diff mbox series

[v3,05/10] pc: Allow instantiating a virtio-iommu device

Message ID 20210914142004.2433568-6-jean-philippe@linaro.org (mailing list archive)
State New, archived
Headers show
Series virtio-iommu: Add ACPI support | expand

Commit Message

Jean-Philippe Brucker Sept. 14, 2021, 2:20 p.m. UTC 
Allow instantiating a virtio-iommu device by adding an ACPI Virtual I/O
Translation table (VIOT), which describes the relation between the
virtio-iommu and the endpoints it manages.

Add a hotplug handler for virtio-iommu on x86 and set the necessary
reserved region property. On x86, the [0xfee00000, 0xfeefffff] DMA
region is reserved for MSIs. DMA transactions to this range either
trigger IRQ remapping in the IOMMU or bypasses IOMMU translation.

Although virtio-iommu does not support IRQ remapping it must be informed
of the reserved region so that it can forward DMA transactions targeting
this region.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
---
 include/hw/i386/pc.h |  2 ++
 hw/i386/acpi-build.c |  5 +++++
 hw/i386/pc.c         | 28 +++++++++++++++++++++++++++-
 hw/i386/Kconfig      |  1 +
 4 files changed, 35 insertions(+), 1 deletion(-)

Comments

Igor Mammedov Sept. 20, 2021, 8:24 a.m. UTC | #1 
On Tue, 14 Sep 2021 15:20:00 +0100
Jean-Philippe Brucker <jean-philippe@linaro.org> wrote:

> Allow instantiating a virtio-iommu device by adding an ACPI Virtual I/O
> Translation table (VIOT), which describes the relation between the
> virtio-iommu and the endpoints it manages.
> 
> Add a hotplug handler for virtio-iommu on x86 and set the necessary
> reserved region property. On x86, the [0xfee00000, 0xfeefffff] DMA
> region is reserved for MSIs. DMA transactions to this range either
> trigger IRQ remapping in the IOMMU or bypasses IOMMU translation.
> 
> Although virtio-iommu does not support IRQ remapping it must be informed
> of the reserved region so that it can forward DMA transactions targeting
> this region.
> 
> Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>
> ---
>  include/hw/i386/pc.h |  2 ++
>  hw/i386/acpi-build.c |  5 +++++
>  hw/i386/pc.c         | 28 +++++++++++++++++++++++++++-
>  hw/i386/Kconfig      |  1 +
>  4 files changed, 35 insertions(+), 1 deletion(-)
> 
> diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
> index 82cf7b7e30..f3ba1ee4c0 100644
> --- a/include/hw/i386/pc.h
> +++ b/include/hw/i386/pc.h
> @@ -45,6 +45,8 @@ typedef struct PCMachineState {
>      bool pit_enabled;
>      bool hpet_enabled;
>      bool default_bus_bypass_iommu;
> +    bool virtio_iommu;
> +    uint16_t virtio_iommu_bdf;
>      uint64_t max_fw_size;
>  
>      /* ACPI Memory hotplug IO base address */
> diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
> index 547cd4ed9d..76845026d8 100644
> --- a/hw/i386/acpi-build.c
> +++ b/hw/i386/acpi-build.c
> @@ -71,6 +71,7 @@
>  
>  #include "hw/acpi/ipmi.h"
>  #include "hw/acpi/hmat.h"
> +#include "hw/acpi/viot.h"
>  
>  /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and
>   * -M pc-i440fx-2.0.  Even if the actual amount of AML generated grows
> @@ -2593,6 +2594,10 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine)
>              build_dmar_q35(tables_blob, tables->linker, x86ms->oem_id,
>                             x86ms->oem_table_id);
>          }
> +    } else if (pcms->virtio_iommu) {
> +        acpi_add_table(table_offsets, tables_blob);
> +        build_viot(tables_blob, tables->linker, pcms->virtio_iommu_bdf,
> +                   x86ms->oem_id, x86ms->oem_table_id);
>      }
>      if (machine->nvdimms_state->is_enabled) {
>          nvdimm_build_acpi(table_offsets, tables_blob, tables->linker,
> diff --git a/hw/i386/pc.c b/hw/i386/pc.c
> index 7e523b913c..a31e950599 100644
> --- a/hw/i386/pc.c
> +++ b/hw/i386/pc.c
> @@ -83,6 +83,7 @@
>  #include "hw/i386/intel_iommu.h"
>  #include "hw/net/ne2000-isa.h"
>  #include "standard-headers/asm-x86/bootparam.h"
> +#include "hw/virtio/virtio-iommu.h"
>  #include "hw/virtio/virtio-pmem-pci.h"
>  #include "hw/virtio/virtio-mem-pci.h"
>  #include "hw/mem/memory-device.h"
> @@ -798,6 +799,11 @@ void pc_machine_done(Notifier *notifier, void *data)
>                       "irqchip support.");
>          exit(EXIT_FAILURE);
>      }
> +
> +    if (pcms->virtio_iommu && x86_iommu_get_default()) {
> +        error_report("QEMU does not support multiple vIOMMUs for x86 yet.");
> +        exit(EXIT_FAILURE);
> +    }

previous patch does similar check, doesn't it?
So is why it's not implement the same way?

>  }
>  
>  void pc_guest_info_init(PCMachineState *pcms)
> @@ -1368,6 +1374,14 @@ static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,
>      } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
>                 object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
>          pc_virtio_md_pci_pre_plug(hotplug_dev, dev, errp);
> +    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
> +        /* Declare the reserved MSI region */
> +        char *resv_prop_str = g_strdup_printf("0xfee00000:0xfeefffff:%d",
> +                                              VIRTIO_IOMMU_RESV_MEM_T_MSI);

add a comment describing where these values come from, pls.

> +
> +        qdev_prop_set_uint32(dev, "len-reserved-regions", 1);
> +        qdev_prop_set_string(dev, "reserved-regions[0]", resv_prop_str);

why not use qom setters directly
(they have error argument and can gracefully error out,
which is expected error handling in pre_plug)

and fix up similar (ab)use of setters in virt_machine_device_pre_plug_cb()

> +        g_free(resv_prop_str);
>      }
>  }
>  
> @@ -1381,6 +1395,17 @@ static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev,
>      } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
>                 object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
>          pc_virtio_md_pci_plug(hotplug_dev, dev, errp);
> +    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
> +        PCMachineState *pcms = PC_MACHINE(hotplug_dev);
> +        PCIDevice *pdev = PCI_DEVICE(dev);
> +
> +        if (pcms->virtio_iommu) {
> +            error_setg(errp,
> +                       "QEMU does not support multiple vIOMMUs for x86 yet.");
> +            return;
> +        }

move to pre_plug please

> +        pcms->virtio_iommu = true;
> +        pcms->virtio_iommu_bdf = pci_get_bdf(pdev);
>      }
>  }
>  
> @@ -1422,7 +1447,8 @@ static HotplugHandler *pc_get_hotplug_handler(MachineState *machine,
>      if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) ||
>          object_dynamic_cast(OBJECT(dev), TYPE_CPU) ||
>          object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
> -        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
> +        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI) ||
> +        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
>          return HOTPLUG_HANDLER(machine);
>      }
>  
> diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig
> index ddedcef0b2..13db05d557 100644
> --- a/hw/i386/Kconfig
> +++ b/hw/i386/Kconfig
> @@ -54,6 +54,7 @@ config PC_ACPI
>      select ACPI_X86
>      select ACPI_CPU_HOTPLUG
>      select ACPI_MEMORY_HOTPLUG
> +    select ACPI_VIOT
>      select SMBUS_EEPROM
>      select PFLASH_CFI01
>      depends on ACPI_SMBUS
Jean-Philippe Brucker Oct. 1, 2021, 3:36 p.m. UTC | #2 
On Mon, Sep 20, 2021 at 10:24:40AM +0200, Igor Mammedov wrote:
> > +    if (pcms->virtio_iommu && x86_iommu_get_default()) {
> > +        error_report("QEMU does not support multiple vIOMMUs for x86 yet.");
> > +        exit(EXIT_FAILURE);
> > +    }
> 
> previous patch does similar check, doesn't it?
> So is why it's not implement the same way?

The existing check for Intel and AMD IOMMUs is in x86_iommu_set_default(),
but virtio-iommu isn't an X86IOMMUState (because it already inherits
virtio object, and because X86IOMMUState is used for IRQ remapping which
isn't supported by virtio-iommu).

I'll move the check from X86IOMMUState into pre_plug to avoid the
duplication.

Thanks,
Jean
diff mbox series

Patch

diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 82cf7b7e30..f3ba1ee4c0 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -45,6 +45,8 @@  typedef struct PCMachineState {
     bool pit_enabled;
     bool hpet_enabled;
     bool default_bus_bypass_iommu;
+    bool virtio_iommu;
+    uint16_t virtio_iommu_bdf;
     uint64_t max_fw_size;
 
     /* ACPI Memory hotplug IO base address */
diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index 547cd4ed9d..76845026d8 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -71,6 +71,7 @@ 
 
 #include "hw/acpi/ipmi.h"
 #include "hw/acpi/hmat.h"
+#include "hw/acpi/viot.h"
 
 /* These are used to size the ACPI tables for -M pc-i440fx-1.7 and
  * -M pc-i440fx-2.0.  Even if the actual amount of AML generated grows
@@ -2593,6 +2594,10 @@  void acpi_build(AcpiBuildTables *tables, MachineState *machine)
             build_dmar_q35(tables_blob, tables->linker, x86ms->oem_id,
                            x86ms->oem_table_id);
         }
+    } else if (pcms->virtio_iommu) {
+        acpi_add_table(table_offsets, tables_blob);
+        build_viot(tables_blob, tables->linker, pcms->virtio_iommu_bdf,
+                   x86ms->oem_id, x86ms->oem_table_id);
     }
     if (machine->nvdimms_state->is_enabled) {
         nvdimm_build_acpi(table_offsets, tables_blob, tables->linker,
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 7e523b913c..a31e950599 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -83,6 +83,7 @@ 
 #include "hw/i386/intel_iommu.h"
 #include "hw/net/ne2000-isa.h"
 #include "standard-headers/asm-x86/bootparam.h"
+#include "hw/virtio/virtio-iommu.h"
 #include "hw/virtio/virtio-pmem-pci.h"
 #include "hw/virtio/virtio-mem-pci.h"
 #include "hw/mem/memory-device.h"
@@ -798,6 +799,11 @@  void pc_machine_done(Notifier *notifier, void *data)
                      "irqchip support.");
         exit(EXIT_FAILURE);
     }
+
+    if (pcms->virtio_iommu && x86_iommu_get_default()) {
+        error_report("QEMU does not support multiple vIOMMUs for x86 yet.");
+        exit(EXIT_FAILURE);
+    }
 }
 
 void pc_guest_info_init(PCMachineState *pcms)
@@ -1368,6 +1374,14 @@  static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
                object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
         pc_virtio_md_pci_pre_plug(hotplug_dev, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
+        /* Declare the reserved MSI region */
+        char *resv_prop_str = g_strdup_printf("0xfee00000:0xfeefffff:%d",
+                                              VIRTIO_IOMMU_RESV_MEM_T_MSI);
+
+        qdev_prop_set_uint32(dev, "len-reserved-regions", 1);
+        qdev_prop_set_string(dev, "reserved-regions[0]", resv_prop_str);
+        g_free(resv_prop_str);
     }
 }
 
@@ -1381,6 +1395,17 @@  static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev,
     } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
                object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
         pc_virtio_md_pci_plug(hotplug_dev, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
+        PCMachineState *pcms = PC_MACHINE(hotplug_dev);
+        PCIDevice *pdev = PCI_DEVICE(dev);
+
+        if (pcms->virtio_iommu) {
+            error_setg(errp,
+                       "QEMU does not support multiple vIOMMUs for x86 yet.");
+            return;
+        }
+        pcms->virtio_iommu = true;
+        pcms->virtio_iommu_bdf = pci_get_bdf(pdev);
     }
 }
 
@@ -1422,7 +1447,8 @@  static HotplugHandler *pc_get_hotplug_handler(MachineState *machine,
     if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) ||
         object_dynamic_cast(OBJECT(dev), TYPE_CPU) ||
         object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) ||
-        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) {
+        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI) ||
+        object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
         return HOTPLUG_HANDLER(machine);
     }
 
diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig
index ddedcef0b2..13db05d557 100644
--- a/hw/i386/Kconfig
+++ b/hw/i386/Kconfig
@@ -54,6 +54,7 @@  config PC_ACPI
     select ACPI_X86
     select ACPI_CPU_HOTPLUG
     select ACPI_MEMORY_HOTPLUG
+    select ACPI_VIOT
     select SMBUS_EEPROM
     select PFLASH_CFI01
     depends on ACPI_SMBUS