[PATCH v1 3/6] intel_iommu: Add a framework to check and sync host IOMMU cap/ecap

From: Zhenzhong Duan <zhenzhong.duan@intel.com>
To: qemu-devel@nongnu.org
Cc: alex.williamson@redhat.com, clg@redhat.com,
	eric.auger@redhat.com, peterx@redhat.com, jasowang@redhat.com,
	mst@redhat.com, jgg@nvidia.com, nicolinc@nvidia.com,
	joao.m.martins@oracle.com, kevin.tian@intel.com,
	yi.l.liu@intel.com, yi.y.sun@intel.com, chao.p.peng@intel.com,
	Yi Sun <yi.y.sun@linux.intel.com>,
	Zhenzhong Duan <zhenzhong.duan@intel.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Richard Henderson <richard.henderson@linaro.org>,
	Eduardo Habkost <eduardo@habkost.net>,
	Marcel Apfelbaum <marcel.apfelbaum@gmail.com>
Subject: [PATCH v1 3/6] intel_iommu: Add a framework to check and sync host IOMMU cap/ecap
Date: Wed, 28 Feb 2024 17:44:29 +0800	[thread overview]
Message-ID: <20240228094432.1092748-4-zhenzhong.duan@intel.com> (raw)
In-Reply-To: <20240228094432.1092748-1-zhenzhong.duan@intel.com>

From: Yi Liu <yi.l.liu@intel.com>

Add a framework to check and synchronize host IOMMU cap/ecap with
vIOMMU cap/ecap.

The sequence will be:

vtd_cap_init() initializes iommu->cap/ecap.
vtd_check_hdev() update iommu->cap/ecap based on host cap/ecap.
iommu->cap_frozen set when machine create done, iommu->cap/ecap become readonly.

Implementation details for different backends will be in following patches.

Signed-off-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
Signed-off-by: Zhenzhong Duan <zhenzhong.duan@intel.com>
---
 include/hw/i386/intel_iommu.h |  1 +
 hw/i386/intel_iommu.c         | 50 ++++++++++++++++++++++++++++++++++-
 2 files changed, 50 insertions(+), 1 deletion(-)

diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index bbc7b96add..c71a133820 100644
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -283,6 +283,7 @@ struct IntelIOMMUState {
 
     uint64_t cap;                   /* The value of capability reg */
     uint64_t ecap;                  /* The value of extended capability reg */
+    bool cap_frozen;                /* cap/ecap become read-only after frozen */
 
     uint32_t context_cache_gen;     /* Should be in [1,MAX] */
     GHashTable *iotlb;              /* IOTLB */
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index ffa1ad6429..a9f9dfd6a7 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -35,6 +35,8 @@
 #include "sysemu/kvm.h"
 #include "sysemu/dma.h"
 #include "sysemu/sysemu.h"
+#include "hw/vfio/vfio-common.h"
+#include "sysemu/iommufd.h"
 #include "hw/i386/apic_internal.h"
 #include "kvm/kvm_i386.h"
 #include "migration/vmstate.h"
@@ -3819,6 +3821,38 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus,
     return vtd_dev_as;
 }
 
+static int vtd_check_legacy_hdev(IntelIOMMUState *s,
+                                 IOMMULegacyDevice *ldev,
+                                 Error **errp)
+{
+    return 0;
+}
+
+static int vtd_check_iommufd_hdev(IntelIOMMUState *s,
+                                  IOMMUFDDevice *idev,
+                                  Error **errp)
+{
+    return 0;
+}
+
+static int vtd_check_hdev(IntelIOMMUState *s, VTDHostIOMMUDevice *vtd_hdev,
+                          Error **errp)
+{
+    HostIOMMUDevice *base_dev = vtd_hdev->dev;
+    IOMMUFDDevice *idev;
+
+    if (base_dev->type == HID_LEGACY) {
+        IOMMULegacyDevice *ldev = container_of(base_dev,
+                                               IOMMULegacyDevice, base);
+
+        return vtd_check_legacy_hdev(s, ldev, errp);
+    }
+
+    idev = container_of(base_dev, IOMMUFDDevice, base);
+
+    return vtd_check_iommufd_hdev(s, idev, errp);
+}
+
 static int vtd_dev_set_iommu_device(PCIBus *bus, void *opaque, int devfn,
                                     HostIOMMUDevice *base_dev, Error **errp)
 {
@@ -3829,6 +3863,7 @@ static int vtd_dev_set_iommu_device(PCIBus *bus, void *opaque, int devfn,
         .devfn = devfn,
     };
     struct vtd_as_key *new_key;
+    int ret;
 
     assert(base_dev);
 
@@ -3848,6 +3883,13 @@ static int vtd_dev_set_iommu_device(PCIBus *bus, void *opaque, int devfn,
     vtd_hdev->iommu_state = s;
     vtd_hdev->dev = base_dev;
 
+    ret = vtd_check_hdev(s, vtd_hdev, errp);
+    if (ret) {
+        g_free(vtd_hdev);
+        vtd_iommu_unlock(s);
+        return ret;
+    }
+
     new_key = g_malloc(sizeof(*new_key));
     new_key->bus = bus;
     new_key->devfn = devfn;
@@ -4083,7 +4125,9 @@ static void vtd_init(IntelIOMMUState *s)
     s->iq_dw = false;
     s->next_frcd_reg = 0;
 
-    vtd_cap_init(s);
+    if (!s->cap_frozen) {
+        vtd_cap_init(s);
+    }
 
     /*
      * Rsvd field masks for spte
@@ -4254,6 +4298,10 @@ static int vtd_machine_done_notify_one(Object *child, void *unused)
 
 static void vtd_machine_done_hook(Notifier *notifier, void *unused)
 {
+    IntelIOMMUState *iommu = INTEL_IOMMU_DEVICE(x86_iommu_get_default());
+
+    iommu->cap_frozen = true;
+
     object_child_foreach_recursive(object_get_root(),
                                    vtd_machine_done_notify_one, NULL);
 }
-- 
2.34.1


