+ selftests-vm-add-test-to-measure-madv_unmergeable-performance.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: selftests/vm: add test to measure MADV_UNMERGEABLE performance
has been added to the -mm mm-unstable branch.  Its filename is
     selftests-vm-add-test-to-measure-madv_unmergeable-performance.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/selftests-vm-add-test-to-measure-madv_unmergeable-performance.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: David Hildenbrand <david@redhat.com>
Subject: selftests/vm: add test to measure MADV_UNMERGEABLE performance
Date: Fri, 30 Sep 2022 16:19:25 +0200

Patch series "mm/ksm: break_ksm() cleanups and fixes".

This series cleans up and fixes break_ksm().  In summary, we no longer use
fake write faults to break COW but instead FAULT_FLAG_UNSHARE.  Further,
we move away from using follow_page() [that we can hopefully remove
completely at one point] and use new walk_page_range_vma() instead.

Fortunately, we can get rid of VM_FAULT_WRITE and FOLL_MIGRATION in common
code now.

Add a selftest to measure MADV_UNMERGEABLE performance.  In my setup (AMD
Ryzen 9 3900X), running the KSM selftest to test unmerge performance on 2
GiB (taskset 0x8 ./ksm_tests -D -s 2048), this results in a performance
degradation of ~8% -- 9% (old: ~5250 MiB/s, new: ~4800 MiB/s).  I don't
think we particularly care for now, but it's good to be aware of the
implication.


This patch (of 7):

Let's add a test to measure performance of KSM breaking not triggered via
COW, but triggered by disabling KSM on an area filled with KSM pages via
MADV_UNMERGEABLE.

Link: https://lkml.kernel.org/r/20220930141931.174362-1-david@redhat.com
Link: https://lkml.kernel.org/r/20220930141931.174362-2-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 tools/testing/selftests/vm/ksm_tests.c |   76 ++++++++++++++++++++++-
 1 file changed, 74 insertions(+), 2 deletions(-)

--- a/tools/testing/selftests/vm/ksm_tests.c~selftests-vm-add-test-to-measure-madv_unmergeable-performance
+++ a/tools/testing/selftests/vm/ksm_tests.c
@@ -40,6 +40,7 @@ enum ksm_test_name {
 	CHECK_KSM_NUMA_MERGE,
 	KSM_MERGE_TIME,
 	KSM_MERGE_TIME_HUGE_PAGES,
+	KSM_UNMERGE_TIME,
 	KSM_COW_TIME
 };
 
@@ -108,7 +109,10 @@ static void print_help(void)
 	       " -P evaluate merging time and speed.\n"
 	       "    For this test, the size of duplicated memory area (in MiB)\n"
 	       "    must be provided using -s option\n"
-				 " -H evaluate merging time and speed of area allocated mostly with huge pages\n"
+	       " -H evaluate merging time and speed of area allocated mostly with huge pages\n"
+	       "    For this test, the size of duplicated memory area (in MiB)\n"
+	       "    must be provided using -s option\n"
+	       " -D evaluate unmerging time and speed when disabling KSM.\n"
 	       "    For this test, the size of duplicated memory area (in MiB)\n"
 	       "    must be provided using -s option\n"
 	       " -C evaluate the time required to break COW of merged pages.\n\n");
@@ -188,6 +192,16 @@ static int ksm_merge_pages(void *addr, s
 	return 0;
 }
 
+static int ksm_unmerge_pages(void *addr, size_t size,
+			     struct timespec start_time, int timeout)
+{
+	if (madvise(addr, size, MADV_UNMERGEABLE)) {
+		perror("madvise");
+		return 1;
+	}
+	return 0;
+}
+
 static bool assert_ksm_pages_count(long dupl_page_count)
 {
 	unsigned long max_page_sharing, pages_sharing, pages_shared;
@@ -560,6 +574,53 @@ err_out:
 	return KSFT_FAIL;
 }
 
+static int ksm_unmerge_time(int mapping, int prot, int timeout, size_t map_size)
+{
+	void *map_ptr;
+	struct timespec start_time, end_time;
+	unsigned long scan_time_ns;
+
+	map_size *= MB;
+
+	map_ptr = allocate_memory(NULL, prot, mapping, '*', map_size);
+	if (!map_ptr)
+		return KSFT_FAIL;
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) {
+		perror("clock_gettime");
+		goto err_out;
+	}
+	if (ksm_merge_pages(map_ptr, map_size, start_time, timeout))
+		goto err_out;
+
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &start_time)) {
+		perror("clock_gettime");
+		goto err_out;
+	}
+	if (ksm_unmerge_pages(map_ptr, map_size, start_time, timeout))
+		goto err_out;
+	if (clock_gettime(CLOCK_MONOTONIC_RAW, &end_time)) {
+		perror("clock_gettime");
+		goto err_out;
+	}
+
+	scan_time_ns = (end_time.tv_sec - start_time.tv_sec) * NSEC_PER_SEC +
+		       (end_time.tv_nsec - start_time.tv_nsec);
+
+	printf("Total size:    %lu MiB\n", map_size / MB);
+	printf("Total time:    %ld.%09ld s\n", scan_time_ns / NSEC_PER_SEC,
+	       scan_time_ns % NSEC_PER_SEC);
+	printf("Average speed:  %.3f MiB/s\n", (map_size / MB) /
+					       ((double)scan_time_ns / NSEC_PER_SEC));
+
+	munmap(map_ptr, map_size);
+	return KSFT_PASS;
+
+err_out:
+	printf("Not OK\n");
+	munmap(map_ptr, map_size);
+	return KSFT_FAIL;
+}
+
 static int ksm_cow_time(int mapping, int prot, int timeout, size_t page_size)
 {
 	void *map_ptr;
@@ -644,7 +705,7 @@ int main(int argc, char *argv[])
 	bool merge_across_nodes = KSM_MERGE_ACROSS_NODES_DEFAULT;
 	long size_MB = 0;
 
-	while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCH")) != -1) {
+	while ((opt = getopt(argc, argv, "ha:p:l:z:m:s:MUZNPCHD")) != -1) {
 		switch (opt) {
 		case 'a':
 			prot = str_to_prot(optarg);
@@ -701,6 +762,9 @@ int main(int argc, char *argv[])
 		case 'H':
 			test_name = KSM_MERGE_TIME_HUGE_PAGES;
 			break;
+		case 'D':
+			test_name = KSM_UNMERGE_TIME;
+			break;
 		case 'C':
 			test_name = KSM_COW_TIME;
 			break;
@@ -762,6 +826,14 @@ int main(int argc, char *argv[])
 		ret = ksm_merge_hugepages_time(MAP_PRIVATE | MAP_ANONYMOUS, prot,
 				ksm_scan_limit_sec, size_MB);
 		break;
+	case KSM_UNMERGE_TIME:
+		if (size_MB == 0) {
+			printf("Option '-s' is required.\n");
+			return KSFT_FAIL;
+		}
+		ret = ksm_unmerge_time(MAP_PRIVATE | MAP_ANONYMOUS, prot,
+				       ksm_scan_limit_sec, size_MB);
+		break;
 	case KSM_COW_TIME:
 		ret = ksm_cow_time(MAP_PRIVATE | MAP_ANONYMOUS, prot, ksm_scan_limit_sec,
 				   page_size);
_

Patches currently in -mm which might be from david@redhat.com are

selftests-vm-add-test-to-measure-madv_unmergeable-performance.patch
mm-ksm-simplify-break_ksm-to-not-rely-on-vm_fault_write.patch
mm-remove-vm_fault_write.patch
mm-ksm-fix-ksm-cow-breaking-with-userfaultfd-wp-via-fault_flag_unshare.patch
mm-pagewalk-add-walk_page_range_vma.patch
mm-ksm-convert-break_ksm-to-use-walk_page_range_vma.patch
mm-gup-remove-foll_migration.patch