iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
linux/mm
History
David Hildenbrand 42b2af2c9b mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage 
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>
2023-03-07 17:04:53 -08:00
..
damon
mm/damon/paddr: fix missing folio_put()
2023-02-27 17:00:14 -08:00
kasan
kasan: test: fix test for new meminstrinsic instrumentation
2023-03-02 21:54:22 -08:00
kfence
hardening updates for v6.2-rc1
2022-12-14 12:20:00 -08:00
kmsan
kmsan: disable ftrace in kmsan core code
2023-02-20 12:46:16 -08:00
backing-dev.c
mm: add /sys/class/bdi/<bdi>/min_ratio_fine knob
2022-11-30 15:59:06 -08:00
balloon_compaction.c
mm: Convert all PageMovable users to movable_operations
2022-08-02 12:34:03 -04:00
bootmem_info.c
bootmem: remove the vmemmap pages from kmemleak in put_page_bootmem
2022-08-28 14:02:45 -07:00
cma_debug.c
mm/cma_debug: show complete cma name in debugfs directories
2022-09-11 20:25:50 -07:00
cma_sysfs.c
…
cma.c
mm/cma: fix potential memory loss on cma_declare_contiguous_nid
2023-02-02 22:33:24 -08:00
cma.h
…
compaction.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
debug_page_ref.c
…
debug_vm_pgtable.c
mm: remove __HAVE_ARCH_PTE_SWP_EXCLUSIVE
2023-02-02 22:33:11 -08:00
debug.c
mm: export dump_mm()
2023-02-09 16:51:40 -08:00
dmapool.c
…
early_ioremap.c
mm/early_ioremap: declare early_memremap_pgprot_adjust()
2022-03-22 15:57:11 -07:00
fadvise.c
mm: support POSIX_FADV_NOREUSE
2023-01-18 17:12:57 -08:00
failslab.c
mm: fix unexpected changes to {failslab|fail_page_alloc}.attr
2022-11-22 18:50:44 -08:00
filemap.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
folio-compat.c
mm: change to return bool for isolate_lru_page()
2023-02-20 12:46:17 -08:00
frontswap.c
frontswap: don't call ->init if no ops are registered
2022-09-26 12:14:34 -07:00
gup_test.c
mm/gup_test: free memory allocated via kvcalloc() using kvfree()
2022-12-15 16:37:48 -08:00
gup_test.h
mm/gup_test: start/stop/read functionality for PIN LONGTERM test
2022-11-08 17:37:15 -08:00
gup.c
mm: change to return bool for folio_isolate_lru()
2023-02-20 12:46:17 -08:00
highmem.c
highmem: fix kmap_to_page() for kmap_local_page() addresses
2022-10-12 18:51:51 -07:00
hmm.c
mm/hugetlb: make walk_hugetlb_range() safe to pmd unshare
2023-01-18 17:12:39 -08:00
huge_memory.c
mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage
2023-03-07 17:04:53 -08:00
hugetlb_cgroup.c
mm/hugetlb: increase use of folios in alloc_huge_page()
2023-02-13 15:54:27 -08:00
hugetlb_vmemmap.c
sysctl: fix proc_dobool() usability
2023-02-21 13:34:07 -08:00
hugetlb_vmemmap.h
mm: hugetlb_vmemmap: improve hugetlb_vmemmap code readability
2022-08-08 18:06:43 -07:00
hugetlb.c
mm: hugetlb: change to return bool for isolate_hugetlb()
2023-02-20 12:46:17 -08:00
hwpoison-inject.c
mm/hwpoison: add __init/__exit annotations to module init/exit funcs
2022-10-03 14:03:05 -07:00
init-mm.c
mm: remove rb tree.
2022-09-26 19:46:16 -07:00
internal.h
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
interval_tree.c
…
io-mapping.c
…
ioremap.c
mm: ioremap: Add ioremap/iounmap_allowed()
2022-06-27 12:22:31 +01:00
Kconfig
zsmalloc: set default zspage chain size to 8
2023-02-02 22:33:23 -08:00
Kconfig.debug
mm: move KMEMLEAK's Kconfig items from lib to mm
2023-02-02 22:33:26 -08:00
khugepaged.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
kmemleak.c
lib/stackdepot, mm: rename stack_depot_want_early_init
2023-02-16 20:43:49 -08:00
ksm.c
Merge branch 'mm-hotfixes-stable' into mm-stable
2023-02-10 15:34:48 -08:00
list_lru.c
mm: kmem: make mem_cgroup_from_obj() vmalloc()-safe
2022-06-16 19:48:31 -07:00
maccess.c
maccess: Fix writing offset in case of fault in strncpy_from_kernel_nofault()
2022-11-11 11:44:46 -08:00
madvise.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
Makefile
mm: memcontrol: drop dead CONFIG_MEMCG_SWAP config symbol
2022-10-03 14:03:36 -07:00
mapping_dirty_helpers.c
mm/mmu_notifier: remove unused mmu_notifier_range_update_to_read_only export
2023-02-02 22:32:54 -08:00
memblock.c
memblock: small optimizations
2023-02-27 09:34:53 -08:00
memcontrol.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
memfd.c
mm/memfd: add write seals when apply SEAL_EXEC to executable memfd
2023-01-18 17:12:37 -08:00
memory_hotplug.c
mm/memory_hotplug: cleanup return value handing in do_migrate_range()
2023-02-20 12:46:18 -08:00
memory-failure.c
mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON
2023-02-27 17:00:14 -08:00
memory-tiers.c
memory tier: release the new_memtier in find_create_memory_tier()
2023-02-09 16:51:40 -08:00
memory.c
mm/uffd: fix comment in handling pte markers
2023-02-20 12:46:18 -08:00
mempolicy.c
mm: hugetlb: change to return bool for isolate_hugetlb()
2023-02-20 12:46:17 -08:00
mempool.c
mempool: do not use ksize() for poisoning
2022-11-30 15:58:41 -08:00
memremap.c
mm/memremap.c: fix outdated comment in devm_memremap_pages
2023-02-09 16:51:46 -08:00
memtest.c
…
migrate_device.c
mm: change to return bool for isolate_lru_page()
2023-02-20 12:46:17 -08:00
migrate.c
mm: avoid gcc complaint about pointer casting
2023-03-04 14:03:27 -08:00
mincore.c
mm: teach mincore_hugetlb about pte markers
2023-03-07 17:04:53 -08:00
mlock.c
mm: introduce vm_flags_reset_once to replace WRITE_ONCE vm_flags updates
2023-02-09 16:51:41 -08:00
mm_init.c
memory: move hotplug memory notifier priority to same file for easy sorting
2022-11-08 17:37:17 -08:00
mm_slot.h
mm: introduce common struct mm_slot
2022-10-03 14:02:43 -07:00
mmap_lock.c
…
mmap.c
mm/mremap: fix dup_anon_vma() in vma_merge() case 4
2023-02-27 17:00:14 -08:00
mmu_gather.c
mm: mmu_gather: allow more than one batch of delayed rmaps
2022-12-11 18:12:21 -08:00
mmu_notifier.c
mm/mmu_notifier: remove unused mmu_notifier_range_update_to_read_only export
2023-02-02 22:32:54 -08:00
mmzone.c
mm: multi-gen LRU: groundwork
2022-09-26 19:46:09 -07:00
mprotect.c
mm/mprotect: Fix successful vma_merge() of next in do_mprotect_pkey()
2023-02-25 20:16:48 -08:00
mremap.c
mm: replace vma->vm_flags direct modifications with modifier calls
2023-02-09 16:51:39 -08:00
msync.c
mm/msync: use vma_find() instead of vma linked list
2022-09-26 19:46:25 -07:00
nommu.c
mm: replace vma->vm_flags direct modifications with modifier calls
2023-02-09 16:51:39 -08:00
oom_kill.c
mm/mmu_notifier: remove unused mmu_notifier_range_update_to_read_only export
2023-02-02 22:32:54 -08:00
page_alloc.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
page_counter.c
mm: page_counter: remove unneeded atomic ops for low/min
2022-09-11 20:26:01 -07:00
page_ext.c
mm/page_ext: init page_ext early if there are no deferred struct pages
2023-02-02 22:33:22 -08:00
page_idle.c
mm: page_idle: convert page idle to use a folio
2023-01-18 17:12:52 -08:00
page_io.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
page_isolation.c
mm/page_isolation: fix clang deadcode warning
2022-10-28 13:37:22 -07:00
page_owner.c
lib/stackdepot, mm: rename stack_depot_want_early_init
2023-02-16 20:43:49 -08:00
page_poison.c
…
page_reporting.c
mm/page_reporting: replace rcu_access_pointer() with rcu_dereference_protected()
2023-01-18 17:12:50 -08:00
page_reporting.h
…
page_table_check.c
mm/page_ext: do not allocate space for page_ext->flags if not needed
2023-02-02 22:33:11 -08:00
page_vma_mapped.c
mm/hugetlb: introduce hugetlb_walk()
2023-01-18 17:12:39 -08:00
page-writeback.c
fs: convert writepage_t callback to pass a folio
2023-02-02 22:33:34 -08:00
pagewalk.c
mm/hugetlb: introduce hugetlb_walk()
2023-01-18 17:12:39 -08:00
percpu-internal.h
mm: percpu: fix incorrect size in pcpu_obj_full_size()
2023-02-16 20:43:55 -08:00
percpu-km.c
…
percpu-stats.c
…
percpu-vm.c
…
percpu.c
mm: memcontrol: rename memcg_kmem_enabled()
2023-02-16 20:43:56 -08:00
pgalloc-track.h
…
pgtable-generic.c
mm: avoid unnecessary flush on change_huge_pmd()
2022-05-13 07:20:05 -07:00
process_vm_access.c
use less confusing names for iov_iter direction initializers
2022-11-25 13:01:55 -05:00
ptdump.c
mm: pagewalk: Fix race between unmap and page walker
2022-09-03 10:13:13 -07:00
readahead.c
readahead: convert readahead_expand() to use a folio
2023-02-02 22:33:21 -08:00
rmap.c
mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON
2023-02-27 17:00:14 -08:00
rodata_test.c
mm/rodata_test: use PAGE_ALIGNED() helper
2022-10-03 14:03:05 -07:00
secretmem.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
shmem.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
shrinker_debug.c
mm: shrinkers: fix deadlock in shrinker debugfs
2023-02-09 15:56:51 -08:00
shuffle.c
mm/shuffle: convert module_param_call to module_param_cb
2022-10-03 14:03:07 -07:00
shuffle.h
…
slab_common.c
mm/kasan: simplify and refine kasan_cache code
2023-01-18 17:12:55 -08:00
slab.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
slab.h
mm: memcontrol: rename memcg_kmem_enabled()
2023-02-16 20:43:56 -08:00
slob.c
Merge branch 'slab/for-6.1/kmalloc_size_roundup' into slab/for-next
2022-09-29 11:30:55 +02:00
slub.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
sparse-vmemmap.c
mm/sparse-vmemmap: generalise vmemmap_populate_hugepages()
2022-12-11 18:12:12 -08:00
sparse.c
mm/sparse: fix "unused function 'pgdat_to_phys'" warning
2023-02-02 22:33:29 -08:00
swap_cgroup.c
mm: memcontrol: don't allocate cgroup swap arrays when memcg is disabled
2022-10-03 14:03:36 -07:00
swap_slots.c
mm/swap: convert put_swap_page() to put_swap_folio()
2022-10-03 14:02:46 -07:00
swap_state.c
swap_state: update shadow_nodes for anonymous page
2023-02-02 22:33:24 -08:00
swap.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
swap.h
mm: remove the __swap_writepage return value
2023-02-02 22:33:33 -08:00
swapfile.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
truncate.c
folio-compat: remove lru_cache_add()
2022-12-11 18:12:13 -08:00
usercopy.c
mm: use kstrtobool() instead of strtobool()
2022-11-30 15:58:45 -08:00
userfaultfd.c
mm/uffd: detect pgtable allocation failures
2023-01-18 17:12:53 -08:00
util.c
mm: fix typo in __vm_enough_memory warning
2023-02-13 15:54:33 -08:00
vmalloc.c
- Daniel Verkamp has contributed a memfd series ("mm/memfd: add
2023-02-23 17:09:35 -08:00
vmpressure.c
…
vmscan.c
mm: change to return bool for folio_isolate_lru()
2023-02-20 12:46:17 -08:00
vmstat.c
mm: vmscan: split khugepaged stats from direct reclaim stats
2022-11-30 15:58:41 -08:00
workingset.c
swap_state: update shadow_nodes for anonymous page
2023-02-02 22:33:24 -08:00
z3fold.c
mm: remove PageMovable export
2023-01-18 17:12:57 -08:00
zbud.c
zpool: clean out dead code
2022-12-11 18:12:10 -08:00
zpool.c
zpool: clean out dead code
2022-12-11 18:12:10 -08:00
zsmalloc.c
zsmalloc: make zspage chain size configurable
2023-02-02 22:33:23 -08:00
zswap.c
zswap: fix writeback lock ordering for zsmalloc
2022-12-11 18:12:09 -08:00