[PATCH v4 1/3] mm: add thp_utilization metrics to debugfs

[<alexlzhu@fb.com>]

From: Alexander Zhu <alexlzhu@fb.com>

This change introduces a tool that scans through all of physical
memory for anonymous THPs and groups them into buckets based
on utilization. It also includes an interface under
/sys/kernel/debug/thp_utilization.

Sample Output:

Utilized[0-50]: 1331 680884
Utilized[51-101]: 9 3983
Utilized[102-152]: 3 1187
Utilized[153-203]: 0 0
Utilized[204-255]: 2 539
Utilized[256-306]: 5 1135
Utilized[307-357]: 1 192
Utilized[358-408]: 0 0
Utilized[409-459]: 1 57
Utilized[460-512]: 400 13
Last Scan Time: 223.98s
Last Scan Duration: 70.65s

This indicates that there are 1331 THPs that have between 0 and 50
utilized (non zero) pages. In total there are 680884 zero pages in
this utilization bucket. THPs in the [0-50] bucket compose 76% of total
THPs, and are responsible for 99% of total zero pages across all
THPs. In other words, the least utilized THPs are responsible for almost
all of the memory waste when THP is always enabled. Similar results
have been observed across production workloads.

The last two lines indicate the timestamp and duration of the most recent
scan through all of physical memory. Here we see that the last scan
occurred 223.98 seconds after boot time and took 70.65 seconds.

Utilization of a THP is defined as the percentage of nonzero
pages in the THP. The worker thread will scan through all
of physical memory and obtain utilization of all anonymous
THPs. It will gather this information by periodically scanning
through all of physical memory for anonymous THPs, group them
into buckets based on utilization, and report utilization
information through debugfs under /sys/kernel/debug/thp_utilization.

Signed-off-by: Alexander Zhu <alexlzhu@fb.com>
---
v3 to v4
-changed thp_utilization_bucket() function to take folios, saves conversion between page and folio
-added newlines where they were previously missing in v2-v3
-moved the thp utilization code out into its own file under mm/thp_utilization.c
-removed is_anonymous_transparent_hugepage function. Use folio_test_anon and folio_test_trans_huge instead.
-changed thp_number_utilized_pages to use memchr_inv

v1 to v2
-reversed ordering of is_transparent_hugepage and PageAnon in is_anon_transparent_hugepage, page->mapping is only meaningful for user pages

RFC to v1
-Refactored out the code to obtain the thp_utilization_bucket, as that now has to be used in multiple places.

 Documentation/admin-guide/mm/transhuge.rst |   9 +
 mm/Makefile                                |   2 +-
 mm/thp_utilization.c                       | 203 +++++++++++++++++++++
 3 files changed, 213 insertions(+), 1 deletion(-)
 create mode 100644 mm/thp_utilization.c

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index 8ee78ec232eb..21d86303c97e 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -304,6 +304,15 @@ To identify what applications are mapping file transparent huge pages, it
 is necessary to read ``/proc/PID/smaps`` and count the FileHugeMapped fields
 for each mapping.
 
+The utilization of transparent hugepages can be viewed by reading
+``/sys/kernel/debug/thp_utilization``. The utilization of a THP is defined
+as the ratio of non zero filled 4kb pages to the total number of pages in a
+THP. The buckets are labelled by the range of total utilized 4kb pages with
+one line per utilization bucket. Each line contains the total number of
+THPs in that bucket and the total number of zero filled 4kb pages summed
+over all THPs in that bucket. The last two lines show the timestamp and
+duration respectively of the most recent scan over all of physical memory.
+
 Note that reading the smaps file is expensive and reading it
 frequently will incur overhead.
 
diff --git a/mm/Makefile b/mm/Makefile
index 8e105e5b3e29..5f76dc6ce044 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -95,7 +95,7 @@ obj-$(CONFIG_MEMTEST)		+= memtest.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_NUMA) += memory-tiers.o
 obj-$(CONFIG_DEVICE_MIGRATION) += migrate_device.o
-obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o khugepaged.o thp_utilization.o
 obj-$(CONFIG_PAGE_COUNTER) += page_counter.o
 obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
 ifdef CONFIG_SWAP
diff --git a/mm/thp_utilization.c b/mm/thp_utilization.c
new file mode 100644
index 000000000000..7b79f8759d12
--- /dev/null
+++ b/mm/thp_utilization.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Copyright (C) 2022  Meta, Inc.
+ *  Authors: Alexander Zhu, Johannes Weiner, Rik van Riel
+ */
+
+#include <linux/mm.h>
+#include <linux/debugfs.h>
+#include <linux/highmem.h>
+/*
+ * The number of utilization buckets THPs will be grouped in
+ * under /sys/kernel/debug/thp_utilization.
+ */
+#define THP_UTIL_BUCKET_NR 10
+/*
+ * The number of hugepages to scan through on each periodic
+ * run of the scanner that generates /sys/kernel/debug/thp_utilization.
+ */
+#define THP_UTIL_SCAN_SIZE 256
+
+static void thp_utilization_workfn(struct work_struct *work);
+static DECLARE_DELAYED_WORK(thp_utilization_work, thp_utilization_workfn);
+
+struct thp_scan_info_bucket {
+	int nr_thps;
+	int nr_zero_pages;
+};
+
+struct thp_scan_info {
+	struct thp_scan_info_bucket buckets[THP_UTIL_BUCKET_NR];
+	struct zone *scan_zone;
+	struct timespec64 last_scan_duration;
+	struct timespec64 last_scan_time;
+	unsigned long pfn;
+};
+
+/*
+ * thp_scan_debugfs is referred to when /sys/kernel/debug/thp_utilization
+ * is opened. thp_scan is used to keep track fo the current scan through
+ * physical memory.
+ */
+static struct thp_scan_info thp_scan_debugfs;
+static struct thp_scan_info thp_scan;
+
+#ifdef CONFIG_DEBUG_FS
+static int thp_utilization_show(struct seq_file *seqf, void *pos)
+{
+	int i;
+	int start;
+	int end;
+
+	for (i = 0; i < THP_UTIL_BUCKET_NR; i++) {
+		start = i * HPAGE_PMD_NR / THP_UTIL_BUCKET_NR;
+		end = (i + 1 == THP_UTIL_BUCKET_NR)
+			   ? HPAGE_PMD_NR
+			   : ((i + 1) * HPAGE_PMD_NR / THP_UTIL_BUCKET_NR - 1);
+		/* The last bucket will need to contain 100 */
+		seq_printf(seqf, "Utilized[%d-%d]: %d %d\n", start, end,
+			   thp_scan_debugfs.buckets[i].nr_thps,
+			   thp_scan_debugfs.buckets[i].nr_zero_pages);
+	}
+
+	seq_printf(seqf, "Last Scan Time: %lu.%02lus\n",
+		   (unsigned long)thp_scan_debugfs.last_scan_time.tv_sec,
+		   (thp_scan_debugfs.last_scan_time.tv_nsec / (NSEC_PER_SEC / 100)));
+
+	seq_printf(seqf, "Last Scan Duration: %lu.%02lus\n",
+		   (unsigned long)thp_scan_debugfs.last_scan_duration.tv_sec,
+		   (thp_scan_debugfs.last_scan_duration.tv_nsec / (NSEC_PER_SEC / 100)));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(thp_utilization);
+
+static int __init thp_utilization_debugfs(void)
+{
+	debugfs_create_file("thp_utilization", 0200, NULL, NULL,
+			    &thp_utilization_fops);
+	return 0;
+}
+late_initcall(thp_utilization_debugfs);
+#endif
+
+static int thp_utilization_bucket(int num_utilized_pages)
+{
+	int bucket;
+
+	if (num_utilized_pages < 0 || num_utilized_pages > HPAGE_PMD_NR)
+		return -1;
+
+	/* Group THPs into utilization buckets */
+	bucket = num_utilized_pages * THP_UTIL_BUCKET_NR / HPAGE_PMD_NR;
+	return min(bucket, THP_UTIL_BUCKET_NR - 1);
+}
+
+static int thp_number_utilized_pages(struct folio *folio)
+{
+	int thp_nr_utilized_pages = HPAGE_PMD_NR;
+	void *kaddr;
+	int i;
+
+	if (!folio || !folio_test_anon(folio) || !folio_test_transhuge(folio))
+		return -1;
+
+	for (i = 0; i < folio_nr_pages(folio); i++) {
+		kaddr = kmap_local_folio(folio, i);
+		if (memchr_inv(kaddr, 0, PAGE_SIZE))
+			thp_nr_utilized_pages--;
+
+		kunmap_local(kaddr);
+	}
+
+	return thp_nr_utilized_pages;
+}
+
+static void thp_scan_next_zone(void)
+{
+	struct timespec64 current_time;
+	bool update_debugfs;
+	/*
+	 * THP utilization worker thread has reached the end
+	 * of the memory zone. Proceed to the next zone.
+	 */
+	thp_scan.scan_zone = next_zone(thp_scan.scan_zone);
+	update_debugfs = !thp_scan.scan_zone;
+	thp_scan.scan_zone = update_debugfs ? (first_online_pgdat())->node_zones
+			: thp_scan.scan_zone;
+	thp_scan.pfn = (thp_scan.scan_zone->zone_start_pfn + HPAGE_PMD_NR - 1)
+			& ~(HPAGE_PMD_SIZE - 1);
+	if (!update_debugfs)
+		return;
+
+	/*
+	 * If the worker has scanned through all of physical memory then
+	 * update information displayed in /sys/kernel/debug/thp_utilization
+	 */
+	ktime_get_ts64(&current_time);
+	thp_scan_debugfs.last_scan_duration = timespec64_sub(current_time,
+							     thp_scan_debugfs.last_scan_time);
+	thp_scan_debugfs.last_scan_time = current_time;
+
+	memcpy(&thp_scan_debugfs.buckets, &thp_scan.buckets, sizeof(thp_scan.buckets));
+	memset(&thp_scan.buckets, 0, sizeof(thp_scan.buckets));
+}
+
+static void thp_util_scan(unsigned long pfn_end)
+{
+	struct page *page = NULL;
+	int bucket, current_pfn, num_utilized_pages;
+	int i;
+	/*
+	 * Scan through each memory zone in chunks of THP_UTIL_SCAN_SIZE
+	 * PFNs every second looking for anonymous THPs.
+	 */
+	for (i = 0; i < THP_UTIL_SCAN_SIZE; i++) {
+		current_pfn = thp_scan.pfn;
+		thp_scan.pfn += HPAGE_PMD_NR;
+		if (current_pfn >= pfn_end)
+			return;
+
+		page = pfn_to_online_page(current_pfn);
+		if (!page)
+			continue;
+
+		num_utilized_pages = thp_number_utilized_pages(page_folio(page));
+		bucket = thp_utilization_bucket(num_utilized_pages);
+		if (bucket < 0)
+			continue;
+
+		thp_scan.buckets[bucket].nr_thps++;
+		thp_scan.buckets[bucket].nr_zero_pages += (HPAGE_PMD_NR - num_utilized_pages);
+	}
+}
+
+static void thp_utilization_workfn(struct work_struct *work)
+{
+	unsigned long pfn_end;
+	/*
+	 * Worker function that scans through all of physical memory
+	 * for anonymous THPs.
+	 */
+	if (!thp_scan.scan_zone)
+		thp_scan.scan_zone = (first_online_pgdat())->node_zones;
+
+	pfn_end = zone_end_pfn(thp_scan.scan_zone);
+	/* If we have reached the end of the zone or end of physical memory
+	 * move on to the next zone. Otherwise, scan the next PFNs in the
+	 * current zone.
+	 */
+	if (!managed_zone(thp_scan.scan_zone) || thp_scan.pfn >= pfn_end)
+		thp_scan_next_zone();
+	else
+		thp_util_scan(pfn_end);
+
+	schedule_delayed_work(&thp_utilization_work, HZ);
+}
+
+static int __init thp_scan_init(void)
+{
+	schedule_delayed_work(&thp_utilization_work, HZ);
+	return 0;
+}
+subsys_initcall(thp_scan_init);
-- 
2.30.2