diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-15 19:40:15 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-04-15 19:40:15 +0000 |
commit | 399644e47874bff147afb19c89228901ac39340e (patch) | |
tree | 1c4c0b733f4c16b5783b41bebb19194a9ef62ad1 /man2/userfaultfd.2 | |
parent | Initial commit. (diff) | |
download | manpages-399644e47874bff147afb19c89228901ac39340e.tar.xz manpages-399644e47874bff147afb19c89228901ac39340e.zip |
Adding upstream version 6.05.01.upstream/6.05.01
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'man2/userfaultfd.2')
-rw-r--r-- | man2/userfaultfd.2 | 943 |
1 files changed, 943 insertions, 0 deletions
diff --git a/man2/userfaultfd.2 b/man2/userfaultfd.2 new file mode 100644 index 0000000..82903c6 --- /dev/null +++ b/man2/userfaultfd.2 @@ -0,0 +1,943 @@ +.\" Copyright (c) 2016, IBM Corporation. +.\" Written by Mike Rapoport <rppt@linux.vnet.ibm.com> +.\" and Copyright (C) 2017 Michael Kerrisk <mtk.manpages@gmail.com> +.\" +.\" SPDX-License-Identifier: Linux-man-pages-copyleft +.\" +.TH userfaultfd 2 2023-05-03 "Linux man-pages 6.05.01" +.SH NAME +userfaultfd \- create a file descriptor for handling page faults in user space +.SH LIBRARY +Standard C library +.RI ( libc ", " \-lc ) +.SH SYNOPSIS +.nf +.BR "#include <fcntl.h>" " /* Definition of " O_* " constants */" +.BR "#include <sys/syscall.h>" " /* Definition of " SYS_* " constants */" +.BR "#include <linux/userfaultfd.h>" " /* Definition of " UFFD_* " constants */" +.B #include <unistd.h> +.PP +.BI "int syscall(SYS_userfaultfd, int " flags ); +.fi +.PP +.IR Note : +glibc provides no wrapper for +.BR userfaultfd (), +necessitating the use of +.BR syscall (2). +.SH DESCRIPTION +.BR userfaultfd () +creates a new userfaultfd object that can be used for delegation of page-fault +handling to a user-space application, +and returns a file descriptor that refers to the new object. +The new userfaultfd object is configured using +.BR ioctl (2). +.PP +Once the userfaultfd object is configured, the application can use +.BR read (2) +to receive userfaultfd notifications. +The reads from userfaultfd may be blocking or non-blocking, +depending on the value of +.I flags +used for the creation of the userfaultfd or subsequent calls to +.BR fcntl (2). +.PP +The following values may be bitwise ORed in +.I flags +to change the behavior of +.BR userfaultfd (): +.TP +.B O_CLOEXEC +Enable the close-on-exec flag for the new userfaultfd file descriptor. +See the description of the +.B O_CLOEXEC +flag in +.BR open (2). +.TP +.B O_NONBLOCK +Enables non-blocking operation for the userfaultfd object. +See the description of the +.B O_NONBLOCK +flag in +.BR open (2). +.TP +.B UFFD_USER_MODE_ONLY +This is an userfaultfd-specific flag that was introduced in Linux 5.11. +When set, the userfaultfd object will only be able to handle +page faults originated from the user space on the registered regions. +When a kernel-originated fault was triggered +on the registered range with this userfaultfd, a +.B SIGBUS +signal will be delivered. +.PP +When the last file descriptor referring to a userfaultfd object is closed, +all memory ranges that were registered with the object are unregistered +and unread events are flushed. +.\" +.PP +Userfaultfd supports three modes of registration: +.TP +.BR UFFDIO_REGISTER_MODE_MISSING " (since Linux 4.10)" +When registered with +.B UFFDIO_REGISTER_MODE_MISSING +mode, user-space will receive a page-fault notification +when a missing page is accessed. +The faulted thread will be stopped from execution until the page fault is +resolved from user-space by either an +.B UFFDIO_COPY +or an +.B UFFDIO_ZEROPAGE +ioctl. +.TP +.BR UFFDIO_REGISTER_MODE_MINOR " (since Linux 5.13)" +When registered with +.B UFFDIO_REGISTER_MODE_MINOR +mode, user-space will receive a page-fault notification +when a minor page fault occurs. +That is, +when a backing page is in the page cache, +but page table entries don't yet exist. +The faulted thread will be stopped from execution +until the page fault is resolved from user-space by an +.B UFFDIO_CONTINUE +ioctl. +.TP +.BR UFFDIO_REGISTER_MODE_WP " (since Linux 5.7)" +When registered with +.B UFFDIO_REGISTER_MODE_WP +mode, user-space will receive a page-fault notification +when a write-protected page is written. +The faulted thread will be stopped from execution +until user-space write-unprotects the page using an +.B UFFDIO_WRITEPROTECT +ioctl. +.PP +Multiple modes can be enabled at the same time for the same memory range. +.PP +Since Linux 4.14, a userfaultfd page-fault notification can selectively embed +faulting thread ID information into the notification. +One needs to enable this feature explicitly using the +.B UFFD_FEATURE_THREAD_ID +feature bit when initializing the userfaultfd context. +By default, thread ID reporting is disabled. +.SS Usage +The userfaultfd mechanism is designed to allow a thread in a multithreaded +program to perform user-space paging for the other threads in the process. +When a page fault occurs for one of the regions registered +to the userfaultfd object, +the faulting thread is put to sleep and +an event is generated that can be read via the userfaultfd file descriptor. +The fault-handling thread reads events from this file descriptor and services +them using the operations described in +.BR ioctl_userfaultfd (2). +When servicing the page fault events, +the fault-handling thread can trigger a wake-up for the sleeping thread. +.PP +It is possible for the faulting threads and the fault-handling threads +to run in the context of different processes. +In this case, these threads may belong to different programs, +and the program that executes the faulting threads +will not necessarily cooperate with the program that handles the page faults. +In such non-cooperative mode, +the process that monitors userfaultfd and handles page faults +needs to be aware of the changes in the virtual memory layout +of the faulting process to avoid memory corruption. +.PP +Since Linux 4.11, +userfaultfd can also notify the fault-handling threads about changes +in the virtual memory layout of the faulting process. +In addition, if the faulting process invokes +.BR fork (2), +the userfaultfd objects associated with the parent may be duplicated +into the child process and the userfaultfd monitor will be notified +(via the +.B UFFD_EVENT_FORK +described below) +about the file descriptor associated with the userfault objects +created for the child process, +which allows the userfaultfd monitor to perform user-space paging +for the child process. +Unlike page faults which have to be synchronous and require an +explicit or implicit wakeup, +all other events are delivered asynchronously and +the non-cooperative process resumes execution as +soon as the userfaultfd manager executes +.BR read (2). +The userfaultfd manager should carefully synchronize calls to +.B UFFDIO_COPY +with the processing of events. +.PP +The current asynchronous model of the event delivery is optimal for +single threaded non-cooperative userfaultfd manager implementations. +.\" Regarding the preceding sentence, Mike Rapoport says: +.\" The major point here is that current events delivery model could be +.\" problematic for multi-threaded monitor. I even suspect that it would be +.\" impossible to ensure synchronization between page faults and non-page +.\" fault events in multi-threaded monitor. +.\" .PP +.\" FIXME elaborate about non-cooperating mode, describe its limitations +.\" for kernels before Linux 4.11, features added in Linux 4.11 +.\" and limitations remaining in Linux 4.11 +.\" Maybe it's worth adding a dedicated sub-section... +.\" +.PP +Since Linux 5.7, userfaultfd is able to do +synchronous page dirty tracking using the new write-protect register mode. +One should check against the feature bit +.B UFFD_FEATURE_PAGEFAULT_FLAG_WP +before using this feature. +Similar to the original userfaultfd missing mode, the write-protect mode will +generate a userfaultfd notification when the protected page is written. +The user needs to resolve the page fault by unprotecting the faulted page and +kicking the faulted thread to continue. +For more information, +please refer to the "Userfaultfd write-protect mode" section. +.\" +.SS Userfaultfd operation +After the userfaultfd object is created with +.BR userfaultfd (), +the application must enable it using the +.B UFFDIO_API +.BR ioctl (2) +operation. +This operation allows a handshake between the kernel and user space +to determine the API version and supported features. +This operation must be performed before any of the other +.BR ioctl (2) +operations described below (or those operations fail with the +.B EINVAL +error). +.PP +After a successful +.B UFFDIO_API +operation, +the application then registers memory address ranges using the +.B UFFDIO_REGISTER +.BR ioctl (2) +operation. +After successful completion of a +.B UFFDIO_REGISTER +operation, +a page fault occurring in the requested memory range, and satisfying +the mode defined at the registration time, will be forwarded by the kernel to +the user-space application. +The application can then use the +.B UFFDIO_COPY , +.B UFFDIO_ZEROPAGE , +or +.B UFFDIO_CONTINUE +.BR ioctl (2) +operations to resolve the page fault. +.PP +Since Linux 4.14, if the application sets the +.B UFFD_FEATURE_SIGBUS +feature bit using the +.B UFFDIO_API +.BR ioctl (2), +no page-fault notification will be forwarded to user space. +Instead a +.B SIGBUS +signal is delivered to the faulting process. +With this feature, +userfaultfd can be used for robustness purposes to simply catch +any access to areas within the registered address range that do not +have pages allocated, without having to listen to userfaultfd events. +No userfaultfd monitor will be required for dealing with such memory +accesses. +For example, this feature can be useful for applications that +want to prevent the kernel from automatically allocating pages and filling +holes in sparse files when the hole is accessed through a memory mapping. +.PP +The +.B UFFD_FEATURE_SIGBUS +feature is implicitly inherited through +.BR fork (2) +if used in combination with +.BR UFFD_FEATURE_FORK . +.PP +Details of the various +.BR ioctl (2) +operations can be found in +.BR ioctl_userfaultfd (2). +.PP +Since Linux 4.11, events other than page-fault may enabled during +.B UFFDIO_API +operation. +.PP +Up to Linux 4.11, +userfaultfd can be used only with anonymous private memory mappings. +Since Linux 4.11, +userfaultfd can be also used with hugetlbfs and shared memory mappings. +.\" +.SS Userfaultfd write-protect mode (since Linux 5.7) +Since Linux 5.7, userfaultfd supports write-protect mode for anonymous memory. +The user needs to first check availability of this feature using +.B UFFDIO_API +ioctl against the feature bit +.B UFFD_FEATURE_PAGEFAULT_FLAG_WP +before using this feature. +.PP +Since Linux 5.19, +the write-protection mode was also supported on +shmem and hugetlbfs memory types. +It can be detected with the feature bit +.BR UFFD_FEATURE_WP_HUGETLBFS_SHMEM . +.PP +To register with userfaultfd write-protect mode, the user needs to initiate the +.B UFFDIO_REGISTER +ioctl with mode +.B UFFDIO_REGISTER_MODE_WP +set. +Note that it is legal to monitor the same memory range with multiple modes. +For example, the user can do +.B UFFDIO_REGISTER +with the mode set to +.BR "UFFDIO_REGISTER_MODE_MISSING | UFFDIO_REGISTER_MODE_WP" . +When there is only +.B UFFDIO_REGISTER_MODE_WP +registered, user-space will +.I not +receive any notification when a missing page is written. +Instead, user-space will receive a write-protect page-fault notification +only when an existing but write-protected page got written. +.PP +After the +.B UFFDIO_REGISTER +ioctl completed with +.B UFFDIO_REGISTER_MODE_WP +mode set, +the user can write-protect any existing memory within the range using the ioctl +.B UFFDIO_WRITEPROTECT +where +.I uffdio_writeprotect.mode +should be set to +.BR UFFDIO_WRITEPROTECT_MODE_WP . +.PP +When a write-protect event happens, +user-space will receive a page-fault notification whose +.I uffd_msg.pagefault.flags +will be with +.B UFFD_PAGEFAULT_FLAG_WP +flag set. +Note: since only writes can trigger this kind of fault, +write-protect notifications will always have the +.B UFFD_PAGEFAULT_FLAG_WRITE +bit set along with the +.B UFFD_PAGEFAULT_FLAG_WP +bit. +.PP +To resolve a write-protection page fault, the user should initiate another +.B UFFDIO_WRITEPROTECT +ioctl, whose +.I uffd_msg.pagefault.flags +should have the flag +.B UFFDIO_WRITEPROTECT_MODE_WP +cleared upon the faulted page or range. +.\" +.SS Userfaultfd minor fault mode (since Linux 5.13) +Since Linux 5.13, +userfaultfd supports minor fault mode. +In this mode, +fault messages are produced not for major faults +(where the page was missing), +but rather for minor faults, +where a page exists in the page cache, +but the page table entries are not yet present. +The user needs to first check availability of this feature using the +.B UFFDIO_API +ioctl with the appropriate feature bits set before using this feature: +.B UFFD_FEATURE_MINOR_HUGETLBFS +since Linux 5.13, +or +.B UFFD_FEATURE_MINOR_SHMEM +since Linux 5.14. +.PP +To register with userfaultfd minor fault mode, +the user needs to initiate the +.B UFFDIO_REGISTER +ioctl with mode +.B UFFD_REGISTER_MODE_MINOR +set. +.PP +When a minor fault occurs, +user-space will receive a page-fault notification +whose +.I uffd_msg.pagefault.flags +will have the +.B UFFD_PAGEFAULT_FLAG_MINOR +flag set. +.PP +To resolve a minor page fault, +the handler should decide whether or not +the existing page contents need to be modified first. +If so, +this should be done in-place via a second, +non-userfaultfd-registered mapping +to the same backing page +(e.g., by mapping the shmem or hugetlbfs file twice). +Once the page is considered "up to date", +the fault can be resolved by initiating an +.B UFFDIO_CONTINUE +ioctl, +which installs the page table entries and +(by default) +wakes up the faulting thread(s). +.PP +Minor fault mode supports only hugetlbfs-backed (since Linux 5.13) +and shmem-backed (since Linux 5.14) memory. +.\" +.SS Reading from the userfaultfd structure +Each +.BR read (2) +from the userfaultfd file descriptor returns one or more +.I uffd_msg +structures, each of which describes a page-fault event +or an event required for the non-cooperative userfaultfd usage: +.PP +.in +4n +.EX +struct uffd_msg { + __u8 event; /* Type of event */ + ... + union { + struct { + __u64 flags; /* Flags describing fault */ + __u64 address; /* Faulting address */ + union { + __u32 ptid; /* Thread ID of the fault */ + } feat; + } pagefault; +\& + struct { /* Since Linux 4.11 */ + __u32 ufd; /* Userfault file descriptor + of the child process */ + } fork; +\& + struct { /* Since Linux 4.11 */ + __u64 from; /* Old address of remapped area */ + __u64 to; /* New address of remapped area */ + __u64 len; /* Original mapping length */ + } remap; +\& + struct { /* Since Linux 4.11 */ + __u64 start; /* Start address of removed area */ + __u64 end; /* End address of removed area */ + } remove; + ... + } arg; +\& + /* Padding fields omitted */ +} __packed; +.EE +.in +.PP +If multiple events are available and the supplied buffer is large enough, +.BR read (2) +returns as many events as will fit in the supplied buffer. +If the buffer supplied to +.BR read (2) +is smaller than the size of the +.I uffd_msg +structure, the +.BR read (2) +fails with the error +.BR EINVAL . +.PP +The fields set in the +.I uffd_msg +structure are as follows: +.TP +.I event +The type of event. +Depending of the event type, +different fields of the +.I arg +union represent details required for the event processing. +The non-page-fault events are generated only when appropriate feature +is enabled during API handshake with +.B UFFDIO_API +.BR ioctl (2). +.IP +The following values can appear in the +.I event +field: +.RS +.TP +.BR UFFD_EVENT_PAGEFAULT " (since Linux 4.3)" +A page-fault event. +The page-fault details are available in the +.I pagefault +field. +.TP +.BR UFFD_EVENT_FORK " (since Linux 4.11)" +Generated when the faulting process invokes +.BR fork (2) +(or +.BR clone (2) +without the +.B CLONE_VM +flag). +The event details are available in the +.I fork +field. +.\" FIXME describe duplication of userfault file descriptor during fork +.TP +.BR UFFD_EVENT_REMAP " (since Linux 4.11)" +Generated when the faulting process invokes +.BR mremap (2). +The event details are available in the +.I remap +field. +.TP +.BR UFFD_EVENT_REMOVE " (since Linux 4.11)" +Generated when the faulting process invokes +.BR madvise (2) +with +.B MADV_DONTNEED +or +.B MADV_REMOVE +advice. +The event details are available in the +.I remove +field. +.TP +.BR UFFD_EVENT_UNMAP " (since Linux 4.11)" +Generated when the faulting process unmaps a memory range, +either explicitly using +.BR munmap (2) +or implicitly during +.BR mmap (2) +or +.BR mremap (2). +The event details are available in the +.I remove +field. +.RE +.TP +.I pagefault.address +The address that triggered the page fault. +.TP +.I pagefault.flags +A bit mask of flags that describe the event. +For +.BR UFFD_EVENT_PAGEFAULT , +the following flag may appear: +.RS +.TP +.B UFFD_PAGEFAULT_FLAG_WP +If this flag is set, then the fault was a write-protect fault. +.TP +.B UFFD_PAGEFAULT_FLAG_MINOR +If this flag is set, then the fault was a minor fault. +.TP +.B UFFD_PAGEFAULT_FLAG_WRITE +If this flag is set, then the fault was a write fault. +.PP +If neither +.B UFFD_PAGEFAULT_FLAG_WP +nor +.B UFFD_PAGEFAULT_FLAG_MINOR +are set, then the fault was a missing fault. +.RE +.TP +.I pagefault.feat.pid +The thread ID that triggered the page fault. +.TP +.I fork.ufd +The file descriptor associated with the userfault object +created for the child created by +.BR fork (2). +.TP +.I remap.from +The original address of the memory range that was remapped using +.BR mremap (2). +.TP +.I remap.to +The new address of the memory range that was remapped using +.BR mremap (2). +.TP +.I remap.len +The original length of the memory range that was remapped using +.BR mremap (2). +.TP +.I remove.start +The start address of the memory range that was freed using +.BR madvise (2) +or unmapped +.TP +.I remove.end +The end address of the memory range that was freed using +.BR madvise (2) +or unmapped +.PP +A +.BR read (2) +on a userfaultfd file descriptor can fail with the following errors: +.TP +.B EINVAL +The userfaultfd object has not yet been enabled using the +.B UFFDIO_API +.BR ioctl (2) +operation +.PP +If the +.B O_NONBLOCK +flag is enabled in the associated open file description, +the userfaultfd file descriptor can be monitored with +.BR poll (2), +.BR select (2), +and +.BR epoll (7). +When events are available, the file descriptor indicates as readable. +If the +.B O_NONBLOCK +flag is not enabled, then +.BR poll (2) +(always) indicates the file as having a +.B POLLERR +condition, and +.BR select (2) +indicates the file descriptor as both readable and writable. +.\" FIXME What is the reason for this seemingly odd behavior with respect +.\" to the O_NONBLOCK flag? (see userfaultfd_poll() in fs/userfaultfd.c). +.\" Something needs to be said about this. +.SH RETURN VALUE +On success, +.BR userfaultfd () +returns a new file descriptor that refers to the userfaultfd object. +On error, \-1 is returned, and +.I errno +is set to indicate the error. +.SH ERRORS +.TP +.B EINVAL +An unsupported value was specified in +.IR flags . +.TP +.B EMFILE +The per-process limit on the number of open file descriptors has been +reached +.TP +.B ENFILE +The system-wide limit on the total number of open files has been +reached. +.TP +.B ENOMEM +Insufficient kernel memory was available. +.TP +.BR EPERM " (since Linux 5.2)" +.\" cefdca0a86be517bc390fc4541e3674b8e7803b0 +The caller is not privileged (does not have the +.B CAP_SYS_PTRACE +capability in the initial user namespace), and +.I /proc/sys/vm/unprivileged_userfaultfd +has the value 0. +.SH STANDARDS +Linux. +.SH HISTORY +Linux 4.3. +.PP +Support for hugetlbfs and shared memory areas and +non-page-fault events was added in Linux 4.11 +.SH NOTES +The userfaultfd mechanism can be used as an alternative to +traditional user-space paging techniques based on the use of the +.B SIGSEGV +signal and +.BR mmap (2). +It can also be used to implement lazy restore +for checkpoint/restore mechanisms, +as well as post-copy migration to allow (nearly) uninterrupted execution +when transferring virtual machines and Linux containers +from one host to another. +.SH BUGS +If the +.B UFFD_FEATURE_EVENT_FORK +is enabled and a system call from the +.BR fork (2) +family is interrupted by a signal or failed, a stale userfaultfd descriptor +might be created. +In this case, a spurious +.B UFFD_EVENT_FORK +will be delivered to the userfaultfd monitor. +.SH EXAMPLES +The program below demonstrates the use of the userfaultfd mechanism. +The program creates two threads, one of which acts as the +page-fault handler for the process, for the pages in a demand-page zero +region created using +.BR mmap (2). +.PP +The program takes one command-line argument, +which is the number of pages that will be created in a mapping +whose page faults will be handled via userfaultfd. +After creating a userfaultfd object, +the program then creates an anonymous private mapping of the specified size +and registers the address range of that mapping using the +.B UFFDIO_REGISTER +.BR ioctl (2) +operation. +The program then creates a second thread that will perform the +task of handling page faults. +.PP +The main thread then walks through the pages of the mapping fetching +bytes from successive pages. +Because the pages have not yet been accessed, +the first access of a byte in each page will trigger a page-fault event +on the userfaultfd file descriptor. +.PP +Each of the page-fault events is handled by the second thread, +which sits in a loop processing input from the userfaultfd file descriptor. +In each loop iteration, the second thread first calls +.BR poll (2) +to check the state of the file descriptor, +and then reads an event from the file descriptor. +All such events should be +.B UFFD_EVENT_PAGEFAULT +events, +which the thread handles by copying a page of data into +the faulting region using the +.B UFFDIO_COPY +.BR ioctl (2) +operation. +.PP +The following is an example of what we see when running the program: +.PP +.in +4n +.EX +$ \fB./userfaultfd_demo 3\fP +Address returned by mmap() = 0x7fd30106c000 +\& +fault_handler_thread(): + poll() returns: nready = 1; POLLIN = 1; POLLERR = 0 + UFFD_EVENT_PAGEFAULT event: flags = 0; address = 7fd30106c00f + (uffdio_copy.copy returned 4096) +Read address 0x7fd30106c00f in main(): A +Read address 0x7fd30106c40f in main(): A +Read address 0x7fd30106c80f in main(): A +Read address 0x7fd30106cc0f in main(): A +\& +fault_handler_thread(): + poll() returns: nready = 1; POLLIN = 1; POLLERR = 0 + UFFD_EVENT_PAGEFAULT event: flags = 0; address = 7fd30106d00f + (uffdio_copy.copy returned 4096) +Read address 0x7fd30106d00f in main(): B +Read address 0x7fd30106d40f in main(): B +Read address 0x7fd30106d80f in main(): B +Read address 0x7fd30106dc0f in main(): B +\& +fault_handler_thread(): + poll() returns: nready = 1; POLLIN = 1; POLLERR = 0 + UFFD_EVENT_PAGEFAULT event: flags = 0; address = 7fd30106e00f + (uffdio_copy.copy returned 4096) +Read address 0x7fd30106e00f in main(): C +Read address 0x7fd30106e40f in main(): C +Read address 0x7fd30106e80f in main(): C +Read address 0x7fd30106ec0f in main(): C +.EE +.in +.SS Program source +\& +.\" SRC BEGIN (userfaultfd.c) +.EX +/* userfaultfd_demo.c +\& + Licensed under the GNU General Public License version 2 or later. +*/ +#define _GNU_SOURCE +#include <err.h> +#include <errno.h> +#include <fcntl.h> +#include <inttypes.h> +#include <linux/userfaultfd.h> +#include <poll.h> +#include <pthread.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> +#include <unistd.h> +\& +static int page_size; +\& +static void * +fault_handler_thread(void *arg) +{ + int nready; + long uffd; /* userfaultfd file descriptor */ + ssize_t nread; + struct pollfd pollfd; + struct uffdio_copy uffdio_copy; +\& + static int fault_cnt = 0; /* Number of faults so far handled */ + static char *page = NULL; + static struct uffd_msg msg; /* Data read from userfaultfd */ +\& + uffd = (long) arg; +\& + /* Create a page that will be copied into the faulting region. */ +\& + if (page == NULL) { + page = mmap(NULL, page_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, \-1, 0); + if (page == MAP_FAILED) + err(EXIT_FAILURE, "mmap"); + } +\& + /* Loop, handling incoming events on the userfaultfd + file descriptor. */ +\& + for (;;) { +\& + /* See what poll() tells us about the userfaultfd. */ +\& + pollfd.fd = uffd; + pollfd.events = POLLIN; + nready = poll(&pollfd, 1, \-1); + if (nready == \-1) + err(EXIT_FAILURE, "poll"); +\& + printf("\enfault_handler_thread():\en"); + printf(" poll() returns: nready = %d; " + "POLLIN = %d; POLLERR = %d\en", nready, + (pollfd.revents & POLLIN) != 0, + (pollfd.revents & POLLERR) != 0); +\& + /* Read an event from the userfaultfd. */ +\& + nread = read(uffd, &msg, sizeof(msg)); + if (nread == 0) { + printf("EOF on userfaultfd!\en"); + exit(EXIT_FAILURE); + } +\& + if (nread == \-1) + err(EXIT_FAILURE, "read"); +\& + /* We expect only one kind of event; verify that assumption. */ +\& + if (msg.event != UFFD_EVENT_PAGEFAULT) { + fprintf(stderr, "Unexpected event on userfaultfd\en"); + exit(EXIT_FAILURE); + } +\& + /* Display info about the page\-fault event. */ +\& + printf(" UFFD_EVENT_PAGEFAULT event: "); + printf("flags = %"PRIx64"; ", msg.arg.pagefault.flags); + printf("address = %"PRIx64"\en", msg.arg.pagefault.address); +\& + /* Copy the page pointed to by \[aq]page\[aq] into the faulting + region. Vary the contents that are copied in, so that it + is more obvious that each fault is handled separately. */ +\& + memset(page, \[aq]A\[aq] + fault_cnt % 20, page_size); + fault_cnt++; +\& + uffdio_copy.src = (unsigned long) page; +\& + /* We need to handle page faults in units of pages(!). + So, round faulting address down to page boundary. */ +\& + uffdio_copy.dst = (unsigned long) msg.arg.pagefault.address & + \[ti](page_size \- 1); + uffdio_copy.len = page_size; + uffdio_copy.mode = 0; + uffdio_copy.copy = 0; + if (ioctl(uffd, UFFDIO_COPY, &uffdio_copy) == \-1) + err(EXIT_FAILURE, "ioctl\-UFFDIO_COPY"); +\& + printf(" (uffdio_copy.copy returned %"PRId64")\en", + uffdio_copy.copy); + } +} +\& +int +main(int argc, char *argv[]) +{ + int s; + char c; + char *addr; /* Start of region handled by userfaultfd */ + long uffd; /* userfaultfd file descriptor */ + size_t len, l; /* Length of region handled by userfaultfd */ + pthread_t thr; /* ID of thread that handles page faults */ + struct uffdio_api uffdio_api; + struct uffdio_register uffdio_register; +\& + if (argc != 2) { + fprintf(stderr, "Usage: %s num\-pages\en", argv[0]); + exit(EXIT_FAILURE); + } +\& + page_size = sysconf(_SC_PAGE_SIZE); + len = strtoull(argv[1], NULL, 0) * page_size; +\& + /* Create and enable userfaultfd object. */ +\& + uffd = syscall(SYS_userfaultfd, O_CLOEXEC | O_NONBLOCK); + if (uffd == \-1) + err(EXIT_FAILURE, "userfaultfd"); +\& + uffdio_api.api = UFFD_API; + uffdio_api.features = 0; + if (ioctl(uffd, UFFDIO_API, &uffdio_api) == \-1) + err(EXIT_FAILURE, "ioctl\-UFFDIO_API"); +\& + /* Create a private anonymous mapping. The memory will be + demand\-zero paged\-\-that is, not yet allocated. When we + actually touch the memory, it will be allocated via + the userfaultfd. */ +\& + addr = mmap(NULL, len, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, \-1, 0); + if (addr == MAP_FAILED) + err(EXIT_FAILURE, "mmap"); +\& + printf("Address returned by mmap() = %p\en", addr); +\& + /* Register the memory range of the mapping we just created for + handling by the userfaultfd object. In mode, we request to track + missing pages (i.e., pages that have not yet been faulted in). */ +\& + uffdio_register.range.start = (unsigned long) addr; + uffdio_register.range.len = len; + uffdio_register.mode = UFFDIO_REGISTER_MODE_MISSING; + if (ioctl(uffd, UFFDIO_REGISTER, &uffdio_register) == \-1) + err(EXIT_FAILURE, "ioctl\-UFFDIO_REGISTER"); +\& + /* Create a thread that will process the userfaultfd events. */ +\& + s = pthread_create(&thr, NULL, fault_handler_thread, (void *) uffd); + if (s != 0) { + errc(EXIT_FAILURE, s, "pthread_create"); + } +\& + /* Main thread now touches memory in the mapping, touching + locations 1024 bytes apart. This will trigger userfaultfd + events for all pages in the region. */ +\& + l = 0xf; /* Ensure that faulting address is not on a page + boundary, in order to test that we correctly + handle that case in fault_handling_thread(). */ + while (l < len) { + c = addr[l]; + printf("Read address %p in %s(): ", addr + l, __func__); + printf("%c\en", c); + l += 1024; + usleep(100000); /* Slow things down a little */ + } +\& + exit(EXIT_SUCCESS); +} +.EE +.\" SRC END +.SH SEE ALSO +.BR fcntl (2), +.BR ioctl (2), +.BR ioctl_userfaultfd (2), +.BR madvise (2), +.BR mmap (2) +.PP +.I Documentation/admin\-guide/mm/userfaultfd.rst +in the Linux kernel source tree |