All of lore.kernel.org
 help / color / mirror / Atom feed
From: Muchun Song <songmuchun@bytedance.com>
To: mike.kravetz@oracle.com, akpm@linux-foundation.org,
	osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com,
	david@redhat.com, chenhuang5@huawei.com, bodeddub@amazon.com,
	corbet@lwn.net, willy@infradead.org, 21cnbao@gmail.com
Cc: duanxiongchun@bytedance.com, fam.zheng@bytedance.com,
	smuchun@gmail.com, zhengqi.arch@bytedance.com,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-mm@kvack.org, Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v4 4/5] selftests: vm: add a hugetlb test case
Date: Sun, 26 Sep 2021 11:13:38 +0800	[thread overview]
Message-ID: <20210926031339.40043-5-songmuchun@bytedance.com> (raw)
In-Reply-To: <20210926031339.40043-1-songmuchun@bytedance.com>

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().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Barry Song <song.bao.hua@hisilicon.com>
---
 tools/testing/selftests/vm/vmemmap_hugetlb.c | 144 +++++++++++++++++++++++++++
 1 file changed, 144 insertions(+)
 create mode 100644 tools/testing/selftests/vm/vmemmap_hugetlb.c

diff --git a/tools/testing/selftests/vm/vmemmap_hugetlb.c b/tools/testing/selftests/vm/vmemmap_hugetlb.c
new file mode 100644
index 000000000000..557bdbd4f87e
--- /dev/null
+++ b/tools/testing/selftests/vm/vmemmap_hugetlb.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;
+}
-- 
2.11.0


  parent reply	other threads:[~2021-09-26  3:15 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-09-26  3:13 [PATCH v4 0/5] Free the 2nd vmemmap page associated with each HugeTLB page Muchun Song
2021-09-26  3:13 ` [PATCH v4 1/5] mm: hugetlb: free " Muchun Song
2021-09-26 20:24   ` Barry Song
2021-09-26 20:24     ` Barry Song
2021-09-28  2:42     ` Muchun Song
2021-09-28  2:42       ` Muchun Song
2021-09-26  3:13 ` [PATCH v4 2/5] mm: hugetlb: replace hugetlb_free_vmemmap_enabled with a static_key Muchun Song
2021-09-26 20:13   ` Barry Song
2021-09-26 20:13     ` Barry Song
2021-09-26  3:13 ` [PATCH v4 3/5] mm: sparsemem: use page table lock to protect kernel pmd operations Muchun Song
2021-09-26  3:13 ` Muchun Song [this message]
2021-09-26  3:13 ` [PATCH v4 5/5] mm: sparsemem: move vmemmap related to HugeTLB to CONFIG_HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2021-09-27  4:38   ` Barry Song
2021-09-27  4:38     ` Barry Song

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20210926031339.40043-5-songmuchun@bytedance.com \
    --to=songmuchun@bytedance.com \
    --cc=21cnbao@gmail.com \
    --cc=akpm@linux-foundation.org \
    --cc=bodeddub@amazon.com \
    --cc=chenhuang5@huawei.com \
    --cc=corbet@lwn.net \
    --cc=david@redhat.com \
    --cc=duanxiongchun@bytedance.com \
    --cc=fam.zheng@bytedance.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=mike.kravetz@oracle.com \
    --cc=osalvador@suse.de \
    --cc=smuchun@gmail.com \
    --cc=song.bao.hua@hisilicon.com \
    --cc=willy@infradead.org \
    --cc=zhengqi.arch@bytedance.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.