mirrors
/
linux-stable
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
1
0
Fork 0
Code Issues Releases Wiki Activity
1,060,214 Commits 103 Branches 5,012 Tags 5.4 GiB
C 97.6%
Assembly 1%
Shell 0.5%
Python 0.3%
Makefile 0.3%
Go to file
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
Documentation docs: Correct missing "d_" prefix for dentry_operations member d_weak_revalidate 2023-03-22 13:31:22 +01:00
LICENSES LICENSES/dual/CC-BY-4.0: Git rid of "smart quotes" 2021-07-15 06:31:24 -06:00
arch riscv: asid: Fixup stale TLB entry cause application crash 2023-03-22 13:31:34 +01:00
block block: don't allow multiple bios for IOCB_NOWAIT issue 2023-03-10 09:39:55 +01:00
certs certs/blacklist_hashes.c: fix const confusion in certs blacklist 2022-06-22 14:22:01 +02:00
crypto crypto: rsa-pkcs1pad - Use akcipher_request_complete 2023-03-10 09:39:16 +01:00
drivers ice: avoid bonding causing auxiliary plug/unplug under RTNL lock 2023-03-22 13:31:35 +01:00
fs cifs: Fix smb2_set_path_size() 2023-03-22 13:31:33 +01:00
include tracing: Make tracepoint lockdep check actually test something 2023-03-22 13:31:33 +01:00
init kbuild: Add CONFIG_PAHOLE_VERSION 2023-02-25 12:06:45 +01:00
io_uring io_uring/poll: allow some retries for poll triggering spuriously 2023-03-10 09:40:04 +01:00
ipc ipc/sem: Fix dangling sem_array access in semtimedop race 2022-12-08 11:28:45 +01:00
kernel ftrace: Fix invalid address access in lookup_rec() when index is 0 2023-03-22 13:31:35 +01:00
lib kobject: Fix slab-out-of-bounds in fill_kobj_path() 2023-03-10 09:39:35 +01:00
mm mm/userfaultfd: propagate uffd-wp bit when PTE-mapping the huge zeropage 2023-03-22 13:31:35 +01:00
net mptcp: fix lockdep false positive in mptcp_pm_nl_create_listen_socket() 2023-03-22 13:31:35 +01:00
samples samples: vfio-mdev: Fix missing pci_disable_device() in mdpy_fb_probe() 2022-12-31 13:14:31 +01:00
scripts kconfig: Update config changed flag before calling callback 2023-03-22 13:31:29 +01:00
security ima: Align ima_file_mmap() parameters with mmap_file LSM hook 2023-03-10 09:40:03 +01:00
sound ALSA: hda/realtek: Fix the speaker output on Samsung Galaxy Book2 Pro 2023-03-22 13:31:33 +01:00
tools selftests: net: devlink_port_split.py: skip test if no suitable device available 2023-03-22 13:31:28 +01:00
usr usr/include/Makefile: add linux/nfc.h to the compile-test coverage 2022-02-01 17:27:15 +01:00
virt KVM: fix memoryleak in kvm_init() 2023-03-17 08:49:04 +01:00
.clang-format clang-format: Update with the latest for_each macro list 2021-05-12 23:32:39 +02:00
.cocciconfig
…
.get_maintainer.ignore Opt out of scripts/get_maintainer.pl 2019-05-16 10:53:40 -07:00
.gitattributes .gitattributes: use 'dts' diff driver for dts files 2019-12-04 19:44:11 -08:00
.gitignore .gitignore: ignore only top-level modules.builtin 2021-05-02 00:43:35 +09:00
.mailmap mailmap: add Andrej Shadura 2021-10-18 20:22:03 -10:00
COPYING COPYING: state that all contributions really are covered by this file 2020-02-10 13:32:20 -08:00
CREDITS MAINTAINERS: Move Daniel Drake to credits 2021-09-21 08:34:58 +03:00
Kbuild kbuild: rename hostprogs-y/always to hostprogs/always-y 2020-02-04 01:53:07 +09:00
Kconfig kbuild: ensure full rebuild when the compiler is updated 2020-05-12 13:28:33 +09:00
MAINTAINERS kbuild: Add CONFIG_PAHOLE_VERSION 2023-02-25 12:06:45 +01:00
Makefile Linux 5.15.103 2023-03-17 08:49:05 +01:00
README
…

README 

Linux kernel
============

There are several guides for kernel developers and users. These guides can
be rendered in a number of formats, like HTML and PDF. Please read
Documentation/admin-guide/README.rst first.

In order to build the documentation, use ``make htmldocs`` or
``make pdfdocs``.  The formatted documentation can also be read online at:

    https://www.kernel.org/doc/html/latest/

There are various text files in the Documentation/ subdirectory,
several of them using the Restructured Text markup notation.

Please read the Documentation/process/changes.rst file, as it contains the
requirements for building and running the kernel, and information about
the problems which may result by upgrading your kernel.