09/10] tools/damon/record: Support NUMA specific recording SeongJae Park
2020-08-31 10:47 ` [RFC v8 10/10] Docs/DAMON: Document physical memory monitoring support SeongJae Park
2020-09-01  6:37 ` [RFC v8 00/10] DAMON: Support Physical Memory Address Space Monitoring SeongJae Park

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200831104730.28970-7-sjpark@amazon.com \
    --to=sjpark@amazon.com \
    --cc=Jonathan.Cameron@Huawei.com \
    --cc=aarcange@redhat.com \
    --cc=acme@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=amit@kernel.org \
    --cc=benh@kernel.crashing.org \
    --cc=brendan.d.gregg@gmail.com \
    --cc=brendanhiggins@google.com \
    --cc=cai@lca.pw \
    --cc=colin.king@canonical.com \
    --cc=corbet@lwn.net \
    --cc=david@redhat.com \
    --cc=dwmw@amazon.com \
    --cc=fan.du@intel.com \
    --cc=foersleo@amazon.de \
    --cc=gthelen@google.com \
    --cc=irogers@google.com \
    --cc=jolsa@redhat.com \
    --cc=kirill@shutemov.name \
    --cc=linux-damon@amazon.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mark.rutland@arm.com \
    --cc=mgorman@suse.de \
    --cc=minchan@kernel.org \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rdunlap@infradead.org \
    --cc=riel@surriel.com \
    --cc=rientjes@google.com \
    --cc=rostedt@goodmis.org \
    --cc=rppt@kernel.org \
    --cc=sblbir@amazon.com \
    --cc=shakeelb@google.com \
    --cc=shuah@kernel.org \
    --cc=sj38.park@gmail.com \
    --cc=sjpark@amazon.de \
    --cc=snu@amazon.de \
    --cc=vbabka@suse.cz \
    --cc=vdavydov.dev@gmail.com \
    --cc=yang.shi@linux.alibaba.com \
    --cc=ying.huang@intel.com \
    --cc=zgf574564920@gmail.com \
    --subject='Re: [RFC v8 06/10] mm/damon: Implement callbacks for physical memory monitoring' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox