On Wed, Jul 08, 2026 at 02:52:43AM +0000, Michael Kelley wrote:
> From: Yu Zhang <[email protected]> Sent: Thursday, July 2, 2026
> 9:05 AM
> >
> > From: Easwar Hariharan <[email protected]>
> >
> > Hyper-V identifies each PCI pass-thru device by a logical device ID in
> > its hypercall interface. This ID consists of a per-bus prefix, derived
> > from the VMBus device instance GUID, combined with the PCI function
> > number of the endpoint device.
> >
> > Add a small registry in hv_common.c that maps a PCI domain number to its
> > logical device ID prefix. The vPCI bus driver (pci-hyperv) registers the
> > prefix when a bus is probed and unregisters it when the bus is removed.
> > Consumers such as the para-virtualized IOMMU driver look up the prefix
> > by PCI domain number and combine it with the function number to form the
> > complete logical device ID for hypercalls.
> >
> > The prefix construction is shared via hv_build_logical_dev_id_prefix() so
> > that pci-hyperv's interrupt retargeting path and the registry use exactly
> > the same byte layout. It is derived on demand from the constant hv_device
> > instance GUID rather than cached in struct hv_pcibus_device, which is
> > private to the pci-hyperv module; this keeps the interface narrow and
> > avoids depending on pci-hyperv internals.
> >
> > Co-developed-by: Yu Zhang <[email protected]>
> > Signed-off-by: Yu Zhang <[email protected]>
> > Signed-off-by: Easwar Hariharan <[email protected]>
> > ---
> > drivers/hv/hv_common.c | 95 +++++++++++++++++++++++++++++
> > drivers/pci/controller/pci-hyperv.c | 21 +++++--
> > include/asm-generic/mshyperv.h | 13 ++++
> > include/linux/hyperv.h | 8 +++
> > 4 files changed, 132 insertions(+), 5 deletions(-)
> >
> > diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
> > index 6b67ac616789..53493f8d14dc 100644
> > --- a/drivers/hv/hv_common.c
> > +++ b/drivers/hv/hv_common.c
> > @@ -26,6 +26,8 @@
> > #include <linux/kmsg_dump.h>
> > #include <linux/sizes.h>
> > #include <linux/slab.h>
> > +#include <linux/list.h>
> > +#include <linux/spinlock.h>
> > #include <linux/dma-map-ops.h>
> > #include <linux/set_memory.h>
> > #include <hyperv/hvhdk.h>
> > @@ -863,3 +865,96 @@ const char *hv_result_to_string(u64 status)
> > return "Unknown";
> > }
> > EXPORT_SYMBOL_GPL(hv_result_to_string);
> > +
> > +#ifdef CONFIG_HYPERV_PVIOMMU
> > +/*
> > + * Logical device ID registry shared between the vPCI bus driver
> > + * (pci-hyperv) and the para-virtualized IOMMU driver. The vPCI driver
> > + * registers the per-bus logical device ID prefix at bus probe time, and
> > + * the pvIOMMU driver looks it up to build the full logical device ID used
> > + * in IOMMU hypercalls.
> > + */
> > +struct hv_pci_busdata {
> > + int pci_domain_nr;
> > + u32 logical_dev_id_prefix;
> > + struct list_head list;
> > +};
> > +
> > +static LIST_HEAD(hv_pci_bus_list);
> > +static DEFINE_SPINLOCK(hv_pci_bus_lock);
> > +
> > +int hv_iommu_register_pci_bus(int pci_domain_nr, u32 logical_dev_id_prefix)
> > +{
> > + struct hv_pci_busdata *bus, *new;
> > + int ret = 0;
> > +
> > + new = kzalloc_obj(*new, GFP_KERNEL);
> > + if (!new)
> > + return -ENOMEM;
> > +
> > + spin_lock(&hv_pci_bus_lock);
> > + list_for_each_entry(bus, &hv_pci_bus_list, list) {
> > + if (bus->pci_domain_nr != pci_domain_nr)
> > + continue;
> > +
> > + if (bus->logical_dev_id_prefix != logical_dev_id_prefix) {
> > + pr_err("stale registration for PCI domain %d (old
> > prefix 0x%08x, new 0x%08x)\n",
> > + pci_domain_nr, bus->logical_dev_id_prefix,
> > + logical_dev_id_prefix);
> > + ret = -EEXIST;
> > + }
> > +
> > + goto out_free;
> > + }
> > +
> > + new->pci_domain_nr = pci_domain_nr;
> > + new->logical_dev_id_prefix = logical_dev_id_prefix;
> > + list_add(&new->list, &hv_pci_bus_list);
> > + spin_unlock(&hv_pci_bus_lock);
> > + return 0;
> > +
> > +out_free:
> > + spin_unlock(&hv_pci_bus_lock);
> > + kfree(new);
> > + return ret;
> > +}
> > +EXPORT_SYMBOL_FOR_MODULES(hv_iommu_register_pci_bus, "pci-hyperv");
> > +
> > +void hv_iommu_unregister_pci_bus(int pci_domain_nr)
> > +{
> > + struct hv_pci_busdata *bus, *tmp;
> > +
> > + spin_lock(&hv_pci_bus_lock);
> > + list_for_each_entry_safe(bus, tmp, &hv_pci_bus_list, list) {
> > + if (bus->pci_domain_nr == pci_domain_nr) {
> > + list_del(&bus->list);
> > + kfree(bus);
> > + break;
> > + }
> > + }
> > + spin_unlock(&hv_pci_bus_lock);
> > +}
> > +EXPORT_SYMBOL_FOR_MODULES(hv_iommu_unregister_pci_bus, "pci-hyperv");
> > +
> > +/*
> > + * Look up the logical device ID prefix registered for @pci_domain_nr.
> > + * Returns 0 on success with *prefix filled in; -ENODEV if no entry is
> > + * registered for that PCI domain.
> > + */
> > +int hv_iommu_lookup_logical_dev_id(int pci_domain_nr, u32 *prefix)
> > +{
> > + struct hv_pci_busdata *bus;
> > + int ret = -ENODEV;
> > +
> > + spin_lock(&hv_pci_bus_lock);
> > + list_for_each_entry(bus, &hv_pci_bus_list, list) {
> > + if (bus->pci_domain_nr == pci_domain_nr) {
> > + *prefix = bus->logical_dev_id_prefix;
> > + ret = 0;
> > + break;
> > + }
> > + }
> > + spin_unlock(&hv_pci_bus_lock);
> > + return ret;
> > +}
>
> I started thinking about the mechanism here because it's somewhat
> annoying that it takes 77 lines of code (sans comments) to manage
> this simple little mapping. I also started thinking about how many entries
> are likely to be in the mapping. A guest VM probably has fewer than 10
> entries unless it has multiple NICs and maybe some GPUs. But this code
> is also intended to be used by the Linux-as-root code, and I'm thinking
> that the number of PCI devices managed by the root could easily be a
> hundred or more if the root is managing a couple dozen VMs on a large
> physical server. Searching a linked list with 100 or more entries could be
> a bit slow.
>
> If only the guest scenario were needed, you could declare a static
> array with 64 entries (64 is an arbitrary upper bound), and just search
> through the array instead of having to allocate memory, deal with
> allocation failures, and deal with linked lists. But a fixed size array
> would need to be much bigger for the root scenario, and you would
> still be doing a linear search.
>
> A better alternative to consider is rhashtable, which is an existing
> Linux kernel facility. Based on what an AI bot generated for me, the
> code for setting up and using rhashtable is straightforward, and
> would probably result in far fewer than 77 lines of code. Lookups
> would also be faster than a linear search, at least for the root case
> with more than just a few entries. I'd suggest looking at rhashtable
> to see whether you like how the resulting code comes out for this
> use case, and whether it really is simpler than a roll-your-own linked
> list.
>
Thank you so much for thinking this through, Michael! That is really
a valid concern.
How about using XArray? It might be more lightweight compared with
rhashtable. Using pci_domain_nr as the key and prefix as the value.
Maybe sth. like:
┃
static DEFINE_XARRAY(hv_pci_bus_xa);
int hv_iommu_register_pci_bus(int domain_nr, u32 prefix)
{
return xa_insert(&hv_pci_bus_xa, domain_nr,
xa_mk_value(prefix), GFP_KERNEL);
}
┃
void hv_iommu_unregister_pci_bus(int domain_nr)
{
xa_erase(&hv_pci_bus_xa, domain_nr);
}
int hv_iommu_lookup_logical_dev_id(int domain_nr, u32 *prefix)
{
void *entry = xa_load(&hv_pci_bus_xa, domain_nr);
if (!entry)
┃
return -ENODEV;
*prefix = xa_to_value(entry);
return 0;
┃
}
B.R.
Yu
┃
> Michael
>
> > +#endif /* CONFIG_HYPERV_PVIOMMU */
> > diff --git a/drivers/pci/controller/pci-hyperv.c
> > b/drivers/pci/controller/pci-hyperv.c
> > index cfc8fa403dad..58ca2c95bd10 100644
> > --- a/drivers/pci/controller/pci-hyperv.c
> > +++ b/drivers/pci/controller/pci-hyperv.c
> > @@ -641,10 +641,7 @@ static void hv_irq_retarget_interrupt(struct irq_data
> > *data)
> > params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
> > params->int_entry.msi_entry.address.as_uint32 = int_desc->address &
> > 0xffffffff;
> > params->int_entry.msi_entry.data.as_uint32 = int_desc->data;
> > - params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
> > - (hbus->hdev->dev_instance.b[4] << 16) |
> > - (hbus->hdev->dev_instance.b[7] << 8) |
> > - (hbus->hdev->dev_instance.b[6] & 0xf8) |
> > + params->device_id = hv_build_logical_dev_id_prefix(hbus->hdev) |
> > PCI_FUNC(pdev->devfn);
> > params->int_target.vector = hv_msi_get_int_vector(data);
> >
> > @@ -3715,6 +3712,7 @@ static int hv_pci_probe(struct hv_device *hdev,
> > struct hv_pcibus_device *hbus;
> > int ret, dom;
> > u16 dom_req;
> > + u32 prefix;
> > char *name;
> >
> > bridge = devm_pci_alloc_host_bridge(&hdev->device, 0);
> > @@ -3857,13 +3855,22 @@ static int hv_pci_probe(struct hv_device *hdev,
> >
> > hbus->state = hv_pcibus_probed;
> >
> > - ret = create_root_hv_pci_bus(hbus);
> > + /* Notify pvIOMMU before any device on the bus is scanned. */
> > + prefix = hv_build_logical_dev_id_prefix(hdev);
> > +
> > + ret = hv_iommu_register_pci_bus(dom, prefix);
> > if (ret)
> > goto free_windows;
> >
> > + ret = create_root_hv_pci_bus(hbus);
> > + if (ret)
> > + goto unregister_pviommu;
> > +
> > mutex_unlock(&hbus->state_lock);
> > return 0;
> >
> > +unregister_pviommu:
> > + hv_iommu_unregister_pci_bus(dom);
> > free_windows:
> > hv_pci_free_bridge_windows(hbus);
> > exit_d0:
> > @@ -3977,6 +3984,8 @@ static void hv_pci_remove(struct hv_device *hdev)
> >
> > hbus = hv_get_drvdata(hdev);
> > if (hbus->state == hv_pcibus_installed) {
> > + int dom = hbus->bridge->domain_nr;
> > +
> > tasklet_disable(&hdev->channel->callback_event);
> > hbus->state = hv_pcibus_removing;
> > tasklet_enable(&hdev->channel->callback_event);
> > @@ -3994,6 +4003,8 @@ static void hv_pci_remove(struct hv_device *hdev)
> > hv_pci_remove_slots(hbus);
> > pci_remove_root_bus(hbus->bridge->bus);
> > pci_unlock_rescan_remove();
> > +
> > + hv_iommu_unregister_pci_bus(dom);
> > }
> >
> > hv_pci_bus_exit(hdev, false);
> > diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
> > index bf601d67cecb..f65344f2bb81 100644
> > --- a/include/asm-generic/mshyperv.h
> > +++ b/include/asm-generic/mshyperv.h
> > @@ -73,6 +73,19 @@ extern enum hv_partition_type hv_curr_partition_type;
> > extern void * __percpu *hyperv_pcpu_input_arg;
> > extern void * __percpu *hyperv_pcpu_output_arg;
> >
> > +#ifdef CONFIG_HYPERV_PVIOMMU
> > +int hv_iommu_register_pci_bus(int pci_domain_nr, u32
> > logical_dev_id_prefix);
> > +void hv_iommu_unregister_pci_bus(int pci_domain_nr);
> > +int hv_iommu_lookup_logical_dev_id(int pci_domain_nr, u32 *prefix);
> > +#else
> > +static inline int hv_iommu_register_pci_bus(int pci_domain_nr,
> > + u32 logical_dev_id_prefix)
> > +{
> > + return 0;
> > +}
> > +static inline void hv_iommu_unregister_pci_bus(int pci_domain_nr) { }
> > +#endif
> > +
> > u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
> > u64 hv_do_fast_hypercall8(u16 control, u64 input8);
> > u64 hv_do_fast_hypercall16(u16 control, u64 input1, u64 input2);
> > diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
> > index 9de2c8d6037a..10ee2c462d7c 100644
> > --- a/include/linux/hyperv.h
> > +++ b/include/linux/hyperv.h
> > @@ -1287,6 +1287,14 @@ struct hv_device {
> > #define device_to_hv_device(d) container_of_const(d, struct hv_device,
> > device)
> > #define drv_to_hv_drv(d) container_of_const(d, struct hv_driver, driver)
> >
> > +static inline u32 hv_build_logical_dev_id_prefix(struct hv_device *hdev)
> > +{
> > + return ((u32)hdev->dev_instance.b[5] << 24) |
> > + ((u32)hdev->dev_instance.b[4] << 16) |
> > + ((u32)hdev->dev_instance.b[7] << 8) |
> > + (hdev->dev_instance.b[6] & 0xf8u);
> > +}
> > +
> > static inline void hv_set_drvdata(struct hv_device *dev, void *data)
> > {
> > dev_set_drvdata(&dev->device, data);
> > --
> > 2.52.0
> >
>
