qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Liu Yi L <yi.l.liu@intel.com>
To: qemu-devel@nongnu.org, alex.williamson@redhat.com, peterx@redhat.com
Cc: kevin.tian@intel.com, yi.l.liu@intel.com,
	Yi Sun <yi.y.sun@linux.intel.com>,
	Eduardo Habkost <ehabkost@redhat.com>,
	kvm@vger.kernel.org, mst@redhat.com, jun.j.tian@intel.com,
	eric.auger@redhat.com, yi.y.sun@intel.com,
	Jacob Pan <jacob.jun.pan@linux.intel.com>,
	pbonzini@redhat.com, Richard Henderson <rth@twiddle.net>,
	david@gibson.dropbear.id.au
Subject: [RFC v3.1 20/22] intel_iommu: propagate PASID-based iotlb invalidation to host
Date: Sat, 22 Feb 2020 00:07:21 -0800	[thread overview]
Message-ID: <1582358843-51931-21-git-send-email-yi.l.liu@intel.com> (raw)
In-Reply-To: <1582358843-51931-1-git-send-email-yi.l.liu@intel.com>

This patch propagates PASID-based iotlb invalidation to host.

Intel VT-d 3.0 supports nested translation in PASID granular.
Guest SVA support could be implemented by configuring nested
translation on specific PASID. This is also known as dual stage
DMA translation.

Under such configuration, guest owns the GVA->GPA translation
which is configured as first level page table in host side for
a specific pasid, and host owns GPA->HPA translation. As guest
owns first level translation table, piotlb invalidation should
be propagated to host since host IOMMU will cache first level
page table related mappings during DMA address translation.

This patch traps the guest PASID-based iotlb flush and propagate
it to host.

Cc: Kevin Tian <kevin.tian@intel.com>
Cc: Jacob Pan <jacob.jun.pan@linux.intel.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Yi Sun <yi.y.sun@linux.intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Liu Yi L <yi.l.liu@intel.com>
---
 hw/i386/intel_iommu.c          | 131 +++++++++++++++++++++++++++++++++++++++++
 hw/i386/intel_iommu_internal.h |   7 +++
 2 files changed, 138 insertions(+)

diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index b712eae..e6326ef 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -3157,15 +3157,146 @@ static bool vtd_process_pasid_desc(IntelIOMMUState *s,
     return (ret == 0) ? true : false;
 }
 
+static void vtd_invalidate_piotlb(IntelIOMMUState *s,
+                                  VTDBus *vtd_bus,
+                                  int devfn,
+                                  DualIOMMUStage1Cache *stage1_cache)
+{
+    PCIDevice *dev;
+    HostIOMMUContext *host_icx;
+    dev = vtd_bus->bus->devices[devfn];
+
+    host_icx = pci_device_host_iommu_context(dev);
+    if (!host_icx) {
+        return;
+    }
+    if (host_iommu_ctx_flush_stage1_cache(host_icx, stage1_cache)) {
+        error_report("Cache flush failed");
+    }
+}
+
+static inline bool vtd_pasid_cache_valid(
+                          VTDPASIDAddressSpace *vtd_pasid_as)
+{
+    return vtd_pasid_as->iommu_state &&
+           (vtd_pasid_as->iommu_state->pasid_cache_gen
+             == vtd_pasid_as->pasid_cache_entry.pasid_cache_gen);
+}
+
+/**
+ * This function is a loop function for the s->vtd_pasid_as
+ * list with VTDPIOTLBInvInfo as execution filter. It propagates
+ * the piotlb invalidation to host. Caller of this function
+ * should hold iommu_lock.
+ */
+static void vtd_flush_pasid_iotlb(gpointer key, gpointer value,
+                                  gpointer user_data)
+{
+    VTDPIOTLBInvInfo *piotlb_info = user_data;
+    VTDPASIDAddressSpace *vtd_pasid_as = value;
+    uint16_t did;
+
+    /*
+     * Needs to check whether the pasid entry cache stored in
+     * vtd_pasid_as is valid or not. "invalid" means the pasid
+     * cache has been flushed, thus host should have done piotlb
+     * invalidation together with a pasid cache invalidation, so
+     * no need to pass down piotlb invalidation to host for better
+     * performance. Only when pasid entry cache is "valid", should
+     * a piotlb invalidation be propagated to host since it means
+     * guest just modified a mapping in its page table.
+     */
+    if (!vtd_pasid_cache_valid(vtd_pasid_as)) {
+        return;
+    }
+
+    did = vtd_pe_get_domain_id(
+                &(vtd_pasid_as->pasid_cache_entry.pasid_entry));
+
+    if ((piotlb_info->domain_id == did) &&
+        (piotlb_info->pasid == vtd_pasid_as->pasid)) {
+        vtd_invalidate_piotlb(vtd_pasid_as->iommu_state,
+                              vtd_pasid_as->vtd_bus,
+                              vtd_pasid_as->devfn,
+                              piotlb_info->stage1_cache);
+    }
+
+    /*
+     * TODO: needs to add QEMU piotlb flush when QEMU piotlb
+     * infrastructure is ready. For now, it is enough for passthru
+     * devices.
+     */
+}
+
 static void vtd_piotlb_pasid_invalidate(IntelIOMMUState *s,
                                         uint16_t domain_id,
                                         uint32_t pasid)
 {
+    VTDPIOTLBInvInfo piotlb_info;
+    DualIOMMUStage1Cache *stage1_cache;
+    struct iommu_cache_invalidate_info *cache_info;
+
+    stage1_cache = g_malloc0(sizeof(*stage1_cache));
+    stage1_cache->pasid = pasid;
+
+    cache_info = &stage1_cache->cache_info;
+    cache_info->version = IOMMU_UAPI_VERSION;
+    cache_info->cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+    cache_info->granularity = IOMMU_INV_GRANU_PASID;
+    cache_info->pasid_info.pasid = pasid;
+    cache_info->pasid_info.flags = IOMMU_INV_PASID_FLAGS_PASID;
+
+    piotlb_info.domain_id = domain_id;
+    piotlb_info.pasid = pasid;
+    piotlb_info.stage1_cache = stage1_cache;
+
+    vtd_iommu_lock(s);
+    /*
+     * Here loops all the vtd_pasid_as instances in s->vtd_pasid_as
+     * to find out the affected devices since piotlb invalidation
+     * should check pasid cache per architecture point of view.
+     */
+    g_hash_table_foreach(s->vtd_pasid_as,
+                         vtd_flush_pasid_iotlb, &piotlb_info);
+    vtd_iommu_unlock(s);
+    g_free(stage1_cache);
 }
 
 static void vtd_piotlb_page_invalidate(IntelIOMMUState *s, uint16_t domain_id,
                              uint32_t pasid, hwaddr addr, uint8_t am, bool ih)
 {
+    VTDPIOTLBInvInfo piotlb_info;
+    DualIOMMUStage1Cache *stage1_cache;
+    struct iommu_cache_invalidate_info *cache_info;
+
+    stage1_cache = g_malloc0(sizeof(*stage1_cache));
+    stage1_cache->pasid = pasid;
+
+    cache_info = &stage1_cache->cache_info;
+    cache_info->version = IOMMU_UAPI_VERSION;
+    cache_info->cache = IOMMU_CACHE_INV_TYPE_IOTLB;
+    cache_info->granularity = IOMMU_INV_GRANU_ADDR;
+    cache_info->addr_info.flags = IOMMU_INV_ADDR_FLAGS_PASID;
+    cache_info->addr_info.flags |= ih ? IOMMU_INV_ADDR_FLAGS_LEAF : 0;
+    cache_info->addr_info.pasid = pasid;
+    cache_info->addr_info.addr = addr;
+    cache_info->addr_info.granule_size = 1 << (12 + am);
+    cache_info->addr_info.nb_granules = 1;
+
+    piotlb_info.domain_id = domain_id;
+    piotlb_info.pasid = pasid;
+    piotlb_info.stage1_cache = stage1_cache;
+
+    vtd_iommu_lock(s);
+    /*
+     * Here loops all the vtd_pasid_as instances in s->vtd_pasid_as
+     * to find out the affected devices since piotlb invalidation
+     * should check pasid cache per architecture point of view.
+     */
+    g_hash_table_foreach(s->vtd_pasid_as,
+                         vtd_flush_pasid_iotlb, &piotlb_info);
+    vtd_iommu_unlock(s);
+    g_free(stage1_cache);
 }
 
 static bool vtd_process_piotlb_desc(IntelIOMMUState *s,
diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index 17c6e84..bd241cb 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -526,6 +526,13 @@ struct VTDPASIDCacheInfo {
                                       VTD_PASID_CACHE_DEVSI)
 typedef struct VTDPASIDCacheInfo VTDPASIDCacheInfo;
 
+struct VTDPIOTLBInvInfo {
+    uint16_t domain_id;
+    uint32_t pasid;
+    DualIOMMUStage1Cache *stage1_cache;
+};
+typedef struct VTDPIOTLBInvInfo VTDPIOTLBInvInfo;
+
 /* Masks for struct VTDRootEntry */
 #define VTD_ROOT_ENTRY_P            1ULL
 #define VTD_ROOT_ENTRY_CTP          (~0xfffULL)
-- 
2.7.4



  parent reply	other threads:[~2020-02-22  8:13 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-02-22  8:07 [RFC v3.1 00/22] intel_iommu: expose Shared Virtual Addressing to VMs Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 01/22] scripts/update-linux-headers: Import iommu.h Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 02/22] header file update VFIO/IOMMU vSVA APIs Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 03/22] vfio: check VFIO_TYPE1_NESTING_IOMMU support Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 04/22] hw/iommu: introduce HostIOMMUContext Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 05/22] hw/pci: add pci_device_setup_iommu Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 06/22] vfio/pci: init HostIOMMUContext per-container Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 07/22] vfio: get nesting iommu cap info from Kernel Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 08/22] vfio/common: add pasid_alloc/free support Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 09/22] hw/pci: add pci_device_host_iommu_context() Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 10/22] intel_iommu: add virtual command capability support Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 11/22] intel_iommu: process pasid cache invalidation Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 12/22] intel_iommu: add PASID cache management infrastructure Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 13/22] vfio: add bind stage-1 page table support Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 14/22] intel_iommu: bind/unbind guest page table to host Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 15/22] intel_iommu: replay guest pasid bindings " Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 16/22] intel_iommu: replay pasid binds after context cache invalidation Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 17/22] intel_iommu: do not pass down pasid bind for PASID #0 Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 18/22] vfio/common: add support for flush iommu stage-1 cache Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 19/22] intel_iommu: process PASID-based iotlb invalidation Liu Yi L
2020-02-22  8:07 ` Liu Yi L [this message]
2020-02-22  8:07 ` [RFC v3.1 21/22] intel_iommu: process PASID-based Device-TLB invalidation Liu Yi L
2020-02-22  8:07 ` [RFC v3.1 22/22] intel_iommu: modify x-scalable-mode to be string option Liu Yi L
2020-02-22  8:21 ` [RFC v3.1 00/22] intel_iommu: expose Shared Virtual Addressing to VMs no-reply

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=1582358843-51931-21-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=ehabkost@redhat.com \
    --cc=eric.auger@redhat.com \
    --cc=jacob.jun.pan@linux.intel.com \
    --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=rth@twiddle.net \
    --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).