Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: Ken Chen <kenchen@xxxxxxxxxx>
Cc: Chris Kennelly <ckennelly@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Kirill Shutemov <kirill@xxxxxxxxxxxxx>
---
Changes in v4:
- Added comments to make test output clearer.
- Modified test case slightly to test hugepage alignment of new_addr.
---
tools/testing/selftests/vm/.gitignore | 1 +
tools/testing/selftests/vm/Makefile | 1 +
tools/testing/selftests/vm/hugepage-mremap.c | 168 +++++++++++++++++++
3 files changed, 170 insertions(+)
create mode 100644 tools/testing/selftests/vm/hugepage-mremap.c
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index b02eac613fdda..2e7e86e852828 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -1,5 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
hugepage-mmap
+hugepage-mremap
hugepage-shm
khugepaged
map_hugetlb
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d9605bd10f2de..1607322a112c9 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -29,6 +29,7 @@ TEST_GEN_FILES = compaction_test
TEST_GEN_FILES += gup_test
TEST_GEN_FILES += hmm-tests
TEST_GEN_FILES += hugepage-mmap
+TEST_GEN_FILES += hugepage-mremap
TEST_GEN_FILES += hugepage-shm
TEST_GEN_FILES += khugepaged
TEST_GEN_FILES += madv_populate
diff --git a/tools/testing/selftests/vm/hugepage-mremap.c b/tools/testing/selftests/vm/hugepage-mremap.c
new file mode 100644
index 0000000000000..ba35b5b13c52c
--- /dev/null
+++ b/tools/testing/selftests/vm/hugepage-mremap.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * hugepage-mremap:
+ *
+ * Example of remapping huge page memory in a user application using the
+ * mremap system call. Before running this application, make sure that the
+ * administrator has mounted the hugetlbfs filesystem (on some directory
+ * like /mnt) using the command mount -t hugetlbfs nodev /mnt. In this
+ * example, the app is requesting memory of size 10MB that is backed by
+ * huge pages.
+ *
+ */
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+#include <errno.h>
+#include <fcntl.h> /* Definition of O_* constants */
+#include <sys/syscall.h> /* Definition of SYS_* constants */
+#include <unistd.h>
+#include <linux/userfaultfd.h>
+#include <sys/ioctl.h>
+
+#define LENGTH (1UL * 1024 * 1024 * 1024)
+
+#define PROTECTION (PROT_READ | PROT_WRITE | PROT_EXEC)
+#define FLAGS (MAP_SHARED | MAP_ANONYMOUS)
+
+static void check_bytes(char *addr)
+{
+ printf("First hex is %x\n", *((unsigned int *)addr));
+}
+
+static void write_bytes(char *addr)
+{
+ unsigned long i;
+
+ for (i = 0; i < LENGTH; i++)
+ *(addr + i) = (char)i;
+}
+
+static int read_bytes(char *addr)
+{
+ unsigned long i;
+
+ check_bytes(addr);
+ for (i = 0; i < LENGTH; i++)
+ if (*(addr + i) != (char)i) {
+ printf("Mismatch at %lu\n", i);
+ return 1;
+ }
+ return 0;
+}
+
+static void register_region_with_uffd(char *addr, size_t len)
+{
+ long uffd; /* userfaultfd file descriptor */
+ struct uffdio_api uffdio_api;
+ struct uffdio_register uffdio_register;
+
+ /* Create and enable userfaultfd object. */
+
+ uffd = syscall(__NR_userfaultfd, O_CLOEXEC | O_NONBLOCK);
+ if (uffd == -1) {
+ perror("userfaultfd");
+ exit(1);
+ }
+
+ uffdio_api.api = UFFD_API;
+ uffdio_api.features = 0;
+ if (ioctl(uffd, UFFDIO_API, &uffdio_api) == -1) {
+ perror("ioctl-UFFDIO_API");
+ exit(1);
+ }
+
+ /* Create a private anonymous mapping. The memory will be
+ * demand-zero paged--that is, not yet allocated. When we
+ * actually touch the memory, it will be allocated via
+ * the userfaultfd.
+ */
+
+ addr = mmap(NULL, len, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+ if (addr == MAP_FAILED) {
+ perror("mmap");
+ exit(1);
+ }
+
+ printf("Address returned by mmap() = %p\n", addr);
+
+ /* Register the memory range of the mapping we just created for
+ * handling by the userfaultfd object. In mode, we request to track
+ * missing pages (i.e., pages that have not yet been faulted in).
+ */
+
+ uffdio_register.range.start = (unsigned long)addr;
+ uffdio_register.range.len = len;
+ uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING;
+ if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == -1) {
+ perror("ioctl-UFFDIO_REGISTER");
+ exit(1);
+ }
+}
+
+int main(void)
+{
+ int ret = 0;
+
+ int fd = open("/mnt/huge/test", O_CREAT | O_RDWR, 0755);
+
+ if (fd < 0) {
+ perror("Open failed");
+ exit(1);
+ }
+
+ /* mmap to a PUD aligned address to hopefully trigger pmd sharing. */
+ unsigned long suggested_addr = 0x7eaa40000000;
+ void *haddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+ MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
+ printf("Map haddr: Returned address is %p\n", haddr);
+ if (haddr == MAP_FAILED) {
+ perror("mmap1");
+ exit(1);
+ }
+
+ /* mmap again to a dummy address to hopefully trigger pmd sharing. */
+ suggested_addr = 0x7daa40000000;
+ void *daddr = mmap((void *)suggested_addr, LENGTH, PROTECTION,
+ MAP_HUGETLB | MAP_SHARED | MAP_POPULATE, fd, 0);
+ printf("Map daddr: Returned address is %p\n", daddr);
+ if (daddr == MAP_FAILED) {
+ perror("mmap3");
+ exit(1);
+ }
+
+ /* Note vaddr is not hugepage aligned. Mremap should hugepage align the
+ * vaddr on remap.
+ */
+ suggested_addr = 0x7faa4002000;
+ void *vaddr =
+ mmap((void *)suggested_addr, LENGTH, PROTECTION, FLAGS, -1, 0);
+ printf("Map vaddr: Returned address is %p\n", vaddr);
+ if (vaddr == MAP_FAILED) {
+ perror("mmap2");
+ exit(1);
+ }
+
+ register_region_with_uffd(haddr, LENGTH);
+
+ void *addr = mremap(haddr, LENGTH, LENGTH,
+ MREMAP_MAYMOVE | MREMAP_FIXED, vaddr);
+ if (addr == MAP_FAILED) {
+ perror("mremap");
+ exit(1);
+ }
+
+ printf("Mremap: Returned address is %p\n", addr);
+ check_bytes(addr);
+ write_bytes(addr);
+ ret = read_bytes(addr);
+
+ munmap(addr, LENGTH);
+
+ return ret;
+}
--
2.33.0.882.g93a45727a2-goog
