[PATCH rfcv2 11/18] intel_iommu: Add set/unset_iommu_device callback

Zhenzhong Duan posted 18 patches 9 months, 4 weeks ago
Maintainers: Yi Liu <yi.l.liu@intel.com>, Eric Auger <eric.auger@redhat.com>, Zhenzhong Duan <zhenzhong.duan@intel.com>, "Michael S. Tsirkin" <mst@redhat.com>, Igor Mammedov <imammedo@redhat.com>, Ani Sinha <anisinha@redhat.com>, Paolo Bonzini <pbonzini@redhat.com>, Richard Henderson <richard.henderson@linaro.org>, Eduardo Habkost <eduardo@habkost.net>, Marcel Apfelbaum <marcel.apfelbaum@gmail.com>, Peter Xu <peterx@redhat.com>, Jason Wang <jasowang@redhat.com>, Thomas Huth <thuth@redhat.com>, Alex Williamson <alex.williamson@redhat.com>, "Cédric Le Goater" <clg@redhat.com>, Tony Krowiak <akrowiak@linux.ibm.com>, Halil Pasic <pasic@linux.ibm.com>, Jason Herne <jjherne@linux.ibm.com>, Eric Farman <farman@linux.ibm.com>, Matthew Rosato <mjrosato@linux.ibm.com>
There is a newer version of this series
[PATCH rfcv2 11/18] intel_iommu: Add set/unset_iommu_device callback
Posted by Zhenzhong Duan 9 months, 4 weeks ago
From: Yi Liu <yi.l.liu@intel.com>

This adds set/unset_iommu_device() implementation in Intel vIOMMU.
In set call, a pointer to host IOMMU device info is stored in hash
table indexed by PCI BDF.

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>
---
 hw/i386/intel_iommu_internal.h | 14 +++++++
 include/hw/i386/intel_iommu.h  |  2 +
 hw/i386/intel_iommu.c          | 74 ++++++++++++++++++++++++++++++++++
 3 files changed, 90 insertions(+)

diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
index f8cf99bddf..3301f54b35 100644
--- a/hw/i386/intel_iommu_internal.h
+++ b/hw/i386/intel_iommu_internal.h
@@ -28,6 +28,8 @@
 #ifndef HW_I386_INTEL_IOMMU_INTERNAL_H
 #define HW_I386_INTEL_IOMMU_INTERNAL_H
 #include "hw/i386/intel_iommu.h"
+#include "sysemu/host_iommu_device.h"
+#include "hw/vfio/vfio-common.h"
 
 /*
  * Intel IOMMU register specification
@@ -537,4 +539,16 @@ typedef struct VTDRootEntry VTDRootEntry;
 #define VTD_SL_IGN_COM              0xbff0000000000000ULL
 #define VTD_SL_TM                   (1ULL << 62)
 
+
+typedef struct VTDHostIOMMUDevice {
+    IntelIOMMUState *iommu_state;
+    PCIBus *bus;
+    uint8_t devfn;
+    union {
+        HostIOMMUDevice *dev;
+        IOMMULegacyDevice *ldev;
+        IOMMUFDDevice *idev;
+    };
+    QLIST_ENTRY(VTDHostIOMMUDevice) next;
+} VTDHostIOMMUDevice;
 #endif
diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
index 7fa0a695c8..bbc7b96add 100644
--- a/include/hw/i386/intel_iommu.h
+++ b/include/hw/i386/intel_iommu.h
@@ -292,6 +292,8 @@ struct IntelIOMMUState {
     /* list of registered notifiers */
     QLIST_HEAD(, VTDAddressSpace) vtd_as_with_notifiers;
 
+    GHashTable *vtd_host_iommu_dev;             /* VTDHostIOMMUDevice */
+
     /* interrupt remapping */
     bool intr_enabled;              /* Whether guest enabled IR */
     dma_addr_t intr_root;           /* Interrupt remapping table pointer */
diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
index 1a07faddb4..9b62441439 100644
--- a/hw/i386/intel_iommu.c
+++ b/hw/i386/intel_iommu.c
@@ -237,6 +237,13 @@ static gboolean vtd_as_equal(gconstpointer v1, gconstpointer v2)
            (key1->pasid == key2->pasid);
 }
 
+static gboolean vtd_as_idev_equal(gconstpointer v1, gconstpointer v2)
+{
+    const struct vtd_as_key *key1 = v1;
+    const struct vtd_as_key *key2 = v2;
+
+    return (key1->bus == key2->bus) && (key1->devfn == key2->devfn);
+}
 /*
  * Note that we use pointer to PCIBus as the key, so hashing/shifting
  * based on the pointer value is intended. Note that we deal with
@@ -3812,6 +3819,68 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus,
     return vtd_dev_as;
 }
 
+static int vtd_dev_set_iommu_device(PCIBus *bus, void *opaque, int devfn,
+                                    HostIOMMUDevice *base_dev, Error **errp)
+{
+    IntelIOMMUState *s = opaque;
+    VTDHostIOMMUDevice *vtd_hdev;
+    struct vtd_as_key key = {
+        .bus = bus,
+        .devfn = devfn,
+    };
+    struct vtd_as_key *new_key;
+
+    assert(base_dev);
+
+    vtd_iommu_lock(s);
+
+    vtd_hdev = g_hash_table_lookup(s->vtd_host_iommu_dev, &key);
+
+    if (vtd_hdev) {
+        error_setg(errp, "IOMMUFD device already exist");
+        vtd_iommu_unlock(s);
+        return -EEXIST;
+    }
+
+    vtd_hdev = g_malloc0(sizeof(VTDHostIOMMUDevice));
+    vtd_hdev->bus = bus;
+    vtd_hdev->devfn = (uint8_t)devfn;
+    vtd_hdev->iommu_state = s;
+    vtd_hdev->dev = base_dev;
+
+    new_key = g_malloc(sizeof(*new_key));
+    new_key->bus = bus;
+    new_key->devfn = devfn;
+
+    g_hash_table_insert(s->vtd_host_iommu_dev, new_key, vtd_hdev);
+
+    vtd_iommu_unlock(s);
+
+    return 0;
+}
+
+static void vtd_dev_unset_iommu_device(PCIBus *bus, void *opaque, int devfn)
+{
+    IntelIOMMUState *s = opaque;
+    VTDHostIOMMUDevice *vtd_hdev;
+    struct vtd_as_key key = {
+        .bus = bus,
+        .devfn = devfn,
+    };
+
+    vtd_iommu_lock(s);
+
+    vtd_hdev = g_hash_table_lookup(s->vtd_host_iommu_dev, &key);
+    if (!vtd_hdev) {
+        vtd_iommu_unlock(s);
+        return;
+    }
+
+    g_hash_table_remove(s->vtd_host_iommu_dev, &key);
+
+    vtd_iommu_unlock(s);
+}
+
 /* Unmap the whole range in the notifier's scope. */
 static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
 {
@@ -4107,6 +4176,8 @@ static AddressSpace *vtd_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
 
 static PCIIOMMUOps vtd_iommu_ops = {
     .get_address_space = vtd_host_dma_iommu,
+    .set_iommu_device = vtd_dev_set_iommu_device,
+    .unset_iommu_device = vtd_dev_unset_iommu_device,
 };
 
 static bool vtd_decide_config(IntelIOMMUState *s, Error **errp)
@@ -4230,6 +4301,9 @@ static void vtd_realize(DeviceState *dev, Error **errp)
                                      g_free, g_free);
     s->vtd_address_spaces = g_hash_table_new_full(vtd_as_hash, vtd_as_equal,
                                       g_free, g_free);
+    s->vtd_host_iommu_dev = g_hash_table_new_full(vtd_as_hash,
+                                                  vtd_as_idev_equal,
+                                                  g_free, g_free);
     vtd_init(s);
     pci_setup_iommu(bus, &vtd_iommu_ops, dev);
     /* Pseudo address space under root PCI bus. */
-- 
2.34.1
Re: [PATCH rfcv2 11/18] intel_iommu: Add set/unset_iommu_device callback
Posted by Eric Auger 9 months, 1 week ago

On 2/1/24 08:28, Zhenzhong Duan wrote:
> From: Yi Liu <yi.l.liu@intel.com>
>
> This adds set/unset_iommu_device() implementation in Intel vIOMMU.
> In set call, a pointer to host IOMMU device info is stored in hash
> table indexed by PCI BDF.
>
> 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>
> ---
>  hw/i386/intel_iommu_internal.h | 14 +++++++
>  include/hw/i386/intel_iommu.h  |  2 +
>  hw/i386/intel_iommu.c          | 74 ++++++++++++++++++++++++++++++++++
>  3 files changed, 90 insertions(+)
>
> diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h
> index f8cf99bddf..3301f54b35 100644
> --- a/hw/i386/intel_iommu_internal.h
> +++ b/hw/i386/intel_iommu_internal.h
> @@ -28,6 +28,8 @@
>  #ifndef HW_I386_INTEL_IOMMU_INTERNAL_H
>  #define HW_I386_INTEL_IOMMU_INTERNAL_H
>  #include "hw/i386/intel_iommu.h"
> +#include "sysemu/host_iommu_device.h"
> +#include "hw/vfio/vfio-common.h"
>  
>  /*
>   * Intel IOMMU register specification
> @@ -537,4 +539,16 @@ typedef struct VTDRootEntry VTDRootEntry;
>  #define VTD_SL_IGN_COM              0xbff0000000000000ULL
>  #define VTD_SL_TM                   (1ULL << 62)
>  
> +
> +typedef struct VTDHostIOMMUDevice {
> +    IntelIOMMUState *iommu_state;
> +    PCIBus *bus;
> +    uint8_t devfn;
> +    union {
> +        HostIOMMUDevice *dev;
> +        IOMMULegacyDevice *ldev;
> +        IOMMUFDDevice *idev;
> +    };
again this looks really weird to me. Why don't we simply have

HostIOMMUDevice *dev;

> +    QLIST_ENTRY(VTDHostIOMMUDevice) next;
> +} VTDHostIOMMUDevice;
>  #endif
> diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h
> index 7fa0a695c8..bbc7b96add 100644
> --- a/include/hw/i386/intel_iommu.h
> +++ b/include/hw/i386/intel_iommu.h
> @@ -292,6 +292,8 @@ struct IntelIOMMUState {
>      /* list of registered notifiers */
>      QLIST_HEAD(, VTDAddressSpace) vtd_as_with_notifiers;
>  
> +    GHashTable *vtd_host_iommu_dev;             /* VTDHostIOMMUDevice */
> +
>      /* interrupt remapping */
>      bool intr_enabled;              /* Whether guest enabled IR */
>      dma_addr_t intr_root;           /* Interrupt remapping table pointer */
> diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c
> index 1a07faddb4..9b62441439 100644
> --- a/hw/i386/intel_iommu.c
> +++ b/hw/i386/intel_iommu.c
> @@ -237,6 +237,13 @@ static gboolean vtd_as_equal(gconstpointer v1, gconstpointer v2)
>             (key1->pasid == key2->pasid);
>  }
>  
> +static gboolean vtd_as_idev_equal(gconstpointer v1, gconstpointer v2)
> +{
> +    const struct vtd_as_key *key1 = v1;
> +    const struct vtd_as_key *key2 = v2;
> +
> +    return (key1->bus == key2->bus) && (key1->devfn == key2->devfn);
> +}
>  /*
>   * Note that we use pointer to PCIBus as the key, so hashing/shifting
>   * based on the pointer value is intended. Note that we deal with
> @@ -3812,6 +3819,68 @@ VTDAddressSpace *vtd_find_add_as(IntelIOMMUState *s, PCIBus *bus,
>      return vtd_dev_as;
>  }
>  
> +static int vtd_dev_set_iommu_device(PCIBus *bus, void *opaque, int devfn,
> +                                    HostIOMMUDevice *base_dev, Error **errp)
> +{
> +    IntelIOMMUState *s = opaque;
> +    VTDHostIOMMUDevice *vtd_hdev;
> +    struct vtd_as_key key = {
> +        .bus = bus,
> +        .devfn = devfn,
> +    };
> +    struct vtd_as_key *new_key;
> +
> +    assert(base_dev);
> +
> +    vtd_iommu_lock(s);
> +
> +    vtd_hdev = g_hash_table_lookup(s->vtd_host_iommu_dev, &key);
> +
> +    if (vtd_hdev) {
> +        error_setg(errp, "IOMMUFD device already exist");
> +        vtd_iommu_unlock(s);
> +        return -EEXIST;
> +    }
> +
> +    vtd_hdev = g_malloc0(sizeof(VTDHostIOMMUDevice));
> +    vtd_hdev->bus = bus;
> +    vtd_hdev->devfn = (uint8_t)devfn;
> +    vtd_hdev->iommu_state = s;
> +    vtd_hdev->dev = base_dev;
and here you set the base pointer.
> +
> +    new_key = g_malloc(sizeof(*new_key));
> +    new_key->bus = bus;
> +    new_key->devfn = devfn;
> +
> +    g_hash_table_insert(s->vtd_host_iommu_dev, new_key, vtd_hdev);
> +
> +    vtd_iommu_unlock(s);
> +
> +    return 0;
> +}
> +
> +static void vtd_dev_unset_iommu_device(PCIBus *bus, void *opaque, int devfn)
> +{
> +    IntelIOMMUState *s = opaque;
> +    VTDHostIOMMUDevice *vtd_hdev;
> +    struct vtd_as_key key = {
> +        .bus = bus,
> +        .devfn = devfn,
> +    };
> +
> +    vtd_iommu_lock(s);
> +
> +    vtd_hdev = g_hash_table_lookup(s->vtd_host_iommu_dev, &key);
> +    if (!vtd_hdev) {
> +        vtd_iommu_unlock(s);
> +        return;
> +    }
> +
> +    g_hash_table_remove(s->vtd_host_iommu_dev, &key);
> +
> +    vtd_iommu_unlock(s);
> +}
> +
>  /* Unmap the whole range in the notifier's scope. */
>  static void vtd_address_space_unmap(VTDAddressSpace *as, IOMMUNotifier *n)
>  {
> @@ -4107,6 +4176,8 @@ static AddressSpace *vtd_host_dma_iommu(PCIBus *bus, void *opaque, int devfn)
>  
>  static PCIIOMMUOps vtd_iommu_ops = {
>      .get_address_space = vtd_host_dma_iommu,
> +    .set_iommu_device = vtd_dev_set_iommu_device,
> +    .unset_iommu_device = vtd_dev_unset_iommu_device,
>  };
>  
>  static bool vtd_decide_config(IntelIOMMUState *s, Error **errp)
> @@ -4230,6 +4301,9 @@ static void vtd_realize(DeviceState *dev, Error **errp)
>                                       g_free, g_free);
>      s->vtd_address_spaces = g_hash_table_new_full(vtd_as_hash, vtd_as_equal,
>                                        g_free, g_free);
> +    s->vtd_host_iommu_dev = g_hash_table_new_full(vtd_as_hash,
> +                                                  vtd_as_idev_equal,
> +                                                  g_free, g_free);
>      vtd_init(s);
>      pci_setup_iommu(bus, &vtd_iommu_ops, dev);
>      /* Pseudo address space under root PCI bus. */
Eric
RE: [PATCH rfcv2 11/18] intel_iommu: Add set/unset_iommu_device callback
Posted by Duan, Zhenzhong 9 months ago

>-----Original Message-----
>From: Eric Auger <eric.auger@redhat.com>
>Subject: Re: [PATCH rfcv2 11/18] intel_iommu: Add
>set/unset_iommu_device callback
>
>
>
>On 2/1/24 08:28, Zhenzhong Duan wrote:
>> From: Yi Liu <yi.l.liu@intel.com>
>>
>> This adds set/unset_iommu_device() implementation in Intel vIOMMU.
>> In set call, a pointer to host IOMMU device info is stored in hash
>> table indexed by PCI BDF.
>>
>> 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>
>> ---
>>  hw/i386/intel_iommu_internal.h | 14 +++++++
>>  include/hw/i386/intel_iommu.h  |  2 +
>>  hw/i386/intel_iommu.c          | 74
>++++++++++++++++++++++++++++++++++
>>  3 files changed, 90 insertions(+)
>>
>> diff --git a/hw/i386/intel_iommu_internal.h
>b/hw/i386/intel_iommu_internal.h
>> index f8cf99bddf..3301f54b35 100644
>> --- a/hw/i386/intel_iommu_internal.h
>> +++ b/hw/i386/intel_iommu_internal.h
>> @@ -28,6 +28,8 @@
>>  #ifndef HW_I386_INTEL_IOMMU_INTERNAL_H
>>  #define HW_I386_INTEL_IOMMU_INTERNAL_H
>>  #include "hw/i386/intel_iommu.h"
>> +#include "sysemu/host_iommu_device.h"
>> +#include "hw/vfio/vfio-common.h"
>>
>>  /*
>>   * Intel IOMMU register specification
>> @@ -537,4 +539,16 @@ typedef struct VTDRootEntry VTDRootEntry;
>>  #define VTD_SL_IGN_COM              0xbff0000000000000ULL
>>  #define VTD_SL_TM                   (1ULL << 62)
>>
>> +
>> +typedef struct VTDHostIOMMUDevice {
>> +    IntelIOMMUState *iommu_state;
>> +    PCIBus *bus;
>> +    uint8_t devfn;
>> +    union {
>> +        HostIOMMUDevice *dev;
>> +        IOMMULegacyDevice *ldev;
>> +        IOMMUFDDevice *idev;
>> +    };
>again this looks really weird to me. Why don't we simply have
>
>HostIOMMUDevice *dev;

Sure, will do.

Thanks
Zhenzhong