drm/amdkfd: Add topology support for CPUs
Currently, the KFD topology information is generated by parsing the CRAT (ACPI) table. However, at present CRAT table is available only for AMD APUs. To support CPUs on systems without a CRAT table, the KFD driver will create a Virtual CRAT (VCRAT) table and then the existing code will parse that table to generate topology. Signed-off-by: Harish Kasiviswanathan <Harish.Kasiviswanathan@amd.com> Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com> Reviewed-by: Oded Gabbay <oded.gabbay@gmail.com> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
This commit is contained in:
parent
bc0c75a367
commit
520b8fb755
|
@ -21,10 +21,9 @@
|
|||
*/
|
||||
#include <linux/acpi.h>
|
||||
#include "kfd_crat.h"
|
||||
#include "kfd_priv.h"
|
||||
#include "kfd_topology.h"
|
||||
|
||||
extern struct kfd_system_properties sys_props;
|
||||
|
||||
static void kfd_populated_cu_info_cpu(struct kfd_topology_device *dev,
|
||||
struct crat_subtype_computeunit *cu)
|
||||
{
|
||||
|
@ -281,7 +280,7 @@ static int kfd_parse_subtype(struct crat_subtype_generic *sub_type_hdr,
|
|||
int kfd_parse_crat_table(void *crat_image, struct list_head *device_list,
|
||||
uint32_t proximity_domain)
|
||||
{
|
||||
struct kfd_topology_device *top_dev;
|
||||
struct kfd_topology_device *top_dev = NULL;
|
||||
struct crat_subtype_generic *sub_type_hdr;
|
||||
uint16_t node_id;
|
||||
int ret = 0;
|
||||
|
@ -314,10 +313,10 @@ int kfd_parse_crat_table(void *crat_image, struct list_head *device_list,
|
|||
goto err;
|
||||
}
|
||||
|
||||
sys_props.platform_id =
|
||||
(*((uint64_t *)crat_table->oem_id)) & CRAT_OEMID_64BIT_MASK;
|
||||
sys_props.platform_oem = *((uint64_t *)crat_table->oem_table_id);
|
||||
sys_props.platform_rev = crat_table->revision;
|
||||
memcpy(top_dev->oem_id, crat_table->oem_id, CRAT_OEMID_LENGTH);
|
||||
memcpy(top_dev->oem_table_id, crat_table->oem_table_id,
|
||||
CRAT_OEMTABLEID_LENGTH);
|
||||
top_dev->oem_revision = crat_table->oem_revision;
|
||||
|
||||
sub_type_hdr = (struct crat_subtype_generic *)(crat_table+1);
|
||||
while ((char *)sub_type_hdr + sizeof(struct crat_subtype_generic) <
|
||||
|
@ -385,8 +384,312 @@ int kfd_create_crat_image_acpi(void **crat_image, size_t *size)
|
|||
return 0;
|
||||
}
|
||||
|
||||
/*
|
||||
* kfd_destroy_crat_image
|
||||
/* Memory required to create Virtual CRAT.
|
||||
* Since there is no easy way to predict the amount of memory required, the
|
||||
* following amount are allocated for CPU and GPU Virtual CRAT. This is
|
||||
* expected to cover all known conditions. But to be safe additional check
|
||||
* is put in the code to ensure we don't overwrite.
|
||||
*/
|
||||
#define VCRAT_SIZE_FOR_CPU (2 * PAGE_SIZE)
|
||||
#define VCRAT_SIZE_FOR_GPU (3 * PAGE_SIZE)
|
||||
|
||||
/* kfd_fill_cu_for_cpu - Fill in Compute info for the given CPU NUMA node
|
||||
*
|
||||
* @numa_node_id: CPU NUMA node id
|
||||
* @avail_size: Available size in the memory
|
||||
* @sub_type_hdr: Memory into which compute info will be filled in
|
||||
*
|
||||
* Return 0 if successful else return -ve value
|
||||
*/
|
||||
static int kfd_fill_cu_for_cpu(int numa_node_id, int *avail_size,
|
||||
int proximity_domain,
|
||||
struct crat_subtype_computeunit *sub_type_hdr)
|
||||
{
|
||||
const struct cpumask *cpumask;
|
||||
|
||||
*avail_size -= sizeof(struct crat_subtype_computeunit);
|
||||
if (*avail_size < 0)
|
||||
return -ENOMEM;
|
||||
|
||||
memset(sub_type_hdr, 0, sizeof(struct crat_subtype_computeunit));
|
||||
|
||||
/* Fill in subtype header data */
|
||||
sub_type_hdr->type = CRAT_SUBTYPE_COMPUTEUNIT_AFFINITY;
|
||||
sub_type_hdr->length = sizeof(struct crat_subtype_computeunit);
|
||||
sub_type_hdr->flags = CRAT_SUBTYPE_FLAGS_ENABLED;
|
||||
|
||||
cpumask = cpumask_of_node(numa_node_id);
|
||||
|
||||
/* Fill in CU data */
|
||||
sub_type_hdr->flags |= CRAT_CU_FLAGS_CPU_PRESENT;
|
||||
sub_type_hdr->proximity_domain = proximity_domain;
|
||||
sub_type_hdr->processor_id_low = kfd_numa_node_to_apic_id(numa_node_id);
|
||||
if (sub_type_hdr->processor_id_low == -1)
|
||||
return -EINVAL;
|
||||
|
||||
sub_type_hdr->num_cpu_cores = cpumask_weight(cpumask);
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* kfd_fill_mem_info_for_cpu - Fill in Memory info for the given CPU NUMA node
|
||||
*
|
||||
* @numa_node_id: CPU NUMA node id
|
||||
* @avail_size: Available size in the memory
|
||||
* @sub_type_hdr: Memory into which compute info will be filled in
|
||||
*
|
||||
* Return 0 if successful else return -ve value
|
||||
*/
|
||||
static int kfd_fill_mem_info_for_cpu(int numa_node_id, int *avail_size,
|
||||
int proximity_domain,
|
||||
struct crat_subtype_memory *sub_type_hdr)
|
||||
{
|
||||
uint64_t mem_in_bytes = 0;
|
||||
pg_data_t *pgdat;
|
||||
int zone_type;
|
||||
|
||||
*avail_size -= sizeof(struct crat_subtype_memory);
|
||||
if (*avail_size < 0)
|
||||
return -ENOMEM;
|
||||
|
||||
memset(sub_type_hdr, 0, sizeof(struct crat_subtype_memory));
|
||||
|
||||
/* Fill in subtype header data */
|
||||
sub_type_hdr->type = CRAT_SUBTYPE_MEMORY_AFFINITY;
|
||||
sub_type_hdr->length = sizeof(struct crat_subtype_memory);
|
||||
sub_type_hdr->flags = CRAT_SUBTYPE_FLAGS_ENABLED;
|
||||
|
||||
/* Fill in Memory Subunit data */
|
||||
|
||||
/* Unlike si_meminfo, si_meminfo_node is not exported. So
|
||||
* the following lines are duplicated from si_meminfo_node
|
||||
* function
|
||||
*/
|
||||
pgdat = NODE_DATA(numa_node_id);
|
||||
for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++)
|
||||
mem_in_bytes += pgdat->node_zones[zone_type].managed_pages;
|
||||
mem_in_bytes <<= PAGE_SHIFT;
|
||||
|
||||
sub_type_hdr->length_low = lower_32_bits(mem_in_bytes);
|
||||
sub_type_hdr->length_high = upper_32_bits(mem_in_bytes);
|
||||
sub_type_hdr->proximity_domain = proximity_domain;
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
static int kfd_fill_iolink_info_for_cpu(int numa_node_id, int *avail_size,
|
||||
uint32_t *num_entries,
|
||||
struct crat_subtype_iolink *sub_type_hdr)
|
||||
{
|
||||
int nid;
|
||||
struct cpuinfo_x86 *c = &cpu_data(0);
|
||||
uint8_t link_type;
|
||||
|
||||
if (c->x86_vendor == X86_VENDOR_AMD)
|
||||
link_type = CRAT_IOLINK_TYPE_HYPERTRANSPORT;
|
||||
else
|
||||
link_type = CRAT_IOLINK_TYPE_QPI_1_1;
|
||||
|
||||
*num_entries = 0;
|
||||
|
||||
/* Create IO links from this node to other CPU nodes */
|
||||
for_each_online_node(nid) {
|
||||
if (nid == numa_node_id) /* node itself */
|
||||
continue;
|
||||
|
||||
*avail_size -= sizeof(struct crat_subtype_iolink);
|
||||
if (*avail_size < 0)
|
||||
return -ENOMEM;
|
||||
|
||||
memset(sub_type_hdr, 0, sizeof(struct crat_subtype_iolink));
|
||||
|
||||
/* Fill in subtype header data */
|
||||
sub_type_hdr->type = CRAT_SUBTYPE_IOLINK_AFFINITY;
|
||||
sub_type_hdr->length = sizeof(struct crat_subtype_iolink);
|
||||
sub_type_hdr->flags = CRAT_SUBTYPE_FLAGS_ENABLED;
|
||||
|
||||
/* Fill in IO link data */
|
||||
sub_type_hdr->proximity_domain_from = numa_node_id;
|
||||
sub_type_hdr->proximity_domain_to = nid;
|
||||
sub_type_hdr->io_interface_type = link_type;
|
||||
|
||||
(*num_entries)++;
|
||||
sub_type_hdr++;
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* kfd_create_vcrat_image_cpu - Create Virtual CRAT for CPU
|
||||
*
|
||||
* @pcrat_image: Fill in VCRAT for CPU
|
||||
* @size: [IN] allocated size of crat_image.
|
||||
* [OUT] actual size of data filled in crat_image
|
||||
*/
|
||||
static int kfd_create_vcrat_image_cpu(void *pcrat_image, size_t *size)
|
||||
{
|
||||
struct crat_header *crat_table = (struct crat_header *)pcrat_image;
|
||||
struct acpi_table_header *acpi_table;
|
||||
acpi_status status;
|
||||
struct crat_subtype_generic *sub_type_hdr;
|
||||
int avail_size = *size;
|
||||
int numa_node_id;
|
||||
uint32_t entries = 0;
|
||||
int ret = 0;
|
||||
|
||||
if (!pcrat_image || avail_size < VCRAT_SIZE_FOR_CPU)
|
||||
return -EINVAL;
|
||||
|
||||
/* Fill in CRAT Header.
|
||||
* Modify length and total_entries as subunits are added.
|
||||
*/
|
||||
avail_size -= sizeof(struct crat_header);
|
||||
if (avail_size < 0)
|
||||
return -ENOMEM;
|
||||
|
||||
memset(crat_table, 0, sizeof(struct crat_header));
|
||||
memcpy(&crat_table->signature, CRAT_SIGNATURE,
|
||||
sizeof(crat_table->signature));
|
||||
crat_table->length = sizeof(struct crat_header);
|
||||
|
||||
status = acpi_get_table("DSDT", 0, &acpi_table);
|
||||
if (status == AE_NOT_FOUND)
|
||||
pr_warn("DSDT table not found for OEM information\n");
|
||||
else {
|
||||
crat_table->oem_revision = acpi_table->revision;
|
||||
memcpy(crat_table->oem_id, acpi_table->oem_id,
|
||||
CRAT_OEMID_LENGTH);
|
||||
memcpy(crat_table->oem_table_id, acpi_table->oem_table_id,
|
||||
CRAT_OEMTABLEID_LENGTH);
|
||||
}
|
||||
crat_table->total_entries = 0;
|
||||
crat_table->num_domains = 0;
|
||||
|
||||
sub_type_hdr = (struct crat_subtype_generic *)(crat_table+1);
|
||||
|
||||
for_each_online_node(numa_node_id) {
|
||||
if (kfd_numa_node_to_apic_id(numa_node_id) == -1)
|
||||
continue;
|
||||
|
||||
/* Fill in Subtype: Compute Unit */
|
||||
ret = kfd_fill_cu_for_cpu(numa_node_id, &avail_size,
|
||||
crat_table->num_domains,
|
||||
(struct crat_subtype_computeunit *)sub_type_hdr);
|
||||
if (ret < 0)
|
||||
return ret;
|
||||
crat_table->length += sub_type_hdr->length;
|
||||
crat_table->total_entries++;
|
||||
|
||||
sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
|
||||
sub_type_hdr->length);
|
||||
|
||||
/* Fill in Subtype: Memory */
|
||||
ret = kfd_fill_mem_info_for_cpu(numa_node_id, &avail_size,
|
||||
crat_table->num_domains,
|
||||
(struct crat_subtype_memory *)sub_type_hdr);
|
||||
if (ret < 0)
|
||||
return ret;
|
||||
crat_table->length += sub_type_hdr->length;
|
||||
crat_table->total_entries++;
|
||||
|
||||
sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
|
||||
sub_type_hdr->length);
|
||||
|
||||
/* Fill in Subtype: IO Link */
|
||||
ret = kfd_fill_iolink_info_for_cpu(numa_node_id, &avail_size,
|
||||
&entries,
|
||||
(struct crat_subtype_iolink *)sub_type_hdr);
|
||||
if (ret < 0)
|
||||
return ret;
|
||||
crat_table->length += (sub_type_hdr->length * entries);
|
||||
crat_table->total_entries += entries;
|
||||
|
||||
sub_type_hdr = (typeof(sub_type_hdr))((char *)sub_type_hdr +
|
||||
sub_type_hdr->length * entries);
|
||||
|
||||
crat_table->num_domains++;
|
||||
}
|
||||
|
||||
/* TODO: Add cache Subtype for CPU.
|
||||
* Currently, CPU cache information is available in function
|
||||
* detect_cache_attributes(cpu) defined in the file
|
||||
* ./arch/x86/kernel/cpu/intel_cacheinfo.c. This function is not
|
||||
* exported and to get the same information the code needs to be
|
||||
* duplicated.
|
||||
*/
|
||||
|
||||
*size = crat_table->length;
|
||||
pr_info("Virtual CRAT table created for CPU\n");
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
/* kfd_create_crat_image_virtual - Allocates memory for CRAT image and
|
||||
* creates a Virtual CRAT (VCRAT) image
|
||||
*
|
||||
* NOTE: Call kfd_destroy_crat_image to free CRAT image memory
|
||||
*
|
||||
* @crat_image: VCRAT image created because ACPI does not have a
|
||||
* CRAT for this device
|
||||
* @size: [OUT] size of virtual crat_image
|
||||
* @flags: COMPUTE_UNIT_CPU - Create VCRAT for CPU device
|
||||
* COMPUTE_UNIT_GPU - Create VCRAT for GPU
|
||||
* (COMPUTE_UNIT_CPU | COMPUTE_UNIT_GPU) - Create VCRAT for APU
|
||||
* -- this option is not currently implemented.
|
||||
* The assumption is that all AMD APUs will have CRAT
|
||||
* @kdev: Valid kfd_device required if flags contain COMPUTE_UNIT_GPU
|
||||
*
|
||||
* Return 0 if successful else return -ve value
|
||||
*/
|
||||
int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
|
||||
int flags, struct kfd_dev *kdev,
|
||||
uint32_t proximity_domain)
|
||||
{
|
||||
void *pcrat_image = NULL;
|
||||
int ret = 0;
|
||||
|
||||
if (!crat_image)
|
||||
return -EINVAL;
|
||||
|
||||
*crat_image = NULL;
|
||||
|
||||
/* Allocate one VCRAT_SIZE_FOR_CPU for CPU virtual CRAT image and
|
||||
* VCRAT_SIZE_FOR_GPU for GPU virtual CRAT image. This should cover
|
||||
* all the current conditions. A check is put not to overwrite beyond
|
||||
* allocated size
|
||||
*/
|
||||
switch (flags) {
|
||||
case COMPUTE_UNIT_CPU:
|
||||
pcrat_image = kmalloc(VCRAT_SIZE_FOR_CPU, GFP_KERNEL);
|
||||
if (!pcrat_image)
|
||||
return -ENOMEM;
|
||||
*size = VCRAT_SIZE_FOR_CPU;
|
||||
ret = kfd_create_vcrat_image_cpu(pcrat_image, size);
|
||||
break;
|
||||
case COMPUTE_UNIT_GPU:
|
||||
/* TODO: */
|
||||
ret = -EINVAL;
|
||||
pr_err("VCRAT not implemented for dGPU\n");
|
||||
break;
|
||||
case (COMPUTE_UNIT_CPU | COMPUTE_UNIT_GPU):
|
||||
/* TODO: */
|
||||
ret = -EINVAL;
|
||||
pr_err("VCRAT not implemented for APU\n");
|
||||
break;
|
||||
default:
|
||||
ret = -EINVAL;
|
||||
}
|
||||
|
||||
if (!ret)
|
||||
*crat_image = pcrat_image;
|
||||
else
|
||||
kfree(pcrat_image);
|
||||
|
||||
return ret;
|
||||
}
|
||||
|
||||
|
||||
/* kfd_destroy_crat_image
|
||||
*
|
||||
* @crat_image: [IN] - crat_image from kfd_create_crat_image_xxx(..)
|
||||
*
|
||||
|
|
|
@ -44,6 +44,10 @@
|
|||
|
||||
#define CRAT_OEMID_64BIT_MASK ((1ULL << (CRAT_OEMID_LENGTH * 8)) - 1)
|
||||
|
||||
/* Compute Unit flags */
|
||||
#define COMPUTE_UNIT_CPU (1 << 0) /* Create Virtual CRAT for CPU */
|
||||
#define COMPUTE_UNIT_GPU (1 << 1) /* Create Virtual CRAT for GPU */
|
||||
|
||||
struct crat_header {
|
||||
uint32_t signature;
|
||||
uint32_t length;
|
||||
|
@ -302,9 +306,14 @@ struct cdit_header {
|
|||
|
||||
#pragma pack()
|
||||
|
||||
struct kfd_dev;
|
||||
|
||||
int kfd_create_crat_image_acpi(void **crat_image, size_t *size);
|
||||
void kfd_destroy_crat_image(void *crat_image);
|
||||
int kfd_parse_crat_table(void *crat_image, struct list_head *device_list,
|
||||
uint32_t proximity_domain);
|
||||
int kfd_create_crat_image_virtual(void **crat_image, size_t *size,
|
||||
int flags, struct kfd_dev *kdev,
|
||||
uint32_t proximity_domain);
|
||||
|
||||
#endif /* KFD_CRAT_H_INCLUDED */
|
||||
|
|
|
@ -671,6 +671,7 @@ int kfd_topology_remove_device(struct kfd_dev *gpu);
|
|||
struct kfd_dev *kfd_device_by_id(uint32_t gpu_id);
|
||||
struct kfd_dev *kfd_device_by_pci_dev(const struct pci_dev *pdev);
|
||||
int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev);
|
||||
int kfd_numa_node_to_apic_id(int numa_node_id);
|
||||
|
||||
/* Interrupts */
|
||||
int kfd_interrupt_init(struct kfd_dev *dev);
|
||||
|
|
|
@ -28,6 +28,8 @@
|
|||
#include <linux/hash.h>
|
||||
#include <linux/cpufreq.h>
|
||||
#include <linux/log2.h>
|
||||
#include <linux/dmi.h>
|
||||
#include <linux/atomic.h>
|
||||
|
||||
#include "kfd_priv.h"
|
||||
#include "kfd_crat.h"
|
||||
|
@ -36,9 +38,10 @@
|
|||
|
||||
/* topology_device_list - Master list of all topology devices */
|
||||
static struct list_head topology_device_list;
|
||||
struct kfd_system_properties sys_props;
|
||||
static struct kfd_system_properties sys_props;
|
||||
|
||||
static DECLARE_RWSEM(topology_lock);
|
||||
static atomic_t topology_crat_proximity_domain;
|
||||
|
||||
struct kfd_dev *kfd_device_by_id(uint32_t gpu_id)
|
||||
{
|
||||
|
@ -691,12 +694,92 @@ static void kfd_topology_update_device_list(struct list_head *temp_list,
|
|||
}
|
||||
}
|
||||
|
||||
static void kfd_debug_print_topology(void)
|
||||
{
|
||||
struct kfd_topology_device *dev;
|
||||
|
||||
down_read(&topology_lock);
|
||||
|
||||
dev = list_last_entry(&topology_device_list,
|
||||
struct kfd_topology_device, list);
|
||||
if (dev) {
|
||||
if (dev->node_props.cpu_cores_count &&
|
||||
dev->node_props.simd_count) {
|
||||
pr_info("Topology: Add APU node [0x%0x:0x%0x]\n",
|
||||
dev->node_props.device_id,
|
||||
dev->node_props.vendor_id);
|
||||
} else if (dev->node_props.cpu_cores_count)
|
||||
pr_info("Topology: Add CPU node\n");
|
||||
else if (dev->node_props.simd_count)
|
||||
pr_info("Topology: Add dGPU node [0x%0x:0x%0x]\n",
|
||||
dev->node_props.device_id,
|
||||
dev->node_props.vendor_id);
|
||||
}
|
||||
up_read(&topology_lock);
|
||||
}
|
||||
|
||||
/* Helper function for intializing platform_xx members of
|
||||
* kfd_system_properties. Uses OEM info from the last CPU/APU node.
|
||||
*/
|
||||
static void kfd_update_system_properties(void)
|
||||
{
|
||||
struct kfd_topology_device *dev;
|
||||
|
||||
down_read(&topology_lock);
|
||||
dev = list_last_entry(&topology_device_list,
|
||||
struct kfd_topology_device, list);
|
||||
if (dev) {
|
||||
sys_props.platform_id =
|
||||
(*((uint64_t *)dev->oem_id)) & CRAT_OEMID_64BIT_MASK;
|
||||
sys_props.platform_oem = *((uint64_t *)dev->oem_table_id);
|
||||
sys_props.platform_rev = dev->oem_revision;
|
||||
}
|
||||
up_read(&topology_lock);
|
||||
}
|
||||
|
||||
static void find_system_memory(const struct dmi_header *dm,
|
||||
void *private)
|
||||
{
|
||||
struct kfd_mem_properties *mem;
|
||||
u16 mem_width, mem_clock;
|
||||
struct kfd_topology_device *kdev =
|
||||
(struct kfd_topology_device *)private;
|
||||
const u8 *dmi_data = (const u8 *)(dm + 1);
|
||||
|
||||
if (dm->type == DMI_ENTRY_MEM_DEVICE && dm->length >= 0x15) {
|
||||
mem_width = (u16)(*(const u16 *)(dmi_data + 0x6));
|
||||
mem_clock = (u16)(*(const u16 *)(dmi_data + 0x11));
|
||||
list_for_each_entry(mem, &kdev->mem_props, list) {
|
||||
if (mem_width != 0xFFFF && mem_width != 0)
|
||||
mem->width = mem_width;
|
||||
if (mem_clock != 0)
|
||||
mem->mem_clk_max = mem_clock;
|
||||
}
|
||||
}
|
||||
}
|
||||
/* kfd_add_non_crat_information - Add information that is not currently
|
||||
* defined in CRAT but is necessary for KFD topology
|
||||
* @dev - topology device to which addition info is added
|
||||
*/
|
||||
static void kfd_add_non_crat_information(struct kfd_topology_device *kdev)
|
||||
{
|
||||
/* Check if CPU only node. */
|
||||
if (!kdev->gpu) {
|
||||
/* Add system memory information */
|
||||
dmi_walk(find_system_memory, kdev);
|
||||
}
|
||||
/* TODO: For GPU node, rearrange code from kfd_topology_add_device */
|
||||
}
|
||||
|
||||
int kfd_topology_init(void)
|
||||
{
|
||||
void *crat_image = NULL;
|
||||
size_t image_size = 0;
|
||||
int ret;
|
||||
struct list_head temp_topology_device_list;
|
||||
int cpu_only_node = 0;
|
||||
struct kfd_topology_device *kdev;
|
||||
int proximity_domain;
|
||||
|
||||
/* topology_device_list - Master list of all topology devices
|
||||
* temp_topology_device_list - temporary list created while parsing CRAT
|
||||
|
@ -711,36 +794,78 @@ int kfd_topology_init(void)
|
|||
|
||||
memset(&sys_props, 0, sizeof(sys_props));
|
||||
|
||||
/* Proximity domains in ACPI CRAT tables start counting at
|
||||
* 0. The same should be true for virtual CRAT tables created
|
||||
* at this stage. GPUs added later in kfd_topology_add_device
|
||||
* use a counter.
|
||||
*/
|
||||
proximity_domain = 0;
|
||||
|
||||
/*
|
||||
* Get the CRAT image from the ACPI
|
||||
* Get the CRAT image from the ACPI. If ACPI doesn't have one
|
||||
* create a virtual CRAT.
|
||||
* NOTE: The current implementation expects all AMD APUs to have
|
||||
* CRAT. If no CRAT is available, it is assumed to be a CPU
|
||||
*/
|
||||
ret = kfd_create_crat_image_acpi(&crat_image, &image_size);
|
||||
if (!ret) {
|
||||
ret = kfd_parse_crat_table(crat_image,
|
||||
&temp_topology_device_list, 0);
|
||||
if (ret)
|
||||
&temp_topology_device_list,
|
||||
proximity_domain);
|
||||
if (ret) {
|
||||
kfd_release_topology_device_list(
|
||||
&temp_topology_device_list);
|
||||
kfd_destroy_crat_image(crat_image);
|
||||
crat_image = NULL;
|
||||
}
|
||||
}
|
||||
|
||||
if (!crat_image) {
|
||||
ret = kfd_create_crat_image_virtual(&crat_image, &image_size,
|
||||
COMPUTE_UNIT_CPU, NULL,
|
||||
proximity_domain);
|
||||
cpu_only_node = 1;
|
||||
if (ret) {
|
||||
pr_err("Error creating VCRAT table for CPU\n");
|
||||
return ret;
|
||||
}
|
||||
|
||||
ret = kfd_parse_crat_table(crat_image,
|
||||
&temp_topology_device_list,
|
||||
proximity_domain);
|
||||
if (ret) {
|
||||
pr_err("Error parsing VCRAT table for CPU\n");
|
||||
goto err;
|
||||
} else if (ret == -ENODATA) {
|
||||
/* TODO: Create fake CRAT table */
|
||||
ret = 0;
|
||||
goto err;
|
||||
} else {
|
||||
pr_err("Couldn't get CRAT table size from ACPI\n");
|
||||
goto err;
|
||||
}
|
||||
}
|
||||
|
||||
down_write(&topology_lock);
|
||||
kfd_topology_update_device_list(&temp_topology_device_list,
|
||||
&topology_device_list);
|
||||
atomic_set(&topology_crat_proximity_domain, sys_props.num_devices-1);
|
||||
ret = kfd_topology_update_sysfs();
|
||||
up_write(&topology_lock);
|
||||
|
||||
if (!ret) {
|
||||
sys_props.generation_count++;
|
||||
kfd_update_system_properties();
|
||||
kfd_debug_print_topology();
|
||||
pr_info("Finished initializing topology\n");
|
||||
} else
|
||||
pr_err("Failed to update topology in sysfs ret=%d\n", ret);
|
||||
|
||||
/* For nodes with GPU, this information gets added
|
||||
* when GPU is detected (kfd_topology_add_device).
|
||||
*/
|
||||
if (cpu_only_node) {
|
||||
/* Add additional information to CPU only node created above */
|
||||
down_write(&topology_lock);
|
||||
kdev = list_first_entry(&topology_device_list,
|
||||
struct kfd_topology_device, list);
|
||||
up_write(&topology_lock);
|
||||
kfd_add_non_crat_information(kdev);
|
||||
}
|
||||
|
||||
err:
|
||||
kfd_destroy_crat_image(crat_image);
|
||||
return ret;
|
||||
|
@ -754,21 +879,6 @@ void kfd_topology_shutdown(void)
|
|||
up_write(&topology_lock);
|
||||
}
|
||||
|
||||
static void kfd_debug_print_topology(void)
|
||||
{
|
||||
struct kfd_topology_device *dev;
|
||||
uint32_t i = 0;
|
||||
|
||||
pr_info("DEBUG PRINT OF TOPOLOGY:");
|
||||
list_for_each_entry(dev, &topology_device_list, list) {
|
||||
pr_info("Node: %d\n", i);
|
||||
pr_info("\tGPU assigned: %s\n", (dev->gpu ? "yes" : "no"));
|
||||
pr_info("\tCPU count: %d\n", dev->node_props.cpu_cores_count);
|
||||
pr_info("\tSIMD count: %d\n", dev->node_props.simd_count);
|
||||
i++;
|
||||
}
|
||||
}
|
||||
|
||||
static uint32_t kfd_generate_gpu_id(struct kfd_dev *gpu)
|
||||
{
|
||||
uint32_t hashout;
|
||||
|
@ -954,6 +1064,34 @@ int kfd_topology_enum_kfd_devices(uint8_t idx, struct kfd_dev **kdev)
|
|||
|
||||
}
|
||||
|
||||
static int kfd_cpumask_to_apic_id(const struct cpumask *cpumask)
|
||||
{
|
||||
const struct cpuinfo_x86 *cpuinfo;
|
||||
int first_cpu_of_numa_node;
|
||||
|
||||
if (!cpumask || cpumask == cpu_none_mask)
|
||||
return -1;
|
||||
first_cpu_of_numa_node = cpumask_first(cpumask);
|
||||
if (first_cpu_of_numa_node >= nr_cpu_ids)
|
||||
return -1;
|
||||
cpuinfo = &cpu_data(first_cpu_of_numa_node);
|
||||
|
||||
return cpuinfo->apicid;
|
||||
}
|
||||
|
||||
/* kfd_numa_node_to_apic_id - Returns the APIC ID of the first logical processor
|
||||
* of the given NUMA node (numa_node_id)
|
||||
* Return -1 on failure
|
||||
*/
|
||||
int kfd_numa_node_to_apic_id(int numa_node_id)
|
||||
{
|
||||
if (numa_node_id == -1) {
|
||||
pr_warn("Invalid NUMA Node. Use online CPU mask\n");
|
||||
return kfd_cpumask_to_apic_id(cpu_online_mask);
|
||||
}
|
||||
return kfd_cpumask_to_apic_id(cpumask_of_node(numa_node_id));
|
||||
}
|
||||
|
||||
#if defined(CONFIG_DEBUG_FS)
|
||||
|
||||
int kfd_debugfs_hqds_by_device(struct seq_file *m, void *data)
|
||||
|
|
|
@ -148,6 +148,9 @@ struct kfd_topology_device {
|
|||
struct attribute attr_gpuid;
|
||||
struct attribute attr_name;
|
||||
struct attribute attr_props;
|
||||
uint8_t oem_id[CRAT_OEMID_LENGTH];
|
||||
uint8_t oem_table_id[CRAT_OEMTABLEID_LENGTH];
|
||||
uint32_t oem_revision;
|
||||
};
|
||||
|
||||
struct kfd_system_properties {
|
||||
|
|
Loading…
Reference in New Issue