From: Liu Yi L <yi.l.liu@intel.com>
To: qemu-devel@nongnu.org, alex.williamson@redhat.com,
peterx@redhat.com, jasowang@redhat.com
Cc: mst@redhat.com, pbonzini@redhat.com, eric.auger@redhat.com,
david@gibson.dropbear.id.au, jean-philippe@linaro.org,
kevin.tian@intel.com, yi.l.liu@intel.com, jun.j.tian@intel.com,
yi.y.sun@intel.com, hao.wu@intel.com, kvm@vger.kernel.org,
Jacob Pan <jacob.jun.pan@linux.intel.com>,
Yi Sun <yi.y.sun@linux.intel.com>
Subject: [RFC v9 12/25] vfio: init HostIOMMUContext per-container
Date: Mon, 27 Jul 2020 23:34:05 -0700 [thread overview]
Message-ID: <1595918058-33392-13-git-send-email-yi.l.liu@intel.com> (raw)
In-Reply-To: <1595918058-33392-1-git-send-email-yi.l.liu@intel.com>
In this patch, QEMU firstly gets iommu info from kernel to check the
supported capabilities by a VFIO_IOMMU_TYPE1_NESTING iommu. And inits
HostIOMMUContet instance.
For vfio-pci devices, it could use pci_device_set/unset_iommu() to
expose host iommu context to vIOMMU emulators. vIOMMU emulators
could make use the methods provided by host iommu context. e.g.
propagate requests to host iommu.
Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Eric Auger <eric.auger@redhat.com>
Cc: Yi Sun <yi.y.sun@linux.intel.com>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
hw/vfio/common.c | 113 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
hw/vfio/pci.c | 17 +++++++++
2 files changed, 130 insertions(+)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 41aaf41..9d90732 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -1227,10 +1227,102 @@ static int vfio_host_iommu_ctx_pasid_free(HostIOMMUContext *iommu_ctx,
return ret;
}
+/**
+ * Get iommu info from host. Caller of this funcion should free
+ * the memory pointed by the returned pointer stored in @info
+ * after a successful calling when finished its usage.
+ */
+static int vfio_get_iommu_info(VFIOContainer *container,
+ struct vfio_iommu_type1_info **info)
+{
+
+ size_t argsz = sizeof(struct vfio_iommu_type1_info);
+
+ *info = g_malloc0(argsz);
+
+retry:
+ (*info)->argsz = argsz;
+
+ if (ioctl(container->fd, VFIO_IOMMU_GET_INFO, *info)) {
+ g_free(*info);
+ *info = NULL;
+ return -errno;
+ }
+
+ if (((*info)->argsz > argsz)) {
+ argsz = (*info)->argsz;
+ *info = g_realloc(*info, argsz);
+ goto retry;
+ }
+
+ return 0;
+}
+
+static struct vfio_info_cap_header *
+vfio_get_iommu_info_cap(struct vfio_iommu_type1_info *info, uint16_t id)
+{
+ struct vfio_info_cap_header *hdr;
+ void *ptr = info;
+
+ if (!(info->flags & VFIO_IOMMU_INFO_CAPS)) {
+ return NULL;
+ }
+
+ for (hdr = ptr + info->cap_offset; hdr != ptr; hdr = ptr + hdr->next) {
+ if (hdr->id == id) {
+ return hdr;
+ }
+ }
+
+ return NULL;
+}
+
+static int vfio_get_nesting_iommu_cap(VFIOContainer *container,
+ struct vfio_iommu_type1_info_cap_nesting **cap_nesting)
+{
+ struct vfio_iommu_type1_info *info;
+ struct vfio_info_cap_header *hdr;
+ struct vfio_iommu_type1_info_cap_nesting *cap;
+ struct iommu_nesting_info *nest_info;
+ int ret;
+ uint32_t minsz, cap_size;
+
+ ret = vfio_get_iommu_info(container, &info);
+ if (ret) {
+ return ret;
+ }
+
+ hdr = vfio_get_iommu_info_cap(info,
+ VFIO_IOMMU_TYPE1_INFO_CAP_NESTING);
+ if (!hdr) {
+ g_free(info);
+ return -EINVAL;
+ }
+
+ cap = container_of(hdr,
+ struct vfio_iommu_type1_info_cap_nesting, header);
+
+ nest_info = &cap->info;
+ minsz = offsetof(struct iommu_nesting_info, data);
+ if (nest_info->argsz < minsz) {
+ g_free(info);
+ return -EINVAL;
+ }
+
+ cap_size = offsetof(struct vfio_iommu_type1_info_cap_nesting, info) +
+ nest_info->argsz;
+ *cap_nesting = g_malloc0(cap_size);
+ memcpy(*cap_nesting, cap, cap_size);
+
+ g_free(info);
+ return 0;
+}
+
static int vfio_init_container(VFIOContainer *container, int group_fd,
bool want_nested, Error **errp)
{
int iommu_type, ret;
+ uint64_t flags = 0;
iommu_type = vfio_get_iommu_type(container, want_nested, errp);
if (iommu_type < 0) {
@@ -1258,6 +1350,27 @@ static int vfio_init_container(VFIOContainer *container, int group_fd,
return -errno;
}
+ if (iommu_type == VFIO_TYPE1_NESTING_IOMMU) {
+ struct vfio_iommu_type1_info_cap_nesting *nesting = NULL;
+ struct iommu_nesting_info *nest_info;
+
+ ret = vfio_get_nesting_iommu_cap(container, &nesting);
+ if (ret) {
+ error_setg_errno(errp, -ret,
+ "Failed to get nesting iommu cap");
+ return ret;
+ }
+
+ nest_info = (struct iommu_nesting_info *) &nesting->info;
+ flags |= (nest_info->features & IOMMU_NESTING_FEAT_SYSWIDE_PASID) ?
+ HOST_IOMMU_PASID_REQUEST : 0;
+ host_iommu_ctx_init(&container->iommu_ctx,
+ sizeof(container->iommu_ctx),
+ TYPE_VFIO_HOST_IOMMU_CONTEXT,
+ flags);
+ g_free(nesting);
+ }
+
container->iommu_type = iommu_type;
return 0;
}
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index 8cd1e72..f954c28 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -2707,6 +2707,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
VFIOPCIDevice *vdev = PCI_VFIO(pdev);
VFIODevice *vbasedev_iter;
VFIOGroup *group;
+ VFIOContainer *container;
char *tmp, *subsys, group_path[PATH_MAX], *group_name;
Error *err = NULL;
ssize_t len;
@@ -2783,6 +2784,15 @@ static void vfio_realize(PCIDevice *pdev, Error **errp)
goto error;
}
+ container = group->container;
+ if (container->iommu_ctx.initialized &&
+ pci_device_set_iommu_context(pdev, &container->iommu_ctx)) {
+ error_setg(errp, "device attachment is denied by vIOMMU, "
+ "please check host IOMMU nesting capability");
+ vfio_put_group(group);
+ goto error;
+ }
+
QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
if (strcmp(vbasedev_iter->name, vdev->vbasedev.name) == 0) {
error_setg(errp, "device is already attached");
@@ -3068,9 +3078,16 @@ static void vfio_instance_finalize(Object *obj)
static void vfio_exitfn(PCIDevice *pdev)
{
VFIOPCIDevice *vdev = PCI_VFIO(pdev);
+ VFIOContainer *container;
vfio_unregister_req_notifier(vdev);
vfio_unregister_err_notifier(vdev);
+
+ container = vdev->vbasedev.group->container;
+ if (container->iommu_ctx.initialized) {
+ pci_device_unset_iommu_context(pdev);
+ }
+
pci_device_set_intx_routing_notifier(&vdev->pdev, NULL);
if (vdev->irqchip_change_notifier.notify) {
kvm_irqchip_remove_change_notifier(&vdev->irqchip_change_notifier);
--
2.7.4
next prev parent reply other threads:[~2020-07-28 6:27 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-28 6:33 [RFC v9 00/25] intel_iommu: expose Shared Virtual Addressing to VMs Liu Yi L
2020-07-28 6:33 ` [RFC v9 01/25] scripts/update-linux-headers: Import iommu.h Liu Yi L
2020-07-28 6:33 ` [RFC v9 02/25] header file update VFIO/IOMMU vSVA APIs kernel 5.8-rc6 Liu Yi L
2020-07-28 6:33 ` [RFC v9 03/25] hw/pci: modify pci_setup_iommu() to set PCIIOMMUOps Liu Yi L
2020-07-28 6:33 ` [RFC v9 04/25] hw/pci: introduce pci_device_get_iommu_attr() Liu Yi L
2020-07-28 6:33 ` [RFC v9 05/25] intel_iommu: add get_iommu_attr() callback Liu Yi L
2020-07-28 6:33 ` [RFC v9 06/25] vfio: pass nesting requirement into vfio_get_group() Liu Yi L
2020-07-28 6:34 ` [RFC v9 07/25] vfio: check VFIO_TYPE1_NESTING_IOMMU support Liu Yi L
2020-07-28 6:34 ` [RFC v9 08/25] hw/iommu: introduce HostIOMMUContext Liu Yi L
2020-07-28 6:34 ` [RFC v9 09/25] hw/pci: introduce pci_device_set/unset_iommu_context() Liu Yi L
2020-07-28 6:34 ` [RFC v9 10/25] intel_iommu: add set/unset_iommu_context callback Liu Yi L
2020-07-28 6:34 ` [RFC v9 11/25] vfio/common: provide PASID alloc/free hooks Liu Yi L
2020-07-28 6:34 ` Liu Yi L [this message]
2020-07-28 6:34 ` [RFC v9 13/25] intel_iommu: add virtual command capability support Liu Yi L
2020-07-28 6:34 ` [RFC v9 14/25] intel_iommu: process PASID cache invalidation Liu Yi L
2020-07-28 6:34 ` [RFC v9 15/25] intel_iommu: add PASID cache management infrastructure Liu Yi L
2020-07-28 6:34 ` [RFC v9 16/25] vfio: add bind stage-1 page table support Liu Yi L
2020-07-28 6:34 ` [RFC v9 17/25] intel_iommu: sync IOMMU nesting cap info for assigned devices Liu Yi L
2020-07-28 6:34 ` [RFC v9 18/25] intel_iommu: bind/unbind guest page table to host Liu Yi L
2020-07-28 6:34 ` [RFC v9 19/25] intel_iommu: replay pasid binds after context cache invalidation Liu Yi L
2020-07-28 6:34 ` [RFC v9 20/25] intel_iommu: do not pass down pasid bind for PASID #0 Liu Yi L
2020-07-28 6:34 ` [RFC v9 21/25] vfio: add support for flush iommu stage-1 cache Liu Yi L
2020-07-28 6:34 ` [RFC v9 22/25] intel_iommu: process PASID-based iotlb invalidation Liu Yi L
2020-07-28 6:34 ` [RFC v9 23/25] intel_iommu: propagate PASID-based iotlb invalidation to host Liu Yi L
2020-07-28 6:34 ` [RFC v9 24/25] intel_iommu: process PASID-based Device-TLB invalidation Liu Yi L
2020-07-28 6:34 ` [RFC v9 25/25] intel_iommu: modify x-scalable-mode to be string option Liu Yi L
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=1595918058-33392-13-git-send-email-yi.l.liu@intel.com \
--to=yi.l.liu@intel.com \
--cc=alex.williamson@redhat.com \
--cc=david@gibson.dropbear.id.au \
--cc=eric.auger@redhat.com \
--cc=hao.wu@intel.com \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jasowang@redhat.com \
--cc=jean-philippe@linaro.org \
--cc=jun.j.tian@intel.com \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=yi.y.sun@intel.com \
--cc=yi.y.sun@linux.intel.com \
/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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).