From patchwork Wed Feb 13 13:25:43 2019 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wei Xu X-Patchwork-Id: 1041264 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (mailfrom) smtp.mailfrom=nongnu.org (client-ip=209.51.188.17; helo=lists.gnu.org; envelope-from=qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org; receiver=) Authentication-Results: ozlabs.org; dmarc=fail (p=none dis=none) header.from=redhat.com Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 4400zD2qtdz9s3l for ; Thu, 14 Feb 2019 00:40:56 +1100 (AEDT) Received: from localhost ([127.0.0.1]:57024 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gtumU-0005xi-C7 for incoming@patchwork.ozlabs.org; Wed, 13 Feb 2019 08:40:54 -0500 Received: from eggs.gnu.org ([209.51.188.92]:52823) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gtujd-00048J-2u for qemu-devel@nongnu.org; Wed, 13 Feb 2019 08:37:58 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gtuja-0006TI-61 for qemu-devel@nongnu.org; Wed, 13 Feb 2019 08:37:56 -0500 Received: from mx1.redhat.com ([209.132.183.28]:52614) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gtujY-0006Gh-4S for qemu-devel@nongnu.org; Wed, 13 Feb 2019 08:37:53 -0500 Received: from smtp.corp.redhat.com (int-mx03.intmail.prod.int.phx2.redhat.com [10.5.11.13]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 2A2BCC057F99; Wed, 13 Feb 2019 13:28:08 +0000 (UTC) Received: from dell-per430-12.lab.eng.pek2.redhat.com (dell-per430-12.lab.eng.pek2.redhat.com [10.73.196.55]) by smtp.corp.redhat.com (Postfix) with ESMTP id 03B7F60857; Wed, 13 Feb 2019 13:28:05 +0000 (UTC) From: wexu@redhat.com To: qemu-devel@nongnu.org Date: Wed, 13 Feb 2019 08:25:43 -0500 Message-Id: <1550064346-17012-9-git-send-email-wexu@redhat.com> In-Reply-To: <1550064346-17012-1-git-send-email-wexu@redhat.com> References: <1550064346-17012-1-git-send-email-wexu@redhat.com> X-Scanned-By: MIMEDefang 2.79 on 10.5.11.13 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.32]); Wed, 13 Feb 2019 13:28:08 +0000 (UTC) X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] X-Received-From: 209.132.183.28 Subject: [Qemu-devel] [PATCH 08/11] virtio: event suppression support for packed ring X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: tiwei.bie@intel.com, mst@redhat.com, jasowang@redhat.com, jfreiman@redhat.com, maxime.coquelin@redhat.com, wexu@redhat.com Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: "Qemu-devel" From: Wei Xu Difference between 'avail_wrap_counter' and 'last_avail_wrap_counter': For Tx(guest transmitting), they are the same after each pop of a desc. For Rx(guest receiving), they are also the same when there are enough descriptors to carry the payload for a packet(e.g. usually 16 descs are needed for a 64k packet in typical iperf tcp connection with tso enabled), however, when the ring is running out of descriptors while there are still a few free ones, e.g. 6 descriptors are available which is not enough to carry an entire packet which needs 16 descriptors, in this case the 'avail_wrap_counter' should be set as the first one pending being handled by guest driver in order to get a notification, and the 'last_avail_wrap_counter' should stay unchanged to the head of available descriptors, like below: Mark meaning: | | -- available |*| -- used A Snapshot of the queue: last_avail_idx = 253 last_avail_wrap_counter = 1 | +---------------------------------------------+ 0 | | | |*|*|*|*|*|*|*|*|*|*|*|*|*|*|*|*|*| | | | 255 +---------------------------------------------+ | shadow_avail_idx = 3 avail_wrap_counter = 0 Signed-off-by: Wei Xu --- hw/virtio/virtio.c | 137 +++++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 128 insertions(+), 9 deletions(-) diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 7e276b4..8cfc7b6 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -234,6 +234,34 @@ static void vring_desc_read(VirtIODevice *vdev, VRingDesc *desc, virtio_tswap16s(vdev, &desc->next); } +static void vring_packed_event_read(VirtIODevice *vdev, + MemoryRegionCache *cache, VRingPackedDescEvent *e) +{ + address_space_read_cached(cache, 0, e, sizeof(*e)); + virtio_tswap16s(vdev, &e->off_wrap); + virtio_tswap16s(vdev, &e->flags); +} + +static void vring_packed_off_wrap_write(VirtIODevice *vdev, + MemoryRegionCache *cache, uint16_t off_wrap) +{ + virtio_tswap16s(vdev, &off_wrap); + address_space_write_cached(cache, offsetof(VRingPackedDescEvent, off_wrap), + &off_wrap, sizeof(off_wrap)); + address_space_cache_invalidate(cache, + offsetof(VRingPackedDescEvent, off_wrap), sizeof(off_wrap)); +} + +static void vring_packed_flags_write(VirtIODevice *vdev, + MemoryRegionCache *cache, uint16_t flags) +{ + virtio_tswap16s(vdev, &flags); + address_space_write_cached(cache, offsetof(VRingPackedDescEvent, flags), + &flags, sizeof(flags)); + address_space_cache_invalidate(cache, + offsetof(VRingPackedDescEvent, flags), sizeof(flags)); +} + static VRingMemoryRegionCaches *vring_get_region_caches(struct VirtQueue *vq) { VRingMemoryRegionCaches *caches = atomic_rcu_read(&vq->vring.caches); @@ -340,14 +368,8 @@ static inline void vring_set_avail_event(VirtQueue *vq, uint16_t val) address_space_cache_invalidate(&caches->used, pa, sizeof(val)); } -void virtio_queue_set_notification(VirtQueue *vq, int enable) +static void virtio_queue_set_notification_split(VirtQueue *vq, int enable) { - vq->notification = enable; - - if (!vq->vring.desc) { - return; - } - rcu_read_lock(); if (virtio_vdev_has_feature(vq->vdev, VIRTIO_RING_F_EVENT_IDX)) { vring_set_avail_event(vq, vring_avail_idx(vq)); @@ -363,6 +385,57 @@ void virtio_queue_set_notification(VirtQueue *vq, int enable) rcu_read_unlock(); } +static void virtio_queue_set_notification_packed(VirtQueue *vq, int enable) +{ + VRingPackedDescEvent e; + VRingMemoryRegionCaches *caches; + + rcu_read_lock(); + caches = vring_get_region_caches(vq); + vring_packed_event_read(vq->vdev, &caches->used, &e); + + if (!enable) { + if (virtio_vdev_has_feature(vq->vdev, VIRTIO_RING_F_EVENT_IDX)) { + /* no need to write device area since this is outdated. */ + goto out; + } + + e.flags = VRING_PACKED_EVENT_FLAG_DISABLE; + goto update; + } + + e.flags = VRING_PACKED_EVENT_FLAG_ENABLE; + if (virtio_vdev_has_feature(vq->vdev, VIRTIO_RING_F_EVENT_IDX)) { + uint16_t off_wrap = vq->shadow_avail_idx | vq->avail_wrap_counter << 15; + + vring_packed_off_wrap_write(vq->vdev, &caches->used, off_wrap); + /* Make sure off_wrap is wrote before flags */ + smp_wmb(); + + e.flags = VRING_PACKED_EVENT_FLAG_DESC; + } + +update: + vring_packed_flags_write(vq->vdev, &caches->used, e.flags); +out: + rcu_read_unlock(); +} + +void virtio_queue_set_notification(VirtQueue *vq, int enable) +{ + vq->notification = enable; + + if (!vq->vring.desc) { + return; + } + + if (virtio_vdev_has_feature(vq->vdev, VIRTIO_F_RING_PACKED)) { + virtio_queue_set_notification_packed(vq, enable); + } else { + virtio_queue_set_notification_split(vq, enable); + } +} + int virtio_queue_ready(VirtQueue *vq) { return vq->vring.avail != 0; @@ -2117,8 +2190,7 @@ static void virtio_set_isr(VirtIODevice *vdev, int value) } } -/* Called within rcu_read_lock(). */ -static bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) +static bool virtio_split_should_notify(VirtIODevice *vdev, VirtQueue *vq) { uint16_t old, new; bool v; @@ -2141,6 +2213,53 @@ static bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) return !v || vring_need_event(vring_get_used_event(vq), new, old); } +static bool vring_packed_need_event(VirtQueue *vq, bool wrap, + uint16_t off_wrap, uint16_t new, uint16_t old) +{ + int off = off_wrap & ~(1 << 15); + + if (wrap != off_wrap >> 15) { + off -= vq->vring.num; + } + + return vring_need_event(off, new, old); +} + +static bool virtio_packed_should_notify(VirtIODevice *vdev, VirtQueue *vq) +{ + VRingPackedDescEvent e; + uint16_t old, new; + bool v; + VRingMemoryRegionCaches *caches; + + caches = vring_get_region_caches(vq); + vring_packed_event_read(vdev, &caches->avail, &e); + + old = vq->signalled_used; + new = vq->signalled_used = vq->used_idx; + v = vq->signalled_used_valid; + vq->signalled_used_valid = true; + + if (e.flags == VRING_PACKED_EVENT_FLAG_DISABLE) { + return false; + } else if (e.flags == VRING_PACKED_EVENT_FLAG_ENABLE) { + return true; + } + + return !v || vring_packed_need_event(vq, + vq->used_wrap_counter, e.off_wrap, new, old); +} + +/* Called within rcu_read_lock(). */ +static bool virtio_should_notify(VirtIODevice *vdev, VirtQueue *vq) +{ + if (virtio_vdev_has_feature(vdev, VIRTIO_F_RING_PACKED)) { + return virtio_packed_should_notify(vdev, vq); + } else { + return virtio_split_should_notify(vdev, vq); + } +} + void virtio_notify_irqfd(VirtIODevice *vdev, VirtQueue *vq) { bool should_notify;