selftests: vm: add a hugetlb test case

Since the head vmemmap page frame associated with each HugeTLB page is
reused, we should hide the PG_head flag of tail struct page from the
user.  Add a tese case to check whether it is work properly.  The test
steps are as follows.

  1) alloc 2MB hugeTLB
  2) get each page frame
  3) apply those APIs in each page frame
  4) Those APIs work completely the same as before.

Reading the flags of a page by /proc/kpageflags is done in
stable_page_flags(), which has invoked PageHead(), PageTail(),
PageCompound() and compound_head().

If those APIs work properly, the head page must have 15 and 17 bits set.
And tail pages must have 16 and 17 bits set but 15 bit unset.  Those
flags are checked in check_page_flags().

Link: https://lkml.kernel.org/r/20211101031651.75851-5-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Barry Song <song.bao.hua@hisilicon.com>
Cc: Bodeddula Balasubramaniam <bodeddub@amazon.com>
Cc: Chen Huang <chenhuang5@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Fam Zheng <fam.zheng@bytedance.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

4 files changed, 157 insertions, 0 deletions

diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 2e7e86e85282..3b5faec3c04f 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -2,6 +2,7 @@
 hugepage-mmap
 hugepage-mremap
 hugepage-shm
+hugepage-vmemmap
 khugepaged
 map_hugetlb
 map_populate
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index 1530c3e0242e..81040f01711f 100644
--- a/tools/testing/selftests/vm/Makefile
+++ b/tools/testing/selftests/vm/Makefile
@@ -33,6 +33,7 @@ TEST_GEN_FILES += hmm-tests
 TEST_GEN_FILES += hugepage-mmap
 TEST_GEN_FILES += hugepage-mremap
 TEST_GEN_FILES += hugepage-shm
+TEST_GEN_FILES += hugepage-vmemmap
 TEST_GEN_FILES += khugepaged
 TEST_GEN_FILES += madv_populate
 TEST_GEN_FILES += map_fixed_noreplace
diff --git a/tools/testing/selftests/vm/hugepage-vmemmap.c b/tools/testing/selftests/vm/hugepage-vmemmap.c
new file mode 100644
index 000000000000..557bdbd4f87e
--- /dev/null
+++ b/tools/testing/selftests/vm/hugepage-vmemmap.c
@@ -0,0 +1,144 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * A test case of using hugepage memory in a user application using the
+ * mmap system call with MAP_HUGETLB flag.  Before running this program
+ * make sure the administrator has allocated enough default sized huge
+ * pages to cover the 2 MB allocation.
+ */
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <fcntl.h>
+
+#define MAP_LENGTH		(2UL * 1024 * 1024)
+
+#ifndef MAP_HUGETLB
+#define MAP_HUGETLB		0x40000	/* arch specific */
+#endif
+
+#define PAGE_SIZE		4096
+
+#define PAGE_COMPOUND_HEAD	(1UL << 15)
+#define PAGE_COMPOUND_TAIL	(1UL << 16)
+#define PAGE_HUGE		(1UL << 17)
+
+#define HEAD_PAGE_FLAGS		(PAGE_COMPOUND_HEAD | PAGE_HUGE)
+#define TAIL_PAGE_FLAGS		(PAGE_COMPOUND_TAIL | PAGE_HUGE)
+
+#define PM_PFRAME_BITS		55
+#define PM_PFRAME_MASK		~((1UL << PM_PFRAME_BITS) - 1)
+
+/*
+ * For ia64 architecture, Linux kernel reserves Region number 4 for hugepages.
+ * That means the addresses starting with 0x800000... will need to be
+ * specified.  Specifying a fixed address is not required on ppc64, i386
+ * or x86_64.
+ */
+#ifdef __ia64__
+#define MAP_ADDR		(void *)(0x8000000000000000UL)
+#define MAP_FLAGS		(MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_FIXED)
+#else
+#define MAP_ADDR		NULL
+#define MAP_FLAGS		(MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB)
+#endif
+
+static void write_bytes(char *addr, size_t length)
+{
+	unsigned long i;
+
+	for (i = 0; i < length; i++)
+		*(addr + i) = (char)i;
+}
+
+static unsigned long virt_to_pfn(void *addr)
+{
+	int fd;
+	unsigned long pagemap;
+
+	fd = open("/proc/self/pagemap", O_RDONLY);
+	if (fd < 0)
+		return -1UL;
+
+	lseek(fd, (unsigned long)addr / PAGE_SIZE * sizeof(pagemap), SEEK_SET);
+	read(fd, &pagemap, sizeof(pagemap));
+	close(fd);
+
+	return pagemap & ~PM_PFRAME_MASK;
+}
+
+static int check_page_flags(unsigned long pfn)
+{
+	int fd, i;
+	unsigned long pageflags;
+
+	fd = open("/proc/kpageflags", O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	lseek(fd, pfn * sizeof(pageflags), SEEK_SET);
+
+	read(fd, &pageflags, sizeof(pageflags));
+	if ((pageflags & HEAD_PAGE_FLAGS) != HEAD_PAGE_FLAGS) {
+		close(fd);
+		printf("Head page flags (%lx) is invalid\n", pageflags);
+		return -1;
+	}
+
+	/*
+	 * pages other than the first page must be tail and shouldn't be head;
+	 * this also verifies kernel has correctly set the fake page_head to tail
+	 * while hugetlb_free_vmemmap is enabled.
+	 */
+	for (i = 1; i < MAP_LENGTH / PAGE_SIZE; i++) {
+		read(fd, &pageflags, sizeof(pageflags));
+		if ((pageflags & TAIL_PAGE_FLAGS) != TAIL_PAGE_FLAGS ||
+		    (pageflags & HEAD_PAGE_FLAGS) == HEAD_PAGE_FLAGS) {
+			close(fd);
+			printf("Tail page flags (%lx) is invalid\n", pageflags);
+			return -1;
+		}
+	}
+
+	close(fd);
+
+	return 0;
+}
+
+int main(int argc, char **argv)
+{
+	void *addr;
+	unsigned long pfn;
+
+	addr = mmap(MAP_ADDR, MAP_LENGTH, PROT_READ | PROT_WRITE, MAP_FLAGS, -1, 0);
+	if (addr == MAP_FAILED) {
+		perror("mmap");
+		exit(1);
+	}
+
+	/* Trigger allocation of HugeTLB page. */
+	write_bytes(addr, MAP_LENGTH);
+
+	pfn = virt_to_pfn(addr);
+	if (pfn == -1UL) {
+		munmap(addr, MAP_LENGTH);
+		perror("virt_to_pfn");
+		exit(1);
+	}
+
+	printf("Returned address is %p whose pfn is %lx\n", addr, pfn);
+
+	if (check_page_flags(pfn) < 0) {
+		munmap(addr, MAP_LENGTH);
+		perror("check_page_flags");
+		exit(1);
+	}
+
+	/* munmap() length of MAP_HUGETLB memory must be hugepage aligned */
+	if (munmap(addr, MAP_LENGTH)) {
+		perror("munmap");
+		exit(1);
+	}
+
+	return 0;
+}
diff --git a/tools/testing/selftests/vm/run_vmtests.sh b/tools/testing/selftests/vm/run_vmtests.sh
index 71d2dc198fc1..e10d50e0b8e8 100755
--- a/tools/testing/selftests/vm/run_vmtests.sh
+++ b/tools/testing/selftests/vm/run_vmtests.sh
@@ -120,6 +120,17 @@ else
 fi
 rm -f $mnt/huge_mremap
 
+echo "------------------------"
+echo "running hugepage-vmemmap"
+echo "------------------------"
+./hugepage-vmemmap
+if [ $? -ne 0 ]; then
+	echo "[FAIL]"
+	exitcode=1
+else
+	echo "[PASS]"
+fi
+
 echo "NOTE: The above hugetlb tests provide minimal coverage.  Use"
 echo "      https://github.com/libhugetlbfs/libhugetlbfs.git for"
 echo "      hugetlb regression testing."