Skip to contentSkip to conversation

VIRTIO-IOMMU probe request support and MSI bypass on ARM

PATCH Superseded Eric Auger 2 participants 10 messages Jun 26, 2020 – Jun 27, 2020

v6 of 7 Superseded Latest is v7 →

lore
Share & tools
lore

Eric Auger

author
#0 lore raw

v6 cover VIRTIO-IOMMU probe request support and MSI bypass on ARM

By default the virtio-iommu translates MSI transactions. This behavior is inherited from ARM SMMU. However the virt machine code knows where the MSI doorbells are, so we can easily declare those regions as VIRTIO_IOMMU_RESV_MEM_T_MSI. With that setting the guest iommu subsystem will not need to map MSIs. This setup will simplify the VFIO integration.

In this series, the ITS or GICV2M doorbells are declared as HW MSI regions to be bypassed by the VIRTIO-IOMMU.

This also paves the way to the x86 integration where the MSI region, [0xFEE00000,0xFEEFFFFF], will be exposed by the q35 machine. However this will be handled in a separate series when not-DT support gets resolved.

Best Regards

Eric

This series can be found at:
https://github.com/eauger/qemu/tree/v5.0.0-virtio-iommu-msi-bypass-v6

History:

v5 -> v6:
- do not hardcode start/end addresses of doorbells
- check reserved region type on realize()

v4 -> v5:
- Take into account some additional comments from Markus:
- reserved region type becomes an unsigned + some comment/desc rewording
- assert if the type is not RESERVED or MSI

v3 -> v4:
- collected Jean and markus's R-bs
- tool into account all Markus' comments in [1/5] (except removal of goto)
- use ':' as delimitor instead of commas
- add example in 4/5 commit message as suggested by Markus

v2 -> v3:
- Introduce VIRT_MSI_CTRL_NONE in VirtMSIControllerType
- do not fill the remainder of the probe buffer

v1 -> v2:
- check which MSI controller is in use and advertise the corresponding MSI doorbell
- managed for both ITS and GICv2M
- various fixes spotted by Peter and Jean-Philippe, see individual logs

v1: Most of those patches were respinned from
[PATCH for-5.0 v11 00/20] VIRTIO-IOMMU device
except the last one which is new

Eric Auger (5):
qdev: Introduce DEFINE_PROP_RESERVED_REGION
virtio-iommu: Implement RESV_MEM probe request
virtio-iommu: Handle reserved regions in the translation process
virtio-iommu-pci: Add array of Interval properties hw/arm/virt: Let the virtio-iommu bypass MSIs

 include/exec/memory.h            |   6 ++
 include/hw/arm/virt.h            |   7 ++
 include/hw/qdev-properties.h     |   3 +
 include/hw/virtio/virtio-iommu.h |   2 +
 include/qemu/typedefs.h          |   1 +
 hw/arm/virt.c                    |  30 +++++++++
 hw/core/qdev-properties.c        |  89 +++++++++++++++++++++++++
 hw/virtio/virtio-iommu-pci.c     |  13 ++++
 hw/virtio/virtio-iommu.c         | 110 +++++++++++++++++++++++++++++--
 hw/virtio/trace-events           |   1 +
 10 files changed, 258 insertions(+), 4 deletions(-)
Signature · 1 line
2.20.1
author
#1 lore raw

PATCH v6 1/5 qdev: Introduce DEFINE_PROP_RESERVED_REGION

Introduce a new property defining a reserved region:
<low address>:<high address>:<type>.

This will be used to encode reserved IOVA regions.

For instance, in virtio-iommu use case, reserved IOVA regions will be passed by the machine code to the virtio-iommu-pci device (an array of those). The type of the reserved region will match the virtio_iommu_probe_resv_mem subtype value:
- VIRTIO_IOMMU_RESV_MEM_T_RESERVED (0)
- VIRTIO_IOMMU_RESV_MEM_T_MSI (1)

on PC/Q35 machine, this will be used to inform the virtio-iommu-pci device it should bypass the MSI region. The reserved region will be: 0xfee00000:0xfeefffff:1.

On ARM, we can declare the ITS MSI doorbell as an MSI region to prevent MSIs from being mapped on guest side.

---

v4 -> v5:
- type becomes an unsigned + comment/error rewording

v3 -> v4:
- use ':' instead of commas as separators.
- rearrange error messages
- check snprintf returned value
- dared to keep Markus' R-b despite those changes

---
 include/exec/memory.h        |  6 +++
 include/hw/qdev-properties.h |  3 ++
 include/qemu/typedefs.h      |  1 +
 hw/core/qdev-properties.c    | 89 ++++++++++++++++++++++++++++++++++++
 4 files changed, 99 insertions(+)
include/exec/memory.h +6 -0
index 7207025bd4..84ee5b7a01 100644
@@ -51,6 +51,12 @@ extern bool global_dirty_log;
 
 typedef struct MemoryRegionOps MemoryRegionOps;
 
+struct ReservedRegion {
+    hwaddr low;
+    hwaddr high;
+    unsigned type;
+};
+
 typedef struct IOMMUTLBEntry IOMMUTLBEntry;
 
 /* See address_space_translate: bit 0 is read, bit 1 is write.  */
include/hw/qdev-properties.h +3 -0
index 49c6cd2460..944e3f2e0c 100644
@@ -19,6 +19,7 @@ extern const PropertyInfo qdev_prop_string;
 extern const PropertyInfo qdev_prop_chr;
 extern const PropertyInfo qdev_prop_tpm;
 extern const PropertyInfo qdev_prop_macaddr;
+extern const PropertyInfo qdev_prop_reserved_region;
 extern const PropertyInfo qdev_prop_on_off_auto;
 extern const PropertyInfo qdev_prop_multifd_compression;
 extern const PropertyInfo qdev_prop_losttickpolicy;
@@ -184,6 +185,8 @@ extern const PropertyInfo qdev_prop_pcie_link_width;
     DEFINE_PROP(_n, _s, _f, qdev_prop_drive_iothread, BlockBackend *)
 #define DEFINE_PROP_MACADDR(_n, _s, _f)         \
     DEFINE_PROP(_n, _s, _f, qdev_prop_macaddr, MACAddr)
+#define DEFINE_PROP_RESERVED_REGION(_n, _s, _f)         \
+    DEFINE_PROP(_n, _s, _f, qdev_prop_reserved_region, ReservedRegion)
 #define DEFINE_PROP_ON_OFF_AUTO(_n, _s, _f, _d) \
     DEFINE_PROP_SIGNED(_n, _s, _f, _d, qdev_prop_on_off_auto, OnOffAuto)
 #define DEFINE_PROP_MULTIFD_COMPRESSION(_n, _s, _f, _d) \
include/qemu/typedefs.h +1 -0
index ce4a78b687..15f5047bf1 100644
@@ -58,6 +58,7 @@ typedef struct ISABus ISABus;
 typedef struct ISADevice ISADevice;
 typedef struct IsaDma IsaDma;
 typedef struct MACAddr MACAddr;
+typedef struct ReservedRegion ReservedRegion;
 typedef struct MachineClass MachineClass;
 typedef struct MachineState MachineState;
 typedef struct MemoryListener MemoryListener;
hw/core/qdev-properties.c +89 -0

101 lines not on this page · raw message

Signature · 1 line
2.20.1
author
#2 lore raw

PATCH v6 2/5 virtio-iommu: Implement RESV_MEM probe request

In reply to Eric Auger

This patch implements the PROBE request. At the moment, only THE RESV_MEM property is handled. The first goal is to report iommu wide reserved regions such as the MSI regions set by the machine code. On x86 this will be the IOAPIC MSI region, [0xFEE00000 - 0xFEEFFFFF], on ARM this may be the ITS doorbell.

In the future we may introduce per device reserved regions. This will be useful when protecting host assigned devices which may expose their own reserved regions

---

v5 -> v6:
- removed validation of s->reserved_regions[i].type in the probe request as it should rather happen in the realize()

v4 -> v5:
- assert if reserved region type is different from RESERVED or MSI

v3 -> v4:
- removed any reference to the NONE property that does not exist anymore.

v2 -> v3:
- on probe, do not fill the reminder of the buffer with zeroes as the buffer was already zero initialized (Bharat)

v1 -> v2:
- move the unlock back to the same place
- remove the push label and factorize the code after the out label
- fix a bunch of cpu_to_leX according to the latest spec revision
- do not remove sizeof(last) from free space
- check the ep exists

---
 include/hw/virtio/virtio-iommu.h |  2 +
 hw/virtio/virtio-iommu.c         | 90 ++++++++++++++++++++++++++++++--
 hw/virtio/trace-events           |  1 +
 3 files changed, 89 insertions(+), 4 deletions(-)
include/hw/virtio/virtio-iommu.h +2 -0
index e653004d7c..49eb105cd8 100644
@@ -53,6 +53,8 @@ typedef struct VirtIOIOMMU {
     GHashTable *as_by_busptr;
     IOMMUPciBus *iommu_pcibus_by_bus_num[PCI_BUS_MAX];
     PCIBus *primary_bus;
+    ReservedRegion *reserved_regions;
+    uint32_t nb_reserved_regions;
     GTree *domains;
     QemuMutex mutex;
     GTree *endpoints;
hw/virtio/virtio-iommu.c +86 -4

143 lines not on this page · raw message

hw/virtio/trace-events +1 -0
index 6427a0047d..23109f69bb 100644
@@ -74,3 +74,4 @@ virtio_iommu_get_domain(uint32_t domain_id) "Alloc domain=%d"
 virtio_iommu_put_domain(uint32_t domain_id) "Free domain=%d"
 virtio_iommu_translate_out(uint64_t virt_addr, uint64_t phys_addr, uint32_t sid) "0x%"PRIx64" -> 0x%"PRIx64 " for sid=%d"
 virtio_iommu_report_fault(uint8_t reason, uint32_t flags, uint32_t endpoint, uint64_t addr) "FAULT reason=%d flags=%d endpoint=%d address =0x%"PRIx64
+virtio_iommu_fill_resv_property(uint32_t devid, uint8_t subtype, uint64_t start, uint64_t end) "dev= %d, type=%d start=0x%"PRIx64" end=0x%"PRIx64
Signature · 1 line
2.20.1
#3 lore raw

Re: [PATCH v6 2/5] virtio-iommu: Implement RESV_MEM probe request

Quoted 11 lines · Eric Auger

This patch implements the PROBE request. At the moment, only THE RESV_MEM property is handled. The first goal is to report iommu wide reserved regions such as the MSI regions set by the machine code. On x86 this will be the IOAPIC MSI region, [0xFEE00000 - 0xFEEFFFFF], on ARM this may be the ITS doorbell.

In the future we may introduce per device reserved regions. This will be useful when protecting host assigned devices which may expose their own reserved regions

Quoted 8 lines

---

v5 -> v6:
- removed validation of s->reserved_regions[i].type in the probe request as it should rather happen in the realize()

Consider keeping the assertion. I'd makes it locally obvious that the assignment to subtype is not supposed to truncate. The realize method is in another file. This is not a demand.

[...]

author
#4 lore raw

Re: [PATCH v6 2/5] virtio-iommu: Implement RESV_MEM probe request

Hi Markus,

Quoted 18 lines · Markus Armbruster
Quoted 16 lines · Eric Auger

This patch implements the PROBE request. At the moment, only THE RESV_MEM property is handled. The first goal is to report iommu wide reserved regions such as the MSI regions set by the machine code. On x86 this will be the IOAPIC MSI region, [0xFEE00000 - 0xFEEFFFFF], on ARM this may be the ITS doorbell.

In the future we may introduce per device reserved regions. This will be useful when protecting host assigned devices which may expose their own reserved regions

---

Quoted 7 lines
Quoted 3 lines

v5 -> v6:
- removed validation of s->reserved_regions[i].type in the probe request as it should rather happen in the realize()

Consider keeping the assertion. I'd makes it locally obvious that the assignment to subtype is not supposed to truncate. The realize method is in another file. This is not a demand.

OK I will add the assert again

Thanks

Eric

Quoted 3 lines

[...]

author
#5 lore raw

PATCH v6 3/5 virtio-iommu: Handle reserved regions in the translation process

In reply to Eric Auger

When translating an address we need to check if it belongs to a reserved virtual address range. If it does, there are 2 cases:

- it belongs to a RESERVED region: the guest should neither use this address in a MAP not instruct the end-point to DMA on them. We report an error

- It belongs to an MSI region: we bypass the translation.

---

v1 -> v2:
- use addr when testing addr belongs to the reserved region and use a block local variable

---
 hw/virtio/virtio-iommu.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
hw/virtio/virtio-iommu.c +20 -0
index 5e72fd53a1..4a50e24d21 100644
@@ -603,6 +603,7 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr,
     uint32_t sid, flags;
     bool bypass_allowed;
     bool found;
+    int i;
 
     interval.low = addr;
     interval.high = addr + 1;
@@ -636,6 +637,25 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr,
         goto unlock;
     }
 
+    for (i = 0; i < s->nb_reserved_regions; i++) {
+        ReservedRegion *reg = &s->reserved_regions[i];
+
+        if (addr >= reg->low && addr <= reg->high) {
+            switch (reg->type) {
+            case VIRTIO_IOMMU_RESV_MEM_T_MSI:
+                entry.perm = flag;
+                break;
+            case VIRTIO_IOMMU_RESV_MEM_T_RESERVED:
+            default:
+                virtio_iommu_report_fault(s, VIRTIO_IOMMU_FAULT_R_MAPPING,
+                                          VIRTIO_IOMMU_FAULT_F_ADDRESS,
+                                          sid, addr);
+                break;
+            }
+            goto unlock;
+        }
+    }
+
     if (!ep->domain) {
         if (!bypass_allowed) {
             error_report_once("%s %02x:%02x.%01x not attached to any domain",
Signature · 1 line
2.20.1
author
#6 lore raw

PATCH v6 4/5 virtio-iommu-pci: Add array of Interval properties

In reply to Eric Auger

The machine may need to pass reserved regions to the virtio-iommu-pci device (such as the MSI window on x86 or the MSI doorbells on ARM).

So let's add an array of Interval properties.

Note: if some reserved regions are already set by the machine code - which should be the case in general -, the length of the property array is already set and prevents the end-user from modifying them. For example, attempting to use:

-device virtio-iommu-pci,\
len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:1

would result in the following error message:

qemu-system-aarch64: -device virtio-iommu-pci,addr=0xa, len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:1:
array size property len-reserved-regions may not be set more than once

Otherwise, for example, adding two reserved regions is achieved using the following options:

-device virtio-iommu-pci,addr=0xa,len-reserved-regions=2,\
reserved-regions[0]=0xfee00000:0xfeefffff:1,\
reserved-regions[1]=0x1000000:100ffff:1

---
v5 -> v6:
- check the type value
- removed Jean's R-b

v3 -> v4:
- added examples in the commit message as suggested by Markus
- added Jean's R-b

---
 hw/virtio/virtio-iommu-pci.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
hw/virtio/virtio-iommu-pci.c +13 -0
index 632533abaf..9c9bda9490 100644
@@ -33,6 +33,9 @@ struct VirtIOIOMMUPCI {
 
 static Property virtio_iommu_pci_properties[] = {
     DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0),
+    DEFINE_PROP_ARRAY("reserved-regions", VirtIOIOMMUPCI,
+                      vdev.nb_reserved_regions, vdev.reserved_regions,
+                      qdev_prop_reserved_region, ReservedRegion),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -40,6 +43,7 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
 {
     VirtIOIOMMUPCI *dev = VIRTIO_IOMMU_PCI(vpci_dev);
     DeviceState *vdev = DEVICE(&dev->vdev);
+    VirtIOIOMMU *s = VIRTIO_IOMMU(vdev);
 
     if (!qdev_get_machine_hotplug_handler(DEVICE(vpci_dev))) {
         MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());
@@ -54,6 +58,15 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
                           "-no-acpi\n");
         return;
     }
+    for (int i = 0; i < s->nb_reserved_regions; i++) {
+        if (s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_RESERVED &&
+            s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_MSI) {
+            error_setg(errp, "reserved region %d has an invalid type", i);
+            error_append_hint(errp, "Valid values are "
+                              "VIRTIO_IOMMU_RESV_MEM_T_RESERVED and "
+                              "VIRTIO_IOMMU_RESV_MEM_T_SMI\n");
+        }
+    }
     object_property_set_link(OBJECT(dev),
                              OBJECT(pci_get_bus(&vpci_dev->pci_dev)),
                              "primary-bus", errp);
Signature · 1 line
2.20.1
Reviewed-by on v6 4/5
#7 lore raw

Re: [PATCH v6 4/5] virtio-iommu-pci: Add array of Interval properties

Quoted 65 lines · Eric Auger

The machine may need to pass reserved regions to the virtio-iommu-pci device (such as the MSI window on x86 or the MSI doorbells on ARM).

So let's add an array of Interval properties.

Note: if some reserved regions are already set by the machine code - which should be the case in general -, the length of the property array is already set and prevents the end-user from modifying them. For example, attempting to use:

-device virtio-iommu-pci,\
len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:1

would result in the following error message:

qemu-system-aarch64: -device virtio-iommu-pci,addr=0xa, len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:1:
array size property len-reserved-regions may not be set more than once

Otherwise, for example, adding two reserved regions is achieved using the following options:

-device virtio-iommu-pci,addr=0xa,len-reserved-regions=2,\
reserved-regions[0]=0xfee00000:0xfeefffff:1,\
reserved-regions[1]=0x1000000:100ffff:1

---
v5 -> v6:
- check the type value
- removed Jean's R-b

v3 -> v4:
- added examples in the commit message as suggested by Markus
- added Jean's R-b

---
 hw/virtio/virtio-iommu-pci.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
hw/virtio/virtio-iommu-pci.c +4 -0
index 632533abaf..9c9bda9490 100644
@@ -33,6 +33,9 @@ struct VirtIOIOMMUPCI {
 
 static Property virtio_iommu_pci_properties[] = {
     DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0),
+    DEFINE_PROP_ARRAY("reserved-regions", VirtIOIOMMUPCI,
+                      vdev.nb_reserved_regions, vdev.reserved_regions,
+                      qdev_prop_reserved_region, ReservedRegion),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -40,6 +43,7 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
 {
     VirtIOIOMMUPCI *dev = VIRTIO_IOMMU_PCI(vpci_dev);
     DeviceState *vdev = DEVICE(&dev->vdev);
+    VirtIOIOMMU *s = VIRTIO_IOMMU(vdev);
 
     if (!qdev_get_machine_hotplug_handler(DEVICE(vpci_dev))) {
         MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());

hw/virtio/virtio-iommu-pci.c static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) · line 67

Quoted 10 lines
hw/virtio/virtio-iommu-pci.c +7 -0
@@ -54,6 +58,15 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
                           "-no-acpi\n");
         return;
     }
+    for (int i = 0; i < s->nb_reserved_regions; i++) {
+        if (s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_RESERVED &&
+            s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_MSI) {
+            error_setg(errp, "reserved region %d has an invalid type", i);
+            error_append_hint(errp, "Valid values are "
+                              "VIRTIO_IOMMU_RESV_MEM_T_RESERVED and "
+                              "VIRTIO_IOMMU_RESV_MEM_T_SMI\n");

Actually, valid values are 0 and 1. Something like

    -device virtio-iommu-pci,len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:VIRTIO_IOMMU_RESV_MEM_T_SMI

will be rejected as invalid.

hw/virtio/virtio-iommu-pci.c static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) · line 72

Quoted 5 lines
hw/virtio/virtio-iommu-pci.c +2 -0
+        }
+    }
     object_property_set_link(OBJECT(dev),
                              OBJECT(pci_get_bus(&vpci_dev->pci_dev)),
                              "primary-bus", errp);

Sorry for having to torture you this way! Have a

with the error message touched up.

author
#8 lore raw

Re: [PATCH v6 4/5] virtio-iommu-pci: Add array of Interval properties

Hi Markus,

Quoted 85 lines · Markus Armbruster
Quoted 65 lines · Eric Auger

The machine may need to pass reserved regions to the virtio-iommu-pci device (such as the MSI window on x86 or the MSI doorbells on ARM).

So let's add an array of Interval properties.

Note: if some reserved regions are already set by the machine code - which should be the case in general -, the length of the property array is already set and prevents the end-user from modifying them. For example, attempting to use:

-device virtio-iommu-pci,\
len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:1

would result in the following error message:

qemu-system-aarch64: -device virtio-iommu-pci,addr=0xa, len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:1:
array size property len-reserved-regions may not be set more than once

Otherwise, for example, adding two reserved regions is achieved using the following options:

-device virtio-iommu-pci,addr=0xa,len-reserved-regions=2,\
reserved-regions[0]=0xfee00000:0xfeefffff:1,\
reserved-regions[1]=0x1000000:100ffff:1

---
v5 -> v6:
- check the type value
- removed Jean's R-b

v3 -> v4:
- added examples in the commit message as suggested by Markus
- added Jean's R-b

---
 hw/virtio/virtio-iommu-pci.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)
hw/virtio/virtio-iommu-pci.c +4 -0
index 632533abaf..9c9bda9490 100644
@@ -33,6 +33,9 @@ struct VirtIOIOMMUPCI {
 
 static Property virtio_iommu_pci_properties[] = {
     DEFINE_PROP_UINT32("class", VirtIOPCIProxy, class_code, 0),
+    DEFINE_PROP_ARRAY("reserved-regions", VirtIOIOMMUPCI,
+                      vdev.nb_reserved_regions, vdev.reserved_regions,
+                      qdev_prop_reserved_region, ReservedRegion),
     DEFINE_PROP_END_OF_LIST(),
 };
 
@@ -40,6 +43,7 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
 {
     VirtIOIOMMUPCI *dev = VIRTIO_IOMMU_PCI(vpci_dev);
     DeviceState *vdev = DEVICE(&dev->vdev);
+    VirtIOIOMMU *s = VIRTIO_IOMMU(vdev);
 
     if (!qdev_get_machine_hotplug_handler(DEVICE(vpci_dev))) {
         MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine());

hw/virtio/virtio-iommu-pci.c static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) · line 67

Quoted 10 lines
hw/virtio/virtio-iommu-pci.c +7 -0
@@ -54,6 +58,15 @@ static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp)
                           "-no-acpi\n");
         return;
     }
+    for (int i = 0; i < s->nb_reserved_regions; i++) {
+        if (s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_RESERVED &&
+            s->reserved_regions[i].type != VIRTIO_IOMMU_RESV_MEM_T_MSI) {
+            error_setg(errp, "reserved region %d has an invalid type", i);
+            error_append_hint(errp, "Valid values are "
+                              "VIRTIO_IOMMU_RESV_MEM_T_RESERVED and "
+                              "VIRTIO_IOMMU_RESV_MEM_T_SMI\n");

Actually, valid values are 0 and 1. Something like

    -device virtio-iommu-pci,len-reserved-regions=1,reserved-regions[0]=0xfee00000:0xfeefffff:VIRTIO_IOMMU_RESV_MEM_T_SMI

will be rejected as invalid.

Quoted 7 lines

hw/virtio/virtio-iommu-pci.c static void virtio_iommu_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) · line 72

Quoted 5 lines
hw/virtio/virtio-iommu-pci.c +2 -0
+        }
+    }
     object_property_set_link(OBJECT(dev),
                              OBJECT(pci_get_bus(&vpci_dev->pci_dev)),
                              "primary-bus", errp);

Sorry for having to torture you this way! Have a

Nah In french we say "when we have no head we have legs ". Anyway there is a type s/SMI/MSI ...

Quoted 2 lines

with the error message touched up.

Than you for your patience!

Eric

Quoted 2 lines
author
#9 lore raw

PATCH v6 5/5 hw/arm/virt: Let the virtio-iommu bypass MSIs

In reply to Eric Auger

At the moment the virtio-iommu translates MSI transactions. This behavior is inherited from ARM SMMU. The virt machine code knows where the guest MSI doorbells are so we can easily declare those regions as VIRTIO_IOMMU_RESV_MEM_T_MSI. With that setting the guest will not map MSIs through the IOMMU and those transactions will be simply bypassed.

Depending on which MSI controller is in use (ITS or GICV2M), we declare either:
- the ITS interrupt translation space (ITS_base + 0x10000), containing the GITS_TRANSLATOR or
- The GICV2M single frame, containing the MSI_SETSP_NS register.

---
v5 -> v6:
- do not hardcode doorbell base and size
- removed Jean's R-b

v3 -> v4:
- use ':' as separators

v2 -> v3:
- Add a new value to VirtMSIControllerType

v1 -> v2:
- Test which MSI controller is instantiated
- If GICV2M is in use, declare its doorbell as an MSI doorbell too

---
 include/hw/arm/virt.h |  7 +++++++
 hw/arm/virt.c         | 30 ++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)
include/hw/arm/virt.h +7 -0
index 31878ddc72..a18b6b397b 100644
@@ -96,6 +96,12 @@ typedef enum VirtIOMMUType {
     VIRT_IOMMU_VIRTIO,
 } VirtIOMMUType;
 
+typedef enum VirtMSIControllerType {
+    VIRT_MSI_CTRL_NONE,
+    VIRT_MSI_CTRL_GICV2M,
+    VIRT_MSI_CTRL_ITS,
+} VirtMSIControllerType;
+
 typedef enum VirtGICType {
     VIRT_GIC_VERSION_MAX,
     VIRT_GIC_VERSION_HOST,
@@ -136,6 +142,7 @@ typedef struct {
     OnOffAuto acpi;
     VirtGICType gic_version;
     VirtIOMMUType iommu;
+    VirtMSIControllerType msi_controller;
     uint16_t virtio_iommu_bdf;
     struct arm_boot_info bootinfo;
     MemMapEntry *memmap;
hw/arm/virt.c +30 -0
index 402c362c14..5ba62d6568 100644
@@ -602,6 +602,7 @@ static void create_its(VirtMachineState *vms)
     sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, vms->memmap[VIRT_GIC_ITS].base);
 
     fdt_add_its_gic_node(vms);
+    vms->msi_controller = VIRT_MSI_CTRL_ITS;
 }
 
 static void create_v2m(VirtMachineState *vms)
@@ -622,6 +623,7 @@ static void create_v2m(VirtMachineState *vms)
     }
 
     fdt_add_v2m_gic_node(vms);
+    vms->msi_controller = VIRT_MSI_CTRL_GICV2M;
 }
 
 static void create_gic(VirtMachineState *vms)
@@ -2149,8 +2151,36 @@ out:
 static void virt_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev,
                                             DeviceState *dev, Error **errp)
 {
+    VirtMachineState *vms = VIRT_MACHINE(hotplug_dev);
+
     if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
         virt_memory_pre_plug(hotplug_dev, dev, errp);
+    } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) {
+        hwaddr db_start = 0, db_end = 0;
+        char *resv_prop_str;
+
+        switch (vms->msi_controller) {
+        case VIRT_MSI_CTRL_NONE:
+            return;
+        case VIRT_MSI_CTRL_ITS:
+            /* GITS_TRANSLATER page */
+            db_start = base_memmap[VIRT_GIC_ITS].base + 0x10000;
+            db_end = base_memmap[VIRT_GIC_ITS].base +
+                     base_memmap[VIRT_GIC_ITS].size - 1;
+            break;
+        case VIRT_MSI_CTRL_GICV2M:
+            /* MSI_SETSPI_NS page */
+            db_start = base_memmap[VIRT_GIC_V2M].base;
+            db_end = db_start + base_memmap[VIRT_GIC_V2M].size - 1;
+            break;
+        }
+        resv_prop_str = g_strdup_printf("0x%"PRIx64":0x%"PRIx64":%u",
+                                        db_start, db_end,
+                                        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);
     }
 }
 
Signature · 1 line
2.20.1