On Wed, Mar 03, 2021 at 08:59:45PM -0500, Peter Xu wrote: > Write-protect mode is supported starting from Linux 5.7. > > Signed-off-by: Peter Xu <peterx@xxxxxxxxxx> > --- > man2/userfaultfd.2 | 88 ++++++++++++++++++++++++++++++++++++++++++++-- > 1 file changed, 86 insertions(+), 2 deletions(-) > > diff --git a/man2/userfaultfd.2 b/man2/userfaultfd.2 > index 2d14effc6..8e1602d62 100644 > --- a/man2/userfaultfd.2 > +++ b/man2/userfaultfd.2 > @@ -78,6 +78,28 @@ all memory ranges that were registered with the object are unregistered > and unread events are flushed. > .\" > .PP > +Currently, userfaultfd supports two modes of registration: > +.TP > +.BR UFFDIO_REGISTER_MODE_MISSING > +When registered with > +.BR UFFDIO_REGISTER_MODE_MISSING > +mode, the userspace will receive a page fault message when a missing page is > +accessed. The faulted thread will be stopped from execution until the page > +fault is resolved from the userspace by either an > +.BR UFFDIO_COPY > +or an > +.BR UFFDIO_ZEROPAGE > +ioctl. > +.TP > +.BR UFFDIO_REGISTER_MODE_WP > +When registered with > +.BR UFFDIO_REGISTER_MODE_WP > +mode, the userspace will receive a page fault message when a write-protected > +page is written. The faulted thread will be stopped from execution until the > +userspace un-write-protect the page using an > +.BR UFFDIO_WRITEPROTECT > +ioctl. > +.PP I'd add a sentence about combining the modes together. Something like "Both modes can be enabled together for the same memory range" > Since Linux 4.14, userfaultfd page fault message can selectively embed fault > thread ID information into the fault message. One needs to enable this feature > explicitly using the > @@ -143,6 +165,16 @@ single threaded non-cooperative userfaultfd manager implementations. > .\" and limitations remaining in 4.11 > .\" Maybe it's worth adding a dedicated sub-section... > .\" > +.PP > +Starting from Linux 5.7, userfaultfd is able to do synchronous page dirty > +tracking using the new write-protection 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 an userfaultfd message when the protected > +page is written. The user needs to resolve the page fault by unprotecting the > +faulted page and kick the faulted thread to continue. For more information, > +please read the "Userfaultfd write-protect mode" section below. > .SS Userfaultfd operation > After the userfaultfd object is created with > .BR userfaultfd (), > @@ -218,6 +250,54 @@ 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, userfaultfd started to support write-protect mode. The user Maybe s/started to support/supports/ > +needs to first check availability of this feature using > +.BR UFFDIO_API > +ioctl against the feature bit > +.BR UFFD_FEATURE_PAGEFAULT_FLAG_WP . > +.PP > +To register with userfaultfd write-protect mode, the user needs to send the > +.BR UFFDIO_REGISTER > +ioctl with mode > +.BR UFFDIO_REGISTER_MODE_WP > +set. Note that it's legal to monitor the same memory range with multiple > +modes. For example, the user can do > +.BR UFFDIO_REGISTER > +with the mode set to > +.BR UFFDIO_REGISTER_MODE_MISSING\ |\ UFFDIO_REGISTER_MODE_WP. > +When there is only > +.BR UFFDIO_REGISTER_MODE_WP > +registered, the userspace will > +.I not > +receive any message when a missing page is written. Instead, the userspace > +will only receive a write-protect page fault message when an existing but > +write-protected page got written. > +.PP > +After the > +.BR UFFDIO_REGISTER > +ioctl completed with > +.BR UFFDIO_REGISTER_MODE_WP > +mode set, one can write-protect any existing memory within the range using the > +ioctl > +.BR UFFDIO_WRITEPROTECT > +where > +.I uffdio_writeprotect.mode > +should be set to > +.BR UFFDIO_WRITEPROTECT_MODE_WP . > +.PP > +When a write-protect event happens, the userspace will receive a page fault > +message whose > +.I uffd_msg.pagefault.flags > +will be with > +.BR UFFD_PAGEFAULT_FLAG_WP > +flag set. Note: since only writes can trigger such kind of fault, > +write-protect messages will always be with > +.BR UFFD_PAGEFAULT_FLAG_WRITE > +bit set too along with > +.BR UFFD_PAGEFAULT_FLAG_WP . > +.PP > +Currently, write-protect mode only supports private anonymous memory. > .SS Reading from the userfaultfd structure > Each > .BR read (2) > @@ -363,8 +443,12 @@ flag (see > .BR ioctl_userfaultfd (2)) > and this flag is set, this a write fault; > otherwise it is a read fault. > -.\" > -.\" UFFD_PAGEFAULT_FLAG_WP is not yet supported. > +.TP > +.B UFFD_PAGEFAULT_FLAG_WP > +If the address is in a range that was registered with the > +.B UFFDIO_REGISTER_MODE_WP > +flag, when this bit is set it means it's a write-protect fault. Otherwise it's > +a page missing fault. > .RE > .TP > .I pagefault.feat.pid > -- > 2.26.2 > -- Sincerely yours, Mike.
