From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1162896AbcG0WvF (ORCPT ); Wed, 27 Jul 2016 18:51:05 -0400 Received: from mx1.redhat.com ([209.132.183.28]:52108 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932335AbcG0Wu5 (ORCPT ); Wed, 27 Jul 2016 18:50:57 -0400 Date: Thu, 28 Jul 2016 01:50:52 +0300 From: "Michael S. Tsirkin" To: linux-kernel@vger.kernel.org Cc: virtualization@lists.linux-foundation.org, Christoph Hellwig , Jason Wang Subject: [PATCH v4] virtio: new feature to detect IOMMU device quirk Message-ID: <1469659378-15957-1-git-send-email-mst@redhat.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline X-Mutt-Fcc: =sent X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.39]); Wed, 27 Jul 2016 22:50:56 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The interaction between virtio and IOMMUs is messy. On most systems with virtio, physical addresses match bus addresses, and it doesn't particularly matter which one we use to program the device. On some systems, including Xen and any system with a physical device that speaks virtio behind a physical IOMMU, we must program the IOMMU for virtio DMA to work at all. On other systems, including SPARC and PPC64, virtio-pci devices are enumerated as though they are behind an IOMMU, but the virtio host ignores the IOMMU, so we must either pretend that the IOMMU isn't there or somehow map everything as the identity. Add a feature bit to detect that quirk: VIRTIO_F_IOMMU_PLATFORM. Any device with this feature bit set to 0 needs a quirk and has to be passed physical addresses (as opposed to bus addresses) even though the device is behind an IOMMU. Note: it has to be a per-device quirk because for example, there could be a mix of passed-through and virtual virtio devices. As another example, some devices could be implemented by an out of process hypervisor backend (in case of qemu vhost, or vhost-user) and so support for an IOMMU needs to be coded up separately. It would be cleanest to handle this in IOMMU core code, but that needs per-device DMA ops. This should not be hard to do, and it will serve to replace the existing Xen hacks, but doesn't seem practical for 4.8 and we don't want to defer hardware support until that's ready. Add a TODO so we remember to clean it up for 4.9. Signed-off-by: Michael S. Tsirkin --- Changes from v3: In response to Christoph's comments, add TODO so we remember to move this into DMA core. Definitely something we want to do but doesn't seem practical for this release cycle. include/uapi/linux/virtio_config.h | 4 +++- drivers/virtio/virtio_ring.c | 15 ++++++++++++++- 2 files changed, 17 insertions(+), 2 deletions(-) diff --git a/include/uapi/linux/virtio_config.h b/include/uapi/linux/virtio_config.h index 4cb65bb..3f6195e 100644 --- a/include/uapi/linux/virtio_config.h +++ b/include/uapi/linux/virtio_config.h @@ -49,7 +49,7 @@ * transport being used (eg. virtio_ring), the rest are per-device feature * bits. */ #define VIRTIO_TRANSPORT_F_START 28 -#define VIRTIO_TRANSPORT_F_END 33 +#define VIRTIO_TRANSPORT_F_END 34 #ifndef VIRTIO_CONFIG_NO_LEGACY /* Do we get callbacks when the ring is completely used, even if we've @@ -63,4 +63,6 @@ /* v1.0 compliant. */ #define VIRTIO_F_VERSION_1 32 +/* Do not bypass the IOMMU (if configured) */ +#define VIRTIO_F_IOMMU_PLATFORM 33 #endif /* _UAPI_LINUX_VIRTIO_CONFIG_H */ diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c index ca6bfdd..a0571f6 100644 --- a/drivers/virtio/virtio_ring.c +++ b/drivers/virtio/virtio_ring.c @@ -117,7 +117,10 @@ struct vring_virtqueue { #define to_vvq(_vq) container_of(_vq, struct vring_virtqueue, vq) /* - * The interaction between virtio and a possible IOMMU is a mess. + * Modern virtio devices might set feature bits to specify whether + * they use the platform IOMMU. If there, just use the DMA API. + * + * If not there, the interaction between virtio and DMA API is messy. * * On most systems with virtio, physical addresses match bus addresses, * and it doesn't particularly matter whether we use the DMA API. @@ -133,10 +136,18 @@ struct vring_virtqueue { * * For the time being, we preserve historic behavior and bypass the DMA * API. + * + * TODO: install a per-device DMA ops structure that does the right thing + * taking into account all the above quirks, and use the DMA API + * unconditionally on data path. */ static bool vring_use_dma_api(struct virtio_device *vdev) { + if (virtio_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM)) + return true; + + /* Otherwise, we are left to guess. */ /* * In theory, it's possible to have a buggy QEMU-supposed * emulated Q35 IOMMU and Xen enabled at the same time. On @@ -1099,6 +1110,8 @@ void vring_transport_features(struct virtio_device *vdev) break; case VIRTIO_F_VERSION_1: break; + case VIRTIO_F_IOMMU_PLATFORM: + break; default: /* We don't understand this bit. */ __virtio_clear_bit(vdev, i); -- MST