Re: EPIPE returned by kevent(2)

Visa Hankala writes: > The EPIPE error relates to the situation where a kevent(2) EVFILT_WRITE > call on a pipe races with the closing of the pipe's other end. > If the close(2) happens before the kevent registration, kevent(2) > returns EPIPE. If the close(2) happens after the kevent(2) call, >

Re: cron: better error checking of random values

Now that the random range changes are committed I would like to revisit this diff. This fixes two issues with the parsing of random values: 1) Garbage after a random value is now detected. This fixes a bug in the random range parsing that handles the optional final number. For example:

Re: installer: amd64 EFI: default to GPT

On Sat, Apr 29, 2023 at 06:47:48PM +, Klemens Nanni wrote: > Installing to a wiped disk on EFI machines suggests MBR not GPT when chosing > (E)dit because MBR vs. GPT in this manual case is picked based on existing > data on the disk, not whether it has EFI. > > Fix that so users get correct

nd6 resolve mutex

Hi, As the nd6 mutex protects the lifetime of struct llinfo_nd6 ln, nd6_mtx must be held longer in nd6_rtrequest() case RTM_RESOLVE. ok? bluhm Index: netinet6/nd6.c === RCS file: /data/mirror/openbsd/cvs/src/sys/netinet6/nd6.c,v

Re: pfioctl: drop net lock from DIOCOSFP{FLUSH,ADD,GET}

On Sat, May 06, 2023 at 08:56:06PM +, Klemens Nanni wrote: > On Sat, May 06, 2023 at 09:33:05PM +0200, Alexander Bluhm wrote: > > On Sat, May 06, 2023 at 11:11:25AM +, Klemens Nanni wrote: > > > pf_osfp.c contains all the locking for these three ioctls, this removes > > > the net lock from

Re: pfioctl: drop net lock from DIOCOSFP{FLUSH,ADD,GET}

On Sat, May 06, 2023 at 09:33:05PM +0200, Alexander Bluhm wrote: > On Sat, May 06, 2023 at 11:11:25AM +, Klemens Nanni wrote: > > pf_osfp.c contains all the locking for these three ioctls, this removes > > the net lock from it. > > > > All data is protected by the pf lock, new asserts verify

Re: pfioctl: drop net lock from DIOCOSFP{FLUSH,ADD,GET}

On Sat, May 06, 2023 at 11:11:25AM +, Klemens Nanni wrote: > pf_osfp.c contains all the locking for these three ioctls, this removes > the net lock from it. > > All data is protected by the pf lock, new asserts verify that. > > Beside the pf ioctl handler, pf_match_rule()'s call to

Re: EPIPE returned by kevent(2)

On Thu, May 04, 2023 at 08:07:44PM -0700, Greg Steuck wrote: > I'm debugging a non-trivial multithreaded unit test in the current > version of lang/ghc. It runs into some kind of unexpected condition not > handled well by GHC. I suspect we do something non-standard to cause > this behavior. These

Re: openbgpd bug - aspa_add_set: bad order of adds

On Sat, May 06, 2023 at 02:58:25PM +0200, Wouter Prins wrote: > FYI, > > Just upgraded towards openbsd 7.3 with the bgpd errata fix. Within an hour > bgpd crashed with the following message: > > May 6 12:14:33 nl-ams-gs-br01 bgpd[67338]: fatal in RDE: aspa_add_set: bad > order of adds > >

openbgpd bug - aspa_add_set: bad order of adds

FYI, Just upgraded towards openbsd 7.3 with the bgpd errata fix. Within an hour bgpd crashed with the following message: May 6 12:14:33 nl-ams-gs-br01 bgpd[67338]: fatal in RDE: aspa_add_set: bad order of adds Temporary fix is to add the -A into the crontab entry of rpki-client, this does not

pfioctl: drop net lock from DIOCOSFP{FLUSH,ADD,GET}

pf_osfp.c contains all the locking for these three ioctls, this removes the net lock from it. All data is protected by the pf lock, new asserts verify that. Beside the pf ioctl handler, pf_match_rule()'s call to pf_osfp_match() is the only hook into it. tcpbump still compiles pf_osfp.c without

Regen cert.pem

WARNING: '/C=JP/O=SECOM Trust.net/OU=Security Communication RootCA1' expires on Sep 30 04:20:49 2023 GMT WARNING: '/C=HK/O=Hongkong Post/CN=Hongkong Post Root CA 1' expires on May 15 04:52:29 2023 GMT no harm in keeping these a while longer ERROR: '/C=PL/O=Unizeto Technologies S.A./OU=Certum