khugepaged: introduce 'max_ptes_shared' tunable

'max_ptes_shared' specifies how many pages can be shared across multiple
processes.  Exceeding the number would block the collapse::

	/sys/kernel/mm/transparent_hugepage/khugepaged/max_ptes_shared

A higher value may increase memory footprint for some workloads.

By default, at least half of pages has to be not shared.

[colin.king@canonical.com: fix several spelling mistakes]
  Link: http://lkml.kernel.org/r/20200420084241.65433-1-colin.king@canonical.com
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Link: http://lkml.kernel.org/r/20200416160026.16538-9-kirill.shutemov@linux.intel.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 83 insertions, 0 deletions

diff --git a/tools/testing/selftests/vm/khugepaged.c b/tools/testing/selftests/vm/khugepaged.c
index ef67a8a3d784..51b89cedd09d 100644
--- a/tools/testing/selftests/vm/khugepaged.c
+++ b/tools/testing/selftests/vm/khugepaged.c
@@ -78,6 +78,7 @@ struct khugepaged_settings {
 	unsigned int scan_sleep_millisecs;
 	unsigned int max_ptes_none;
 	unsigned int max_ptes_swap;
+	unsigned int max_ptes_shared;
 	unsigned long pages_to_scan;
 };
 
@@ -277,6 +278,7 @@ static void write_settings(struct settings *settings)
 			khugepaged->scan_sleep_millisecs);
 	write_num("khugepaged/max_ptes_none", khugepaged->max_ptes_none);
 	write_num("khugepaged/max_ptes_swap", khugepaged->max_ptes_swap);
+	write_num("khugepaged/max_ptes_shared", khugepaged->max_ptes_shared);
 	write_num("khugepaged/pages_to_scan", khugepaged->pages_to_scan);
 }
 
@@ -313,6 +315,7 @@ static void save_settings(void)
 			read_num("khugepaged/scan_sleep_millisecs"),
 		.max_ptes_none = read_num("khugepaged/max_ptes_none"),
 		.max_ptes_swap = read_num("khugepaged/max_ptes_swap"),
+		.max_ptes_shared = read_num("khugepaged/max_ptes_shared"),
 		.pages_to_scan = read_num("khugepaged/pages_to_scan"),
 	};
 	success("OK");
@@ -896,12 +899,90 @@ static void collapse_fork_compound(void)
 			fail("Fail");
 		fill_memory(p, 0, page_size);
 
+		write_num("khugepaged/max_ptes_shared", hpage_pmd_nr - 1);
 		if (wait_for_scan("Collapse PTE table full of compound pages in child", p))
 			fail("Timeout");
 		else if (check_huge(p))
 			success("OK");
 		else
 			fail("Fail");
+		write_num("khugepaged/max_ptes_shared",
+				default_settings.khugepaged.max_ptes_shared);
+
+		validate_memory(p, 0, hpage_pmd_size);
+		munmap(p, hpage_pmd_size);
+		exit(exit_status);
+	}
+
+	wait(&wstatus);
+	exit_status += WEXITSTATUS(wstatus);
+
+	printf("Check if parent still has huge page...");
+	if (check_huge(p))
+		success("OK");
+	else
+		fail("Fail");
+	validate_memory(p, 0, hpage_pmd_size);
+	munmap(p, hpage_pmd_size);
+}
+
+static void collapse_max_ptes_shared()
+{
+	int max_ptes_shared = read_num("khugepaged/max_ptes_shared");
+	int wstatus;
+	void *p;
+
+	p = alloc_mapping();
+
+	printf("Allocate huge page...");
+	madvise(p, hpage_pmd_size, MADV_HUGEPAGE);
+	fill_memory(p, 0, hpage_pmd_size);
+	if (check_huge(p))
+		success("OK");
+	else
+		fail("Fail");
+
+	printf("Share huge page over fork()...");
+	if (!fork()) {
+		/* Do not touch settings on child exit */
+		skip_settings_restore = true;
+		exit_status = 0;
+
+		if (check_huge(p))
+			success("OK");
+		else
+			fail("Fail");
+
+		printf("Trigger CoW on page %d of %d...",
+				hpage_pmd_nr - max_ptes_shared - 1, hpage_pmd_nr);
+		fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared - 1) * page_size);
+		if (!check_huge(p))
+			success("OK");
+		else
+			fail("Fail");
+
+		if (wait_for_scan("Do not collapse with max_ptes_shared exceeded", p))
+			fail("Timeout");
+		else if (!check_huge(p))
+			success("OK");
+		else
+			fail("Fail");
+
+		printf("Trigger CoW on page %d of %d...",
+				hpage_pmd_nr - max_ptes_shared, hpage_pmd_nr);
+		fill_memory(p, 0, (hpage_pmd_nr - max_ptes_shared) * page_size);
+		if (!check_huge(p))
+			success("OK");
+		else
+			fail("Fail");
+
+
+		if (wait_for_scan("Collapse with max_ptes_shared PTEs shared", p))
+			fail("Timeout");
+		else if (check_huge(p))
+			success("OK");
+		else
+			fail("Fail");
 
 		validate_memory(p, 0, hpage_pmd_size);
 		munmap(p, hpage_pmd_size);
@@ -930,6 +1011,7 @@ int main(void)
 
 	default_settings.khugepaged.max_ptes_none = hpage_pmd_nr - 1;
 	default_settings.khugepaged.max_ptes_swap = hpage_pmd_nr / 8;
+	default_settings.khugepaged.max_ptes_shared = hpage_pmd_nr / 2;
 	default_settings.khugepaged.pages_to_scan = hpage_pmd_nr * 8;
 
 	save_settings();
@@ -947,6 +1029,7 @@ int main(void)
 	collapse_compound_extreme();
 	collapse_fork();
 	collapse_fork_compound();
+	collapse_max_ptes_shared();
 
 	restore_settings(0);
 }