| Message ID | 20231007201740.30335-3-ankita@nvidia.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v2,1/3] qom: new object to associate device to numa node | expand |
On Sun, 8 Oct 2023 01:47:39 +0530 <ankita@nvidia.com> wrote: > From: Ankit Agrawal <ankita@nvidia.com> > > ACPI spec provides a scheme to associate "Generic Initiators" [1] > (e.g. heterogeneous processors and accelerators, GPUs, and I/O devices with > integrated compute or DMA engines GPUs) with Proximity Domains. This is > achieved using Generic Initiator Affinity Structure in SRAT. During bootup, > Linux kernel parse the ACPI SRAT to determine the PXM ids and create a NUMA > node for each unique PXM ID encountered. Qemu currently do not implement > these structures while building SRAT. > > Add GI structures while building VM ACPI SRAT. The association between > devices and PXM are stored using acpi-generic-initiator object. Lookup > presence of all such objects and use them to build these structures. > > The structure needs a PCI device handle [2] that consists of the device BDF. > The vfio-pci-nohotplug device corresponding to the acpi-generic-initiator > object is located to determine the BDF. > > [1] ACPI Spec 6.5, Section 5.2.16.6 > [2] ACPI Spec 6.5, Table 5.66 > > Signed-off-by: Ankit Agrawal <ankita@nvidia.com> > --- > hw/acpi/acpi-generic-initiator.c | 78 ++++++++++++++++++++++++ > hw/arm/virt-acpi-build.c | 3 + > hw/vfio/pci.c | 2 - > hw/vfio/pci.h | 2 + > include/hw/acpi/acpi-generic-initiator.h | 22 +++++++ > 5 files changed, 105 insertions(+), 2 deletions(-) > > diff --git a/hw/acpi/acpi-generic-initiator.c b/hw/acpi/acpi-generic-initiator.c > index 6406736090..1ae79639be 100644 > --- a/hw/acpi/acpi-generic-initiator.c > +++ b/hw/acpi/acpi-generic-initiator.c > @@ -72,3 +72,81 @@ static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data) > NULL, acpi_generic_initiator_set_node, NULL, > NULL); > } > + > +static int acpi_generic_initiator_list(Object *obj, void *opaque) > +{ > + GSList **list = opaque; > + > + if (object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) { > + *list = g_slist_append(*list, ACPI_GENERIC_INITIATOR(obj)); > + } > + > + object_child_foreach(obj, acpi_generic_initiator_list, opaque); > + return 0; > +} > + > +/* > + * Identify Generic Initiator objects and link them into the list which is > + * returned to the caller. > + * > + * Note: it is the caller's responsibility to free the list to avoid > + * memory leak. > + */ > +static GSList *acpi_generic_initiator_get_list(void) > +{ > + GSList *list = NULL; > + > + object_child_foreach(object_get_root(), acpi_generic_initiator_list, &list); > + return list; > +} > + > +/* > + * ACPI spec, Revision 6.5 > + * 5.2.16.6 Generic Initiator Affinity Structure > + */ > +static void build_srat_generic_initiator_affinity(GArray *table_data, int node, > + PCIDeviceHandle *handle, > + GenericAffinityFlags flags) > +{ > + build_append_int_noprefix(table_data, 5, 1); /* Type */ > + build_append_int_noprefix(table_data, 32, 1); /* Length */ > + build_append_int_noprefix(table_data, 0, 1); /* Reserved */ > + build_append_int_noprefix(table_data, 1, 1); /* Device Handle Type */ > + build_append_int_noprefix(table_data, node, 4); /* Proximity Domain */ > + build_append_int_noprefix(table_data, handle->segment, 2); > + build_append_int_noprefix(table_data, handle->bdf, 2); > + build_append_int_noprefix(table_data, handle->res0, 4); > + build_append_int_noprefix(table_data, handle->res1, 8); Why are we storing reserved fields in the PCIDeviceHandle? This function is already specific to building a PCI Device Handle, so we could just loop build_append_byte() with a fixed zero value here. > + build_append_int_noprefix(table_data, flags, 4); /* Flags */ > + build_append_int_noprefix(table_data, 0, 4); /* Reserved */ > +} > + > +void build_srat_generic_initiator(GArray *table_data) > +{ > + GSList *gi_list, *list = acpi_generic_initiator_get_list(); > + for (gi_list = list; gi_list; gi_list = gi_list->next) { > + AcpiGenericInitiator *gi = gi_list->data; > + Object *o; > + int count; > + > + if (gi->node == MAX_NODES) { > + continue; > + } Why do we have uninitialized AcpiGenericInitiator objects lingering? > + > + o = object_resolve_path_type(gi->device, TYPE_VFIO_PCI_NOHOTPLUG, NULL); TYPE_PCI_DEVICE? Maybe you could check hotpluggable from the device class, but certainly the generic code should not be dependent on being a vfio-pci-nohotplug device. The spec also supports an ACPI object description, so should this be build_srat_generic_pci_initiator()? > + if (!o) { > + continue; > + } > + > + for (count = 0; count < gi->node_count; count++) { > + PCIDeviceHandle dev_handle = {0}; > + PCIDevice *pci_dev = PCI_DEVICE(o); > + > + dev_handle.bdf = pci_dev->devfn; Where does the bus part of the bdf get filled in? > + build_srat_generic_initiator_affinity(table_data, > + gi->node + count, &dev_handle, > + GEN_AFFINITY_ENABLED); Seems like the code that built the AcpiGenericInitiator object should supply the flags. In fact the flag GEN_AFFINITY_ENABLED might be a better indicator to populate the SRAT with the GI than the node value. Thanks, Alex > + } > + } > + g_slist_free(list); > +} > diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c > index 6b674231c2..7337d8076b 100644 > --- a/hw/arm/virt-acpi-build.c > +++ b/hw/arm/virt-acpi-build.c > @@ -58,6 +58,7 @@ > #include "migration/vmstate.h" > #include "hw/acpi/ghes.h" > #include "hw/acpi/viot.h" > +#include "hw/acpi/acpi-generic-initiator.h" > > #define ARM_SPI_BASE 32 > > @@ -558,6 +559,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) > } > } > > + build_srat_generic_initiator(table_data); > + > if (ms->nvdimms_state->is_enabled) { > nvdimm_build_srat(table_data); > } > diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c > index a205c6b113..5e2a7c650a 100644 > --- a/hw/vfio/pci.c > +++ b/hw/vfio/pci.c > @@ -43,8 +43,6 @@ > #include "migration/blocker.h" > #include "migration/qemu-file.h" > > -#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" > - > /* Protected by BQL */ > static KVMRouteChange vfio_route_change; > > diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h > index a2771b9ff3..74ac77a260 100644 > --- a/hw/vfio/pci.h > +++ b/hw/vfio/pci.h > @@ -118,6 +118,8 @@ typedef struct VFIOMSIXInfo { > #define TYPE_VFIO_PCI "vfio-pci" > OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI) > > +#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" > + > struct VFIOPCIDevice { > PCIDevice pdev; > VFIODevice vbasedev; > diff --git a/include/hw/acpi/acpi-generic-initiator.h b/include/hw/acpi/acpi-generic-initiator.h > index e67e6e23b1..e8e2670309 100644 > --- a/include/hw/acpi/acpi-generic-initiator.h > +++ b/include/hw/acpi/acpi-generic-initiator.h > @@ -27,4 +27,26 @@ typedef struct AcpiGenericInitiatorClass { > ObjectClass parent_class; > } AcpiGenericInitiatorClass; > > +/* > + * ACPI 6.5: Table 5-68 Flags - Generic Initiator > + */ > +typedef enum { > + GEN_AFFINITY_NOFLAGS = 0, > + GEN_AFFINITY_ENABLED = (1 << 0), > + GEN_AFFINITY_ARCH_TRANS = (1 << 1), > +} GenericAffinityFlags; > + > +/* > + * ACPI 6.5: Table 5-66 Device Handle - PCI > + * Device Handle definition > + */ > +typedef struct PCIDeviceHandle { > + uint16_t segment; > + uint16_t bdf; > + uint32_t res0; > + uint64_t res1; > +} PCIDeviceHandle; > + > +void build_srat_generic_initiator(GArray *table_data); > + > #endif
>> +static void build_srat_generic_initiator_affinity(GArray *table_data, int node, >> + PCIDeviceHandle *handle, >> + GenericAffinityFlags flags) >> +{ >> + build_append_int_noprefix(table_data, 5, 1); /* Type */ >> + build_append_int_noprefix(table_data, 32, 1); /* Length */ >> + build_append_int_noprefix(table_data, 0, 1); /* Reserved */ >> + build_append_int_noprefix(table_data, 1, 1); /* Device Handle Type */ >> + build_append_int_noprefix(table_data, node, 4); /* Proximity Domain */ >> + build_append_int_noprefix(table_data, handle->segment, 2); >> + build_append_int_noprefix(table_data, handle->bdf, 2); >> + build_append_int_noprefix(table_data, handle->res0, 4); >> + build_append_int_noprefix(table_data, handle->res1, 8); > > Why are we storing reserved fields in the PCIDeviceHandle? This > function is already specific to building a PCI Device Handle, so we > could just loop build_append_byte() with a fixed zero value here. Good point, will make the change. >> +void build_srat_generic_initiator(GArray *table_data) >> +{ >> + GSList *gi_list, *list = acpi_generic_initiator_get_list(); >> + for (gi_list = list; gi_list; gi_list = gi_list->next) { >> + AcpiGenericInitiator *gi = gi_list->data; >> + Object *o; >> + int count; >> + >> + if (gi->node == MAX_NODES) { >> + continue; >> + } > > Why do we have uninitialized AcpiGenericInitiator objects lingering? Right, we don't need the check. >> + >> + o = object_resolve_path_type(gi->device, TYPE_VFIO_PCI_NOHOTPLUG, NULL); > > TYPE_PCI_DEVICE? Maybe you could check hotpluggable from the device > class, but certainly the generic code should not be dependent on being > a vfio-pci-nohotplug device. Understood. > The spec also supports an ACPI object > description, so should this be build_srat_generic_pci_initiator()? Sure, makes sense. >> + if (!o) { >> + continue; >> + } >> + >> + for (count = 0; count < gi->node_count; count++) { >> + PCIDeviceHandle dev_handle = {0}; >> + PCIDevice *pci_dev = PCI_DEVICE(o); >> + >> + dev_handle.bdf = pci_dev->devfn; > > Where does the bus part of the bdf get filled in? Good catch, should have code to added the bus. >> + build_srat_generic_initiator_affinity(table_data, >> + gi->node + count, &dev_handle, >> + GEN_AFFINITY_ENABLED); > > Seems like the code that built the AcpiGenericInitiator object should > supply the flags. In fact the flag GEN_AFFINITY_ENABLED might be a > better indicator to populate the SRAT with the GI than the node value. Yeah, sure.
diff --git a/hw/acpi/acpi-generic-initiator.c b/hw/acpi/acpi-generic-initiator.c index 6406736090..1ae79639be 100644 --- a/hw/acpi/acpi-generic-initiator.c +++ b/hw/acpi/acpi-generic-initiator.c @@ -72,3 +72,81 @@ static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data) NULL, acpi_generic_initiator_set_node, NULL, NULL); } + +static int acpi_generic_initiator_list(Object *obj, void *opaque) +{ + GSList **list = opaque; + + if (object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) { + *list = g_slist_append(*list, ACPI_GENERIC_INITIATOR(obj)); + } + + object_child_foreach(obj, acpi_generic_initiator_list, opaque); + return 0; +} + +/* + * Identify Generic Initiator objects and link them into the list which is + * returned to the caller. + * + * Note: it is the caller's responsibility to free the list to avoid + * memory leak. + */ +static GSList *acpi_generic_initiator_get_list(void) +{ + GSList *list = NULL; + + object_child_foreach(object_get_root(), acpi_generic_initiator_list, &list); + return list; +} + +/* + * ACPI spec, Revision 6.5 + * 5.2.16.6 Generic Initiator Affinity Structure + */ +static void build_srat_generic_initiator_affinity(GArray *table_data, int node, + PCIDeviceHandle *handle, + GenericAffinityFlags flags) +{ + build_append_int_noprefix(table_data, 5, 1); /* Type */ + build_append_int_noprefix(table_data, 32, 1); /* Length */ + build_append_int_noprefix(table_data, 0, 1); /* Reserved */ + build_append_int_noprefix(table_data, 1, 1); /* Device Handle Type */ + build_append_int_noprefix(table_data, node, 4); /* Proximity Domain */ + build_append_int_noprefix(table_data, handle->segment, 2); + build_append_int_noprefix(table_data, handle->bdf, 2); + build_append_int_noprefix(table_data, handle->res0, 4); + build_append_int_noprefix(table_data, handle->res1, 8); + build_append_int_noprefix(table_data, flags, 4); /* Flags */ + build_append_int_noprefix(table_data, 0, 4); /* Reserved */ +} + +void build_srat_generic_initiator(GArray *table_data) +{ + GSList *gi_list, *list = acpi_generic_initiator_get_list(); + for (gi_list = list; gi_list; gi_list = gi_list->next) { + AcpiGenericInitiator *gi = gi_list->data; + Object *o; + int count; + + if (gi->node == MAX_NODES) { + continue; + } + + o = object_resolve_path_type(gi->device, TYPE_VFIO_PCI_NOHOTPLUG, NULL); + if (!o) { + continue; + } + + for (count = 0; count < gi->node_count; count++) { + PCIDeviceHandle dev_handle = {0}; + PCIDevice *pci_dev = PCI_DEVICE(o); + + dev_handle.bdf = pci_dev->devfn; + build_srat_generic_initiator_affinity(table_data, + gi->node + count, &dev_handle, + GEN_AFFINITY_ENABLED); + } + } + g_slist_free(list); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 6b674231c2..7337d8076b 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -58,6 +58,7 @@ #include "migration/vmstate.h" #include "hw/acpi/ghes.h" #include "hw/acpi/viot.h" +#include "hw/acpi/acpi-generic-initiator.h" #define ARM_SPI_BASE 32 @@ -558,6 +559,8 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) } } + build_srat_generic_initiator(table_data); + if (ms->nvdimms_state->is_enabled) { nvdimm_build_srat(table_data); } diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index a205c6b113..5e2a7c650a 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -43,8 +43,6 @@ #include "migration/blocker.h" #include "migration/qemu-file.h" -#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" - /* Protected by BQL */ static KVMRouteChange vfio_route_change; diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index a2771b9ff3..74ac77a260 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -118,6 +118,8 @@ typedef struct VFIOMSIXInfo { #define TYPE_VFIO_PCI "vfio-pci" OBJECT_DECLARE_SIMPLE_TYPE(VFIOPCIDevice, VFIO_PCI) +#define TYPE_VFIO_PCI_NOHOTPLUG "vfio-pci-nohotplug" + struct VFIOPCIDevice { PCIDevice pdev; VFIODevice vbasedev; diff --git a/include/hw/acpi/acpi-generic-initiator.h b/include/hw/acpi/acpi-generic-initiator.h index e67e6e23b1..e8e2670309 100644 --- a/include/hw/acpi/acpi-generic-initiator.h +++ b/include/hw/acpi/acpi-generic-initiator.h @@ -27,4 +27,26 @@ typedef struct AcpiGenericInitiatorClass { ObjectClass parent_class; } AcpiGenericInitiatorClass; +/* + * ACPI 6.5: Table 5-68 Flags - Generic Initiator + */ +typedef enum { + GEN_AFFINITY_NOFLAGS = 0, + GEN_AFFINITY_ENABLED = (1 << 0), + GEN_AFFINITY_ARCH_TRANS = (1 << 1), +} GenericAffinityFlags; + +/* + * ACPI 6.5: Table 5-66 Device Handle - PCI + * Device Handle definition + */ +typedef struct PCIDeviceHandle { + uint16_t segment; + uint16_t bdf; + uint32_t res0; + uint64_t res1; +} PCIDeviceHandle; + +void build_srat_generic_initiator(GArray *table_data); + #endif