Lines Matching full:the
10 Userfaults allow the implementation of on-demand paging from userland
12 memory page faults, something otherwise only the kernel code could do.
15 of the ``PROT_NONE+SIGSEGV`` trick.
20 Userfaults are delivered and resolved through the ``userfaultfd`` syscall.
22 The ``userfaultfd`` (aside from registering and unregistering virtual
25 1) ``read/POLLIN`` protocol to notify a userland thread of the faults
28 2) various ``UFFDIO_*`` ioctls that can manage the virtual memory regions
29 registered in the ``userfaultfd`` that allows userland to efficiently
30 resolve the userfaults it receives via 1) or to manage the virtual
31 memory in the background
33 The real advantage of userfaults if compared to regular virtual memory
34 management of mremap/mprotect is that the userfaults in all their
35 operations never involve heavyweight structures like vmas (in fact the
36 ``userfaultfd`` runtime load never takes the mmap_lock for writing).
42 The ``userfaultfd`` once opened by invoking the syscall, can also be
43 passed using unix domain sockets to a manager process, so the same
44 manager process could handle the userfaults of a multitude of
46 (well of course unless they later try to use the ``userfaultfd``
47 themselves on the same region the manager is already tracking, which
53 When first opened the ``userfaultfd`` must be enabled invoking the
55 a later API version) which will specify the ``read/POLLIN`` protocol
56 userland intends to speak on the ``UFFD`` and the ``uffdio_api.features``
57 userland requires. The ``UFFDIO_API`` ioctl if successful (i.e. if the
58 requested ``uffdio_api.api`` is spoken also by the running kernel and the
61 respectively all the available features of the read(2) protocol and
62 the generic ioctl available.
64 The ``uffdio_api.features`` bitmask returned by the ``UFFDIO_API`` ioctl
65 defines what memory types are supported by the ``userfaultfd`` and what
68 - The ``UFFD_FEATURE_EVENT_*`` flags indicate that various other events
70 detail below in the `Non-cooperative userfaultfd`_ section.
73 indicate that the kernel supports ``UFFDIO_REGISTER_MODE_MISSING``
78 - ``UFFD_FEATURE_MINOR_HUGETLBFS`` indicates that the kernel supports
80 areas. ``UFFD_FEATURE_MINOR_SHMEM`` is the analogous feature indicating
83 The userland application should set the feature flags it intends to use
84 when invoking the ``UFFDIO_API`` ioctl, to request that those features be
87 Once the ``userfaultfd`` API has been enabled the ``UFFDIO_REGISTER``
88 ioctl should be invoked (if present in the returned ``uffdio_api.ioctls``
89 bitmask) to register a memory range in the ``userfaultfd`` by setting the
90 uffdio_register structure accordingly. The ``uffdio_register.mode``
91 bitmask will specify to the kernel which kind of faults to track for
92 the range. The ``UFFDIO_REGISTER`` ioctl will return the
94 userfaults on the range registered. Not all ioctls will necessarily be
98 Userland can use the ``uffdio_register.ioctls`` to manage the virtual
99 address space in the background (to add or potentially also remove
100 memory from the ``userfaultfd`` registered range). This means a userfault
101 could be triggering just before userland maps in the background the
112 - ``UFFDIO_ZEROPAGE`` atomically zeros the new page.
116 These operations are atomic in the sense that they guarantee nothing can
117 see a half-populated page, since readers will keep userfaulting until the
120 By default, these wake up userfaults blocked on the range in question.
124 Which ioctl to choose depends on the kind of page fault, and what we'd
127 - For ``UFFDIO_REGISTER_MODE_MISSING`` faults, the fault needs to be
129 the zero page (``UFFDIO_ZEROPAGE``). By default, the kernel would map
130 the zero page for a missing fault. With userfaultfd, userspace can
131 decide what content to provide before the faulting thread continues.
134 the page cache). Userspace has the option of modifying the page's
135 contents before resolving the fault. Once the contents are correct
136 (modified or not), userspace asks the kernel to map the page and let the
142 ``pagefault.flags`` within the ``uffd_msg``, checking for the
145 - None of the page-delivering ioctls default to the range that you
146 registered with. You must fill in all fields for the appropriate
147 ioctl struct including the range.
149 - You get the address of the access that triggered the missing page
150 event out of a struct uffd_msg that you read in the thread from the
152 Keep in mind that unless you used DONTWAKE then the first of any of
153 those IOCTLs wakes up the faulting thread.
169 in the struct passed in. The range does not default to and does not
170 have to be identical to the range you registered with. You can write
171 protect as many ranges as you like (inside the registered range).
172 Then, in the thread reading from uffd the struct will have
176 set. This wakes up the thread which will continue to run with writes. This
177 allows you to do the bookkeeping about the write in the uffd reading
178 thread before the ioctl.
181 ``UFFDIO_REGISTER_MODE_WP`` then you need to think about the sequence in
183 difference between writes into a WP area and into a !WP area. The
184 former will have ``UFFD_PAGEFAULT_FLAG_WP`` set, the latter
185 ``UFFD_PAGEFAULT_FLAG_WRITE``. The latter did not fail on protection but
192 QEMU/KVM is using the ``userfaultfd`` syscall to implement postcopy live
195 all of its memory residing on a different node in the cloud. The
202 page faults in the guest scheduler so those guest processes that
204 the guest vcpus.
210 The implementation of postcopy live migration currently uses one
211 single bidirectional socket but in the future two different sockets
212 will be used (to reduce the latency of the userfaults to the minimum
215 The QEMU in the source node writes all pages that it knows are missing
216 in the destination node, into the socket, and the migration thread of
217 the QEMU running in the destination node runs ``UFFDIO_COPY|ZEROPAGE``
218 ioctls on the ``userfaultfd`` in order to map the received pages into the
219 guest (``UFFDIO_ZEROCOPY`` is used if the source page was a zero page).
221 A different postcopy thread in the destination node listens with
222 poll() to the ``userfaultfd`` in parallel. When a ``POLLIN`` event is
223 generated after a userfault triggers, the postcopy thread read() from
224 the ``userfaultfd`` and receives the fault address (or ``-EAGAIN`` in case the
226 by the parallel QEMU migration thread).
228 After the QEMU postcopy thread (running in the destination node) gets
229 the userfault address it writes the information about the missing page
230 into the socket. The QEMU source node receives the information and
233 (just the time to flush the tcp_wmem queue through the network) the
234 migration thread in the QEMU running in the destination node will
235 receive the page that triggered the userfault and it'll map it as
236 usual with the ``UFFDIO_COPY|ZEROPAGE`` (without actually knowing if it
237 was spontaneously sent by the source or if it was an urgent page
240 By the time the userfaults start, the QEMU in the destination node
241 doesn't need to keep any per-page state bitmap relative to the live
243 the QEMU running in the source node to know which pages are still
244 missing in the destination node. The bitmap in the source node is
247 course the bitmap is updated accordingly. It's also useful to avoid
248 sending the same page twice (in case the userfault is read by the
249 postcopy thread just before ``UFFDIO_COPY|ZEROPAGE`` runs in the migration
255 When the ``userfaultfd`` is monitored by an external manager, the manager
256 must be able to track changes in the process virtual memory
257 layout. Userfaultfd can notify the manager about such changes using
258 the same read(2) protocol as for the page fault notifications. The
264 enabled, the ``userfaultfd`` context of the parent process is
265 duplicated into the newly created process. The manager
266 receives ``UFFD_EVENT_FORK`` with file descriptor of the new
267 ``userfaultfd`` context in the ``uffd_msg.fork``.
270 enable notifications about mremap() calls. When the
272 different location, the manager will receive
273 ``UFFD_EVENT_REMAP``. The ``uffd_msg.remap`` will contain the old and
274 new addresses of the area and its original length.
278 madvise(MADV_DONTNEED) calls. The event ``UFFD_EVENT_REMOVE`` will
279 be generated upon these calls to madvise(). The ``uffd_msg.remove``
280 will contain start and end addresses of the removed area.
283 enable notifications about memory unmapping. The manager will
285 end addresses of the unmapped area.
287 Although the ``UFFD_FEATURE_EVENT_REMOVE`` and ``UFFD_FEATURE_EVENT_UNMAP``
288 are pretty similar, they quite differ in the action expected from the
289 ``userfaultfd`` manager. In the former case, the virtual memory is
290 removed, but the area is not, the area remains monitored by the
292 delivered to the manager. The proper resolution for such page fault is
293 to zeromap the faulting address. However, in the latter case, when an
295 implicitly (e.g. during mremap()), the area is removed and in turn the
296 ``userfaultfd`` context for such area disappears too and the manager will
297 not get further userland page faults from the removed area. Still, the
299 ``UFFDIO_COPY`` on the unmapped area.
302 explicit or implicit wakeup, all the events are delivered
303 asynchronously and the non-cooperative process resumes execution as
304 soon as manager executes read(). The ``userfaultfd`` manager should
305 carefully synchronize calls to ``UFFDIO_COPY`` with the events
306 processing. To aid the synchronization, the ``UFFDIO_COPY`` ioctl will
307 return ``-ENOSPC`` when the monitored process exits at the time of
308 ``UFFDIO_COPY``, and ``-ENOENT``, when the non-cooperative process has changed
312 The current asynchronous model of the event delivery is optimal for
315 ``userfaultfd`` feature to facilitate multithreading enhancements of the
317 run in parallel to the event reception. Single threaded
318 implementations should continue to use the current async event