arch: Create ACPI IORT table

The virtual IOMMU exposed through virtio-iommu device has a dependency
on ACPI. It needs to expose the device ID of the virtio-iommu device,
and all the other devices attached to this virtual IOMMU. The IDs are
expressed from a PCI bus perspective, based on segment, bus, device and
function.

The guest relies on the topology description provided by the IORT table
to attach devices to the virtio-iommu device.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>

arch/src/aarch64/mod.rs

@@ -17,6 +17,7 @@ pub fn configure_system(
     _cmdline_size: usize,
     _num_cpus: u8,
     _serial_enabled: bool,
+    _virt_iommu: Option<(u32, &[u32])>,
 ) -> super::Result<()> {
     Ok(())
 }

arch/src/x86_64/acpi.rs

@@ -10,6 +10,8 @@ use vm_memory::{GuestAddress, GuestMemoryMmap};
 
 use vm_memory::{Address, ByteValued, Bytes};
 
+use std::convert::TryInto;
+
 use super::layout;
 
 #[repr(packed)]
@@ -53,6 +55,57 @@ struct PCIRangeEntry {
     _reserved: u32,
 }
 
+#[repr(packed)]
+#[derive(Default)]
+struct IortParavirtIommuNode {
+    pub type_: u8,
+    pub length: u16,
+    pub revision: u8,
+    _reserved1: u32,
+    pub num_id_mappings: u32,
+    pub ref_id_mappings: u32,
+    pub device_id: u32,
+    _reserved2: [u32; 3],
+    pub model: u32,
+    pub flags: u32,
+    _reserved3: [u32; 4],
+}
+
+#[repr(packed)]
+#[derive(Default)]
+struct IortPciRootComplexNode {
+    pub type_: u8,
+    pub length: u16,
+    pub revision: u8,
+    _reserved1: u32,
+    pub num_id_mappings: u32,
+    pub ref_id_mappings: u32,
+    pub mem_access_props: IortMemoryAccessProperties,
+    pub ats_attr: u32,
+    pub pci_seg_num: u32,
+    pub mem_addr_size_limit: u8,
+    _reserved2: [u8; 3],
+}
+
+#[repr(packed)]
+#[derive(Default)]
+struct IortMemoryAccessProperties {
+    pub cca: u32,
+    pub ah: u8,
+    _reserved: u16,
+    pub maf: u8,
+}
+
+#[repr(packed)]
+#[derive(Default)]
+struct IortIdMapping {
+    pub input_base: u32,
+    pub num_of_ids: u32,
+    pub ouput_base: u32,
+    pub output_ref: u32,
+    pub flags: u32,
+}
+
 pub fn create_dsdt_table(
     serial_enabled: bool,
     start_of_device_area: GuestAddress,
@@ -247,6 +300,7 @@ pub fn create_acpi_tables(
     serial_enabled: bool,
     start_of_device_area: GuestAddress,
     end_of_device_area: GuestAddress,
+    virt_iommu: Option<(u32, &[u32])>,
 ) -> GuestAddress {
     // RSDP is at the EBDA
     let rsdp_offset = layout::RSDP_POINTER;
@@ -349,6 +403,65 @@ pub fn create_acpi_tables(
         .expect("Error writing MCFG table");
     tables.push(mcfg_offset.0);
 
+    let (prev_tbl_len, prev_tbl_off) = if let Some((iommu_id, dev_ids)) = &virt_iommu {
+        // IORT
+        let mut iort = SDT::new(*b"IORT", 36, 1, *b"CLOUDH", *b"CHIORT  ", 1);
+        // IORT number of nodes
+        iort.append(2u32);
+        // IORT offset to array of IORT nodes
+        iort.append(48u32);
+        // IORT reserved 4 bytes
+        iort.append(0u32);
+        // IORT paravirtualized IOMMU node
+        iort.append(IortParavirtIommuNode {
+            type_: 128,
+            length: 56,
+            revision: 0,
+            num_id_mappings: 0,
+            ref_id_mappings: 56,
+            device_id: *iommu_id,
+            model: 1,
+            ..Default::default()
+        });
+
+        let num_entries = dev_ids.len();
+        let length: u16 = (36 + (20 * num_entries)).try_into().unwrap();
+
+        // IORT PCI root complex node
+        iort.append(IortPciRootComplexNode {
+            type_: 2,
+            length,
+            revision: 0,
+            num_id_mappings: num_entries as u32,
+            ref_id_mappings: 36,
+            ats_attr: 0,
+            pci_seg_num: 0,
+            mem_addr_size_limit: 255,
+            ..Default::default()
+        });
+
+        for dev_id in dev_ids.iter() {
+            // IORT ID mapping
+            iort.append(IortIdMapping {
+                input_base: *dev_id,
+                num_of_ids: 1,
+                ouput_base: *dev_id,
+                output_ref: 48,
+                flags: 0,
+            });
+        }
+
+        let iort_offset = mcfg_offset.checked_add(mcfg.len() as u64).unwrap();
+        guest_mem
+            .write_slice(iort.as_slice(), iort_offset)
+            .expect("Error writing IORT table");
+        tables.push(iort_offset.0);
+
+        (iort.len(), iort_offset)
+    } else {
+        (mcfg.len(), mcfg_offset)
+    };
+
     // XSDT
     let mut xsdt = SDT::new(*b"XSDT", 36, 1, *b"CLOUDH", *b"CHXSDT  ", 1);
     for table in tables {
@@ -356,7 +469,7 @@ pub fn create_acpi_tables(
     }
     xsdt.update_checksum();
 
-    let xsdt_offset = mcfg_offset.checked_add(mcfg.len() as u64).unwrap();
+    let xsdt_offset = prev_tbl_off.checked_add(prev_tbl_len as u64).unwrap();
     guest_mem
         .write_slice(xsdt.as_slice(), xsdt_offset)
         .expect("Error writing XSDT table");

arch/src/x86_64/mod.rs

@@ -104,6 +104,7 @@ pub fn arch_memory_regions(size: GuestUsize) -> Vec<(GuestAddress, usize, Region
 /// * `cmdline_addr` - Address in `guest_mem` where the kernel command line was loaded.
 /// * `cmdline_size` - Size of the kernel command line in bytes including the null terminator.
 /// * `num_cpus` - Number of virtual CPUs the guest will have.
+#[allow(clippy::too_many_arguments)]
 pub fn configure_system(
     guest_mem: &GuestMemoryMmap,
     cmdline_addr: GuestAddress,
@@ -112,6 +113,7 @@ pub fn configure_system(
     setup_hdr: Option<setup_header>,
     _serial_enabled: bool,
     _end_of_range: GuestAddress,
+    _virt_iommu: Option<(u32, &[u32])>,
 ) -> super::Result<()> {
     const KERNEL_BOOT_FLAG_MAGIC: u16 = 0xaa55;
     const KERNEL_HDR_MAGIC: u32 = 0x53726448;
@@ -183,6 +185,7 @@ pub fn configure_system(
             _serial_enabled,
             start_of_device_area,
             _end_of_range,
+            _virt_iommu,
         );
         params.0.acpi_rsdp_addr = rsdp_addr.0;
     }
@@ -251,6 +254,7 @@ mod tests {
             None,
             false,
             GuestAddress((1 << 36) - 1),
+            None,
         );
         assert!(config_err.is_err());
         assert_eq!(
@@ -277,6 +281,7 @@ mod tests {
             None,
             false,
             GuestAddress((1 << 36) - 1),
+            None,
         )
         .unwrap();
 
@@ -297,6 +302,7 @@ mod tests {
             None,
             false,
             GuestAddress((1 << 36) - 1),
+            None,
         )
         .unwrap();
 
@@ -317,6 +323,7 @@ mod tests {
             None,
             false,
             GuestAddress((1 << 36) - 1),
+            None,
         )
         .unwrap();
     }

vmm/src/vm.rs

@@ -745,6 +745,7 @@ impl Vm {
                     Some(hdr),
                     self.config.serial.mode != ConsoleOutputMode::Off,
                     end_of_range,
+                    None,
                 )
                 .map_err(|_| Error::CmdLine)?;
 
@@ -765,6 +766,7 @@ impl Vm {
                     None,
                     self.config.serial.mode != ConsoleOutputMode::Off,
                     end_of_range,
+                    None,
                 )
                 .map_err(|_| Error::CmdLine)?;