@@ -3399,7 +3399,7 @@ static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma)
}
static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
- unsigned long vaddr_end)
+ unsigned long vaddr_end, unsigned int new_order)
{
int ret = 0;
struct task_struct *task;
@@ -3463,13 +3463,19 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
goto next;
total++;
- if (!can_split_folio(folio, NULL))
+ /*
+ * For folios with private, split_huge_page_to_list_to_order()
+ * will try to drop it before split and then check if the folio
+ * can be split or not. So skip the check here.
+ */
+ if (!folio_test_private(folio) &&
+ !can_split_folio(folio, NULL))
goto next;
if (!folio_trylock(folio))
goto next;
- if (!split_folio(folio))
+ if (!split_folio_to_order(folio, new_order))
split++;
folio_unlock(folio);
@@ -3487,7 +3493,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
}
static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
- pgoff_t off_end)
+ pgoff_t off_end, unsigned int new_order)
{
struct filename *file;
struct file *candidate;
@@ -3526,7 +3532,7 @@ static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start,
if (!folio_trylock(folio))
goto next;
- if (!split_folio(folio))
+ if (!split_folio_to_order(folio, new_order))
split++;
folio_unlock(folio);
@@ -3551,10 +3557,14 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
{
static DEFINE_MUTEX(split_debug_mutex);
ssize_t ret;
- /* hold pid, start_vaddr, end_vaddr or file_path, off_start, off_end */
+ /*
+ * hold pid, start_vaddr, end_vaddr, new_order or
+ * file_path, off_start, off_end, new_order
+ */
char input_buf[MAX_INPUT_BUF_SZ];
int pid;
unsigned long vaddr_start, vaddr_end;
+ unsigned int new_order = 0;
ret = mutex_lock_interruptible(&split_debug_mutex);
if (ret)
@@ -3583,29 +3593,29 @@ static ssize_t split_huge_pages_write(struct file *file, const char __user *buf,
goto out;
}
- ret = sscanf(buf, "0x%lx,0x%lx", &off_start, &off_end);
- if (ret != 2) {
+ ret = sscanf(buf, "0x%lx,0x%lx,%d", &off_start, &off_end, &new_order);
+ if (ret != 2 && ret != 3) {
ret = -EINVAL;
goto out;
}
- ret = split_huge_pages_in_file(file_path, off_start, off_end);
+ ret = split_huge_pages_in_file(file_path, off_start, off_end, new_order);
if (!ret)
ret = input_len;
goto out;
}
- ret = sscanf(input_buf, "%d,0x%lx,0x%lx", &pid, &vaddr_start, &vaddr_end);
+ ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d", &pid, &vaddr_start, &vaddr_end, &new_order);
if (ret == 1 && pid == 1) {
split_huge_pages_all();
ret = strlen(input_buf);
goto out;
- } else if (ret != 3) {
+ } else if (ret != 3 && ret != 4) {
ret = -EINVAL;
goto out;
}
- ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end);
+ ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order);
if (!ret)
ret = strlen(input_buf);
out:
@@ -16,6 +16,7 @@
#include <sys/mount.h>
#include <malloc.h>
#include <stdbool.h>
+#include <time.h>
#include "vm_util.h"
#include "../kselftest.h"
@@ -24,10 +25,12 @@ unsigned int pageshift;
uint64_t pmd_pagesize;
#define SPLIT_DEBUGFS "/sys/kernel/debug/split_huge_pages"
+#define SMAP_PATH "/proc/self/smaps"
+#define THP_FS_PATH "/mnt/thp_fs"
#define INPUT_MAX 80
-#define PID_FMT "%d,0x%lx,0x%lx"
-#define PATH_FMT "%s,0x%lx,0x%lx"
+#define PID_FMT "%d,0x%lx,0x%lx,%d"
+#define PATH_FMT "%s,0x%lx,0x%lx,%d"
#define PFN_MASK ((1UL<<55)-1)
#define KPF_THP (1UL<<22)
@@ -102,7 +105,7 @@ void split_pmd_thp(void)
/* split all THPs */
write_debugfs(PID_FMT, getpid(), (uint64_t)one_page,
- (uint64_t)one_page + len);
+ (uint64_t)one_page + len, 0);
for (i = 0; i < len; i++)
if (one_page[i] != (char)i)
@@ -177,7 +180,7 @@ void split_pte_mapped_thp(void)
/* split all remapped THPs */
write_debugfs(PID_FMT, 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;
@@ -237,7 +240,7 @@ void split_file_backed_thp(void)
}
/* split the file-backed THP */
- write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end);
+ write_debugfs(PATH_FMT, testfile, pgoff_start, pgoff_end, 0);
status = unlink(testfile);
if (status) {
@@ -265,8 +268,188 @@ void split_file_backed_thp(void)
ksft_exit_fail_msg("Error occurred\n");
}
+void create_pagecache_thp_and_fd(const char *testfile, size_t fd_size, int *fd, char **addr)
+{
+ size_t i;
+ int dummy;
+
+ srand(time(NULL));
+
+ *fd = open(testfile, O_CREAT | O_RDWR, 0664);
+ if (*fd == -1)
+ ksft_exit_fail_msg("Failed to create a file at "THP_FS_PATH);
+
+ 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) {
+ ksft_perror("open drop_caches");
+ goto err_out_unlink;
+ }
+ if (write(*fd, "3", 1) != 1) {
+ ksft_perror("write to drop_caches");
+ goto err_out_unlink;
+ }
+ close(*fd);
+
+ *fd = open(testfile, O_RDWR);
+ if (*fd == -1) {
+ ksft_perror("Failed to open a file at "THP_FS_PATH);
+ goto err_out_unlink;
+ }
+
+ *addr = mmap(NULL, fd_size, PROT_READ|PROT_WRITE, MAP_SHARED, *fd, 0);
+ if (*addr == (char *)-1) {
+ ksft_perror("cannot mmap");
+ goto err_out_close;
+ }
+ madvise(*addr, fd_size, MADV_HUGEPAGE);
+
+ for (size_t i = 0; i < fd_size; i++)
+ dummy += *(*addr + i);
+
+ if (!check_huge_file(*addr, fd_size / pmd_pagesize, pmd_pagesize)) {
+ ksft_print_msg("No large pagecache folio generated, please mount a filesystem supporting large folio at "THP_FS_PATH"\n");
+ goto err_out_close;
+ }
+ return;
+err_out_close:
+ close(*fd);
+err_out_unlink:
+ unlink(testfile);
+ ksft_exit_fail_msg("Failed to create large pagecache folios\n");
+}
+
+void split_thp_in_pagecache_to_order(size_t fd_size, int order)
+{
+ int fd;
+ char *addr;
+ size_t i;
+ const char testfile[] = THP_FS_PATH "/test";
+ int err = 0;
+
+ create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr);
+
+ write_debugfs(PID_FMT, getpid(), (uint64_t)addr, (uint64_t)addr + fd_size, order);
+
+ for (i = 0; i < fd_size; i++)
+ if (*(addr + i) != (char)i) {
+ ksft_print_msg("%lu byte corrupted in the file\n", i);
+ err = EXIT_FAILURE;
+ goto out;
+ }
+
+ if (!check_huge_file(addr, 0, pmd_pagesize)) {
+ ksft_print_msg("Still FilePmdMapped not split\n");
+ err = EXIT_FAILURE;
+ goto out;
+ }
+
+out:
+ close(fd);
+ unlink(testfile);
+ if (err)
+ ksft_exit_fail_msg("Split PMD-mapped pagecache folio to order %d failed\n", order);
+ ksft_test_result_pass("Split PMD-mapped pagecache folio to order %d passed\n", order);
+}
+
+void truncate_thp_in_pagecache_to_order(size_t fd_size, int order)
+{
+ int fd;
+ char *addr;
+ size_t i;
+ const char testfile[] = THP_FS_PATH "/test";
+ int err = 0;
+
+ create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr);
+
+ ftruncate(fd, pagesize << order);
+
+ for (i = 0; i < (pagesize << order); i++)
+ if (*(addr + i) != (char)i) {
+ ksft_print_msg("%lu byte corrupted in the file\n", i);
+ err = EXIT_FAILURE;
+ goto out;
+ }
+
+ if (!check_huge_file(addr, 0, pmd_pagesize)) {
+ ksft_print_msg("Still FilePmdMapped not split after truncate\n");
+ err = EXIT_FAILURE;
+ goto out;
+ }
+
+out:
+ close(fd);
+ unlink(testfile);
+ if (err)
+ ksft_exit_fail_msg("Truncate PMD-mapped pagecache folio to order %d failed\n", order);
+ ksft_test_result_pass("Truncate PMD-mapped pagecache folio to order %d passed\n", order);
+}
+
+void punch_hole_in_pagecache_thp(size_t fd_size, off_t offset[], off_t len[],
+ int n, int num_left_thps)
+{
+ int fd, j;
+ char *addr;
+ size_t i;
+ const char testfile[] = THP_FS_PATH "/test";
+ int err = 0;
+
+ create_pagecache_thp_and_fd(testfile, fd_size, &fd, &addr);
+
+ for (j = 0; j < n; j++) {
+ ksft_print_msg("punch a hole to %ld kB PMD-mapped pagecache page at addr: %lx, offset %ld, and len %ld ...\n",
+ fd_size >> 10, (unsigned long)addr, offset[j], len[j]);
+ fallocate(fd, FALLOC_FL_PUNCH_HOLE|FALLOC_FL_KEEP_SIZE, offset[j], len[j]);
+ }
+
+ 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) {
+ if (*(addr + i)) {
+ ksft_print_msg("%lu byte non-zero after punch\n", i);
+ err = EXIT_FAILURE;
+ goto out;
+ }
+ continue;
+ }
+ if (*(addr + i) != (char)i) {
+ ksft_print_msg("%lu byte corrupted in the file\n", i);
+ err = EXIT_FAILURE;
+ goto out;
+ }
+ }
+
+ if (!check_huge_file(addr, num_left_thps, pmd_pagesize)) {
+ ksft_print_msg("Still FilePmdMapped not split after punch\n");
+ goto out;
+ }
+out:
+ close(fd);
+ unlink(testfile);
+ if (err)
+ ksft_exit_fail_msg("Punch holes in PMD-mapped pagecache folio failed\n");
+ ksft_test_result_pass("Punch holes PMD-mapped pagecache folio passed\n");
+}
+
int main(int argc, char **argv)
{
+ int i;
+ size_t fd_size;
+ off_t offset[2], len[2];
+
ksft_print_header();
if (geteuid() != 0) {
@@ -274,7 +457,7 @@ int main(int argc, char **argv)
ksft_finished();
}
- ksft_set_plan(3);
+ ksft_set_plan(3+8+9+2);
pagesize = getpagesize();
pageshift = ffs(pagesize) - 1;
@@ -282,9 +465,37 @@ int main(int argc, char **argv)
if (!pmd_pagesize)
ksft_exit_fail_msg("Reading PMD pagesize failed\n");
+ fd_size = 2 * pmd_pagesize;
+
split_pmd_thp();
split_pte_mapped_thp();
split_file_backed_thp();
+ for (i = 8; i >= 0; i--)
+ if (i != 1)
+ 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;
+ offset[1] = 4 * pagesize;
+ len[0] = 200 * pagesize;
+ len[1] = 16 * pagesize;
+ punch_hole_in_pagecache_thp(fd_size, offset, len, 2, 1);
+
+ offset[0] = 259 * pagesize + pagesize / 2;
+ offset[1] = 33 * pagesize;
+ len[0] = 129 * pagesize;
+ len[1] = 16 * pagesize;
+ punch_hole_in_pagecache_thp(fd_size, offset, len, 2, 1);
+
ksft_finished();
+
+ return 0;
}