From mboxrd@z Thu Jan 1 00:00:00 1970 From: Avi Kivity Subject: Re: [RFC] sched: make callers check lock contention for cond_resched_lock() Date: Thu, 03 May 2012 17:38:23 +0300 Message-ID: <4FA2985F.6080802@redhat.com> References: <20120503171244.2debdd80931ccf35f387c5fe@gmail.com> <1336034127.13683.197.camel@twins> <20120503212244.6abbfa8bc3f46a7f7a932bb7@gmail.com> <1336048150.22523.17.camel@twins> <4FA27E5E.5000002@redhat.com> <20120503231107.e8c5a5dde90e109e570ba32e@gmail.com> <4FA295BE.7010706@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Peter Zijlstra , mingo@elte.hu, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org, kvm@vger.kernel.org, mtosatti@redhat.com, yoshikawa.takuya@oss.ntt.co.jp To: Takuya Yoshikawa Return-path: In-Reply-To: <4FA295BE.7010706@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-fsdevel.vger.kernel.org On 05/03/2012 05:27 PM, Avi Kivity wrote: > On 05/03/2012 05:11 PM, Takuya Yoshikawa wrote: > > On Thu, 03 May 2012 15:47:26 +0300 > > Avi Kivity wrote: > > > > > On 05/03/2012 03:29 PM, Peter Zijlstra wrote: > > > > On Thu, 2012-05-03 at 21:22 +0900, Takuya Yoshikawa wrote: > > > > > Although the real use case is out of this RFC patch, we are now discussing > > > > > a case in which we may hold a spin_lock for long time, ms order, depending > > > > > on workload; and in that case, other threads -- VCPU threads -- should be > > > > > given higher priority for that problematic lock. > > > > > > > > Firstly, if you can hold a lock that long, it shouldn't be a spinlock, > > > > > > In fact with your mm preemptibility work it can be made into a mutex, if > > > the entire mmu notifier path can be done in task context. However it > > > ends up a strange mutex - you can sleep while holding it but you may not > > > allocate, because you might recurse into an mmu notifier again. > > > > > > Most uses of the lock only involve tweaking some bits though. > > > > I might find a real way to go. > > > > After your "mmu_lock -- TLB-flush" decoupling, we can change the current > > get_dirty work flow like this: > > > > for ... { > > take mmu_lock > > for 4K*8 gfns { // with 4KB dirty_bitmap_buffer > > xchg dirty bits // 64/32 gfns at once > > write protect them > > } > > release mmu_lock > > copy_to_user > > } > > TLB flush > > > > This reduces the size of dirty_bitmap_buffer and does not hold mmu_lock > > so long. > > Good idea. Hopefully the lock acquisition costs are low enough - we're > adding two atomic operations per iteration here. > btw, this requires my kvm_cond_flush_remote_tlbs(). Otherwise another thread can acquire the lock, see a pagetable marked read-only by this code, and proceed to shadow it, while the guest still has a writeable tlb entry pointing at it. -- error compiling committee.c: too many arguments to function