2019-06-04 01:11:32 -07:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* fs/userfaultfd.c
|
|
|
|
*
|
|
|
|
* Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
|
|
|
|
* Copyright (C) 2008-2009 Red Hat, Inc.
|
|
|
|
* Copyright (C) 2015 Red Hat, Inc.
|
|
|
|
*
|
|
|
|
* Some part derived from fs/eventfd.c (anon inode setup) and
|
|
|
|
* mm/ksm.c (mm hashing).
|
|
|
|
*/
|
|
|
|
|
2017-02-22 16:42:21 -07:00
|
|
|
#include <linux/list.h>
|
2015-09-04 15:46:31 -07:00
|
|
|
#include <linux/hashtable.h>
|
2017-02-02 11:15:33 -07:00
|
|
|
#include <linux/sched/signal.h>
|
2017-02-08 10:51:29 -07:00
|
|
|
#include <linux/sched/mm.h>
|
2015-09-04 15:46:31 -07:00
|
|
|
#include <linux/mm.h>
|
2022-01-14 15:06:07 -07:00
|
|
|
#include <linux/mm_inline.h>
|
2021-05-04 18:33:13 -07:00
|
|
|
#include <linux/mmu_notifier.h>
|
2015-09-04 15:46:31 -07:00
|
|
|
#include <linux/poll.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/seq_file.h>
|
|
|
|
#include <linux/file.h>
|
|
|
|
#include <linux/bug.h>
|
|
|
|
#include <linux/anon_inodes.h>
|
|
|
|
#include <linux/syscalls.h>
|
|
|
|
#include <linux/userfaultfd_k.h>
|
|
|
|
#include <linux/mempolicy.h>
|
|
|
|
#include <linux/ioctl.h>
|
|
|
|
#include <linux/security.h>
|
2017-02-22 16:43:04 -07:00
|
|
|
#include <linux/hugetlb.h>
|
2022-05-12 20:22:52 -07:00
|
|
|
#include <linux/swapops.h>
|
userfaultfd: add /dev/userfaultfd for fine grained access control
Historically, it has been shown that intercepting kernel faults with
userfaultfd (thereby forcing the kernel to wait for an arbitrary amount of
time) can be exploited, or at least can make some kinds of exploits
easier. So, in 37cd0575b8 "userfaultfd: add UFFD_USER_MODE_ONLY" we
changed things so, in order for kernel faults to be handled by
userfaultfd, either the process needs CAP_SYS_PTRACE, or this sysctl must
be configured so that any unprivileged user can do it.
In a typical implementation of a hypervisor with live migration (take
QEMU/KVM as one such example), we do indeed need to be able to handle
kernel faults. But, both options above are less than ideal:
- Toggling the sysctl increases attack surface by allowing any
unprivileged user to do it.
- Granting the live migration process CAP_SYS_PTRACE gives it this
ability, but *also* the ability to "observe and control the
execution of another process [...], and examine and change [its]
memory and registers" (from ptrace(2)). This isn't something we need
or want to be able to do, so granting this permission violates the
"principle of least privilege".
This is all a long winded way to say: we want a more fine-grained way to
grant access to userfaultfd, without granting other additional permissions
at the same time.
To achieve this, add a /dev/userfaultfd misc device. This device provides
an alternative to the userfaultfd(2) syscall for the creation of new
userfaultfds. The idea is, any userfaultfds created this way will be able
to handle kernel faults, without the caller having any special
capabilities. Access to this mechanism is instead restricted using e.g.
standard filesystem permissions.
[axelrasmussen@google.com: Handle misc_register() failure properly]
Link: https://lkml.kernel.org/r/20220819205201.658693-3-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20220808175614.3885028-3-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-08-08 10:56:11 -07:00
|
|
|
#include <linux/miscdevice.h>
|
2024-04-02 11:26:41 -07:00
|
|
|
#include <linux/uio.h>
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2023-03-01 03:06:27 -07:00
|
|
|
static int sysctl_unprivileged_userfaultfd __read_mostly;
|
|
|
|
|
|
|
|
#ifdef CONFIG_SYSCTL
|
|
|
|
static struct ctl_table vm_userfaultfd_table[] = {
|
|
|
|
{
|
|
|
|
.procname = "unprivileged_userfaultfd",
|
|
|
|
.data = &sysctl_unprivileged_userfaultfd,
|
|
|
|
.maxlen = sizeof(sysctl_unprivileged_userfaultfd),
|
|
|
|
.mode = 0644,
|
|
|
|
.proc_handler = proc_dointvec_minmax,
|
|
|
|
.extra1 = SYSCTL_ZERO,
|
|
|
|
.extra2 = SYSCTL_ONE,
|
|
|
|
},
|
|
|
|
};
|
|
|
|
#endif
|
userfaultfd/sysctl: add vm.unprivileged_userfaultfd
Userfaultfd can be misued to make it easier to exploit existing
use-after-free (and similar) bugs that might otherwise only make a
short window or race condition available. By using userfaultfd to
stall a kernel thread, a malicious program can keep some state that it
wrote, stable for an extended period, which it can then access using an
existing exploit. While it doesn't cause the exploit itself, and while
it's not the only thing that can stall a kernel thread when accessing a
memory location, it's one of the few that never needs privilege.
We can add a flag, allowing userfaultfd to be restricted, so that in
general it won't be useable by arbitrary user programs, but in
environments that require userfaultfd it can be turned back on.
Add a global sysctl knob "vm.unprivileged_userfaultfd" to control
whether userfaultfd is allowed by unprivileged users. When this is
set to zero, only privileged users (root user, or users with the
CAP_SYS_PTRACE capability) will be able to use the userfaultfd
syscalls.
Andrea said:
: The only difference between the bpf sysctl and the userfaultfd sysctl
: this way is that the bpf sysctl adds the CAP_SYS_ADMIN capability
: requirement, while userfaultfd adds the CAP_SYS_PTRACE requirement,
: because the userfaultfd monitor is more likely to need CAP_SYS_PTRACE
: already if it's doing other kind of tracking on processes runtime, in
: addition of userfaultfd. In other words both syscalls works only for
: root, when the two sysctl are opt-in set to 1.
[dgilbert@redhat.com: changelog additions]
[akpm@linux-foundation.org: documentation tweak, per Mike]
Link: http://lkml.kernel.org/r/20190319030722.12441-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Suggested-by: Andrea Arcangeli <aarcange@redhat.com>
Suggested-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: Maya Gokhale <gokhale2@llnl.gov>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Martin Cracauer <cracauer@cons.org>
Cc: Denis Plotnikov <dplotnikov@virtuozzo.com>
Cc: Marty McFadden <mcfadden8@llnl.gov>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: "Kirill A . Shutemov" <kirill@shutemov.name>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-13 17:16:41 -07:00
|
|
|
|
2023-10-11 09:55:00 -07:00
|
|
|
static struct kmem_cache *userfaultfd_ctx_cachep __ro_after_init;
|
2015-09-04 15:46:48 -07:00
|
|
|
|
2017-02-22 16:42:27 -07:00
|
|
|
struct userfaultfd_fork_ctx {
|
|
|
|
struct userfaultfd_ctx *orig;
|
|
|
|
struct userfaultfd_ctx *new;
|
|
|
|
struct list_head list;
|
|
|
|
};
|
|
|
|
|
2017-02-24 15:58:22 -07:00
|
|
|
struct userfaultfd_unmap_ctx {
|
|
|
|
struct userfaultfd_ctx *ctx;
|
|
|
|
unsigned long start;
|
|
|
|
unsigned long end;
|
|
|
|
struct list_head list;
|
|
|
|
};
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
struct userfaultfd_wait_queue {
|
2015-09-04 15:46:37 -07:00
|
|
|
struct uffd_msg msg;
|
2017-06-20 03:06:13 -07:00
|
|
|
wait_queue_entry_t wq;
|
2015-09-04 15:46:31 -07:00
|
|
|
struct userfaultfd_ctx *ctx;
|
userfaultfd: fix SIGBUS resulting from false rwsem wakeups
With >=32 CPUs the userfaultfd selftest triggered a graceful but
unexpected SIGBUS because VM_FAULT_RETRY was returned by
handle_userfault() despite the UFFDIO_COPY wasn't completed.
This seems caused by rwsem waking the thread blocked in
handle_userfault() and we can't run up_read() before the wait_event
sequence is complete.
Keeping the wait_even sequence identical to the first one, would require
running userfaultfd_must_wait() again to know if the loop should be
repeated, and it would also require retaking the rwsem and revalidating
the whole vma status.
It seems simpler to wait the targeted wakeup so that if false wakeups
materialize we still wait for our specific wakeup event, unless of
course there are signals or the uffd was released.
Debug code collecting the stack trace of the wakeup showed this:
$ ./userfaultfd 100 99999
nr_pages: 25600, nr_pages_per_cpu: 800
bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2
bounces: 99997, mode: rnd ver poll, Bus error (core dumped)
save_stack_trace+0x2b/0x50
try_to_wake_up+0x2a6/0x580
wake_up_q+0x32/0x70
rwsem_wake+0xe0/0x120
call_rwsem_wake+0x1b/0x30
up_write+0x3b/0x40
vm_mmap_pgoff+0x9c/0xc0
SyS_mmap_pgoff+0x1a9/0x240
SyS_mmap+0x22/0x30
entry_SYSCALL_64_fastpath+0x1f/0xbd
0xffffffffffffffff
FAULT_FLAG_ALLOW_RETRY missing 70
CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
Call Trace:
dump_stack+0xb8/0x112
handle_userfault+0x572/0x650
handle_mm_fault+0x12cb/0x1520
__do_page_fault+0x175/0x500
trace_do_page_fault+0x61/0x270
do_async_page_fault+0x19/0x90
async_page_fault+0x25/0x30
This always happens when the main userfault selftest thread is running
clone() while glibc runs either mprotect or mmap (both taking mmap_sem
down_write()) to allocate the thread stack of the background threads,
while locking/userfault threads already run at full throttle and are
susceptible to false wakeups that may cause handle_userfault() to return
before than expected (which results in graceful SIGBUS at the next
attempt).
This was reproduced only with >=32 CPUs because the loop to start the
thread where clone() is too quick with fewer CPUs, while with 32 CPUs
there's already significant activity on ~32 locking and userfault
threads when the last background threads are started with clone().
This >=32 CPUs SMP race condition is likely reproducible only with the
selftest because of the much heavier userfault load it generates if
compared to real apps.
We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a
patch floating around that provides it also hidden this problem but in
reality only is successfully at hiding the problem.
False wakeups could still happen again the second time
handle_userfault() is invoked, even if it's a so rare race condition
that getting false wakeups twice in a row is impossible to reproduce.
This full fix is needed for correctness, the only alternative would be
to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP
support can stick to a strict "one more" VM_FAULT_RETRY logic (no need
of returning it infinite times to avoid the SIGBUS).
Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-24 16:17:59 -07:00
|
|
|
bool waken;
|
2015-09-04 15:46:31 -07:00
|
|
|
};
|
|
|
|
|
|
|
|
struct userfaultfd_wake_range {
|
|
|
|
unsigned long start;
|
|
|
|
unsigned long len;
|
|
|
|
};
|
|
|
|
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
/* internal indication that UFFD_API ioctl was successfully executed */
|
|
|
|
#define UFFD_FEATURE_INITIALIZED (1u << 31)
|
|
|
|
|
|
|
|
static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
|
|
|
|
{
|
|
|
|
return ctx->features & UFFD_FEATURE_INITIALIZED;
|
|
|
|
}
|
|
|
|
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
static bool userfaultfd_wp_async_ctx(struct userfaultfd_ctx *ctx)
|
|
|
|
{
|
|
|
|
return ctx && (ctx->features & UFFD_FEATURE_WP_ASYNC);
|
|
|
|
}
|
|
|
|
|
mm/uffd: UFFD_FEATURE_WP_UNPOPULATED
Patch series "mm/uffd: Add feature bit UFFD_FEATURE_WP_UNPOPULATED", v4.
The new feature bit makes anonymous memory acts the same as file memory on
userfaultfd-wp in that it'll also wr-protect none ptes.
It can be useful in two cases:
(1) Uffd-wp app that needs to wr-protect none ptes like QEMU snapshot,
so pre-fault can be replaced by enabling this flag and speed up
protections
(2) It helps to implement async uffd-wp mode that Muhammad is working on [1]
It's debatable whether this is the most ideal solution because with the
new feature bit set, wr-protect none pte needs to pre-populate the
pgtables to the last level (PAGE_SIZE). But it seems fine so far to
service either purpose above, so we can leave optimizations for later.
The series brings pte markers to anonymous memory too. There's some
change in the common mm code path in the 1st patch, great to have some eye
looking at it, but hopefully they're still relatively straightforward.
This patch (of 2):
This is a new feature that controls how uffd-wp handles none ptes. When
it's set, the kernel will handle anonymous memory the same way as file
memory, by allowing the user to wr-protect unpopulated ptes.
File memories handles none ptes consistently by allowing wr-protecting of
none ptes because of the unawareness of page cache being exist or not.
For anonymous it was not as persistent because we used to assume that we
don't need protections on none ptes or known zero pages.
One use case of such a feature bit was VM live snapshot, where if without
wr-protecting empty ptes the snapshot can contain random rubbish in the
holes of the anonymous memory, which can cause misbehave of the guest when
the guest OS assumes the pages should be all zeros.
QEMU worked it around by pre-populate the section with reads to fill in
zero page entries before starting the whole snapshot process [1].
Recently there's another need raised on using userfaultfd wr-protect for
detecting dirty pages (to replace soft-dirty in some cases) [2]. In that
case if without being able to wr-protect none ptes by default, the dirty
info can get lost, since we cannot treat every none pte to be dirty (the
current design is identify a page dirty based on uffd-wp bit being
cleared).
In general, we want to be able to wr-protect empty ptes too even for
anonymous.
This patch implements UFFD_FEATURE_WP_UNPOPULATED so that it'll make
uffd-wp handling on none ptes being consistent no matter what the memory
type is underneath. It doesn't have any impact on file memories so far
because we already have pte markers taking care of that. So it only
affects anonymous.
The feature bit is by default off, so the old behavior will be maintained.
Sometimes it may be wanted because the wr-protect of none ptes will
contain overheads not only during UFFDIO_WRITEPROTECT (by applying pte
markers to anonymous), but also on creating the pgtables to store the pte
markers. So there's potentially less chance of using thp on the first
fault for a none pmd or larger than a pmd.
The major implementation part is teaching the whole kernel to understand
pte markers even for anonymously mapped ranges, meanwhile allowing the
UFFDIO_WRITEPROTECT ioctl to apply pte markers for anonymous too when the
new feature bit is set.
Note that even if the patch subject starts with mm/uffd, there're a few
small refactors to major mm path of handling anonymous page faults. But
they should be straightforward.
With WP_UNPOPUATED, application like QEMU can avoid pre-read faults all
the memory before wr-protect during taking a live snapshot. Quotting from
Muhammad's test result here [3] based on a simple program [4]:
(1) With huge page disabled
echo madvise > /sys/kernel/mm/transparent_hugepage/enabled
./uffd_wp_perf
Test DEFAULT: 4
Test PRE-READ: 1111453 (pre-fault 1101011)
Test MADVISE: 278276 (pre-fault 266378)
Test WP-UNPOPULATE: 11712
(2) With Huge page enabled
echo always > /sys/kernel/mm/transparent_hugepage/enabled
./uffd_wp_perf
Test DEFAULT: 4
Test PRE-READ: 22521 (pre-fault 22348)
Test MADVISE: 4909 (pre-fault 4743)
Test WP-UNPOPULATE: 14448
There'll be a great perf boost for no-thp case, while for thp enabled with
extreme case of all-thp-zero WP_UNPOPULATED can be slower than MADVISE,
but that's low possibility in reality, also the overhead was not reduced
but postponed until a follow up write on any huge zero thp, so potentially
it is faster by making the follow up writes slower.
[1] https://lore.kernel.org/all/20210401092226.102804-4-andrey.gruzdev@virtuozzo.com/
[2] https://lore.kernel.org/all/Y+v2HJ8+3i%2FKzDBu@x1n/
[3] https://lore.kernel.org/all/d0eb0a13-16dc-1ac1-653a-78b7273781e3@collabora.com/
[4] https://github.com/xzpeter/clibs/blob/master/uffd-test/uffd-wp-perf.c
[peterx@redhat.com: comment changes, oneliner fix to khugepaged]
Link: https://lkml.kernel.org/r/ZB2/8jPhD3fpx5U8@x1n
Link: https://lkml.kernel.org/r/20230309223711.823547-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20230309223711.823547-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-03-09 15:37:10 -07:00
|
|
|
/*
|
|
|
|
* Whether WP_UNPOPULATED is enabled on the uffd context. It is only
|
|
|
|
* meaningful when userfaultfd_wp()==true on the vma and when it's
|
|
|
|
* anonymous.
|
|
|
|
*/
|
|
|
|
bool userfaultfd_wp_unpopulated(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
|
|
|
|
|
|
|
|
if (!ctx)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return ctx->features & UFFD_FEATURE_WP_UNPOPULATED;
|
|
|
|
}
|
|
|
|
|
2017-06-20 03:06:13 -07:00
|
|
|
static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
|
2015-09-04 15:46:31 -07:00
|
|
|
int wake_flags, void *key)
|
|
|
|
{
|
|
|
|
struct userfaultfd_wake_range *range = key;
|
|
|
|
int ret;
|
|
|
|
struct userfaultfd_wait_queue *uwq;
|
|
|
|
unsigned long start, len;
|
|
|
|
|
|
|
|
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
|
|
|
|
ret = 0;
|
|
|
|
/* len == 0 means wake all */
|
|
|
|
start = range->start;
|
|
|
|
len = range->len;
|
2015-09-04 15:46:37 -07:00
|
|
|
if (len && (start > uwq->msg.arg.pagefault.address ||
|
|
|
|
start + len <= uwq->msg.arg.pagefault.address))
|
2015-09-04 15:46:31 -07:00
|
|
|
goto out;
|
userfaultfd: fix SIGBUS resulting from false rwsem wakeups
With >=32 CPUs the userfaultfd selftest triggered a graceful but
unexpected SIGBUS because VM_FAULT_RETRY was returned by
handle_userfault() despite the UFFDIO_COPY wasn't completed.
This seems caused by rwsem waking the thread blocked in
handle_userfault() and we can't run up_read() before the wait_event
sequence is complete.
Keeping the wait_even sequence identical to the first one, would require
running userfaultfd_must_wait() again to know if the loop should be
repeated, and it would also require retaking the rwsem and revalidating
the whole vma status.
It seems simpler to wait the targeted wakeup so that if false wakeups
materialize we still wait for our specific wakeup event, unless of
course there are signals or the uffd was released.
Debug code collecting the stack trace of the wakeup showed this:
$ ./userfaultfd 100 99999
nr_pages: 25600, nr_pages_per_cpu: 800
bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2
bounces: 99997, mode: rnd ver poll, Bus error (core dumped)
save_stack_trace+0x2b/0x50
try_to_wake_up+0x2a6/0x580
wake_up_q+0x32/0x70
rwsem_wake+0xe0/0x120
call_rwsem_wake+0x1b/0x30
up_write+0x3b/0x40
vm_mmap_pgoff+0x9c/0xc0
SyS_mmap_pgoff+0x1a9/0x240
SyS_mmap+0x22/0x30
entry_SYSCALL_64_fastpath+0x1f/0xbd
0xffffffffffffffff
FAULT_FLAG_ALLOW_RETRY missing 70
CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
Call Trace:
dump_stack+0xb8/0x112
handle_userfault+0x572/0x650
handle_mm_fault+0x12cb/0x1520
__do_page_fault+0x175/0x500
trace_do_page_fault+0x61/0x270
do_async_page_fault+0x19/0x90
async_page_fault+0x25/0x30
This always happens when the main userfault selftest thread is running
clone() while glibc runs either mprotect or mmap (both taking mmap_sem
down_write()) to allocate the thread stack of the background threads,
while locking/userfault threads already run at full throttle and are
susceptible to false wakeups that may cause handle_userfault() to return
before than expected (which results in graceful SIGBUS at the next
attempt).
This was reproduced only with >=32 CPUs because the loop to start the
thread where clone() is too quick with fewer CPUs, while with 32 CPUs
there's already significant activity on ~32 locking and userfault
threads when the last background threads are started with clone().
This >=32 CPUs SMP race condition is likely reproducible only with the
selftest because of the much heavier userfault load it generates if
compared to real apps.
We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a
patch floating around that provides it also hidden this problem but in
reality only is successfully at hiding the problem.
False wakeups could still happen again the second time
handle_userfault() is invoked, even if it's a so rare race condition
that getting false wakeups twice in a row is impossible to reproduce.
This full fix is needed for correctness, the only alternative would be
to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP
support can stick to a strict "one more" VM_FAULT_RETRY logic (no need
of returning it infinite times to avoid the SIGBUS).
Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-24 16:17:59 -07:00
|
|
|
WRITE_ONCE(uwq->waken, true);
|
|
|
|
/*
|
2017-06-07 08:51:27 -07:00
|
|
|
* The Program-Order guarantees provided by the scheduler
|
|
|
|
* ensure uwq->waken is visible before the task is woken.
|
userfaultfd: fix SIGBUS resulting from false rwsem wakeups
With >=32 CPUs the userfaultfd selftest triggered a graceful but
unexpected SIGBUS because VM_FAULT_RETRY was returned by
handle_userfault() despite the UFFDIO_COPY wasn't completed.
This seems caused by rwsem waking the thread blocked in
handle_userfault() and we can't run up_read() before the wait_event
sequence is complete.
Keeping the wait_even sequence identical to the first one, would require
running userfaultfd_must_wait() again to know if the loop should be
repeated, and it would also require retaking the rwsem and revalidating
the whole vma status.
It seems simpler to wait the targeted wakeup so that if false wakeups
materialize we still wait for our specific wakeup event, unless of
course there are signals or the uffd was released.
Debug code collecting the stack trace of the wakeup showed this:
$ ./userfaultfd 100 99999
nr_pages: 25600, nr_pages_per_cpu: 800
bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2
bounces: 99997, mode: rnd ver poll, Bus error (core dumped)
save_stack_trace+0x2b/0x50
try_to_wake_up+0x2a6/0x580
wake_up_q+0x32/0x70
rwsem_wake+0xe0/0x120
call_rwsem_wake+0x1b/0x30
up_write+0x3b/0x40
vm_mmap_pgoff+0x9c/0xc0
SyS_mmap_pgoff+0x1a9/0x240
SyS_mmap+0x22/0x30
entry_SYSCALL_64_fastpath+0x1f/0xbd
0xffffffffffffffff
FAULT_FLAG_ALLOW_RETRY missing 70
CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
Call Trace:
dump_stack+0xb8/0x112
handle_userfault+0x572/0x650
handle_mm_fault+0x12cb/0x1520
__do_page_fault+0x175/0x500
trace_do_page_fault+0x61/0x270
do_async_page_fault+0x19/0x90
async_page_fault+0x25/0x30
This always happens when the main userfault selftest thread is running
clone() while glibc runs either mprotect or mmap (both taking mmap_sem
down_write()) to allocate the thread stack of the background threads,
while locking/userfault threads already run at full throttle and are
susceptible to false wakeups that may cause handle_userfault() to return
before than expected (which results in graceful SIGBUS at the next
attempt).
This was reproduced only with >=32 CPUs because the loop to start the
thread where clone() is too quick with fewer CPUs, while with 32 CPUs
there's already significant activity on ~32 locking and userfault
threads when the last background threads are started with clone().
This >=32 CPUs SMP race condition is likely reproducible only with the
selftest because of the much heavier userfault load it generates if
compared to real apps.
We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a
patch floating around that provides it also hidden this problem but in
reality only is successfully at hiding the problem.
False wakeups could still happen again the second time
handle_userfault() is invoked, even if it's a so rare race condition
that getting false wakeups twice in a row is impossible to reproduce.
This full fix is needed for correctness, the only alternative would be
to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP
support can stick to a strict "one more" VM_FAULT_RETRY logic (no need
of returning it infinite times to avoid the SIGBUS).
Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-24 16:17:59 -07:00
|
|
|
*/
|
2015-09-04 15:46:31 -07:00
|
|
|
ret = wake_up_state(wq->private, mode);
|
2017-06-07 08:51:27 -07:00
|
|
|
if (ret) {
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* Wake only once, autoremove behavior.
|
|
|
|
*
|
2017-06-07 08:51:27 -07:00
|
|
|
* After the effect of list_del_init is visible to the other
|
|
|
|
* CPUs, the waitqueue may disappear from under us, see the
|
|
|
|
* !list_empty_careful() in handle_userfault().
|
|
|
|
*
|
|
|
|
* try_to_wake_up() has an implicit smp_mb(), and the
|
|
|
|
* wq->private is read before calling the extern function
|
|
|
|
* "wake_up_state" (which in turns calls try_to_wake_up).
|
2015-09-04 15:46:31 -07:00
|
|
|
*/
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
list_del_init(&wq->entry);
|
2017-06-07 08:51:27 -07:00
|
|
|
}
|
2015-09-04 15:46:31 -07:00
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
|
|
|
|
* context.
|
|
|
|
* @ctx: [in] Pointer to the userfaultfd context.
|
|
|
|
*/
|
|
|
|
static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
|
|
|
|
{
|
2018-12-28 01:34:43 -07:00
|
|
|
refcount_inc(&ctx->refcount);
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* userfaultfd_ctx_put - Releases a reference to the internal userfaultfd
|
|
|
|
* context.
|
|
|
|
* @ctx: [in] Pointer to userfaultfd context.
|
|
|
|
*
|
|
|
|
* The userfaultfd context reference must have been previously acquired either
|
|
|
|
* with userfaultfd_ctx_get() or userfaultfd_ctx_fdget().
|
|
|
|
*/
|
|
|
|
static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
|
|
|
|
{
|
2018-12-28 01:34:43 -07:00
|
|
|
if (refcount_dec_and_test(&ctx->refcount)) {
|
2015-09-04 15:46:31 -07:00
|
|
|
VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock));
|
|
|
|
VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh));
|
|
|
|
VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock));
|
|
|
|
VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
|
2017-02-22 16:42:21 -07:00
|
|
|
VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
|
|
|
|
VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
|
2015-09-04 15:46:31 -07:00
|
|
|
VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
|
|
|
|
VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
|
2016-05-20 16:58:36 -07:00
|
|
|
mmdrop(ctx->mm);
|
2015-09-04 15:46:48 -07:00
|
|
|
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:37 -07:00
|
|
|
static inline void msg_init(struct uffd_msg *msg)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
2015-09-04 15:46:37 -07:00
|
|
|
BUILD_BUG_ON(sizeof(struct uffd_msg) != 32);
|
|
|
|
/*
|
|
|
|
* Must use memset to zero out the paddings or kernel data is
|
|
|
|
* leaked to userland.
|
|
|
|
*/
|
|
|
|
memset(msg, 0, sizeof(struct uffd_msg));
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline struct uffd_msg userfault_msg(unsigned long address,
|
2022-07-11 09:59:06 -07:00
|
|
|
unsigned long real_address,
|
2015-09-04 15:46:37 -07:00
|
|
|
unsigned int flags,
|
2017-09-06 16:23:56 -07:00
|
|
|
unsigned long reason,
|
|
|
|
unsigned int features)
|
2015-09-04 15:46:37 -07:00
|
|
|
{
|
|
|
|
struct uffd_msg msg;
|
2022-07-11 09:59:06 -07:00
|
|
|
|
2015-09-04 15:46:37 -07:00
|
|
|
msg_init(&msg);
|
|
|
|
msg.event = UFFD_EVENT_PAGEFAULT;
|
userfaultfd: provide unmasked address on page-fault
Userfaultfd is supposed to provide the full address (i.e., unmasked) of
the faulting access back to userspace. However, that is not the case for
quite some time.
Even running "userfaultfd_demo" from the userfaultfd man page provides the
wrong output (and contradicts the man page). Notice that
"UFFD_EVENT_PAGEFAULT event" shows the masked address (7fc5e30b3000) and
not the first read address (0x7fc5e30b300f).
Address returned by mmap() = 0x7fc5e30b3000
fault_handler_thread():
poll() returns: nready = 1; POLLIN = 1; POLLERR = 0
UFFD_EVENT_PAGEFAULT event: flags = 0; address = 7fc5e30b3000
(uffdio_copy.copy returned 4096)
Read address 0x7fc5e30b300f in main(): A
Read address 0x7fc5e30b340f in main(): A
Read address 0x7fc5e30b380f in main(): A
Read address 0x7fc5e30b3c0f in main(): A
The exact address is useful for various reasons and specifically for
prefetching decisions. If it is known that the memory is populated by
certain objects whose size is not page-aligned, then based on the faulting
address, the uffd-monitor can decide whether to prefetch and prefault the
adjacent page.
This bug has been for quite some time in the kernel: since commit
1a29d85eb0f1 ("mm: use vmf->address instead of of vmf->virtual_address")
vmf->virtual_address"), which dates back to 2016. A concern has been
raised that existing userspace application might rely on the old/wrong
behavior in which the address is masked. Therefore, it was suggested to
provide the masked address unless the user explicitly asks for the exact
address.
Add a new userfaultfd feature UFFD_FEATURE_EXACT_ADDRESS to direct
userfaultfd to provide the exact address. Add a new "real_address" field
to vmf to hold the unmasked address. Provide the address to userspace
accordingly.
Initialize real_address in various code-paths to be consistent with
address, even when it is not used, to be on the safe side.
[namit@vmware.com: initialize real_address on all code paths, per Jan]
Link: https://lkml.kernel.org/r/20220226022655.350562-1-namit@vmware.com
[akpm@linux-foundation.org: fix typo in comment, per Jan]
Link: https://lkml.kernel.org/r/20220218041003.3508-1-namit@vmware.com
Signed-off-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2022-03-22 14:45:32 -07:00
|
|
|
|
2022-07-11 09:59:06 -07:00
|
|
|
msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ?
|
|
|
|
real_address : address;
|
|
|
|
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
/*
|
|
|
|
* These flags indicate why the userfault occurred:
|
|
|
|
* - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
|
|
|
|
* - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault.
|
|
|
|
* - Neither of these flags being set indicates a MISSING fault.
|
|
|
|
*
|
|
|
|
* Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write
|
|
|
|
* fault. Otherwise, it was a read fault.
|
|
|
|
*/
|
2015-09-04 15:46:31 -07:00
|
|
|
if (flags & FAULT_FLAG_WRITE)
|
2015-09-04 15:46:37 -07:00
|
|
|
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
|
2015-09-04 15:46:31 -07:00
|
|
|
if (reason & VM_UFFD_WP)
|
2015-09-04 15:46:37 -07:00
|
|
|
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
if (reason & VM_UFFD_MINOR)
|
|
|
|
msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR;
|
2017-09-06 16:23:56 -07:00
|
|
|
if (features & UFFD_FEATURE_THREAD_ID)
|
2017-09-06 16:23:59 -07:00
|
|
|
msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
|
2015-09-04 15:46:37 -07:00
|
|
|
return msg;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
2017-02-22 16:43:10 -07:00
|
|
|
#ifdef CONFIG_HUGETLB_PAGE
|
|
|
|
/*
|
|
|
|
* Same functionality as userfaultfd_must_wait below with modifications for
|
|
|
|
* hugepmd ranges.
|
|
|
|
*/
|
|
|
|
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
|
2023-06-30 14:19:57 -07:00
|
|
|
struct vm_fault *vmf,
|
|
|
|
unsigned long reason)
|
2017-02-22 16:43:10 -07:00
|
|
|
{
|
2023-06-30 14:19:57 -07:00
|
|
|
struct vm_area_struct *vma = vmf->vma;
|
2018-07-03 17:02:39 -07:00
|
|
|
pte_t *ptep, pte;
|
2017-02-22 16:43:10 -07:00
|
|
|
bool ret = true;
|
|
|
|
|
2023-06-30 14:19:57 -07:00
|
|
|
assert_fault_locked(vmf);
|
2018-07-03 17:02:39 -07:00
|
|
|
|
2023-06-30 14:19:57 -07:00
|
|
|
ptep = hugetlb_walk(vma, vmf->address, vma_mmu_pagesize(vma));
|
2018-07-03 17:02:39 -07:00
|
|
|
if (!ptep)
|
2017-02-22 16:43:10 -07:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = false;
|
2024-07-02 06:51:20 -07:00
|
|
|
pte = huge_ptep_get(vma->vm_mm, vmf->address, ptep);
|
2017-02-22 16:43:10 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Lockless access: we're in a wait_event so it's ok if it
|
2022-05-12 20:22:52 -07:00
|
|
|
* changes under us. PTE markers should be handled the same as none
|
|
|
|
* ptes here.
|
2017-02-22 16:43:10 -07:00
|
|
|
*/
|
2022-05-12 20:22:52 -07:00
|
|
|
if (huge_pte_none_mostly(pte))
|
2017-02-22 16:43:10 -07:00
|
|
|
ret = true;
|
2018-07-03 17:02:39 -07:00
|
|
|
if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
|
2017-02-22 16:43:10 -07:00
|
|
|
ret = true;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
|
2023-06-30 14:19:57 -07:00
|
|
|
struct vm_fault *vmf,
|
|
|
|
unsigned long reason)
|
2017-02-22 16:43:10 -07:00
|
|
|
{
|
|
|
|
return false; /* should never get here */
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_HUGETLB_PAGE */
|
|
|
|
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
/*
|
|
|
|
* Verify the pagetables are still not ok after having reigstered into
|
|
|
|
* the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
|
2024-04-02 11:26:41 -07:00
|
|
|
* userfault that has already been resolved, if userfaultfd_read_iter and
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
* UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
|
|
|
|
* threads.
|
|
|
|
*/
|
|
|
|
static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
|
2023-06-30 14:19:57 -07:00
|
|
|
struct vm_fault *vmf,
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
unsigned long reason)
|
|
|
|
{
|
|
|
|
struct mm_struct *mm = ctx->mm;
|
2023-06-30 14:19:57 -07:00
|
|
|
unsigned long address = vmf->address;
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
pgd_t *pgd;
|
2017-03-09 07:24:07 -07:00
|
|
|
p4d_t *p4d;
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
pud_t *pud;
|
|
|
|
pmd_t *pmd, _pmd;
|
|
|
|
pte_t *pte;
|
mm: ptep_get() conversion
Convert all instances of direct pte_t* dereferencing to instead use
ptep_get() helper. This means that by default, the accesses change from a
C dereference to a READ_ONCE(). This is technically the correct thing to
do since where pgtables are modified by HW (for access/dirty) they are
volatile and therefore we should always ensure READ_ONCE() semantics.
But more importantly, by always using the helper, it can be overridden by
the architecture to fully encapsulate the contents of the pte. Arch code
is deliberately not converted, as the arch code knows best. It is
intended that arch code (arm64) will override the default with its own
implementation that can (e.g.) hide certain bits from the core code, or
determine young/dirty status by mixing in state from another source.
Conversion was done using Coccinelle:
----
// $ make coccicheck \
// COCCI=ptepget.cocci \
// SPFLAGS="--include-headers" \
// MODE=patch
virtual patch
@ depends on patch @
pte_t *v;
@@
- *v
+ ptep_get(v)
----
Then reviewed and hand-edited to avoid multiple unnecessary calls to
ptep_get(), instead opting to store the result of a single call in a
variable, where it is correct to do so. This aims to negate any cost of
READ_ONCE() and will benefit arch-overrides that may be more complex.
Included is a fix for an issue in an earlier version of this patch that
was pointed out by kernel test robot. The issue arose because config
MMU=n elides definition of the ptep helper functions, including
ptep_get(). HUGETLB_PAGE=n configs still define a simple
huge_ptep_clear_flush() for linking purposes, which dereferences the ptep.
So when both configs are disabled, this caused a build error because
ptep_get() is not defined. Fix by continuing to do a direct dereference
when MMU=n. This is safe because for this config the arch code cannot be
trying to virtualize the ptes because none of the ptep helpers are
defined.
Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 08:15:45 -07:00
|
|
|
pte_t ptent;
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
bool ret = true;
|
|
|
|
|
2023-06-30 14:19:57 -07:00
|
|
|
assert_fault_locked(vmf);
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
|
|
|
|
pgd = pgd_offset(mm, address);
|
|
|
|
if (!pgd_present(*pgd))
|
|
|
|
goto out;
|
2017-03-09 07:24:07 -07:00
|
|
|
p4d = p4d_offset(pgd, address);
|
|
|
|
if (!p4d_present(*p4d))
|
|
|
|
goto out;
|
|
|
|
pud = pud_offset(p4d, address);
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
if (!pud_present(*pud))
|
|
|
|
goto out;
|
|
|
|
pmd = pmd_offset(pud, address);
|
2023-06-08 18:24:38 -07:00
|
|
|
again:
|
mm: use pmdp_get_lockless() without surplus barrier()
Patch series "mm: allow pte_offset_map[_lock]() to fail", v2.
What is it all about? Some mmap_lock avoidance i.e. latency reduction.
Initially just for the case of collapsing shmem or file pages to THPs; but
likely to be relied upon later in other contexts e.g. freeing of empty
page tables (but that's not work I'm doing). mmap_write_lock avoidance
when collapsing to anon THPs? Perhaps, but again that's not work I've
done: a quick attempt was not as easy as the shmem/file case.
I would much prefer not to have to make these small but wide-ranging
changes for such a niche case; but failed to find another way, and have
heard that shmem MADV_COLLAPSE's usefulness is being limited by that
mmap_write_lock it currently requires.
These changes (though of course not these exact patches) have been in
Google's data centre kernel for three years now: we do rely upon them.
What is this preparatory series about?
The current mmap locking will not be enough to guard against that tricky
transition between pmd entry pointing to page table, and empty pmd entry,
and pmd entry pointing to huge page: pte_offset_map() will have to
validate the pmd entry for itself, returning NULL if no page table is
there. What to do about that varies: sometimes nearby error handling
indicates just to skip it; but in many cases an ACTION_AGAIN or "goto
again" is appropriate (and if that risks an infinite loop, then there must
have been an oops, or pfn 0 mistaken for page table, before).
Given the likely extension to freeing empty page tables, I have not
limited this set of changes to a THP config; and it has been easier, and
sets a better example, if each site is given appropriate handling: even
where deeper study might prove that failure could only happen if the pmd
table were corrupted.
Several of the patches are, or include, cleanup on the way; and by the
end, pmd_trans_unstable() and suchlike are deleted: pte_offset_map() and
pte_offset_map_lock() then handle those original races and more. Most
uses of pte_lockptr() are deprecated, with pte_offset_map_nolock() taking
its place.
This patch (of 32):
Use pmdp_get_lockless() in preference to READ_ONCE(*pmdp), to get a more
reliable result with PAE (or READ_ONCE as before without PAE); and remove
the unnecessary extra barrier()s which got left behind in its callers.
HOWEVER: Note the small print in linux/pgtable.h, where it was designed
specifically for fast GUP, and depends on interrupts being disabled for
its full guarantee: most callers which have been added (here and before)
do NOT have interrupts disabled, so there is still some need for caution.
Link: https://lkml.kernel.org/r/f35279a9-9ac0-de22-d245-591afbfb4dc@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Yu Zhao <yuzhao@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zack Rusin <zackr@vmware.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-08 18:06:53 -07:00
|
|
|
_pmd = pmdp_get_lockless(pmd);
|
mm, userfaultfd, THP: avoid waiting when PMD under THP migration
If THP migration is enabled, for a VMA handled by userfaultfd, consider
the following situation,
do_page_fault()
__do_huge_pmd_anonymous_page()
handle_userfault()
userfault_msg()
/* a huge page is allocated and mapped at fault address */
/* the huge page is under migration, leaves migration entry
in page table */
userfaultfd_must_wait()
/* return true because !pmd_present() */
/* may wait in loop until fatal signal */
That is, it may be possible for userfaultfd_must_wait() encounters a PMD
entry which is !pmd_none() && !pmd_present(). In the current
implementation, we will wait for such PMD entries, which may cause
unnecessary waiting, and potential soft lockup.
This is fixed via avoiding to wait when !pmd_none() && !pmd_present(),
only wait when pmd_none().
This may be not a problem in practice, because userfaultfd_must_wait()
is always called with mm->mmap_sem read-locked. mremap() will
write-lock mm->mmap_sem. And UFFDIO_COPY doesn't support to copy THP
mapping. But the change introduced still makes the code more correct,
and makes the PMD and PTE code more consistent.
Link: http://lkml.kernel.org/r/20171207011752.3292-1-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.UK>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-01-31 17:17:32 -07:00
|
|
|
if (pmd_none(_pmd))
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = false;
|
2023-06-08 18:24:38 -07:00
|
|
|
if (!pmd_present(_pmd) || pmd_devmap(_pmd))
|
mm, userfaultfd, THP: avoid waiting when PMD under THP migration
If THP migration is enabled, for a VMA handled by userfaultfd, consider
the following situation,
do_page_fault()
__do_huge_pmd_anonymous_page()
handle_userfault()
userfault_msg()
/* a huge page is allocated and mapped at fault address */
/* the huge page is under migration, leaves migration entry
in page table */
userfaultfd_must_wait()
/* return true because !pmd_present() */
/* may wait in loop until fatal signal */
That is, it may be possible for userfaultfd_must_wait() encounters a PMD
entry which is !pmd_none() && !pmd_present(). In the current
implementation, we will wait for such PMD entries, which may cause
unnecessary waiting, and potential soft lockup.
This is fixed via avoiding to wait when !pmd_none() && !pmd_present(),
only wait when pmd_none().
This may be not a problem in practice, because userfaultfd_must_wait()
is always called with mm->mmap_sem read-locked. mremap() will
write-lock mm->mmap_sem. And UFFDIO_COPY doesn't support to copy THP
mapping. But the change introduced still makes the code more correct,
and makes the PMD and PTE code more consistent.
Link: http://lkml.kernel.org/r/20171207011752.3292-1-ying.huang@intel.com
Signed-off-by: "Huang, Ying" <ying.huang@intel.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Alexander Viro <viro@zeniv.linux.org.UK>
Cc: Zi Yan <zi.yan@cs.rutgers.edu>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-01-31 17:17:32 -07:00
|
|
|
goto out;
|
|
|
|
|
2020-04-06 20:06:12 -07:00
|
|
|
if (pmd_trans_huge(_pmd)) {
|
|
|
|
if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
|
|
|
|
ret = true;
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
goto out;
|
2020-04-06 20:06:12 -07:00
|
|
|
}
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
|
|
|
|
pte = pte_offset_map(pmd, address);
|
2023-06-08 18:24:38 -07:00
|
|
|
if (!pte) {
|
|
|
|
ret = true;
|
|
|
|
goto again;
|
|
|
|
}
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
/*
|
|
|
|
* Lockless access: we're in a wait_event so it's ok if it
|
2022-05-12 20:22:52 -07:00
|
|
|
* changes under us. PTE markers should be handled the same as none
|
|
|
|
* ptes here.
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
*/
|
mm: ptep_get() conversion
Convert all instances of direct pte_t* dereferencing to instead use
ptep_get() helper. This means that by default, the accesses change from a
C dereference to a READ_ONCE(). This is technically the correct thing to
do since where pgtables are modified by HW (for access/dirty) they are
volatile and therefore we should always ensure READ_ONCE() semantics.
But more importantly, by always using the helper, it can be overridden by
the architecture to fully encapsulate the contents of the pte. Arch code
is deliberately not converted, as the arch code knows best. It is
intended that arch code (arm64) will override the default with its own
implementation that can (e.g.) hide certain bits from the core code, or
determine young/dirty status by mixing in state from another source.
Conversion was done using Coccinelle:
----
// $ make coccicheck \
// COCCI=ptepget.cocci \
// SPFLAGS="--include-headers" \
// MODE=patch
virtual patch
@ depends on patch @
pte_t *v;
@@
- *v
+ ptep_get(v)
----
Then reviewed and hand-edited to avoid multiple unnecessary calls to
ptep_get(), instead opting to store the result of a single call in a
variable, where it is correct to do so. This aims to negate any cost of
READ_ONCE() and will benefit arch-overrides that may be more complex.
Included is a fix for an issue in an earlier version of this patch that
was pointed out by kernel test robot. The issue arose because config
MMU=n elides definition of the ptep helper functions, including
ptep_get(). HUGETLB_PAGE=n configs still define a simple
huge_ptep_clear_flush() for linking purposes, which dereferences the ptep.
So when both configs are disabled, this caused a build error because
ptep_get() is not defined. Fix by continuing to do a direct dereference
when MMU=n. This is safe because for this config the arch code cannot be
trying to virtualize the ptes because none of the ptep helpers are
defined.
Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 08:15:45 -07:00
|
|
|
ptent = ptep_get(pte);
|
|
|
|
if (pte_none_mostly(ptent))
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
ret = true;
|
mm: ptep_get() conversion
Convert all instances of direct pte_t* dereferencing to instead use
ptep_get() helper. This means that by default, the accesses change from a
C dereference to a READ_ONCE(). This is technically the correct thing to
do since where pgtables are modified by HW (for access/dirty) they are
volatile and therefore we should always ensure READ_ONCE() semantics.
But more importantly, by always using the helper, it can be overridden by
the architecture to fully encapsulate the contents of the pte. Arch code
is deliberately not converted, as the arch code knows best. It is
intended that arch code (arm64) will override the default with its own
implementation that can (e.g.) hide certain bits from the core code, or
determine young/dirty status by mixing in state from another source.
Conversion was done using Coccinelle:
----
// $ make coccicheck \
// COCCI=ptepget.cocci \
// SPFLAGS="--include-headers" \
// MODE=patch
virtual patch
@ depends on patch @
pte_t *v;
@@
- *v
+ ptep_get(v)
----
Then reviewed and hand-edited to avoid multiple unnecessary calls to
ptep_get(), instead opting to store the result of a single call in a
variable, where it is correct to do so. This aims to negate any cost of
READ_ONCE() and will benefit arch-overrides that may be more complex.
Included is a fix for an issue in an earlier version of this patch that
was pointed out by kernel test robot. The issue arose because config
MMU=n elides definition of the ptep helper functions, including
ptep_get(). HUGETLB_PAGE=n configs still define a simple
huge_ptep_clear_flush() for linking purposes, which dereferences the ptep.
So when both configs are disabled, this caused a build error because
ptep_get() is not defined. Fix by continuing to do a direct dereference
when MMU=n. This is safe because for this config the arch code cannot be
trying to virtualize the ptes because none of the ptep helpers are
defined.
Link: https://lkml.kernel.org/r/20230612151545.3317766-4-ryan.roberts@arm.com
Reported-by: kernel test robot <lkp@intel.com>
Link: https://lore.kernel.org/oe-kbuild-all/202305120142.yXsNEo6H-lkp@intel.com/
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Potapenko <glider@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Konovalov <andreyknvl@gmail.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Dave Airlie <airlied@gmail.com>
Cc: Dimitri Sivanich <dimitri.sivanich@hpe.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oleksandr Tyshchenko <oleksandr_tyshchenko@epam.com>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Uladzislau Rezki (Sony) <urezki@gmail.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Yu Zhao <yuzhao@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-12 08:15:45 -07:00
|
|
|
if (!pte_write(ptent) && (reason & VM_UFFD_WP))
|
2020-04-06 20:06:12 -07:00
|
|
|
ret = true;
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
pte_unmap(pte);
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2021-06-11 01:28:17 -07:00
|
|
|
static inline unsigned int userfaultfd_get_blocking_state(unsigned int flags)
|
2020-04-01 21:09:00 -07:00
|
|
|
{
|
|
|
|
if (flags & FAULT_FLAG_INTERRUPTIBLE)
|
|
|
|
return TASK_INTERRUPTIBLE;
|
|
|
|
|
|
|
|
if (flags & FAULT_FLAG_KILLABLE)
|
|
|
|
return TASK_KILLABLE;
|
|
|
|
|
|
|
|
return TASK_UNINTERRUPTIBLE;
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* The locking rules involved in returning VM_FAULT_RETRY depending on
|
|
|
|
* FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
|
|
|
|
* FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
|
|
|
|
* recommendation in __lock_page_or_retry is not an understatement.
|
|
|
|
*
|
2020-06-08 21:33:54 -07:00
|
|
|
* If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released
|
2015-09-04 15:46:31 -07:00
|
|
|
* before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
|
|
|
|
* not set.
|
|
|
|
*
|
|
|
|
* If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
|
|
|
|
* set, VM_FAULT_RETRY can still be returned if and only if there are
|
2020-06-08 21:33:54 -07:00
|
|
|
* fatal_signal_pending()s, and the mmap_lock must be released before
|
2015-09-04 15:46:31 -07:00
|
|
|
* returning it.
|
|
|
|
*/
|
2018-08-23 17:01:36 -07:00
|
|
|
vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
2022-12-16 08:52:17 -07:00
|
|
|
struct vm_area_struct *vma = vmf->vma;
|
|
|
|
struct mm_struct *mm = vma->vm_mm;
|
2015-09-04 15:46:31 -07:00
|
|
|
struct userfaultfd_ctx *ctx;
|
|
|
|
struct userfaultfd_wait_queue uwq;
|
2018-08-23 17:01:36 -07:00
|
|
|
vm_fault_t ret = VM_FAULT_SIGBUS;
|
2020-04-01 21:09:00 -07:00
|
|
|
bool must_wait;
|
2021-06-11 01:28:17 -07:00
|
|
|
unsigned int blocking_state;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2017-06-16 14:02:37 -07:00
|
|
|
/*
|
2024-07-31 07:20:00 -07:00
|
|
|
* We don't do userfault handling for the final child pid update
|
|
|
|
* and when coredumping (faults triggered by get_dump_page()).
|
2017-06-16 14:02:37 -07:00
|
|
|
*/
|
|
|
|
if (current->flags & (PF_EXITING|PF_DUMPCORE))
|
|
|
|
goto out;
|
|
|
|
|
2023-06-30 14:19:57 -07:00
|
|
|
assert_fault_locked(vmf);
|
2017-06-16 14:02:37 -07:00
|
|
|
|
2022-12-16 08:52:17 -07:00
|
|
|
ctx = vma->vm_userfaultfd_ctx.ctx;
|
2015-09-04 15:46:31 -07:00
|
|
|
if (!ctx)
|
2015-09-04 15:46:41 -07:00
|
|
|
goto out;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
BUG_ON(ctx->mm != mm);
|
|
|
|
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
/* Any unrecognized flag is a bug. */
|
|
|
|
VM_BUG_ON(reason & ~__VM_UFFD_FLAGS);
|
|
|
|
/* 0 or > 1 flags set is a bug; we expect exactly 1. */
|
|
|
|
VM_BUG_ON(!reason || (reason & (reason - 1)));
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2017-09-06 16:23:39 -07:00
|
|
|
if (ctx->features & UFFD_FEATURE_SIGBUS)
|
|
|
|
goto out;
|
userfaultfd: add /dev/userfaultfd for fine grained access control
Historically, it has been shown that intercepting kernel faults with
userfaultfd (thereby forcing the kernel to wait for an arbitrary amount of
time) can be exploited, or at least can make some kinds of exploits
easier. So, in 37cd0575b8 "userfaultfd: add UFFD_USER_MODE_ONLY" we
changed things so, in order for kernel faults to be handled by
userfaultfd, either the process needs CAP_SYS_PTRACE, or this sysctl must
be configured so that any unprivileged user can do it.
In a typical implementation of a hypervisor with live migration (take
QEMU/KVM as one such example), we do indeed need to be able to handle
kernel faults. But, both options above are less than ideal:
- Toggling the sysctl increases attack surface by allowing any
unprivileged user to do it.
- Granting the live migration process CAP_SYS_PTRACE gives it this
ability, but *also* the ability to "observe and control the
execution of another process [...], and examine and change [its]
memory and registers" (from ptrace(2)). This isn't something we need
or want to be able to do, so granting this permission violates the
"principle of least privilege".
This is all a long winded way to say: we want a more fine-grained way to
grant access to userfaultfd, without granting other additional permissions
at the same time.
To achieve this, add a /dev/userfaultfd misc device. This device provides
an alternative to the userfaultfd(2) syscall for the creation of new
userfaultfds. The idea is, any userfaultfds created this way will be able
to handle kernel faults, without the caller having any special
capabilities. Access to this mechanism is instead restricted using e.g.
standard filesystem permissions.
[axelrasmussen@google.com: Handle misc_register() failure properly]
Link: https://lkml.kernel.org/r/20220819205201.658693-3-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20220808175614.3885028-3-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-08-08 10:56:11 -07:00
|
|
|
if (!(vmf->flags & FAULT_FLAG_USER) && (ctx->flags & UFFD_USER_MODE_ONLY))
|
userfaultfd: add UFFD_USER_MODE_ONLY
Patch series "Control over userfaultfd kernel-fault handling", v6.
This patch series is split from [1]. The other series enables SELinux
support for userfaultfd file descriptors so that its creation and movement
can be controlled.
It has been demonstrated on various occasions that suspending kernel code
execution for an arbitrary amount of time at any access to userspace
memory (copy_from_user()/copy_to_user()/...) can be exploited to change
the intended behavior of the kernel. For instance, handling page faults
in kernel-mode using userfaultfd has been exploited in [2, 3]. Likewise,
FUSE, which is similar to userfaultfd in this respect, has been exploited
in [4, 5] for similar outcome.
This small patch series adds a new flag to userfaultfd(2) that allows
callers to give up the ability to handle kernel-mode faults with the
resulting UFFD file object. It then adds a 'user-mode only' option to the
unprivileged_userfaultfd sysctl knob to require unprivileged callers to
use this new flag.
The purpose of this new interface is to decrease the chance of an
unprivileged userfaultfd user taking advantage of userfaultfd to enhance
security vulnerabilities by lengthening the race window in kernel code.
[1] https://lore.kernel.org/lkml/20200211225547.235083-1-dancol@google.com/
[2] https://duasynt.com/blog/linux-kernel-heap-spray
[3] https://duasynt.com/blog/cve-2016-6187-heap-off-by-one-exploit
[4] https://googleprojectzero.blogspot.com/2016/06/exploiting-recursion-in-linux-kernel_20.html
[5] https://bugs.chromium.org/p/project-zero/issues/detail?id=808
This patch (of 2):
userfaultfd handles page faults from both user and kernel code. Add a new
UFFD_USER_MODE_ONLY flag for userfaultfd(2) that makes the resulting
userfaultfd object refuse to handle faults from kernel mode, treating
these faults as if SIGBUS were always raised, causing the kernel code to
fail with EFAULT.
A future patch adds a knob allowing administrators to give some processes
the ability to create userfaultfd file objects only if they pass
UFFD_USER_MODE_ONLY, reducing the likelihood that these processes will
exploit userfaultfd's ability to delay kernel page faults to open timing
windows for future exploits.
Link: https://lkml.kernel.org/r/20201120030411.2690816-1-lokeshgidra@google.com
Link: https://lkml.kernel.org/r/20201120030411.2690816-2-lokeshgidra@google.com
Signed-off-by: Daniel Colascione <dancol@google.com>
Signed-off-by: Lokesh Gidra <lokeshgidra@google.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: <calin@google.com>
Cc: Daniel Colascione <dancol@dancol.org>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nitin Gupta <nigupta@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Shaohua Li <shli@fb.com>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-14 20:13:49 -07:00
|
|
|
goto out;
|
2017-09-06 16:23:39 -07:00
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* If it's already released don't get it. This avoids to loop
|
|
|
|
* in __get_user_pages if userfaultfd_release waits on the
|
2020-06-08 21:33:54 -07:00
|
|
|
* caller of handle_userfault to release the mmap_lock.
|
2015-09-04 15:46:31 -07:00
|
|
|
*/
|
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE()
Please do not apply this to mainline directly, instead please re-run the
coccinelle script shown below and apply its output.
For several reasons, it is desirable to use {READ,WRITE}_ONCE() in
preference to ACCESS_ONCE(), and new code is expected to use one of the
former. So far, there's been no reason to change most existing uses of
ACCESS_ONCE(), as these aren't harmful, and changing them results in
churn.
However, for some features, the read/write distinction is critical to
correct operation. To distinguish these cases, separate read/write
accessors must be used. This patch migrates (most) remaining
ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following
coccinelle script:
----
// Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and
// WRITE_ONCE()
// $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch
virtual patch
@ depends on patch @
expression E1, E2;
@@
- ACCESS_ONCE(E1) = E2
+ WRITE_ONCE(E1, E2)
@ depends on patch @
expression E;
@@
- ACCESS_ONCE(E)
+ READ_ONCE(E)
----
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: linux-arch@vger.kernel.org
Cc: mpe@ellerman.id.au
Cc: shuah@kernel.org
Cc: snitzer@redhat.com
Cc: thor.thayer@linux.intel.com
Cc: tj@kernel.org
Cc: viro@zeniv.linux.org.uk
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-23 14:07:29 -07:00
|
|
|
if (unlikely(READ_ONCE(ctx->released))) {
|
2017-09-08 16:12:42 -07:00
|
|
|
/*
|
|
|
|
* Don't return VM_FAULT_SIGBUS in this case, so a non
|
|
|
|
* cooperative manager can close the uffd after the
|
|
|
|
* last UFFDIO_COPY, without risking to trigger an
|
|
|
|
* involuntary SIGBUS if the process was starting the
|
|
|
|
* userfaultfd while the userfaultfd was still armed
|
|
|
|
* (but after the last UFFDIO_COPY). If the uffd
|
|
|
|
* wasn't already closed when the userfault reached
|
|
|
|
* this point, that would normally be solved by
|
|
|
|
* userfaultfd_must_wait returning 'false'.
|
|
|
|
*
|
|
|
|
* If we were to return VM_FAULT_SIGBUS here, the non
|
|
|
|
* cooperative manager would be instead forced to
|
|
|
|
* always call UFFDIO_UNREGISTER before it can safely
|
|
|
|
* close the uffd.
|
|
|
|
*/
|
|
|
|
ret = VM_FAULT_NOPAGE;
|
2015-09-04 15:46:41 -07:00
|
|
|
goto out;
|
2017-09-08 16:12:42 -07:00
|
|
|
}
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Check that we can return VM_FAULT_RETRY.
|
|
|
|
*
|
|
|
|
* NOTE: it should become possible to return VM_FAULT_RETRY
|
|
|
|
* even if FAULT_FLAG_TRIED is set without leading to gup()
|
|
|
|
* -EBUSY failures, if the userfaultfd is to be extended for
|
|
|
|
* VM_UFFD_WP tracking and we intend to arm the userfault
|
|
|
|
* without first stopping userland access to the memory. For
|
|
|
|
* VM_UFFD_MISSING userfaults this is enough for now.
|
|
|
|
*/
|
2016-12-14 16:06:58 -07:00
|
|
|
if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) {
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* Validate the invariant that nowait must allow retry
|
|
|
|
* to be sure not to return SIGBUS erroneously on
|
|
|
|
* nowait invocations.
|
|
|
|
*/
|
2016-12-14 16:06:58 -07:00
|
|
|
BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
|
2015-09-04 15:46:31 -07:00
|
|
|
#ifdef CONFIG_DEBUG_VM
|
|
|
|
if (printk_ratelimit()) {
|
|
|
|
printk(KERN_WARNING
|
2016-12-14 16:06:58 -07:00
|
|
|
"FAULT_FLAG_ALLOW_RETRY missing %x\n",
|
|
|
|
vmf->flags);
|
2015-09-04 15:46:31 -07:00
|
|
|
dump_stack();
|
|
|
|
}
|
|
|
|
#endif
|
2015-09-04 15:46:41 -07:00
|
|
|
goto out;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Handle nowait, not much to do other than tell it to retry
|
|
|
|
* and wait.
|
|
|
|
*/
|
2015-09-04 15:46:41 -07:00
|
|
|
ret = VM_FAULT_RETRY;
|
2016-12-14 16:06:58 -07:00
|
|
|
if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
|
2015-09-04 15:46:41 -07:00
|
|
|
goto out;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2020-06-08 21:33:54 -07:00
|
|
|
/* take the reference before dropping the mmap_lock */
|
2015-09-04 15:46:31 -07:00
|
|
|
userfaultfd_ctx_get(ctx);
|
|
|
|
|
|
|
|
init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
|
|
|
|
uwq.wq.private = current;
|
2022-07-11 09:59:06 -07:00
|
|
|
uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags,
|
|
|
|
reason, ctx->features);
|
2015-09-04 15:46:31 -07:00
|
|
|
uwq.ctx = ctx;
|
userfaultfd: fix SIGBUS resulting from false rwsem wakeups
With >=32 CPUs the userfaultfd selftest triggered a graceful but
unexpected SIGBUS because VM_FAULT_RETRY was returned by
handle_userfault() despite the UFFDIO_COPY wasn't completed.
This seems caused by rwsem waking the thread blocked in
handle_userfault() and we can't run up_read() before the wait_event
sequence is complete.
Keeping the wait_even sequence identical to the first one, would require
running userfaultfd_must_wait() again to know if the loop should be
repeated, and it would also require retaking the rwsem and revalidating
the whole vma status.
It seems simpler to wait the targeted wakeup so that if false wakeups
materialize we still wait for our specific wakeup event, unless of
course there are signals or the uffd was released.
Debug code collecting the stack trace of the wakeup showed this:
$ ./userfaultfd 100 99999
nr_pages: 25600, nr_pages_per_cpu: 800
bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2
bounces: 99997, mode: rnd ver poll, Bus error (core dumped)
save_stack_trace+0x2b/0x50
try_to_wake_up+0x2a6/0x580
wake_up_q+0x32/0x70
rwsem_wake+0xe0/0x120
call_rwsem_wake+0x1b/0x30
up_write+0x3b/0x40
vm_mmap_pgoff+0x9c/0xc0
SyS_mmap_pgoff+0x1a9/0x240
SyS_mmap+0x22/0x30
entry_SYSCALL_64_fastpath+0x1f/0xbd
0xffffffffffffffff
FAULT_FLAG_ALLOW_RETRY missing 70
CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
Call Trace:
dump_stack+0xb8/0x112
handle_userfault+0x572/0x650
handle_mm_fault+0x12cb/0x1520
__do_page_fault+0x175/0x500
trace_do_page_fault+0x61/0x270
do_async_page_fault+0x19/0x90
async_page_fault+0x25/0x30
This always happens when the main userfault selftest thread is running
clone() while glibc runs either mprotect or mmap (both taking mmap_sem
down_write()) to allocate the thread stack of the background threads,
while locking/userfault threads already run at full throttle and are
susceptible to false wakeups that may cause handle_userfault() to return
before than expected (which results in graceful SIGBUS at the next
attempt).
This was reproduced only with >=32 CPUs because the loop to start the
thread where clone() is too quick with fewer CPUs, while with 32 CPUs
there's already significant activity on ~32 locking and userfault
threads when the last background threads are started with clone().
This >=32 CPUs SMP race condition is likely reproducible only with the
selftest because of the much heavier userfault load it generates if
compared to real apps.
We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a
patch floating around that provides it also hidden this problem but in
reality only is successfully at hiding the problem.
False wakeups could still happen again the second time
handle_userfault() is invoked, even if it's a so rare race condition
that getting false wakeups twice in a row is impossible to reproduce.
This full fix is needed for correctness, the only alternative would be
to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP
support can stick to a strict "one more" VM_FAULT_RETRY logic (no need
of returning it infinite times to avoid the SIGBUS).
Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-24 16:17:59 -07:00
|
|
|
uwq.waken = false;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2020-04-01 21:09:00 -07:00
|
|
|
blocking_state = userfaultfd_get_blocking_state(vmf->flags);
|
2015-09-04 15:47:18 -07:00
|
|
|
|
2022-12-16 08:52:17 -07:00
|
|
|
/*
|
|
|
|
* Take the vma lock now, in order to safely call
|
|
|
|
* userfaultfd_huge_must_wait() later. Since acquiring the
|
|
|
|
* (sleepable) vma lock can modify the current task state, that
|
|
|
|
* must be before explicitly calling set_current_state().
|
|
|
|
*/
|
|
|
|
if (is_vm_hugetlb_page(vma))
|
|
|
|
hugetlb_vma_lock_read(vma);
|
|
|
|
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* After the __add_wait_queue the uwq is visible to userland
|
|
|
|
* through poll/read().
|
|
|
|
*/
|
2015-09-04 15:46:44 -07:00
|
|
|
__add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq);
|
|
|
|
/*
|
|
|
|
* The smp_mb() after __set_current_state prevents the reads
|
|
|
|
* following the spin_unlock to happen before the list_add in
|
|
|
|
* __add_wait_queue.
|
|
|
|
*/
|
userfaultfd: fix SIGBUS resulting from false rwsem wakeups
With >=32 CPUs the userfaultfd selftest triggered a graceful but
unexpected SIGBUS because VM_FAULT_RETRY was returned by
handle_userfault() despite the UFFDIO_COPY wasn't completed.
This seems caused by rwsem waking the thread blocked in
handle_userfault() and we can't run up_read() before the wait_event
sequence is complete.
Keeping the wait_even sequence identical to the first one, would require
running userfaultfd_must_wait() again to know if the loop should be
repeated, and it would also require retaking the rwsem and revalidating
the whole vma status.
It seems simpler to wait the targeted wakeup so that if false wakeups
materialize we still wait for our specific wakeup event, unless of
course there are signals or the uffd was released.
Debug code collecting the stack trace of the wakeup showed this:
$ ./userfaultfd 100 99999
nr_pages: 25600, nr_pages_per_cpu: 800
bounces: 99998, mode: racing ver poll, userfaults: 32 35 90 232 30 138 69 82 34 30 139 40 40 31 20 19 43 13 15 28 27 38 21 43 56 22 1 17 31 8 4 2
bounces: 99997, mode: rnd ver poll, Bus error (core dumped)
save_stack_trace+0x2b/0x50
try_to_wake_up+0x2a6/0x580
wake_up_q+0x32/0x70
rwsem_wake+0xe0/0x120
call_rwsem_wake+0x1b/0x30
up_write+0x3b/0x40
vm_mmap_pgoff+0x9c/0xc0
SyS_mmap_pgoff+0x1a9/0x240
SyS_mmap+0x22/0x30
entry_SYSCALL_64_fastpath+0x1f/0xbd
0xffffffffffffffff
FAULT_FLAG_ALLOW_RETRY missing 70
CPU: 24 PID: 1054 Comm: userfaultfd Tainted: G W 4.8.0+ #30
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.9.3-0-ge2fc41e-prebuilt.qemu-project.org 04/01/2014
Call Trace:
dump_stack+0xb8/0x112
handle_userfault+0x572/0x650
handle_mm_fault+0x12cb/0x1520
__do_page_fault+0x175/0x500
trace_do_page_fault+0x61/0x270
do_async_page_fault+0x19/0x90
async_page_fault+0x25/0x30
This always happens when the main userfault selftest thread is running
clone() while glibc runs either mprotect or mmap (both taking mmap_sem
down_write()) to allocate the thread stack of the background threads,
while locking/userfault threads already run at full throttle and are
susceptible to false wakeups that may cause handle_userfault() to return
before than expected (which results in graceful SIGBUS at the next
attempt).
This was reproduced only with >=32 CPUs because the loop to start the
thread where clone() is too quick with fewer CPUs, while with 32 CPUs
there's already significant activity on ~32 locking and userfault
threads when the last background threads are started with clone().
This >=32 CPUs SMP race condition is likely reproducible only with the
selftest because of the much heavier userfault load it generates if
compared to real apps.
We'll have to allow "one more" VM_FAULT_RETRY for the WP support and a
patch floating around that provides it also hidden this problem but in
reality only is successfully at hiding the problem.
False wakeups could still happen again the second time
handle_userfault() is invoked, even if it's a so rare race condition
that getting false wakeups twice in a row is impossible to reproduce.
This full fix is needed for correctness, the only alternative would be
to allow VM_FAULT_RETRY to be returned infinitely. With this fix the WP
support can stick to a strict "one more" VM_FAULT_RETRY logic (no need
of returning it infinite times to avoid the SIGBUS).
Link: http://lkml.kernel.org/r/20170111005535.13832-2-aarcange@redhat.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Shubham Kumar Sharma <shubham.kumar.sharma@oracle.com>
Tested-by: Mike Kravetz <mike.kravetz@oracle.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Michael Rapoport <RAPOPORT@il.ibm.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-01-24 16:17:59 -07:00
|
|
|
set_current_state(blocking_state);
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2022-12-16 08:52:17 -07:00
|
|
|
if (!is_vm_hugetlb_page(vma))
|
2023-06-30 14:19:57 -07:00
|
|
|
must_wait = userfaultfd_must_wait(ctx, vmf, reason);
|
2017-02-22 16:43:10 -07:00
|
|
|
else
|
2023-06-30 14:19:57 -07:00
|
|
|
must_wait = userfaultfd_huge_must_wait(ctx, vmf, reason);
|
2022-12-16 08:52:17 -07:00
|
|
|
if (is_vm_hugetlb_page(vma))
|
|
|
|
hugetlb_vma_unlock_read(vma);
|
2023-06-30 14:19:57 -07:00
|
|
|
release_fault_lock(vmf);
|
userfaultfd: solve the race between UFFDIO_COPY|ZEROPAGE and read
Solve in-kernel the race between UFFDIO_COPY|ZEROPAGE and
userfaultfd_read if they are run on different threads simultaneously.
Until now qemu solved the race in userland: the race was explicitly
and intentionally left for userland to solve. However we can also
solve it in kernel.
Requiring all users to solve this race if they use two threads (one
for the background transfer and one for the userfault reads) isn't
very attractive from an API prospective, furthermore this allows to
remove a whole bunch of mutex and bitmap code from qemu, making it
faster. The cost of __get_user_pages_fast should be insignificant
considering it scales perfectly and the pagetables are already hot in
the CPU cache, compared to the overhead in userland to maintain those
structures.
Applying this patch is backwards compatible with respect to the
userfaultfd userland API, however reverting this change wouldn't be
backwards compatible anymore.
Without this patch qemu in the background transfer thread, has to read
the old state, and do UFFDIO_WAKE if old_state is missing but it
become REQUESTED by the time it tries to set it to RECEIVED (signaling
the other side received an userfault).
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
postcopy_pmi_change_state(MISSING, REQUESTED) -> REQUESTED
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> REQUESTED
/* check that no userfault raced with UFFDIO_COPY */
if (old_state == MISSING && tmp_state == REQUESTED)
UFFDIO_WAKE from background thread
And a second case where a UFFDIO_WAKE would be needed is in the userfault thread:
vcpu background_thr userfault_thr
----- ----- -----
vcpu0 handle_mm_fault()
postcopy_place_page
read old_state -> MISSING
UFFDIO_COPY 0x7fb76a139000 (no wakeup, still pending)
tmp_state = postcopy_pmi_change_state(old_state, RECEIVED) -> RECEIVED
vcpu0 fault at 0x7fb76a139000 enters handle_userfault
poll() is kicked
poll() -> POLLIN
read() -> 0x7fb76a139000
if (postcopy_pmi_change_state(MISSING, REQUESTED) == RECEIVED)
UFFDIO_WAKE from userfault thread
This patch removes the need of both UFFDIO_WAKE and of the associated
per-page tristate as well.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Pavel Emelyanov <xemul@parallels.com>
Cc: Sanidhya Kashyap <sanidhya.gatech@gmail.com>
Cc: zhang.zhanghailiang@huawei.com
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Andres Lagar-Cavilla <andreslc@google.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Hugh Dickins <hughd@google.com>
Cc: Peter Feiner <pfeiner@google.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: "Huangpeng (Peter)" <peter.huangpeng@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-09-04 15:46:51 -07:00
|
|
|
|
2020-08-02 10:42:31 -07:00
|
|
|
if (likely(must_wait && !READ_ONCE(ctx->released))) {
|
2018-02-11 15:34:03 -07:00
|
|
|
wake_up_poll(&ctx->fd_wqh, EPOLLIN);
|
2015-09-04 15:46:31 -07:00
|
|
|
schedule();
|
2015-09-04 15:46:41 -07:00
|
|
|
}
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2015-09-04 15:46:41 -07:00
|
|
|
__set_current_state(TASK_RUNNING);
|
2015-09-04 15:46:44 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Here we race with the list_del; list_add in
|
|
|
|
* userfaultfd_ctx_read(), however because we don't ever run
|
|
|
|
* list_del_init() to refile across the two lists, the prev
|
|
|
|
* and next pointers will never point to self. list_add also
|
|
|
|
* would never let any of the two pointers to point to
|
|
|
|
* self. So list_empty_careful won't risk to see both pointers
|
|
|
|
* pointing to self at any time during the list refile. The
|
|
|
|
* only case where list_del_init() is called is the full
|
|
|
|
* removal in the wake function and there we don't re-list_add
|
|
|
|
* and it's fine not to block on the spinlock. The uwq on this
|
|
|
|
* kernel stack can be released after the list_del_init.
|
|
|
|
*/
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
if (!list_empty_careful(&uwq.wq.entry)) {
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:44 -07:00
|
|
|
/*
|
|
|
|
* No need of list_del_init(), the uwq on the stack
|
|
|
|
* will be freed shortly anyway.
|
|
|
|
*/
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
list_del(&uwq.wq.entry);
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ctx may go away after this if the userfault pseudo fd is
|
|
|
|
* already released.
|
|
|
|
*/
|
|
|
|
userfaultfd_ctx_put(ctx);
|
|
|
|
|
2015-09-04 15:46:41 -07:00
|
|
|
out:
|
|
|
|
return ret;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
2017-03-09 17:16:54 -07:00
|
|
|
static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
|
|
|
|
struct userfaultfd_wait_queue *ewq)
|
2017-02-22 16:42:21 -07:00
|
|
|
{
|
2018-01-04 17:18:09 -07:00
|
|
|
struct userfaultfd_ctx *release_new_ctx;
|
|
|
|
|
2017-03-09 17:16:52 -07:00
|
|
|
if (WARN_ON_ONCE(current->flags & PF_EXITING))
|
|
|
|
goto out;
|
2017-02-22 16:42:21 -07:00
|
|
|
|
|
|
|
ewq->ctx = ctx;
|
|
|
|
init_waitqueue_entry(&ewq->wq, current);
|
2018-01-04 17:18:09 -07:00
|
|
|
release_new_ctx = NULL;
|
2017-02-22 16:42:21 -07:00
|
|
|
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->event_wqh.lock);
|
2017-02-22 16:42:21 -07:00
|
|
|
/*
|
|
|
|
* After the __add_wait_queue the uwq is visible to userland
|
|
|
|
* through poll/read().
|
|
|
|
*/
|
|
|
|
__add_wait_queue(&ctx->event_wqh, &ewq->wq);
|
|
|
|
for (;;) {
|
|
|
|
set_current_state(TASK_KILLABLE);
|
|
|
|
if (ewq->msg.event == 0)
|
|
|
|
break;
|
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE()
Please do not apply this to mainline directly, instead please re-run the
coccinelle script shown below and apply its output.
For several reasons, it is desirable to use {READ,WRITE}_ONCE() in
preference to ACCESS_ONCE(), and new code is expected to use one of the
former. So far, there's been no reason to change most existing uses of
ACCESS_ONCE(), as these aren't harmful, and changing them results in
churn.
However, for some features, the read/write distinction is critical to
correct operation. To distinguish these cases, separate read/write
accessors must be used. This patch migrates (most) remaining
ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following
coccinelle script:
----
// Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and
// WRITE_ONCE()
// $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch
virtual patch
@ depends on patch @
expression E1, E2;
@@
- ACCESS_ONCE(E1) = E2
+ WRITE_ONCE(E1, E2)
@ depends on patch @
expression E;
@@
- ACCESS_ONCE(E)
+ READ_ONCE(E)
----
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: linux-arch@vger.kernel.org
Cc: mpe@ellerman.id.au
Cc: shuah@kernel.org
Cc: snitzer@redhat.com
Cc: thor.thayer@linux.intel.com
Cc: tj@kernel.org
Cc: viro@zeniv.linux.org.uk
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-23 14:07:29 -07:00
|
|
|
if (READ_ONCE(ctx->released) ||
|
2017-02-22 16:42:21 -07:00
|
|
|
fatal_signal_pending(current)) {
|
2017-10-03 16:15:38 -07:00
|
|
|
/*
|
|
|
|
* &ewq->wq may be queued in fork_event, but
|
|
|
|
* __remove_wait_queue ignores the head
|
|
|
|
* parameter. It would be a problem if it
|
|
|
|
* didn't.
|
|
|
|
*/
|
2017-02-22 16:42:21 -07:00
|
|
|
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
|
2017-03-09 17:17:09 -07:00
|
|
|
if (ewq->msg.event == UFFD_EVENT_FORK) {
|
|
|
|
struct userfaultfd_ctx *new;
|
|
|
|
|
|
|
|
new = (struct userfaultfd_ctx *)
|
|
|
|
(unsigned long)
|
|
|
|
ewq->msg.arg.reserved.reserved1;
|
2018-01-04 17:18:09 -07:00
|
|
|
release_new_ctx = new;
|
2017-03-09 17:17:09 -07:00
|
|
|
}
|
2017-02-22 16:42:21 -07:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->event_wqh.lock);
|
2017-02-22 16:42:21 -07:00
|
|
|
|
2018-02-11 15:34:03 -07:00
|
|
|
wake_up_poll(&ctx->fd_wqh, EPOLLIN);
|
2017-02-22 16:42:21 -07:00
|
|
|
schedule();
|
|
|
|
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->event_wqh.lock);
|
2017-02-22 16:42:21 -07:00
|
|
|
}
|
|
|
|
__set_current_state(TASK_RUNNING);
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->event_wqh.lock);
|
2017-02-22 16:42:21 -07:00
|
|
|
|
2018-01-04 17:18:09 -07:00
|
|
|
if (release_new_ctx) {
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
userfaultfd_release_new(release_new_ctx);
|
2018-01-04 17:18:09 -07:00
|
|
|
userfaultfd_ctx_put(release_new_ctx);
|
|
|
|
}
|
|
|
|
|
2017-02-22 16:42:21 -07:00
|
|
|
/*
|
|
|
|
* ctx may go away after this if the userfault pseudo fd is
|
|
|
|
* already released.
|
|
|
|
*/
|
2017-03-09 17:16:52 -07:00
|
|
|
out:
|
2021-09-02 14:58:56 -07:00
|
|
|
atomic_dec(&ctx->mmap_changing);
|
|
|
|
VM_BUG_ON(atomic_read(&ctx->mmap_changing) < 0);
|
2017-02-22 16:42:21 -07:00
|
|
|
userfaultfd_ctx_put(ctx);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
|
|
|
|
struct userfaultfd_wait_queue *ewq)
|
|
|
|
{
|
|
|
|
ewq->msg.event = 0;
|
|
|
|
wake_up_locked(&ctx->event_wqh);
|
|
|
|
__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
|
|
|
|
}
|
|
|
|
|
2017-02-22 16:42:27 -07:00
|
|
|
int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
|
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx = NULL, *octx;
|
|
|
|
struct userfaultfd_fork_ctx *fctx;
|
|
|
|
|
|
|
|
octx = vma->vm_userfaultfd_ctx.ctx;
|
2024-03-27 02:08:35 -07:00
|
|
|
if (!octx)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
if (!(octx->features & UFFD_FEATURE_EVENT_FORK)) {
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
userfaultfd_reset_ctx(vma);
|
2017-02-22 16:42:27 -07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
list_for_each_entry(fctx, fcs, list)
|
|
|
|
if (fctx->orig == octx) {
|
|
|
|
ctx = fctx->new;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!ctx) {
|
|
|
|
fctx = kmalloc(sizeof(*fctx), GFP_KERNEL);
|
|
|
|
if (!fctx)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
|
|
|
|
if (!ctx) {
|
|
|
|
kfree(fctx);
|
|
|
|
return -ENOMEM;
|
|
|
|
}
|
|
|
|
|
2018-12-28 01:34:43 -07:00
|
|
|
refcount_set(&ctx->refcount, 1);
|
2017-02-22 16:42:27 -07:00
|
|
|
ctx->flags = octx->flags;
|
|
|
|
ctx->features = octx->features;
|
|
|
|
ctx->released = false;
|
2024-02-15 11:27:54 -07:00
|
|
|
init_rwsem(&ctx->map_changing_lock);
|
2021-09-02 14:58:56 -07:00
|
|
|
atomic_set(&ctx->mmap_changing, 0);
|
2017-02-22 16:42:27 -07:00
|
|
|
ctx->mm = vma->vm_mm;
|
2017-11-15 18:36:56 -07:00
|
|
|
mmgrab(ctx->mm);
|
2017-02-22 16:42:27 -07:00
|
|
|
|
|
|
|
userfaultfd_ctx_get(octx);
|
2024-02-15 11:27:54 -07:00
|
|
|
down_write(&octx->map_changing_lock);
|
2021-09-02 14:58:56 -07:00
|
|
|
atomic_inc(&octx->mmap_changing);
|
2024-02-15 11:27:54 -07:00
|
|
|
up_write(&octx->map_changing_lock);
|
2017-02-22 16:42:27 -07:00
|
|
|
fctx->orig = octx;
|
|
|
|
fctx->new = ctx;
|
|
|
|
list_add_tail(&fctx->list, fcs);
|
|
|
|
}
|
|
|
|
|
|
|
|
vma->vm_userfaultfd_ctx.ctx = ctx;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-03-09 17:16:54 -07:00
|
|
|
static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
|
2017-02-22 16:42:27 -07:00
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx = fctx->orig;
|
|
|
|
struct userfaultfd_wait_queue ewq;
|
|
|
|
|
|
|
|
msg_init(&ewq.msg);
|
|
|
|
|
|
|
|
ewq.msg.event = UFFD_EVENT_FORK;
|
|
|
|
ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
|
|
|
|
|
2017-03-09 17:16:54 -07:00
|
|
|
userfaultfd_event_wait_completion(ctx, &ewq);
|
2017-02-22 16:42:27 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
void dup_userfaultfd_complete(struct list_head *fcs)
|
|
|
|
{
|
|
|
|
struct userfaultfd_fork_ctx *fctx, *n;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(fctx, n, fcs, list) {
|
2017-03-09 17:16:54 -07:00
|
|
|
dup_fctx(fctx);
|
2017-02-22 16:42:27 -07:00
|
|
|
list_del(&fctx->list);
|
|
|
|
kfree(fctx);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
fork: do not invoke uffd on fork if error occurs
Patch series "fork: do not expose incomplete mm on fork".
During fork we may place the virtual memory address space into an
inconsistent state before the fork operation is complete.
In addition, we may encounter an error during the fork operation that
indicates that the virtual memory address space is invalidated.
As a result, we should not be exposing it in any way to external machinery
that might interact with the mm or VMAs, machinery that is not designed to
deal with incomplete state.
We specifically update the fork logic to defer khugepaged and ksm to the
end of the operation and only to be invoked if no error arose, and
disallow uffd from observing fork events should an error have occurred.
This patch (of 2):
Currently on fork we expose the virtual address space of a process to
userland unconditionally if uffd is registered in VMAs, regardless of
whether an error arose in the fork.
This is performed in dup_userfaultfd_complete() which is invoked
unconditionally, and performs two duties - invoking registered handlers
for the UFFD_EVENT_FORK event via dup_fctx(), and clearing down
userfaultfd_fork_ctx objects established in dup_userfaultfd().
This is problematic, because the virtual address space may not yet be
correctly initialised if an error arose.
The change in commit d24062914837 ("fork: use __mt_dup() to duplicate
maple tree in dup_mmap()") makes this more pertinent as we may be in a
state where entries in the maple tree are not yet consistent.
We address this by, on fork error, ensuring that we roll back state that
we would otherwise expect to clean up through the event being handled by
userland and perform the memory freeing duty otherwise performed by
dup_userfaultfd_complete().
We do this by implementing a new function, dup_userfaultfd_fail(), which
performs the same loop, only decrementing reference counts.
Note that we perform mmgrab() on the parent and child mm's, however
userfaultfd_ctx_put() will mmdrop() this once the reference count drops to
zero, so we will avoid memory leaks correctly here.
Link: https://lkml.kernel.org/r/cover.1729014377.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/d3691d58bb58712b6fb3df2be441d175bd3cdf07.1729014377.git.lorenzo.stoakes@oracle.com
Fixes: d24062914837 ("fork: use __mt_dup() to duplicate maple tree in dup_mmap()")
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reported-by: Jann Horn <jannh@google.com>
Reviewed-by: Jann Horn <jannh@google.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Linus Torvalds <torvalds@linuxfoundation.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-10-15 10:56:05 -07:00
|
|
|
void dup_userfaultfd_fail(struct list_head *fcs)
|
|
|
|
{
|
|
|
|
struct userfaultfd_fork_ctx *fctx, *n;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* An error has occurred on fork, we will tear memory down, but have
|
|
|
|
* allocated memory for fctx's and raised reference counts for both the
|
|
|
|
* original and child contexts (and on the mm for each as a result).
|
|
|
|
*
|
|
|
|
* These would ordinarily be taken care of by a user handling the event,
|
|
|
|
* but we are no longer doing so, so manually clean up here.
|
|
|
|
*
|
|
|
|
* mm tear down will take care of cleaning up VMA contexts.
|
|
|
|
*/
|
|
|
|
list_for_each_entry_safe(fctx, n, fcs, list) {
|
|
|
|
struct userfaultfd_ctx *octx = fctx->orig;
|
|
|
|
struct userfaultfd_ctx *ctx = fctx->new;
|
|
|
|
|
|
|
|
atomic_dec(&octx->mmap_changing);
|
|
|
|
VM_BUG_ON(atomic_read(&octx->mmap_changing) < 0);
|
|
|
|
userfaultfd_ctx_put(octx);
|
|
|
|
userfaultfd_ctx_put(ctx);
|
|
|
|
|
|
|
|
list_del(&fctx->list);
|
|
|
|
kfree(fctx);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-02-22 16:42:34 -07:00
|
|
|
void mremap_userfaultfd_prep(struct vm_area_struct *vma,
|
|
|
|
struct vm_userfaultfd_ctx *vm_ctx)
|
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx;
|
|
|
|
|
|
|
|
ctx = vma->vm_userfaultfd_ctx.ctx;
|
2018-12-28 01:38:47 -07:00
|
|
|
|
|
|
|
if (!ctx)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (ctx->features & UFFD_FEATURE_EVENT_REMAP) {
|
2017-02-22 16:42:34 -07:00
|
|
|
vm_ctx->ctx = ctx;
|
|
|
|
userfaultfd_ctx_get(ctx);
|
2024-02-15 11:27:54 -07:00
|
|
|
down_write(&ctx->map_changing_lock);
|
2021-09-02 14:58:56 -07:00
|
|
|
atomic_inc(&ctx->mmap_changing);
|
2024-02-15 11:27:54 -07:00
|
|
|
up_write(&ctx->map_changing_lock);
|
2018-12-28 01:38:47 -07:00
|
|
|
} else {
|
|
|
|
/* Drop uffd context if remap feature not enabled */
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
userfaultfd_reset_ctx(vma);
|
2017-02-22 16:42:34 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2017-02-22 16:42:37 -07:00
|
|
|
void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
|
2017-02-22 16:42:34 -07:00
|
|
|
unsigned long from, unsigned long to,
|
|
|
|
unsigned long len)
|
|
|
|
{
|
2017-02-22 16:42:37 -07:00
|
|
|
struct userfaultfd_ctx *ctx = vm_ctx->ctx;
|
2017-02-22 16:42:34 -07:00
|
|
|
struct userfaultfd_wait_queue ewq;
|
|
|
|
|
|
|
|
if (!ctx)
|
|
|
|
return;
|
|
|
|
|
|
|
|
if (to & ~PAGE_MASK) {
|
|
|
|
userfaultfd_ctx_put(ctx);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
msg_init(&ewq.msg);
|
|
|
|
|
|
|
|
ewq.msg.event = UFFD_EVENT_REMAP;
|
|
|
|
ewq.msg.arg.remap.from = from;
|
|
|
|
ewq.msg.arg.remap.to = to;
|
|
|
|
ewq.msg.arg.remap.len = len;
|
|
|
|
|
|
|
|
userfaultfd_event_wait_completion(ctx, &ewq);
|
|
|
|
}
|
|
|
|
|
2017-03-09 17:17:11 -07:00
|
|
|
bool userfaultfd_remove(struct vm_area_struct *vma,
|
2017-02-24 15:56:02 -07:00
|
|
|
unsigned long start, unsigned long end)
|
2017-02-22 16:42:40 -07:00
|
|
|
{
|
|
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
|
|
struct userfaultfd_ctx *ctx;
|
|
|
|
struct userfaultfd_wait_queue ewq;
|
|
|
|
|
|
|
|
ctx = vma->vm_userfaultfd_ctx.ctx;
|
2017-02-24 15:56:02 -07:00
|
|
|
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
|
2017-03-09 17:17:11 -07:00
|
|
|
return true;
|
2017-02-22 16:42:40 -07:00
|
|
|
|
|
|
|
userfaultfd_ctx_get(ctx);
|
2024-02-15 11:27:54 -07:00
|
|
|
down_write(&ctx->map_changing_lock);
|
2021-09-02 14:58:56 -07:00
|
|
|
atomic_inc(&ctx->mmap_changing);
|
2024-02-15 11:27:54 -07:00
|
|
|
up_write(&ctx->map_changing_lock);
|
2020-06-08 21:33:25 -07:00
|
|
|
mmap_read_unlock(mm);
|
2017-02-22 16:42:40 -07:00
|
|
|
|
|
|
|
msg_init(&ewq.msg);
|
|
|
|
|
2017-02-24 15:56:02 -07:00
|
|
|
ewq.msg.event = UFFD_EVENT_REMOVE;
|
|
|
|
ewq.msg.arg.remove.start = start;
|
|
|
|
ewq.msg.arg.remove.end = end;
|
2017-02-22 16:42:40 -07:00
|
|
|
|
|
|
|
userfaultfd_event_wait_completion(ctx, &ewq);
|
|
|
|
|
2017-03-09 17:17:11 -07:00
|
|
|
return false;
|
2017-02-22 16:42:40 -07:00
|
|
|
}
|
|
|
|
|
2017-02-24 15:58:22 -07:00
|
|
|
static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
|
|
|
|
unsigned long start, unsigned long end)
|
|
|
|
{
|
|
|
|
struct userfaultfd_unmap_ctx *unmap_ctx;
|
|
|
|
|
|
|
|
list_for_each_entry(unmap_ctx, unmaps, list)
|
|
|
|
if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
|
|
|
|
unmap_ctx->end == end)
|
|
|
|
return true;
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2023-05-31 18:54:02 -07:00
|
|
|
int userfaultfd_unmap_prep(struct vm_area_struct *vma, unsigned long start,
|
2022-09-06 12:48:57 -07:00
|
|
|
unsigned long end, struct list_head *unmaps)
|
2017-02-24 15:58:22 -07:00
|
|
|
{
|
2023-05-31 18:54:02 -07:00
|
|
|
struct userfaultfd_unmap_ctx *unmap_ctx;
|
|
|
|
struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
|
2017-02-24 15:58:22 -07:00
|
|
|
|
2023-05-31 18:54:02 -07:00
|
|
|
if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
|
|
|
|
has_unmap_ctx(ctx, unmaps, start, end))
|
|
|
|
return 0;
|
2017-02-24 15:58:22 -07:00
|
|
|
|
2023-05-31 18:54:02 -07:00
|
|
|
unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
|
|
|
|
if (!unmap_ctx)
|
|
|
|
return -ENOMEM;
|
2017-02-24 15:58:22 -07:00
|
|
|
|
2023-05-31 18:54:02 -07:00
|
|
|
userfaultfd_ctx_get(ctx);
|
2024-02-15 11:27:54 -07:00
|
|
|
down_write(&ctx->map_changing_lock);
|
2023-05-31 18:54:02 -07:00
|
|
|
atomic_inc(&ctx->mmap_changing);
|
2024-02-15 11:27:54 -07:00
|
|
|
up_write(&ctx->map_changing_lock);
|
2023-05-31 18:54:02 -07:00
|
|
|
unmap_ctx->ctx = ctx;
|
|
|
|
unmap_ctx->start = start;
|
|
|
|
unmap_ctx->end = end;
|
|
|
|
list_add_tail(&unmap_ctx->list, unmaps);
|
2017-02-24 15:58:22 -07:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
|
|
|
|
{
|
|
|
|
struct userfaultfd_unmap_ctx *ctx, *n;
|
|
|
|
struct userfaultfd_wait_queue ewq;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(ctx, n, uf, list) {
|
|
|
|
msg_init(&ewq.msg);
|
|
|
|
|
|
|
|
ewq.msg.event = UFFD_EVENT_UNMAP;
|
|
|
|
ewq.msg.arg.remove.start = ctx->start;
|
|
|
|
ewq.msg.arg.remove.end = ctx->end;
|
|
|
|
|
|
|
|
userfaultfd_event_wait_completion(ctx->ctx, &ewq);
|
|
|
|
|
|
|
|
list_del(&ctx->list);
|
|
|
|
kfree(ctx);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
static int userfaultfd_release(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx = file->private_data;
|
|
|
|
struct mm_struct *mm = ctx->mm;
|
|
|
|
/* len == 0 means wake all */
|
|
|
|
struct userfaultfd_wake_range range = { .len = 0, };
|
|
|
|
|
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE()
Please do not apply this to mainline directly, instead please re-run the
coccinelle script shown below and apply its output.
For several reasons, it is desirable to use {READ,WRITE}_ONCE() in
preference to ACCESS_ONCE(), and new code is expected to use one of the
former. So far, there's been no reason to change most existing uses of
ACCESS_ONCE(), as these aren't harmful, and changing them results in
churn.
However, for some features, the read/write distinction is critical to
correct operation. To distinguish these cases, separate read/write
accessors must be used. This patch migrates (most) remaining
ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following
coccinelle script:
----
// Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and
// WRITE_ONCE()
// $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch
virtual patch
@ depends on patch @
expression E1, E2;
@@
- ACCESS_ONCE(E1) = E2
+ WRITE_ONCE(E1, E2)
@ depends on patch @
expression E;
@@
- ACCESS_ONCE(E)
+ READ_ONCE(E)
----
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: linux-arch@vger.kernel.org
Cc: mpe@ellerman.id.au
Cc: shuah@kernel.org
Cc: snitzer@redhat.com
Cc: thor.thayer@linux.intel.com
Cc: tj@kernel.org
Cc: viro@zeniv.linux.org.uk
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-23 14:07:29 -07:00
|
|
|
WRITE_ONCE(ctx->released, true);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
userfaultfd_release_all(mm, ctx);
|
mm: abstract the vma_merge()/split_vma() pattern for mprotect() et al.
mprotect() and other functions which change VMA parameters over a range
each employ a pattern of:-
1. Attempt to merge the range with adjacent VMAs.
2. If this fails, and the range spans a subset of the VMA, split it
accordingly.
This is open-coded and duplicated in each case. Also in each case most of
the parameters passed to vma_merge() remain the same.
Create a new function, vma_modify(), which abstracts this operation,
accepting only those parameters which can be changed.
To avoid the mess of invoking each function call with unnecessary
parameters, create inline wrapper functions for each of the modify
operations, parameterised only by what is required to perform the action.
We can also significantly simplify the logic - by returning the VMA if we
split (or merged VMA if we do not) we no longer need specific handling for
merge/split cases in any of the call sites.
Note that the userfaultfd_release() case works even though it does not
split VMAs - since start is set to vma->vm_start and end is set to
vma->vm_end, the split logic does not trigger.
In addition, since we calculate pgoff to be equal to vma->vm_pgoff + (start
- vma->vm_start) >> PAGE_SHIFT, and start - vma->vm_start will be 0 in this
instance, this invocation will remain unchanged.
We eliminate a VM_WARN_ON() in mprotect_fixup() as this simply asserts that
vma_merge() correctly ensures that flags remain the same, something that is
already checked in is_mergeable_vma() and elsewhere, and in any case is not
specific to mprotect().
Link: https://lkml.kernel.org/r/0dfa9368f37199a423674bf0ee312e8ea0619044.1697043508.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-11 10:04:28 -07:00
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
2015-09-04 15:46:44 -07:00
|
|
|
* After no new page faults can wait on this fault_*wqh, flush
|
2015-09-04 15:46:31 -07:00
|
|
|
* the last page faults that may have been already waiting on
|
2015-09-04 15:46:44 -07:00
|
|
|
* the fault_*wqh.
|
2015-09-04 15:46:31 -07:00
|
|
|
*/
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-22 14:58:49 -07:00
|
|
|
__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
|
2018-08-21 21:56:30 -07:00
|
|
|
__wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range);
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2017-08-02 13:32:24 -07:00
|
|
|
/* Flush pending events that may still wait on event_wqh */
|
|
|
|
wake_up_all(&ctx->event_wqh);
|
|
|
|
|
2018-02-11 15:34:03 -07:00
|
|
|
wake_up_poll(&ctx->fd_wqh, EPOLLHUP);
|
2015-09-04 15:46:31 -07:00
|
|
|
userfaultfd_ctx_put(ctx);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:44 -07:00
|
|
|
/* fault_pending_wqh.lock must be hold by the caller */
|
2017-02-22 16:42:18 -07:00
|
|
|
static inline struct userfaultfd_wait_queue *find_userfault_in(
|
|
|
|
wait_queue_head_t *wqh)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
2017-06-20 03:06:13 -07:00
|
|
|
wait_queue_entry_t *wq;
|
2015-09-04 15:46:44 -07:00
|
|
|
struct userfaultfd_wait_queue *uwq;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2018-10-04 23:45:44 -07:00
|
|
|
lockdep_assert_held(&wqh->lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2015-09-04 15:46:44 -07:00
|
|
|
uwq = NULL;
|
2017-02-22 16:42:18 -07:00
|
|
|
if (!waitqueue_active(wqh))
|
2015-09-04 15:46:44 -07:00
|
|
|
goto out;
|
|
|
|
/* walk in reverse to provide FIFO behavior to read userfaults */
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
wq = list_last_entry(&wqh->head, typeof(*wq), entry);
|
2015-09-04 15:46:44 -07:00
|
|
|
uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
|
|
|
|
out:
|
|
|
|
return uwq;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
2017-02-22 16:42:18 -07:00
|
|
|
|
|
|
|
static inline struct userfaultfd_wait_queue *find_userfault(
|
|
|
|
struct userfaultfd_ctx *ctx)
|
|
|
|
{
|
|
|
|
return find_userfault_in(&ctx->fault_pending_wqh);
|
|
|
|
}
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2017-02-22 16:42:21 -07:00
|
|
|
static inline struct userfaultfd_wait_queue *find_userfault_evt(
|
|
|
|
struct userfaultfd_ctx *ctx)
|
|
|
|
{
|
|
|
|
return find_userfault_in(&ctx->event_wqh);
|
|
|
|
}
|
|
|
|
|
2017-07-02 22:02:18 -07:00
|
|
|
static __poll_t userfaultfd_poll(struct file *file, poll_table *wait)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx = file->private_data;
|
2017-07-02 22:02:18 -07:00
|
|
|
__poll_t ret;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
poll_wait(file, &ctx->fd_wqh, wait);
|
|
|
|
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
if (!userfaultfd_is_initialized(ctx))
|
2018-02-11 15:34:03 -07:00
|
|
|
return EPOLLERR;
|
2017-02-22 16:42:21 -07:00
|
|
|
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
/*
|
|
|
|
* poll() never guarantees that read won't block.
|
|
|
|
* userfaults can be waken before they're read().
|
|
|
|
*/
|
|
|
|
if (unlikely(!(file->f_flags & O_NONBLOCK)))
|
2018-02-11 15:34:03 -07:00
|
|
|
return EPOLLERR;
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
/*
|
|
|
|
* lockless access to see if there are pending faults
|
|
|
|
* __pollwait last action is the add_wait_queue but
|
|
|
|
* the spin_unlock would allow the waitqueue_active to
|
|
|
|
* pass above the actual list_add inside
|
|
|
|
* add_wait_queue critical section. So use a full
|
|
|
|
* memory barrier to serialize the list_add write of
|
|
|
|
* add_wait_queue() with the waitqueue_active read
|
|
|
|
* below.
|
|
|
|
*/
|
|
|
|
ret = 0;
|
|
|
|
smp_mb();
|
|
|
|
if (waitqueue_active(&ctx->fault_pending_wqh))
|
|
|
|
ret = EPOLLIN;
|
|
|
|
else if (waitqueue_active(&ctx->event_wqh))
|
|
|
|
ret = EPOLLIN;
|
|
|
|
|
|
|
|
return ret;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
2017-02-22 16:42:27 -07:00
|
|
|
static const struct file_operations userfaultfd_fops;
|
|
|
|
|
2021-01-08 15:22:23 -07:00
|
|
|
static int resolve_userfault_fork(struct userfaultfd_ctx *new,
|
|
|
|
struct inode *inode,
|
2017-02-22 16:42:27 -07:00
|
|
|
struct uffd_msg *msg)
|
|
|
|
{
|
|
|
|
int fd;
|
|
|
|
|
fs: Rename anon_inode_getfile_secure() and anon_inode_getfd_secure()
The call to the inode_init_security_anon() LSM hook is not the sole
reason to use anon_inode_getfile_secure() or anon_inode_getfd_secure().
For example, the functions also allow one to create a file with non-zero
size, without needing a full-blown filesystem. In this case, you don't
need a "secure" version, just unique inodes; the current name of the
functions is confusing and does not explain well the difference with
the more "standard" anon_inode_getfile() and anon_inode_getfd().
Of course, there is another side of the coin; neither io_uring nor
userfaultfd strictly speaking need distinct inodes, and it is not
that clear anymore that anon_inode_create_get{file,fd}() allow the LSM
to intercept and block the inode's creation. If one was so inclined,
anon_inode_getfile_secure() and anon_inode_getfd_secure() could be kept,
using the shared inode or a new one depending on CONFIG_SECURITY.
However, this is probably overkill, and potentially a cause of bugs in
different configurations. Therefore, just add a comment to io_uring
and userfaultfd explaining the choice of the function.
While at it, remove the export for what is now anon_inode_create_getfd().
There is no in-tree module that uses it, and the old name is gone anyway.
If anybody actually needs the symbol, they can ask or they can just use
anon_inode_create_getfile(), which will be exported very soon for use
in KVM.
Suggested-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2023-11-03 03:47:51 -07:00
|
|
|
fd = anon_inode_create_getfd("[userfaultfd]", &userfaultfd_fops, new,
|
2022-07-08 02:34:51 -07:00
|
|
|
O_RDONLY | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
|
2017-02-22 16:42:27 -07:00
|
|
|
if (fd < 0)
|
|
|
|
return fd;
|
|
|
|
|
|
|
|
msg->arg.reserved.reserved1 = 0;
|
|
|
|
msg->arg.fork.ufd = fd;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
|
2021-01-08 15:22:23 -07:00
|
|
|
struct uffd_msg *msg, struct inode *inode)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
|
|
|
ssize_t ret;
|
|
|
|
DECLARE_WAITQUEUE(wait, current);
|
2015-09-04 15:46:44 -07:00
|
|
|
struct userfaultfd_wait_queue *uwq;
|
2017-02-22 16:42:27 -07:00
|
|
|
/*
|
|
|
|
* Handling fork event requires sleeping operations, so
|
|
|
|
* we drop the event_wqh lock, then do these ops, then
|
|
|
|
* lock it back and wake up the waiter. While the lock is
|
|
|
|
* dropped the ewq may go away so we keep track of it
|
|
|
|
* carefully.
|
|
|
|
*/
|
|
|
|
LIST_HEAD(fork_event);
|
|
|
|
struct userfaultfd_ctx *fork_nctx = NULL;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2015-09-04 15:46:44 -07:00
|
|
|
/* always take the fd_wqh lock before the fault_pending_wqh lock */
|
2018-10-26 15:02:19 -07:00
|
|
|
spin_lock_irq(&ctx->fd_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
__add_wait_queue(&ctx->fd_wqh, &wait);
|
|
|
|
for (;;) {
|
|
|
|
set_current_state(TASK_INTERRUPTIBLE);
|
2015-09-04 15:46:44 -07:00
|
|
|
spin_lock(&ctx->fault_pending_wqh.lock);
|
|
|
|
uwq = find_userfault(ctx);
|
|
|
|
if (uwq) {
|
2015-09-04 15:47:23 -07:00
|
|
|
/*
|
|
|
|
* Use a seqcount to repeat the lockless check
|
|
|
|
* in wake_userfault() to avoid missing
|
|
|
|
* wakeups because during the refile both
|
|
|
|
* waitqueue could become empty if this is the
|
|
|
|
* only userfault.
|
|
|
|
*/
|
|
|
|
write_seqcount_begin(&ctx->refile_seq);
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
2015-09-04 15:46:44 -07:00
|
|
|
* The fault_pending_wqh.lock prevents the uwq
|
|
|
|
* to disappear from under us.
|
|
|
|
*
|
|
|
|
* Refile this userfault from
|
|
|
|
* fault_pending_wqh to fault_wqh, it's not
|
|
|
|
* pending anymore after we read it.
|
|
|
|
*
|
|
|
|
* Use list_del() by hand (as
|
|
|
|
* userfaultfd_wake_function also uses
|
|
|
|
* list_del_init() by hand) to be sure nobody
|
|
|
|
* changes __remove_wait_queue() to use
|
|
|
|
* list_del_init() in turn breaking the
|
|
|
|
* !list_empty_careful() check in
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
* handle_userfault(). The uwq->wq.head list
|
2015-09-04 15:46:44 -07:00
|
|
|
* must never be empty at any time during the
|
|
|
|
* refile, or the waitqueue could disappear
|
|
|
|
* from under us. The "wait_queue_head_t"
|
|
|
|
* parameter of __remove_wait_queue() is unused
|
|
|
|
* anyway.
|
2015-09-04 15:46:31 -07:00
|
|
|
*/
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
list_del(&uwq->wq.entry);
|
2018-08-21 21:56:30 -07:00
|
|
|
add_wait_queue(&ctx->fault_wqh, &uwq->wq);
|
2015-09-04 15:46:44 -07:00
|
|
|
|
2015-09-04 15:47:23 -07:00
|
|
|
write_seqcount_end(&ctx->refile_seq);
|
|
|
|
|
2015-09-04 15:46:37 -07:00
|
|
|
/* careful to always initialize msg if ret == 0 */
|
|
|
|
*msg = uwq->msg;
|
2015-09-04 15:46:44 -07:00
|
|
|
spin_unlock(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
ret = 0;
|
|
|
|
break;
|
|
|
|
}
|
2015-09-04 15:46:44 -07:00
|
|
|
spin_unlock(&ctx->fault_pending_wqh.lock);
|
2017-02-22 16:42:21 -07:00
|
|
|
|
|
|
|
spin_lock(&ctx->event_wqh.lock);
|
|
|
|
uwq = find_userfault_evt(ctx);
|
|
|
|
if (uwq) {
|
|
|
|
*msg = uwq->msg;
|
|
|
|
|
2017-02-22 16:42:27 -07:00
|
|
|
if (uwq->msg.event == UFFD_EVENT_FORK) {
|
|
|
|
fork_nctx = (struct userfaultfd_ctx *)
|
|
|
|
(unsigned long)
|
|
|
|
uwq->msg.arg.reserved.reserved1;
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
list_move(&uwq->wq.entry, &fork_event);
|
2017-10-03 16:15:38 -07:00
|
|
|
/*
|
|
|
|
* fork_nctx can be freed as soon as
|
|
|
|
* we drop the lock, unless we take a
|
|
|
|
* reference on it.
|
|
|
|
*/
|
|
|
|
userfaultfd_ctx_get(fork_nctx);
|
2017-02-22 16:42:27 -07:00
|
|
|
spin_unlock(&ctx->event_wqh.lock);
|
|
|
|
ret = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
2017-02-22 16:42:21 -07:00
|
|
|
userfaultfd_event_complete(ctx, uwq);
|
|
|
|
spin_unlock(&ctx->event_wqh.lock);
|
|
|
|
ret = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
spin_unlock(&ctx->event_wqh.lock);
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
if (signal_pending(current)) {
|
|
|
|
ret = -ERESTARTSYS;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (no_wait) {
|
|
|
|
ret = -EAGAIN;
|
|
|
|
break;
|
|
|
|
}
|
2018-10-26 15:02:19 -07:00
|
|
|
spin_unlock_irq(&ctx->fd_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
schedule();
|
2018-10-26 15:02:19 -07:00
|
|
|
spin_lock_irq(&ctx->fd_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
__remove_wait_queue(&ctx->fd_wqh, &wait);
|
|
|
|
__set_current_state(TASK_RUNNING);
|
2018-10-26 15:02:19 -07:00
|
|
|
spin_unlock_irq(&ctx->fd_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2017-02-22 16:42:27 -07:00
|
|
|
if (!ret && msg->event == UFFD_EVENT_FORK) {
|
2021-01-08 15:22:23 -07:00
|
|
|
ret = resolve_userfault_fork(fork_nctx, inode, msg);
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->event_wqh.lock);
|
2017-10-03 16:15:38 -07:00
|
|
|
if (!list_empty(&fork_event)) {
|
|
|
|
/*
|
|
|
|
* The fork thread didn't abort, so we can
|
|
|
|
* drop the temporary refcount.
|
|
|
|
*/
|
|
|
|
userfaultfd_ctx_put(fork_nctx);
|
|
|
|
|
|
|
|
uwq = list_first_entry(&fork_event,
|
|
|
|
typeof(*uwq),
|
|
|
|
wq.entry);
|
|
|
|
/*
|
|
|
|
* If fork_event list wasn't empty and in turn
|
|
|
|
* the event wasn't already released by fork
|
|
|
|
* (the event is allocated on fork kernel
|
|
|
|
* stack), put the event back to its place in
|
|
|
|
* the event_wq. fork_event head will be freed
|
|
|
|
* as soon as we return so the event cannot
|
|
|
|
* stay queued there no matter the current
|
|
|
|
* "ret" value.
|
|
|
|
*/
|
|
|
|
list_del(&uwq->wq.entry);
|
|
|
|
__add_wait_queue(&ctx->event_wqh, &uwq->wq);
|
2017-02-22 16:42:27 -07:00
|
|
|
|
2017-10-03 16:15:38 -07:00
|
|
|
/*
|
|
|
|
* Leave the event in the waitqueue and report
|
|
|
|
* error to userland if we failed to resolve
|
|
|
|
* the userfault fork.
|
|
|
|
*/
|
|
|
|
if (likely(!ret))
|
2017-02-22 16:42:27 -07:00
|
|
|
userfaultfd_event_complete(ctx, uwq);
|
2017-10-03 16:15:38 -07:00
|
|
|
} else {
|
|
|
|
/*
|
|
|
|
* Here the fork thread aborted and the
|
|
|
|
* refcount from the fork thread on fork_nctx
|
|
|
|
* has already been released. We still hold
|
|
|
|
* the reference we took before releasing the
|
|
|
|
* lock above. If resolve_userfault_fork
|
|
|
|
* failed we've to drop it because the
|
|
|
|
* fork_nctx has to be freed in such case. If
|
|
|
|
* it succeeded we'll hold it because the new
|
|
|
|
* uffd references it.
|
|
|
|
*/
|
|
|
|
if (ret)
|
|
|
|
userfaultfd_ctx_put(fork_nctx);
|
2017-02-22 16:42:27 -07:00
|
|
|
}
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->event_wqh.lock);
|
2017-02-22 16:42:27 -07:00
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2024-04-02 11:26:41 -07:00
|
|
|
static ssize_t userfaultfd_read_iter(struct kiocb *iocb, struct iov_iter *to)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
2024-04-02 11:26:41 -07:00
|
|
|
struct file *file = iocb->ki_filp;
|
2015-09-04 15:46:31 -07:00
|
|
|
struct userfaultfd_ctx *ctx = file->private_data;
|
|
|
|
ssize_t _ret, ret = 0;
|
2015-09-04 15:46:37 -07:00
|
|
|
struct uffd_msg msg;
|
2021-01-08 15:22:23 -07:00
|
|
|
struct inode *inode = file_inode(file);
|
2024-04-02 11:26:41 -07:00
|
|
|
bool no_wait;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
if (!userfaultfd_is_initialized(ctx))
|
2015-09-04 15:46:31 -07:00
|
|
|
return -EINVAL;
|
|
|
|
|
2024-04-02 11:26:41 -07:00
|
|
|
no_wait = file->f_flags & O_NONBLOCK || iocb->ki_flags & IOCB_NOWAIT;
|
2015-09-04 15:46:31 -07:00
|
|
|
for (;;) {
|
2024-04-02 11:26:41 -07:00
|
|
|
if (iov_iter_count(to) < sizeof(msg))
|
2015-09-04 15:46:31 -07:00
|
|
|
return ret ? ret : -EINVAL;
|
2021-01-08 15:22:23 -07:00
|
|
|
_ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode);
|
2015-09-04 15:46:31 -07:00
|
|
|
if (_ret < 0)
|
|
|
|
return ret ? ret : _ret;
|
2024-04-02 11:26:41 -07:00
|
|
|
_ret = !copy_to_iter_full(&msg, sizeof(msg), to);
|
|
|
|
if (_ret)
|
2015-09-04 15:46:31 -07:00
|
|
|
return ret ? ret : -EFAULT;
|
2015-09-04 15:46:37 -07:00
|
|
|
ret += sizeof(msg);
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* Allow to read more than one fault at time but only
|
|
|
|
* block if waiting for the very first one.
|
|
|
|
*/
|
2024-04-02 11:26:41 -07:00
|
|
|
no_wait = true;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __wake_userfault(struct userfaultfd_ctx *ctx,
|
|
|
|
struct userfaultfd_wake_range *range)
|
|
|
|
{
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
/* wake all in the range and autoremove */
|
2015-09-04 15:46:44 -07:00
|
|
|
if (waitqueue_active(&ctx->fault_pending_wqh))
|
2015-09-22 14:58:49 -07:00
|
|
|
__wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
|
2015-09-04 15:46:44 -07:00
|
|
|
range);
|
|
|
|
if (waitqueue_active(&ctx->fault_wqh))
|
2018-08-21 21:56:30 -07:00
|
|
|
__wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range);
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
|
|
|
|
struct userfaultfd_wake_range *range)
|
|
|
|
{
|
2015-09-04 15:47:23 -07:00
|
|
|
unsigned seq;
|
|
|
|
bool need_wakeup;
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* To be sure waitqueue_active() is not reordered by the CPU
|
|
|
|
* before the pagetable update, use an explicit SMP memory
|
2020-06-08 21:33:51 -07:00
|
|
|
* barrier here. PT lock release or mmap_read_unlock(mm) still
|
2015-09-04 15:46:31 -07:00
|
|
|
* have release semantics that can allow the
|
|
|
|
* waitqueue_active() to be reordered before the pte update.
|
|
|
|
*/
|
|
|
|
smp_mb();
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Use waitqueue_active because it's very frequent to
|
|
|
|
* change the address space atomically even if there are no
|
|
|
|
* userfaults yet. So we take the spinlock only when we're
|
|
|
|
* sure we've userfaults to wake.
|
|
|
|
*/
|
2015-09-04 15:47:23 -07:00
|
|
|
do {
|
|
|
|
seq = read_seqcount_begin(&ctx->refile_seq);
|
|
|
|
need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
|
|
|
|
waitqueue_active(&ctx->fault_wqh);
|
|
|
|
cond_resched();
|
|
|
|
} while (read_seqcount_retry(&ctx->refile_seq, seq));
|
|
|
|
if (need_wakeup)
|
2015-09-04 15:46:31 -07:00
|
|
|
__wake_userfault(ctx, range);
|
|
|
|
}
|
|
|
|
|
2023-07-07 14:55:34 -07:00
|
|
|
static __always_inline int validate_unaligned_range(
|
|
|
|
struct mm_struct *mm, __u64 start, __u64 len)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
|
|
|
__u64 task_size = mm->task_size;
|
|
|
|
|
|
|
|
if (len & ~PAGE_MASK)
|
|
|
|
return -EINVAL;
|
|
|
|
if (!len)
|
|
|
|
return -EINVAL;
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
if (start < mmap_min_addr)
|
2015-09-04 15:46:31 -07:00
|
|
|
return -EINVAL;
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
if (start >= task_size)
|
2015-09-04 15:46:31 -07:00
|
|
|
return -EINVAL;
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
if (len > task_size - start)
|
2015-09-04 15:46:31 -07:00
|
|
|
return -EINVAL;
|
2023-07-07 14:55:34 -07:00
|
|
|
if (start + len <= start)
|
|
|
|
return -EINVAL;
|
2015-09-04 15:46:31 -07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2023-07-07 14:55:34 -07:00
|
|
|
static __always_inline int validate_range(struct mm_struct *mm,
|
|
|
|
__u64 start, __u64 len)
|
|
|
|
{
|
|
|
|
if (start & ~PAGE_MASK)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
return validate_unaligned_range(mm, start, len);
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
static int userfaultfd_register(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
struct mm_struct *mm = ctx->mm;
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
struct vm_area_struct *vma, *cur;
|
2015-09-04 15:46:31 -07:00
|
|
|
int ret;
|
|
|
|
struct uffdio_register uffdio_register;
|
|
|
|
struct uffdio_register __user *user_uffdio_register;
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
unsigned long vm_flags;
|
2015-09-04 15:46:31 -07:00
|
|
|
bool found;
|
2017-09-06 16:23:12 -07:00
|
|
|
bool basic_ioctls;
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
unsigned long start, end;
|
2023-01-20 09:26:17 -07:00
|
|
|
struct vma_iterator vmi;
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
bool wp_async = userfaultfd_wp_async_ctx(ctx);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
user_uffdio_register = (struct uffdio_register __user *) arg;
|
|
|
|
|
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(&uffdio_register, user_uffdio_register,
|
|
|
|
sizeof(uffdio_register)-sizeof(__u64)))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (!uffdio_register.mode)
|
|
|
|
goto out;
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES)
|
2015-09-04 15:46:31 -07:00
|
|
|
goto out;
|
|
|
|
vm_flags = 0;
|
|
|
|
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
|
|
|
|
vm_flags |= VM_UFFD_MISSING;
|
2021-06-30 18:49:06 -07:00
|
|
|
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP) {
|
|
|
|
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
|
|
|
|
goto out;
|
|
|
|
#endif
|
2015-09-04 15:46:31 -07:00
|
|
|
vm_flags |= VM_UFFD_WP;
|
2021-06-30 18:49:06 -07:00
|
|
|
}
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
|
|
|
|
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
|
|
|
|
goto out;
|
|
|
|
#endif
|
|
|
|
vm_flags |= VM_UFFD_MINOR;
|
|
|
|
}
|
2015-09-04 15:46:31 -07:00
|
|
|
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
ret = validate_range(mm, uffdio_register.range.start,
|
2015-09-04 15:46:31 -07:00
|
|
|
uffdio_register.range.len);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
start = uffdio_register.range.start;
|
|
|
|
end = start + uffdio_register.range.len;
|
|
|
|
|
2016-05-20 16:58:36 -07:00
|
|
|
ret = -ENOMEM;
|
|
|
|
if (!mmget_not_zero(mm))
|
|
|
|
goto out;
|
|
|
|
|
2023-01-20 09:26:17 -07:00
|
|
|
ret = -EINVAL;
|
2020-06-08 21:33:25 -07:00
|
|
|
mmap_write_lock(mm);
|
2023-01-20 09:26:17 -07:00
|
|
|
vma_iter_init(&vmi, mm, start);
|
|
|
|
vma = vma_find(&vmi, end);
|
2015-09-04 15:46:31 -07:00
|
|
|
if (!vma)
|
|
|
|
goto out_unlock;
|
|
|
|
|
2017-02-22 16:43:04 -07:00
|
|
|
/*
|
|
|
|
* If the first vma contains huge pages, make sure start address
|
|
|
|
* is aligned to huge page size.
|
|
|
|
*/
|
|
|
|
if (is_vm_hugetlb_page(vma)) {
|
|
|
|
unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
|
|
|
|
|
|
|
|
if (start & (vma_hpagesize - 1))
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* Search for not compatible vmas.
|
|
|
|
*/
|
|
|
|
found = false;
|
2017-09-06 16:23:12 -07:00
|
|
|
basic_ioctls = false;
|
2023-01-20 09:26:17 -07:00
|
|
|
cur = vma;
|
|
|
|
do {
|
2015-09-04 15:46:31 -07:00
|
|
|
cond_resched();
|
|
|
|
|
|
|
|
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
!!(cur->vm_flags & __VM_UFFD_FLAGS));
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
/* check not compatible vmas */
|
|
|
|
ret = -EINVAL;
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
if (!vma_can_userfault(cur, vm_flags, wp_async))
|
2015-09-04 15:46:31 -07:00
|
|
|
goto out_unlock;
|
2018-11-30 15:09:32 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* UFFDIO_COPY will fill file holes even without
|
|
|
|
* PROT_WRITE. This check enforces that if this is a
|
|
|
|
* MAP_SHARED, the process has write permission to the backing
|
|
|
|
* file. If VM_MAYWRITE is set it also enforces that on a
|
|
|
|
* MAP_SHARED vma: there is no F_WRITE_SEAL and no further
|
|
|
|
* F_WRITE_SEAL can be taken until the vma is destroyed.
|
|
|
|
*/
|
|
|
|
ret = -EPERM;
|
|
|
|
if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
|
|
|
|
goto out_unlock;
|
|
|
|
|
2017-02-22 16:43:04 -07:00
|
|
|
/*
|
|
|
|
* If this vma contains ending address, and huge pages
|
|
|
|
* check alignment.
|
|
|
|
*/
|
|
|
|
if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
|
|
|
|
end > cur->vm_start) {
|
|
|
|
unsigned long vma_hpagesize = vma_kernel_pagesize(cur);
|
|
|
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
|
|
|
|
if (end & (vma_hpagesize - 1))
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
2020-04-06 20:06:12 -07:00
|
|
|
if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE))
|
|
|
|
goto out_unlock;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Check that this vma isn't already owned by a
|
|
|
|
* different userfaultfd. We can't allow more than one
|
|
|
|
* userfaultfd to own a single vma simultaneously or we
|
|
|
|
* wouldn't know which one to deliver the userfaults to.
|
|
|
|
*/
|
|
|
|
ret = -EBUSY;
|
|
|
|
if (cur->vm_userfaultfd_ctx.ctx &&
|
|
|
|
cur->vm_userfaultfd_ctx.ctx != ctx)
|
|
|
|
goto out_unlock;
|
|
|
|
|
2017-02-22 16:43:04 -07:00
|
|
|
/*
|
|
|
|
* Note vmas containing huge pages
|
|
|
|
*/
|
2017-09-06 16:23:12 -07:00
|
|
|
if (is_vm_hugetlb_page(cur))
|
|
|
|
basic_ioctls = true;
|
2017-02-22 16:43:04 -07:00
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
found = true;
|
2023-01-20 09:26:17 -07:00
|
|
|
} for_each_vma_range(vmi, cur, end);
|
2015-09-04 15:46:31 -07:00
|
|
|
BUG_ON(!found);
|
|
|
|
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
ret = userfaultfd_register_range(ctx, vma, vm_flags, start, end,
|
|
|
|
wp_async);
|
2023-01-20 09:26:17 -07:00
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
out_unlock:
|
2020-06-08 21:33:25 -07:00
|
|
|
mmap_write_unlock(mm);
|
2016-05-20 16:58:36 -07:00
|
|
|
mmput(mm);
|
2015-09-04 15:46:31 -07:00
|
|
|
if (!ret) {
|
2020-04-06 20:06:29 -07:00
|
|
|
__u64 ioctls_out;
|
|
|
|
|
|
|
|
ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
|
|
|
|
UFFD_API_RANGE_IOCTLS;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Declare the WP ioctl only if the WP mode is
|
|
|
|
* specified and all checks passed with the range
|
|
|
|
*/
|
|
|
|
if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
|
|
|
|
ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
|
|
|
|
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
/* CONTINUE ioctl is only supported for MINOR ranges. */
|
|
|
|
if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR))
|
|
|
|
ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE);
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* Now that we scanned all vmas we can already tell
|
|
|
|
* userland which ioctls methods are guaranteed to
|
|
|
|
* succeed on this range.
|
|
|
|
*/
|
2020-04-06 20:06:29 -07:00
|
|
|
if (put_user(ioctls_out, &user_uffdio_register->ioctls))
|
2015-09-04 15:46:31 -07:00
|
|
|
ret = -EFAULT;
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
struct mm_struct *mm = ctx->mm;
|
|
|
|
struct vm_area_struct *vma, *prev, *cur;
|
|
|
|
int ret;
|
|
|
|
struct uffdio_range uffdio_unregister;
|
|
|
|
bool found;
|
|
|
|
unsigned long start, end, vma_end;
|
|
|
|
const void __user *buf = (void __user *)arg;
|
2023-01-20 09:26:17 -07:00
|
|
|
struct vma_iterator vmi;
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
bool wp_async = userfaultfd_wp_async_ctx(ctx);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
|
|
|
|
goto out;
|
|
|
|
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
ret = validate_range(mm, uffdio_unregister.start,
|
2015-09-04 15:46:31 -07:00
|
|
|
uffdio_unregister.len);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
start = uffdio_unregister.start;
|
|
|
|
end = start + uffdio_unregister.len;
|
|
|
|
|
2016-05-20 16:58:36 -07:00
|
|
|
ret = -ENOMEM;
|
|
|
|
if (!mmget_not_zero(mm))
|
|
|
|
goto out;
|
|
|
|
|
2020-06-08 21:33:25 -07:00
|
|
|
mmap_write_lock(mm);
|
2015-09-04 15:46:31 -07:00
|
|
|
ret = -EINVAL;
|
2023-01-20 09:26:17 -07:00
|
|
|
vma_iter_init(&vmi, mm, start);
|
|
|
|
vma = vma_find(&vmi, end);
|
|
|
|
if (!vma)
|
2015-09-04 15:46:31 -07:00
|
|
|
goto out_unlock;
|
|
|
|
|
2017-02-22 16:43:04 -07:00
|
|
|
/*
|
|
|
|
* If the first vma contains huge pages, make sure start address
|
|
|
|
* is aligned to huge page size.
|
|
|
|
*/
|
|
|
|
if (is_vm_hugetlb_page(vma)) {
|
|
|
|
unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
|
|
|
|
|
|
|
|
if (start & (vma_hpagesize - 1))
|
|
|
|
goto out_unlock;
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* Search for not compatible vmas.
|
|
|
|
*/
|
|
|
|
found = false;
|
2023-01-20 09:26:17 -07:00
|
|
|
cur = vma;
|
|
|
|
do {
|
2015-09-04 15:46:31 -07:00
|
|
|
cond_resched();
|
|
|
|
|
|
|
|
BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
!!(cur->vm_flags & __VM_UFFD_FLAGS));
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Check not compatible vmas, not strictly required
|
|
|
|
* here as not compatible vmas cannot have an
|
|
|
|
* userfaultfd_ctx registered on them, but this
|
|
|
|
* provides for more strict behavior to notice
|
|
|
|
* unregistration errors.
|
|
|
|
*/
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
if (!vma_can_userfault(cur, cur->vm_flags, wp_async))
|
2015-09-04 15:46:31 -07:00
|
|
|
goto out_unlock;
|
|
|
|
|
|
|
|
found = true;
|
2023-01-20 09:26:17 -07:00
|
|
|
} for_each_vma_range(vmi, cur, end);
|
2015-09-04 15:46:31 -07:00
|
|
|
BUG_ON(!found);
|
|
|
|
|
2023-01-20 09:26:17 -07:00
|
|
|
vma_iter_set(&vmi, start);
|
|
|
|
prev = vma_prev(&vmi);
|
2023-05-17 12:09:15 -07:00
|
|
|
if (vma->vm_start < start)
|
|
|
|
prev = vma;
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
ret = 0;
|
2023-01-20 09:26:17 -07:00
|
|
|
for_each_vma_range(vmi, vma, end) {
|
2015-09-04 15:46:31 -07:00
|
|
|
cond_resched();
|
|
|
|
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
BUG_ON(!vma_can_userfault(vma, vma->vm_flags, wp_async));
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Nothing to do: this vma is already registered into this
|
|
|
|
* userfaultfd and with the right tracking mode too.
|
|
|
|
*/
|
|
|
|
if (!vma->vm_userfaultfd_ctx.ctx)
|
|
|
|
goto skip;
|
|
|
|
|
2018-12-14 15:17:17 -07:00
|
|
|
WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
if (vma->vm_start > start)
|
|
|
|
start = vma->vm_start;
|
|
|
|
vma_end = min(end, vma->vm_end);
|
|
|
|
|
2017-02-22 16:42:46 -07:00
|
|
|
if (userfaultfd_missing(vma)) {
|
|
|
|
/*
|
|
|
|
* Wake any concurrent pending userfault while
|
|
|
|
* we unregister, so they will not hang
|
|
|
|
* permanently and it avoids userland to call
|
|
|
|
* UFFDIO_WAKE explicitly.
|
|
|
|
*/
|
|
|
|
struct userfaultfd_wake_range range;
|
|
|
|
range.start = start;
|
|
|
|
range.len = vma_end - start;
|
|
|
|
wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
|
|
|
|
}
|
|
|
|
|
userfaultfd: move core VMA manipulation logic to mm/userfaultfd.c
Patch series "Make core VMA operations internal and testable", v4.
There are a number of "core" VMA manipulation functions implemented in
mm/mmap.c, notably those concerning VMA merging, splitting, modifying,
expanding and shrinking, which logically don't belong there.
More importantly this functionality represents an internal implementation
detail of memory management and should not be exposed outside of mm/
itself.
This patch series isolates core VMA manipulation functionality into its
own file, mm/vma.c, and provides an API to the rest of the mm code in
mm/vma.h.
Importantly, it also carefully implements mm/vma_internal.h, which
specifies which headers need to be imported by vma.c, leading to the very
useful property that vma.c depends only on mm/vma.h and mm/vma_internal.h.
This means we can then re-implement vma_internal.h in userland, adding
shims for kernel mechanisms as required, allowing us to unit test internal
VMA functionality.
This testing is useful as opposed to an e.g. kunit implementation as this
way we can avoid all external kernel side-effects while testing, run tests
VERY quickly, and iterate on and debug problems quickly.
Excitingly this opens the door to, in the future, recreating precise
problems observed in production in userland and very quickly debugging
problems that might otherwise be very difficult to reproduce.
This patch series takes advantage of existing shim logic and full userland
maple tree support contained in tools/testing/radix-tree/ and
tools/include/linux/, separating out shared components of the radix tree
implementation to provide this testing.
Kernel functionality is stubbed and shimmed as needed in
tools/testing/vma/ which contains a fully functional userland
vma_internal.h file and which imports mm/vma.c and mm/vma.h to be directly
tested from userland.
A simple, skeleton testing implementation is provided in
tools/testing/vma/vma.c as a proof-of-concept, asserting that simple VMA
merge, modify (testing split), expand and shrink functionality work
correctly.
This patch (of 4):
This patch forms part of a patch series intending to separate out VMA
logic and render it testable from userspace, which requires that core
manipulation functions be exposed in an mm/-internal header file.
In order to do this, we must abstract APIs we wish to test, in this
instance functions which ultimately invoke vma_modify().
This patch therefore moves all logic which ultimately invokes vma_modify()
to mm/userfaultfd.c, trying to transfer code at a functional granularity
where possible.
[lorenzo.stoakes@oracle.com: fix user-after-free in userfaultfd_clear_vma()]
Link: https://lkml.kernel.org/r/3c947ddc-b804-49b7-8fe9-3ea3ca13def5@lucifer.local
Link: https://lkml.kernel.org/r/cover.1722251717.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/50c3ed995fd81c45876c86304c8a00bf3e396cfd.1722251717.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Higgins <brendanhiggins@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Gow <davidgow@google.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Kees Cook <kees@kernel.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Rae Moar <rmoar@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Pengfei Xu <pengfei.xu@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-29 04:50:35 -07:00
|
|
|
vma = userfaultfd_clear_vma(&vmi, prev, vma,
|
|
|
|
start, vma_end);
|
mm: abstract the vma_merge()/split_vma() pattern for mprotect() et al.
mprotect() and other functions which change VMA parameters over a range
each employ a pattern of:-
1. Attempt to merge the range with adjacent VMAs.
2. If this fails, and the range spans a subset of the VMA, split it
accordingly.
This is open-coded and duplicated in each case. Also in each case most of
the parameters passed to vma_merge() remain the same.
Create a new function, vma_modify(), which abstracts this operation,
accepting only those parameters which can be changed.
To avoid the mess of invoking each function call with unnecessary
parameters, create inline wrapper functions for each of the modify
operations, parameterised only by what is required to perform the action.
We can also significantly simplify the logic - by returning the VMA if we
split (or merged VMA if we do not) we no longer need specific handling for
merge/split cases in any of the call sites.
Note that the userfaultfd_release() case works even though it does not
split VMAs - since start is set to vma->vm_start and end is set to
vma->vm_end, the split logic does not trigger.
In addition, since we calculate pgoff to be equal to vma->vm_pgoff + (start
- vma->vm_start) >> PAGE_SHIFT, and start - vma->vm_start will be 0 in this
instance, this invocation will remain unchanged.
We eliminate a VM_WARN_ON() in mprotect_fixup() as this simply asserts that
vma_merge() correctly ensures that flags remain the same, something that is
already checked in is_mergeable_vma() and elsewhere, and in any case is not
specific to mprotect().
Link: https://lkml.kernel.org/r/0dfa9368f37199a423674bf0ee312e8ea0619044.1697043508.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-11 10:04:28 -07:00
|
|
|
if (IS_ERR(vma)) {
|
|
|
|
ret = PTR_ERR(vma);
|
|
|
|
break;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
mm: abstract the vma_merge()/split_vma() pattern for mprotect() et al.
mprotect() and other functions which change VMA parameters over a range
each employ a pattern of:-
1. Attempt to merge the range with adjacent VMAs.
2. If this fails, and the range spans a subset of the VMA, split it
accordingly.
This is open-coded and duplicated in each case. Also in each case most of
the parameters passed to vma_merge() remain the same.
Create a new function, vma_modify(), which abstracts this operation,
accepting only those parameters which can be changed.
To avoid the mess of invoking each function call with unnecessary
parameters, create inline wrapper functions for each of the modify
operations, parameterised only by what is required to perform the action.
We can also significantly simplify the logic - by returning the VMA if we
split (or merged VMA if we do not) we no longer need specific handling for
merge/split cases in any of the call sites.
Note that the userfaultfd_release() case works even though it does not
split VMAs - since start is set to vma->vm_start and end is set to
vma->vm_end, the split logic does not trigger.
In addition, since we calculate pgoff to be equal to vma->vm_pgoff + (start
- vma->vm_start) >> PAGE_SHIFT, and start - vma->vm_start will be 0 in this
instance, this invocation will remain unchanged.
We eliminate a VM_WARN_ON() in mprotect_fixup() as this simply asserts that
vma_merge() correctly ensures that flags remain the same, something that is
already checked in is_mergeable_vma() and elsewhere, and in any case is not
specific to mprotect().
Link: https://lkml.kernel.org/r/0dfa9368f37199a423674bf0ee312e8ea0619044.1697043508.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-10-11 10:04:28 -07:00
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
skip:
|
|
|
|
prev = vma;
|
|
|
|
start = vma->vm_end;
|
2023-01-20 09:26:17 -07:00
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
out_unlock:
|
2020-06-08 21:33:25 -07:00
|
|
|
mmap_write_unlock(mm);
|
2016-05-20 16:58:36 -07:00
|
|
|
mmput(mm);
|
2015-09-04 15:46:31 -07:00
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
2015-09-04 15:46:41 -07:00
|
|
|
* userfaultfd_wake may be used in combination with the
|
|
|
|
* UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches.
|
2015-09-04 15:46:31 -07:00
|
|
|
*/
|
|
|
|
static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct uffdio_range uffdio_wake;
|
|
|
|
struct userfaultfd_wake_range range;
|
|
|
|
const void __user *buf = (void __user *)arg;
|
|
|
|
|
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
|
|
|
|
goto out;
|
|
|
|
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
|
2015-09-04 15:46:31 -07:00
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
range.start = uffdio_wake.start;
|
|
|
|
range.len = uffdio_wake.len;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* len == 0 means wake all and we don't want to wake all here,
|
|
|
|
* so check it again to be sure.
|
|
|
|
*/
|
|
|
|
VM_BUG_ON(!range.len);
|
|
|
|
|
|
|
|
wake_userfault(ctx, &range);
|
|
|
|
ret = 0;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:47:11 -07:00
|
|
|
static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
__s64 ret;
|
|
|
|
struct uffdio_copy uffdio_copy;
|
|
|
|
struct uffdio_copy __user *user_uffdio_copy;
|
|
|
|
struct userfaultfd_wake_range range;
|
2023-03-14 15:12:49 -07:00
|
|
|
uffd_flags_t flags = 0;
|
2015-09-04 15:47:11 -07:00
|
|
|
|
|
|
|
user_uffdio_copy = (struct uffdio_copy __user *) arg;
|
|
|
|
|
userfaultfd: prevent non-cooperative events vs mcopy_atomic races
If a process monitored with userfaultfd changes it's memory mappings or
forks() at the same time as uffd monitor fills the process memory with
UFFDIO_COPY, the actual creation of page table entries and copying of
the data in mcopy_atomic may happen either before of after the memory
mapping modifications and there is no way for the uffd monitor to
maintain consistent view of the process memory layout.
For instance, let's consider fork() running in parallel with
userfaultfd_copy():
process | uffd monitor
---------------------------------+------------------------------
fork() | userfaultfd_copy()
... | ...
dup_mmap() | down_read(mmap_sem)
down_write(mmap_sem) | /* create PTEs, copy data */
dup_uffd() | up_read(mmap_sem)
copy_page_range() |
up_write(mmap_sem) |
dup_uffd_complete() |
/* notify monitor */ |
If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will
be present by the time copy_page_range() is called and they will appear
in the child's memory mappings. However, if the fork() is the first to
take the mmap_sem, the new pages won't be mapped in the child's address
space.
If the pages are not present and child tries to access them, the monitor
will get page fault notification and everything is fine. However, if
the pages *are present*, the child can access them without uffd
noticing. And if we copy them into child it'll see the wrong data.
Since we are talking about background copy, we'd need to decide whether
the pages should be copied or not regardless #PF notifications.
Since userfaultfd monitor has no way to determine what was the order,
let's disallow userfaultfd_copy in parallel with the non-cooperative
events. In such case we return -EAGAIN and the uffd monitor can
understand that userfaultfd_copy() clashed with a non-cooperative event
and take an appropriate action.
Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-07 17:09:25 -07:00
|
|
|
ret = -EAGAIN;
|
2021-09-02 14:58:56 -07:00
|
|
|
if (atomic_read(&ctx->mmap_changing))
|
userfaultfd: prevent non-cooperative events vs mcopy_atomic races
If a process monitored with userfaultfd changes it's memory mappings or
forks() at the same time as uffd monitor fills the process memory with
UFFDIO_COPY, the actual creation of page table entries and copying of
the data in mcopy_atomic may happen either before of after the memory
mapping modifications and there is no way for the uffd monitor to
maintain consistent view of the process memory layout.
For instance, let's consider fork() running in parallel with
userfaultfd_copy():
process | uffd monitor
---------------------------------+------------------------------
fork() | userfaultfd_copy()
... | ...
dup_mmap() | down_read(mmap_sem)
down_write(mmap_sem) | /* create PTEs, copy data */
dup_uffd() | up_read(mmap_sem)
copy_page_range() |
up_write(mmap_sem) |
dup_uffd_complete() |
/* notify monitor */ |
If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will
be present by the time copy_page_range() is called and they will appear
in the child's memory mappings. However, if the fork() is the first to
take the mmap_sem, the new pages won't be mapped in the child's address
space.
If the pages are not present and child tries to access them, the monitor
will get page fault notification and everything is fine. However, if
the pages *are present*, the child can access them without uffd
noticing. And if we copy them into child it'll see the wrong data.
Since we are talking about background copy, we'd need to decide whether
the pages should be copied or not regardless #PF notifications.
Since userfaultfd monitor has no way to determine what was the order,
let's disallow userfaultfd_copy in parallel with the non-cooperative
events. In such case we return -EAGAIN and the uffd monitor can
understand that userfaultfd_copy() clashed with a non-cooperative event
and take an appropriate action.
Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-07 17:09:25 -07:00
|
|
|
goto out;
|
|
|
|
|
2015-09-04 15:47:11 -07:00
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(&uffdio_copy, user_uffdio_copy,
|
|
|
|
/* don't copy "copy" last field */
|
|
|
|
sizeof(uffdio_copy)-sizeof(__s64)))
|
|
|
|
goto out;
|
|
|
|
|
2023-07-07 14:55:34 -07:00
|
|
|
ret = validate_unaligned_range(ctx->mm, uffdio_copy.src,
|
|
|
|
uffdio_copy.len);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
|
2015-09-04 15:47:11 -07:00
|
|
|
if (ret)
|
|
|
|
goto out;
|
2023-07-07 14:55:34 -07:00
|
|
|
|
2015-09-04 15:47:11 -07:00
|
|
|
ret = -EINVAL;
|
2020-04-06 20:05:41 -07:00
|
|
|
if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
|
2015-09-04 15:47:11 -07:00
|
|
|
goto out;
|
2023-03-14 15:12:49 -07:00
|
|
|
if (uffdio_copy.mode & UFFDIO_COPY_MODE_WP)
|
|
|
|
flags |= MFILL_ATOMIC_WP;
|
2016-05-20 16:58:36 -07:00
|
|
|
if (mmget_not_zero(ctx->mm)) {
|
2024-02-15 11:27:54 -07:00
|
|
|
ret = mfill_atomic_copy(ctx, uffdio_copy.dst, uffdio_copy.src,
|
|
|
|
uffdio_copy.len, flags);
|
2016-05-20 16:58:36 -07:00
|
|
|
mmput(ctx->mm);
|
2017-02-24 15:58:31 -07:00
|
|
|
} else {
|
2017-08-10 15:24:32 -07:00
|
|
|
return -ESRCH;
|
2016-05-20 16:58:36 -07:00
|
|
|
}
|
2015-09-04 15:47:11 -07:00
|
|
|
if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
|
|
|
|
return -EFAULT;
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
BUG_ON(!ret);
|
|
|
|
/* len == 0 would wake all */
|
|
|
|
range.len = ret;
|
|
|
|
if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
|
|
|
|
range.start = uffdio_copy.dst;
|
|
|
|
wake_userfault(ctx, &range);
|
|
|
|
}
|
|
|
|
ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
__s64 ret;
|
|
|
|
struct uffdio_zeropage uffdio_zeropage;
|
|
|
|
struct uffdio_zeropage __user *user_uffdio_zeropage;
|
|
|
|
struct userfaultfd_wake_range range;
|
|
|
|
|
|
|
|
user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
|
|
|
|
|
userfaultfd: prevent non-cooperative events vs mcopy_atomic races
If a process monitored with userfaultfd changes it's memory mappings or
forks() at the same time as uffd monitor fills the process memory with
UFFDIO_COPY, the actual creation of page table entries and copying of
the data in mcopy_atomic may happen either before of after the memory
mapping modifications and there is no way for the uffd monitor to
maintain consistent view of the process memory layout.
For instance, let's consider fork() running in parallel with
userfaultfd_copy():
process | uffd monitor
---------------------------------+------------------------------
fork() | userfaultfd_copy()
... | ...
dup_mmap() | down_read(mmap_sem)
down_write(mmap_sem) | /* create PTEs, copy data */
dup_uffd() | up_read(mmap_sem)
copy_page_range() |
up_write(mmap_sem) |
dup_uffd_complete() |
/* notify monitor */ |
If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will
be present by the time copy_page_range() is called and they will appear
in the child's memory mappings. However, if the fork() is the first to
take the mmap_sem, the new pages won't be mapped in the child's address
space.
If the pages are not present and child tries to access them, the monitor
will get page fault notification and everything is fine. However, if
the pages *are present*, the child can access them without uffd
noticing. And if we copy them into child it'll see the wrong data.
Since we are talking about background copy, we'd need to decide whether
the pages should be copied or not regardless #PF notifications.
Since userfaultfd monitor has no way to determine what was the order,
let's disallow userfaultfd_copy in parallel with the non-cooperative
events. In such case we return -EAGAIN and the uffd monitor can
understand that userfaultfd_copy() clashed with a non-cooperative event
and take an appropriate action.
Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-07 17:09:25 -07:00
|
|
|
ret = -EAGAIN;
|
2021-09-02 14:58:56 -07:00
|
|
|
if (atomic_read(&ctx->mmap_changing))
|
userfaultfd: prevent non-cooperative events vs mcopy_atomic races
If a process monitored with userfaultfd changes it's memory mappings or
forks() at the same time as uffd monitor fills the process memory with
UFFDIO_COPY, the actual creation of page table entries and copying of
the data in mcopy_atomic may happen either before of after the memory
mapping modifications and there is no way for the uffd monitor to
maintain consistent view of the process memory layout.
For instance, let's consider fork() running in parallel with
userfaultfd_copy():
process | uffd monitor
---------------------------------+------------------------------
fork() | userfaultfd_copy()
... | ...
dup_mmap() | down_read(mmap_sem)
down_write(mmap_sem) | /* create PTEs, copy data */
dup_uffd() | up_read(mmap_sem)
copy_page_range() |
up_write(mmap_sem) |
dup_uffd_complete() |
/* notify monitor */ |
If the userfaultfd_copy() takes the mmap_sem first, the new page(s) will
be present by the time copy_page_range() is called and they will appear
in the child's memory mappings. However, if the fork() is the first to
take the mmap_sem, the new pages won't be mapped in the child's address
space.
If the pages are not present and child tries to access them, the monitor
will get page fault notification and everything is fine. However, if
the pages *are present*, the child can access them without uffd
noticing. And if we copy them into child it'll see the wrong data.
Since we are talking about background copy, we'd need to decide whether
the pages should be copied or not regardless #PF notifications.
Since userfaultfd monitor has no way to determine what was the order,
let's disallow userfaultfd_copy in parallel with the non-cooperative
events. In such case we return -EAGAIN and the uffd monitor can
understand that userfaultfd_copy() clashed with a non-cooperative event
and take an appropriate action.
Link: http://lkml.kernel.org/r/1527061324-19949-1-git-send-email-rppt@linux.vnet.ibm.com
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Pavel Emelyanov <xemul@virtuozzo.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-06-07 17:09:25 -07:00
|
|
|
goto out;
|
|
|
|
|
2015-09-04 15:47:11 -07:00
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
|
|
|
|
/* don't copy "zeropage" last field */
|
|
|
|
sizeof(uffdio_zeropage)-sizeof(__s64)))
|
|
|
|
goto out;
|
|
|
|
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
|
2015-09-04 15:47:11 -07:00
|
|
|
uffdio_zeropage.range.len);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
|
|
|
|
goto out;
|
|
|
|
|
2016-05-20 16:58:36 -07:00
|
|
|
if (mmget_not_zero(ctx->mm)) {
|
2024-02-15 11:27:54 -07:00
|
|
|
ret = mfill_atomic_zeropage(ctx, uffdio_zeropage.range.start,
|
|
|
|
uffdio_zeropage.range.len);
|
2016-05-20 16:58:36 -07:00
|
|
|
mmput(ctx->mm);
|
2017-08-02 13:32:15 -07:00
|
|
|
} else {
|
2017-08-10 15:24:32 -07:00
|
|
|
return -ESRCH;
|
2016-05-20 16:58:36 -07:00
|
|
|
}
|
2015-09-04 15:47:11 -07:00
|
|
|
if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
|
|
|
|
return -EFAULT;
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
/* len == 0 would wake all */
|
|
|
|
BUG_ON(!ret);
|
|
|
|
range.len = ret;
|
|
|
|
if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
|
|
|
|
range.start = uffdio_zeropage.range.start;
|
|
|
|
wake_userfault(ctx, &range);
|
|
|
|
}
|
|
|
|
ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2020-04-06 20:06:12 -07:00
|
|
|
static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
struct uffdio_writeprotect uffdio_wp;
|
|
|
|
struct uffdio_writeprotect __user *user_uffdio_wp;
|
|
|
|
struct userfaultfd_wake_range range;
|
2020-04-06 20:06:20 -07:00
|
|
|
bool mode_wp, mode_dontwake;
|
2020-04-06 20:06:12 -07:00
|
|
|
|
2021-09-02 14:58:56 -07:00
|
|
|
if (atomic_read(&ctx->mmap_changing))
|
2020-04-06 20:06:12 -07:00
|
|
|
return -EAGAIN;
|
|
|
|
|
|
|
|
user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
|
|
|
|
|
|
|
|
if (copy_from_user(&uffdio_wp, user_uffdio_wp,
|
|
|
|
sizeof(struct uffdio_writeprotect)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
ret = validate_range(ctx->mm, uffdio_wp.range.start,
|
2020-04-06 20:06:12 -07:00
|
|
|
uffdio_wp.range.len);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
|
|
|
|
UFFDIO_WRITEPROTECT_MODE_WP))
|
|
|
|
return -EINVAL;
|
2020-04-06 20:06:20 -07:00
|
|
|
|
|
|
|
mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
|
|
|
|
mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;
|
|
|
|
|
|
|
|
if (mode_wp && mode_dontwake)
|
2020-04-06 20:06:12 -07:00
|
|
|
return -EINVAL;
|
|
|
|
|
2021-10-18 15:15:25 -07:00
|
|
|
if (mmget_not_zero(ctx->mm)) {
|
2024-02-15 11:27:54 -07:00
|
|
|
ret = mwriteprotect_range(ctx, uffdio_wp.range.start,
|
|
|
|
uffdio_wp.range.len, mode_wp);
|
2021-10-18 15:15:25 -07:00
|
|
|
mmput(ctx->mm);
|
|
|
|
} else {
|
|
|
|
return -ESRCH;
|
|
|
|
}
|
|
|
|
|
2020-04-06 20:06:12 -07:00
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
2020-04-06 20:06:20 -07:00
|
|
|
if (!mode_wp && !mode_dontwake) {
|
2020-04-06 20:06:12 -07:00
|
|
|
range.start = uffdio_wp.range.start;
|
|
|
|
range.len = uffdio_wp.range.len;
|
|
|
|
wake_userfault(ctx, &range);
|
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
|
|
|
|
{
|
|
|
|
__s64 ret;
|
|
|
|
struct uffdio_continue uffdio_continue;
|
|
|
|
struct uffdio_continue __user *user_uffdio_continue;
|
|
|
|
struct userfaultfd_wake_range range;
|
2023-03-14 15:12:50 -07:00
|
|
|
uffd_flags_t flags = 0;
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
|
|
|
|
user_uffdio_continue = (struct uffdio_continue __user *)arg;
|
|
|
|
|
|
|
|
ret = -EAGAIN;
|
2021-09-02 14:58:56 -07:00
|
|
|
if (atomic_read(&ctx->mmap_changing))
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(&uffdio_continue, user_uffdio_continue,
|
|
|
|
/* don't copy the output fields */
|
|
|
|
sizeof(uffdio_continue) - (sizeof(__s64))))
|
|
|
|
goto out;
|
|
|
|
|
userfaultfd: do not untag user pointers
Patch series "userfaultfd: do not untag user pointers", v5.
If a user program uses userfaultfd on ranges of heap memory, it may end
up passing a tagged pointer to the kernel in the range.start field of
the UFFDIO_REGISTER ioctl. This can happen when using an MTE-capable
allocator, or on Android if using the Tagged Pointers feature for MTE
readiness [1].
When a fault subsequently occurs, the tag is stripped from the fault
address returned to the application in the fault.address field of struct
uffd_msg. However, from the application's perspective, the tagged
address *is* the memory address, so if the application is unaware of
memory tags, it may get confused by receiving an address that is, from
its point of view, outside of the bounds of the allocation. We observed
this behavior in the kselftest for userfaultfd [2] but other
applications could have the same problem.
Address this by not untagging pointers passed to the userfaultfd ioctls.
Instead, let the system call fail. Also change the kselftest to use
mmap so that it doesn't encounter this problem.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
This patch (of 2):
Do not untag pointers passed to the userfaultfd ioctls. Instead, let
the system call fail. This will provide an early indication of problems
with tag-unaware userspace code instead of letting the code get confused
later, and is consistent with how we decided to handle brk/mmap/mremap
in commit dcde237319e6 ("mm: Avoid creating virtual address aliases in
brk()/mmap()/mremap()"), as well as being consistent with the existing
tagged address ABI documentation relating to how ioctl arguments are
handled.
The code change is a revert of commit 7d0325749a6c ("userfaultfd: untag
user pointers") plus some fixups to some additional calls to
validate_range that have appeared since then.
[1] https://source.android.com/devices/tech/debug/tagged-pointers
[2] tools/testing/selftests/vm/userfaultfd.c
Link: https://lkml.kernel.org/r/20210714195437.118982-1-pcc@google.com
Link: https://lkml.kernel.org/r/20210714195437.118982-2-pcc@google.com
Link: https://linux-review.googlesource.com/id/I761aa9f0344454c482b83fcfcce547db0a25501b
Fixes: 63f0c6037965 ("arm64: Introduce prctl() options to control the tagged user addresses ABI")
Signed-off-by: Peter Collingbourne <pcc@google.com>
Reviewed-by: Andrey Konovalov <andreyknvl@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alistair Delva <adelva@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dave Martin <Dave.Martin@arm.com>
Cc: Evgenii Stepanov <eugenis@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mitch Phillips <mitchp@google.com>
Cc: Vincenzo Frascino <vincenzo.frascino@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: William McVicker <willmcvicker@google.com>
Cc: <stable@vger.kernel.org> [5.4]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-07-23 15:50:01 -07:00
|
|
|
ret = validate_range(ctx->mm, uffdio_continue.range.start,
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
uffdio_continue.range.len);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = -EINVAL;
|
2023-03-14 15:12:50 -07:00
|
|
|
if (uffdio_continue.mode & ~(UFFDIO_CONTINUE_MODE_DONTWAKE |
|
|
|
|
UFFDIO_CONTINUE_MODE_WP))
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
goto out;
|
2023-03-14 15:12:50 -07:00
|
|
|
if (uffdio_continue.mode & UFFDIO_CONTINUE_MODE_WP)
|
|
|
|
flags |= MFILL_ATOMIC_WP;
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
|
|
|
|
if (mmget_not_zero(ctx->mm)) {
|
2024-02-15 11:27:54 -07:00
|
|
|
ret = mfill_atomic_continue(ctx, uffdio_continue.range.start,
|
|
|
|
uffdio_continue.range.len, flags);
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
mmput(ctx->mm);
|
|
|
|
} else {
|
|
|
|
return -ESRCH;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
|
|
|
|
return -EFAULT;
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* len == 0 would wake all */
|
|
|
|
BUG_ON(!ret);
|
|
|
|
range.len = ret;
|
|
|
|
if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) {
|
|
|
|
range.start = uffdio_continue.range.start;
|
|
|
|
wake_userfault(ctx, &range);
|
|
|
|
}
|
|
|
|
ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
mm: userfaultfd: add new UFFDIO_POISON ioctl
The basic idea here is to "simulate" memory poisoning for VMs. A VM
running on some host might encounter a memory error, after which some
page(s) are poisoned (i.e., future accesses SIGBUS). They expect that
once poisoned, pages can never become "un-poisoned". So, when we live
migrate the VM, we need to preserve the poisoned status of these pages.
When live migrating, we try to get the guest running on its new host as
quickly as possible. So, we start it running before all memory has been
copied, and before we're certain which pages should be poisoned or not.
So the basic way to use this new feature is:
- On the new host, the guest's memory is registered with userfaultfd, in
either MISSING or MINOR mode (doesn't really matter for this purpose).
- On any first access, we get a userfaultfd event. At this point we can
communicate with the old host to find out if the page was poisoned.
- If so, we can respond with a UFFDIO_POISON - this places a swap marker
so any future accesses will SIGBUS. Because the pte is now "present",
future accesses won't generate more userfaultfd events, they'll just
SIGBUS directly.
UFFDIO_POISON does not handle unmapping previously-present PTEs. This
isn't needed, because during live migration we want to intercept all
accesses with userfaultfd (not just writes, so WP mode isn't useful for
this). So whether minor or missing mode is being used (or both), the PTE
won't be present in any case, so handling that case isn't needed.
Similarly, UFFDIO_POISON won't replace existing PTE markers. This might
be okay to do, but it seems to be safer to just refuse to overwrite any
existing entry (like a UFFD_WP PTE marker).
Link: https://lkml.kernel.org/r/20230707215540.2324998-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Huang, Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Cc: Jiaqi Yan <jiaqiyan@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nadav Amit <namit@vmware.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: T.J. Alumbaugh <talumbau@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-07-07 14:55:36 -07:00
|
|
|
static inline int userfaultfd_poison(struct userfaultfd_ctx *ctx, unsigned long arg)
|
|
|
|
{
|
|
|
|
__s64 ret;
|
|
|
|
struct uffdio_poison uffdio_poison;
|
|
|
|
struct uffdio_poison __user *user_uffdio_poison;
|
|
|
|
struct userfaultfd_wake_range range;
|
|
|
|
|
|
|
|
user_uffdio_poison = (struct uffdio_poison __user *)arg;
|
|
|
|
|
|
|
|
ret = -EAGAIN;
|
|
|
|
if (atomic_read(&ctx->mmap_changing))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_from_user(&uffdio_poison, user_uffdio_poison,
|
|
|
|
/* don't copy the output fields */
|
|
|
|
sizeof(uffdio_poison) - (sizeof(__s64))))
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = validate_range(ctx->mm, uffdio_poison.range.start,
|
|
|
|
uffdio_poison.range.len);
|
|
|
|
if (ret)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (uffdio_poison.mode & ~UFFDIO_POISON_MODE_DONTWAKE)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (mmget_not_zero(ctx->mm)) {
|
2024-02-15 11:27:54 -07:00
|
|
|
ret = mfill_atomic_poison(ctx, uffdio_poison.range.start,
|
|
|
|
uffdio_poison.range.len, 0);
|
mm: userfaultfd: add new UFFDIO_POISON ioctl
The basic idea here is to "simulate" memory poisoning for VMs. A VM
running on some host might encounter a memory error, after which some
page(s) are poisoned (i.e., future accesses SIGBUS). They expect that
once poisoned, pages can never become "un-poisoned". So, when we live
migrate the VM, we need to preserve the poisoned status of these pages.
When live migrating, we try to get the guest running on its new host as
quickly as possible. So, we start it running before all memory has been
copied, and before we're certain which pages should be poisoned or not.
So the basic way to use this new feature is:
- On the new host, the guest's memory is registered with userfaultfd, in
either MISSING or MINOR mode (doesn't really matter for this purpose).
- On any first access, we get a userfaultfd event. At this point we can
communicate with the old host to find out if the page was poisoned.
- If so, we can respond with a UFFDIO_POISON - this places a swap marker
so any future accesses will SIGBUS. Because the pte is now "present",
future accesses won't generate more userfaultfd events, they'll just
SIGBUS directly.
UFFDIO_POISON does not handle unmapping previously-present PTEs. This
isn't needed, because during live migration we want to intercept all
accesses with userfaultfd (not just writes, so WP mode isn't useful for
this). So whether minor or missing mode is being used (or both), the PTE
won't be present in any case, so handling that case isn't needed.
Similarly, UFFDIO_POISON won't replace existing PTE markers. This might
be okay to do, but it seems to be safer to just refuse to overwrite any
existing entry (like a UFFD_WP PTE marker).
Link: https://lkml.kernel.org/r/20230707215540.2324998-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Huang, Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Cc: Jiaqi Yan <jiaqiyan@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nadav Amit <namit@vmware.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: T.J. Alumbaugh <talumbau@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-07-07 14:55:36 -07:00
|
|
|
mmput(ctx->mm);
|
|
|
|
} else {
|
|
|
|
return -ESRCH;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (unlikely(put_user(ret, &user_uffdio_poison->updated)))
|
|
|
|
return -EFAULT;
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* len == 0 would wake all */
|
|
|
|
BUG_ON(!ret);
|
|
|
|
range.len = ret;
|
|
|
|
if (!(uffdio_poison.mode & UFFDIO_POISON_MODE_DONTWAKE)) {
|
|
|
|
range.start = uffdio_poison.range.start;
|
|
|
|
wake_userfault(ctx, &range);
|
|
|
|
}
|
|
|
|
ret = range.len == uffdio_poison.range.len ? 0 : -EAGAIN;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
bool userfaultfd_wp_async(struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
return userfaultfd_wp_async_ctx(vma->vm_userfaultfd_ctx.ctx);
|
|
|
|
}
|
|
|
|
|
2017-02-22 16:42:21 -07:00
|
|
|
static inline unsigned int uffd_ctx_features(__u64 user_features)
|
|
|
|
{
|
|
|
|
/*
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
* For the current set of features the bits just coincide. Set
|
|
|
|
* UFFD_FEATURE_INITIALIZED to mark the features as enabled.
|
2017-02-22 16:42:21 -07:00
|
|
|
*/
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
|
2017-02-22 16:42:21 -07:00
|
|
|
}
|
|
|
|
|
userfaultfd: UFFDIO_MOVE uABI
Implement the uABI of UFFDIO_MOVE ioctl.
UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application
needs pages to be allocated [1]. However, with UFFDIO_MOVE, if pages are
available (in userspace) for recycling, as is usually the case in heap
compaction algorithms, then we can avoid the page allocation and memcpy
(done by UFFDIO_COPY). Also, since the pages are recycled in the
userspace, we avoid the need to release (via madvise) the pages back to
the kernel [2].
We see over 40% reduction (on a Google pixel 6 device) in the compacting
thread's completion time by using UFFDIO_MOVE vs. UFFDIO_COPY. This was
measured using a benchmark that emulates a heap compaction implementation
using userfaultfd (to allow concurrent accesses by application threads).
More details of the usecase are explained in [2]. Furthermore,
UFFDIO_MOVE enables moving swapped-out pages without touching them within
the same vma. Today, it can only be done by mremap, however it forces
splitting the vma.
[1] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redhat.com/
[2] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyjniNVjp0Aw@mail.gmail.com/
Update for the ioctl_userfaultfd(2) manpage:
UFFDIO_MOVE
(Since Linux xxx) Move a continuous memory chunk into the
userfault registered range and optionally wake up the blocked
thread. The source and destination addresses and the number of
bytes to move are specified by the src, dst, and len fields of
the uffdio_move structure pointed to by argp:
struct uffdio_move {
__u64 dst; /* Destination of move */
__u64 src; /* Source of move */
__u64 len; /* Number of bytes to move */
__u64 mode; /* Flags controlling behavior of move */
__s64 move; /* Number of bytes moved, or negated error */
};
The following value may be bitwise ORed in mode to change the
behavior of the UFFDIO_MOVE operation:
UFFDIO_MOVE_MODE_DONTWAKE
Do not wake up the thread that waits for page-fault
resolution
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES
Allow holes in the source virtual range that is being moved.
When not specified, the holes will result in ENOENT error.
When specified, the holes will be accounted as successfully
moved memory. This is mostly useful to move hugepage aligned
virtual regions without knowing if there are transparent
hugepages in the regions or not, but preventing the risk of
having to split the hugepage during the operation.
The move field is used by the kernel to return the number of
bytes that was actually moved, or an error (a negated errno-
style value). If the value returned in move doesn't match the
value that was specified in len, the operation fails with the
error EAGAIN. The move field is output-only; it is not read by
the UFFDIO_MOVE operation.
The operation may fail for various reasons. Usually, remapping of
pages that are not exclusive to the given process fail; once KSM
might deduplicate pages or fork() COW-shares pages during fork()
with child processes, they are no longer exclusive. Further, the
kernel might only perform lightweight checks for detecting whether
the pages are exclusive, and return -EBUSY in case that check fails.
To make the operation more likely to succeed, KSM should be
disabled, fork() should be avoided or MADV_DONTFORK should be
configured for the source VMA before fork().
This ioctl(2) operation returns 0 on success. In this case, the
entire area was moved. On error, -1 is returned and errno is
set to indicate the error. Possible errors include:
EAGAIN The number of bytes moved (i.e., the value returned in
the move field) does not equal the value that was
specified in the len field.
EINVAL Either dst or len was not a multiple of the system page
size, or the range specified by src and len or dst and len
was invalid.
EINVAL An invalid bit was specified in the mode field.
ENOENT
The source virtual memory range has unmapped holes and
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES is not set.
EEXIST
The destination virtual memory range is fully or partially
mapped.
EBUSY
The pages in the source virtual memory range are either
pinned or not exclusive to the process. The kernel might
only perform lightweight checks for detecting whether the
pages are exclusive. To make the operation more likely to
succeed, KSM should be disabled, fork() should be avoided
or MADV_DONTFORK should be configured for the source virtual
memory area before fork().
ENOMEM Allocating memory needed for the operation failed.
ESRCH
The target process has exited at the time of a UFFDIO_MOVE
operation.
Link: https://lkml.kernel.org/r/20231206103702.3873743-3-surenb@google.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-12-06 03:36:56 -07:00
|
|
|
static int userfaultfd_move(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
__s64 ret;
|
|
|
|
struct uffdio_move uffdio_move;
|
|
|
|
struct uffdio_move __user *user_uffdio_move;
|
|
|
|
struct userfaultfd_wake_range range;
|
|
|
|
struct mm_struct *mm = ctx->mm;
|
|
|
|
|
|
|
|
user_uffdio_move = (struct uffdio_move __user *) arg;
|
|
|
|
|
|
|
|
if (atomic_read(&ctx->mmap_changing))
|
|
|
|
return -EAGAIN;
|
|
|
|
|
|
|
|
if (copy_from_user(&uffdio_move, user_uffdio_move,
|
|
|
|
/* don't copy "move" last field */
|
|
|
|
sizeof(uffdio_move)-sizeof(__s64)))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
/* Do not allow cross-mm moves. */
|
|
|
|
if (mm != current->mm)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
ret = validate_range(mm, uffdio_move.dst, uffdio_move.len);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
ret = validate_range(mm, uffdio_move.src, uffdio_move.len);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
if (uffdio_move.mode & ~(UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES|
|
|
|
|
UFFDIO_MOVE_MODE_DONTWAKE))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (mmget_not_zero(mm)) {
|
2024-02-15 11:27:56 -07:00
|
|
|
ret = move_pages(ctx, uffdio_move.dst, uffdio_move.src,
|
|
|
|
uffdio_move.len, uffdio_move.mode);
|
userfaultfd: UFFDIO_MOVE uABI
Implement the uABI of UFFDIO_MOVE ioctl.
UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application
needs pages to be allocated [1]. However, with UFFDIO_MOVE, if pages are
available (in userspace) for recycling, as is usually the case in heap
compaction algorithms, then we can avoid the page allocation and memcpy
(done by UFFDIO_COPY). Also, since the pages are recycled in the
userspace, we avoid the need to release (via madvise) the pages back to
the kernel [2].
We see over 40% reduction (on a Google pixel 6 device) in the compacting
thread's completion time by using UFFDIO_MOVE vs. UFFDIO_COPY. This was
measured using a benchmark that emulates a heap compaction implementation
using userfaultfd (to allow concurrent accesses by application threads).
More details of the usecase are explained in [2]. Furthermore,
UFFDIO_MOVE enables moving swapped-out pages without touching them within
the same vma. Today, it can only be done by mremap, however it forces
splitting the vma.
[1] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redhat.com/
[2] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyjniNVjp0Aw@mail.gmail.com/
Update for the ioctl_userfaultfd(2) manpage:
UFFDIO_MOVE
(Since Linux xxx) Move a continuous memory chunk into the
userfault registered range and optionally wake up the blocked
thread. The source and destination addresses and the number of
bytes to move are specified by the src, dst, and len fields of
the uffdio_move structure pointed to by argp:
struct uffdio_move {
__u64 dst; /* Destination of move */
__u64 src; /* Source of move */
__u64 len; /* Number of bytes to move */
__u64 mode; /* Flags controlling behavior of move */
__s64 move; /* Number of bytes moved, or negated error */
};
The following value may be bitwise ORed in mode to change the
behavior of the UFFDIO_MOVE operation:
UFFDIO_MOVE_MODE_DONTWAKE
Do not wake up the thread that waits for page-fault
resolution
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES
Allow holes in the source virtual range that is being moved.
When not specified, the holes will result in ENOENT error.
When specified, the holes will be accounted as successfully
moved memory. This is mostly useful to move hugepage aligned
virtual regions without knowing if there are transparent
hugepages in the regions or not, but preventing the risk of
having to split the hugepage during the operation.
The move field is used by the kernel to return the number of
bytes that was actually moved, or an error (a negated errno-
style value). If the value returned in move doesn't match the
value that was specified in len, the operation fails with the
error EAGAIN. The move field is output-only; it is not read by
the UFFDIO_MOVE operation.
The operation may fail for various reasons. Usually, remapping of
pages that are not exclusive to the given process fail; once KSM
might deduplicate pages or fork() COW-shares pages during fork()
with child processes, they are no longer exclusive. Further, the
kernel might only perform lightweight checks for detecting whether
the pages are exclusive, and return -EBUSY in case that check fails.
To make the operation more likely to succeed, KSM should be
disabled, fork() should be avoided or MADV_DONTFORK should be
configured for the source VMA before fork().
This ioctl(2) operation returns 0 on success. In this case, the
entire area was moved. On error, -1 is returned and errno is
set to indicate the error. Possible errors include:
EAGAIN The number of bytes moved (i.e., the value returned in
the move field) does not equal the value that was
specified in the len field.
EINVAL Either dst or len was not a multiple of the system page
size, or the range specified by src and len or dst and len
was invalid.
EINVAL An invalid bit was specified in the mode field.
ENOENT
The source virtual memory range has unmapped holes and
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES is not set.
EEXIST
The destination virtual memory range is fully or partially
mapped.
EBUSY
The pages in the source virtual memory range are either
pinned or not exclusive to the process. The kernel might
only perform lightweight checks for detecting whether the
pages are exclusive. To make the operation more likely to
succeed, KSM should be disabled, fork() should be avoided
or MADV_DONTFORK should be configured for the source virtual
memory area before fork().
ENOMEM Allocating memory needed for the operation failed.
ESRCH
The target process has exited at the time of a UFFDIO_MOVE
operation.
Link: https://lkml.kernel.org/r/20231206103702.3873743-3-surenb@google.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-12-06 03:36:56 -07:00
|
|
|
mmput(mm);
|
|
|
|
} else {
|
|
|
|
return -ESRCH;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (unlikely(put_user(ret, &user_uffdio_move->move)))
|
|
|
|
return -EFAULT;
|
|
|
|
if (ret < 0)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
/* len == 0 would wake all */
|
|
|
|
VM_WARN_ON(!ret);
|
|
|
|
range.len = ret;
|
|
|
|
if (!(uffdio_move.mode & UFFDIO_MOVE_MODE_DONTWAKE)) {
|
|
|
|
range.start = uffdio_move.dst;
|
|
|
|
wake_userfault(ctx, &range);
|
|
|
|
}
|
|
|
|
ret = range.len == uffdio_move.len ? 0 : -EAGAIN;
|
|
|
|
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
/*
|
|
|
|
* userland asks for a certain API version and we return which bits
|
|
|
|
* and ioctl commands are implemented in this kernel for such API
|
|
|
|
* version or -EINVAL if unknown.
|
|
|
|
*/
|
|
|
|
static int userfaultfd_api(struct userfaultfd_ctx *ctx,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
struct uffdio_api uffdio_api;
|
|
|
|
void __user *buf = (void __user *)arg;
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
unsigned int ctx_features;
|
2015-09-04 15:46:31 -07:00
|
|
|
int ret;
|
2017-02-22 16:42:24 -07:00
|
|
|
__u64 features;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
ret = -EFAULT;
|
2015-09-04 15:46:37 -07:00
|
|
|
if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
|
2015-09-04 15:46:31 -07:00
|
|
|
goto out;
|
2023-04-12 09:38:52 -07:00
|
|
|
features = uffdio_api.features;
|
|
|
|
ret = -EINVAL;
|
2024-06-26 06:05:11 -07:00
|
|
|
if (uffdio_api.api != UFFD_API)
|
2023-04-12 09:38:52 -07:00
|
|
|
goto err_out;
|
2019-11-30 18:58:01 -07:00
|
|
|
ret = -EPERM;
|
|
|
|
if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
|
|
|
|
goto err_out;
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
|
|
|
|
/* WP_ASYNC relies on WP_UNPOPULATED, choose it unconditionally */
|
|
|
|
if (features & UFFD_FEATURE_WP_ASYNC)
|
|
|
|
features |= UFFD_FEATURE_WP_UNPOPULATED;
|
|
|
|
|
2017-02-22 16:42:24 -07:00
|
|
|
/* report all available features and ioctls to userland */
|
|
|
|
uffdio_api.features = UFFD_API_FEATURES;
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
|
2021-06-30 18:49:27 -07:00
|
|
|
uffdio_api.features &=
|
|
|
|
~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
|
2021-06-30 18:49:06 -07:00
|
|
|
#endif
|
|
|
|
#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
|
|
|
|
uffdio_api.features &= ~UFFD_FEATURE_PAGEFAULT_FLAG_WP;
|
2022-05-12 20:22:56 -07:00
|
|
|
#endif
|
|
|
|
#ifndef CONFIG_PTE_MARKER_UFFD_WP
|
|
|
|
uffdio_api.features &= ~UFFD_FEATURE_WP_HUGETLBFS_SHMEM;
|
mm/uffd: UFFD_FEATURE_WP_UNPOPULATED
Patch series "mm/uffd: Add feature bit UFFD_FEATURE_WP_UNPOPULATED", v4.
The new feature bit makes anonymous memory acts the same as file memory on
userfaultfd-wp in that it'll also wr-protect none ptes.
It can be useful in two cases:
(1) Uffd-wp app that needs to wr-protect none ptes like QEMU snapshot,
so pre-fault can be replaced by enabling this flag and speed up
protections
(2) It helps to implement async uffd-wp mode that Muhammad is working on [1]
It's debatable whether this is the most ideal solution because with the
new feature bit set, wr-protect none pte needs to pre-populate the
pgtables to the last level (PAGE_SIZE). But it seems fine so far to
service either purpose above, so we can leave optimizations for later.
The series brings pte markers to anonymous memory too. There's some
change in the common mm code path in the 1st patch, great to have some eye
looking at it, but hopefully they're still relatively straightforward.
This patch (of 2):
This is a new feature that controls how uffd-wp handles none ptes. When
it's set, the kernel will handle anonymous memory the same way as file
memory, by allowing the user to wr-protect unpopulated ptes.
File memories handles none ptes consistently by allowing wr-protecting of
none ptes because of the unawareness of page cache being exist or not.
For anonymous it was not as persistent because we used to assume that we
don't need protections on none ptes or known zero pages.
One use case of such a feature bit was VM live snapshot, where if without
wr-protecting empty ptes the snapshot can contain random rubbish in the
holes of the anonymous memory, which can cause misbehave of the guest when
the guest OS assumes the pages should be all zeros.
QEMU worked it around by pre-populate the section with reads to fill in
zero page entries before starting the whole snapshot process [1].
Recently there's another need raised on using userfaultfd wr-protect for
detecting dirty pages (to replace soft-dirty in some cases) [2]. In that
case if without being able to wr-protect none ptes by default, the dirty
info can get lost, since we cannot treat every none pte to be dirty (the
current design is identify a page dirty based on uffd-wp bit being
cleared).
In general, we want to be able to wr-protect empty ptes too even for
anonymous.
This patch implements UFFD_FEATURE_WP_UNPOPULATED so that it'll make
uffd-wp handling on none ptes being consistent no matter what the memory
type is underneath. It doesn't have any impact on file memories so far
because we already have pte markers taking care of that. So it only
affects anonymous.
The feature bit is by default off, so the old behavior will be maintained.
Sometimes it may be wanted because the wr-protect of none ptes will
contain overheads not only during UFFDIO_WRITEPROTECT (by applying pte
markers to anonymous), but also on creating the pgtables to store the pte
markers. So there's potentially less chance of using thp on the first
fault for a none pmd or larger than a pmd.
The major implementation part is teaching the whole kernel to understand
pte markers even for anonymously mapped ranges, meanwhile allowing the
UFFDIO_WRITEPROTECT ioctl to apply pte markers for anonymous too when the
new feature bit is set.
Note that even if the patch subject starts with mm/uffd, there're a few
small refactors to major mm path of handling anonymous page faults. But
they should be straightforward.
With WP_UNPOPUATED, application like QEMU can avoid pre-read faults all
the memory before wr-protect during taking a live snapshot. Quotting from
Muhammad's test result here [3] based on a simple program [4]:
(1) With huge page disabled
echo madvise > /sys/kernel/mm/transparent_hugepage/enabled
./uffd_wp_perf
Test DEFAULT: 4
Test PRE-READ: 1111453 (pre-fault 1101011)
Test MADVISE: 278276 (pre-fault 266378)
Test WP-UNPOPULATE: 11712
(2) With Huge page enabled
echo always > /sys/kernel/mm/transparent_hugepage/enabled
./uffd_wp_perf
Test DEFAULT: 4
Test PRE-READ: 22521 (pre-fault 22348)
Test MADVISE: 4909 (pre-fault 4743)
Test WP-UNPOPULATE: 14448
There'll be a great perf boost for no-thp case, while for thp enabled with
extreme case of all-thp-zero WP_UNPOPULATED can be slower than MADVISE,
but that's low possibility in reality, also the overhead was not reduced
but postponed until a follow up write on any huge zero thp, so potentially
it is faster by making the follow up writes slower.
[1] https://lore.kernel.org/all/20210401092226.102804-4-andrey.gruzdev@virtuozzo.com/
[2] https://lore.kernel.org/all/Y+v2HJ8+3i%2FKzDBu@x1n/
[3] https://lore.kernel.org/all/d0eb0a13-16dc-1ac1-653a-78b7273781e3@collabora.com/
[4] https://github.com/xzpeter/clibs/blob/master/uffd-test/uffd-wp-perf.c
[peterx@redhat.com: comment changes, oneliner fix to khugepaged]
Link: https://lkml.kernel.org/r/ZB2/8jPhD3fpx5U8@x1n
Link: https://lkml.kernel.org/r/20230309223711.823547-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20230309223711.823547-2-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Nadav Amit <nadav.amit@gmail.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-03-09 15:37:10 -07:00
|
|
|
uffdio_api.features &= ~UFFD_FEATURE_WP_UNPOPULATED;
|
userfaultfd: UFFD_FEATURE_WP_ASYNC
Patch series "Implement IOCTL to get and optionally clear info about
PTEs", v33.
*Motivation*
The real motivation for adding PAGEMAP_SCAN IOCTL is to emulate Windows
GetWriteWatch() and ResetWriteWatch() syscalls [1]. The GetWriteWatch()
retrieves the addresses of the pages that are written to in a region of
virtual memory.
This syscall is used in Windows applications and games etc. This syscall
is being emulated in pretty slow manner in userspace. Our purpose is to
enhance the kernel such that we translate it efficiently in a better way.
Currently some out of tree hack patches are being used to efficiently
emulate it in some kernels. We intend to replace those with these
patches. So the whole gaming on Linux can effectively get benefit from
this. It means there would be tons of users of this code.
CRIU use case [2] was mentioned by Andrei and Danylo:
> Use cases for migrating sparse VMAs are binaries sanitized with ASAN,
> MSAN or TSAN [3]. All of these sanitizers produce sparse mappings of
> shadow memory [4]. Being able to migrate such binaries allows to highly
> reduce the amount of work needed to identify and fix post-migration
> crashes, which happen constantly.
Andrei defines the following uses of this code:
* it is more granular and allows us to track changed pages more
effectively. The current interface can clear dirty bits for the entire
process only. In addition, reading info about pages is a separate
operation. It means we must freeze the process to read information
about all its pages, reset dirty bits, only then we can start dumping
pages. The information about pages becomes more and more outdated,
while we are processing pages. The new interface solves both these
downsides. First, it allows us to read pte bits and clear the
soft-dirty bit atomically. It means that CRIU will not need to freeze
processes to pre-dump their memory. Second, it clears soft-dirty bits
for a specified region of memory. It means CRIU will have actual info
about pages to the moment of dumping them.
* The new interface has to be much faster because basic page filtering
is happening in the kernel. With the old interface, we have to read
pagemap for each page.
*Implementation Evolution (Short Summary)*
From the definition of GetWriteWatch(), we feel like kernel's soft-dirty
feature can be used under the hood with some additions like:
* reset soft-dirty flag for only a specific region of memory instead of
clearing the flag for the entire process
* get and clear soft-dirty flag for a specific region atomically
So we decided to use ioctl on pagemap file to read or/and reset soft-dirty
flag. But using soft-dirty flag, sometimes we get extra pages which weren't
even written. They had become soft-dirty because of VMA merging and
VM_SOFTDIRTY flag. This breaks the definition of GetWriteWatch(). We were
able to by-pass this short coming by ignoring VM_SOFTDIRTY until David
reported that mprotect etc messes up the soft-dirty flag while ignoring
VM_SOFTDIRTY [5]. This wasn't happening until [6] got introduced. We
discussed if we can revert these patches. But we could not reach to any
conclusion. So at this point, I made couple of tries to solve this whole
VM_SOFTDIRTY issue by correcting the soft-dirty implementation:
* [7] Correct the bug fixed wrongly back in 2014. It had potential to cause
regression. We left it behind.
* [8] Keep a list of soft-dirty part of a VMA across splits and merges. I
got the reply don't increase the size of the VMA by 8 bytes.
At this point, we left soft-dirty considering it is too much delicate and
userfaultfd [9] seemed like the only way forward. From there onward, we
have been basing soft-dirty emulation on userfaultfd wp feature where
kernel resolves the faults itself when WP_ASYNC feature is used. It was
straight forward to add WP_ASYNC feature in userfautlfd. Now we get only
those pages dirty or written-to which are really written in reality. (PS
There is another WP_UNPOPULATED userfautfd feature is required which is
needed to avoid pre-faulting memory before write-protecting [9].)
All the different masks were added on the request of CRIU devs to create
interface more generic and better.
[1] https://learn.microsoft.com/en-us/windows/win32/api/memoryapi/nf-memoryapi-getwritewatch
[2] https://lore.kernel.org/all/20221014134802.1361436-1-mdanylo@google.com
[3] https://github.com/google/sanitizers
[4] https://github.com/google/sanitizers/wiki/AddressSanitizerAlgorithm#64-bit
[5] https://lore.kernel.org/all/bfcae708-db21-04b4-0bbe-712badd03071@redhat.com
[6] https://lore.kernel.org/all/20220725142048.30450-1-peterx@redhat.com/
[7] https://lore.kernel.org/all/20221122115007.2787017-1-usama.anjum@collabora.com
[8] https://lore.kernel.org/all/20221220162606.1595355-1-usama.anjum@collabora.com
[9] https://lore.kernel.org/all/20230306213925.617814-1-peterx@redhat.com
[10] https://lore.kernel.org/all/20230125144529.1630917-1-mdanylo@google.com
This patch (of 6):
Add a new userfaultfd-wp feature UFFD_FEATURE_WP_ASYNC, that allows
userfaultfd wr-protect faults to be resolved by the kernel directly.
It can be used like a high accuracy version of soft-dirty, without vma
modifications during tracking, and also with ranged support by default
rather than for a whole mm when reset the protections due to existence of
ioctl(UFFDIO_WRITEPROTECT).
Several goals of such a dirty tracking interface:
1. All types of memory should be supported and tracable. This is nature
for soft-dirty but should mention when the context is userfaultfd,
because it used to only support anon/shmem/hugetlb. The problem is for
a dirty tracking purpose these three types may not be enough, and it's
legal to track anything e.g. any page cache writes from mmap.
2. Protections can be applied to partial of a memory range, without vma
split/merge fuss. The hope is that the tracking itself should not
affect any vma layout change. It also helps when reset happens because
the reset will not need mmap write lock which can block the tracee.
3. Accuracy needs to be maintained. This means we need pte markers to work
on any type of VMA.
One could question that, the whole concept of async dirty tracking is not
really close to fundamentally what userfaultfd used to be: it's not "a
fault to be serviced by userspace" anymore. However, using userfaultfd-wp
here as a framework is convenient for us in at least:
1. VM_UFFD_WP vma flag, which has a very good name to suite something like
this, so we don't need VM_YET_ANOTHER_SOFT_DIRTY. Just use a new
feature bit to identify from a sync version of uffd-wp registration.
2. PTE markers logic can be leveraged across the whole kernel to maintain
the uffd-wp bit as long as an arch supports, this also applies to this
case where uffd-wp bit will be a hint to dirty information and it will
not go lost easily (e.g. when some page cache ptes got zapped).
3. Reuse ioctl(UFFDIO_WRITEPROTECT) interface for either starting or
resetting a range of memory, while there's no counterpart in the old
soft-dirty world, hence if this is wanted in a new design we'll need a
new interface otherwise.
We can somehow understand that commonality because uffd-wp was
fundamentally a similar idea of write-protecting pages just like
soft-dirty.
This implementation allows WP_ASYNC to imply WP_UNPOPULATED, because so
far WP_ASYNC seems to not usable if without WP_UNPOPULATE. This also
gives us chance to modify impl of WP_ASYNC just in case it could be not
depending on WP_UNPOPULATED anymore in the future kernels. It's also fine
to imply that because both features will rely on PTE_MARKER_UFFD_WP config
option, so they'll show up together (or both missing) in an UFFDIO_API
probe.
vma_can_userfault() now allows any VMA if the userfaultfd registration is
only about async uffd-wp. So we can track dirty for all kinds of memory
including generic file systems (like XFS, EXT4 or BTRFS).
One trick worth mention in do_wp_page() is that we need to manually update
vmf->orig_pte here because it can be used later with a pte_same() check -
this path always has FAULT_FLAG_ORIG_PTE_VALID set in the flags.
The major defect of this approach of dirty tracking is we need to populate
the pgtables when tracking starts. Soft-dirty doesn't do it like that.
It's unwanted in the case where the range of memory to track is huge and
unpopulated (e.g., tracking updates on a 10G file with mmap() on top,
without having any page cache installed yet). One way to improve this is
to allow pte markers exist for larger than PTE level for PMD+. That will
not change the interface if to implemented, so we can leave that for
later.
Link: https://lkml.kernel.org/r/20230821141518.870589-1-usama.anjum@collabora.com
Link: https://lkml.kernel.org/r/20230821141518.870589-2-usama.anjum@collabora.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Co-developed-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Signed-off-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Alex Sierra <alex.sierra@amd.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrei Vagin <avagin@gmail.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gustavo A. R. Silva <gustavoars@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Michal Miroslaw <emmir@google.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nadav Amit <namit@vmware.com>
Cc: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Paul Gofman <pgofman@codeweavers.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Yun Zhou <yun.zhou@windriver.com>
Cc: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-08-21 07:15:13 -07:00
|
|
|
uffdio_api.features &= ~UFFD_FEATURE_WP_ASYNC;
|
userfaultfd: add minor fault registration mode
Patch series "userfaultfd: add minor fault handling", v9.
Overview
========
This series adds a new userfaultfd feature, UFFD_FEATURE_MINOR_HUGETLBFS.
When enabled (via the UFFDIO_API ioctl), this feature means that any
hugetlbfs VMAs registered with UFFDIO_REGISTER_MODE_MISSING will *also*
get events for "minor" faults. By "minor" fault, I mean the following
situation:
Let there exist two mappings (i.e., VMAs) to the same page(s) (shared
memory). One of the mappings is registered with userfaultfd (in minor
mode), and the other is not. Via the non-UFFD mapping, the underlying
pages have already been allocated & filled with some contents. The UFFD
mapping has not yet been faulted in; when it is touched for the first
time, this results in what I'm calling a "minor" fault. As a concrete
example, when working with hugetlbfs, we have huge_pte_none(), but
find_lock_page() finds an existing page.
We also add a new ioctl to resolve such faults: UFFDIO_CONTINUE. The idea
is, userspace resolves the fault by either a) doing nothing if the
contents are already correct, or b) updating the underlying contents using
the second, non-UFFD mapping (via memcpy/memset or similar, or something
fancier like RDMA, or etc...). In either case, userspace issues
UFFDIO_CONTINUE to tell the kernel "I have ensured the page contents are
correct, carry on setting up the mapping".
Use Case
========
Consider the use case of VM live migration (e.g. under QEMU/KVM):
1. While a VM is still running, we copy the contents of its memory to a
target machine. The pages are populated on the target by writing to the
non-UFFD mapping, using the setup described above. The VM is still running
(and therefore its memory is likely changing), so this may be repeated
several times, until we decide the target is "up to date enough".
2. We pause the VM on the source, and start executing on the target machine.
During this gap, the VM's user(s) will *see* a pause, so it is desirable to
minimize this window.
3. Between the last time any page was copied from the source to the target, and
when the VM was paused, the contents of that page may have changed - and
therefore the copy we have on the target machine is out of date. Although we
can keep track of which pages are out of date, for VMs with large amounts of
memory, it is "slow" to transfer this information to the target machine. We
want to resume execution before such a transfer would complete.
4. So, the guest begins executing on the target machine. The first time it
touches its memory (via the UFFD-registered mapping), userspace wants to
intercept this fault. Userspace checks whether or not the page is up to date,
and if not, copies the updated page from the source machine, via the non-UFFD
mapping. Finally, whether a copy was performed or not, userspace issues a
UFFDIO_CONTINUE ioctl to tell the kernel "I have ensured the page contents
are correct, carry on setting up the mapping".
We don't have to do all of the final updates on-demand. The userfaultfd manager
can, in the background, also copy over updated pages once it receives the map of
which pages are up-to-date or not.
Interaction with Existing APIs
==============================
Because this is a feature, a registered VMA could potentially receive both
missing and minor faults. I spent some time thinking through how the
existing API interacts with the new feature:
UFFDIO_CONTINUE cannot be used to resolve non-minor faults, as it does not
allocate a new page. If UFFDIO_CONTINUE is used on a non-minor fault:
- For non-shared memory or shmem, -EINVAL is returned.
- For hugetlb, -EFAULT is returned.
UFFDIO_COPY and UFFDIO_ZEROPAGE cannot be used to resolve minor faults.
Without modifications, the existing codepath assumes a new page needs to
be allocated. This is okay, since userspace must have a second
non-UFFD-registered mapping anyway, thus there isn't much reason to want
to use these in any case (just memcpy or memset or similar).
- If UFFDIO_COPY is used on a minor fault, -EEXIST is returned.
- If UFFDIO_ZEROPAGE is used on a minor fault, -EEXIST is returned (or -EINVAL
in the case of hugetlb, as UFFDIO_ZEROPAGE is unsupported in any case).
- UFFDIO_WRITEPROTECT simply doesn't work with shared memory, and returns
-ENOENT in that case (regardless of the kind of fault).
Future Work
===========
This series only supports hugetlbfs. I have a second series in flight to
support shmem as well, extending the functionality. This series is more
mature than the shmem support at this point, and the functionality works
fully on hugetlbfs, so this series can be merged first and then shmem
support will follow.
This patch (of 6):
This feature allows userspace to intercept "minor" faults. By "minor"
faults, I mean the following situation:
Let there exist two mappings (i.e., VMAs) to the same page(s). One of the
mappings is registered with userfaultfd (in minor mode), and the other is
not. Via the non-UFFD mapping, the underlying pages have already been
allocated & filled with some contents. The UFFD mapping has not yet been
faulted in; when it is touched for the first time, this results in what
I'm calling a "minor" fault. As a concrete example, when working with
hugetlbfs, we have huge_pte_none(), but find_lock_page() finds an existing
page.
This commit adds the new registration mode, and sets the relevant flag on
the VMAs being registered. In the hugetlb fault path, if we find that we
have huge_pte_none(), but find_lock_page() does indeed find an existing
page, then we have a "minor" fault, and if the VMA has the userfaultfd
registration flag, we call into userfaultfd to handle it.
This is implemented as a new registration mode, instead of an API feature.
This is because the alternative implementation has significant drawbacks
[1].
However, doing it this was requires we allocate a VM_* flag for the new
registration mode. On 32-bit systems, there are no unused bits, so this
feature is only supported on architectures with
CONFIG_ARCH_USES_HIGH_VMA_FLAGS. When attempting to register a VMA in
MINOR mode on 32-bit architectures, we return -EINVAL.
[1] https://lore.kernel.org/patchwork/patch/1380226/
[peterx@redhat.com: fix minor fault page leak]
Link: https://lkml.kernel.org/r/20210322175132.36659-1-peterx@redhat.com
Link: https://lkml.kernel.org/r/20210301222728.176417-1-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20210301222728.176417-2-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Steven Price <steven.price@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:36 -07:00
|
|
|
#endif
|
2024-06-26 06:05:11 -07:00
|
|
|
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (features & ~uffdio_api.features)
|
|
|
|
goto err_out;
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
uffdio_api.ioctls = UFFD_API_IOCTLS;
|
|
|
|
ret = -EFAULT;
|
|
|
|
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
|
|
|
|
goto out;
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
|
2017-02-22 16:42:24 -07:00
|
|
|
/* only enable the requested features for this uffd context */
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
ctx_features = uffd_ctx_features(features);
|
|
|
|
ret = -EINVAL;
|
|
|
|
if (cmpxchg(&ctx->features, 0, ctx_features) != 0)
|
|
|
|
goto err_out;
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
ret = 0;
|
|
|
|
out:
|
|
|
|
return ret;
|
2019-11-30 18:58:01 -07:00
|
|
|
err_out:
|
|
|
|
memset(&uffdio_api, 0, sizeof(uffdio_api));
|
|
|
|
if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
|
|
|
|
ret = -EFAULT;
|
|
|
|
goto out;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
|
|
|
|
static long userfaultfd_ioctl(struct file *file, unsigned cmd,
|
|
|
|
unsigned long arg)
|
|
|
|
{
|
|
|
|
int ret = -EINVAL;
|
|
|
|
struct userfaultfd_ctx *ctx = file->private_data;
|
|
|
|
|
userfaultfd: prevent concurrent API initialization
userfaultfd assumes that the enabled features are set once and never
changed after UFFDIO_API ioctl succeeded.
However, currently, UFFDIO_API can be called concurrently from two
different threads, succeed on both threads and leave userfaultfd's
features in non-deterministic state. Theoretically, other uffd operations
(ioctl's and page-faults) can be dispatched while adversely affected by
such changes of features.
Moreover, the writes to ctx->state and ctx->features are not ordered,
which can - theoretically, again - let userfaultfd_ioctl() think that
userfaultfd API completed, while the features are still not initialized.
To avoid races, it is arguably best to get rid of ctx->state. Since there
are only 2 states, record the API initialization in ctx->features as the
uppermost bit and remove ctx->state.
Link: https://lkml.kernel.org/r/20210808020724.1022515-3-namit@vmware.com
Fixes: 9cd75c3cd4c3d ("userfaultfd: non-cooperative: add ability to report non-PF events from uffd descriptor")
Signed-off-by: Nadav Amit <namit@vmware.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-09-02 14:58:59 -07:00
|
|
|
if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx))
|
2015-09-04 15:47:15 -07:00
|
|
|
return -EINVAL;
|
|
|
|
|
2015-09-04 15:46:31 -07:00
|
|
|
switch(cmd) {
|
|
|
|
case UFFDIO_API:
|
|
|
|
ret = userfaultfd_api(ctx, arg);
|
|
|
|
break;
|
|
|
|
case UFFDIO_REGISTER:
|
|
|
|
ret = userfaultfd_register(ctx, arg);
|
|
|
|
break;
|
|
|
|
case UFFDIO_UNREGISTER:
|
|
|
|
ret = userfaultfd_unregister(ctx, arg);
|
|
|
|
break;
|
|
|
|
case UFFDIO_WAKE:
|
|
|
|
ret = userfaultfd_wake(ctx, arg);
|
|
|
|
break;
|
2015-09-04 15:47:11 -07:00
|
|
|
case UFFDIO_COPY:
|
|
|
|
ret = userfaultfd_copy(ctx, arg);
|
|
|
|
break;
|
|
|
|
case UFFDIO_ZEROPAGE:
|
|
|
|
ret = userfaultfd_zeropage(ctx, arg);
|
|
|
|
break;
|
userfaultfd: UFFDIO_MOVE uABI
Implement the uABI of UFFDIO_MOVE ioctl.
UFFDIO_COPY performs ~20% better than UFFDIO_MOVE when the application
needs pages to be allocated [1]. However, with UFFDIO_MOVE, if pages are
available (in userspace) for recycling, as is usually the case in heap
compaction algorithms, then we can avoid the page allocation and memcpy
(done by UFFDIO_COPY). Also, since the pages are recycled in the
userspace, we avoid the need to release (via madvise) the pages back to
the kernel [2].
We see over 40% reduction (on a Google pixel 6 device) in the compacting
thread's completion time by using UFFDIO_MOVE vs. UFFDIO_COPY. This was
measured using a benchmark that emulates a heap compaction implementation
using userfaultfd (to allow concurrent accesses by application threads).
More details of the usecase are explained in [2]. Furthermore,
UFFDIO_MOVE enables moving swapped-out pages without touching them within
the same vma. Today, it can only be done by mremap, however it forces
splitting the vma.
[1] https://lore.kernel.org/all/1425575884-2574-1-git-send-email-aarcange@redhat.com/
[2] https://lore.kernel.org/linux-mm/CA+EESO4uO84SSnBhArH4HvLNhaUQ5nZKNKXqxRCyjniNVjp0Aw@mail.gmail.com/
Update for the ioctl_userfaultfd(2) manpage:
UFFDIO_MOVE
(Since Linux xxx) Move a continuous memory chunk into the
userfault registered range and optionally wake up the blocked
thread. The source and destination addresses and the number of
bytes to move are specified by the src, dst, and len fields of
the uffdio_move structure pointed to by argp:
struct uffdio_move {
__u64 dst; /* Destination of move */
__u64 src; /* Source of move */
__u64 len; /* Number of bytes to move */
__u64 mode; /* Flags controlling behavior of move */
__s64 move; /* Number of bytes moved, or negated error */
};
The following value may be bitwise ORed in mode to change the
behavior of the UFFDIO_MOVE operation:
UFFDIO_MOVE_MODE_DONTWAKE
Do not wake up the thread that waits for page-fault
resolution
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES
Allow holes in the source virtual range that is being moved.
When not specified, the holes will result in ENOENT error.
When specified, the holes will be accounted as successfully
moved memory. This is mostly useful to move hugepage aligned
virtual regions without knowing if there are transparent
hugepages in the regions or not, but preventing the risk of
having to split the hugepage during the operation.
The move field is used by the kernel to return the number of
bytes that was actually moved, or an error (a negated errno-
style value). If the value returned in move doesn't match the
value that was specified in len, the operation fails with the
error EAGAIN. The move field is output-only; it is not read by
the UFFDIO_MOVE operation.
The operation may fail for various reasons. Usually, remapping of
pages that are not exclusive to the given process fail; once KSM
might deduplicate pages or fork() COW-shares pages during fork()
with child processes, they are no longer exclusive. Further, the
kernel might only perform lightweight checks for detecting whether
the pages are exclusive, and return -EBUSY in case that check fails.
To make the operation more likely to succeed, KSM should be
disabled, fork() should be avoided or MADV_DONTFORK should be
configured for the source VMA before fork().
This ioctl(2) operation returns 0 on success. In this case, the
entire area was moved. On error, -1 is returned and errno is
set to indicate the error. Possible errors include:
EAGAIN The number of bytes moved (i.e., the value returned in
the move field) does not equal the value that was
specified in the len field.
EINVAL Either dst or len was not a multiple of the system page
size, or the range specified by src and len or dst and len
was invalid.
EINVAL An invalid bit was specified in the mode field.
ENOENT
The source virtual memory range has unmapped holes and
UFFDIO_MOVE_MODE_ALLOW_SRC_HOLES is not set.
EEXIST
The destination virtual memory range is fully or partially
mapped.
EBUSY
The pages in the source virtual memory range are either
pinned or not exclusive to the process. The kernel might
only perform lightweight checks for detecting whether the
pages are exclusive. To make the operation more likely to
succeed, KSM should be disabled, fork() should be avoided
or MADV_DONTFORK should be configured for the source virtual
memory area before fork().
ENOMEM Allocating memory needed for the operation failed.
ESRCH
The target process has exited at the time of a UFFDIO_MOVE
operation.
Link: https://lkml.kernel.org/r/20231206103702.3873743-3-surenb@google.com
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-12-06 03:36:56 -07:00
|
|
|
case UFFDIO_MOVE:
|
|
|
|
ret = userfaultfd_move(ctx, arg);
|
|
|
|
break;
|
2020-04-06 20:06:12 -07:00
|
|
|
case UFFDIO_WRITEPROTECT:
|
|
|
|
ret = userfaultfd_writeprotect(ctx, arg);
|
|
|
|
break;
|
userfaultfd: add UFFDIO_CONTINUE ioctl
This ioctl is how userspace ought to resolve "minor" userfaults. The
idea is, userspace is notified that a minor fault has occurred. It
might change the contents of the page using its second non-UFFD mapping,
or not. Then, it calls UFFDIO_CONTINUE to tell the kernel "I have
ensured the page contents are correct, carry on setting up the mapping".
Note that it doesn't make much sense to use UFFDIO_{COPY,ZEROPAGE} for
MINOR registered VMAs. ZEROPAGE maps the VMA to the zero page; but in
the minor fault case, we already have some pre-existing underlying page.
Likewise, UFFDIO_COPY isn't useful if we have a second non-UFFD mapping.
We'd just use memcpy() or similar instead.
It turns out hugetlb_mcopy_atomic_pte() already does very close to what
we want, if an existing page is provided via `struct page **pagep`. We
already special-case the behavior a bit for the UFFDIO_ZEROPAGE case, so
just extend that design: add an enum for the three modes of operation,
and make the small adjustments needed for the MCOPY_ATOMIC_CONTINUE
case. (Basically, look up the existing page, and avoid adding the
existing page to the page cache or calling set_page_huge_active() on
it.)
Link: https://lkml.kernel.org/r/20210301222728.176417-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Adam Ruprecht <ruprecht@google.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Cannon Matthews <cannonmatthews@google.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chinwen Chang <chinwen.chang@mediatek.com>
Cc: David Rientjes <rientjes@google.com>
Cc: "Dr . David Alan Gilbert" <dgilbert@redhat.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Kirill A. Shutemov <kirill@shutemov.name>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michal Koutn" <mkoutny@suse.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oliver Upton <oupton@google.com>
Cc: Shaohua Li <shli@fb.com>
Cc: Shawn Anastasio <shawn@anastas.io>
Cc: Steven Price <steven.price@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2021-05-04 18:35:49 -07:00
|
|
|
case UFFDIO_CONTINUE:
|
|
|
|
ret = userfaultfd_continue(ctx, arg);
|
|
|
|
break;
|
mm: userfaultfd: add new UFFDIO_POISON ioctl
The basic idea here is to "simulate" memory poisoning for VMs. A VM
running on some host might encounter a memory error, after which some
page(s) are poisoned (i.e., future accesses SIGBUS). They expect that
once poisoned, pages can never become "un-poisoned". So, when we live
migrate the VM, we need to preserve the poisoned status of these pages.
When live migrating, we try to get the guest running on its new host as
quickly as possible. So, we start it running before all memory has been
copied, and before we're certain which pages should be poisoned or not.
So the basic way to use this new feature is:
- On the new host, the guest's memory is registered with userfaultfd, in
either MISSING or MINOR mode (doesn't really matter for this purpose).
- On any first access, we get a userfaultfd event. At this point we can
communicate with the old host to find out if the page was poisoned.
- If so, we can respond with a UFFDIO_POISON - this places a swap marker
so any future accesses will SIGBUS. Because the pte is now "present",
future accesses won't generate more userfaultfd events, they'll just
SIGBUS directly.
UFFDIO_POISON does not handle unmapping previously-present PTEs. This
isn't needed, because during live migration we want to intercept all
accesses with userfaultfd (not just writes, so WP mode isn't useful for
this). So whether minor or missing mode is being used (or both), the PTE
won't be present in any case, so handling that case isn't needed.
Similarly, UFFDIO_POISON won't replace existing PTE markers. This might
be okay to do, but it seems to be safer to just refuse to overwrite any
existing entry (like a UFFD_WP PTE marker).
Link: https://lkml.kernel.org/r/20230707215540.2324998-5-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gaosheng Cui <cuigaosheng1@huawei.com>
Cc: Huang, Ying <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: James Houghton <jthoughton@google.com>
Cc: Jan Alexander Steffens (heftig) <heftig@archlinux.org>
Cc: Jiaqi Yan <jiaqiyan@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nadav Amit <namit@vmware.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Suleiman Souhlal <suleiman@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: T.J. Alumbaugh <talumbau@google.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-07-07 14:55:36 -07:00
|
|
|
case UFFDIO_POISON:
|
|
|
|
ret = userfaultfd_poison(ctx, arg);
|
|
|
|
break;
|
2015-09-04 15:46:31 -07:00
|
|
|
}
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
|
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx = f->private_data;
|
2017-06-20 03:06:13 -07:00
|
|
|
wait_queue_entry_t *wq;
|
2015-09-04 15:46:31 -07:00
|
|
|
unsigned long pending = 0, total = 0;
|
|
|
|
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_lock_irq(&ctx->fault_pending_wqh.lock);
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) {
|
2015-09-04 15:46:44 -07:00
|
|
|
pending++;
|
|
|
|
total++;
|
|
|
|
}
|
sched/wait: Disambiguate wq_entry->task_list and wq_head->task_list naming
So I've noticed a number of instances where it was not obvious from the
code whether ->task_list was for a wait-queue head or a wait-queue entry.
Furthermore, there's a number of wait-queue users where the lists are
not for 'tasks' but other entities (poll tables, etc.), in which case
the 'task_list' name is actively confusing.
To clear this all up, name the wait-queue head and entry list structure
fields unambiguously:
struct wait_queue_head::task_list => ::head
struct wait_queue_entry::task_list => ::entry
For example, this code:
rqw->wait.task_list.next != &wait->task_list
... is was pretty unclear (to me) what it's doing, while now it's written this way:
rqw->wait.head.next != &wait->entry
... which makes it pretty clear that we are iterating a list until we see the head.
Other examples are:
list_for_each_entry_safe(pos, next, &x->task_list, task_list) {
list_for_each_entry(wq, &fence->wait.task_list, task_list) {
... where it's unclear (to me) what we are iterating, and during review it's
hard to tell whether it's trying to walk a wait-queue entry (which would be
a bug), while now it's written as:
list_for_each_entry_safe(pos, next, &x->head, entry) {
list_for_each_entry(wq, &fence->wait.head, entry) {
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-06-20 03:06:46 -07:00
|
|
|
list_for_each_entry(wq, &ctx->fault_wqh.head, entry) {
|
2015-09-04 15:46:31 -07:00
|
|
|
total++;
|
|
|
|
}
|
2019-07-04 15:14:39 -07:00
|
|
|
spin_unlock_irq(&ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If more protocols will be added, there will be all shown
|
|
|
|
* separated by a space. Like this:
|
|
|
|
* protocols: aa:... bb:...
|
|
|
|
*/
|
|
|
|
seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
|
2017-04-07 16:04:42 -07:00
|
|
|
pending, total, UFFD_API, ctx->features,
|
2015-09-04 15:46:31 -07:00
|
|
|
UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
static const struct file_operations userfaultfd_fops = {
|
|
|
|
#ifdef CONFIG_PROC_FS
|
|
|
|
.show_fdinfo = userfaultfd_show_fdinfo,
|
|
|
|
#endif
|
|
|
|
.release = userfaultfd_release,
|
|
|
|
.poll = userfaultfd_poll,
|
2024-04-02 11:26:41 -07:00
|
|
|
.read_iter = userfaultfd_read_iter,
|
2015-09-04 15:46:31 -07:00
|
|
|
.unlocked_ioctl = userfaultfd_ioctl,
|
2018-09-11 12:59:08 -07:00
|
|
|
.compat_ioctl = compat_ptr_ioctl,
|
2015-09-04 15:46:31 -07:00
|
|
|
.llseek = noop_llseek,
|
|
|
|
};
|
|
|
|
|
2015-09-04 15:46:48 -07:00
|
|
|
static void init_once_userfaultfd_ctx(void *mem)
|
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem;
|
|
|
|
|
|
|
|
init_waitqueue_head(&ctx->fault_pending_wqh);
|
|
|
|
init_waitqueue_head(&ctx->fault_wqh);
|
2017-02-22 16:42:21 -07:00
|
|
|
init_waitqueue_head(&ctx->event_wqh);
|
2015-09-04 15:46:48 -07:00
|
|
|
init_waitqueue_head(&ctx->fd_wqh);
|
2020-07-20 08:55:28 -07:00
|
|
|
seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
|
2015-09-04 15:46:48 -07:00
|
|
|
}
|
|
|
|
|
userfaultfd: add /dev/userfaultfd for fine grained access control
Historically, it has been shown that intercepting kernel faults with
userfaultfd (thereby forcing the kernel to wait for an arbitrary amount of
time) can be exploited, or at least can make some kinds of exploits
easier. So, in 37cd0575b8 "userfaultfd: add UFFD_USER_MODE_ONLY" we
changed things so, in order for kernel faults to be handled by
userfaultfd, either the process needs CAP_SYS_PTRACE, or this sysctl must
be configured so that any unprivileged user can do it.
In a typical implementation of a hypervisor with live migration (take
QEMU/KVM as one such example), we do indeed need to be able to handle
kernel faults. But, both options above are less than ideal:
- Toggling the sysctl increases attack surface by allowing any
unprivileged user to do it.
- Granting the live migration process CAP_SYS_PTRACE gives it this
ability, but *also* the ability to "observe and control the
execution of another process [...], and examine and change [its]
memory and registers" (from ptrace(2)). This isn't something we need
or want to be able to do, so granting this permission violates the
"principle of least privilege".
This is all a long winded way to say: we want a more fine-grained way to
grant access to userfaultfd, without granting other additional permissions
at the same time.
To achieve this, add a /dev/userfaultfd misc device. This device provides
an alternative to the userfaultfd(2) syscall for the creation of new
userfaultfds. The idea is, any userfaultfds created this way will be able
to handle kernel faults, without the caller having any special
capabilities. Access to this mechanism is instead restricted using e.g.
standard filesystem permissions.
[axelrasmussen@google.com: Handle misc_register() failure properly]
Link: https://lkml.kernel.org/r/20220819205201.658693-3-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20220808175614.3885028-3-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-08-08 10:56:11 -07:00
|
|
|
static int new_userfaultfd(int flags)
|
2015-09-04 15:46:31 -07:00
|
|
|
{
|
|
|
|
struct userfaultfd_ctx *ctx;
|
2024-04-02 11:26:41 -07:00
|
|
|
struct file *file;
|
2018-01-31 17:19:48 -07:00
|
|
|
int fd;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
|
|
|
BUG_ON(!current->mm);
|
|
|
|
|
|
|
|
/* Check the UFFD_* constants for consistency. */
|
userfaultfd: add UFFD_USER_MODE_ONLY
Patch series "Control over userfaultfd kernel-fault handling", v6.
This patch series is split from [1]. The other series enables SELinux
support for userfaultfd file descriptors so that its creation and movement
can be controlled.
It has been demonstrated on various occasions that suspending kernel code
execution for an arbitrary amount of time at any access to userspace
memory (copy_from_user()/copy_to_user()/...) can be exploited to change
the intended behavior of the kernel. For instance, handling page faults
in kernel-mode using userfaultfd has been exploited in [2, 3]. Likewise,
FUSE, which is similar to userfaultfd in this respect, has been exploited
in [4, 5] for similar outcome.
This small patch series adds a new flag to userfaultfd(2) that allows
callers to give up the ability to handle kernel-mode faults with the
resulting UFFD file object. It then adds a 'user-mode only' option to the
unprivileged_userfaultfd sysctl knob to require unprivileged callers to
use this new flag.
The purpose of this new interface is to decrease the chance of an
unprivileged userfaultfd user taking advantage of userfaultfd to enhance
security vulnerabilities by lengthening the race window in kernel code.
[1] https://lore.kernel.org/lkml/20200211225547.235083-1-dancol@google.com/
[2] https://duasynt.com/blog/linux-kernel-heap-spray
[3] https://duasynt.com/blog/cve-2016-6187-heap-off-by-one-exploit
[4] https://googleprojectzero.blogspot.com/2016/06/exploiting-recursion-in-linux-kernel_20.html
[5] https://bugs.chromium.org/p/project-zero/issues/detail?id=808
This patch (of 2):
userfaultfd handles page faults from both user and kernel code. Add a new
UFFD_USER_MODE_ONLY flag for userfaultfd(2) that makes the resulting
userfaultfd object refuse to handle faults from kernel mode, treating
these faults as if SIGBUS were always raised, causing the kernel code to
fail with EFAULT.
A future patch adds a knob allowing administrators to give some processes
the ability to create userfaultfd file objects only if they pass
UFFD_USER_MODE_ONLY, reducing the likelihood that these processes will
exploit userfaultfd's ability to delay kernel page faults to open timing
windows for future exploits.
Link: https://lkml.kernel.org/r/20201120030411.2690816-1-lokeshgidra@google.com
Link: https://lkml.kernel.org/r/20201120030411.2690816-2-lokeshgidra@google.com
Signed-off-by: Daniel Colascione <dancol@google.com>
Signed-off-by: Lokesh Gidra <lokeshgidra@google.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: <calin@google.com>
Cc: Daniel Colascione <dancol@dancol.org>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nitin Gupta <nigupta@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Shaohua Li <shli@fb.com>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-14 20:13:49 -07:00
|
|
|
BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS);
|
2015-09-04 15:46:31 -07:00
|
|
|
BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
|
|
|
|
BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
|
|
|
|
|
userfaultfd: add UFFD_USER_MODE_ONLY
Patch series "Control over userfaultfd kernel-fault handling", v6.
This patch series is split from [1]. The other series enables SELinux
support for userfaultfd file descriptors so that its creation and movement
can be controlled.
It has been demonstrated on various occasions that suspending kernel code
execution for an arbitrary amount of time at any access to userspace
memory (copy_from_user()/copy_to_user()/...) can be exploited to change
the intended behavior of the kernel. For instance, handling page faults
in kernel-mode using userfaultfd has been exploited in [2, 3]. Likewise,
FUSE, which is similar to userfaultfd in this respect, has been exploited
in [4, 5] for similar outcome.
This small patch series adds a new flag to userfaultfd(2) that allows
callers to give up the ability to handle kernel-mode faults with the
resulting UFFD file object. It then adds a 'user-mode only' option to the
unprivileged_userfaultfd sysctl knob to require unprivileged callers to
use this new flag.
The purpose of this new interface is to decrease the chance of an
unprivileged userfaultfd user taking advantage of userfaultfd to enhance
security vulnerabilities by lengthening the race window in kernel code.
[1] https://lore.kernel.org/lkml/20200211225547.235083-1-dancol@google.com/
[2] https://duasynt.com/blog/linux-kernel-heap-spray
[3] https://duasynt.com/blog/cve-2016-6187-heap-off-by-one-exploit
[4] https://googleprojectzero.blogspot.com/2016/06/exploiting-recursion-in-linux-kernel_20.html
[5] https://bugs.chromium.org/p/project-zero/issues/detail?id=808
This patch (of 2):
userfaultfd handles page faults from both user and kernel code. Add a new
UFFD_USER_MODE_ONLY flag for userfaultfd(2) that makes the resulting
userfaultfd object refuse to handle faults from kernel mode, treating
these faults as if SIGBUS were always raised, causing the kernel code to
fail with EFAULT.
A future patch adds a knob allowing administrators to give some processes
the ability to create userfaultfd file objects only if they pass
UFFD_USER_MODE_ONLY, reducing the likelihood that these processes will
exploit userfaultfd's ability to delay kernel page faults to open timing
windows for future exploits.
Link: https://lkml.kernel.org/r/20201120030411.2690816-1-lokeshgidra@google.com
Link: https://lkml.kernel.org/r/20201120030411.2690816-2-lokeshgidra@google.com
Signed-off-by: Daniel Colascione <dancol@google.com>
Signed-off-by: Lokesh Gidra <lokeshgidra@google.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: <calin@google.com>
Cc: Daniel Colascione <dancol@dancol.org>
Cc: Eric Biggers <ebiggers@kernel.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Rapoport <rppt@linux.vnet.ibm.com>
Cc: Nitin Gupta <nigupta@nvidia.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Shaohua Li <shli@fb.com>
Cc: Stephen Smalley <stephen.smalley.work@gmail.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-12-14 20:13:49 -07:00
|
|
|
if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY))
|
2018-01-31 17:19:48 -07:00
|
|
|
return -EINVAL;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2015-09-04 15:46:48 -07:00
|
|
|
ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
|
2015-09-04 15:46:31 -07:00
|
|
|
if (!ctx)
|
2018-01-31 17:19:48 -07:00
|
|
|
return -ENOMEM;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
2018-12-28 01:34:43 -07:00
|
|
|
refcount_set(&ctx->refcount, 1);
|
2015-09-04 15:46:31 -07:00
|
|
|
ctx->flags = flags;
|
2017-02-22 16:42:21 -07:00
|
|
|
ctx->features = 0;
|
2015-09-04 15:46:31 -07:00
|
|
|
ctx->released = false;
|
2024-02-15 11:27:54 -07:00
|
|
|
init_rwsem(&ctx->map_changing_lock);
|
2021-09-02 14:58:56 -07:00
|
|
|
atomic_set(&ctx->mmap_changing, 0);
|
2015-09-04 15:46:31 -07:00
|
|
|
ctx->mm = current->mm;
|
2024-04-02 11:26:41 -07:00
|
|
|
|
|
|
|
fd = get_unused_fd_flags(flags & UFFD_SHARED_FCNTL_FLAGS);
|
|
|
|
if (fd < 0)
|
|
|
|
goto err_out;
|
2015-09-04 15:46:31 -07:00
|
|
|
|
fs: Rename anon_inode_getfile_secure() and anon_inode_getfd_secure()
The call to the inode_init_security_anon() LSM hook is not the sole
reason to use anon_inode_getfile_secure() or anon_inode_getfd_secure().
For example, the functions also allow one to create a file with non-zero
size, without needing a full-blown filesystem. In this case, you don't
need a "secure" version, just unique inodes; the current name of the
functions is confusing and does not explain well the difference with
the more "standard" anon_inode_getfile() and anon_inode_getfd().
Of course, there is another side of the coin; neither io_uring nor
userfaultfd strictly speaking need distinct inodes, and it is not
that clear anymore that anon_inode_create_get{file,fd}() allow the LSM
to intercept and block the inode's creation. If one was so inclined,
anon_inode_getfile_secure() and anon_inode_getfd_secure() could be kept,
using the shared inode or a new one depending on CONFIG_SECURITY.
However, this is probably overkill, and potentially a cause of bugs in
different configurations. Therefore, just add a comment to io_uring
and userfaultfd explaining the choice of the function.
While at it, remove the export for what is now anon_inode_create_getfd().
There is no in-tree module that uses it, and the old name is gone anyway.
If anybody actually needs the symbol, they can ask or they can just use
anon_inode_create_getfile(), which will be exported very soon for use
in KVM.
Suggested-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
2023-11-03 03:47:51 -07:00
|
|
|
/* Create a new inode so that the LSM can block the creation. */
|
2024-04-02 11:26:41 -07:00
|
|
|
file = anon_inode_create_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
|
2022-07-08 02:34:51 -07:00
|
|
|
O_RDONLY | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
|
2024-04-02 11:26:41 -07:00
|
|
|
if (IS_ERR(file)) {
|
|
|
|
put_unused_fd(fd);
|
|
|
|
fd = PTR_ERR(file);
|
|
|
|
goto err_out;
|
2015-09-17 16:01:54 -07:00
|
|
|
}
|
2024-04-02 11:26:41 -07:00
|
|
|
/* prevent the mm struct to be freed */
|
|
|
|
mmgrab(ctx->mm);
|
|
|
|
file->f_mode |= FMODE_NOWAIT;
|
|
|
|
fd_install(fd, file);
|
|
|
|
return fd;
|
|
|
|
err_out:
|
|
|
|
kmem_cache_free(userfaultfd_ctx_cachep, ctx);
|
2015-09-04 15:46:31 -07:00
|
|
|
return fd;
|
|
|
|
}
|
2015-09-04 15:46:48 -07:00
|
|
|
|
userfaultfd: add /dev/userfaultfd for fine grained access control
Historically, it has been shown that intercepting kernel faults with
userfaultfd (thereby forcing the kernel to wait for an arbitrary amount of
time) can be exploited, or at least can make some kinds of exploits
easier. So, in 37cd0575b8 "userfaultfd: add UFFD_USER_MODE_ONLY" we
changed things so, in order for kernel faults to be handled by
userfaultfd, either the process needs CAP_SYS_PTRACE, or this sysctl must
be configured so that any unprivileged user can do it.
In a typical implementation of a hypervisor with live migration (take
QEMU/KVM as one such example), we do indeed need to be able to handle
kernel faults. But, both options above are less than ideal:
- Toggling the sysctl increases attack surface by allowing any
unprivileged user to do it.
- Granting the live migration process CAP_SYS_PTRACE gives it this
ability, but *also* the ability to "observe and control the
execution of another process [...], and examine and change [its]
memory and registers" (from ptrace(2)). This isn't something we need
or want to be able to do, so granting this permission violates the
"principle of least privilege".
This is all a long winded way to say: we want a more fine-grained way to
grant access to userfaultfd, without granting other additional permissions
at the same time.
To achieve this, add a /dev/userfaultfd misc device. This device provides
an alternative to the userfaultfd(2) syscall for the creation of new
userfaultfds. The idea is, any userfaultfds created this way will be able
to handle kernel faults, without the caller having any special
capabilities. Access to this mechanism is instead restricted using e.g.
standard filesystem permissions.
[axelrasmussen@google.com: Handle misc_register() failure properly]
Link: https://lkml.kernel.org/r/20220819205201.658693-3-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20220808175614.3885028-3-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-08-08 10:56:11 -07:00
|
|
|
static inline bool userfaultfd_syscall_allowed(int flags)
|
|
|
|
{
|
|
|
|
/* Userspace-only page faults are always allowed */
|
|
|
|
if (flags & UFFD_USER_MODE_ONLY)
|
|
|
|
return true;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The user is requesting a userfaultfd which can handle kernel faults.
|
|
|
|
* Privileged users are always allowed to do this.
|
|
|
|
*/
|
|
|
|
if (capable(CAP_SYS_PTRACE))
|
|
|
|
return true;
|
|
|
|
|
|
|
|
/* Otherwise, access to kernel fault handling is sysctl controlled. */
|
|
|
|
return sysctl_unprivileged_userfaultfd;
|
|
|
|
}
|
|
|
|
|
|
|
|
SYSCALL_DEFINE1(userfaultfd, int, flags)
|
|
|
|
{
|
|
|
|
if (!userfaultfd_syscall_allowed(flags))
|
|
|
|
return -EPERM;
|
|
|
|
|
|
|
|
return new_userfaultfd(flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static long userfaultfd_dev_ioctl(struct file *file, unsigned int cmd, unsigned long flags)
|
|
|
|
{
|
|
|
|
if (cmd != USERFAULTFD_IOC_NEW)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
return new_userfaultfd(flags);
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations userfaultfd_dev_fops = {
|
|
|
|
.unlocked_ioctl = userfaultfd_dev_ioctl,
|
|
|
|
.compat_ioctl = userfaultfd_dev_ioctl,
|
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.llseek = noop_llseek,
|
|
|
|
};
|
|
|
|
|
|
|
|
static struct miscdevice userfaultfd_misc = {
|
|
|
|
.minor = MISC_DYNAMIC_MINOR,
|
|
|
|
.name = "userfaultfd",
|
|
|
|
.fops = &userfaultfd_dev_fops
|
|
|
|
};
|
|
|
|
|
2015-09-04 15:46:48 -07:00
|
|
|
static int __init userfaultfd_init(void)
|
|
|
|
{
|
userfaultfd: add /dev/userfaultfd for fine grained access control
Historically, it has been shown that intercepting kernel faults with
userfaultfd (thereby forcing the kernel to wait for an arbitrary amount of
time) can be exploited, or at least can make some kinds of exploits
easier. So, in 37cd0575b8 "userfaultfd: add UFFD_USER_MODE_ONLY" we
changed things so, in order for kernel faults to be handled by
userfaultfd, either the process needs CAP_SYS_PTRACE, or this sysctl must
be configured so that any unprivileged user can do it.
In a typical implementation of a hypervisor with live migration (take
QEMU/KVM as one such example), we do indeed need to be able to handle
kernel faults. But, both options above are less than ideal:
- Toggling the sysctl increases attack surface by allowing any
unprivileged user to do it.
- Granting the live migration process CAP_SYS_PTRACE gives it this
ability, but *also* the ability to "observe and control the
execution of another process [...], and examine and change [its]
memory and registers" (from ptrace(2)). This isn't something we need
or want to be able to do, so granting this permission violates the
"principle of least privilege".
This is all a long winded way to say: we want a more fine-grained way to
grant access to userfaultfd, without granting other additional permissions
at the same time.
To achieve this, add a /dev/userfaultfd misc device. This device provides
an alternative to the userfaultfd(2) syscall for the creation of new
userfaultfds. The idea is, any userfaultfds created this way will be able
to handle kernel faults, without the caller having any special
capabilities. Access to this mechanism is instead restricted using e.g.
standard filesystem permissions.
[axelrasmussen@google.com: Handle misc_register() failure properly]
Link: https://lkml.kernel.org/r/20220819205201.658693-3-axelrasmussen@google.com
Link: https://lkml.kernel.org/r/20220808175614.3885028-3-axelrasmussen@google.com
Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>
Acked-by: Nadav Amit <namit@vmware.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dmitry V. Levin <ldv@altlinux.org>
Cc: Gleb Fotengauer-Malinovskiy <glebfm@altlinux.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Shuah Khan <skhan@linuxfoundation.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zhang Yi <yi.zhang@huawei.com>
Cc: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-08-08 10:56:11 -07:00
|
|
|
int ret;
|
|
|
|
|
|
|
|
ret = misc_register(&userfaultfd_misc);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
|
2015-09-04 15:46:48 -07:00
|
|
|
userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
|
|
|
|
sizeof(struct userfaultfd_ctx),
|
|
|
|
0,
|
|
|
|
SLAB_HWCACHE_ALIGN|SLAB_PANIC,
|
|
|
|
init_once_userfaultfd_ctx);
|
2023-03-01 03:06:27 -07:00
|
|
|
#ifdef CONFIG_SYSCTL
|
|
|
|
register_sysctl_init("vm", vm_userfaultfd_table);
|
|
|
|
#endif
|
2015-09-04 15:46:48 -07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
__initcall(userfaultfd_init);
|