From: "Michael S. Tsirkin" <mst@redhat.com> To: Peter Zijlstra <peterz@infradead.org> Cc: linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, Jason Wang <jasowang@redhat.com>, qemu-devel@nongnu.org, Alexander Duyck <alexander.duyck@gmail.com> Subject: Re: [PATCH] virtio_ring: use smp_store_mb Date: Thu, 17 Dec 2015 16:34:57 +0200 [thread overview] Message-ID: <20151217163412-mutt-send-email-mst@redhat.com> (raw) In-Reply-To: <20151217140212.GB6344@twins.programming.kicks-ass.net> On Thu, Dec 17, 2015 at 03:02:12PM +0100, Peter Zijlstra wrote: > On Thu, Dec 17, 2015 at 03:26:29PM +0200, Michael S. Tsirkin wrote: > > > Note that virtio_mb() is weirdly inconsistent with virtio_[rw]mb() in > > > that they use dma_* ops for weak_barriers, while virtio_mb() uses > > > smp_mb(). > > > > It's a hack really. I think I'll clean it up a bit to > > make it more consistent. > > > > To simplify things, you may consider things before > > the optimization brought in by > > commit 9e1a27ea42691429e31f158cce6fc61bc79bb2e9 > > Author: Alexander Duyck <alexander.h.duyck@redhat.com> > > Date: Mon Apr 13 21:03:49 2015 +0930 > > > > virtio_ring: Update weak barriers to use dma_wmb/rmb > > That commit doesn't make any sense. dma_*mb() explicitly does _NOT_ > cover the smp_*mb() part. > > Again, look at the ARM definitions, the smp_*mb() primitives use the > inner coherence stuff, while the dma_*mb() primitives use the outer > coherent stuff. Does outer coherent imply inner coherent? > the *mb() primitives cover both.
WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com> To: Peter Zijlstra <peterz@infradead.org> Cc: qemu-devel@nongnu.org, Jason Wang <jasowang@redhat.com>, linux-kernel@vger.kernel.org, Alexander Duyck <alexander.duyck@gmail.com>, virtualization@lists.linux-foundation.org Subject: Re: [Qemu-devel] [PATCH] virtio_ring: use smp_store_mb Date: Thu, 17 Dec 2015 16:34:57 +0200 [thread overview] Message-ID: <20151217163412-mutt-send-email-mst@redhat.com> (raw) In-Reply-To: <20151217140212.GB6344@twins.programming.kicks-ass.net> On Thu, Dec 17, 2015 at 03:02:12PM +0100, Peter Zijlstra wrote: > On Thu, Dec 17, 2015 at 03:26:29PM +0200, Michael S. Tsirkin wrote: > > > Note that virtio_mb() is weirdly inconsistent with virtio_[rw]mb() in > > > that they use dma_* ops for weak_barriers, while virtio_mb() uses > > > smp_mb(). > > > > It's a hack really. I think I'll clean it up a bit to > > make it more consistent. > > > > To simplify things, you may consider things before > > the optimization brought in by > > commit 9e1a27ea42691429e31f158cce6fc61bc79bb2e9 > > Author: Alexander Duyck <alexander.h.duyck@redhat.com> > > Date: Mon Apr 13 21:03:49 2015 +0930 > > > > virtio_ring: Update weak barriers to use dma_wmb/rmb > > That commit doesn't make any sense. dma_*mb() explicitly does _NOT_ > cover the smp_*mb() part. > > Again, look at the ARM definitions, the smp_*mb() primitives use the > inner coherence stuff, while the dma_*mb() primitives use the outer > coherent stuff. Does outer coherent imply inner coherent? > the *mb() primitives cover both.
next prev parent reply other threads:[~2015-12-17 14:35 UTC|newest] Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top 2015-12-17 10:32 [PATCH] virtio_ring: use smp_store_mb Michael S. Tsirkin 2015-12-17 10:32 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-17 10:52 ` Peter Zijlstra 2015-12-17 10:52 ` Peter Zijlstra 2015-12-17 10:52 ` [Qemu-devel] " Peter Zijlstra 2015-12-17 13:16 ` Michael S. Tsirkin 2015-12-17 13:16 ` Michael S. Tsirkin 2015-12-17 13:16 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-17 13:57 ` Peter Zijlstra 2015-12-17 13:57 ` Peter Zijlstra 2015-12-17 13:57 ` [Qemu-devel] " Peter Zijlstra 2015-12-17 14:33 ` Michael S. Tsirkin 2015-12-17 14:33 ` Michael S. Tsirkin 2015-12-17 14:33 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-17 14:39 ` Peter Zijlstra 2015-12-17 14:39 ` Peter Zijlstra 2015-12-17 14:39 ` [Qemu-devel] " Peter Zijlstra 2015-12-17 14:43 ` Michael S. Tsirkin 2015-12-17 14:43 ` Michael S. Tsirkin 2015-12-17 14:43 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-20 9:25 ` new barrier type for paravirt (was Re: [PATCH] virtio_ring: use smp_store_mb) Michael S. Tsirkin 2015-12-20 9:25 ` Michael S. Tsirkin 2015-12-20 9:25 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-20 17:07 ` Andrew Cooper 2015-12-20 17:07 ` [Xen-devel] " Andrew Cooper 2015-12-20 17:07 ` Andrew Cooper 2015-12-20 17:07 ` [Qemu-devel] " Andrew Cooper 2015-12-20 19:59 ` Peter Zijlstra 2015-12-20 19:59 ` Peter Zijlstra 2015-12-20 19:59 ` [Qemu-devel] " Peter Zijlstra 2015-12-21 7:10 ` Michael S. Tsirkin 2015-12-21 7:10 ` [Xen-devel] " Michael S. Tsirkin 2015-12-21 7:10 ` Michael S. Tsirkin 2015-12-21 7:10 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-21 7:22 ` [PATCH RFC] smp_store_mb should use smp_mb Michael S. Tsirkin 2015-12-21 7:22 ` Michael S. Tsirkin 2015-12-21 7:22 ` Michael S. Tsirkin 2015-12-21 7:22 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-20 19:59 ` new barrier type for paravirt (was Re: [PATCH] virtio_ring: use smp_store_mb) Peter Zijlstra 2015-12-21 10:47 ` David Vrabel 2015-12-21 10:47 ` [Xen-devel] " David Vrabel 2015-12-21 10:47 ` David Vrabel 2015-12-21 10:47 ` [Qemu-devel] " David Vrabel 2015-12-21 11:52 ` Michael S. Tsirkin 2015-12-21 11:52 ` [Xen-devel] " Michael S. Tsirkin 2015-12-21 11:52 ` Michael S. Tsirkin 2015-12-21 11:52 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-21 14:50 ` Stefano Stabellini 2015-12-21 14:50 ` Stefano Stabellini 2015-12-21 14:50 ` Stefano Stabellini 2015-12-21 14:50 ` Stefano Stabellini 2015-12-21 14:50 ` [Qemu-devel] " Stefano Stabellini 2015-12-20 9:25 ` Michael S. Tsirkin 2015-12-17 11:22 ` [PATCH] virtio_ring: use smp_store_mb Peter Zijlstra 2015-12-17 11:22 ` [Qemu-devel] " Peter Zijlstra 2015-12-17 13:26 ` Michael S. Tsirkin 2015-12-17 13:26 ` Michael S. Tsirkin 2015-12-17 13:26 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-17 14:02 ` Peter Zijlstra 2015-12-17 14:02 ` Peter Zijlstra 2015-12-17 14:02 ` [Qemu-devel] " Peter Zijlstra 2015-12-17 14:34 ` Michael S. Tsirkin 2015-12-17 14:34 ` Michael S. Tsirkin [this message] 2015-12-17 14:34 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-17 15:09 ` Peter Zijlstra 2015-12-17 15:09 ` Peter Zijlstra 2015-12-17 15:09 ` [Qemu-devel] " Peter Zijlstra 2015-12-17 15:52 ` Will Deacon 2015-12-17 15:52 ` Will Deacon 2015-12-17 15:52 ` [Qemu-devel] " Will Deacon 2015-12-17 19:21 ` Michael S. Tsirkin 2015-12-17 19:21 ` Michael S. Tsirkin 2015-12-17 19:21 ` [Qemu-devel] " Michael S. Tsirkin 2015-12-17 11:22 ` Peter Zijlstra -- strict thread matches above, loose matches on Subject: below -- 2015-12-17 10:32 Michael S. Tsirkin
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20151217163412-mutt-send-email-mst@redhat.com \ --to=mst@redhat.com \ --cc=alexander.duyck@gmail.com \ --cc=jasowang@redhat.com \ --cc=linux-kernel@vger.kernel.org \ --cc=peterz@infradead.org \ --cc=qemu-devel@nongnu.org \ --cc=virtualization@lists.linux-foundation.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.