From patchwork Sat Feb 6 19:12:53 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Michael S. Tsirkin" X-Patchwork-Id: 8243131 Return-Path: X-Original-To: patchwork-qemu-devel@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 020BC9F1C0 for ; Sat, 6 Feb 2016 19:16:42 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 2C39520260 for ; Sat, 6 Feb 2016 19:16:41 +0000 (UTC) Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPS id 286AF20253 for ; Sat, 6 Feb 2016 19:16:40 +0000 (UTC) Received: from localhost ([::1]:56058 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aS8LX-0007Th-FS for patchwork-qemu-devel@patchwork.kernel.org; Sat, 06 Feb 2016 14:16:39 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:53031) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aS8I0-0001P6-3i for qemu-devel@nongnu.org; Sat, 06 Feb 2016 14:13:05 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1aS8Hy-0002Bi-4V for qemu-devel@nongnu.org; Sat, 06 Feb 2016 14:12:59 -0500 Received: from mx1.redhat.com ([209.132.183.28]:35171) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1aS8Hx-0002Bc-P3 for qemu-devel@nongnu.org; Sat, 06 Feb 2016 14:12:58 -0500 Received: from int-mx13.intmail.prod.int.phx2.redhat.com (int-mx13.intmail.prod.int.phx2.redhat.com [10.5.11.26]) by mx1.redhat.com (Postfix) with ESMTPS id 7F37F8F4F4; Sat, 6 Feb 2016 19:12:57 +0000 (UTC) Received: from redhat.com (vpn1-5-159.ams2.redhat.com [10.36.5.159]) by int-mx13.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with SMTP id u16JCsqx016014; Sat, 6 Feb 2016 14:12:55 -0500 Date: Sat, 6 Feb 2016 21:12:53 +0200 From: "Michael S. Tsirkin" To: qemu-devel@nongnu.org Message-ID: <1454784308-21177-12-git-send-email-mst@redhat.com> References: <1454784308-21177-1-git-send-email-mst@redhat.com> MIME-Version: 1.0 Content-Disposition: inline In-Reply-To: <1454784308-21177-1-git-send-email-mst@redhat.com> X-Mutt-Fcc: =sent X-Scanned-By: MIMEDefang 2.68 on 10.5.11.26 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 209.132.183.28 Cc: Cornelia Huck , Peter Maydell , Eduardo Habkost , Paolo Bonzini Subject: [Qemu-devel] [PULL v2 11/45] virtio: combine the read of a descriptor X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org X-Spam-Status: No, score=-6.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP From: Paolo Bonzini Compared to vring, virtio has a performance penalty of 10%. Fix it by combining all the reads for a descriptor in a single address_space_read call. This also simplifies the code nicely. Reviewed-by: Cornelia Huck Signed-off-by: Paolo Bonzini Reviewed-by: Michael S. Tsirkin Signed-off-by: Michael S. Tsirkin --- hw/virtio/virtio.c | 86 ++++++++++++++++++++++-------------------------------- 1 file changed, 35 insertions(+), 51 deletions(-) diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index c3e00a8..225ee6d 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -107,35 +107,15 @@ void virtio_queue_update_rings(VirtIODevice *vdev, int n) vring->align); } -static inline uint64_t vring_desc_addr(VirtIODevice *vdev, hwaddr desc_pa, - int i) +static void vring_desc_read(VirtIODevice *vdev, VRingDesc *desc, + hwaddr desc_pa, int i) { - hwaddr pa; - pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, addr); - return virtio_ldq_phys(vdev, pa); -} - -static inline uint32_t vring_desc_len(VirtIODevice *vdev, hwaddr desc_pa, int i) -{ - hwaddr pa; - pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, len); - return virtio_ldl_phys(vdev, pa); -} - -static inline uint16_t vring_desc_flags(VirtIODevice *vdev, hwaddr desc_pa, - int i) -{ - hwaddr pa; - pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, flags); - return virtio_lduw_phys(vdev, pa); -} - -static inline uint16_t vring_desc_next(VirtIODevice *vdev, hwaddr desc_pa, - int i) -{ - hwaddr pa; - pa = desc_pa + sizeof(VRingDesc) * i + offsetof(VRingDesc, next); - return virtio_lduw_phys(vdev, pa); + address_space_read(&address_space_memory, desc_pa + i * sizeof(VRingDesc), + MEMTXATTRS_UNSPECIFIED, (void *)desc, sizeof(VRingDesc)); + virtio_tswap64s(vdev, &desc->addr); + virtio_tswap32s(vdev, &desc->len); + virtio_tswap16s(vdev, &desc->flags); + virtio_tswap16s(vdev, &desc->next); } static inline uint16_t vring_avail_flags(VirtQueue *vq) @@ -345,18 +325,18 @@ static unsigned int virtqueue_get_head(VirtQueue *vq, unsigned int idx) return head; } -static unsigned virtqueue_next_desc(VirtIODevice *vdev, hwaddr desc_pa, - unsigned int i, unsigned int max) +static unsigned virtqueue_read_next_desc(VirtIODevice *vdev, VRingDesc *desc, + hwaddr desc_pa, unsigned int max) { unsigned int next; /* If this descriptor says it doesn't chain, we're done. */ - if (!(vring_desc_flags(vdev, desc_pa, i) & VRING_DESC_F_NEXT)) { + if (!(desc->flags & VRING_DESC_F_NEXT)) { return max; } /* Check they're not leading us off end of descriptors. */ - next = vring_desc_next(vdev, desc_pa, i); + next = desc->next; /* Make sure compiler knows to grab that: we don't want it changing! */ smp_wmb(); @@ -365,6 +345,7 @@ static unsigned virtqueue_next_desc(VirtIODevice *vdev, hwaddr desc_pa, exit(1); } + vring_desc_read(vdev, desc, desc_pa, next); return next; } @@ -381,6 +362,7 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, while (virtqueue_num_heads(vq, idx)) { VirtIODevice *vdev = vq->vdev; unsigned int max, num_bufs, indirect = 0; + VRingDesc desc; hwaddr desc_pa; int i; @@ -388,9 +370,10 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, num_bufs = total_bufs; i = virtqueue_get_head(vq, idx++); desc_pa = vq->vring.desc; + vring_desc_read(vdev, &desc, desc_pa, i); - if (vring_desc_flags(vdev, desc_pa, i) & VRING_DESC_F_INDIRECT) { - if (vring_desc_len(vdev, desc_pa, i) % sizeof(VRingDesc)) { + if (desc.flags & VRING_DESC_F_INDIRECT) { + if (desc.len % sizeof(VRingDesc)) { error_report("Invalid size for indirect buffer table"); exit(1); } @@ -403,9 +386,10 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, /* loop over the indirect descriptor table */ indirect = 1; - max = vring_desc_len(vdev, desc_pa, i) / sizeof(VRingDesc); - desc_pa = vring_desc_addr(vdev, desc_pa, i); + max = desc.len / sizeof(VRingDesc); + desc_pa = desc.addr; num_bufs = i = 0; + vring_desc_read(vdev, &desc, desc_pa, i); } do { @@ -415,15 +399,15 @@ void virtqueue_get_avail_bytes(VirtQueue *vq, unsigned int *in_bytes, exit(1); } - if (vring_desc_flags(vdev, desc_pa, i) & VRING_DESC_F_WRITE) { - in_total += vring_desc_len(vdev, desc_pa, i); + if (desc.flags & VRING_DESC_F_WRITE) { + in_total += desc.len; } else { - out_total += vring_desc_len(vdev, desc_pa, i); + out_total += desc.len; } if (in_total >= max_in_bytes && out_total >= max_out_bytes) { goto done; } - } while ((i = virtqueue_next_desc(vdev, desc_pa, i, max)) != max); + } while ((i = virtqueue_read_next_desc(vdev, &desc, desc_pa, max)) != max); if (!indirect) total_bufs = num_bufs; @@ -545,6 +529,7 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) unsigned out_num, in_num; hwaddr addr[VIRTQUEUE_MAX_SIZE]; struct iovec iov[VIRTQUEUE_MAX_SIZE]; + VRingDesc desc; if (!virtqueue_num_heads(vq, vq->last_avail_idx)) { return NULL; @@ -560,33 +545,32 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) vring_set_avail_event(vq, vq->last_avail_idx); } - if (vring_desc_flags(vdev, desc_pa, i) & VRING_DESC_F_INDIRECT) { - if (vring_desc_len(vdev, desc_pa, i) % sizeof(VRingDesc)) { + vring_desc_read(vdev, &desc, desc_pa, i); + if (desc.flags & VRING_DESC_F_INDIRECT) { + if (desc.len % sizeof(VRingDesc)) { error_report("Invalid size for indirect buffer table"); exit(1); } /* loop over the indirect descriptor table */ - max = vring_desc_len(vdev, desc_pa, i) / sizeof(VRingDesc); - desc_pa = vring_desc_addr(vdev, desc_pa, i); + max = desc.len / sizeof(VRingDesc); + desc_pa = desc.addr; i = 0; + vring_desc_read(vdev, &desc, desc_pa, i); } /* Collect all the descriptors */ do { - hwaddr pa = vring_desc_addr(vdev, desc_pa, i); - size_t len = vring_desc_len(vdev, desc_pa, i); - - if (vring_desc_flags(vdev, desc_pa, i) & VRING_DESC_F_WRITE) { + if (desc.flags & VRING_DESC_F_WRITE) { virtqueue_map_desc(&in_num, addr + out_num, iov + out_num, - VIRTQUEUE_MAX_SIZE - out_num, true, pa, len); + VIRTQUEUE_MAX_SIZE - out_num, true, desc.addr, desc.len); } else { if (in_num) { error_report("Incorrect order for descriptors"); exit(1); } virtqueue_map_desc(&out_num, addr, iov, - VIRTQUEUE_MAX_SIZE, false, pa, len); + VIRTQUEUE_MAX_SIZE, false, desc.addr, desc.len); } /* If we've got too many, that implies a descriptor loop. */ @@ -594,7 +578,7 @@ void *virtqueue_pop(VirtQueue *vq, size_t sz) error_report("Looped descriptor"); exit(1); } - } while ((i = virtqueue_next_desc(vdev, desc_pa, i, max)) != max); + } while ((i = virtqueue_read_next_desc(vdev, &desc, desc_pa, max)) != max); /* Now copy what we have collected and mapped */ elem = virtqueue_alloc_element(sz, out_num, in_num);