tools/mm: introduce a tool to assess swap entry allocation for thp_swapout

Both Ryan and Chris have been utilizing the small test program to aid in
debugging and identifying issues with swap entry allocation.  While a real
or intricate workload might be more suitable for assessing the correctness
and effectiveness of the swap allocation policy, a small test program
presents a simpler means of understanding the problem and initially
verifying the improvements being made.

Let's endeavor to integrate it into tools/mm.  Although it presently only
accommodates 64KB and 4KB, I'm optimistic that we can expand its
capabilities to support multiple sizes and simulate more complex systems
in the future as required.

Basically, we have

1. Use MADV_PAGEPUT for rapid swap-out, putting the swap allocation
   code under high exercise in a short time.

2. Use MADV_DONTNEED to simulate the behavior of libc and Java heap in
   freeing memory, as well as for munmap, app exits, or OOM killer
   scenarios.  This ensures new mTHP is always generated, released or
   swapped out, similar to the behavior on a PC or Android phone where
   many applications are frequently started and terminated.

3. Swap in with or without the "-a" option to observe how fragments
   due to swap-in and the incoming swap-in of large folios will impact
   swap-out fallback.

Due to 2, we ensure a certain proportion of mTHP.  Similarly, because of
3, we maintain a certain proportion of small folios, as we don't support
large folios swap-in, meaning any swap-in will immediately result in small
folios.  Therefore, with both 2 and 3, we automatically achieve a system
containing both mTHP and small folios.  Additionally, 1 provides the
ability to continuously swap them out.

We can also use "-s" to add a dedicated small folios memory area.

[akpm@linux-foundation.org: thp_swap_allocator_test.c needs mman.h, per Kairui Song]
Link: https://lkml.kernel.org/r/20240622071231.576056-2-21cnbao@gmail.com
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Acked-by: Chris Li <chrisl@kernel.org>
Tested-by: Chris Li <chrisl@kernel.org>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 235 insertions, 1 deletions

diff --git a/tools/mm/Makefile b/tools/mm/Makefile
index 7bb03606b9ea..15791c1c5b28 100644
--- a/tools/mm/Makefile
+++ b/tools/mm/Makefile
@@ -3,7 +3,7 @@
 #
 include ../scripts/Makefile.include
 
-BUILD_TARGETS=page-types slabinfo page_owner_sort
+BUILD_TARGETS=page-types slabinfo page_owner_sort thp_swap_allocator_test
 INSTALL_TARGETS = $(BUILD_TARGETS) thpmaps
 
 LIB_DIR = ../lib/api
diff --git a/tools/mm/thp_swap_allocator_test.c b/tools/mm/thp_swap_allocator_test.c
new file mode 100644
index 000000000000..83afc52275a5
--- /dev/null
+++ b/tools/mm/thp_swap_allocator_test.c
@@ -0,0 +1,234 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * thp_swap_allocator_test
+ *
+ * The purpose of this test program is helping check if THP swpout
+ * can correctly get swap slots to swap out as a whole instead of
+ * being split. It randomly releases swap entries through madvise
+ * DONTNEED and swapin/out on two memory areas: a memory area for
+ * 64KB THP and the other area for small folios. The second memory
+ * can be enabled by "-s".
+ * Before running the program, we need to setup a zRAM or similar
+ * swap device by:
+ *  echo lzo > /sys/block/zram0/comp_algorithm
+ *  echo 64M > /sys/block/zram0/disksize
+ *  echo never > /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled
+ *  echo always > /sys/kernel/mm/transparent_hugepage/hugepages-64kB/enabled
+ *  mkswap /dev/zram0
+ *  swapon /dev/zram0
+ * The expected result should be 0% anon swpout fallback ratio w/ or
+ * w/o "-s".
+ *
+ * Author(s): Barry Song <v-songbaohua@oppo.com>
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <string.h>
+#include <linux/mman.h>
+#include <sys/mman.h>
+#include <errno.h>
+#include <time.h>
+
+#define MEMSIZE_MTHP (60 * 1024 * 1024)
+#define MEMSIZE_SMALLFOLIO (4 * 1024 * 1024)
+#define ALIGNMENT_MTHP (64 * 1024)
+#define ALIGNMENT_SMALLFOLIO (4 * 1024)
+#define TOTAL_DONTNEED_MTHP (16 * 1024 * 1024)
+#define TOTAL_DONTNEED_SMALLFOLIO (1 * 1024 * 1024)
+#define MTHP_FOLIO_SIZE (64 * 1024)
+
+#define SWPOUT_PATH \
+	"/sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout"
+#define SWPOUT_FALLBACK_PATH \
+	"/sys/kernel/mm/transparent_hugepage/hugepages-64kB/stats/swpout_fallback"
+
+static void *aligned_alloc_mem(size_t size, size_t alignment)
+{
+	void *mem = NULL;
+
+	if (posix_memalign(&mem, alignment, size) != 0) {
+		perror("posix_memalign");
+		return NULL;
+	}
+	return mem;
+}
+
+/*
+ * This emulates the behavior of native libc and Java heap,
+ * as well as process exit and munmap. It helps generate mTHP
+ * and ensures that iterations can proceed with mTHP, as we
+ * currently don't support large folios swap-in.
+ */
+static void random_madvise_dontneed(void *mem, size_t mem_size,
+		size_t align_size, size_t total_dontneed_size)
+{
+	size_t num_pages = total_dontneed_size / align_size;
+	size_t i;
+	size_t offset;
+	void *addr;
+
+	for (i = 0; i < num_pages; ++i) {
+		offset = (rand() % (mem_size / align_size)) * align_size;
+		addr = (char *)mem + offset;
+		if (madvise(addr, align_size, MADV_DONTNEED) != 0)
+			perror("madvise dontneed");
+
+		memset(addr, 0x11, align_size);
+	}
+}
+
+static void random_swapin(void *mem, size_t mem_size,
+		size_t align_size, size_t total_swapin_size)
+{
+	size_t num_pages = total_swapin_size / align_size;
+	size_t i;
+	size_t offset;
+	void *addr;
+
+	for (i = 0; i < num_pages; ++i) {
+		offset = (rand() % (mem_size / align_size)) * align_size;
+		addr = (char *)mem + offset;
+		memset(addr, 0x11, align_size);
+	}
+}
+
+static unsigned long read_stat(const char *path)
+{
+	FILE *file;
+	unsigned long value;
+
+	file = fopen(path, "r");
+	if (!file) {
+		perror("fopen");
+		return 0;
+	}
+
+	if (fscanf(file, "%lu", &value) != 1) {
+		perror("fscanf");
+		fclose(file);
+		return 0;
+	}
+
+	fclose(file);
+	return value;
+}
+
+int main(int argc, char *argv[])
+{
+	int use_small_folio = 0, aligned_swapin = 0;
+	void *mem1 = NULL, *mem2 = NULL;
+	int i;
+
+	for (i = 1; i < argc; ++i) {
+		if (strcmp(argv[i], "-s") == 0)
+			use_small_folio = 1;
+		else if (strcmp(argv[i], "-a") == 0)
+			aligned_swapin = 1;
+	}
+
+	mem1 = aligned_alloc_mem(MEMSIZE_MTHP, ALIGNMENT_MTHP);
+	if (mem1 == NULL) {
+		fprintf(stderr, "Failed to allocate large folios memory\n");
+		return EXIT_FAILURE;
+	}
+
+	if (madvise(mem1, MEMSIZE_MTHP, MADV_HUGEPAGE) != 0) {
+		perror("madvise hugepage for mem1");
+		free(mem1);
+		return EXIT_FAILURE;
+	}
+
+	if (use_small_folio) {
+		mem2 = aligned_alloc_mem(MEMSIZE_SMALLFOLIO, ALIGNMENT_MTHP);
+		if (mem2 == NULL) {
+			fprintf(stderr, "Failed to allocate small folios memory\n");
+			free(mem1);
+			return EXIT_FAILURE;
+		}
+
+		if (madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_NOHUGEPAGE) != 0) {
+			perror("madvise nohugepage for mem2");
+			free(mem1);
+			free(mem2);
+			return EXIT_FAILURE;
+		}
+	}
+
+	/* warm-up phase to occupy the swapfile */
+	memset(mem1, 0x11, MEMSIZE_MTHP);
+	madvise(mem1, MEMSIZE_MTHP, MADV_PAGEOUT);
+	if (use_small_folio) {
+		memset(mem2, 0x11, MEMSIZE_SMALLFOLIO);
+		madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_PAGEOUT);
+	}
+
+	/* iterations with newly created mTHP, swap-in, and swap-out */
+	for (i = 0; i < 100; ++i) {
+		unsigned long initial_swpout;
+		unsigned long initial_swpout_fallback;
+		unsigned long final_swpout;
+		unsigned long final_swpout_fallback;
+		unsigned long swpout_inc;
+		unsigned long swpout_fallback_inc;
+		double fallback_percentage;
+
+		initial_swpout = read_stat(SWPOUT_PATH);
+		initial_swpout_fallback = read_stat(SWPOUT_FALLBACK_PATH);
+
+		/*
+		 * The following setup creates a 1:1 ratio of mTHP to small folios
+		 * since large folio swap-in isn't supported yet. Once we support
+		 * mTHP swap-in, we'll likely need to reduce MEMSIZE_MTHP and
+		 * increase MEMSIZE_SMALLFOLIO to maintain the ratio.
+		 */
+		random_swapin(mem1, MEMSIZE_MTHP,
+				aligned_swapin ? ALIGNMENT_MTHP : ALIGNMENT_SMALLFOLIO,
+				TOTAL_DONTNEED_MTHP);
+		random_madvise_dontneed(mem1, MEMSIZE_MTHP, ALIGNMENT_MTHP,
+				TOTAL_DONTNEED_MTHP);
+
+		if (use_small_folio) {
+			random_swapin(mem2, MEMSIZE_SMALLFOLIO,
+					ALIGNMENT_SMALLFOLIO,
+					TOTAL_DONTNEED_SMALLFOLIO);
+		}
+
+		if (madvise(mem1, MEMSIZE_MTHP, MADV_PAGEOUT) != 0) {
+			perror("madvise pageout for mem1");
+			free(mem1);
+			if (mem2 != NULL)
+				free(mem2);
+			return EXIT_FAILURE;
+		}
+
+		if (use_small_folio) {
+			if (madvise(mem2, MEMSIZE_SMALLFOLIO, MADV_PAGEOUT) != 0) {
+				perror("madvise pageout for mem2");
+				free(mem1);
+				free(mem2);
+				return EXIT_FAILURE;
+			}
+		}
+
+		final_swpout = read_stat(SWPOUT_PATH);
+		final_swpout_fallback = read_stat(SWPOUT_FALLBACK_PATH);
+
+		swpout_inc = final_swpout - initial_swpout;
+		swpout_fallback_inc = final_swpout_fallback - initial_swpout_fallback;
+
+		fallback_percentage = (double)swpout_fallback_inc /
+			(swpout_fallback_inc + swpout_inc) * 100;
+
+		printf("Iteration %d: swpout inc: %lu, swpout fallback inc: %lu, Fallback percentage: %.2f%%\n",
+				i + 1, swpout_inc, swpout_fallback_inc, fallback_percentage);
+	}
+
+	free(mem1);
+	if (mem2 != NULL)
+		free(mem2);
+
+	return EXIT_SUCCESS;
+}