iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
linux/mm
History
David Hildenbrand b2747b690c mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage 
commit 42b2af2c9b7eede8ef21d0943f84d135e21a32a3 upstream.

Currently, we'd lose the userfaultfd-wp marker when PTE-mapping a huge
zeropage, resulting in the next write faults in the PMD range not
triggering uffd-wp events.

Various actions (partial MADV_DONTNEED, partial mremap, partial munmap,
partial mprotect) could trigger this.  However, most importantly,
un-protecting a single sub-page from the userfaultfd-wp handler when
processing a uffd-wp event will PTE-map the shared huge zeropage and lose
the uffd-wp bit for the remainder of the PMD.

Let's properly propagate the uffd-wp bit to the PMDs.

 #define _GNU_SOURCE
 #include <stdio.h>
 #include <stdlib.h>
 #include <stdint.h>
 #include <stdbool.h>
 #include <inttypes.h>
 #include <fcntl.h>
 #include <unistd.h>
 #include <errno.h>
 #include <poll.h>
 #include <pthread.h>
 #include <sys/mman.h>
 #include <sys/syscall.h>
 #include <sys/ioctl.h>
 #include <linux/userfaultfd.h>

 static size_t pagesize;
 static int uffd;
 static volatile bool uffd_triggered;

 #define barrier() __asm__ __volatile__("": : :"memory")

 static void uffd_wp_range(char *start, size_t size, bool wp)
 {
 	struct uffdio_writeprotect uffd_writeprotect;

 	uffd_writeprotect.range.start = (unsigned long) start;
 	uffd_writeprotect.range.len = size;
 	if (wp) {
 		uffd_writeprotect.mode = UFFDIO_WRITEPROTECT_MODE_WP;
 	} else {
 		uffd_writeprotect.mode = 0;
 	}
 	if (ioctl(uffd, UFFDIO_WRITEPROTECT, &uffd_writeprotect)) {
 		fprintf(stderr, "UFFDIO_WRITEPROTECT failed: %d\n", errno);
 		exit(1);
 	}
 }

 static void *uffd_thread_fn(void *arg)
 {
 	static struct uffd_msg msg;
 	ssize_t nread;

 	while (1) {
 		struct pollfd pollfd;
 		int nready;

 		pollfd.fd = uffd;
 		pollfd.events = POLLIN;
 		nready = poll(&pollfd, 1, -1);
 		if (nready == -1) {
 			fprintf(stderr, "poll() failed: %d\n", errno);
 			exit(1);
 		}

 		nread = read(uffd, &msg, sizeof(msg));
 		if (nread <= 0)
 			continue;

 		if (msg.event != UFFD_EVENT_PAGEFAULT ||
 		    !(msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP)) {
 			printf("FAIL: wrong uffd-wp event fired\n");
 			exit(1);
 		}

 		/* un-protect the single page. */
 		uffd_triggered = true;
 		uffd_wp_range((char *)(uintptr_t)msg.arg.pagefault.address,
 			      pagesize, false);
 	}
 	return arg;
 }

 static int setup_uffd(char *map, size_t size)
 {
 	struct uffdio_api uffdio_api;
 	struct uffdio_register uffdio_register;
 	pthread_t thread;

 	uffd = syscall(__NR_userfaultfd,
 		       O_CLOEXEC | O_NONBLOCK | UFFD_USER_MODE_ONLY);
 	if (uffd < 0) {
 		fprintf(stderr, "syscall() failed: %d\n", errno);
 		return -errno;
 	}

 	uffdio_api.api = UFFD_API;
 	uffdio_api.features = UFFD_FEATURE_PAGEFAULT_FLAG_WP;
 	if (ioctl(uffd, UFFDIO_API, &uffdio_api) < 0) {
 		fprintf(stderr, "UFFDIO_API failed: %d\n", errno);
 		return -errno;
 	}

 	if (!(uffdio_api.features & UFFD_FEATURE_PAGEFAULT_FLAG_WP)) {
 		fprintf(stderr, "UFFD_FEATURE_WRITEPROTECT missing\n");
 		return -ENOSYS;
 	}

 	uffdio_register.range.start = (unsigned long) map;
 	uffdio_register.range.len = size;
 	uffdio_register.mode = UFFDIO_REGISTER_MODE_WP;
 	if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) < 0) {
 		fprintf(stderr, "UFFDIO_REGISTER failed: %d\n", errno);
 		return -errno;
 	}

 	pthread_create(&thread, NULL, uffd_thread_fn, NULL);

 	return 0;
 }

 int main(void)
 {
 	const size_t size = 4 * 1024 * 1024ull;
 	char *map, *cur;

 	pagesize = getpagesize();

 	map = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANON, -1, 0);
 	if (map == MAP_FAILED) {
 		fprintf(stderr, "mmap() failed\n");
 		return -errno;
 	}

 	if (madvise(map, size, MADV_HUGEPAGE)) {
 		fprintf(stderr, "MADV_HUGEPAGE failed\n");
 		return -errno;
 	}

 	if (setup_uffd(map, size))
 		return 1;

 	/* Read the whole range, populating zeropages. */
 	madvise(map, size, MADV_POPULATE_READ);

 	/* Write-protect the whole range. */
 	uffd_wp_range(map, size, true);

 	/* Make sure uffd-wp triggers on each page. */
 	for (cur = map; cur < map + size; cur += pagesize) {
 		uffd_triggered = false;

 		barrier();
 		/* Trigger a write fault. */
 		*cur = 1;
 		barrier();

 		if (!uffd_triggered) {
 			printf("FAIL: uffd-wp did not trigger\n");
 			return 1;
 		}
 	}

 	printf("PASS: uffd-wp triggered\n");
 	return 0;
 }

Link: https://lkml.kernel.org/r/20230302175423.589164-1-david@redhat.com
Fixes: e06f1e1dd499 ("userfaultfd: wp: enabled write protection in userfaultfd API")
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2023-03-22 13:30:04 +01:00
..
kasan
panic: Consolidate open-coded panic_on_warn checks
2023-02-01 08:23:20 +01:00
backing-dev.c
mm: bdi: initialize bdi_min_ratio when bdi is unregistered
2021-12-14 11:32:37 +01:00
balloon_compaction.c
…
cleancache.c
…
cma_debug.c
debugfs: make sure we can remove u32_array files cleanly
2020-07-10 13:54:00 -07:00
cma.c
cma: don't quit at first error when activating reserved areas
2020-08-12 10:57:57 -07:00
cma.h
mm: cma: use CMA_MAX_NAME to define the length of cma name array
2020-09-01 09:19:43 +02:00
compaction.c
mm, compaction: fix fast_isolate_around() to stay within boundaries
2023-01-14 10:16:27 +01:00
debug_page_ref.c
…
debug_vm_pgtable.c
mm/debug_vm_pgtable: remove pte entry from the page table
2022-02-08 18:30:35 +01:00
debug.c
mm, dump_page: rename head_mapcount() --> head_compound_mapcount()
2020-10-13 18:38:29 -07:00
dmapool.c
mm/dmapool.c: replace hard coded function name with __func__
2020-10-13 18:38:32 -07:00
early_ioremap.c
…
fadvise.c
mm, fadvise: improve the expensive remote LRU cache draining after FADV_DONTNEED
2020-10-13 18:38:29 -07:00
failslab.c
…
filemap.c
mm: fs: initialize fsdata passed to write_begin/write_end interface
2022-11-25 17:45:56 +01:00
frame_vector.c
v4l2: don't fall back to follow_pfn() if pin_user_pages_fast() fails
2022-12-08 11:24:00 +01:00
frontswap.c
mm/frontswap: mark various intentional data races
2020-08-14 19:56:56 -07:00
gup_benchmark.c
mm/gup_benchmark: take the mmap lock around GUP
2020-10-18 09:27:09 -07:00
gup.c
mm/migration: return errno when isolate_huge_page failed
2023-02-15 17:22:21 +01:00
highmem.c
mm/highmem.c: clean up endif comments
2020-10-16 11:11:18 -07:00
hmm.c
mm/hmm.c: allow VM_MIXEDMAP to work with hmm_range_fault
2022-01-27 10:54:36 +01:00
huge_memory.c
mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage
2023-03-22 13:30:04 +01:00
hugetlb_cgroup.c
hugetlb_cgroup: fix imbalanced css_get and css_put pair for shared mappings
2021-03-30 14:31:54 +02:00
hugetlb.c
mm/migration: return errno when isolate_huge_page failed
2023-02-15 17:22:21 +01:00
hwpoison-inject.c
mm,hwpoison-inject: don't pin for hwpoison_filter
2020-10-16 11:11:16 -07:00
init-mm.c
mm/gup: prevent gup_fast from racing with COW during fork
2020-12-30 11:53:54 +01:00
internal.h
mm/thp: fix vma_address() if virtual address below file offset
2021-06-30 08:47:27 -04:00
interval_tree.c
…
ioremap.c
mm: move p?d_alloc_track to separate header file
2020-08-07 11:33:26 -07:00
Kconfig
mm/zsmalloc.c: drop ZSMALLOC_PGTABLE_MAPPING
2020-12-06 10:19:07 -08:00
Kconfig.debug
treewide: replace '---help---' in Kconfig files with 'help'
2020-06-14 01:57:21 +09:00
khugepaged.c
mm/khugepaged: fix collapse_pte_mapped_thp() to allow anon_vma
2023-01-24 07:20:01 +01:00
kmemleak.c
Revert "mm: kmemleak: take a full lowmem check in kmemleak_*_phys()"
2022-09-15 11:32:02 +02:00
ksm.c
ksm: fix potential missing rmap_item for stable_node
2021-05-19 10:13:07 +02:00
list_lru.c
mm: list_lru: set shrinker map bit when child nr_items is not zero
2020-12-06 10:19:07 -08:00
maccess.c
maccess: Fix writing offset in case of fault in strncpy_from_kernel_nofault()
2022-11-25 17:45:53 +01:00
madvise.c
mm: fix madivse_pageout mishandling on non-LRU page
2022-10-05 10:38:40 +02:00
Makefile
mm,kmemleak-test.c: move kmemleak-test.c to samples dir
2020-10-13 18:38:27 -07:00
mapping_dirty_helpers.c
…
memblock.c
Revert "mm: Always release pages to the buddy allocator in memblock_free_late()."
2023-02-22 12:55:56 +01:00
memcontrol.c
mm: memcontrol: deprecate charge moving
2023-03-11 16:40:04 +01:00
memfd.c
memfd: fix F_SEAL_WRITE after shmem huge page allocated
2022-03-08 19:09:36 +01:00
memory_hotplug.c
mm/migration: return errno when isolate_huge_page failed
2023-02-15 17:22:21 +01:00
memory-failure.c
mm/migration: return errno when isolate_huge_page failed
2023-02-15 17:22:21 +01:00
memory.c
mm/memory: add non-anonymous page check in the copy_present_page()
2022-11-03 23:57:50 +09:00
mempolicy.c
migrate: hugetlb: check for hugetlb shared PMD in node migration
2023-02-15 17:22:21 +01:00
mempool.c
mm/mempool: add 'else' to split mutually exclusive case
2020-10-13 18:38:34 -07:00
memremap.c
mm/memremap.c: map FS_DAX device memory as decrypted
2022-11-16 09:57:17 +01:00
memtest.c
…
migrate.c
mm/migration: return errno when isolate_huge_page failed
2023-02-15 17:22:21 +01:00
mincore.c
mm: factor find_get_incore_page out of mincore_page
2020-10-13 18:38:29 -07:00
mlock.c
mlock: fix unevictable_pgs event counts on THP
2020-09-19 13:13:38 -07:00
mm_init.c
mm: adjust vm_committed_as_batch according to vm overcommit policy
2020-08-07 11:33:26 -07:00
mmap.c
mm/mmap: undo ->mmap() when arch_validate_flags() fails
2022-10-26 13:25:11 +02:00
mmu_gather.c
mm/khugepaged: fix GUP-fast interaction by sending IPI
2022-12-14 11:31:55 +01:00
mmu_notifier.c
mm/mmu_notifier.c: fix race in mmu_interval_notifier_remove()
2022-04-27 13:53:54 +02:00
mmzone.c
arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
2022-05-15 20:00:09 +02:00
mprotect.c
mm: don't try to NUMA-migrate COW pages that have other uses
2022-02-23 12:00:57 +01:00
mremap.c
mm/mremap: hold the rmap lock in write mode when moving page table entries.
2022-08-21 15:15:21 +02:00
msync.c
mmap locking API: use coccinelle to convert mmap_sem rwsem call sites
2020-06-09 09:39:14 -07:00
nommu.c
mm: remove alloc_vm_area
2020-10-18 09:27:10 -07:00
oom_kill.c
oom_kill.c: futex: delay the OOM reaper to allow time for proper futex cleanup
2022-04-27 13:53:54 +02:00
page_alloc.c
Fix page corruption caused by racy check in __free_pages
2023-02-15 17:22:27 +01:00
page_counter.c
mm/page_counter: correct the obsolete func name in the comment of page_counter_try_charge()
2020-10-13 18:38:30 -07:00
page_ext.c
mm/page_ext.c: drop pfn_present() check when onlining
2020-04-07 10:43:40 -07:00
page_idle.c
mm/page_idle.c: skip offline pages
2020-06-08 11:05:55 -07:00
page_io.c
mm: fix unexpected zeroed page mapping with zram swap
2022-04-20 09:23:25 +02:00
page_isolation.c
mm: rename page_order() to buddy_order()
2020-10-16 11:11:19 -07:00
page_owner.c
mm: rename page_order() to buddy_order()
2020-10-16 11:11:19 -07:00
page_poison.c
mm/page_poison.c: replace bool variable with static key
2020-10-16 11:11:17 -07:00
page_reporting.c
mm: rename page_order() to buddy_order()
2020-10-16 11:11:19 -07:00
page_reporting.h
mm: introduce include/linux/pgtable.h
2020-06-09 09:39:13 -07:00
page_vma_mapped.c
mm/thp: another PVMW_SYNC fix in page_vma_mapped_walk()
2021-06-30 08:47:29 -04:00
page-writeback.c
mm: make wait_on_page_writeback() wait for multiple pending writebacks
2021-01-12 20:18:22 +01:00
pagewalk.c
mm: pagewalk: Fix race between unmap and page walker
2022-09-08 11:11:38 +02:00
percpu-internal.h
percpu: make pcpu_nr_empty_pop_pages per chunk type
2021-04-14 08:42:03 +02:00
percpu-km.c
mm: memcg/percpu: account percpu memory to memory cgroups
2020-08-12 10:57:55 -07:00
percpu-stats.c
percpu: make pcpu_nr_empty_pop_pages per chunk type
2021-04-14 08:42:03 +02:00
percpu-vm.c
mm: memcg/percpu: account percpu memory to memory cgroups
2020-08-12 10:57:55 -07:00
percpu.c
percpu: make pcpu_nr_empty_pop_pages per chunk type
2021-04-14 08:42:03 +02:00
pgalloc-track.h
mm: move p?d_alloc_track to separate header file
2020-08-07 11:33:26 -07:00
pgtable-generic.c
mm/thp: fix __split_huge_pmd_locked() on shmem migration entry
2021-06-30 08:47:26 -04:00
process_vm_access.c
mm/process_vm_access.c: include compat.h
2021-01-19 18:27:21 +01:00
ptdump.c
mm: pagewalk: Fix race between unmap and page walker
2022-09-08 11:11:38 +02:00
readahead.c
mm: use limited read-ahead to satisfy read
2020-10-17 13:49:08 -06:00
rmap.c
mm/rmap: Fix anon_vma->degree ambiguity leading to double-reuse
2022-09-05 10:28:56 +02:00
rodata_test.c
mm/rodata_test.c: fix missing function declaration
2020-08-21 09:52:53 -07:00
shmem.c
shmem: fix a race between shmem_unused_huge_shrink and shmem_evict_inode
2022-01-27 10:53:44 +01:00
shuffle.c
mm: rename page_order() to buddy_order()
2020-10-16 11:11:19 -07:00
shuffle.h
mm/shuffle: remove dynamic reconfiguration
2020-08-07 11:33:29 -07:00
slab_common.c
mm/slub: fix redzoning for small allocations
2021-06-23 14:42:54 +02:00
slab.c
mm/sl?b.c: remove ctor argument from kmem_cache_flags
2021-05-14 09:50:45 +02:00
slab.h
mm: kmemleak: slob: respect SLAB_NOLEAKTRACE flag
2021-11-26 10:39:19 +01:00
slob.c
mm: memcg: convert vmstat slab counters to bytes
2020-08-07 11:33:24 -07:00
slub.c
mm/slub: fix to return errno if kmalloc() fails
2022-09-28 11:10:28 +02:00
sparse-vmemmap.c
mm/sparse: only sub-section aligned range would be populated
2020-08-07 11:33:27 -07:00
sparse.c
mm/sparse: add the missing sparse_buffer_fini() in error branch
2021-05-14 09:50:45 +02:00
swap_cgroup.c
mm: memcontrol: make swap tracking an integral part of memory control
2020-06-03 20:09:48 -07:00
swap_slots.c
mm/swap_slots.c: remove always zero and unused return value of enable_swap_slots_cache()
2020-10-13 18:38:30 -07:00
swap_state.c
mm: swap: get rid of livelock in swapin readahead
2022-03-23 09:13:27 +01:00
swap.c
mm: move call to compound_head() in release_pages()
2020-10-13 18:38:33 -07:00
swapfile.c
mm/swapfile: add cond_resched() in get_swap_pages()
2023-02-15 17:22:20 +01:00
truncate.c
mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page()
2021-06-30 08:47:27 -04:00
usercopy.c
mm/usercopy: return 1 from hardened_usercopy __setup() handler
2022-04-08 14:40:43 +02:00
userfaultfd.c
mm: userfaultfd: fix missing cache flush in mcopy_atomic_pte() and __mcopy_atomic()
2022-05-15 20:00:09 +02:00
util.c
mm: Add kvrealloc()
2022-08-21 15:15:21 +02:00
vmacache.c
kernel: better document the use_mm/unuse_mm API contract
2020-06-10 19:14:18 -07:00
vmalloc.c
mm/vmalloc.c: fix potential memory leak
2021-01-19 18:27:21 +01:00
vmpressure.c
…
vmscan.c
mm: vmscan: fix extreme overreclaim and swap floods
2022-12-02 17:40:04 +01:00
vmstat.c
arm: remove CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
2022-05-15 20:00:09 +02:00
workingset.c
XArray updates for 5.9
2020-10-20 14:39:37 -07:00
z3fold.c
mm/z3fold: use release_z3fold_page_locked() to release locked z3fold page
2021-07-14 16:56:51 +02:00
zbud.c
mm/zbud: remove redundant initialization
2020-10-13 18:38:34 -07:00
zpool.c
mm/zpool.c: delete duplicated word and fix grammar
2020-08-12 10:57:58 -07:00
zsmalloc.c
zsmalloc: fix races between asynchronous zspage free and page migration
2022-06-06 08:42:43 +02:00
zswap.c
mm/zswap: allow setting default status, compressor and allocator in Kconfig
2020-04-07 10:43:41 -07:00