diff mbox series

[2/6] hw/acpi: Add VIOT table

Message ID 20210810084505.2257983-3-jean-philippe@linaro.org
State New
Headers show
Series virtio-iommu: Add ACPI support | expand

Commit Message

Jean-Philippe Brucker Aug. 10, 2021, 8:45 a.m. UTC 
Add a function that generates a Virtual I/O Translation table (VIOT),
describing the topology of paravirtual IOMMUs. The table is created when
instantiating a virtio-iommu device. It contains a virtio-iommu node and
PCI Range nodes for endpoints managed by the IOMMU. By default, a single
node describes all PCI devices. When passing the "default_bus_bypass_iommu"
machine option and "bypass_iommu" PXB option, only buses that do not
bypass the IOMMU are described by PCI Range nodes.

Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>

---
 hw/acpi/viot.h      | 13 +++++++
 hw/acpi/viot.c      | 82 +++++++++++++++++++++++++++++++++++++++++++++
 hw/acpi/Kconfig     |  4 +++
 hw/acpi/meson.build |  1 +
 4 files changed, 100 insertions(+)
 create mode 100644 hw/acpi/viot.h
 create mode 100644 hw/acpi/viot.c

-- 
2.32.0

Comments

Igor Mammedov Aug. 10, 2021, 9:22 a.m. UTC | #1 
On Tue, 10 Aug 2021 10:45:02 +0200
Jean-Philippe Brucker <jean-philippe@linaro.org> wrote:

> Add a function that generates a Virtual I/O Translation table (VIOT),

> describing the topology of paravirtual IOMMUs. The table is created when

> instantiating a virtio-iommu device. It contains a virtio-iommu node and

> PCI Range nodes for endpoints managed by the IOMMU. By default, a single

> node describes all PCI devices. When passing the "default_bus_bypass_iommu"

> machine option and "bypass_iommu" PXB option, only buses that do not

> bypass the IOMMU are described by PCI Range nodes.

> 

> Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>



using packed structures for composing ACPI tables is discouraged,
pls use build_append_int_noprefix() API instead. You can look at
build_amd_iommu() as an example.

PS:
Also note field comments format.
/it should be verbatim copy of entry name from respective table in spec/


> ---

>  hw/acpi/viot.h      | 13 +++++++

>  hw/acpi/viot.c      | 82 +++++++++++++++++++++++++++++++++++++++++++++

>  hw/acpi/Kconfig     |  4 +++

>  hw/acpi/meson.build |  1 +

>  4 files changed, 100 insertions(+)

>  create mode 100644 hw/acpi/viot.h

>  create mode 100644 hw/acpi/viot.c

> 

> diff --git a/hw/acpi/viot.h b/hw/acpi/viot.h

> new file mode 100644

> index 0000000000..4cef29a640

> --- /dev/null

> +++ b/hw/acpi/viot.h

> @@ -0,0 +1,13 @@

> +/*

> + * ACPI Virtual I/O Translation Table implementation

> + *

> + * SPDX-License-Identifier: GPL-2.0-or-later

> + */

> +#ifndef VIOT_H

> +#define VIOT_H

> +

> +void build_viot(GArray *table_data, BIOSLinker *linker,

> +                uint16_t virtio_iommu_bdf, const char *oem_id,

> +                const char *oem_table_id);

> +

> +#endif /* VIOT_H */

> diff --git a/hw/acpi/viot.c b/hw/acpi/viot.c

> new file mode 100644

> index 0000000000..5cd10e9553

> --- /dev/null

> +++ b/hw/acpi/viot.c

> @@ -0,0 +1,82 @@

> +/*

> + * ACPI Virtual I/O Translation table implementation

> + *

> + * SPDX-License-Identifier: GPL-2.0-or-later

> + */

> +#include "qemu/osdep.h"

> +#include "hw/acpi/acpi.h"

> +#include "hw/acpi/aml-build.h"

> +#include "hw/acpi/viot.h"

> +#include "hw/pci/pci.h"

> +#include "hw/pci/pci_host.h"

> +

> +/* Build PCI range for a given PCI host bridge */

> +static int viot_host_bridges(Object *obj, void *opaque)

> +{

> +    GArray *pci_range_blob = opaque;

> +

> +    if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) {

> +        PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus;

> +

> +        if (bus && !pci_bus_bypass_iommu(bus)) {

> +            int min_bus, max_bus;

> +

> +            pci_bus_range(bus, &min_bus, &max_bus);

> +

> +            AcpiViotPciRange pci_range = {

> +                .type = ACPI_VIOT_NODE_PCI_RANGE,

> +                .length = cpu_to_le16(sizeof(pci_range)),

> +                .bdf_start = cpu_to_le16(PCI_BUILD_BDF(min_bus, 0)),

> +                .bdf_end = cpu_to_le16(PCI_BUILD_BDF(max_bus, 0xff)),

> +                .endpoint_start = cpu_to_le32(PCI_BUILD_BDF(min_bus, 0)),

> +            };

> +

> +            g_array_append_val(pci_range_blob, pci_range);

> +        }

> +    }

> +

> +    return 0;

> +}

> +

> +/*

> + * Generate a VIOT table with one PCI-based virtio-iommu that manages PCI

> + * endpoints.

> + */

> +void build_viot(GArray *table_data, BIOSLinker *linker,

> +                uint16_t virtio_iommu_bdf, const char *oem_id,

> +                const char *oem_table_id)

> +{

> +    int i;

> +    AcpiViot *viot;

> +    AcpiViotPciRange *pci_range;

> +    AcpiViotVirtioIommuPci *viommu;

> +    int viommu_off = sizeof(*viot);

> +    int viot_start = table_data->len;

> +    GArray *pci_ranges = g_array_new(false, true, sizeof(*pci_range));

> +

> +    viot = acpi_data_push(table_data, sizeof(*viot));

> +    viot->node_offset = cpu_to_le16(viommu_off);

> +

> +    viommu = acpi_data_push(table_data, sizeof(*viommu));

> +    viommu->type = ACPI_VIOT_NODE_VIRTIO_IOMMU_PCI;

> +    viommu->length = cpu_to_le16(sizeof(*viommu));

> +    viommu->bdf = cpu_to_le16(virtio_iommu_bdf);

> +

> +    /* Build the list of PCI ranges that this viommu manages */

> +    object_child_foreach_recursive(object_get_root(), viot_host_bridges,

> +                                   pci_ranges);

> +

> +    for (i = 0; i < pci_ranges->len; i++) {

> +        pci_range = &g_array_index(pci_ranges, AcpiViotPciRange, i);

> +        pci_range->output_node = cpu_to_le16(viommu_off);

> +    }

> +    viot->node_count = cpu_to_le16(pci_ranges->len + 1);

> +

> +    g_array_append_vals(table_data, pci_ranges->data,

> +                        pci_ranges->len * sizeof(*pci_range));

> +    g_array_free(pci_ranges, true);

> +

> +    build_header(linker, table_data, (void *)(table_data->data + viot_start),

> +                 "VIOT", table_data->len - viot_start, 0, oem_id, oem_table_id);

> +}

> +

> diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig

> index cfc4ede8d9..abad79c103 100644

> --- a/hw/acpi/Kconfig

> +++ b/hw/acpi/Kconfig

> @@ -41,6 +41,10 @@ config ACPI_VMGENID

>      default y

>      depends on PC

>  

> +config ACPI_VIOT

> +    bool

> +    depends on ACPI

> +

>  config ACPI_HW_REDUCED

>      bool

>      select ACPI

> diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build

> index 29f804d13e..a510988b27 100644

> --- a/hw/acpi/meson.build

> +++ b/hw/acpi/meson.build

> @@ -16,6 +16,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device

>  acpi_ss.add(when: 'CONFIG_ACPI_HMAT', if_true: files('hmat.c'))

>  acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files('ghes-stub.c'))

>  acpi_ss.add(when: 'CONFIG_ACPI_X86', if_true: files('piix4.c', 'pcihp.c'))

> +acpi_ss.add(when: 'CONFIG_ACPI_VIOT', if_true: files('viot.c'))

>  acpi_ss.add(when: 'CONFIG_ACPI_X86_ICH', if_true: files('ich9.c', 'tco.c'))

>  acpi_ss.add(when: 'CONFIG_IPMI', if_true: files('ipmi.c'), if_false: files('ipmi-stub.c'))

>  acpi_ss.add(when: 'CONFIG_PC', if_false: files('acpi-x86-stub.c'))
Jean-Philippe Brucker Aug. 27, 2021, 1:29 p.m. UTC | #2 
On Tue, Aug 10, 2021 at 11:22:27AM +0200, Igor Mammedov wrote:
> On Tue, 10 Aug 2021 10:45:02 +0200

> Jean-Philippe Brucker <jean-philippe@linaro.org> wrote:

> 

> > Add a function that generates a Virtual I/O Translation table (VIOT),

> > describing the topology of paravirtual IOMMUs. The table is created when

> > instantiating a virtio-iommu device. It contains a virtio-iommu node and

> > PCI Range nodes for endpoints managed by the IOMMU. By default, a single

> > node describes all PCI devices. When passing the "default_bus_bypass_iommu"

> > machine option and "bypass_iommu" PXB option, only buses that do not

> > bypass the IOMMU are described by PCI Range nodes.

> > 

> > Signed-off-by: Jean-Philippe Brucker <jean-philippe@linaro.org>

> 

> 

> using packed structures for composing ACPI tables is discouraged,

> pls use build_append_int_noprefix() API instead. You can look at

> build_amd_iommu() as an example.

> 

> PS:

> Also note field comments format.

> /it should be verbatim copy of entry name from respective table in spec/


Got it, I'll switch to build_append_int_noprefix()

Thanks,
Jean
diff mbox series

Patch

diff --git a/hw/acpi/viot.h b/hw/acpi/viot.h
new file mode 100644
index 0000000000..4cef29a640
--- /dev/null
+++ b/hw/acpi/viot.h
@@ -0,0 +1,13 @@ 
+/*
+ * ACPI Virtual I/O Translation Table implementation
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#ifndef VIOT_H
+#define VIOT_H
+
+void build_viot(GArray *table_data, BIOSLinker *linker,
+                uint16_t virtio_iommu_bdf, const char *oem_id,
+                const char *oem_table_id);
+
+#endif /* VIOT_H */
diff --git a/hw/acpi/viot.c b/hw/acpi/viot.c
new file mode 100644
index 0000000000..5cd10e9553
--- /dev/null
+++ b/hw/acpi/viot.c
@@ -0,0 +1,82 @@ 
+/*
+ * ACPI Virtual I/O Translation table implementation
+ *
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ */
+#include "qemu/osdep.h"
+#include "hw/acpi/acpi.h"
+#include "hw/acpi/aml-build.h"
+#include "hw/acpi/viot.h"
+#include "hw/pci/pci.h"
+#include "hw/pci/pci_host.h"
+
+/* Build PCI range for a given PCI host bridge */
+static int viot_host_bridges(Object *obj, void *opaque)
+{
+    GArray *pci_range_blob = opaque;
+
+    if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) {
+        PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus;
+
+        if (bus && !pci_bus_bypass_iommu(bus)) {
+            int min_bus, max_bus;
+
+            pci_bus_range(bus, &min_bus, &max_bus);
+
+            AcpiViotPciRange pci_range = {
+                .type = ACPI_VIOT_NODE_PCI_RANGE,
+                .length = cpu_to_le16(sizeof(pci_range)),
+                .bdf_start = cpu_to_le16(PCI_BUILD_BDF(min_bus, 0)),
+                .bdf_end = cpu_to_le16(PCI_BUILD_BDF(max_bus, 0xff)),
+                .endpoint_start = cpu_to_le32(PCI_BUILD_BDF(min_bus, 0)),
+            };
+
+            g_array_append_val(pci_range_blob, pci_range);
+        }
+    }
+
+    return 0;
+}
+
+/*
+ * Generate a VIOT table with one PCI-based virtio-iommu that manages PCI
+ * endpoints.
+ */
+void build_viot(GArray *table_data, BIOSLinker *linker,
+                uint16_t virtio_iommu_bdf, const char *oem_id,
+                const char *oem_table_id)
+{
+    int i;
+    AcpiViot *viot;
+    AcpiViotPciRange *pci_range;
+    AcpiViotVirtioIommuPci *viommu;
+    int viommu_off = sizeof(*viot);
+    int viot_start = table_data->len;
+    GArray *pci_ranges = g_array_new(false, true, sizeof(*pci_range));
+
+    viot = acpi_data_push(table_data, sizeof(*viot));
+    viot->node_offset = cpu_to_le16(viommu_off);
+
+    viommu = acpi_data_push(table_data, sizeof(*viommu));
+    viommu->type = ACPI_VIOT_NODE_VIRTIO_IOMMU_PCI;
+    viommu->length = cpu_to_le16(sizeof(*viommu));
+    viommu->bdf = cpu_to_le16(virtio_iommu_bdf);
+
+    /* Build the list of PCI ranges that this viommu manages */
+    object_child_foreach_recursive(object_get_root(), viot_host_bridges,
+                                   pci_ranges);
+
+    for (i = 0; i < pci_ranges->len; i++) {
+        pci_range = &g_array_index(pci_ranges, AcpiViotPciRange, i);
+        pci_range->output_node = cpu_to_le16(viommu_off);
+    }
+    viot->node_count = cpu_to_le16(pci_ranges->len + 1);
+
+    g_array_append_vals(table_data, pci_ranges->data,
+                        pci_ranges->len * sizeof(*pci_range));
+    g_array_free(pci_ranges, true);
+
+    build_header(linker, table_data, (void *)(table_data->data + viot_start),
+                 "VIOT", table_data->len - viot_start, 0, oem_id, oem_table_id);
+}
+
diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig
index cfc4ede8d9..abad79c103 100644
--- a/hw/acpi/Kconfig
+++ b/hw/acpi/Kconfig
@@ -41,6 +41,10 @@  config ACPI_VMGENID
     default y
     depends on PC
 
+config ACPI_VIOT
+    bool
+    depends on ACPI
+
 config ACPI_HW_REDUCED
     bool
     select ACPI
diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build
index 29f804d13e..a510988b27 100644
--- a/hw/acpi/meson.build
+++ b/hw/acpi/meson.build
@@ -16,6 +16,7 @@  acpi_ss.add(when: 'CONFIG_ACPI_HW_REDUCED', if_true: files('generic_event_device
 acpi_ss.add(when: 'CONFIG_ACPI_HMAT', if_true: files('hmat.c'))
 acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files('ghes-stub.c'))
 acpi_ss.add(when: 'CONFIG_ACPI_X86', if_true: files('piix4.c', 'pcihp.c'))
+acpi_ss.add(when: 'CONFIG_ACPI_VIOT', if_true: files('viot.c'))
 acpi_ss.add(when: 'CONFIG_ACPI_X86_ICH', if_true: files('ich9.c', 'tco.c'))
 acpi_ss.add(when: 'CONFIG_IPMI', if_true: files('ipmi.c'), if_false: files('ipmi-stub.c'))
 acpi_ss.add(when: 'CONFIG_PC', if_false: files('acpi-x86-stub.c'))