[PATCH v5 1/2] mm: huge_memory: a new debugfs interface for splitting THP tests.

[PATCH v5 1/2] mm: huge_memory: a new debugfs interface for splitting THP tests.

[Zi Yan]

From: Zi Yan <ziy@nvidia.com>

We did not have a direct user interface of splitting the compound page
backing a THP and there is no need unless we want to expose the THP
implementation details to users. Make <debugfs>/split_huge_pages accept
a new command to do that.

By writing "<pid>,<vaddr_start>,<vaddr_end>" to
<debugfs>/split_huge_pages, THPs within the given virtual address range
from the process with the given pid are split. It is used to test
split_huge_page function. In addition, a selftest program is added to
tools/testing/selftests/vm to utilize the interface by splitting
PMD THPs and PTE-mapped THPs.

This does not change the old behavior, i.e., writing 1 to the interface
to split all THPs in the system.

Changelog:

From v5:
1. Skipped special VMAs and other fixes. (suggested by Yang Shi)

From v4:
1. Fixed the error code return issue, spotted by kernel test robot
   <lkp@intel.com>.

From v3:
1. Factored out split huge pages in the given pid code to a separate
   function.
2. Added the missing put_page for not split pages.
3. pr_debug -> pr_info, make reading results simpler.

From v2:
1. Reused existing <debugfs>/split_huge_pages interface. (suggested by
   Yang Shi)

From v1:
1. Removed unnecessary calling to vma_migratable, spotted by kernel test
   robot <lkp@intel.com>.
2. Dropped the use of find_mm_struct and code it directly, since there
   is no need for the permission check in that function and the function
   is only available when migration is on.
3. Added some comments in the selftest program to clarify how PTE-mapped
   THPs are formed.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/huge_memory.c                              | 143 +++++++-
 tools/testing/selftests/vm/.gitignore         |   1 +
 tools/testing/selftests/vm/Makefile           |   1 +
 .../selftests/vm/split_huge_page_test.c       | 318 ++++++++++++++++++
 4 files changed, 456 insertions(+), 7 deletions(-)
 create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index bff92dea5ab3..9bf9bc489228 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -7,6 +7,7 @@
 
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/sched/coredump.h>
 #include <linux/sched/numa_balancing.h>
 #include <linux/highmem.h>
@@ -2922,16 +2923,14 @@ static struct shrinker deferred_split_shrinker = {
 };
 
 #ifdef CONFIG_DEBUG_FS
-static int split_huge_pages_set(void *data, u64 val)
+static void split_huge_pages_all(void)
 {
 	struct zone *zone;
 	struct page *page;
 	unsigned long pfn, max_zone_pfn;
 	unsigned long total = 0, split = 0;
 
-	if (val != 1)
-		return -EINVAL;
-
+	pr_info("Split all THPs\n");
 	for_each_populated_zone(zone) {
 		max_zone_pfn = zone_end_pfn(zone);
 		for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
@@ -2959,11 +2958,141 @@ static int split_huge_pages_set(void *data, u64 val)
 	}
 
 	pr_info("%lu of %lu THP split\n", split, total);
+}
 
-	return 0;
+static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
+				unsigned long vaddr_end)
+{
+	int ret = 0;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	unsigned long total = 0, split = 0;
+	unsigned long addr;
+
+	vaddr_start &= PAGE_MASK;
+	vaddr_end &= PAGE_MASK;
+
+	/* Find the task_struct from pid */
+	rcu_read_lock();
+	task = find_task_by_vpid(pid);
+	if (!task) {
+		rcu_read_unlock();
+		ret = -ESRCH;
+		goto out;
+	}
+	get_task_struct(task);
+	rcu_read_unlock();
+
+	/* Find the mm_struct */
+	mm = get_task_mm(task);
+	put_task_struct(task);
+
+	if (!mm) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	pr_info("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n",
+		 pid, vaddr_start, vaddr_end);
+
+	mmap_read_lock(mm);
+	/*
+	 * always increase addr by PAGE_SIZE, since we could have a PTE page
+	 * table filled with PTE-mapped THPs, each of which is distinct.
+	 */
+	for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
+		struct vm_area_struct *vma = find_vma(mm, addr);
+		unsigned int follflags;
+		struct page *page;
+
+		if (!vma || addr < vma->vm_start)
+			break;
+
+		/* skip special VMA and hugetlb VMA */
+		if (vma_is_special_huge(vma) || is_vm_hugetlb_page(vma)) {
+			addr = vma->vm_end;
+			continue;
+		}
+
+		/* FOLL_DUMP to ignore special (like zero) pages */
+		follflags = FOLL_GET | FOLL_DUMP;
+		page = follow_page(vma, addr, follflags);
+
+		if (IS_ERR(page))
+			continue;
+		if (!page)
+			continue;
+
+		if (!is_transparent_hugepage(page))
+			goto next;
+
+		total++;
+		if (!can_split_huge_page(compound_head(page), NULL))
+			goto next;
+
+		if (!trylock_page(page))
+			goto next;
+
+		if (!split_huge_page(page))
+			split++;
+
+		unlock_page(page);
+next:
+		put_page(page);
+	}
+	mmap_read_unlock(mm);
+	mmput(mm);
+
+	pr_info("%lu of %lu THP split\n", split, total);
+
+out:
+	return ret;
 }
-DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
-		"%llu\n");
+
+static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
+				size_t count, loff_t *ppops)
+{
+	static DEFINE_MUTEX(split_debug_mutex);
+	ssize_t ret;
+	char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */
+	int pid;
+	unsigned long vaddr_start, vaddr_end;
+
+	ret = mutex_lock_interruptible(&split_debug_mutex);
+	if (ret)
+		return ret;
+
+	ret = -EFAULT;
+
+	memset(input_buf, 0, 80);
+	if (copy_from_user(input_buf, buf, min_t(size_t, count, 80)))
+		goto out;
+
+	input_buf[79] = '\0';
+	ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
+	if (ret == 1 && pid == 1) {
+		split_huge_pages_all();
+		ret = strlen(input_buf);
+		goto out;
+	} else if (ret != 3) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end);
+	if (!ret)
+		ret = strlen(input_buf);
+out:
+	mutex_unlock(&split_debug_mutex);
+	return ret;
+
+}
+
+static const struct file_operations split_huge_pages_fops = {
+	.owner	 = THIS_MODULE,
+	.write	 = split_huge_pages_write,
+	.llseek  = no_llseek,
+};
 
 static int __init split_huge_pages_debugfs(void)
 {
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 9a35c3f6a557..1f651e85ed60 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -22,3 +22,4 @@ map_fixed_noreplace
 write_to_hugetlbfs
 hmm-tests
 local_config.*
+split_huge_page_test
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d42115e4284d..4cbc91d6869f 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -42,6 +42,7 @@ TEST_GEN_FILES += on-fault-limit
 TEST_GEN_FILES += thuge-gen
 TEST_GEN_FILES += transhuge-stress
 TEST_GEN_FILES += userfaultfd
+TEST_GEN_FILES += split_huge_page_test
 
 ifeq ($(MACHINE),x86_64)
 CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c
new file mode 100644
index 000000000000..2c0c18e60c57
--- /dev/null
+++ b/tools/testing/selftests/vm/split_huge_page_test.c
@@ -0,0 +1,318 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual
+ * address range in a process via <debugfs>/split_huge_pages interface.
+ */
+
+#define _GNU_SOURCE
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <inttypes.h>
+#include <string.h>
+#include <fcntl.h>
+#include <sys/mman.h>
+#include <malloc.h>
+#include <stdbool.h>
+
+uint64_t pagesize;
+unsigned int pageshift;
+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"
+#define SMAP_PATH "/proc/self/smaps"
+#define INPUT_MAX 80
+
+#define PFN_MASK     ((1UL<<55)-1)
+#define KPF_THP      (1UL<<22)
+
+int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file)
+{
+	uint64_t paddr;
+	uint64_t page_flags;
+
+	if (pagemap_file) {
+		pread(pagemap_file, &paddr, sizeof(paddr),
+			((long)vaddr >> pageshift) * sizeof(paddr));
+
+		if (kpageflags_file) {
+			pread(kpageflags_file, &page_flags, sizeof(page_flags),
+				(paddr & PFN_MASK) * sizeof(page_flags));
+
+			return !!(page_flags & KPF_THP);
+		}
+	}
+	return 0;
+}
+
+
+static uint64_t read_pmd_pagesize(void)
+{
+	int fd;
+	char buf[20];
+	ssize_t num_read;
+
+	fd = open(PMD_SIZE_PATH, O_RDONLY);
+	if (fd == -1) {
+		perror("Open hpage_pmd_size failed");
+		exit(EXIT_FAILURE);
+	}
+	num_read = read(fd, buf, 19);
+	if (num_read < 1) {
+		close(fd);
+		perror("Read hpage_pmd_size failed");
+		exit(EXIT_FAILURE);
+	}
+	buf[num_read] = '\0';
+	close(fd);
+
+	return strtoul(buf, NULL, 10);
+}
+
+static int write_file(const char *path, const char *buf, size_t buflen)
+{
+	int fd;
+	ssize_t numwritten;
+
+	fd = open(path, O_WRONLY);
+	if (fd == -1)
+		return 0;
+
+	numwritten = write(fd, buf, buflen - 1);
+	close(fd);
+	if (numwritten < 1)
+		return 0;
+
+	return (unsigned int) numwritten;
+}
+
+static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end)
+{
+	char input[INPUT_MAX];
+	int ret;
+
+	ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start,
+			vaddr_end);
+	if (ret >= INPUT_MAX) {
+		printf("%s: Debugfs input is too long\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+
+	if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) {
+		perror(SPLIT_DEBUGFS);
+		exit(EXIT_FAILURE);
+	}
+}
+
+#define MAX_LINE_LENGTH 500
+
+static bool check_for_pattern(FILE *fp, const char *pattern, char *buf)
+{
+	while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) {
+		if (!strncmp(buf, pattern, strlen(pattern)))
+			return true;
+	}
+	return false;
+}
+
+static uint64_t check_huge(void *addr)
+{
+	uint64_t thp = 0;
+	int ret;
+	FILE *fp;
+	char buffer[MAX_LINE_LENGTH];
+	char addr_pattern[MAX_LINE_LENGTH];
+
+	ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-",
+		       (unsigned long) addr);
+	if (ret >= MAX_LINE_LENGTH) {
+		printf("%s: Pattern is too long\n", __func__);
+		exit(EXIT_FAILURE);
+	}
+
+
+	fp = fopen(SMAP_PATH, "r");
+	if (!fp) {
+		printf("%s: Failed to open file %s\n", __func__, SMAP_PATH);
+		exit(EXIT_FAILURE);
+	}
+	if (!check_for_pattern(fp, addr_pattern, buffer))
+		goto err_out;
+
+	/*
+	 * Fetch the AnonHugePages: in the same block and check the number of
+	 * hugepages.
+	 */
+	if (!check_for_pattern(fp, "AnonHugePages:", buffer))
+		goto err_out;
+
+	if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) {
+		printf("Reading smap error\n");
+		exit(EXIT_FAILURE);
+	}
+
+err_out:
+	fclose(fp);
+	return thp;
+}
+
+void split_pmd_thp(void)
+{
+	char *one_page;
+	size_t len = 4 * pmd_pagesize;
+	uint64_t thp_size;
+	size_t i;
+
+	one_page = memalign(pmd_pagesize, len);
+
+	if (!one_page) {
+		printf("Fail to allocate memory\n");
+		exit(EXIT_FAILURE);
+	}
+
+	madvise(one_page, len, MADV_HUGEPAGE);
+
+	for (i = 0; i < len; i++)
+		one_page[i] = (char)i;
+
+	thp_size = check_huge(one_page);
+	if (!thp_size) {
+		printf("No THP is allocated\n");
+		exit(EXIT_FAILURE);
+	}
+
+	/* split all THPs */
+	write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len);
+
+	for (i = 0; i < len; i++)
+		if (one_page[i] != (char)i) {
+			printf("%ld byte corrupted\n", i);
+			exit(EXIT_FAILURE);
+		}
+
+
+	thp_size = check_huge(one_page);
+	if (thp_size) {
+		printf("Still %ld kB AnonHugePages not split\n", thp_size);
+		exit(EXIT_FAILURE);
+	}
+
+	printf("Split huge pages successful\n");
+	free(one_page);
+}
+
+void split_pte_mapped_thp(void)
+{
+	char *one_page, *pte_mapped, *pte_mapped2;
+	size_t len = 4 * pmd_pagesize;
+	uint64_t thp_size;
+	size_t i;
+	const char *pagemap_template = "/proc/%d/pagemap";
+	const char *kpageflags_proc = "/proc/kpageflags";
+	char pagemap_proc[255];
+	int pagemap_fd;
+	int kpageflags_fd;
+
+	if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) {
+		perror("get pagemap proc error");
+		exit(EXIT_FAILURE);
+	}
+	pagemap_fd = open(pagemap_proc, O_RDONLY);
+
+	if (pagemap_fd == -1) {
+		perror("read pagemap:");
+		exit(EXIT_FAILURE);
+	}
+
+	kpageflags_fd = open(kpageflags_proc, O_RDONLY);
+
+	if (kpageflags_fd == -1) {
+		perror("read kpageflags:");
+		exit(EXIT_FAILURE);
+	}
+
+	one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+
+	madvise(one_page, len, MADV_HUGEPAGE);
+
+	for (i = 0; i < len; i++)
+		one_page[i] = (char)i;
+
+	thp_size = check_huge(one_page);
+	if (!thp_size) {
+		printf("No THP is allocated\n");
+		exit(EXIT_FAILURE);
+	}
+
+	/* remap the first pagesize of first THP */
+	pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE);
+
+	/* remap the Nth pagesize of Nth THP */
+	for (i = 1; i < 4; i++) {
+		pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i,
+				     pagesize, pagesize,
+				     MREMAP_MAYMOVE|MREMAP_FIXED,
+				     pte_mapped + pagesize * i);
+		if (pte_mapped2 == (char *)-1) {
+			perror("mremap failed");
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	/* smap does not show THPs after mremap, use kpageflags instead */
+	thp_size = 0;
+	for (i = 0; i < pagesize * 4; i++)
+		if (i % pagesize == 0 &&
+		    is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
+			thp_size++;
+
+	if (thp_size != 4) {
+		printf("Some THPs are missing during mremap\n");
+		exit(EXIT_FAILURE);
+	}
+
+	/* split all remapped THPs */
+	write_debugfs(getpid(), (uint64_t)pte_mapped,
+		      (uint64_t)pte_mapped + pagesize * 4);
+
+	/* smap does not show THPs after mremap, use kpageflags instead */
+	thp_size = 0;
+	for (i = 0; i < pagesize * 4; i++) {
+		if (pte_mapped[i] != (char)i) {
+			printf("%ld byte corrupted\n", i);
+			exit(EXIT_FAILURE);
+		}
+		if (i % pagesize == 0 &&
+		    is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
+			thp_size++;
+	}
+
+	if (thp_size) {
+		printf("Still %ld THPs not split\n", thp_size);
+		exit(EXIT_FAILURE);
+	}
+
+	printf("Split PTE-mapped huge pages successful\n");
+	munmap(one_page, len);
+	close(pagemap_fd);
+	close(kpageflags_fd);
+}
+
+int main(int argc, char **argv)
+{
+	if (geteuid() != 0) {
+		printf("Please run the benchmark as root\n");
+		exit(EXIT_FAILURE);
+	}
+
+	pagesize = getpagesize();
+	pageshift = ffs(pagesize) - 1;
+	pmd_pagesize = read_pmd_pagesize();
+
+	split_pmd_thp();
+	split_pte_mapped_thp();
+
+	return 0;
+}
-- 
2.30.2

[PATCH v5 2/2] mm: huge_memory: debugfs for file-backed THP split.

[Zi Yan]

From: Zi Yan <ziy@nvidia.com>

Further extend <debugfs>/split_huge_pages to accept
"<path>,<off_start>,<off_end>" for file-backed THP split tests since
tmpfs may have file backed by THP that mapped nowhere.

Update selftest program to test file-backed THP split too.

Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 mm/huge_memory.c                              | 97 ++++++++++++++++++-
 .../selftests/vm/split_huge_page_test.c       | 79 ++++++++++++++-
 2 files changed, 168 insertions(+), 8 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9bf9bc489228..6d6537cc8c56 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3049,12 +3049,74 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
 	return ret;
 }
 
+static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
+				pgoff_t off_end)
+{
+	struct filename *file;
+	struct file *candidate;
+	struct address_space *mapping;
+	int ret = -EINVAL;
+	pgoff_t off_cur;
+	unsigned long total = 0, split = 0;
+
+	file = getname_kernel(file_path);
+	if (IS_ERR(file))
+		return ret;
+
+	candidate = file_open_name(file, O_RDONLY, 0);
+	if (IS_ERR(candidate))
+		goto out;
+
+	pr_info("split file-backed THPs in file: %s, offset: [0x%lx - 0x%lx]\n",
+		 file_path, off_start, off_end);
+
+	mapping = candidate->f_mapping;
+
+	for (off_cur = off_start; off_cur < off_end;) {
+		struct page *fpage = pagecache_get_page(mapping, off_cur,
+						FGP_ENTRY | FGP_HEAD, 0);
+
+		if (xa_is_value(fpage) || !fpage) {
+			off_cur += PAGE_SIZE;
+			continue;
+		}
+
+		if (!is_transparent_hugepage(fpage)) {
+			off_cur += PAGE_SIZE;
+			goto next;
+		}
+		total++;
+		off_cur = fpage->index + thp_size(fpage);
+
+		if (!trylock_page(fpage))
+			goto next;
+
+		if (!split_huge_page(fpage))
+			split++;
+
+		unlock_page(fpage);
+next:
+		put_page(fpage);
+	}
+
+	filp_close(candidate, NULL);
+	ret = 0;
+
+	pr_info("%lu of %lu file-backed THP split\n", split, total);
+out:
+	putname(file);
+	return ret;
+}
+
+#define MAX_INPUT_BUF_SZ 255
+
 static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppops)
 {
 	static DEFINE_MUTEX(split_debug_mutex);
 	ssize_t ret;
-	char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */
+	/* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */
+	char input_buf[MAX_INPUT_BUF_SZ];
 	int pid;
 	unsigned long vaddr_start, vaddr_end;
 
@@ -3064,11 +3126,40 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
 
 	ret = -EFAULT;
 
-	memset(input_buf, 0, 80);
+	memset(input_buf, 0, MAX_INPUT_BUF_SZ);
 	if (copy_from_user(input_buf, buf, min_t(size_t, count, 80)))
 		goto out;
 
-	input_buf[79] = '\0';
+	input_buf[MAX_INPUT_BUF_SZ - 1] = '\0';
+
+	if (input_buf[0] == '/') {
+		char *tok;
+		char *buf = input_buf;
+		char file_path[MAX_INPUT_BUF_SZ];
+		pgoff_t off_start = 0, off_end = 0;
+		size_t input_len = strlen(input_buf);
+
+		tok = strsep(&buf, ",");
+		if (tok) {
+			strncpy(file_path, tok, MAX_INPUT_BUF_SZ);
+		} else {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end);
+		if (ret != 2) {
+			pr_info("ret: %ld\n", ret);
+			ret = -EINVAL;
+			goto out;
+		}
+		ret = split_huge_pages_in_file(file_path, off_start, off_end);
+		if (!ret)
+			ret = input_len;
+
+		goto out;
+	}
+
 	ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
 	if (ret == 1 && pid == 1) {
 		split_huge_pages_all();
diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c
index 2c0c18e60c57..ebdf2d738978 100644
--- a/tools/testing/selftests/vm/split_huge_page_test.c
+++ b/tools/testing/selftests/vm/split_huge_page_test.c
@@ -7,11 +7,13 @@
 #define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
+#include <stdarg.h>
 #include <unistd.h>
 #include <inttypes.h>
 #include <string.h>
 #include <fcntl.h>
 #include <sys/mman.h>
+#include <sys/mount.h>
 #include <malloc.h>
 #include <stdbool.h>
 
@@ -24,6 +26,9 @@ uint64_t pmd_pagesize;
 #define SMAP_PATH "/proc/self/smaps"
 #define INPUT_MAX 80
 
+#define PID_FMT "%d,0x%lx,0x%lx"
+#define PATH_FMT "%s,0x%lx,0x%lx"
+
 #define PFN_MASK     ((1UL<<55)-1)
 #define KPF_THP      (1UL<<22)
 
@@ -87,13 +92,16 @@ 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(const char *fmt, ...)
 {
 	char input[INPUT_MAX];
 	int ret;
+	va_list argp;
+
+	va_start(argp, fmt);
+	ret = vsnprintf(input, INPUT_MAX, fmt, argp);
+	va_end(argp);
 
-	ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start,
-			vaddr_end);
 	if (ret >= INPUT_MAX) {
 		printf("%s: Debugfs input is too long\n", __func__);
 		exit(EXIT_FAILURE);
@@ -183,7 +191,8 @@ void split_pmd_thp(void)
 	}
 
 	/* split all THPs */
-	write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len);
+	write_debugfs(PID_FMT, getpid(), (uint64_t)one_page,
+		(uint64_t)one_page + len);
 
 	for (i = 0; i < len; i++)
 		if (one_page[i] != (char)i) {
@@ -274,7 +283,7 @@ void split_pte_mapped_thp(void)
 	}
 
 	/* split all remapped THPs */
-	write_debugfs(getpid(), (uint64_t)pte_mapped,
+	write_debugfs(PID_FMT, getpid(), (uint64_t)pte_mapped,
 		      (uint64_t)pte_mapped + pagesize * 4);
 
 	/* smap does not show THPs after mremap, use kpageflags instead */
@@ -300,6 +309,65 @@ void split_pte_mapped_thp(void)
 	close(kpageflags_fd);
 }
 
+void split_file_backed_thp(void)
+{
+	int status;
+	int fd;
+	ssize_t num_written;
+	char tmpfs_template[] = "/tmp/thp_split_XXXXXX";
+	const char *tmpfs_loc = mkdtemp(tmpfs_template);
+	char testfile[INPUT_MAX];
+
+	status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m");
+
+	if (status) {
+		printf("Unable to create a tmpfs for testing\n");
+		exit(EXIT_FAILURE);
+	}
+
+	status = snprintf(testfile, INPUT_MAX, "%s/thp_file", tmpfs_loc);
+	if (status >= INPUT_MAX) {
+		printf("Fail to create file-backed THP split testing file\n");
+		goto cleanup;
+	}
+
+	fd = open(testfile, O_CREAT|O_WRONLY);
+	if (fd == -1) {
+		perror("Cannot open testing file\n");
+		goto cleanup;
+	}
+
+	/* write something to the file, so a file-backed THP can be allocated */
+	num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc));
+	close(fd);
+
+	if (num_written < 1) {
+		printf("Fail to write data to testing file\n");
+		goto cleanup;
+	}
+
+	/* split the file-backed THP */
+	write_debugfs(PATH_FMT, testfile, 0, 1024);
+
+	status = unlink(testfile);
+	if (status)
+		perror("Cannot remove testing file\n");
+
+cleanup:
+	status = umount(tmpfs_loc);
+	if (status) {
+		printf("Unable to umount %s\n", tmpfs_loc);
+		exit(EXIT_FAILURE);
+	}
+	status = rmdir(tmpfs_loc);
+	if (status) {
+		perror("cannot remove tmp dir");
+		exit(EXIT_FAILURE);
+	}
+
+	printf("file-backed THP split test done, please check dmesg for more information\n");
+}
+
 int main(int argc, char **argv)
 {
 	if (geteuid() != 0) {
@@ -313,6 +381,7 @@ int main(int argc, char **argv)
 
 	split_pmd_thp();
 	split_pte_mapped_thp();
+	split_file_backed_thp();
 
 	return 0;
 }
-- 
2.30.2

Re: [PATCH v5 2/2] mm: huge_memory: debugfs for file-backed THP split.

[Yang Shi]

On Thu, Mar 18, 2021 at 5:52 PM Zi Yan <zi.yan@sent.com> wrote:
>
> From: Zi Yan <ziy@nvidia.com>
>
> Further extend <debugfs>/split_huge_pages to accept
> "<path>,<off_start>,<off_end>" for file-backed THP split tests since
> tmpfs may have file backed by THP that mapped nowhere.
>
> Update selftest program to test file-backed THP split too.
>
> Suggested-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Signed-off-by: Zi Yan <ziy@nvidia.com>
> ---
>  mm/huge_memory.c                              | 97 ++++++++++++++++++-
>  .../selftests/vm/split_huge_page_test.c       | 79 ++++++++++++++-
>  2 files changed, 168 insertions(+), 8 deletions(-)
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 9bf9bc489228..6d6537cc8c56 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -3049,12 +3049,74 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
>         return ret;
>  }
>
> +static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
> +                               pgoff_t off_end)
> +{
> +       struct filename *file;
> +       struct file *candidate;
> +       struct address_space *mapping;
> +       int ret = -EINVAL;
> +       pgoff_t off_cur;
> +       unsigned long total = 0, split = 0;
> +
> +       file = getname_kernel(file_path);
> +       if (IS_ERR(file))
> +               return ret;
> +
> +       candidate = file_open_name(file, O_RDONLY, 0);
> +       if (IS_ERR(candidate))
> +               goto out;
> +
> +       pr_info("split file-backed THPs in file: %s, offset: [0x%lx - 0x%lx]\n",
> +                file_path, off_start, off_end);
> +
> +       mapping = candidate->f_mapping;
> +
> +       for (off_cur = off_start; off_cur < off_end;) {
> +               struct page *fpage = pagecache_get_page(mapping, off_cur,
> +                                               FGP_ENTRY | FGP_HEAD, 0);
> +
> +               if (xa_is_value(fpage) || !fpage) {
> +                       off_cur += PAGE_SIZE;
> +                       continue;
> +               }
> +
> +               if (!is_transparent_hugepage(fpage)) {
> +                       off_cur += PAGE_SIZE;
> +                       goto next;
> +               }
> +               total++;
> +               off_cur = fpage->index + thp_size(fpage);
> +
> +               if (!trylock_page(fpage))
> +                       goto next;
> +
> +               if (!split_huge_page(fpage))
> +                       split++;
> +
> +               unlock_page(fpage);
> +next:
> +               put_page(fpage);
> +       }
> +
> +       filp_close(candidate, NULL);
> +       ret = 0;
> +
> +       pr_info("%lu of %lu file-backed THP split\n", split, total);
> +out:
> +       putname(file);
> +       return ret;
> +}
> +
> +#define MAX_INPUT_BUF_SZ 255

As I mentioned in the first patch, you may move this to the first
patch. I don't think it is necessary to add some code then remove it
right in the following patch.

Otherwise the patch looks good to me. Reviewed-by: Yang Shi
<shy828301@gmail.com>

> +
>  static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
>                                 size_t count, loff_t *ppops)
>  {
>         static DEFINE_MUTEX(split_debug_mutex);
>         ssize_t ret;
> -       char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */
> +       /* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */
> +       char input_buf[MAX_INPUT_BUF_SZ];
>         int pid;
>         unsigned long vaddr_start, vaddr_end;
>
> @@ -3064,11 +3126,40 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
>
>         ret = -EFAULT;
>
> -       memset(input_buf, 0, 80);
> +       memset(input_buf, 0, MAX_INPUT_BUF_SZ);
>         if (copy_from_user(input_buf, buf, min_t(size_t, count, 80)))
>                 goto out;
>
> -       input_buf[79] = '\0';
> +       input_buf[MAX_INPUT_BUF_SZ - 1] = '\0';
> +
> +       if (input_buf[0] == '/') {
> +               char *tok;
> +               char *buf = input_buf;
> +               char file_path[MAX_INPUT_BUF_SZ];
> +               pgoff_t off_start = 0, off_end = 0;
> +               size_t input_len = strlen(input_buf);
> +
> +               tok = strsep(&buf, ",");
> +               if (tok) {
> +                       strncpy(file_path, tok, MAX_INPUT_BUF_SZ);
> +               } else {
> +                       ret = -EINVAL;
> +                       goto out;
> +               }
> +
> +               ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end);
> +               if (ret != 2) {
> +                       pr_info("ret: %ld\n", ret);
> +                       ret = -EINVAL;
> +                       goto out;
> +               }
> +               ret = split_huge_pages_in_file(file_path, off_start, off_end);
> +               if (!ret)
> +                       ret = input_len;
> +
> +               goto out;
> +       }
> +
>         ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
>         if (ret == 1 && pid == 1) {
>                 split_huge_pages_all();
> diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c
> index 2c0c18e60c57..ebdf2d738978 100644
> --- a/tools/testing/selftests/vm/split_huge_page_test.c
> +++ b/tools/testing/selftests/vm/split_huge_page_test.c
> @@ -7,11 +7,13 @@
>  #define _GNU_SOURCE
>  #include <stdio.h>
>  #include <stdlib.h>
> +#include <stdarg.h>
>  #include <unistd.h>
>  #include <inttypes.h>
>  #include <string.h>
>  #include <fcntl.h>
>  #include <sys/mman.h>
> +#include <sys/mount.h>
>  #include <malloc.h>
>  #include <stdbool.h>
>
> @@ -24,6 +26,9 @@ uint64_t pmd_pagesize;
>  #define SMAP_PATH "/proc/self/smaps"
>  #define INPUT_MAX 80
>
> +#define PID_FMT "%d,0x%lx,0x%lx"
> +#define PATH_FMT "%s,0x%lx,0x%lx"
> +
>  #define PFN_MASK     ((1UL<<55)-1)
>  #define KPF_THP      (1UL<<22)
>
> @@ -87,13 +92,16 @@ 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(const char *fmt, ...)
>  {
>         char input[INPUT_MAX];
>         int ret;
> +       va_list argp;
> +
> +       va_start(argp, fmt);
> +       ret = vsnprintf(input, INPUT_MAX, fmt, argp);
> +       va_end(argp);
>
> -       ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start,
> -                       vaddr_end);
>         if (ret >= INPUT_MAX) {
>                 printf("%s: Debugfs input is too long\n", __func__);
>                 exit(EXIT_FAILURE);
> @@ -183,7 +191,8 @@ void split_pmd_thp(void)
>         }
>
>         /* split all THPs */
> -       write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len);
> +       write_debugfs(PID_FMT, getpid(), (uint64_t)one_page,
> +               (uint64_t)one_page + len);
>
>         for (i = 0; i < len; i++)
>                 if (one_page[i] != (char)i) {
> @@ -274,7 +283,7 @@ void split_pte_mapped_thp(void)
>         }
>
>         /* split all remapped THPs */
> -       write_debugfs(getpid(), (uint64_t)pte_mapped,
> +       write_debugfs(PID_FMT, getpid(), (uint64_t)pte_mapped,
>                       (uint64_t)pte_mapped + pagesize * 4);
>
>         /* smap does not show THPs after mremap, use kpageflags instead */
> @@ -300,6 +309,65 @@ void split_pte_mapped_thp(void)
>         close(kpageflags_fd);
>  }
>
> +void split_file_backed_thp(void)
> +{
> +       int status;
> +       int fd;
> +       ssize_t num_written;
> +       char tmpfs_template[] = "/tmp/thp_split_XXXXXX";
> +       const char *tmpfs_loc = mkdtemp(tmpfs_template);
> +       char testfile[INPUT_MAX];
> +
> +       status = mount("tmpfs", tmpfs_loc, "tmpfs", 0, "huge=always,size=4m");
> +
> +       if (status) {
> +               printf("Unable to create a tmpfs for testing\n");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       status = snprintf(testfile, INPUT_MAX, "%s/thp_file", tmpfs_loc);
> +       if (status >= INPUT_MAX) {
> +               printf("Fail to create file-backed THP split testing file\n");
> +               goto cleanup;
> +       }
> +
> +       fd = open(testfile, O_CREAT|O_WRONLY);
> +       if (fd == -1) {
> +               perror("Cannot open testing file\n");
> +               goto cleanup;
> +       }
> +
> +       /* write something to the file, so a file-backed THP can be allocated */
> +       num_written = write(fd, tmpfs_loc, sizeof(tmpfs_loc));
> +       close(fd);
> +
> +       if (num_written < 1) {
> +               printf("Fail to write data to testing file\n");
> +               goto cleanup;
> +       }
> +
> +       /* split the file-backed THP */
> +       write_debugfs(PATH_FMT, testfile, 0, 1024);
> +
> +       status = unlink(testfile);
> +       if (status)
> +               perror("Cannot remove testing file\n");
> +
> +cleanup:
> +       status = umount(tmpfs_loc);
> +       if (status) {
> +               printf("Unable to umount %s\n", tmpfs_loc);
> +               exit(EXIT_FAILURE);
> +       }
> +       status = rmdir(tmpfs_loc);
> +       if (status) {
> +               perror("cannot remove tmp dir");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       printf("file-backed THP split test done, please check dmesg for more information\n");
> +}
> +
>  int main(int argc, char **argv)
>  {
>         if (geteuid() != 0) {
> @@ -313,6 +381,7 @@ int main(int argc, char **argv)
>
>         split_pmd_thp();
>         split_pte_mapped_thp();
> +       split_file_backed_thp();
>
>         return 0;
>  }
> --
> 2.30.2
>

Re: [PATCH v5 1/2] mm: huge_memory: a new debugfs interface for splitting THP tests.

[Yang Shi]

On Thu, Mar 18, 2021 at 5:52 PM Zi Yan <zi.yan@sent.com> wrote:
>
> From: Zi Yan <ziy@nvidia.com>
>
> We did not have a direct user interface of splitting the compound page
> backing a THP and there is no need unless we want to expose the THP
> implementation details to users. Make <debugfs>/split_huge_pages accept
> a new command to do that.
>
> By writing "<pid>,<vaddr_start>,<vaddr_end>" to
> <debugfs>/split_huge_pages, THPs within the given virtual address range
> from the process with the given pid are split. It is used to test
> split_huge_page function. In addition, a selftest program is added to
> tools/testing/selftests/vm to utilize the interface by splitting
> PMD THPs and PTE-mapped THPs.
>
> This does not change the old behavior, i.e., writing 1 to the interface
> to split all THPs in the system.
>
> Changelog:
>
> From v5:
> 1. Skipped special VMAs and other fixes. (suggested by Yang Shi)

Looks good to me. Reviewed-by: Yang Shi <shy828301@gmail.com>

Some nits below:

>
> From v4:
> 1. Fixed the error code return issue, spotted by kernel test robot
>    <lkp@intel.com>.
>
> From v3:
> 1. Factored out split huge pages in the given pid code to a separate
>    function.
> 2. Added the missing put_page for not split pages.
> 3. pr_debug -> pr_info, make reading results simpler.
>
> From v2:
> 1. Reused existing <debugfs>/split_huge_pages interface. (suggested by
>    Yang Shi)
>
> From v1:
> 1. Removed unnecessary calling to vma_migratable, spotted by kernel test
>    robot <lkp@intel.com>.
> 2. Dropped the use of find_mm_struct and code it directly, since there
>    is no need for the permission check in that function and the function
>    is only available when migration is on.
> 3. Added some comments in the selftest program to clarify how PTE-mapped
>    THPs are formed.
>
> Signed-off-by: Zi Yan <ziy@nvidia.com>
> ---
>  mm/huge_memory.c                              | 143 +++++++-
>  tools/testing/selftests/vm/.gitignore         |   1 +
>  tools/testing/selftests/vm/Makefile           |   1 +
>  .../selftests/vm/split_huge_page_test.c       | 318 ++++++++++++++++++
>  4 files changed, 456 insertions(+), 7 deletions(-)
>  create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c
>
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index bff92dea5ab3..9bf9bc489228 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -7,6 +7,7 @@
>
>  #include <linux/mm.h>
>  #include <linux/sched.h>
> +#include <linux/sched/mm.h>
>  #include <linux/sched/coredump.h>
>  #include <linux/sched/numa_balancing.h>
>  #include <linux/highmem.h>
> @@ -2922,16 +2923,14 @@ static struct shrinker deferred_split_shrinker = {
>  };
>
>  #ifdef CONFIG_DEBUG_FS
> -static int split_huge_pages_set(void *data, u64 val)
> +static void split_huge_pages_all(void)
>  {
>         struct zone *zone;
>         struct page *page;
>         unsigned long pfn, max_zone_pfn;
>         unsigned long total = 0, split = 0;
>
> -       if (val != 1)
> -               return -EINVAL;
> -
> +       pr_info("Split all THPs\n");
>         for_each_populated_zone(zone) {
>                 max_zone_pfn = zone_end_pfn(zone);
>                 for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
> @@ -2959,11 +2958,141 @@ static int split_huge_pages_set(void *data, u64 val)
>         }
>
>         pr_info("%lu of %lu THP split\n", split, total);
> +}
>
> -       return 0;
> +static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
> +                               unsigned long vaddr_end)
> +{
> +       int ret = 0;
> +       struct task_struct *task;
> +       struct mm_struct *mm;
> +       unsigned long total = 0, split = 0;
> +       unsigned long addr;
> +
> +       vaddr_start &= PAGE_MASK;
> +       vaddr_end &= PAGE_MASK;
> +
> +       /* Find the task_struct from pid */
> +       rcu_read_lock();
> +       task = find_task_by_vpid(pid);
> +       if (!task) {
> +               rcu_read_unlock();
> +               ret = -ESRCH;
> +               goto out;
> +       }
> +       get_task_struct(task);
> +       rcu_read_unlock();
> +
> +       /* Find the mm_struct */
> +       mm = get_task_mm(task);
> +       put_task_struct(task);
> +
> +       if (!mm) {
> +               ret = -EINVAL;
> +               goto out;
> +       }
> +
> +       pr_info("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n",
> +                pid, vaddr_start, vaddr_end);
> +
> +       mmap_read_lock(mm);
> +       /*
> +        * always increase addr by PAGE_SIZE, since we could have a PTE page
> +        * table filled with PTE-mapped THPs, each of which is distinct.
> +        */
> +       for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
> +               struct vm_area_struct *vma = find_vma(mm, addr);
> +               unsigned int follflags;
> +               struct page *page;
> +
> +               if (!vma || addr < vma->vm_start)
> +                       break;
> +
> +               /* skip special VMA and hugetlb VMA */
> +               if (vma_is_special_huge(vma) || is_vm_hugetlb_page(vma)) {

VM_IO vma should be skipped as well. And you may extract this into a helper?

> +                       addr = vma->vm_end;
> +                       continue;
> +               }
> +
> +               /* FOLL_DUMP to ignore special (like zero) pages */
> +               follflags = FOLL_GET | FOLL_DUMP;
> +               page = follow_page(vma, addr, follflags);
> +
> +               if (IS_ERR(page))
> +                       continue;
> +               if (!page)
> +                       continue;
> +
> +               if (!is_transparent_hugepage(page))
> +                       goto next;
> +
> +               total++;
> +               if (!can_split_huge_page(compound_head(page), NULL))
> +                       goto next;
> +
> +               if (!trylock_page(page))
> +                       goto next;
> +
> +               if (!split_huge_page(page))
> +                       split++;
> +
> +               unlock_page(page);
> +next:
> +               put_page(page);
> +       }
> +       mmap_read_unlock(mm);
> +       mmput(mm);
> +
> +       pr_info("%lu of %lu THP split\n", split, total);
> +
> +out:
> +       return ret;
>  }
> -DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
> -               "%llu\n");
> +
> +static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
> +                               size_t count, loff_t *ppops)
> +{
> +       static DEFINE_MUTEX(split_debug_mutex);
> +       ssize_t ret;
> +       char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */

Why not move buf len macro in the following patch to this patch? Then
you don't have to change the length again.

> +       int pid;
> +       unsigned long vaddr_start, vaddr_end;
> +
> +       ret = mutex_lock_interruptible(&split_debug_mutex);
> +       if (ret)
> +               return ret;
> +
> +       ret = -EFAULT;
> +
> +       memset(input_buf, 0, 80);
> +       if (copy_from_user(input_buf, buf, min_t(size_t, count, 80)))
> +               goto out;
> +
> +       input_buf[79] = '\0';
> +       ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
> +       if (ret == 1 && pid == 1) {
> +               split_huge_pages_all();
> +               ret = strlen(input_buf);
> +               goto out;
> +       } else if (ret != 3) {
> +               ret = -EINVAL;
> +               goto out;
> +       }
> +
> +       ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end);
> +       if (!ret)
> +               ret = strlen(input_buf);
> +out:
> +       mutex_unlock(&split_debug_mutex);
> +       return ret;
> +
> +}
> +
> +static const struct file_operations split_huge_pages_fops = {
> +       .owner   = THIS_MODULE,
> +       .write   = split_huge_pages_write,
> +       .llseek  = no_llseek,
> +};
>
>  static int __init split_huge_pages_debugfs(void)
>  {
> diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
> index 9a35c3f6a557..1f651e85ed60 100644
> --- a/tools/testing/selftests/vm/.gitignore
> +++ b/tools/testing/selftests/vm/.gitignore
> @@ -22,3 +22,4 @@ map_fixed_noreplace
>  write_to_hugetlbfs
>  hmm-tests
>  local_config.*
> +split_huge_page_test
> diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
> index d42115e4284d..4cbc91d6869f 100644
> --- a/tools/testing/selftests/vm/Makefile
> +++ b/tools/testing/selftests/vm/Makefile
> @@ -42,6 +42,7 @@ TEST_GEN_FILES += on-fault-limit
>  TEST_GEN_FILES += thuge-gen
>  TEST_GEN_FILES += transhuge-stress
>  TEST_GEN_FILES += userfaultfd
> +TEST_GEN_FILES += split_huge_page_test
>
>  ifeq ($(MACHINE),x86_64)
>  CAN_BUILD_I386 := $(shell ./../x86/check_cc.sh $(CC) ../x86/trivial_32bit_program.c -m32)
> diff --git a/tools/testing/selftests/vm/split_huge_page_test.c b/tools/testing/selftests/vm/split_huge_page_test.c
> new file mode 100644
> index 000000000000..2c0c18e60c57
> --- /dev/null
> +++ b/tools/testing/selftests/vm/split_huge_page_test.c
> @@ -0,0 +1,318 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * A test of splitting PMD THPs and PTE-mapped THPs from a specified virtual
> + * address range in a process via <debugfs>/split_huge_pages interface.
> + */
> +
> +#define _GNU_SOURCE
> +#include <stdio.h>
> +#include <stdlib.h>
> +#include <unistd.h>
> +#include <inttypes.h>
> +#include <string.h>
> +#include <fcntl.h>
> +#include <sys/mman.h>
> +#include <malloc.h>
> +#include <stdbool.h>
> +
> +uint64_t pagesize;
> +unsigned int pageshift;
> +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"
> +#define SMAP_PATH "/proc/self/smaps"
> +#define INPUT_MAX 80
> +
> +#define PFN_MASK     ((1UL<<55)-1)
> +#define KPF_THP      (1UL<<22)
> +
> +int is_backed_by_thp(char *vaddr, int pagemap_file, int kpageflags_file)
> +{
> +       uint64_t paddr;
> +       uint64_t page_flags;
> +
> +       if (pagemap_file) {
> +               pread(pagemap_file, &paddr, sizeof(paddr),
> +                       ((long)vaddr >> pageshift) * sizeof(paddr));
> +
> +               if (kpageflags_file) {
> +                       pread(kpageflags_file, &page_flags, sizeof(page_flags),
> +                               (paddr & PFN_MASK) * sizeof(page_flags));
> +
> +                       return !!(page_flags & KPF_THP);
> +               }
> +       }
> +       return 0;
> +}
> +
> +
> +static uint64_t read_pmd_pagesize(void)
> +{
> +       int fd;
> +       char buf[20];
> +       ssize_t num_read;
> +
> +       fd = open(PMD_SIZE_PATH, O_RDONLY);
> +       if (fd == -1) {
> +               perror("Open hpage_pmd_size failed");
> +               exit(EXIT_FAILURE);
> +       }
> +       num_read = read(fd, buf, 19);
> +       if (num_read < 1) {
> +               close(fd);
> +               perror("Read hpage_pmd_size failed");
> +               exit(EXIT_FAILURE);
> +       }
> +       buf[num_read] = '\0';
> +       close(fd);
> +
> +       return strtoul(buf, NULL, 10);
> +}
> +
> +static int write_file(const char *path, const char *buf, size_t buflen)
> +{
> +       int fd;
> +       ssize_t numwritten;
> +
> +       fd = open(path, O_WRONLY);
> +       if (fd == -1)
> +               return 0;
> +
> +       numwritten = write(fd, buf, buflen - 1);
> +       close(fd);
> +       if (numwritten < 1)
> +               return 0;
> +
> +       return (unsigned int) numwritten;
> +}
> +
> +static void write_debugfs(int pid, uint64_t vaddr_start, uint64_t vaddr_end)
> +{
> +       char input[INPUT_MAX];
> +       int ret;
> +
> +       ret = snprintf(input, INPUT_MAX, "%d,0x%lx,0x%lx", pid, vaddr_start,
> +                       vaddr_end);
> +       if (ret >= INPUT_MAX) {
> +               printf("%s: Debugfs input is too long\n", __func__);
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       if (!write_file(SPLIT_DEBUGFS, input, ret + 1)) {
> +               perror(SPLIT_DEBUGFS);
> +               exit(EXIT_FAILURE);
> +       }
> +}
> +
> +#define MAX_LINE_LENGTH 500
> +
> +static bool check_for_pattern(FILE *fp, const char *pattern, char *buf)
> +{
> +       while (fgets(buf, MAX_LINE_LENGTH, fp) != NULL) {
> +               if (!strncmp(buf, pattern, strlen(pattern)))
> +                       return true;
> +       }
> +       return false;
> +}
> +
> +static uint64_t check_huge(void *addr)
> +{
> +       uint64_t thp = 0;
> +       int ret;
> +       FILE *fp;
> +       char buffer[MAX_LINE_LENGTH];
> +       char addr_pattern[MAX_LINE_LENGTH];
> +
> +       ret = snprintf(addr_pattern, MAX_LINE_LENGTH, "%08lx-",
> +                      (unsigned long) addr);
> +       if (ret >= MAX_LINE_LENGTH) {
> +               printf("%s: Pattern is too long\n", __func__);
> +               exit(EXIT_FAILURE);
> +       }
> +
> +
> +       fp = fopen(SMAP_PATH, "r");
> +       if (!fp) {
> +               printf("%s: Failed to open file %s\n", __func__, SMAP_PATH);
> +               exit(EXIT_FAILURE);
> +       }
> +       if (!check_for_pattern(fp, addr_pattern, buffer))
> +               goto err_out;
> +
> +       /*
> +        * Fetch the AnonHugePages: in the same block and check the number of
> +        * hugepages.
> +        */
> +       if (!check_for_pattern(fp, "AnonHugePages:", buffer))
> +               goto err_out;
> +
> +       if (sscanf(buffer, "AnonHugePages:%10ld kB", &thp) != 1) {
> +               printf("Reading smap error\n");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +err_out:
> +       fclose(fp);
> +       return thp;
> +}
> +
> +void split_pmd_thp(void)
> +{
> +       char *one_page;
> +       size_t len = 4 * pmd_pagesize;
> +       uint64_t thp_size;
> +       size_t i;
> +
> +       one_page = memalign(pmd_pagesize, len);
> +
> +       if (!one_page) {
> +               printf("Fail to allocate memory\n");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       madvise(one_page, len, MADV_HUGEPAGE);
> +
> +       for (i = 0; i < len; i++)
> +               one_page[i] = (char)i;
> +
> +       thp_size = check_huge(one_page);
> +       if (!thp_size) {
> +               printf("No THP is allocated\n");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       /* split all THPs */
> +       write_debugfs(getpid(), (uint64_t)one_page, (uint64_t)one_page + len);
> +
> +       for (i = 0; i < len; i++)
> +               if (one_page[i] != (char)i) {
> +                       printf("%ld byte corrupted\n", i);
> +                       exit(EXIT_FAILURE);
> +               }
> +
> +
> +       thp_size = check_huge(one_page);
> +       if (thp_size) {
> +               printf("Still %ld kB AnonHugePages not split\n", thp_size);
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       printf("Split huge pages successful\n");
> +       free(one_page);
> +}
> +
> +void split_pte_mapped_thp(void)
> +{
> +       char *one_page, *pte_mapped, *pte_mapped2;
> +       size_t len = 4 * pmd_pagesize;
> +       uint64_t thp_size;
> +       size_t i;
> +       const char *pagemap_template = "/proc/%d/pagemap";
> +       const char *kpageflags_proc = "/proc/kpageflags";
> +       char pagemap_proc[255];
> +       int pagemap_fd;
> +       int kpageflags_fd;
> +
> +       if (snprintf(pagemap_proc, 255, pagemap_template, getpid()) < 0) {
> +               perror("get pagemap proc error");
> +               exit(EXIT_FAILURE);
> +       }
> +       pagemap_fd = open(pagemap_proc, O_RDONLY);
> +
> +       if (pagemap_fd == -1) {
> +               perror("read pagemap:");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       kpageflags_fd = open(kpageflags_proc, O_RDONLY);
> +
> +       if (kpageflags_fd == -1) {
> +               perror("read kpageflags:");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       one_page = mmap((void *)(1UL << 30), len, PROT_READ | PROT_WRITE,
> +                       MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
> +
> +       madvise(one_page, len, MADV_HUGEPAGE);
> +
> +       for (i = 0; i < len; i++)
> +               one_page[i] = (char)i;
> +
> +       thp_size = check_huge(one_page);
> +       if (!thp_size) {
> +               printf("No THP is allocated\n");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       /* remap the first pagesize of first THP */
> +       pte_mapped = mremap(one_page, pagesize, pagesize, MREMAP_MAYMOVE);
> +
> +       /* remap the Nth pagesize of Nth THP */
> +       for (i = 1; i < 4; i++) {
> +               pte_mapped2 = mremap(one_page + pmd_pagesize * i + pagesize * i,
> +                                    pagesize, pagesize,
> +                                    MREMAP_MAYMOVE|MREMAP_FIXED,
> +                                    pte_mapped + pagesize * i);
> +               if (pte_mapped2 == (char *)-1) {
> +                       perror("mremap failed");
> +                       exit(EXIT_FAILURE);
> +               }
> +       }
> +
> +       /* smap does not show THPs after mremap, use kpageflags instead */
> +       thp_size = 0;
> +       for (i = 0; i < pagesize * 4; i++)
> +               if (i % pagesize == 0 &&
> +                   is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
> +                       thp_size++;
> +
> +       if (thp_size != 4) {
> +               printf("Some THPs are missing during mremap\n");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       /* split all remapped THPs */
> +       write_debugfs(getpid(), (uint64_t)pte_mapped,
> +                     (uint64_t)pte_mapped + pagesize * 4);
> +
> +       /* smap does not show THPs after mremap, use kpageflags instead */
> +       thp_size = 0;
> +       for (i = 0; i < pagesize * 4; i++) {
> +               if (pte_mapped[i] != (char)i) {
> +                       printf("%ld byte corrupted\n", i);
> +                       exit(EXIT_FAILURE);
> +               }
> +               if (i % pagesize == 0 &&
> +                   is_backed_by_thp(&pte_mapped[i], pagemap_fd, kpageflags_fd))
> +                       thp_size++;
> +       }
> +
> +       if (thp_size) {
> +               printf("Still %ld THPs not split\n", thp_size);
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       printf("Split PTE-mapped huge pages successful\n");
> +       munmap(one_page, len);
> +       close(pagemap_fd);
> +       close(kpageflags_fd);
> +}
> +
> +int main(int argc, char **argv)
> +{
> +       if (geteuid() != 0) {
> +               printf("Please run the benchmark as root\n");
> +               exit(EXIT_FAILURE);
> +       }
> +
> +       pagesize = getpagesize();
> +       pageshift = ffs(pagesize) - 1;
> +       pmd_pagesize = read_pmd_pagesize();
> +
> +       split_pmd_thp();
> +       split_pte_mapped_thp();
> +
> +       return 0;
> +}
> --
> 2.30.2
>

Re: [PATCH v5 1/2] mm: huge_memory: a new debugfs interface for splitting THP tests.

[Zi Yan]

[-- Attachment #1: Type: text/plain, Size: 7126 bytes --]

On 19 Mar 2021, at 19:37, Yang Shi wrote:

> On Thu, Mar 18, 2021 at 5:52 PM Zi Yan <zi.yan@sent.com> wrote:
>>
>> From: Zi Yan <ziy@nvidia.com>
>>
>> We did not have a direct user interface of splitting the compound page
>> backing a THP and there is no need unless we want to expose the THP
>> implementation details to users. Make <debugfs>/split_huge_pages accept
>> a new command to do that.
>>
>> By writing "<pid>,<vaddr_start>,<vaddr_end>" to
>> <debugfs>/split_huge_pages, THPs within the given virtual address range
>> from the process with the given pid are split. It is used to test
>> split_huge_page function. In addition, a selftest program is added to
>> tools/testing/selftests/vm to utilize the interface by splitting
>> PMD THPs and PTE-mapped THPs.
>>
>> This does not change the old behavior, i.e., writing 1 to the interface
>> to split all THPs in the system.
>>
>> Changelog:
>>
>> From v5:
>> 1. Skipped special VMAs and other fixes. (suggested by Yang Shi)
>
> Looks good to me. Reviewed-by: Yang Shi <shy828301@gmail.com>
>
> Some nits below:
>
>>
>> From v4:
>> 1. Fixed the error code return issue, spotted by kernel test robot
>>    <lkp@intel.com>.
>>
>> From v3:
>> 1. Factored out split huge pages in the given pid code to a separate
>>    function.
>> 2. Added the missing put_page for not split pages.
>> 3. pr_debug -> pr_info, make reading results simpler.
>>
>> From v2:
>> 1. Reused existing <debugfs>/split_huge_pages interface. (suggested by
>>    Yang Shi)
>>
>> From v1:
>> 1. Removed unnecessary calling to vma_migratable, spotted by kernel test
>>    robot <lkp@intel.com>.
>> 2. Dropped the use of find_mm_struct and code it directly, since there
>>    is no need for the permission check in that function and the function
>>    is only available when migration is on.
>> 3. Added some comments in the selftest program to clarify how PTE-mapped
>>    THPs are formed.
>>
>> Signed-off-by: Zi Yan <ziy@nvidia.com>
>> ---
>>  mm/huge_memory.c                              | 143 +++++++-
>>  tools/testing/selftests/vm/.gitignore         |   1 +
>>  tools/testing/selftests/vm/Makefile           |   1 +
>>  .../selftests/vm/split_huge_page_test.c       | 318 ++++++++++++++++++
>>  4 files changed, 456 insertions(+), 7 deletions(-)
>>  create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c
>>
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index bff92dea5ab3..9bf9bc489228 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -7,6 +7,7 @@
>>
>>  #include <linux/mm.h>
>>  #include <linux/sched.h>
>> +#include <linux/sched/mm.h>
>>  #include <linux/sched/coredump.h>
>>  #include <linux/sched/numa_balancing.h>
>>  #include <linux/highmem.h>
>> @@ -2922,16 +2923,14 @@ static struct shrinker deferred_split_shrinker = {
>>  };
>>
>>  #ifdef CONFIG_DEBUG_FS
>> -static int split_huge_pages_set(void *data, u64 val)
>> +static void split_huge_pages_all(void)
>>  {
>>         struct zone *zone;
>>         struct page *page;
>>         unsigned long pfn, max_zone_pfn;
>>         unsigned long total = 0, split = 0;
>>
>> -       if (val != 1)
>> -               return -EINVAL;
>> -
>> +       pr_info("Split all THPs\n");
>>         for_each_populated_zone(zone) {
>>                 max_zone_pfn = zone_end_pfn(zone);
>>                 for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
>> @@ -2959,11 +2958,141 @@ static int split_huge_pages_set(void *data, u64 val)
>>         }
>>
>>         pr_info("%lu of %lu THP split\n", split, total);
>> +}
>>
>> -       return 0;
>> +static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
>> +                               unsigned long vaddr_end)
>> +{
>> +       int ret = 0;
>> +       struct task_struct *task;
>> +       struct mm_struct *mm;
>> +       unsigned long total = 0, split = 0;
>> +       unsigned long addr;
>> +
>> +       vaddr_start &= PAGE_MASK;
>> +       vaddr_end &= PAGE_MASK;
>> +
>> +       /* Find the task_struct from pid */
>> +       rcu_read_lock();
>> +       task = find_task_by_vpid(pid);
>> +       if (!task) {
>> +               rcu_read_unlock();
>> +               ret = -ESRCH;
>> +               goto out;
>> +       }
>> +       get_task_struct(task);
>> +       rcu_read_unlock();
>> +
>> +       /* Find the mm_struct */
>> +       mm = get_task_mm(task);
>> +       put_task_struct(task);
>> +
>> +       if (!mm) {
>> +               ret = -EINVAL;
>> +               goto out;
>> +       }
>> +
>> +       pr_info("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n",
>> +                pid, vaddr_start, vaddr_end);
>> +
>> +       mmap_read_lock(mm);
>> +       /*
>> +        * always increase addr by PAGE_SIZE, since we could have a PTE page
>> +        * table filled with PTE-mapped THPs, each of which is distinct.
>> +        */
>> +       for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
>> +               struct vm_area_struct *vma = find_vma(mm, addr);
>> +               unsigned int follflags;
>> +               struct page *page;
>> +
>> +               if (!vma || addr < vma->vm_start)
>> +                       break;
>> +
>> +               /* skip special VMA and hugetlb VMA */
>> +               if (vma_is_special_huge(vma) || is_vm_hugetlb_page(vma)) {
>
> VM_IO vma should be skipped as well. And you may extract this into a helper?

Sure. Any name suggestion? :)


>> +                       addr = vma->vm_end;
>> +                       continue;
>> +               }
>> +
>> +               /* FOLL_DUMP to ignore special (like zero) pages */
>> +               follflags = FOLL_GET | FOLL_DUMP;
>> +               page = follow_page(vma, addr, follflags);
>> +
>> +               if (IS_ERR(page))
>> +                       continue;
>> +               if (!page)
>> +                       continue;
>> +
>> +               if (!is_transparent_hugepage(page))
>> +                       goto next;
>> +
>> +               total++;
>> +               if (!can_split_huge_page(compound_head(page), NULL))
>> +                       goto next;
>> +
>> +               if (!trylock_page(page))
>> +                       goto next;
>> +
>> +               if (!split_huge_page(page))
>> +                       split++;
>> +
>> +               unlock_page(page);
>> +next:
>> +               put_page(page);
>> +       }
>> +       mmap_read_unlock(mm);
>> +       mmput(mm);
>> +
>> +       pr_info("%lu of %lu THP split\n", split, total);
>> +
>> +out:
>> +       return ret;
>>  }
>> -DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
>> -               "%llu\n");
>> +
>> +static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
>> +                               size_t count, loff_t *ppops)
>> +{
>> +       static DEFINE_MUTEX(split_debug_mutex);
>> +       ssize_t ret;
>> +       char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */
>
> Why not move buf len macro in the following patch to this patch? Then
> you don't have to change the length again.

Sure.

Thanks for the comments.

--
Best Regards,
Yan Zi

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 854 bytes --]

Re: [PATCH v5 1/2] mm: huge_memory: a new debugfs interface for splitting THP tests.

[Yang Shi]

On Sun, Mar 21, 2021 at 7:11 PM Zi Yan <ziy@nvidia.com> wrote:
>
> On 19 Mar 2021, at 19:37, Yang Shi wrote:
>
> > On Thu, Mar 18, 2021 at 5:52 PM Zi Yan <zi.yan@sent.com> wrote:
> >>
> >> From: Zi Yan <ziy@nvidia.com>
> >>
> >> We did not have a direct user interface of splitting the compound page
> >> backing a THP and there is no need unless we want to expose the THP
> >> implementation details to users. Make <debugfs>/split_huge_pages accept
> >> a new command to do that.
> >>
> >> By writing "<pid>,<vaddr_start>,<vaddr_end>" to
> >> <debugfs>/split_huge_pages, THPs within the given virtual address range
> >> from the process with the given pid are split. It is used to test
> >> split_huge_page function. In addition, a selftest program is added to
> >> tools/testing/selftests/vm to utilize the interface by splitting
> >> PMD THPs and PTE-mapped THPs.
> >>
> >> This does not change the old behavior, i.e., writing 1 to the interface
> >> to split all THPs in the system.
> >>
> >> Changelog:
> >>
> >> From v5:
> >> 1. Skipped special VMAs and other fixes. (suggested by Yang Shi)
> >
> > Looks good to me. Reviewed-by: Yang Shi <shy828301@gmail.com>
> >
> > Some nits below:
> >
> >>
> >> From v4:
> >> 1. Fixed the error code return issue, spotted by kernel test robot
> >>    <lkp@intel.com>.
> >>
> >> From v3:
> >> 1. Factored out split huge pages in the given pid code to a separate
> >>    function.
> >> 2. Added the missing put_page for not split pages.
> >> 3. pr_debug -> pr_info, make reading results simpler.
> >>
> >> From v2:
> >> 1. Reused existing <debugfs>/split_huge_pages interface. (suggested by
> >>    Yang Shi)
> >>
> >> From v1:
> >> 1. Removed unnecessary calling to vma_migratable, spotted by kernel test
> >>    robot <lkp@intel.com>.
> >> 2. Dropped the use of find_mm_struct and code it directly, since there
> >>    is no need for the permission check in that function and the function
> >>    is only available when migration is on.
> >> 3. Added some comments in the selftest program to clarify how PTE-mapped
> >>    THPs are formed.
> >>
> >> Signed-off-by: Zi Yan <ziy@nvidia.com>
> >> ---
> >>  mm/huge_memory.c                              | 143 +++++++-
> >>  tools/testing/selftests/vm/.gitignore         |   1 +
> >>  tools/testing/selftests/vm/Makefile           |   1 +
> >>  .../selftests/vm/split_huge_page_test.c       | 318 ++++++++++++++++++
> >>  4 files changed, 456 insertions(+), 7 deletions(-)
> >>  create mode 100644 tools/testing/selftests/vm/split_huge_page_test.c
> >>
> >> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> >> index bff92dea5ab3..9bf9bc489228 100644
> >> --- a/mm/huge_memory.c
> >> +++ b/mm/huge_memory.c
> >> @@ -7,6 +7,7 @@
> >>
> >>  #include <linux/mm.h>
> >>  #include <linux/sched.h>
> >> +#include <linux/sched/mm.h>
> >>  #include <linux/sched/coredump.h>
> >>  #include <linux/sched/numa_balancing.h>
> >>  #include <linux/highmem.h>
> >> @@ -2922,16 +2923,14 @@ static struct shrinker deferred_split_shrinker = {
> >>  };
> >>
> >>  #ifdef CONFIG_DEBUG_FS
> >> -static int split_huge_pages_set(void *data, u64 val)
> >> +static void split_huge_pages_all(void)
> >>  {
> >>         struct zone *zone;
> >>         struct page *page;
> >>         unsigned long pfn, max_zone_pfn;
> >>         unsigned long total = 0, split = 0;
> >>
> >> -       if (val != 1)
> >> -               return -EINVAL;
> >> -
> >> +       pr_info("Split all THPs\n");
> >>         for_each_populated_zone(zone) {
> >>                 max_zone_pfn = zone_end_pfn(zone);
> >>                 for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) {
> >> @@ -2959,11 +2958,141 @@ static int split_huge_pages_set(void *data, u64 val)
> >>         }
> >>
> >>         pr_info("%lu of %lu THP split\n", split, total);
> >> +}
> >>
> >> -       return 0;
> >> +static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
> >> +                               unsigned long vaddr_end)
> >> +{
> >> +       int ret = 0;
> >> +       struct task_struct *task;
> >> +       struct mm_struct *mm;
> >> +       unsigned long total = 0, split = 0;
> >> +       unsigned long addr;
> >> +
> >> +       vaddr_start &= PAGE_MASK;
> >> +       vaddr_end &= PAGE_MASK;
> >> +
> >> +       /* Find the task_struct from pid */
> >> +       rcu_read_lock();
> >> +       task = find_task_by_vpid(pid);
> >> +       if (!task) {
> >> +               rcu_read_unlock();
> >> +               ret = -ESRCH;
> >> +               goto out;
> >> +       }
> >> +       get_task_struct(task);
> >> +       rcu_read_unlock();
> >> +
> >> +       /* Find the mm_struct */
> >> +       mm = get_task_mm(task);
> >> +       put_task_struct(task);
> >> +
> >> +       if (!mm) {
> >> +               ret = -EINVAL;
> >> +               goto out;
> >> +       }
> >> +
> >> +       pr_info("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n",
> >> +                pid, vaddr_start, vaddr_end);
> >> +
> >> +       mmap_read_lock(mm);
> >> +       /*
> >> +        * always increase addr by PAGE_SIZE, since we could have a PTE page
> >> +        * table filled with PTE-mapped THPs, each of which is distinct.
> >> +        */
> >> +       for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
> >> +               struct vm_area_struct *vma = find_vma(mm, addr);
> >> +               unsigned int follflags;
> >> +               struct page *page;
> >> +
> >> +               if (!vma || addr < vma->vm_start)
> >> +                       break;
> >> +
> >> +               /* skip special VMA and hugetlb VMA */
> >> +               if (vma_is_special_huge(vma) || is_vm_hugetlb_page(vma)) {
> >
> > VM_IO vma should be skipped as well. And you may extract this into a helper?
>
> Sure. Any name suggestion? :)

How's about not_suitable_for_split() or suitable_for_split()?

>
>
> >> +                       addr = vma->vm_end;
> >> +                       continue;
> >> +               }
> >> +
> >> +               /* FOLL_DUMP to ignore special (like zero) pages */
> >> +               follflags = FOLL_GET | FOLL_DUMP;
> >> +               page = follow_page(vma, addr, follflags);
> >> +
> >> +               if (IS_ERR(page))
> >> +                       continue;
> >> +               if (!page)
> >> +                       continue;
> >> +
> >> +               if (!is_transparent_hugepage(page))
> >> +                       goto next;
> >> +
> >> +               total++;
> >> +               if (!can_split_huge_page(compound_head(page), NULL))
> >> +                       goto next;
> >> +
> >> +               if (!trylock_page(page))
> >> +                       goto next;
> >> +
> >> +               if (!split_huge_page(page))
> >> +                       split++;
> >> +
> >> +               unlock_page(page);
> >> +next:
> >> +               put_page(page);
> >> +       }
> >> +       mmap_read_unlock(mm);
> >> +       mmput(mm);
> >> +
> >> +       pr_info("%lu of %lu THP split\n", split, total);
> >> +
> >> +out:
> >> +       return ret;
> >>  }
> >> -DEFINE_DEBUGFS_ATTRIBUTE(split_huge_pages_fops, NULL, split_huge_pages_set,
> >> -               "%llu\n");
> >> +
> >> +static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
> >> +                               size_t count, loff_t *ppops)
> >> +{
> >> +       static DEFINE_MUTEX(split_debug_mutex);
> >> +       ssize_t ret;
> >> +       char input_buf[80]; /* hold pid, start_vaddr, end_vaddr */
> >
> > Why not move buf len macro in the following patch to this patch? Then
> > you don't have to change the length again.
>
> Sure.
>
> Thanks for the comments.
>
> --
> Best Regards,
> Yan Zi