Linux/Documentation/admin-guide/mm/userfaultfd.rst

Version: ~ [ linux-6.12-rc7 ] ~ [ linux-6.11.7 ] ~ [ linux-6.10.14 ] ~ [ linux-6.9.12 ] ~ [ linux-6.8.12 ] ~ [ linux-6.7.12 ] ~ [ linux-6.6.60 ] ~ [ linux-6.5.13 ] ~ [ linux-6.4.16 ] ~ [ linux-6.3.13 ] ~ [ linux-6.2.16 ] ~ [ linux-6.1.116 ] ~ [ linux-6.0.19 ] ~ [ linux-5.19.17 ] ~ [ linux-5.18.19 ] ~ [ linux-5.17.15 ] ~ [ linux-5.16.20 ] ~ [ linux-5.15.171 ] ~ [ linux-5.14.21 ] ~ [ linux-5.13.19 ] ~ [ linux-5.12.19 ] ~ [ linux-5.11.22 ] ~ [ linux-5.10.229 ] ~ [ linux-5.9.16 ] ~ [ linux-5.8.18 ] ~ [ linux-5.7.19 ] ~ [ linux-5.6.19 ] ~ [ linux-5.5.19 ] ~ [ linux-5.4.285 ] ~ [ linux-5.3.18 ] ~ [ linux-5.2.21 ] ~ [ linux-5.1.21 ] ~ [ linux-5.0.21 ] ~ [ linux-4.20.17 ] ~ [ linux-4.19.323 ] ~ [ linux-4.18.20 ] ~ [ linux-4.17.19 ] ~ [ linux-4.16.18 ] ~ [ linux-4.15.18 ] ~ [ linux-4.14.336 ] ~ [ linux-4.13.16 ] ~ [ linux-4.12.14 ] ~ [ linux-4.11.12 ] ~ [ linux-4.10.17 ] ~ [ linux-4.9.337 ] ~ [ linux-4.4.302 ] ~ [ linux-3.10.108 ] ~ [ linux-2.6.32.71 ] ~ [ linux-2.6.0 ] ~ [ linux-2.4.37.11 ] ~ [ unix-v6-master ] ~ [ ccs-tools-1.8.12 ] ~ [ policy-sample ] ~
Architecture: ~ [ i386 ] ~ [ alpha ] ~ [ m68k ] ~ [ mips ] ~ [ ppc ] ~ [ sparc ] ~ [ sparc64 ] ~

Diff markup

>> 1 .. _userfaultfd: >> 2 1 =========== 3 =========== 2 Userfaultfd 4 Userfaultfd 3 =========== 5 =========== 4 6 5 Objective 7 Objective 6 ========= 8 ========= 7 9 8 Userfaults allow the implementation of on-dema 10 Userfaults allow the implementation of on-demand paging from userland 9 and more generally they allow userland to take 11 and more generally they allow userland to take control of various 10 memory page faults, something otherwise only t 12 memory page faults, something otherwise only the kernel code could do. 11 13 12 For example userfaults allows a proper and mor 14 For example userfaults allows a proper and more optimal implementation 13 of the ``PROT_NONE+SIGSEGV`` trick. !! 15 of the PROT_NONE+SIGSEGV trick. 14 16 15 Design 17 Design 16 ====== 18 ====== 17 19 18 Userspace creates a new userfaultfd, initializ !! 20 Userfaults are delivered and resolved through the userfaultfd syscall. 19 regions of virtual memory with it. Then, any p << 20 region(s) result in a message being delivered << 21 userspace of the fault. << 22 21 23 The ``userfaultfd`` (aside from registering an !! 22 The userfaultfd (aside from registering and unregistering virtual 24 memory ranges) provides two primary functional 23 memory ranges) provides two primary functionalities: 25 24 26 1) ``read/POLLIN`` protocol to notify a userla !! 25 1) read/POLLIN protocol to notify a userland thread of the faults 27 happening 26 happening 28 27 29 2) various ``UFFDIO_*`` ioctls that can manage !! 28 2) various UFFDIO_* ioctls that can manage the virtual memory regions 30 registered in the ``userfaultfd`` that allo !! 29 registered in the userfaultfd that allows userland to efficiently 31 resolve the userfaults it receives via 1) o 30 resolve the userfaults it receives via 1) or to manage the virtual 32 memory in the background 31 memory in the background 33 32 34 The real advantage of userfaults if compared t 33 The real advantage of userfaults if compared to regular virtual memory 35 management of mremap/mprotect is that the user 34 management of mremap/mprotect is that the userfaults in all their 36 operations never involve heavyweight structure 35 operations never involve heavyweight structures like vmas (in fact the 37 ``userfaultfd`` runtime load never takes the m !! 36 userfaultfd runtime load never takes the mmap_sem for writing). >> 37 38 Vmas are not suitable for page- (or hugepage) 38 Vmas are not suitable for page- (or hugepage) granular fault tracking 39 when dealing with virtual address spaces that 39 when dealing with virtual address spaces that could span 40 Terabytes. Too many vmas would be needed for t 40 Terabytes. Too many vmas would be needed for that. 41 41 42 The ``userfaultfd``, once created, can also be !! 42 The userfaultfd once opened by invoking the syscall, can also be 43 passed using unix domain sockets to a manager 43 passed using unix domain sockets to a manager process, so the same 44 manager process could handle the userfaults of 44 manager process could handle the userfaults of a multitude of 45 different processes without them being aware a 45 different processes without them being aware about what is going on 46 (well of course unless they later try to use t !! 46 (well of course unless they later try to use the userfaultfd 47 themselves on the same region the manager is a 47 themselves on the same region the manager is already tracking, which 48 is a corner case that would currently return ` !! 48 is a corner case that would currently return -EBUSY). 49 49 50 API 50 API 51 === 51 === 52 52 53 Creating a userfaultfd !! 53 When first opened the userfaultfd must be enabled invoking the 54 ---------------------- !! 54 UFFDIO_API ioctl specifying a uffdio_api.api value set to UFFD_API (or 55 !! 55 a later API version) which will specify the read/POLLIN protocol 56 There are two ways to create a new userfaultfd !! 56 userland intends to speak on the UFFD and the uffdio_api.features 57 restrict access to this functionality (since h !! 57 userland requires. The UFFDIO_API ioctl if successful (i.e. if the 58 handle kernel page faults have been a useful t !! 58 requested uffdio_api.api is spoken also by the running kernel and the 59 << 60 The first way, supported since userfaultfd was << 61 userfaultfd(2) syscall. Access to this is cont << 62 << 63 - Any user can always create a userfaultfd whi << 64 only. Such a userfaultfd can be created usin << 65 with the flag UFFD_USER_MODE_ONLY. << 66 << 67 - In order to also trap kernel page faults for << 68 process needs the CAP_SYS_PTRACE capability, << 69 vm.unprivileged_userfaultfd set to 1. By def << 70 is set to 0. << 71 << 72 The second way, added to the kernel more recen << 73 /dev/userfaultfd and issuing a USERFAULTFD_IOC << 74 yields equivalent userfaultfds to the userfaul << 75 << 76 Unlike userfaultfd(2), access to /dev/userfaul << 77 filesystem permissions (user/group/mode), whic << 78 userfaultfd specifically, without also grantin << 79 the same time (as e.g. granting CAP_SYS_PTRACE << 80 to /dev/userfaultfd can always create userfaul << 81 vm.unprivileged_userfaultfd is not considered. << 82 << 83 Initializing a userfaultfd << 84 -------------------------- << 85 << 86 When first opened the ``userfaultfd`` must be << 87 ``UFFDIO_API`` ioctl specifying a ``uffdio_api << 88 a later API version) which will specify the `` << 89 userland intends to speak on the ``UFFD`` and << 90 userland requires. The ``UFFDIO_API`` ioctl if << 91 requested ``uffdio_api.api`` is spoken also by << 92 requested features are going to be enabled) wi 59 requested features are going to be enabled) will return into 93 ``uffdio_api.features`` and ``uffdio_api.ioctl !! 60 uffdio_api.features and uffdio_api.ioctls two 64bit bitmasks of 94 respectively all the available features of the 61 respectively all the available features of the read(2) protocol and 95 the generic ioctl available. 62 the generic ioctl available. 96 63 97 The ``uffdio_api.features`` bitmask returned b !! 64 The uffdio_api.features bitmask returned by the UFFDIO_API ioctl 98 defines what memory types are supported by the !! 65 defines what memory types are supported by the userfaultfd and what 99 events, except page fault notifications, may b !! 66 events, except page fault notifications, may be generated. 100 !! 67 101 - The ``UFFD_FEATURE_EVENT_*`` flags indicate !! 68 If the kernel supports registering userfaultfd ranges on hugetlbfs 102 other than page faults are supported. These !! 69 virtual memory areas, UFFD_FEATURE_MISSING_HUGETLBFS will be set in 103 detail below in the `Non-cooperative userfau !! 70 uffdio_api.features. Similarly, UFFD_FEATURE_MISSING_SHMEM will be 104 !! 71 set if the kernel supports registering userfaultfd ranges on shared 105 - ``UFFD_FEATURE_MISSING_HUGETLBFS`` and ``UFF !! 72 memory (covering all shmem APIs, i.e. tmpfs, IPCSHM, /dev/zero 106 indicate that the kernel supports ``UFFDIO_R !! 73 MAP_SHARED, memfd_create, etc). 107 registrations for hugetlbfs and shared memor !! 74 108 i.e. tmpfs, ``IPCSHM``, ``/dev/zero``, ``MAP !! 75 The userland application that wants to use userfaultfd with hugetlbfs 109 etc) virtual memory areas, respectively. !! 76 or shared memory need to set the corresponding flag in 110 !! 77 uffdio_api.features to enable those features. 111 - ``UFFD_FEATURE_MINOR_HUGETLBFS`` indicates t !! 78 112 ``UFFDIO_REGISTER_MODE_MINOR`` registration !! 79 If the userland desires to receive notifications for events other than 113 areas. ``UFFD_FEATURE_MINOR_SHMEM`` is the a !! 80 page faults, it has to verify that uffdio_api.features has appropriate 114 support for shmem virtual memory areas. !! 81 UFFD_FEATURE_EVENT_* bits set. These events are described in more 115 !! 82 detail below in "Non-cooperative userfaultfd" section. 116 - ``UFFD_FEATURE_MOVE`` indicates that the ker !! 83 117 existing page contents from userspace. !! 84 Once the userfaultfd has been enabled the UFFDIO_REGISTER ioctl should 118 !! 85 be invoked (if present in the returned uffdio_api.ioctls bitmask) to 119 The userland application should set the featur !! 86 register a memory range in the userfaultfd by setting the 120 when invoking the ``UFFDIO_API`` ioctl, to req !! 87 uffdio_register structure accordingly. The uffdio_register.mode 121 enabled if supported. << 122 << 123 Once the ``userfaultfd`` API has been enabled << 124 ioctl should be invoked (if present in the ret << 125 bitmask) to register a memory range in the ``u << 126 uffdio_register structure accordingly. The ``u << 127 bitmask will specify to the kernel which kind 88 bitmask will specify to the kernel which kind of faults to track for 128 the range. The ``UFFDIO_REGISTER`` ioctl will !! 89 the range (UFFDIO_REGISTER_MODE_MISSING would track missing 129 ``uffdio_register.ioctls`` bitmask of ioctls t !! 90 pages). The UFFDIO_REGISTER ioctl will return the >> 91 uffdio_register.ioctls bitmask of ioctls that are suitable to resolve 130 userfaults on the range registered. Not all io 92 userfaults on the range registered. Not all ioctls will necessarily be 131 supported for all memory types (e.g. anonymous !! 93 supported for all memory types depending on the underlying virtual 132 hugetlbfs), or all types of intercepted faults !! 94 memory backend (anonymous memory vs tmpfs vs real filebacked >> 95 mappings). 133 96 134 Userland can use the ``uffdio_register.ioctls` !! 97 Userland can use the uffdio_register.ioctls to manage the virtual 135 address space in the background (to add or pot 98 address space in the background (to add or potentially also remove 136 memory from the ``userfaultfd`` registered ran !! 99 memory from the userfaultfd registered range). This means a userfault 137 could be triggering just before userland maps 100 could be triggering just before userland maps in the background the 138 user-faulted page. 101 user-faulted page. 139 102 140 Resolving Userfaults !! 103 The primary ioctl to resolve userfaults is UFFDIO_COPY. That 141 -------------------- !! 104 atomically copies a page into the userfault registered range and wakes 142 !! 105 up the blocked userfaults (unless uffdio_copy.mode & 143 There are three basic ways to resolve userfaul !! 106 UFFDIO_COPY_MODE_DONTWAKE is set). Other ioctl works similarly to 144 !! 107 UFFDIO_COPY. They're atomic as in guaranteeing that nothing can see an 145 - ``UFFDIO_COPY`` atomically copies some exist !! 108 half copied page since it'll keep userfaulting until the copy has 146 userspace. !! 109 finished. 147 << 148 - ``UFFDIO_ZEROPAGE`` atomically zeros the new << 149 << 150 - ``UFFDIO_CONTINUE`` maps an existing, previo << 151 << 152 These operations are atomic in the sense that << 153 see a half-populated page, since readers will << 154 operation has finished. << 155 << 156 By default, these wake up userfaults blocked o << 157 They support a ``UFFDIO_*_MODE_DONTWAKE`` ``mo << 158 that waking will be done separately at some la << 159 << 160 Which ioctl to choose depends on the kind of p << 161 like to do to resolve it: << 162 << 163 - For ``UFFDIO_REGISTER_MODE_MISSING`` faults, << 164 resolved by either providing a new page (``U << 165 the zero page (``UFFDIO_ZEROPAGE``). By defa << 166 the zero page for a missing fault. With user << 167 decide what content to provide before the fa << 168 << 169 - For ``UFFDIO_REGISTER_MODE_MINOR`` faults, t << 170 the page cache). Userspace has the option of << 171 contents before resolving the fault. Once th << 172 (modified or not), userspace asks the kernel << 173 faulting thread continue with ``UFFDIO_CONTI << 174 110 175 Notes: 111 Notes: 176 112 177 - You can tell which kind of fault occurred by !! 113 - If you requested UFFDIO_REGISTER_MODE_MISSING when registering then 178 ``pagefault.flags`` within the ``uffd_msg``, !! 114 you must provide some kind of page in your thread after reading from 179 ``UFFD_PAGEFAULT_FLAG_*`` flags. !! 115 the uffd. You must provide either UFFDIO_COPY or UFFDIO_ZEROPAGE. >> 116 The normal behavior of the OS automatically providing a zero page on >> 117 an annonymous mmaping is not in place. 180 118 181 - None of the page-delivering ioctls default t 119 - None of the page-delivering ioctls default to the range that you 182 registered with. You must fill in all field 120 registered with. You must fill in all fields for the appropriate 183 ioctl struct including the range. 121 ioctl struct including the range. 184 122 185 - You get the address of the access that trigg 123 - You get the address of the access that triggered the missing page 186 event out of a struct uffd_msg that you read 124 event out of a struct uffd_msg that you read in the thread from the 187 uffd. You can supply as many pages as you w !! 125 uffd. You can supply as many pages as you want with UFFDIO_COPY or 188 Keep in mind that unless you used DONTWAKE t !! 126 UFFDIO_ZEROPAGE. Keep in mind that unless you used DONTWAKE then 189 those IOCTLs wakes up the faulting thread. !! 127 the first of any of those IOCTLs wakes up the faulting thread. 190 !! 128 191 - Be sure to test for all errors including !! 129 - Be sure to test for all errors including (pollfd[0].revents & 192 (``pollfd[0].revents & POLLERR``). This can !! 130 POLLERR). This can happen, e.g. when ranges supplied were 193 supplied were incorrect. !! 131 incorrect. 194 132 195 Write Protect Notifications 133 Write Protect Notifications 196 --------------------------- 134 --------------------------- 197 135 198 This is equivalent to (but faster than) using 136 This is equivalent to (but faster than) using mprotect and a SIGSEGV 199 signal handler. 137 signal handler. 200 138 201 Firstly you need to register a range with ``UF !! 139 Firstly you need to register a range with UFFDIO_REGISTER_MODE_WP. 202 Instead of using mprotect(2) you use !! 140 Instead of using mprotect(2) you use ioctl(uffd, UFFDIO_WRITEPROTECT, 203 ``ioctl(uffd, UFFDIO_WRITEPROTECT, struct *uff !! 141 struct *uffdio_writeprotect) while mode = UFFDIO_WRITEPROTECT_MODE_WP 204 while ``mode = UFFDIO_WRITEPROTECT_MODE_WP`` << 205 in the struct passed in. The range does not d 142 in the struct passed in. The range does not default to and does not 206 have to be identical to the range you register 143 have to be identical to the range you registered with. You can write 207 protect as many ranges as you like (inside the 144 protect as many ranges as you like (inside the registered range). 208 Then, in the thread reading from uffd the stru 145 Then, in the thread reading from uffd the struct will have 209 ``msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLA !! 146 msg.arg.pagefault.flags & UFFD_PAGEFAULT_FLAG_WP set. Now you send 210 ``ioctl(uffd, UFFDIO_WRITEPROTECT, struct *uff !! 147 ioctl(uffd, UFFDIO_WRITEPROTECT, struct *uffdio_writeprotect) again 211 again while ``pagefault.mode`` does not have ` !! 148 while pagefault.mode does not have UFFDIO_WRITEPROTECT_MODE_WP set. 212 set. This wakes up the thread which will conti !! 149 This wakes up the thread which will continue to run with writes. This 213 allows you to do the bookkeeping about the wri 150 allows you to do the bookkeeping about the write in the uffd reading 214 thread before the ioctl. 151 thread before the ioctl. 215 152 216 If you registered with both ``UFFDIO_REGISTER_ !! 153 If you registered with both UFFDIO_REGISTER_MODE_MISSING and 217 ``UFFDIO_REGISTER_MODE_WP`` then you need to t !! 154 UFFDIO_REGISTER_MODE_WP then you need to think about the sequence in 218 which you supply a page and undo write protect 155 which you supply a page and undo write protect. Note that there is a 219 difference between writes into a WP area and i 156 difference between writes into a WP area and into a !WP area. The 220 former will have ``UFFD_PAGEFAULT_FLAG_WP`` se !! 157 former will have UFFD_PAGEFAULT_FLAG_WP set, the latter 221 ``UFFD_PAGEFAULT_FLAG_WRITE``. The latter did !! 158 UFFD_PAGEFAULT_FLAG_WRITE. The latter did not fail on protection but 222 you still need to supply a page when ``UFFDIO_ !! 159 you still need to supply a page when UFFDIO_REGISTER_MODE_MISSING was 223 used. 160 used. 224 161 225 Userfaultfd write-protect mode currently behav << 226 (when e.g. page is missing) over different typ << 227 << 228 For anonymous memory, ``ioctl(UFFDIO_WRITEPROT << 229 (e.g. when pages are missing and not populated << 230 like shmem and hugetlbfs, none ptes will be wr << 231 present pte. In other words, there will be a << 232 message generated when writing to a missing pa << 233 as long as the page range was write-protected << 234 not be generated on anonymous memories by defa << 235 << 236 If the application wants to be able to write p << 237 memory, one can pre-populate the memory with e << 238 newer kernels, one can also detect the feature << 239 and set the feature bit in advance to make sur << 240 write protected even upon anonymous memory. << 241 << 242 When using ``UFFDIO_REGISTER_MODE_WP`` in comb << 243 ``UFFDIO_REGISTER_MODE_MISSING`` or ``UFFDIO_R << 244 resolving missing / minor faults with ``UFFDIO << 245 respectively, it may be desirable for the new << 246 write-protected (so future writes will also re << 247 support a mode flag (``UFFDIO_COPY_MODE_WP`` o << 248 respectively) to configure the mapping this wa << 249 << 250 If the userfaultfd context has ``UFFD_FEATURE_ << 251 any vma registered with write-protection will << 252 than the default sync mode. << 253 << 254 In async mode, there will be no message genera << 255 happens, meanwhile the write-protection will b << 256 the kernel. It can be seen as a more accurate << 257 tracking and it can be different in a few ways << 258 << 259 - The dirty result will not be affected by v << 260 merging) because the dirty is only tracked << 261 << 262 - It supports range operations by default, s << 263 any range of memory as long as page aligne << 264 << 265 - Dirty information will not get lost if the << 266 various reasons (e.g. during split of a sh << 267 << 268 - Due to a reverted meaning of soft-dirty (p << 269 set; dirty when uffd-wp bit cleared), it h << 270 some of the memory operations. For exampl << 271 anonymous (or ``MADV_REMOVE`` on a file ma << 272 dirtying of memory by dropping uffd-wp bit << 273 << 274 The user app can collect the "written/dirty" s << 275 uffd-wp bit for the pages being interested in << 276 << 277 The page will not be under track of uffd-wp as << 278 explicitly write-protected by ``ioctl(UFFDIO_W << 279 flag ``UFFDIO_WRITEPROTECT_MODE_WP`` set. Try << 280 that was tracked by async mode userfaultfd-wp << 281 << 282 When userfaultfd-wp async mode is used alone, << 283 kinds of memory. << 284 << 285 Memory Poisioning Emulation << 286 --------------------------- << 287 << 288 In response to a fault (either missing or mino << 289 take to "resolve" it is to issue a ``UFFDIO_PO << 290 future faulters to either get a SIGBUS, or in << 291 receive an MCE as if there were hardware memor << 292 << 293 This is used to emulate hardware memory poison << 294 machine which experiences a real hardware memo << 295 the VM to another physical machine. Since we w << 296 transparent to the guest, we want that same ad << 297 still poisoned, even though it's on a new phys << 298 doesn't have a memory error in the exact same << 299 << 300 QEMU/KVM 162 QEMU/KVM 301 ======== 163 ======== 302 164 303 QEMU/KVM is using the ``userfaultfd`` syscall !! 165 QEMU/KVM is using the userfaultfd syscall to implement postcopy live 304 migration. Postcopy live migration is one form 166 migration. Postcopy live migration is one form of memory 305 externalization consisting of a virtual machin 167 externalization consisting of a virtual machine running with part or 306 all of its memory residing on a different node 168 all of its memory residing on a different node in the cloud. The 307 ``userfaultfd`` abstraction is generic enough !! 169 userfaultfd abstraction is generic enough that not a single line of 308 KVM kernel code had to be modified in order to 170 KVM kernel code had to be modified in order to add postcopy live 309 migration to QEMU. 171 migration to QEMU. 310 172 311 Guest async page faults, ``FOLL_NOWAIT`` and a !! 173 Guest async page faults, FOLL_NOWAIT and all other GUP features work 312 just fine in combination with userfaults. User 174 just fine in combination with userfaults. Userfaults trigger async 313 page faults in the guest scheduler so those gu 175 page faults in the guest scheduler so those guest processes that 314 aren't waiting for userfaults (i.e. network bo 176 aren't waiting for userfaults (i.e. network bound) can keep running in 315 the guest vcpus. 177 the guest vcpus. 316 178 317 It is generally beneficial to run one pass of 179 It is generally beneficial to run one pass of precopy live migration 318 just before starting postcopy live migration, 180 just before starting postcopy live migration, in order to avoid 319 generating userfaults for readonly guest regio 181 generating userfaults for readonly guest regions. 320 182 321 The implementation of postcopy live migration 183 The implementation of postcopy live migration currently uses one 322 single bidirectional socket but in the future 184 single bidirectional socket but in the future two different sockets 323 will be used (to reduce the latency of the use 185 will be used (to reduce the latency of the userfaults to the minimum 324 possible without having to decrease ``/proc/sy !! 186 possible without having to decrease /proc/sys/net/ipv4/tcp_wmem). 325 187 326 The QEMU in the source node writes all pages t 188 The QEMU in the source node writes all pages that it knows are missing 327 in the destination node, into the socket, and 189 in the destination node, into the socket, and the migration thread of 328 the QEMU running in the destination node runs !! 190 the QEMU running in the destination node runs UFFDIO_COPY|ZEROPAGE 329 ioctls on the ``userfaultfd`` in order to map !! 191 ioctls on the userfaultfd in order to map the received pages into the 330 guest (``UFFDIO_ZEROCOPY`` is used if the sour !! 192 guest (UFFDIO_ZEROCOPY is used if the source page was a zero page). 331 193 332 A different postcopy thread in the destination 194 A different postcopy thread in the destination node listens with 333 poll() to the ``userfaultfd`` in parallel. Whe !! 195 poll() to the userfaultfd in parallel. When a POLLIN event is 334 generated after a userfault triggers, the post 196 generated after a userfault triggers, the postcopy thread read() from 335 the ``userfaultfd`` and receives the fault add !! 197 the userfaultfd and receives the fault address (or -EAGAIN in case the 336 userfault was already resolved and waken by a !! 198 userfault was already resolved and waken by a UFFDIO_COPY|ZEROPAGE run 337 by the parallel QEMU migration thread). 199 by the parallel QEMU migration thread). 338 200 339 After the QEMU postcopy thread (running in the 201 After the QEMU postcopy thread (running in the destination node) gets 340 the userfault address it writes the informatio 202 the userfault address it writes the information about the missing page 341 into the socket. The QEMU source node receives 203 into the socket. The QEMU source node receives the information and 342 roughly "seeks" to that page address and conti 204 roughly "seeks" to that page address and continues sending all 343 remaining missing pages from that new page off 205 remaining missing pages from that new page offset. Soon after that 344 (just the time to flush the tcp_wmem queue thr 206 (just the time to flush the tcp_wmem queue through the network) the 345 migration thread in the QEMU running in the de 207 migration thread in the QEMU running in the destination node will 346 receive the page that triggered the userfault 208 receive the page that triggered the userfault and it'll map it as 347 usual with the ``UFFDIO_COPY|ZEROPAGE`` (witho !! 209 usual with the UFFDIO_COPY|ZEROPAGE (without actually knowing if it 348 was spontaneously sent by the source or if it 210 was spontaneously sent by the source or if it was an urgent page 349 requested through a userfault). 211 requested through a userfault). 350 212 351 By the time the userfaults start, the QEMU in 213 By the time the userfaults start, the QEMU in the destination node 352 doesn't need to keep any per-page state bitmap 214 doesn't need to keep any per-page state bitmap relative to the live 353 migration around and a single per-page bitmap 215 migration around and a single per-page bitmap has to be maintained in 354 the QEMU running in the source node to know wh 216 the QEMU running in the source node to know which pages are still 355 missing in the destination node. The bitmap in 217 missing in the destination node. The bitmap in the source node is 356 checked to find which missing pages to send in 218 checked to find which missing pages to send in round robin and we seek 357 over it when receiving incoming userfaults. Af 219 over it when receiving incoming userfaults. After sending each page of 358 course the bitmap is updated accordingly. It's 220 course the bitmap is updated accordingly. It's also useful to avoid 359 sending the same page twice (in case the userf 221 sending the same page twice (in case the userfault is read by the 360 postcopy thread just before ``UFFDIO_COPY|ZERO !! 222 postcopy thread just before UFFDIO_COPY|ZEROPAGE runs in the migration 361 thread). 223 thread). 362 224 363 Non-cooperative userfaultfd 225 Non-cooperative userfaultfd 364 =========================== 226 =========================== 365 227 366 When the ``userfaultfd`` is monitored by an ex !! 228 When the userfaultfd is monitored by an external manager, the manager 367 must be able to track changes in the process v 229 must be able to track changes in the process virtual memory 368 layout. Userfaultfd can notify the manager abo 230 layout. Userfaultfd can notify the manager about such changes using 369 the same read(2) protocol as for the page faul 231 the same read(2) protocol as for the page fault notifications. The 370 manager has to explicitly enable these events 232 manager has to explicitly enable these events by setting appropriate 371 bits in ``uffdio_api.features`` passed to ``UF !! 233 bits in uffdio_api.features passed to UFFDIO_API ioctl: 372 234 373 ``UFFD_FEATURE_EVENT_FORK`` !! 235 UFFD_FEATURE_EVENT_FORK 374 enable ``userfaultfd`` hooks for fork( !! 236 enable userfaultfd hooks for fork(). When this feature is 375 enabled, the ``userfaultfd`` context o !! 237 enabled, the userfaultfd context of the parent process is 376 duplicated into the newly created proc 238 duplicated into the newly created process. The manager 377 receives ``UFFD_EVENT_FORK`` with file !! 239 receives UFFD_EVENT_FORK with file descriptor of the new 378 ``userfaultfd`` context in the ``uffd_ !! 240 userfaultfd context in the uffd_msg.fork. 379 241 380 ``UFFD_FEATURE_EVENT_REMAP`` !! 242 UFFD_FEATURE_EVENT_REMAP 381 enable notifications about mremap() ca 243 enable notifications about mremap() calls. When the 382 non-cooperative process moves a virtua 244 non-cooperative process moves a virtual memory area to a 383 different location, the manager will r 245 different location, the manager will receive 384 ``UFFD_EVENT_REMAP``. The ``uffd_msg.r !! 246 UFFD_EVENT_REMAP. The uffd_msg.remap will contain the old and 385 new addresses of the area and its orig 247 new addresses of the area and its original length. 386 248 387 ``UFFD_FEATURE_EVENT_REMOVE`` !! 249 UFFD_FEATURE_EVENT_REMOVE 388 enable notifications about madvise(MAD 250 enable notifications about madvise(MADV_REMOVE) and 389 madvise(MADV_DONTNEED) calls. The even !! 251 madvise(MADV_DONTNEED) calls. The event UFFD_EVENT_REMOVE will 390 be generated upon these calls to madvi !! 252 be generated upon these calls to madvise. The uffd_msg.remove 391 will contain start and end addresses o 253 will contain start and end addresses of the removed area. 392 254 393 ``UFFD_FEATURE_EVENT_UNMAP`` !! 255 UFFD_FEATURE_EVENT_UNMAP 394 enable notifications about memory unma 256 enable notifications about memory unmapping. The manager will 395 get ``UFFD_EVENT_UNMAP`` with ``uffd_m !! 257 get UFFD_EVENT_UNMAP with uffd_msg.remove containing start and 396 end addresses of the unmapped area. 258 end addresses of the unmapped area. 397 259 398 Although the ``UFFD_FEATURE_EVENT_REMOVE`` and !! 260 Although the UFFD_FEATURE_EVENT_REMOVE and UFFD_FEATURE_EVENT_UNMAP 399 are pretty similar, they quite differ in the a 261 are pretty similar, they quite differ in the action expected from the 400 ``userfaultfd`` manager. In the former case, t !! 262 userfaultfd manager. In the former case, the virtual memory is 401 removed, but the area is not, the area remains 263 removed, but the area is not, the area remains monitored by the 402 ``userfaultfd``, and if a page fault occurs in !! 264 userfaultfd, and if a page fault occurs in that area it will be 403 delivered to the manager. The proper resolutio 265 delivered to the manager. The proper resolution for such page fault is 404 to zeromap the faulting address. However, in t 266 to zeromap the faulting address. However, in the latter case, when an 405 area is unmapped, either explicitly (with munm 267 area is unmapped, either explicitly (with munmap() system call), or 406 implicitly (e.g. during mremap()), the area is 268 implicitly (e.g. during mremap()), the area is removed and in turn the 407 ``userfaultfd`` context for such area disappea !! 269 userfaultfd context for such area disappears too and the manager will 408 not get further userland page faults from the 270 not get further userland page faults from the removed area. Still, the 409 notification is required in order to prevent m 271 notification is required in order to prevent manager from using 410 ``UFFDIO_COPY`` on the unmapped area. !! 272 UFFDIO_COPY on the unmapped area. 411 273 412 Unlike userland page faults which have to be s 274 Unlike userland page faults which have to be synchronous and require 413 explicit or implicit wakeup, all the events ar 275 explicit or implicit wakeup, all the events are delivered 414 asynchronously and the non-cooperative process 276 asynchronously and the non-cooperative process resumes execution as 415 soon as manager executes read(). The ``userfau !! 277 soon as manager executes read(). The userfaultfd manager should 416 carefully synchronize calls to ``UFFDIO_COPY`` !! 278 carefully synchronize calls to UFFDIO_COPY with the events 417 processing. To aid the synchronization, the `` !! 279 processing. To aid the synchronization, the UFFDIO_COPY ioctl will 418 return ``-ENOSPC`` when the monitored process !! 280 return -ENOSPC when the monitored process exits at the time of 419 ``UFFDIO_COPY``, and ``-ENOENT``, when the non !! 281 UFFDIO_COPY, and -ENOENT, when the non-cooperative process has changed 420 its virtual memory layout simultaneously with !! 282 its virtual memory layout simultaneously with outstanding UFFDIO_COPY 421 operation. 283 operation. 422 284 423 The current asynchronous model of the event de 285 The current asynchronous model of the event delivery is optimal for 424 single threaded non-cooperative ``userfaultfd` !! 286 single threaded non-cooperative userfaultfd manager implementations. A 425 synchronous event delivery model can be added 287 synchronous event delivery model can be added later as a new 426 ``userfaultfd`` feature to facilitate multithr !! 288 userfaultfd feature to facilitate multithreading enhancements of the 427 non cooperative manager, for example to allow !! 289 non cooperative manager, for example to allow UFFDIO_COPY ioctls to 428 run in parallel to the event reception. Single 290 run in parallel to the event reception. Single threaded 429 implementations should continue to use the cur 291 implementations should continue to use the current async event 430 delivery model instead. 292 delivery model instead.

Linux® is a registered trademark of Linus Torvalds in the United States and other countries.
TOMOYO® is a registered trademark of NTT DATA CORPORATION.

TOMOYO Linux Cross Reference
Linux/Documentation/admin-guide/mm/userfaultfd.rst

Diff markup

Differences between /Documentation/admin-guide/mm/userfaultfd.rst (Version linux-6.12-rc7) and /Documentation/admin-guide/mm/userfaultfd.rst (Version linux-5.7.19)

TOMOYO Linux Cross Reference Linux/Documentation/admin-guide/mm/userfaultfd.rst

Diff markup

Differences between /Documentation/admin-guide/mm/userfaultfd.rst (Version linux-6.12-rc7) and /Documentation/admin-guide/mm/userfaultfd.rst (Version linux-5.7.19)

TOMOYO Linux Cross Reference
Linux/Documentation/admin-guide/mm/userfaultfd.rst