Re: svn commit: r245850 - in head/sys/sparc64: include sparc64

2013-01-28 Thread Andriy Gapon
on 28/01/2013 16:54 John Baldwin said the following: > On Saturday, January 26, 2013 5:11:24 am Andriy Gapon wrote: >> on 24/01/2013 00:52 Marius Strobl said the following: >>> This is due to >>> the fact that on sparc64, spinlock_enter() only raises the PIL but doesn't >>> disable interrupts c

Re: svn commit: r245850 - in head/sys/sparc64: include sparc64

2013-01-28 Thread John Baldwin
On Saturday, January 26, 2013 5:11:24 am Andriy Gapon wrote: > on 24/01/2013 00:52 Marius Strobl said the following: > > This is due to > > the fact that on sparc64, spinlock_enter() only raises the PIL but doesn't > > disable interrupts completely. > > John, > > I wonder if you are consideri

Re: svn commit: r245850 - in head/sys/sparc64: include sparc64

2013-01-26 Thread Andriy Gapon
on 24/01/2013 00:52 Marius Strobl said the following: > This is due to > the fact that on sparc64, spinlock_enter() only raises the PIL but doesn't > disable interrupts completely. John, I wonder if you are considering pushing your amd64 TPR patch some day... -- Andriy Gapon ___

svn commit: r245850 - in head/sys/sparc64: include sparc64

2013-01-23 Thread Marius Strobl
Author: marius Date: Wed Jan 23 22:52:20 2013 New Revision: 245850 URL: http://svnweb.freebsd.org/changeset/base/245850 Log: Revert the part of r239864 which removed obtaining the SMP mutex around reading registers from other CPUs. As it turns out, the hardware doesn't really like concurrent