| Message ID | 20210914142004.2433568-2-jean-philippe@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | virtio-iommu: Add ACPI support | expand |
Hi Jean, On 9/14/21 4:19 PM, Jean-Philippe Brucker 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> > --- > Sizes and types are hardcoded because it will now be the default style > https://lore.kernel.org/qemu-devel/20210708154617.1538485-1-imammedo@redhat.com/ > --- > hw/acpi/viot.h | 13 +++++ > hw/acpi/viot.c | 112 ++++++++++++++++++++++++++++++++++++++++++++ > hw/acpi/Kconfig | 4 ++ > hw/acpi/meson.build | 1 + > 4 files changed, 130 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..e7f7605119 > --- /dev/null > +++ b/hw/acpi/viot.c > @@ -0,0 +1,112 @@ > +/* > + * 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" > + > +struct viot_pci_ranges { > + GArray *blob; > + size_t count; > + uint16_t output_node; > +}; > + > +/* Build PCI range for a given PCI host bridge */ > +static int viot_host_bridges(Object *obj, void *opaque) nit: rename the function into something like build_pci_range_node() which actually indicates what it does > +{ > + struct viot_pci_ranges *pci_ranges = opaque; > + GArray *blob = pci_ranges->blob; > + > + 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); > + > + /* Type (PCI range) */ > + build_append_int_noprefix(blob, 1, 1); > + /* Reserved */ > + build_append_int_noprefix(blob, 0, 1); > + /* Length */ > + build_append_int_noprefix(blob, 24, 2); > + /* Endpoint start */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 4); > + /* PCI Segment start */ > + build_append_int_noprefix(blob, 0, 2); > + /* PCI Segment end */ > + build_append_int_noprefix(blob, 0, 2); > + /* PCI BDF start */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 2); > + /* PCI BDF end */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(max_bus, 0xff), 2); > + /* Output node */ > + build_append_int_noprefix(blob, pci_ranges->output_node, 2); > + /* Reserved */ > + build_append_int_noprefix(blob, 0, 6); > + > + pci_ranges->count++; > + } > + } > + > + 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) > +{ > + /* The virtio-iommu node follows the 48-bytes header */ > + int viommu_off = 48; > + AcpiTable table = { .sig = "VIOT", .rev = 0, > + .oem_id = oem_id, .oem_table_id = oem_table_id }; > + struct viot_pci_ranges pci_ranges = { > + .output_node = viommu_off, > + .blob = g_array_new(false, true, 1), nit add clear comment as in the other places? .blob = g_array_new(false, /* clear */ true, 1), > + }; > + > + /* Build the list of PCI ranges that this viommu manages */ > + object_child_foreach_recursive(object_get_root(), viot_host_bridges, > + &pci_ranges); > + > + /* ACPI table header */ > + acpi_table_begin(&table, table_data); > + /* Node count */ > + build_append_int_noprefix(table_data, pci_ranges.count + 1, 2); > + /* Node offset */ > + build_append_int_noprefix(table_data, viommu_off, 2); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 8); > + > + /* Virtio-iommu node */ > + /* Type (virtio-pci IOMMU) */ > + build_append_int_noprefix(table_data, 3, 1); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 1); > + /* Length */ > + build_append_int_noprefix(table_data, 16, 2); > + /* PCI Segment */ > + build_append_int_noprefix(table_data, 0, 2); > + /* PCI BDF number */ > + build_append_int_noprefix(table_data, virtio_iommu_bdf, 2); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 8); > + > + /* PCI ranges found above */ > + g_array_append_vals(table_data, pci_ranges.blob->data, > + pci_ranges.blob->len); > + g_array_free(pci_ranges.blob, true); > + > + acpi_table_end(linker, &table); > +} > + > diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig > index 3b5e118c54..622b0b50b7 100644 > --- a/hw/acpi/Kconfig > +++ b/hw/acpi/Kconfig > @@ -51,6 +51,10 @@ 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 7d8c0eb43e..adf6347bc4 100644 > --- a/hw/acpi/meson.build > +++ b/hw/acpi/meson.build > @@ -20,6 +20,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files( > acpi_ss.add(when: 'CONFIG_ACPI_PIIX4', if_true: files('piix4.c')) > acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_true: files('pcihp.c')) > acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_false: files('acpi-pci-hotplug-stub.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')) Besides Reviewed-by: Eric Auger <eric.auger@redhat.com> Tested with default root bus and pxb-pci. Feel free to add Tested-by: Eric Auger <eric.auger@redhat.com> Thanks Eric
On Tue, 14 Sep 2021 15:19:56 +0100 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> > --- > Sizes and types are hardcoded because it will now be the default style > https://lore.kernel.org/qemu-devel/20210708154617.1538485-1-imammedo@redhat.com/ > --- > hw/acpi/viot.h | 13 +++++ > hw/acpi/viot.c | 112 ++++++++++++++++++++++++++++++++++++++++++++ > hw/acpi/Kconfig | 4 ++ > hw/acpi/meson.build | 1 + > 4 files changed, 130 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..e7f7605119 > --- /dev/null > +++ b/hw/acpi/viot.c > @@ -0,0 +1,112 @@ > +/* > + * 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" > + > +struct viot_pci_ranges { > + GArray *blob; > + size_t count; > + uint16_t output_node; > +}; > + > +/* Build PCI range for a given PCI host bridge */ > +static int viot_host_bridges(Object *obj, void *opaque) > +{ > + struct viot_pci_ranges *pci_ranges = opaque; > + GArray *blob = pci_ranges->blob; > + > + 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); > + > + /* Type (PCI range) */ > + build_append_int_noprefix(blob, 1, 1); > + /* Reserved */ > + build_append_int_noprefix(blob, 0, 1); > + /* Length */ > + build_append_int_noprefix(blob, 24, 2); > + /* Endpoint start */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 4); > + /* PCI Segment start */ > + build_append_int_noprefix(blob, 0, 2); > + /* PCI Segment end */ > + build_append_int_noprefix(blob, 0, 2); > + /* PCI BDF start */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 2); > + /* PCI BDF end */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(max_bus, 0xff), 2); > + /* Output node */ > + build_append_int_noprefix(blob, pci_ranges->output_node, 2); > + /* Reserved */ > + build_append_int_noprefix(blob, 0, 6); > + > + pci_ranges->count++; > + } > + } > + > + return 0; > +} > + > +/* > + * Generate a VIOT table with one PCI-based virtio-iommu that manages PCI > + * endpoints. We usually put a pointer to spec/revision and chapter in it that describes being implemented table, so reviewer would have a reference to compare code with. Otherwise I have no idea if implementation is correct or not. ex: build_hmat_mpda the same applies to viot_host_bridges > + */ > +void build_viot(GArray *table_data, BIOSLinker *linker, > + uint16_t virtio_iommu_bdf, const char *oem_id, > + const char *oem_table_id) > +{ > + /* The virtio-iommu node follows the 48-bytes header */ > + int viommu_off = 48; > + AcpiTable table = { .sig = "VIOT", .rev = 0, > + .oem_id = oem_id, .oem_table_id = oem_table_id }; > + struct viot_pci_ranges pci_ranges = { > + .output_node = viommu_off, > + .blob = g_array_new(false, true, 1), > + }; > + > + /* Build the list of PCI ranges that this viommu manages */ > + object_child_foreach_recursive(object_get_root(), viot_host_bridges, > + &pci_ranges); > + > + /* ACPI table header */ > + acpi_table_begin(&table, table_data); > + /* Node count */ > + build_append_int_noprefix(table_data, pci_ranges.count + 1, 2); > + /* Node offset */ > + build_append_int_noprefix(table_data, viommu_off, 2); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 8); > + > + /* Virtio-iommu node */ > + /* Type (virtio-pci IOMMU) */ > + build_append_int_noprefix(table_data, 3, 1); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 1); > + /* Length */ > + build_append_int_noprefix(table_data, 16, 2); > + /* PCI Segment */ > + build_append_int_noprefix(table_data, 0, 2); > + /* PCI BDF number */ > + build_append_int_noprefix(table_data, virtio_iommu_bdf, 2); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 8); > + > + /* PCI ranges found above */ > + g_array_append_vals(table_data, pci_ranges.blob->data, > + pci_ranges.blob->len); > + g_array_free(pci_ranges.blob, true); > + > + acpi_table_end(linker, &table); > +} > + > diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig > index 3b5e118c54..622b0b50b7 100644 > --- a/hw/acpi/Kconfig > +++ b/hw/acpi/Kconfig > @@ -51,6 +51,10 @@ 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 7d8c0eb43e..adf6347bc4 100644 > --- a/hw/acpi/meson.build > +++ b/hw/acpi/meson.build > @@ -20,6 +20,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files( > acpi_ss.add(when: 'CONFIG_ACPI_PIIX4', if_true: files('piix4.c')) > acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_true: files('pcihp.c')) > acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_false: files('acpi-pci-hotplug-stub.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'))
On Tue, 14 Sep 2021 15:19:56 +0100 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> > --- > Sizes and types are hardcoded because it will now be the default style > https://lore.kernel.org/qemu-devel/20210708154617.1538485-1-imammedo@redhat.com/ > --- > hw/acpi/viot.h | 13 +++++ > hw/acpi/viot.c | 112 ++++++++++++++++++++++++++++++++++++++++++++ > hw/acpi/Kconfig | 4 ++ > hw/acpi/meson.build | 1 + > 4 files changed, 130 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..e7f7605119 > --- /dev/null > +++ b/hw/acpi/viot.c > @@ -0,0 +1,112 @@ > +/* > + * 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" > + > +struct viot_pci_ranges { > + GArray *blob; > + size_t count; > + uint16_t output_node; > +}; > + > +/* Build PCI range for a given PCI host bridge */ > +static int viot_host_bridges(Object *obj, void *opaque) > +{ > + struct viot_pci_ranges *pci_ranges = opaque; > + GArray *blob = pci_ranges->blob; > + > + 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); > + > + /* Type (PCI range) */ > + build_append_int_noprefix(blob, 1, 1); > + /* Reserved */ > + build_append_int_noprefix(blob, 0, 1); > + /* Length */ > + build_append_int_noprefix(blob, 24, 2); > + /* Endpoint start */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 4); > + /* PCI Segment start */ > + build_append_int_noprefix(blob, 0, 2); > + /* PCI Segment end */ > + build_append_int_noprefix(blob, 0, 2); > + /* PCI BDF start */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 2); > + /* PCI BDF end */ > + build_append_int_noprefix(blob, PCI_BUILD_BDF(max_bus, 0xff), 2); > + /* Output node */ > + build_append_int_noprefix(blob, pci_ranges->output_node, 2); > + /* Reserved */ > + build_append_int_noprefix(blob, 0, 6); > + > + pci_ranges->count++; > + } > + } > + > + 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) > +{ > + /* The virtio-iommu node follows the 48-bytes header */ > + int viommu_off = 48; > + AcpiTable table = { .sig = "VIOT", .rev = 0, > + .oem_id = oem_id, .oem_table_id = oem_table_id }; > + struct viot_pci_ranges pci_ranges = { > + .output_node = viommu_off, > + .blob = g_array_new(false, true, 1), > + }; > + > + /* Build the list of PCI ranges that this viommu manages */ > + object_child_foreach_recursive(object_get_root(), viot_host_bridges, I'd limit scope to machine and re-use one that caller already uses. in arm case: virt_acpi_build(VirtMachineState *vms, ... q35: acpi_build(..., MachineState *machine) > + &pci_ranges); > + > + /* ACPI table header */ > + acpi_table_begin(&table, table_data); > + /* Node count */ > + build_append_int_noprefix(table_data, pci_ranges.count + 1, 2); > + /* Node offset */ > + build_append_int_noprefix(table_data, viommu_off, 2); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 8); > + > + /* Virtio-iommu node */ > + /* Type (virtio-pci IOMMU) */ > + build_append_int_noprefix(table_data, 3, 1); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 1); > + /* Length */ > + build_append_int_noprefix(table_data, 16, 2); > + /* PCI Segment */ > + build_append_int_noprefix(table_data, 0, 2); > + /* PCI BDF number */ > + build_append_int_noprefix(table_data, virtio_iommu_bdf, 2); > + /* Reserved */ > + build_append_int_noprefix(table_data, 0, 8); > + > + /* PCI ranges found above */ > + g_array_append_vals(table_data, pci_ranges.blob->data, > + pci_ranges.blob->len); > + g_array_free(pci_ranges.blob, true); > + > + acpi_table_end(linker, &table); > +} > + > diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig > index 3b5e118c54..622b0b50b7 100644 > --- a/hw/acpi/Kconfig > +++ b/hw/acpi/Kconfig > @@ -51,6 +51,10 @@ 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 7d8c0eb43e..adf6347bc4 100644 > --- a/hw/acpi/meson.build > +++ b/hw/acpi/meson.build > @@ -20,6 +20,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files( > acpi_ss.add(when: 'CONFIG_ACPI_PIIX4', if_true: files('piix4.c')) > acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_true: files('pcihp.c')) > acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_false: files('acpi-pci-hotplug-stub.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'))
On Mon, Sep 20, 2021 at 10:06:09AM +0200, Igor Mammedov wrote: > > +/* > > + * Generate a VIOT table with one PCI-based virtio-iommu that manages PCI > > + * endpoints. > > We usually put a pointer to spec/revision and chapter in it > that describes being implemented table, so reviewer would > have a reference to compare code with. Otherwise I have no > idea if implementation is correct or not. The 6.5 ACPI specification isn't out yet unfortunately, so I can't put any reference at the moment. I don't know when it will be published. The draft specification is here: https://jpbrucker.net/virtio-iommu/viot/viot-v9.pdf But that's only temporary. I can make a note to add the pointers once the spec is out. The acpica implementation could also be used for cross-reference: https://github.com/acpica/acpica/commit/fc4e33319c1ee08f20f5c44853dd8426643f6dfd Thanks, Jean > > ex: build_hmat_mpda > > the same applies to viot_host_bridges >
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..e7f7605119 --- /dev/null +++ b/hw/acpi/viot.c @@ -0,0 +1,112 @@ +/* + * 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" + +struct viot_pci_ranges { + GArray *blob; + size_t count; + uint16_t output_node; +}; + +/* Build PCI range for a given PCI host bridge */ +static int viot_host_bridges(Object *obj, void *opaque) +{ + struct viot_pci_ranges *pci_ranges = opaque; + GArray *blob = pci_ranges->blob; + + 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); + + /* Type (PCI range) */ + build_append_int_noprefix(blob, 1, 1); + /* Reserved */ + build_append_int_noprefix(blob, 0, 1); + /* Length */ + build_append_int_noprefix(blob, 24, 2); + /* Endpoint start */ + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 4); + /* PCI Segment start */ + build_append_int_noprefix(blob, 0, 2); + /* PCI Segment end */ + build_append_int_noprefix(blob, 0, 2); + /* PCI BDF start */ + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 2); + /* PCI BDF end */ + build_append_int_noprefix(blob, PCI_BUILD_BDF(max_bus, 0xff), 2); + /* Output node */ + build_append_int_noprefix(blob, pci_ranges->output_node, 2); + /* Reserved */ + build_append_int_noprefix(blob, 0, 6); + + pci_ranges->count++; + } + } + + 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) +{ + /* The virtio-iommu node follows the 48-bytes header */ + int viommu_off = 48; + AcpiTable table = { .sig = "VIOT", .rev = 0, + .oem_id = oem_id, .oem_table_id = oem_table_id }; + struct viot_pci_ranges pci_ranges = { + .output_node = viommu_off, + .blob = g_array_new(false, true, 1), + }; + + /* Build the list of PCI ranges that this viommu manages */ + object_child_foreach_recursive(object_get_root(), viot_host_bridges, + &pci_ranges); + + /* ACPI table header */ + acpi_table_begin(&table, table_data); + /* Node count */ + build_append_int_noprefix(table_data, pci_ranges.count + 1, 2); + /* Node offset */ + build_append_int_noprefix(table_data, viommu_off, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 8); + + /* Virtio-iommu node */ + /* Type (virtio-pci IOMMU) */ + build_append_int_noprefix(table_data, 3, 1); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 1); + /* Length */ + build_append_int_noprefix(table_data, 16, 2); + /* PCI Segment */ + build_append_int_noprefix(table_data, 0, 2); + /* PCI BDF number */ + build_append_int_noprefix(table_data, virtio_iommu_bdf, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 8); + + /* PCI ranges found above */ + g_array_append_vals(table_data, pci_ranges.blob->data, + pci_ranges.blob->len); + g_array_free(pci_ranges.blob, true); + + acpi_table_end(linker, &table); +} + diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index 3b5e118c54..622b0b50b7 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -51,6 +51,10 @@ 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 7d8c0eb43e..adf6347bc4 100644 --- a/hw/acpi/meson.build +++ b/hw/acpi/meson.build @@ -20,6 +20,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files( acpi_ss.add(when: 'CONFIG_ACPI_PIIX4', if_true: files('piix4.c')) acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_true: files('pcihp.c')) acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_false: files('acpi-pci-hotplug-stub.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'))
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> --- Sizes and types are hardcoded because it will now be the default style https://lore.kernel.org/qemu-devel/20210708154617.1538485-1-imammedo@redhat.com/ --- hw/acpi/viot.h | 13 +++++ hw/acpi/viot.c | 112 ++++++++++++++++++++++++++++++++++++++++++++ hw/acpi/Kconfig | 4 ++ hw/acpi/meson.build | 1 + 4 files changed, 130 insertions(+) create mode 100644 hw/acpi/viot.h create mode 100644 hw/acpi/viot.c -- 2.33.0