On Wed, Mar 17, 2021 at 8:00 AM Zi Yan <ziy@xxxxxxxxxx> wrote:
>
> On 16 Mar 2021, at 19:18, Yang Shi wrote:
>
> > On Mon, Mar 15, 2021 at 1:34 PM Zi Yan <zi.yan@xxxxxxxx> wrote:
> >>
> >> From: Zi Yan <ziy@xxxxxxxxxx>
> >>
> >> 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@xxxxxxxxxxxxxxx>
> >> Signed-off-by: Zi Yan <ziy@xxxxxxxxxx>
> >> ---
> >> mm/huge_memory.c | 95 ++++++++++++++++++-
> >> .../selftests/vm/split_huge_page_test.c | 79 ++++++++++++++-
> >> 2 files changed, 166 insertions(+), 8 deletions(-)
> >>
> >> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> >> index 3bfee54e2cd0..da91ee97d944 100644
> >> --- a/mm/huge_memory.c
> >> +++ b/mm/huge_memory.c
> >> @@ -3043,12 +3043,72 @@ 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) {
> >
> > Why do you have FGP_ENTRY? It seems it would return page instead of
> > NULL if page is value. So I think you could remove FGP_ENTRY and
> > xa_is_value() check as well.
>
> The comment on FGP_ENTRY says “If there is a shadow/swap/DAX entry, return
> it instead of allocating a new page to replace it”. I do not think we
> want to allocate new pages here. I mostly follow the use of pagecache_get_page()
> in shmem_getpage_gfp without swapin or allocating new pages.
Yes, you are correct. I overlooked that.
>
> >
> >> + 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;
> >> +}
> >> +
> >> static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
> >> size_t count, loff_t *ppops)
> >> {
> >> static DEFINE_MUTEX(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];
> >
> > I didn't find where MAX_INPUT is defined in your patch. Just saw
> > include/uapi/linux/limits.h have it defined. Is it the one you really
> > refer to?
>
> Yeah, I want to use 255 as the max input size and find MAX_INPUT. From your comment,
> I think it is better to define a MACRO here explicitly.
>
>
> >> int pid;
> >> unsigned long vaddr_start, vaddr_end;
> >>
> >> @@ -3058,11 +3118,40 @@ 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);
> >> if (copy_from_user(input_buf, buf, min_t(size_t, count, 80)))
> >> goto out;
> >>
> >> - input_buf[79] = '\0';
> >> + input_buf[MAX_INPUT - 1] = '\0';
> >> +
> >> + if (input_buf[0] == '/') {
> >> + char *tok;
> >> + char *buf = input_buf;
> >> + char file_path[MAX_INPUT];
> >> + 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);
> >> + } 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 9f33ddbb3182..0202702f7eda 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);
> >> @@ -178,7 +186,8 @@ 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) {
> >> @@ -269,7 +278,7 @@ 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 */
> >> @@ -295,6 +304,65 @@ 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) {
> >> @@ -308,6 +376,7 @@ int main(int argc, char **argv)
> >>
> >> split_pmd_thp();
> >> split_pte_mapped_thp();
> >> + split_file_backed_thp();
> >>
> >> return 0;
> >> }
> >> --
> >> 2.30.1
> >>
>
> Thanks for the comments. :)
>
> —
> Best Regards,
> Yan Zi
