From: Muchun Song songmuchun@bytedance.com
mainline inclusion from mainline-v5.18-rc1 commit b147c89cd429321a59147368378c8aba17c8480f category: feature bugzilla: 187198, https://gitee.com/openeuler/kernel/issues/I5GVFO CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
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 Conflicts: tools/testing/selftests/vm/Makefile tools/testing/selftests/vm/run_vmtests.sh Signed-off-by: Liu Shixin liushixin2@huawei.com Reviewed-by: Kefeng Wang wangkefeng.wang@huawei.com Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com --- tools/testing/selftests/vm/.gitignore | 1 + tools/testing/selftests/vm/Makefile | 1 + tools/testing/selftests/vm/hugepage-vmemmap.c | 144 ++++++++++++++++++ tools/testing/selftests/vm/run_vmtests | 11 ++ 4 files changed, 157 insertions(+) create mode 100644 tools/testing/selftests/vm/hugepage-vmemmap.c
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore index b3a183c36cb5..905dc4efa879 100644 --- a/tools/testing/selftests/vm/.gitignore +++ b/tools/testing/selftests/vm/.gitignore @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only hugepage-mmap hugepage-shm +hugepage-vmemmap khugepaged map_hugetlb map_populate diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile index b150cc837177..549761bc7193 100644 --- a/tools/testing/selftests/vm/Makefile +++ b/tools/testing/selftests/vm/Makefile @@ -27,6 +27,7 @@ TEST_GEN_FILES += gup_benchmark TEST_GEN_FILES += hmm-tests TEST_GEN_FILES += hugepage-mmap TEST_GEN_FILES += hugepage-shm +TEST_GEN_FILES += hugepage-vmemmap TEST_GEN_FILES += map_hugetlb TEST_GEN_FILES += map_fixed_noreplace TEST_GEN_FILES += map_populate 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 b/tools/testing/selftests/vm/run_vmtests index d578ad831813..949c71fe5951 100755 --- a/tools/testing/selftests/vm/run_vmtests +++ b/tools/testing/selftests/vm/run_vmtests @@ -108,6 +108,17 @@ else echo "[PASS]" fi
+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."