Message-Id: <20201119160605.1272425-8-zi.yan@sent.com>
Date:   Thu, 19 Nov 2020 11:06:05 -0500
From:   Zi Yan <zi.yan@...t.com>
To:     linux-mm@...ck.org, Matthew Wilcox <willy@...radead.org>,
        "Kirill A . Shutemov" <kirill.shutemov@...ux.intel.com>
Cc:     Roman Gushchin <guro@...com>,
        Andrew Morton <akpm@...ux-foundation.org>,
        linux-kernel@...r.kernel.org, linux-kselftest@...r.kernel.org,
        Yang Shi <shy828301@...il.com>,
        Michal Hocko <mhocko@...nel.org>,
        John Hubbard <jhubbard@...dia.com>,
        Ralph Campbell <rcampbell@...dia.com>,
        David Nellans <dnellans@...dia.com>, Zi Yan <ziy@...dia.com>
Subject: [PATCH 7/7] mm: huge_memory: enable debugfs to split huge pages to any order.

From: Zi Yan <ziy@...dia.com>

It is used to test split_huge_page_to_list_to_order for pagecache THPs.
Also add test cases for split_huge_page_to_list_to_order via both
debugfs, truncating a file, and punching holes in a file.

Signed-off-by: Zi Yan <ziy@...dia.com>
---
 mm/huge_memory.c                              |  13 +-
 .../selftests/vm/split_huge_page_test.c       | 192 ++++++++++++++++--
 2 files changed, 186 insertions(+), 19 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cc70f70862d8..d6ce7be65fb2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2999,7 +2999,7 @@ static ssize_t split_huge_pages_in_range_pid_write(struct file *file,
 	static DEFINE_MUTEX(mutex);
 	ssize_t ret;
 	char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */
-	int pid;
+	int pid, to_order = 0;
 	unsigned long vaddr_start, vaddr_end, addr;
 	nodemask_t task_nodes;
 	struct mm_struct *mm;
@@ -3016,8 +3016,9 @@ static ssize_t split_huge_pages_in_range_pid_write(struct file *file,
 		goto out;
 
 	input_buf[79] = '\0';
-	ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
-	if (ret != 3) {
+	ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d", &pid, &vaddr_start, &vaddr_end, &to_order);
+	/* cannot split to order-1 THP, which is not possible */
+	if ((ret != 3 && ret != 4) || to_order == 1) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -3025,8 +3026,8 @@ static ssize_t split_huge_pages_in_range_pid_write(struct file *file,
 	vaddr_end &= PAGE_MASK;
 
 	ret = strlen(input_buf);
-	pr_debug("split huge pages in pid: %d, vaddr: [%lx - %lx]\n",
-		 pid, vaddr_start, vaddr_end);
+	pr_debug("split huge pages in pid: %d, vaddr: [%lx - %lx], to order: %d\n",
+		 pid, vaddr_start, vaddr_end, to_order);
 
 	mm = find_mm_struct(pid, &task_nodes);
 	if (IS_ERR(mm)) {
@@ -3066,7 +3067,7 @@ static ssize_t split_huge_pages_in_range_pid_write(struct file *file,
 		if (!trylock_page(page))
 			continue;
 
-		if (!split_huge_page(page))
+		if (!split_huge_page_to_list_to_order(page, NULL, to_order))
 			split++;
 
 		unlock_page(page);
diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c
index cd2ced8c1261..bfd35ae9cfd2 100644
--- a/tools/testing/selftests/vm/split_huge_page_test.c
+++ b/tools/testing/selftests/vm/split_huge_page_test.c
@@ -16,6 +16,7 @@
 #include <sys/wait.h>
 #include <malloc.h>
 #include <stdbool.h>
+#include <time.h>
 
 uint64_t pagesize;
 unsigned int pageshift;
@@ -24,6 +25,7 @@ uint64_t pmd_pagesize;
 #define PMD_SIZE_PATH "/sys/kernel/mm/transparent_hugepage/hpage_pmd_size"
 #define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages_in_range_pid"
 #define SMAP_PATH "/proc/self/smaps"
+#define THP_FS_PATH "/mnt/thp_fs"
 #define INPUT_MAX 80
 
 #define PFN_MASK     ((1UL<<55)-1)
@@ -89,19 +91,20 @@ static int write_file(const char *path, const char *buf, size_t buflen)
 	return (unsigned int) numwritten;
 }
 
-static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end)
+static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end, int order)
 {
 	char input[INPUT_MAX];
 	int ret;
 
-	ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start,
-			vaddr_end);
+	ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx,%d", pid, vaddr_start,
+			vaddr_end, order);
 	if (ret >= INPUT_MAX) {
 		printf("%s: Debugfs input is too long\n", __func__);
 		exit(EXIT_FAILURE);
 	}
 
-	if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) {
+	/* order == 1 is an invalid input that should be detected. */
+	if (order != 1 && !write_file(SPLIT_DEBUGFS, input, ret + 1)) {
 		perror(SPLIT_DEBUGFS);
 		exit(EXIT_FAILURE);
 	}
@@ -118,7 +121,7 @@ static bool check_for_pattern(FILE *fp, const char *pattern, char *buf)
 	return false;
 }
 
-static uint64_t check_huge(void *addr)
+static uint64_t check_huge(void *addr, const char *prefix)
 {
 	uint64_t thp = 0;
 	int ret;
@@ -143,13 +146,13 @@ static uint64_t check_huge(void *addr)
 		goto err_out;
 
 	/*
-	 * Fetch the AnonHugePages: in the same block and check the number of
+	 * Fetch the @prefix in the same block and check the number of
 	 * hugepages.
 	 */
-	if (!check_for_pattern(fp, "AnonHugePages:", buffer))
+	if (!check_for_pattern(fp, prefix, buffer))
 		goto err_out;
 
-	if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) {
+	if (sscanf(&buffer[strlen(prefix)], "%10ld kB", &thp) != 1) {
 		printf("Reading smap error\n");
 		exit(EXIT_FAILURE);
 	}
@@ -173,14 +176,14 @@ void split_pmd_thp(void)
 	for (i = 0; i < len; i++)
 		one_page[i] = (char)i;
 
-	thp_size = check_huge(one_page);
+	thp_size = check_huge(one_page, "AnonHugePages:");
 	if (!thp_size) {
 		printf("No THP is allocatd");
 		exit(EXIT_FAILURE);
 	}
 
 	/* split all possible huge pages */
-	write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len);
+	write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len, 0);
 
 	for (i = 0; i < len; i++)
 		if (one_page[i] != (char)i) {
@@ -189,7 +192,7 @@ void split_pmd_thp(void)
 		}
 
 
-	thp_size = check_huge(one_page);
+	thp_size = check_huge(one_page, "AnonHugePages:");
 	if (thp_size) {
 		printf("Still %ld kB AnonHugePages not split\n", thp_size);
 		exit(EXIT_FAILURE);
@@ -237,7 +240,7 @@ void split_pte_mapped_thp(void)
 	for (i = 0; i < len; i++)
 		one_page[i] = (char)i;
 
-	thp_size = check_huge(one_page);
+	thp_size = check_huge(one_page, "AnonHugePages:");
 	if (!thp_size) {
 		printf("No THP is allocatd");
 		exit(EXIT_FAILURE);
@@ -270,7 +273,7 @@ void split_pte_mapped_thp(void)
 
 	/* split all possible huge pages */
 	write_debugfs(getpid(), (uint64_t)pte_mapped,
-		      (uint64_t)pte_mapped + pagesize * 4);
+		      (uint64_t)pte_mapped + pagesize * 4, 0);
 
 	/* smap does not show THPs after mremap, use kpageflags instead */
 	thp_size = 0;
@@ -295,19 +298,182 @@ void split_pte_mapped_thp(void)
 	close(kpageflags_fd);
 }
 
+void create_pagecache_thp_and_fd(size_t fd_size, int *fd, char **addr)
+{
+	const char testfile[] = THP_FS_PATH "/test";
+	size_t i;
+	int dummy;
+
+	srand(time(NULL));
+
+	*fd = open(testfile, O_CREAT | O_RDWR, 0664);
+	if (*fd == -1) {
+		perror("Failed to create a file at "THP_FS_PATH);
+		exit(EXIT_FAILURE);
+	}
+
+	for (i = 0; i < fd_size; i++) {
+		unsigned char byte = (unsigned char)i;
+
+		write(*fd, &byte, sizeof(byte));
+	}
+	close(*fd);
+	sync();
+	*fd = open("/proc/sys/vm/drop_caches", O_WRONLY);
+	if (*fd == -1) {
+		perror("open drop_caches");
+		exit(EXIT_FAILURE);
+	}
+	if (write(*fd, "3", 1) != 1) {
+		perror("write to drop_caches");
+		exit(EXIT_FAILURE);
+	}
+	close(*fd);
+
+	*fd = open(testfile, O_RDWR);
+	if (*fd == -1) {
+		perror("Failed to open a file at "THP_FS_PATH);
+		exit(EXIT_FAILURE);
+	}
+
+	*addr = mmap(NULL, fd_size, PROT_READ|PROT_WRITE, MAP_SHARED, *fd, 0);
+	if (*addr == (char *)-1) {
+		perror("cannot mmap");
+		exit(1);
+	}
+	madvise(*addr, fd_size, MADV_HUGEPAGE);
+
+	for (size_t i = 0; i < fd_size; i++)
+		dummy += *(*addr + i);
+
+	if (!check_huge(*addr, "FilePmdMapped:")) {
+		printf("No pagecache THP generated, please mount a filesystem "
+		       "supporting pagecache THP at "THP_FS_PATH"\n");
+		exit(EXIT_FAILURE);
+	}
+}
+
+void split_thp_in_pagecache_to_order(size_t fd_size, int order)
+{
+	int fd;
+	char *addr;
+	size_t i;
+
+	create_pagecache_thp_and_fd(fd_size, &fd, &addr);
+
+	printf("split %ld kB pagecache page to order %d ... ", fd_size >> 10, order);
+	write_debugfs(getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order);
+
+	for (i = 0; i < fd_size; i++)
+		if (*(addr + i) != (char)i) {
+			printf("%lu byte corrupted in the file\n");
+			exit(EXIT_FAILURE);
+		}
+
+	close(fd);
+	printf("done\n");
+}
+
+void truncate_thp_in_pagecache_to_order(size_t fd_size, int order)
+{
+	int fd;
+	char *addr;
+	size_t i;
+
+	create_pagecache_thp_and_fd(fd_size, &fd, &addr);
+
+	printf("truncate %ld kB pagecache page to size %lu kB ... ", fd_size >> 10, 4UL << order);
+	ftruncate(fd, pagesize << order);
+
+	for (i = 0; i < (pagesize << order); i++)
+		if (*(addr + i) != (char)i) {
+			printf("%lu byte corrupted in the file\n");
+			exit(EXIT_FAILURE);
+		}
+
+	close(fd);
+	printf("done\n");
+}
+
+void punch_hole_in_pagecache_thp(size_t fd_size, off_t offset[], off_t len[], int n)
+{
+	int fd, j;
+	char *addr;
+	size_t i;
+
+	create_pagecache_thp_and_fd(fd_size, &fd, &addr);
+
+	for (j = 0; j < n; j++) {
+		printf("addr: %lx, punch a hole at offset %ld kB with len %ld kB ... ",
+			addr, offset[j] >> 10, len[j] >> 10);
+		fallocate(fd, FALLOC_FL_PUNCH_HOLE|FALLOC_FL_KEEP_SIZE, offset[j], len[j]);
+		printf("done\n");
+	}
+
+	for (i = 0; i < fd_size; i++) {
+		int in_hole = 0;
+
+		for (j = 0; j < n; j++)
+			if (i >= offset[j] && i <= (offset[j] + len[j])) {
+				in_hole = 1;
+				break;
+			}
+
+		if (in_hole)
+			continue;
+		if (*(addr + i) != (char)i) {
+			printf("%lu byte corrupted in the file\n", i);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	close(fd);
+
+}
+
 int main(int argc, char **argv)
 {
+	int i;
+	size_t fd_size;
+	off_t offset[2], len[2];
+
 	if (geteuid() != 0) {
 		printf("Please run the benchmark as root\n");
 		exit(EXIT_FAILURE);
 	}
 
+	setbuf(stdout, NULL);
+
 	pagesize = getpagesize();
 	pageshift = ffs(pagesize) - 1;
 	pmd_pagesize = read_pmd_pagesize();
+	fd_size = 2 * pmd_pagesize;
 
 	split_pmd_thp();
 	split_pte_mapped_thp();
 
+	for (i = 8; i >= 0; i--)
+		split_thp_in_pagecache_to_order(fd_size, i);
+
+	/*
+	 * for i is 1, truncate code in the kernel should create order-0 pages
+	 * instead of order-1 THPs, since order-1 THP is not supported. No error
+	 * is expected.
+	 */
+	for (i = 8; i >= 0; i--)
+		truncate_thp_in_pagecache_to_order(fd_size, i);
+
+	offset[0] = 123 * pagesize;
+	offset[1] = 4 * pagesize;
+	len[0] = 200 * pagesize;
+	len[1] = 16 * pagesize;
+	punch_hole_in_pagecache_thp(fd_size, offset, len, 2);
+
+	offset[0] = 259 * pagesize;
+	offset[1] = 33 * pagesize;
+	len[0] = 129 * pagesize;
+	len[1] = 16 * pagesize;
+	punch_hole_in_pagecache_thp(fd_size, offset, len, 2);
+
 	return 0;
 }
-- 
2.28.0

Powered by blists - more mailing lists