drm/amdkfd: Move packet writer functions into ASIC-specific file

This is in preparation for GFXv9 (Vega10) which uses incompatible PM4
packet formats from previous ASIC generations.

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@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:
Felix Kuehling 2018-04-10 17:33:06 -04:00 committed by Oded Gabbay
parent ef568db792
commit f6e27ff19d
4 changed files with 420 additions and 316 deletions

View File

@ -196,15 +196,19 @@ static int allocate_vmid(struct device_queue_manager *dqm,
static int flush_texture_cache_nocpsch(struct kfd_dev *kdev, static int flush_texture_cache_nocpsch(struct kfd_dev *kdev,
struct qcm_process_device *qpd) struct qcm_process_device *qpd)
{ {
uint32_t len; const struct packet_manager_funcs *pmf = qpd->dqm->packets.pmf;
int ret;
if (!qpd->ib_kaddr) if (!qpd->ib_kaddr)
return -ENOMEM; return -ENOMEM;
len = pm_create_release_mem(qpd->ib_base, (uint32_t *)qpd->ib_kaddr); ret = pmf->release_mem(qpd->ib_base, (uint32_t *)qpd->ib_kaddr);
if (ret)
return ret;
return kdev->kfd2kgd->submit_ib(kdev->kgd, KGD_ENGINE_MEC1, qpd->vmid, return kdev->kfd2kgd->submit_ib(kdev->kgd, KGD_ENGINE_MEC1, qpd->vmid,
qpd->ib_base, (uint32_t *)qpd->ib_kaddr, len); qpd->ib_base, (uint32_t *)qpd->ib_kaddr,
pmf->release_mem_size / sizeof(uint32_t));
} }
static void deallocate_vmid(struct device_queue_manager *dqm, static void deallocate_vmid(struct device_queue_manager *dqm,

View File

@ -22,6 +22,9 @@
*/ */
#include "kfd_kernel_queue.h" #include "kfd_kernel_queue.h"
#include "kfd_device_queue_manager.h"
#include "kfd_pm4_headers_vi.h"
#include "kfd_pm4_opcodes.h"
static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev, static bool initialize_vi(struct kernel_queue *kq, struct kfd_dev *dev,
enum kfd_queue_type type, unsigned int queue_size); enum kfd_queue_type type, unsigned int queue_size);
@ -54,3 +57,310 @@ static void uninitialize_vi(struct kernel_queue *kq)
{ {
kfd_gtt_sa_free(kq->dev, kq->eop_mem); kfd_gtt_sa_free(kq->dev, kq->eop_mem);
} }
static unsigned int build_pm4_header(unsigned int opcode, size_t packet_size)
{
union PM4_MES_TYPE_3_HEADER header;
header.u32All = 0;
header.opcode = opcode;
header.count = packet_size / 4 - 2;
header.type = PM4_TYPE_3;
return header.u32All;
}
static int pm_map_process_vi(struct packet_manager *pm, uint32_t *buffer,
struct qcm_process_device *qpd)
{
struct pm4_mes_map_process *packet;
packet = (struct pm4_mes_map_process *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_map_process));
packet->header.u32All = build_pm4_header(IT_MAP_PROCESS,
sizeof(struct pm4_mes_map_process));
packet->bitfields2.diq_enable = (qpd->is_debug) ? 1 : 0;
packet->bitfields2.process_quantum = 1;
packet->bitfields2.pasid = qpd->pqm->process->pasid;
packet->bitfields3.page_table_base = qpd->page_table_base;
packet->bitfields10.gds_size = qpd->gds_size;
packet->bitfields10.num_gws = qpd->num_gws;
packet->bitfields10.num_oac = qpd->num_oac;
packet->bitfields10.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
packet->sh_mem_config = qpd->sh_mem_config;
packet->sh_mem_bases = qpd->sh_mem_bases;
packet->sh_mem_ape1_base = qpd->sh_mem_ape1_base;
packet->sh_mem_ape1_limit = qpd->sh_mem_ape1_limit;
packet->sh_hidden_private_base_vmid = qpd->sh_hidden_private_base;
packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
return 0;
}
static int pm_runlist_vi(struct packet_manager *pm, uint32_t *buffer,
uint64_t ib, size_t ib_size_in_dwords, bool chain)
{
struct pm4_mes_runlist *packet;
int concurrent_proc_cnt = 0;
struct kfd_dev *kfd = pm->dqm->dev;
if (WARN_ON(!ib))
return -EFAULT;
/* Determine the number of processes to map together to HW:
* it can not exceed the number of VMIDs available to the
* scheduler, and it is determined by the smaller of the number
* of processes in the runlist and kfd module parameter
* hws_max_conc_proc.
* Note: the arbitration between the number of VMIDs and
* hws_max_conc_proc has been done in
* kgd2kfd_device_init().
*/
concurrent_proc_cnt = min(pm->dqm->processes_count,
kfd->max_proc_per_quantum);
packet = (struct pm4_mes_runlist *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_runlist));
packet->header.u32All = build_pm4_header(IT_RUN_LIST,
sizeof(struct pm4_mes_runlist));
packet->bitfields4.ib_size = ib_size_in_dwords;
packet->bitfields4.chain = chain ? 1 : 0;
packet->bitfields4.offload_polling = 0;
packet->bitfields4.valid = 1;
packet->bitfields4.process_cnt = concurrent_proc_cnt;
packet->ordinal2 = lower_32_bits(ib);
packet->bitfields3.ib_base_hi = upper_32_bits(ib);
return 0;
}
static int pm_set_resources_vi(struct packet_manager *pm, uint32_t *buffer,
struct scheduling_resources *res)
{
struct pm4_mes_set_resources *packet;
packet = (struct pm4_mes_set_resources *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_set_resources));
packet->header.u32All = build_pm4_header(IT_SET_RESOURCES,
sizeof(struct pm4_mes_set_resources));
packet->bitfields2.queue_type =
queue_type__mes_set_resources__hsa_interface_queue_hiq;
packet->bitfields2.vmid_mask = res->vmid_mask;
packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY_MS / 100;
packet->bitfields7.oac_mask = res->oac_mask;
packet->bitfields8.gds_heap_base = res->gds_heap_base;
packet->bitfields8.gds_heap_size = res->gds_heap_size;
packet->gws_mask_lo = lower_32_bits(res->gws_mask);
packet->gws_mask_hi = upper_32_bits(res->gws_mask);
packet->queue_mask_lo = lower_32_bits(res->queue_mask);
packet->queue_mask_hi = upper_32_bits(res->queue_mask);
return 0;
}
static int pm_map_queues_vi(struct packet_manager *pm, uint32_t *buffer,
struct queue *q, bool is_static)
{
struct pm4_mes_map_queues *packet;
bool use_static = is_static;
packet = (struct pm4_mes_map_queues *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_map_queues));
packet->header.u32All = build_pm4_header(IT_MAP_QUEUES,
sizeof(struct pm4_mes_map_queues));
packet->bitfields2.alloc_format =
alloc_format__mes_map_queues__one_per_pipe_vi;
packet->bitfields2.num_queues = 1;
packet->bitfields2.queue_sel =
queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi;
packet->bitfields2.engine_sel =
engine_sel__mes_map_queues__compute_vi;
packet->bitfields2.queue_type =
queue_type__mes_map_queues__normal_compute_vi;
switch (q->properties.type) {
case KFD_QUEUE_TYPE_COMPUTE:
if (use_static)
packet->bitfields2.queue_type =
queue_type__mes_map_queues__normal_latency_static_queue_vi;
break;
case KFD_QUEUE_TYPE_DIQ:
packet->bitfields2.queue_type =
queue_type__mes_map_queues__debug_interface_queue_vi;
break;
case KFD_QUEUE_TYPE_SDMA:
packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
engine_sel__mes_map_queues__sdma0_vi;
use_static = false; /* no static queues under SDMA */
break;
default:
WARN(1, "queue type %d", q->properties.type);
return -EINVAL;
}
packet->bitfields3.doorbell_offset =
q->properties.doorbell_off;
packet->mqd_addr_lo =
lower_32_bits(q->gart_mqd_addr);
packet->mqd_addr_hi =
upper_32_bits(q->gart_mqd_addr);
packet->wptr_addr_lo =
lower_32_bits((uint64_t)q->properties.write_ptr);
packet->wptr_addr_hi =
upper_32_bits((uint64_t)q->properties.write_ptr);
return 0;
}
static int pm_unmap_queues_vi(struct packet_manager *pm, uint32_t *buffer,
enum kfd_queue_type type,
enum kfd_unmap_queues_filter filter,
uint32_t filter_param, bool reset,
unsigned int sdma_engine)
{
struct pm4_mes_unmap_queues *packet;
packet = (struct pm4_mes_unmap_queues *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
packet->header.u32All = build_pm4_header(IT_UNMAP_QUEUES,
sizeof(struct pm4_mes_unmap_queues));
switch (type) {
case KFD_QUEUE_TYPE_COMPUTE:
case KFD_QUEUE_TYPE_DIQ:
packet->bitfields2.engine_sel =
engine_sel__mes_unmap_queues__compute;
break;
case KFD_QUEUE_TYPE_SDMA:
packet->bitfields2.engine_sel =
engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
break;
default:
WARN(1, "queue type %d", type);
return -EINVAL;
}
if (reset)
packet->bitfields2.action =
action__mes_unmap_queues__reset_queues;
else
packet->bitfields2.action =
action__mes_unmap_queues__preempt_queues;
switch (filter) {
case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
packet->bitfields2.num_queues = 1;
packet->bitfields3b.doorbell_offset0 = filter_param;
break;
case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
packet->bitfields3a.pasid = filter_param;
break;
case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__unmap_all_queues;
break;
case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
/* in this case, we do not preempt static queues */
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
break;
default:
WARN(1, "filter %d", filter);
return -EINVAL;
}
return 0;
}
static int pm_query_status_vi(struct packet_manager *pm, uint32_t *buffer,
uint64_t fence_address, uint32_t fence_value)
{
struct pm4_mes_query_status *packet;
packet = (struct pm4_mes_query_status *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_query_status));
packet->header.u32All = build_pm4_header(IT_QUERY_STATUS,
sizeof(struct pm4_mes_query_status));
packet->bitfields2.context_id = 0;
packet->bitfields2.interrupt_sel =
interrupt_sel__mes_query_status__completion_status;
packet->bitfields2.command =
command__mes_query_status__fence_only_after_write_ack;
packet->addr_hi = upper_32_bits((uint64_t)fence_address);
packet->addr_lo = lower_32_bits((uint64_t)fence_address);
packet->data_hi = upper_32_bits((uint64_t)fence_value);
packet->data_lo = lower_32_bits((uint64_t)fence_value);
return 0;
}
static int pm_release_mem_vi(uint64_t gpu_addr, uint32_t *buffer)
{
struct pm4_mec_release_mem *packet;
packet = (struct pm4_mec_release_mem *)buffer;
memset(buffer, 0, sizeof(*packet));
packet->header.u32All = build_pm4_header(IT_RELEASE_MEM,
sizeof(*packet));
packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
packet->bitfields2.event_index = event_index___release_mem__end_of_pipe;
packet->bitfields2.tcl1_action_ena = 1;
packet->bitfields2.tc_action_ena = 1;
packet->bitfields2.cache_policy = cache_policy___release_mem__lru;
packet->bitfields2.atc = 0;
packet->bitfields3.data_sel = data_sel___release_mem__send_32_bit_low;
packet->bitfields3.int_sel =
int_sel___release_mem__send_interrupt_after_write_confirm;
packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
packet->address_hi = upper_32_bits(gpu_addr);
packet->data_lo = 0;
return 0;
}
const struct packet_manager_funcs kfd_vi_pm_funcs = {
.map_process = pm_map_process_vi,
.runlist = pm_runlist_vi,
.set_resources = pm_set_resources_vi,
.map_queues = pm_map_queues_vi,
.unmap_queues = pm_unmap_queues_vi,
.query_status = pm_query_status_vi,
.release_mem = pm_release_mem_vi,
.map_process_size = sizeof(struct pm4_mes_map_process),
.runlist_size = sizeof(struct pm4_mes_runlist),
.set_resources_size = sizeof(struct pm4_mes_set_resources),
.map_queues_size = sizeof(struct pm4_mes_map_queues),
.unmap_queues_size = sizeof(struct pm4_mes_unmap_queues),
.query_status_size = sizeof(struct pm4_mes_query_status),
.release_mem_size = sizeof(struct pm4_mec_release_mem)
};

View File

@ -26,8 +26,6 @@
#include "kfd_device_queue_manager.h" #include "kfd_device_queue_manager.h"
#include "kfd_kernel_queue.h" #include "kfd_kernel_queue.h"
#include "kfd_priv.h" #include "kfd_priv.h"
#include "kfd_pm4_headers_vi.h"
#include "kfd_pm4_opcodes.h"
static inline void inc_wptr(unsigned int *wptr, unsigned int increment_bytes, static inline void inc_wptr(unsigned int *wptr, unsigned int increment_bytes,
unsigned int buffer_size_bytes) unsigned int buffer_size_bytes)
@ -39,18 +37,6 @@ static inline void inc_wptr(unsigned int *wptr, unsigned int increment_bytes,
*wptr = temp; *wptr = temp;
} }
static unsigned int build_pm4_header(unsigned int opcode, size_t packet_size)
{
union PM4_MES_TYPE_3_HEADER header;
header.u32All = 0;
header.opcode = opcode;
header.count = packet_size / 4 - 2;
header.type = PM4_TYPE_3;
return header.u32All;
}
static void pm_calc_rlib_size(struct packet_manager *pm, static void pm_calc_rlib_size(struct packet_manager *pm,
unsigned int *rlib_size, unsigned int *rlib_size,
bool *over_subscription) bool *over_subscription)
@ -80,9 +66,9 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
pr_debug("Over subscribed runlist\n"); pr_debug("Over subscribed runlist\n");
} }
map_queue_size = sizeof(struct pm4_mes_map_queues); map_queue_size = pm->pmf->map_queues_size;
/* calculate run list ib allocation size */ /* calculate run list ib allocation size */
*rlib_size = process_count * sizeof(struct pm4_mes_map_process) + *rlib_size = process_count * pm->pmf->map_process_size +
queue_count * map_queue_size; queue_count * map_queue_size;
/* /*
@ -90,7 +76,7 @@ static void pm_calc_rlib_size(struct packet_manager *pm,
* when over subscription * when over subscription
*/ */
if (*over_subscription) if (*over_subscription)
*rlib_size += sizeof(struct pm4_mes_runlist); *rlib_size += pm->pmf->runlist_size;
pr_debug("runlist ib size %d\n", *rlib_size); pr_debug("runlist ib size %d\n", *rlib_size);
} }
@ -124,137 +110,6 @@ static int pm_allocate_runlist_ib(struct packet_manager *pm,
return retval; return retval;
} }
static int pm_create_runlist(struct packet_manager *pm, uint32_t *buffer,
uint64_t ib, size_t ib_size_in_dwords, bool chain)
{
struct pm4_mes_runlist *packet;
int concurrent_proc_cnt = 0;
struct kfd_dev *kfd = pm->dqm->dev;
if (WARN_ON(!ib))
return -EFAULT;
/* Determine the number of processes to map together to HW:
* it can not exceed the number of VMIDs available to the
* scheduler, and it is determined by the smaller of the number
* of processes in the runlist and kfd module parameter
* hws_max_conc_proc.
* Note: the arbitration between the number of VMIDs and
* hws_max_conc_proc has been done in
* kgd2kfd_device_init().
*/
concurrent_proc_cnt = min(pm->dqm->processes_count,
kfd->max_proc_per_quantum);
packet = (struct pm4_mes_runlist *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_runlist));
packet->header.u32All = build_pm4_header(IT_RUN_LIST,
sizeof(struct pm4_mes_runlist));
packet->bitfields4.ib_size = ib_size_in_dwords;
packet->bitfields4.chain = chain ? 1 : 0;
packet->bitfields4.offload_polling = 0;
packet->bitfields4.valid = 1;
packet->bitfields4.process_cnt = concurrent_proc_cnt;
packet->ordinal2 = lower_32_bits(ib);
packet->bitfields3.ib_base_hi = upper_32_bits(ib);
return 0;
}
static int pm_create_map_process(struct packet_manager *pm, uint32_t *buffer,
struct qcm_process_device *qpd)
{
struct pm4_mes_map_process *packet;
packet = (struct pm4_mes_map_process *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_map_process));
packet->header.u32All = build_pm4_header(IT_MAP_PROCESS,
sizeof(struct pm4_mes_map_process));
packet->bitfields2.diq_enable = (qpd->is_debug) ? 1 : 0;
packet->bitfields2.process_quantum = 1;
packet->bitfields2.pasid = qpd->pqm->process->pasid;
packet->bitfields3.page_table_base = qpd->page_table_base;
packet->bitfields10.gds_size = qpd->gds_size;
packet->bitfields10.num_gws = qpd->num_gws;
packet->bitfields10.num_oac = qpd->num_oac;
packet->bitfields10.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
packet->sh_mem_config = qpd->sh_mem_config;
packet->sh_mem_bases = qpd->sh_mem_bases;
packet->sh_mem_ape1_base = qpd->sh_mem_ape1_base;
packet->sh_mem_ape1_limit = qpd->sh_mem_ape1_limit;
packet->sh_hidden_private_base_vmid = qpd->sh_hidden_private_base;
packet->gds_addr_lo = lower_32_bits(qpd->gds_context_area);
packet->gds_addr_hi = upper_32_bits(qpd->gds_context_area);
return 0;
}
static int pm_create_map_queue(struct packet_manager *pm, uint32_t *buffer,
struct queue *q, bool is_static)
{
struct pm4_mes_map_queues *packet;
bool use_static = is_static;
packet = (struct pm4_mes_map_queues *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_map_queues));
packet->header.u32All = build_pm4_header(IT_MAP_QUEUES,
sizeof(struct pm4_mes_map_queues));
packet->bitfields2.alloc_format =
alloc_format__mes_map_queues__one_per_pipe_vi;
packet->bitfields2.num_queues = 1;
packet->bitfields2.queue_sel =
queue_sel__mes_map_queues__map_to_hws_determined_queue_slots_vi;
packet->bitfields2.engine_sel =
engine_sel__mes_map_queues__compute_vi;
packet->bitfields2.queue_type =
queue_type__mes_map_queues__normal_compute_vi;
switch (q->properties.type) {
case KFD_QUEUE_TYPE_COMPUTE:
if (use_static)
packet->bitfields2.queue_type =
queue_type__mes_map_queues__normal_latency_static_queue_vi;
break;
case KFD_QUEUE_TYPE_DIQ:
packet->bitfields2.queue_type =
queue_type__mes_map_queues__debug_interface_queue_vi;
break;
case KFD_QUEUE_TYPE_SDMA:
packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
engine_sel__mes_map_queues__sdma0_vi;
use_static = false; /* no static queues under SDMA */
break;
default:
WARN(1, "queue type %d", q->properties.type);
return -EINVAL;
}
packet->bitfields3.doorbell_offset =
q->properties.doorbell_off;
packet->mqd_addr_lo =
lower_32_bits(q->gart_mqd_addr);
packet->mqd_addr_hi =
upper_32_bits(q->gart_mqd_addr);
packet->wptr_addr_lo =
lower_32_bits((uint64_t)q->properties.write_ptr);
packet->wptr_addr_hi =
upper_32_bits((uint64_t)q->properties.write_ptr);
return 0;
}
static int pm_create_runlist_ib(struct packet_manager *pm, static int pm_create_runlist_ib(struct packet_manager *pm,
struct list_head *queues, struct list_head *queues,
uint64_t *rl_gpu_addr, uint64_t *rl_gpu_addr,
@ -292,12 +147,12 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
return -ENOMEM; return -ENOMEM;
} }
retval = pm_create_map_process(pm, &rl_buffer[rl_wptr], qpd); retval = pm->pmf->map_process(pm, &rl_buffer[rl_wptr], qpd);
if (retval) if (retval)
return retval; return retval;
proccesses_mapped++; proccesses_mapped++;
inc_wptr(&rl_wptr, sizeof(struct pm4_mes_map_process), inc_wptr(&rl_wptr, pm->pmf->map_process_size,
alloc_size_bytes); alloc_size_bytes);
list_for_each_entry(kq, &qpd->priv_queue_list, list) { list_for_each_entry(kq, &qpd->priv_queue_list, list) {
@ -307,7 +162,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
pr_debug("static_queue, mapping kernel q %d, is debug status %d\n", pr_debug("static_queue, mapping kernel q %d, is debug status %d\n",
kq->queue->queue, qpd->is_debug); kq->queue->queue, qpd->is_debug);
retval = pm_create_map_queue(pm, retval = pm->pmf->map_queues(pm,
&rl_buffer[rl_wptr], &rl_buffer[rl_wptr],
kq->queue, kq->queue,
qpd->is_debug); qpd->is_debug);
@ -315,7 +170,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
return retval; return retval;
inc_wptr(&rl_wptr, inc_wptr(&rl_wptr,
sizeof(struct pm4_mes_map_queues), pm->pmf->map_queues_size,
alloc_size_bytes); alloc_size_bytes);
} }
@ -326,7 +181,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
pr_debug("static_queue, mapping user queue %d, is debug status %d\n", pr_debug("static_queue, mapping user queue %d, is debug status %d\n",
q->queue, qpd->is_debug); q->queue, qpd->is_debug);
retval = pm_create_map_queue(pm, retval = pm->pmf->map_queues(pm,
&rl_buffer[rl_wptr], &rl_buffer[rl_wptr],
q, q,
qpd->is_debug); qpd->is_debug);
@ -335,7 +190,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
return retval; return retval;
inc_wptr(&rl_wptr, inc_wptr(&rl_wptr,
sizeof(struct pm4_mes_map_queues), pm->pmf->map_queues_size,
alloc_size_bytes); alloc_size_bytes);
} }
} }
@ -343,7 +198,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
pr_debug("Finished map process and queues to runlist\n"); pr_debug("Finished map process and queues to runlist\n");
if (is_over_subscription) if (is_over_subscription)
retval = pm_create_runlist(pm, &rl_buffer[rl_wptr], retval = pm->pmf->runlist(pm, &rl_buffer[rl_wptr],
*rl_gpu_addr, *rl_gpu_addr,
alloc_size_bytes / sizeof(uint32_t), alloc_size_bytes / sizeof(uint32_t),
true); true);
@ -355,45 +210,25 @@ static int pm_create_runlist_ib(struct packet_manager *pm,
return retval; return retval;
} }
/* pm_create_release_mem - Create a RELEASE_MEM packet and return the size
* of this packet
* @gpu_addr - GPU address of the packet. It's a virtual address.
* @buffer - buffer to fill up with the packet. It's a CPU kernel pointer
* Return - length of the packet
*/
uint32_t pm_create_release_mem(uint64_t gpu_addr, uint32_t *buffer)
{
struct pm4_mec_release_mem *packet;
WARN_ON(!buffer);
packet = (struct pm4_mec_release_mem *)buffer;
memset(buffer, 0, sizeof(*packet));
packet->header.u32All = build_pm4_header(IT_RELEASE_MEM,
sizeof(*packet));
packet->bitfields2.event_type = CACHE_FLUSH_AND_INV_TS_EVENT;
packet->bitfields2.event_index = event_index___release_mem__end_of_pipe;
packet->bitfields2.tcl1_action_ena = 1;
packet->bitfields2.tc_action_ena = 1;
packet->bitfields2.cache_policy = cache_policy___release_mem__lru;
packet->bitfields2.atc = 0;
packet->bitfields3.data_sel = data_sel___release_mem__send_32_bit_low;
packet->bitfields3.int_sel =
int_sel___release_mem__send_interrupt_after_write_confirm;
packet->bitfields4.address_lo_32b = (gpu_addr & 0xffffffff) >> 2;
packet->address_hi = upper_32_bits(gpu_addr);
packet->data_lo = 0;
return sizeof(*packet) / sizeof(unsigned int);
}
int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm) int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm)
{ {
switch (dqm->dev->device_info->asic_family) {
case CHIP_KAVERI:
case CHIP_HAWAII:
/* PM4 packet structures on CIK are the same as on VI */
case CHIP_CARRIZO:
case CHIP_TONGA:
case CHIP_FIJI:
case CHIP_POLARIS10:
case CHIP_POLARIS11:
pm->pmf = &kfd_vi_pm_funcs;
break;
default:
WARN(1, "Unexpected ASIC family %u",
dqm->dev->device_info->asic_family);
return -EINVAL;
}
pm->dqm = dqm; pm->dqm = dqm;
mutex_init(&pm->lock); mutex_init(&pm->lock);
pm->priv_queue = kernel_queue_init(dqm->dev, KFD_QUEUE_TYPE_HIQ); pm->priv_queue = kernel_queue_init(dqm->dev, KFD_QUEUE_TYPE_HIQ);
@ -415,38 +250,25 @@ void pm_uninit(struct packet_manager *pm)
int pm_send_set_resources(struct packet_manager *pm, int pm_send_set_resources(struct packet_manager *pm,
struct scheduling_resources *res) struct scheduling_resources *res)
{ {
struct pm4_mes_set_resources *packet; uint32_t *buffer, size;
int retval = 0; int retval = 0;
size = pm->pmf->set_resources_size;
mutex_lock(&pm->lock); mutex_lock(&pm->lock);
pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue, pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
sizeof(*packet) / sizeof(uint32_t), size / sizeof(uint32_t),
(unsigned int **)&packet); (unsigned int **)&buffer);
if (!packet) { if (!buffer) {
pr_err("Failed to allocate buffer on kernel queue\n"); pr_err("Failed to allocate buffer on kernel queue\n");
retval = -ENOMEM; retval = -ENOMEM;
goto out; goto out;
} }
memset(packet, 0, sizeof(struct pm4_mes_set_resources)); retval = pm->pmf->set_resources(pm, buffer, res);
packet->header.u32All = build_pm4_header(IT_SET_RESOURCES, if (!retval)
sizeof(struct pm4_mes_set_resources)); pm->priv_queue->ops.submit_packet(pm->priv_queue);
else
packet->bitfields2.queue_type = pm->priv_queue->ops.rollback_packet(pm->priv_queue);
queue_type__mes_set_resources__hsa_interface_queue_hiq;
packet->bitfields2.vmid_mask = res->vmid_mask;
packet->bitfields2.unmap_latency = KFD_UNMAP_LATENCY_MS / 100;
packet->bitfields7.oac_mask = res->oac_mask;
packet->bitfields8.gds_heap_base = res->gds_heap_base;
packet->bitfields8.gds_heap_size = res->gds_heap_size;
packet->gws_mask_lo = lower_32_bits(res->gws_mask);
packet->gws_mask_hi = upper_32_bits(res->gws_mask);
packet->queue_mask_lo = lower_32_bits(res->queue_mask);
packet->queue_mask_hi = upper_32_bits(res->queue_mask);
pm->priv_queue->ops.submit_packet(pm->priv_queue);
out: out:
mutex_unlock(&pm->lock); mutex_unlock(&pm->lock);
@ -468,7 +290,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
pr_debug("runlist IB address: 0x%llX\n", rl_gpu_ib_addr); pr_debug("runlist IB address: 0x%llX\n", rl_gpu_ib_addr);
packet_size_dwords = sizeof(struct pm4_mes_runlist) / sizeof(uint32_t); packet_size_dwords = pm->pmf->runlist_size / sizeof(uint32_t);
mutex_lock(&pm->lock); mutex_lock(&pm->lock);
retval = pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue, retval = pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
@ -476,7 +298,7 @@ int pm_send_runlist(struct packet_manager *pm, struct list_head *dqm_queues)
if (retval) if (retval)
goto fail_acquire_packet_buffer; goto fail_acquire_packet_buffer;
retval = pm_create_runlist(pm, rl_buffer, rl_gpu_ib_addr, retval = pm->pmf->runlist(pm, rl_buffer, rl_gpu_ib_addr,
rl_ib_size / sizeof(uint32_t), false); rl_ib_size / sizeof(uint32_t), false);
if (retval) if (retval)
goto fail_create_runlist; goto fail_create_runlist;
@ -499,37 +321,29 @@ fail_create_runlist_ib:
int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address, int pm_send_query_status(struct packet_manager *pm, uint64_t fence_address,
uint32_t fence_value) uint32_t fence_value)
{ {
int retval; uint32_t *buffer, size;
struct pm4_mes_query_status *packet; int retval = 0;
if (WARN_ON(!fence_address)) if (WARN_ON(!fence_address))
return -EFAULT; return -EFAULT;
size = pm->pmf->query_status_size;
mutex_lock(&pm->lock); mutex_lock(&pm->lock);
retval = pm->priv_queue->ops.acquire_packet_buffer( pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
pm->priv_queue, size / sizeof(uint32_t), (unsigned int **)&buffer);
sizeof(struct pm4_mes_query_status) / sizeof(uint32_t), if (!buffer) {
(unsigned int **)&packet); pr_err("Failed to allocate buffer on kernel queue\n");
if (retval) retval = -ENOMEM;
goto fail_acquire_packet_buffer; goto out;
}
packet->header.u32All = build_pm4_header(IT_QUERY_STATUS, retval = pm->pmf->query_status(pm, buffer, fence_address, fence_value);
sizeof(struct pm4_mes_query_status)); if (!retval)
pm->priv_queue->ops.submit_packet(pm->priv_queue);
else
pm->priv_queue->ops.rollback_packet(pm->priv_queue);
packet->bitfields2.context_id = 0; out:
packet->bitfields2.interrupt_sel =
interrupt_sel__mes_query_status__completion_status;
packet->bitfields2.command =
command__mes_query_status__fence_only_after_write_ack;
packet->addr_hi = upper_32_bits((uint64_t)fence_address);
packet->addr_lo = lower_32_bits((uint64_t)fence_address);
packet->data_hi = upper_32_bits((uint64_t)fence_value);
packet->data_lo = lower_32_bits((uint64_t)fence_value);
pm->priv_queue->ops.submit_packet(pm->priv_queue);
fail_acquire_packet_buffer:
mutex_unlock(&pm->lock); mutex_unlock(&pm->lock);
return retval; return retval;
} }
@ -539,82 +353,27 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
uint32_t filter_param, bool reset, uint32_t filter_param, bool reset,
unsigned int sdma_engine) unsigned int sdma_engine)
{ {
int retval; uint32_t *buffer, size;
uint32_t *buffer; int retval = 0;
struct pm4_mes_unmap_queues *packet;
size = pm->pmf->unmap_queues_size;
mutex_lock(&pm->lock); mutex_lock(&pm->lock);
retval = pm->priv_queue->ops.acquire_packet_buffer( pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
pm->priv_queue, size / sizeof(uint32_t), (unsigned int **)&buffer);
sizeof(struct pm4_mes_unmap_queues) / sizeof(uint32_t), if (!buffer) {
&buffer); pr_err("Failed to allocate buffer on kernel queue\n");
if (retval) retval = -ENOMEM;
goto err_acquire_packet_buffer; goto out;
packet = (struct pm4_mes_unmap_queues *)buffer;
memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues));
pr_debug("static_queue: unmapping queues: filter is %d , reset is %d , type is %d\n",
filter, reset, type);
packet->header.u32All = build_pm4_header(IT_UNMAP_QUEUES,
sizeof(struct pm4_mes_unmap_queues));
switch (type) {
case KFD_QUEUE_TYPE_COMPUTE:
case KFD_QUEUE_TYPE_DIQ:
packet->bitfields2.engine_sel =
engine_sel__mes_unmap_queues__compute;
break;
case KFD_QUEUE_TYPE_SDMA:
packet->bitfields2.engine_sel =
engine_sel__mes_unmap_queues__sdma0 + sdma_engine;
break;
default:
WARN(1, "queue type %d", type);
retval = -EINVAL;
goto err_invalid;
} }
if (reset) retval = pm->pmf->unmap_queues(pm, buffer, type, filter, filter_param,
packet->bitfields2.action = reset, sdma_engine);
action__mes_unmap_queues__reset_queues; if (!retval)
pm->priv_queue->ops.submit_packet(pm->priv_queue);
else else
packet->bitfields2.action = pm->priv_queue->ops.rollback_packet(pm->priv_queue);
action__mes_unmap_queues__preempt_queues;
switch (filter) { out:
case KFD_UNMAP_QUEUES_FILTER_SINGLE_QUEUE:
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__perform_request_on_specified_queues;
packet->bitfields2.num_queues = 1;
packet->bitfields3b.doorbell_offset0 = filter_param;
break;
case KFD_UNMAP_QUEUES_FILTER_BY_PASID:
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__perform_request_on_pasid_queues;
packet->bitfields3a.pasid = filter_param;
break;
case KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES:
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__unmap_all_queues;
break;
case KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES:
/* in this case, we do not preempt static queues */
packet->bitfields2.queue_sel =
queue_sel__mes_unmap_queues__unmap_all_non_static_queues;
break;
default:
WARN(1, "filter %d", filter);
retval = -EINVAL;
goto err_invalid;
}
pm->priv_queue->ops.submit_packet(pm->priv_queue);
mutex_unlock(&pm->lock);
return 0;
err_invalid:
pm->priv_queue->ops.rollback_packet(pm->priv_queue);
err_acquire_packet_buffer:
mutex_unlock(&pm->lock); mutex_unlock(&pm->lock);
return retval; return retval;
} }

View File

@ -866,8 +866,41 @@ struct packet_manager {
bool allocated; bool allocated;
struct kfd_mem_obj *ib_buffer_obj; struct kfd_mem_obj *ib_buffer_obj;
unsigned int ib_size_bytes; unsigned int ib_size_bytes;
const struct packet_manager_funcs *pmf;
}; };
struct packet_manager_funcs {
/* Support ASIC-specific packet formats for PM4 packets */
int (*map_process)(struct packet_manager *pm, uint32_t *buffer,
struct qcm_process_device *qpd);
int (*runlist)(struct packet_manager *pm, uint32_t *buffer,
uint64_t ib, size_t ib_size_in_dwords, bool chain);
int (*set_resources)(struct packet_manager *pm, uint32_t *buffer,
struct scheduling_resources *res);
int (*map_queues)(struct packet_manager *pm, uint32_t *buffer,
struct queue *q, bool is_static);
int (*unmap_queues)(struct packet_manager *pm, uint32_t *buffer,
enum kfd_queue_type type,
enum kfd_unmap_queues_filter mode,
uint32_t filter_param, bool reset,
unsigned int sdma_engine);
int (*query_status)(struct packet_manager *pm, uint32_t *buffer,
uint64_t fence_address, uint32_t fence_value);
int (*release_mem)(uint64_t gpu_addr, uint32_t *buffer);
/* Packet sizes */
int map_process_size;
int runlist_size;
int set_resources_size;
int map_queues_size;
int unmap_queues_size;
int query_status_size;
int release_mem_size;
};
extern const struct packet_manager_funcs kfd_vi_pm_funcs;
int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm); int pm_init(struct packet_manager *pm, struct device_queue_manager *dqm);
void pm_uninit(struct packet_manager *pm); void pm_uninit(struct packet_manager *pm);
int pm_send_set_resources(struct packet_manager *pm, int pm_send_set_resources(struct packet_manager *pm,
@ -883,8 +916,6 @@ int pm_send_unmap_queue(struct packet_manager *pm, enum kfd_queue_type type,
void pm_release_ib(struct packet_manager *pm); void pm_release_ib(struct packet_manager *pm);
uint32_t pm_create_release_mem(uint64_t gpu_addr, uint32_t *buffer);
uint64_t kfd_get_number_elems(struct kfd_dev *kfd); uint64_t kfd_get_number_elems(struct kfd_dev *kfd);
/* Events */ /* Events */