From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Paul E. McKenney" Subject: Re: [PATCH 4/4] kvm,rcu: use RCU extended quiescent state when running KVM guest Date: Thu, 5 Feb 2015 11:27:04 -0800 Message-ID: <20150205192704.GM5370@linux.vnet.ibm.com> References: <1423154134-17391-1-git-send-email-riel@redhat.com> <1423154134-17391-5-git-send-email-riel@redhat.com> <54D39DF0.3020109@de.ibm.com> <54D39FD5.2040402@redhat.com> <20150205175014.GG5370@linux.vnet.ibm.com> <54D3B1CF.1000301@redhat.com> <20150205185627.GK5370@linux.vnet.ibm.com> <54D3BE4B.9090301@redhat.com> Reply-To: paulmck@linux.vnet.ibm.com Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Christian Borntraeger , kvm@vger.kernel.org, linux-kernel@vger.kernel.org, mtosatti@redhat.com, mingo@kernel.org, ak@linux.intel.com, oleg@redhat.com, masami.hiramatsu.pt@hitachi.com, fweisbec@gmail.com, lcapitulino@redhat.com, pbonzini@redhat.com To: Rik van Riel Return-path: Content-Disposition: inline In-Reply-To: <54D3BE4B.9090301@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: kvm.vger.kernel.org On Thu, Feb 05, 2015 at 02:02:35PM -0500, Rik van Riel wrote: > On 02/05/2015 01:56 PM, Paul E. McKenney wrote: > > > The real danger is doing neither. > > > > On tick_nohz_full_cpu() CPUs, the exit-to-userspace code should invoke > > rcu_user_enter(), which sets some per-CPU state telling RCU to ignore > > that CPU, since it cannot possibly do host RCU read-side critical sections > > while running a guest. > > > > In contrast, a non-tick_nohz_full_cpu() CPU doesn't let RCU > > know that it is executing in a guest or in userspace. So the > > rcu_virt_note_context_switch() does the notification in that case. > > Looking at context_tracking.h, I see the > function context_tracking_cpu_is_enabled(). > > That looks like it should do the right thing > in this case. Right you are -- that same check is used to guard the context_tracking_user_enter() function's call to rcu_user_enter(). Not sure why it open-codes the check rather than invoking context_tracking_cpu_is_enabled(). Hmmm.... One reason is that the context_tracking_cpu_is_enabled() function isn't available in that context, according to my compiler. ;-) Thanx, Paul