Date: Sat, 24 Apr 2010 09:08:32 +0100 From: Bruce Cran <bruce@cran.org.uk> To: freebsd-bugs@freebsd.org Cc: Michael Moll <kvedulv@kvedulv.de>, kib@freebsd.org Subject: Re: amd64/135014: [padlock] Using padlock(4) in 8-current triggers "fpudna in kernel mode!" warnings Message-ID: <201004240908.32856.bruce@cran.org.uk> In-Reply-To: <201004221904.58736.bruce@cran.org.uk> References: <20100405141508.GC7513@darkthrone.kvedulv.de> <201004051622.36096.bruce@cran.org.uk> <201004221904.58736.bruce@cran.org.uk>
next in thread | previous in thread | raw e-mail | index | archive | help
On Thursday 22 April 2010 19:04:58 Bruce Cran wrote: > On Monday 05 April 2010 16:22:36 Bruce Cran wrote: > > On Monday 05 April 2010 15:15:08 Michael Moll wrote: > > > the patch from > > > http://people.freebsd.org/~kib/misc/kern_fpu.2.patch > > > fixes this problem for me. > > > > The patch fixes the problem on my i386 mini-iTX system too. > > I don't know if it's related, but I've been having regular crashes on the > same box since applying the patch. Sometimes it runs for 12 hours, other > times only for a few minutes. I had thought the dumps were being corrupted but taking another look I've found the machine started generating core.txt files a couple of days ago which confirmed the crashes happening in fpu_kern_leave. I've built a kernel with the kern_fpu.3.patch and the machine has survived lots of network and disk traffic, which would normally have caused a crash. -- Bruce Cran
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201004240908.32856.bruce>