microsoft
/
WSL2-Linux-Kernel
зеркало из https://github.com/microsoft/WSL2-Linux-Kernel.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
WSL2-Linux-Kernel/mm
История
David Hildenbrand b02de083c7 mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage 
commit 42b2af2c9b 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: e06f1e1dd4 ("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 13:31:35 +01:00
..
damon mm/damon/dbgfs: check if rm_contexts input is for a real context 2022-11-16 09:58:27 +01:00
kasan panic: Consolidate open-coded panic_on_warn checks 2023-02-01 08:27:22 +01:00
kfence panic: Consolidate open-coded panic_on_warn checks 2023-02-01 08:27:22 +01:00
Kconfig kmap_local: don't assume kmap PTEs are linear arrays in memory 2021-11-25 09:48:43 +01:00
Kconfig.debug mm, page_poison: remove CONFIG_PAGE_POISONING_ZERO 2020-12-15 12:13:46 -08:00
Makefile mm: introduce Data Access MONitor (DAMON) 2021-09-08 11:50:24 -07:00
backing-dev.c writeback: avoid use-after-free after removing device 2022-08-31 17:16:47 +02:00
balloon_compaction.c mm: fix typos in comments 2021-05-07 00:26:35 -07:00
bootmem_info.c bootmem: remove the vmemmap pages from kmemleak in put_page_bootmem 2022-08-31 17:16:48 +02:00
cleancache.c
…
cma.c Revert "mm/cma.c: remove redundant cma_mutex lock" 2022-06-09 10:23:27 +02:00
cma.h mm: cma: support sysfs 2021-05-05 11:27:24 -07:00
cma_debug.c mm/cma: change cma mutex to irq safe spinlock 2021-05-05 11:27:21 -07:00
cma_sysfs.c mm: cma: support sysfs 2021-05-05 11:27:24 -07:00
compaction.c mm, compaction: fix fast_isolate_around() to stay within boundaries 2023-01-12 11:58:47 +01:00
debug.c mm/debug: sync up latest migrate_reason to migrate_reason_names 2021-09-24 16:13:35 -07:00
debug_page_ref.c
…
debug_vm_pgtable.c mm/debug_vm_pgtable: remove pte entry from the page table 2022-02-08 18:34:05 +01:00
dmapool.c mm/dmapool: use DEVICE_ATTR_RO macro 2021-06-29 10:53:52 -07:00
early_ioremap.c mm/early_ioremap.c: remove redundant early_ioremap_shutdown() 2021-09-08 11:50:24 -07:00
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/filemap: fix page end in filemap_get_read_batch 2023-02-22 12:57:10 +01:00
frontswap.c mm/mempool: minor coding style tweaks 2021-05-05 11:27:27 -07:00
gup.c mm/migration: return errno when isolate_huge_page failed 2023-02-14 19:17:56 +01:00
gup_test.c selftests/vm: gup_test: test faulting in kernel, and verify pinnable pages 2021-05-05 11:27:26 -07:00
gup_test.h selftests/vm: gup_test: fix test flag 2021-05-05 11:27:26 -07:00
highmem.c highmem: fix checks in __kmap_local_sched_{in,out} 2022-04-13 20:59:21 +02:00
hmm.c mm/hmm: fault non-owner device private entries 2022-08-03 12:03:54 +02:00
huge_memory.c mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage 2023-03-22 13:31:35 +01:00
hugetlb.c mm/migration: return errno when isolate_huge_page failed 2023-02-14 19:17:56 +01:00
hugetlb_cgroup.c hugetlb: make free_huge_page irq safe 2021-05-05 11:27:22 -07:00
hugetlb_vmemmap.c mm: hugetlb: introduce CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON 2021-06-30 20:47:26 -07:00
hugetlb_vmemmap.h mm: hugetlb: introduce nr_free_vmemmap_pages in the struct hstate 2021-06-30 20:47:25 -07:00
hwpoison-inject.c mm/hwpoison: avoid the impact of hwpoison_filter() return value on mce handler 2022-07-12 16:35:05 +02:00
init-mm.c mm: add setup_initial_init_mm() helper 2021-07-08 11:48:21 -07:00
internal.h mm/numa: automatically generate node migration order 2021-09-03 09:58:16 -07:00
interval_tree.c mm/interval_tree: add comments to improve code readability 2021-04-30 11:20:38 -07:00
io-mapping.c mm: add a io_mapping_map_user helper 2021-04-30 11:20:39 -07:00
ioremap.c mm: move ioremap_page_range to vmalloc.c 2021-09-08 11:50:24 -07:00
khugepaged.c mm/khugepaged: fix collapse_pte_mapped_thp() to allow anon_vma 2023-01-24 07:22:49 +01:00
kmemleak.c Revert "mm: kmemleak: take a full lowmem check in kmemleak_*_phys()" 2022-09-15 11:30:00 +02:00
ksm.c mm/ksm: remove old GCC 4.9+ check 2021-09-13 10:18:28 -07:00
list_lru.c mm: vmscan: consolidate shrinker_maps handling code 2021-05-05 11:27:23 -07:00
maccess.c maccess: Fix writing offset in case of fault in strncpy_from_kernel_nofault() 2022-11-26 09:24:47 +01:00
madvise.c mm: fix madivse_pageout mishandling on non-LRU page 2022-10-05 10:39:39 +02:00
mapping_dirty_helpers.c mm/mapping_dirty_helpers: remove double Note in kerneldoc 2021-07-01 11:06:02 -07:00
memblock.c Revert "mm: Always release pages to the buddy allocator in memblock_free_late()." 2023-02-22 12:57:07 +01:00
memcontrol.c mm: memcontrol: deprecate charge moving 2023-03-10 09:40:09 +01:00
memfd.c memfd: fix F_SEAL_WRITE after shmem huge page allocated 2022-03-08 19:12:48 +01:00
memory-failure.c mm/migration: return errno when isolate_huge_page failed 2023-02-14 19:17:56 +01:00
memory.c mm: fix page leak with multiple threads mapping the same page 2022-08-03 12:03:42 +02:00
memory_hotplug.c mm/migration: return errno when isolate_huge_page failed 2023-02-14 19:17:56 +01:00
mempolicy.c migrate: hugetlb: check for hugetlb shared PMD in node migration 2023-02-14 19:17:56 +01:00
mempool.c kasan: use separate (un)poison implementation for integrated init 2021-06-04 19:32:21 +01:00
memremap.c mm/memremap.c: map FS_DAX device memory as decrypted 2022-11-16 09:58:27 +01:00
memtest.c
…
migrate.c mm/migration: return errno when isolate_huge_page failed 2023-02-14 19:17:56 +01:00
mincore.c inode: make init and permission helpers idmapped mount aware 2021-01-24 14:27:16 +01:00
mlock.c mm/mlock: fix potential imbalanced rlimit ucounts adjustment 2022-05-15 20:18:53 +02:00
mm_init.c include/linux/page-flags-layout.h: cleanups 2021-04-30 11:20:42 -07:00
mmap.c mm/mmap: undo ->mmap() when arch_validate_flags() fails 2022-10-26 12:34:24 +02:00
mmap_lock.c mm: mmap_lock: fix disabling preemption directly 2021-07-23 17:43:28 -07:00
mmu_gather.c mm/khugepaged: fix GUP-fast interaction by sending IPI 2022-12-14 11:37:17 +01:00
mmu_notifier.c mm/mmu_notifier.c: fix race in mmu_interval_notifier_remove() 2022-04-27 14:38:58 +02:00
mmzone.c mm/lru: replace pgdat lru_lock with lruvec lock 2020-12-15 14:48:04 -08:00
mprotect.c mm: don't try to NUMA-migrate COW pages that have other uses 2022-02-23 12:03:03 +01:00
mremap.c mmmremap.c: avoid pointless invalidate_range_start/end on mremap(old_size=0) 2022-04-13 20:59:22 +02:00
msync.c mm/msync: exit early when the flags is an MS_ASYNC and start < vm_start 2021-04-30 11:20:37 -07:00
nommu.c Merge tag 'denywrite-for-5.15' of git://github.com/davidhildenbrand/linux 2021-09-04 11:35:47 -07:00
oom_kill.c oom_kill.c: futex: delay the OOM reaper to allow time for proper futex cleanup 2022-04-27 14:38:58 +02:00
page-writeback.c writeback: avoid use-after-free after removing device 2022-08-31 17:16:47 +02:00
page_alloc.c Fix page corruption caused by racy check in __free_pages 2023-02-14 19:18:04 +01:00
page_counter.c mm: page_counter: mitigate consequences of a page_counter underflow 2021-04-30 11:20:38 -07:00
page_ext.c mm/migrate: add CPU hotplug to demotion #ifdef 2021-10-18 20:22:02 -10:00
page_idle.c mm/idle_page_tracking: make PG_idle reusable 2021-09-08 11:50:24 -07:00
page_io.c mm: fix unexpected zeroed page mapping with zram swap 2022-04-20 09:34:18 +02:00
page_isolation.c Merge branch 'akpm' (patches from Andrew) 2021-09-08 12:55:35 -07:00
page_owner.c mm: remove pfn_valid_within() and CONFIG_HOLES_IN_ZONE 2021-09-08 11:50:22 -07:00
page_poison.c mm: page_poison: print page info when corruption is caught 2021-04-30 11:20:36 -07:00
page_reporting.c mm/page_reporting: allow driver to specify reporting order 2021-06-29 10:53:47 -07:00
page_reporting.h mm/page_reporting: export reporting order as module parameter 2021-06-29 10:53:47 -07:00
page_vma_mapped.c mm: device exclusive memory access 2021-07-01 11:06:03 -07:00
pagewalk.c mm: pagewalk: Fix race between unmap and page walker 2022-09-08 12:28:05 +02:00
percpu-internal.h Merge branch 'for-5.14' of git://git.kernel.org/pub/scm/linux/kernel/git/dennis/percpu 2021-07-01 17:17:24 -07:00
percpu-km.c percpu: flush tlb in pcpu_reclaim_populated() 2021-07-04 18:30:17 +00:00
percpu-stats.c percpu: rework memcg accounting 2021-06-05 20:43:15 +00:00
percpu-vm.c percpu: flush tlb in pcpu_reclaim_populated() 2021-07-04 18:30:17 +00:00
percpu.c Merge branch 'akpm' (patches from Andrew) 2021-09-08 12:55:35 -07:00
pgalloc-track.h mm: fix typos in comments 2021-05-07 00:26:35 -07:00
pgtable-generic.c mm/thp: fix __split_huge_pmd_locked() on shmem migration entry 2021-06-16 09:24:42 -07:00
process_vm_access.c mm/process_vm_access.c: remove duplicate include 2021-05-05 11:27:27 -07:00
ptdump.c mm: pagewalk: Fix race between unmap and page walker 2022-09-08 12:28:05 +02:00
readahead.c mm: Protect operations adding pages to page cache with invalidate_lock 2021-07-13 13:14:27 +02:00
rmap.c mm/rmap: Fix anon_vma->degree ambiguity leading to double-reuse 2022-09-05 10:30:07 +02:00
rodata_test.c mm/rodata_test.c: fix missing function declaration 2020-08-21 09:52:53 -07:00
secretmem.c mm: fix dereferencing possible ERR_PTR 2022-10-05 10:39:39 +02:00
shmem.c mm: shmem: don't truncate page if memory failure happens 2022-11-26 09:24:28 +01:00
shuffle.c mm: eliminate "expecting prototype" kernel-doc warnings 2021-04-16 16:10:36 -07:00
shuffle.h mm/shuffle: fix section mismatch warning 2021-05-22 15:09:07 -10:00
slab.c mm, kfence: support kmem_dump_obj() for KFENCE objects 2022-04-27 14:38:51 +02:00
slab.h mm, kfence: support kmem_dump_obj() for KFENCE objects 2022-04-27 14:38:51 +02:00
slab_common.c mm, kfence: support kmem_dump_obj() for KFENCE objects 2022-04-27 14:38:51 +02:00
slob.c mm, kfence: support kmem_dump_obj() for KFENCE objects 2022-04-27 14:38:51 +02:00
slub.c mm: slub: fix flush_cpu_slab()/__free_slab() invocations in task context. 2022-09-28 11:11:44 +02:00
sparse-vmemmap.c mm: sparsemem: split the huge PMD mapping of vmemmap pages 2021-06-30 20:47:26 -07:00
sparse.c mm: introduce memmap_alloc() to unify memory map allocation 2021-09-03 09:58:15 -07:00
swap.c mm: fs: invalidate bh_lrus for only cold path 2021-09-24 16:13:35 -07:00
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: Replace deprecated CPU-hotplug functions. 2021-08-28 01:46:17 +02:00
swap_state.c mm: swap: get rid of livelock in swapin readahead 2022-03-23 09:16:41 +01:00
swapfile.c mm/swapfile: add cond_resched() in get_swap_pages() 2023-02-09 11:26:45 +01:00
truncate.c Merge branch 'akpm' (patches from Andrew) 2021-09-03 10:08:28 -07:00
usercopy.c mm/usercopy: return 1 from hardened_usercopy __setup() handler 2022-04-08 14:24:14 +02:00
userfaultfd.c mm: shmem: don't truncate page if memory failure happens 2022-11-26 09:24:28 +01:00
util.c mm: vmalloc: introduce array allocation functions 2022-07-12 16:35:01 +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: defer kmemleak object creation of module_alloc() 2022-03-08 19:12:38 +01:00
vmpressure.c mm/vmpressure: replace vmpressure_to_css() with vmpressure_to_memcg() 2021-09-03 09:58:17 -07:00
vmscan.c mm: __isolate_lru_page_prepare() in isolate_migratepages_block() 2022-12-08 11:28:44 +01:00
vmstat.c mm/vmstat: protect per cpu variables with preempt disable on RT 2021-09-08 15:32:34 -07:00
workingset.c memcg: sync flush only if periodic flush is delayed 2022-04-27 14:38:57 +02:00
z3fold.c mm/z3fold: add kerneldoc fields for z3fold_pool 2021-07-01 11:06:03 -07:00
zbud.c mm/zbud: add kerneldoc fields for zbud_pool 2021-07-01 11:06:03 -07:00
zpool.c mm: fix typos in comments 2021-05-07 00:26:35 -07:00
zsmalloc.c zsmalloc: fix races between asynchronous zspage free and page migration 2022-06-06 08:43:39 +02:00
zswap.c mm/zswap.c: fix two bugs in zswap_writeback_entry() 2021-06-30 20:47:31 -07:00