IIRC the amdgpu devs had been holding back on publishing the updated MEC microcode (with scratch support) because that WOULD have broken Kaveri. With this change from Felix we should be able to publish the newest microcode for both amdgpu and amdkfd WITHOUT breaking Kaveri.
IOW this is the "scratch fix for Kaveri KFD" you have wanted for a couple of years :) >-----Original Message----- >From: amd-gfx [mailto:amd-gfx-boun...@lists.freedesktop.org] On Behalf >Of Kuehling, Felix >Sent: Saturday, August 12, 2017 2:16 PM >To: Oded Gabbay >Cc: amd-gfx list >Subject: Re: [PATCH 16/19] drm/amdkfd: Update PM4 packet headers > >> Do you mean that it won't work with Kaveri anymore ? > >Kaveri got the same firmware changes, mostly for scratch memory support. >The Kaveri firmware headers name the structures and fields a bit differently >but they should be binary compatible. So we simplified the code to use only >one set of headers. I'll grab a Kaveri system to confirm that it works. > >Regards, > Felix > >From: Oded Gabbay <oded.gab...@gmail.com> >Sent: Saturday, August 12, 2017 11:10 AM >To: Kuehling, Felix >Cc: amd-gfx list >Subject: Re: [PATCH 16/19] drm/amdkfd: Update PM4 packet headers > >On Sat, Aug 12, 2017 at 12:56 AM, Felix Kuehling <felix.kuehl...@amd.com> >wrote: >> To match current firmware. The map process packet has been extended to >> support scratch. This is a non-backwards compatible change and it's >> about two years old. So no point keeping the old version around >> conditionally. > >Do you mean that it won't work with Kaveri anymore ? >I believe we aren't allowed to break older H/W support without some >serious justification. > >Oded > >> >> Signed-off-by: Felix Kuehling <felix.kuehl...@amd.com> >> --- >> drivers/gpu/drm/amd/amdkfd/kfd_device.c | 8 +- >> drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c | 161 ++++-------- >> drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers.h | 314 >>+++--------------------- >> drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_vi.h | 130 +++++++++- >> 4 files changed, 199 insertions(+), 414 deletions(-) >> >> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c >> b/drivers/gpu/drm/amd/amdkfd/kfd_device.c >> index e1c2ad2..e790e7f 100644 >> --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c >> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c >> @@ -26,7 +26,7 @@ >> #include <linux/slab.h> >> #include "kfd_priv.h" >> #include "kfd_device_queue_manager.h" >> -#include "kfd_pm4_headers.h" >> +#include "kfd_pm4_headers_vi.h" >> >> #define MQD_SIZE_ALIGNED 768 >> >> @@ -238,9 +238,9 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd, >> * calculate max size of runlist packet. >> * There can be only 2 packets at once >> */ >> - size += (KFD_MAX_NUM_OF_PROCESSES * sizeof(struct >>pm4_map_process) + >> - max_num_of_queues_per_device * >> - sizeof(struct pm4_map_queues) + sizeof(struct >>pm4_runlist)) * 2; >> + size += (KFD_MAX_NUM_OF_PROCESSES * sizeof(struct >> +pm4_mes_map_process) + >> + max_num_of_queues_per_device * sizeof(struct >> +pm4_mes_map_queues) >> + + sizeof(struct pm4_mes_runlist)) * 2; >> >> /* Add size of HIQ & DIQ */ >> size += KFD_KERNEL_QUEUE_SIZE * 2; diff --git >>a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c >>b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c >> index 77a6f2b..3141e05 100644 >> --- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c >> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c >> @@ -26,7 +26,6 @@ >> #include "kfd_device_queue_manager.h" >> #include "kfd_kernel_queue.h" >> #include "kfd_priv.h" >> -#include "kfd_pm4_headers.h" >> #include "kfd_pm4_headers_vi.h" >> #include "kfd_pm4_opcodes.h" >> >> @@ -44,12 +43,12 @@ static unsigned int build_pm4_header(unsigned int >>opcode, size_t packet_size) >> { >> union PM4_MES_TYPE_3_HEADER header; >> >> - header.u32all = 0; >> + header.u32All = 0; >> header.opcode = opcode; >> header.count = packet_size/sizeof(uint32_t) - 2; >> header.type = PM4_TYPE_3; >> >> - return header.u32all; >> + return header.u32All; >> } >> >> static void pm_calc_rlib_size(struct packet_manager *pm, @@ -69,12 >>+68,9 @@ static void pm_calc_rlib_size(struct packet_manager *pm, >> pr_debug("Over subscribed runlist\n"); >> } >> >> - map_queue_size = >> - (pm->dqm->dev->device_info->asic_family == CHIP_CARRIZO) ? >> - sizeof(struct pm4_mes_map_queues) : >> - sizeof(struct pm4_map_queues); >> + map_queue_size = sizeof(struct pm4_mes_map_queues); >> /* calculate run list ib allocation size */ >> - *rlib_size = process_count * sizeof(struct pm4_map_process) + >> + *rlib_size = process_count * sizeof(struct >> +pm4_mes_map_process) + >> queue_count * map_queue_size; >> >> /* >> @@ -82,7 +78,7 @@ static void pm_calc_rlib_size(struct packet_manager >>*pm, >> * when over subscription >> */ >> if (*over_subscription) >> - *rlib_size += sizeof(struct pm4_runlist); >> + *rlib_size += sizeof(struct pm4_mes_runlist); >> >> pr_debug("runlist ib size %d\n", *rlib_size); >> } >> @@ -119,16 +115,16 @@ static int pm_allocate_runlist_ib(struct >>packet_manager *pm, >> 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_runlist *packet; >> + struct pm4_mes_runlist *packet; >> >> if (WARN_ON(!ib)) >> return -EFAULT; >> >> - packet = (struct pm4_runlist *)buffer; >> + packet = (struct pm4_mes_runlist *)buffer; >> >> - memset(buffer, 0, sizeof(struct pm4_runlist)); >> - packet->header.u32all = build_pm4_header(IT_RUN_LIST, >> - sizeof(struct >> pm4_runlist)); >> + 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; @@ -143,16 +139,16 >>@@ static int pm_create_runlist(struct packet_manager *pm, uint32_t >>*buffer, >> static int pm_create_map_process(struct packet_manager *pm, uint32_t >>*buffer, >> struct qcm_process_device *qpd) >> { >> - struct pm4_map_process *packet; >> + struct pm4_mes_map_process *packet; >> struct queue *cur; >> uint32_t num_queues; >> >> - packet = (struct pm4_map_process *)buffer; >> + packet = (struct pm4_mes_map_process *)buffer; >> >> - memset(buffer, 0, sizeof(struct pm4_map_process)); >> + memset(buffer, 0, sizeof(struct pm4_mes_map_process)); >> >> - packet->header.u32all = build_pm4_header(IT_MAP_PROCESS, >> - sizeof(struct >> pm4_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; @@ >>-170,23 +166,26 @@ static int pm_create_map_process(struct >>packet_manager *pm, uint32_t *buffer, >> packet->sh_mem_ape1_base = qpd->sh_mem_ape1_base; >> packet->sh_mem_ape1_limit = qpd->sh_mem_ape1_limit; >> >> + /* TODO: scratch support */ >> + packet->sh_hidden_private_base_vmid = 0; >> + >> 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_vi(struct packet_manager *pm, uint32_t >> *buffer, >> +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_map_queues)); >> + memset(buffer, 0, sizeof(struct pm4_mes_map_queues)); >> >> - packet->header.u32all = build_pm4_header(IT_MAP_QUEUES, >> - sizeof(struct >> pm4_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; @@ -235,64 +234,6 @@ >>static int pm_create_map_queue_vi(struct packet_manager *pm, uint32_t >>*buffer, >> return 0; >> } >> >> -static int pm_create_map_queue(struct packet_manager *pm, uint32_t >>*buffer, >> - struct queue *q, bool is_static) -{ >> - struct pm4_map_queues *packet; >> - bool use_static = is_static; >> - >> - packet = (struct pm4_map_queues *)buffer; >> - memset(buffer, 0, sizeof(struct pm4_map_queues)); >> - >> - packet->header.u32all = build_pm4_header(IT_MAP_QUEUES, >> - sizeof(struct >>pm4_map_queues)); >> - packet->bitfields2.alloc_format = >> - >>alloc_format__mes_map_queues__one_per_pipe; >> - packet->bitfields2.num_queues = 1; >> - packet->bitfields2.queue_sel = >> - >>queue_sel__mes_map_queues__map_to_hws_determined_queue_slots; >> - >> - packet->bitfields2.vidmem = (q->properties.is_interop) ? >> - vidmem__mes_map_queues__uses_video_memory : >> - vidmem__mes_map_queues__uses_no_video_memory; >> - >> - switch (q->properties.type) { >> - case KFD_QUEUE_TYPE_COMPUTE: >> - case KFD_QUEUE_TYPE_DIQ: >> - packet->bitfields2.engine_sel = >> - engine_sel__mes_map_queues__compute; >> - break; >> - case KFD_QUEUE_TYPE_SDMA: >> - packet->bitfields2.engine_sel = >> - engine_sel__mes_map_queues__sdma0; >> - use_static = false; /* no static queues under SDMA */ >> - break; >> - default: >> - WARN(1, "queue type %d", q->properties.type); >> - return -EINVAL; >> - } >> - >> - packet->mes_map_queues_ordinals[0].bitfields3.doorbell_offset >>= >> - q->properties.doorbell_off; >> - >> - packet->mes_map_queues_ordinals[0].bitfields3.is_static = >> - (use_static) ? 1 : 0; >> - >> - packet->mes_map_queues_ordinals[0].mqd_addr_lo = >> - lower_32_bits(q->gart_mqd_addr); >> - >> - packet->mes_map_queues_ordinals[0].mqd_addr_hi = >> - upper_32_bits(q->gart_mqd_addr); >> - >> - packet->mes_map_queues_ordinals[0].wptr_addr_lo = >> - >>lower_32_bits((uint64_t)q->properties.write_ptr); >> - >> - packet->mes_map_queues_ordinals[0].wptr_addr_hi = >> - >>upper_32_bits((uint64_t)q->properties.write_ptr); >> - >> - return 0; >> -} >> - >> static int pm_create_runlist_ib(struct packet_manager *pm, >> struct list_head *queues, >> uint64_t *rl_gpu_addr, @@ -334,7 >>+275,7 @@ static int pm_create_runlist_ib(struct packet_manager *pm, >> return retval; >> >> proccesses_mapped++; >> - inc_wptr(&rl_wptr, sizeof(struct pm4_map_process), >> + inc_wptr(&rl_wptr, sizeof(struct pm4_mes_map_process), >> alloc_size_bytes); >> >> list_for_each_entry(kq, &qpd->priv_queue_list, list) { >>@@ -344,14 +285,7 @@ static int pm_create_runlist_ib(struct >>packet_manager *pm, >> pr_debug("static_queue, mapping kernel q %d, >>is debug status %d\n", >> kq->queue->queue, qpd->is_debug); >> >> - if (pm->dqm->dev->device_info->asic_family == >> - CHIP_CARRIZO) >> - retval = pm_create_map_queue_vi(pm, >> - &rl_buffer[rl_wptr], >> - kq->queue, >> - qpd->is_debug); >> - else >> - retval = pm_create_map_queue(pm, >> + retval = pm_create_map_queue(pm, >> &rl_buffer[rl_wptr], >> kq->queue, >> qpd->is_debug); @@ >>-359,7 +293,7 @@ static int pm_create_runlist_ib(struct packet_manager >>*pm, >> return retval; >> >> inc_wptr(&rl_wptr, >> - sizeof(struct pm4_map_queues), >> + sizeof(struct pm4_mes_map_queues), >> alloc_size_bytes); >> } >> >> @@ -370,14 +304,7 @@ static int pm_create_runlist_ib(struct >>packet_manager *pm, >> pr_debug("static_queue, mapping user queue %d, >>is debug status %d\n", >> q->queue, qpd->is_debug); >> >> - if (pm->dqm->dev->device_info->asic_family == >> - CHIP_CARRIZO) >> - retval = pm_create_map_queue_vi(pm, >> - &rl_buffer[rl_wptr], >> - q, >> - qpd->is_debug); >> - else >> - retval = pm_create_map_queue(pm, >> + retval = pm_create_map_queue(pm, >> &rl_buffer[rl_wptr], >> q, >> qpd->is_debug); @@ >>-386,7 +313,7 @@ static int pm_create_runlist_ib(struct packet_manager >>*pm, >> return retval; >> >> inc_wptr(&rl_wptr, >> - sizeof(struct pm4_map_queues), >> + sizeof(struct pm4_mes_map_queues), >> alloc_size_bytes); >> } >> } >> @@ -429,7 +356,7 @@ void pm_uninit(struct packet_manager *pm) >> int pm_send_set_resources(struct packet_manager *pm, >> struct scheduling_resources *res) >> { >> - struct pm4_set_resources *packet; >> + struct pm4_mes_set_resources *packet; >> int retval = 0; >> >> mutex_lock(&pm->lock); >> @@ -442,9 +369,9 @@ int pm_send_set_resources(struct packet_manager >>*pm, >> goto out; >> } >> >> - memset(packet, 0, sizeof(struct pm4_set_resources)); >> - packet->header.u32all = build_pm4_header(IT_SET_RESOURCES, >> - sizeof(struct >> pm4_set_resources)); >> + memset(packet, 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; >> @@ -482,7 +409,7 @@ 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); >> >> - packet_size_dwords = sizeof(struct pm4_runlist) / >> sizeof(uint32_t); >> + packet_size_dwords = sizeof(struct pm4_mes_runlist) / >> +sizeof(uint32_t); >> mutex_lock(&pm->lock); >> >> retval = >>pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue, >> @@ -514,7 +441,7 @@ int pm_send_query_status(struct packet_manager >>*pm, uint64_t fence_address, >> uint32_t fence_value) >> { >> int retval; >> - struct pm4_query_status *packet; >> + struct pm4_mes_query_status *packet; >> >> if (WARN_ON(!fence_address)) >> return -EFAULT; >> @@ -522,13 +449,13 @@ int pm_send_query_status(struct packet_manager >>*pm, uint64_t fence_address, >> mutex_lock(&pm->lock); >> retval = pm->priv_queue->ops.acquire_packet_buffer( >> pm->priv_queue, >> - sizeof(struct pm4_query_status) / >>sizeof(uint32_t), >> + sizeof(struct pm4_mes_query_status) / >> +sizeof(uint32_t), >> (unsigned int **)&packet); >> if (retval) >> goto fail_acquire_packet_buffer; >> >> - packet->header.u32all = build_pm4_header(IT_QUERY_STATUS, >> - sizeof(struct >> pm4_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 = @@ -555,22 +482,22 @@ int >>pm_send_unmap_queue(struct packet_manager *pm, enum >kfd_queue_type >>type, >> { >> int retval; >> uint32_t *buffer; >> - struct pm4_unmap_queues *packet; >> + struct pm4_mes_unmap_queues *packet; >> >> mutex_lock(&pm->lock); >> retval = pm->priv_queue->ops.acquire_packet_buffer( >> pm->priv_queue, >> - sizeof(struct pm4_unmap_queues) / >>sizeof(uint32_t), >> + sizeof(struct pm4_mes_unmap_queues) / >> +sizeof(uint32_t), >> &buffer); >> if (retval) >> goto err_acquire_packet_buffer; >> >> - packet = (struct pm4_unmap_queues *)buffer; >> - memset(buffer, 0, sizeof(struct pm4_unmap_queues)); >> + packet = (struct pm4_mes_unmap_queues *)buffer; >> + memset(buffer, 0, sizeof(struct pm4_mes_unmap_queues)); >> pr_debug("static_queue: unmapping queues: mode is %d , reset >>is %d , type is %d\n", >> mode, reset, type); >> - packet->header.u32all = build_pm4_header(IT_UNMAP_QUEUES, >> - sizeof(struct >>pm4_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: >> @@ -608,12 +535,12 @@ int pm_send_unmap_queue(struct >packet_manager >>*pm, enum kfd_queue_type type, >> break; >> case KFD_PREEMPT_TYPE_FILTER_ALL_QUEUES: >> packet->bitfields2.queue_sel = >> - >>queue_sel__mes_unmap_queues__perform_request_on_all_active_queue >s; >> + >> +queue_sel__mes_unmap_queues__unmap_all_queues; >> break; >> case KFD_PREEMPT_TYPE_FILTER_DYNAMIC_QUEUES: >> /* in this case, we do not preempt static queues */ >> packet->bitfields2.queue_sel = >> - >>queue_sel__mes_unmap_queues__perform_request_on_dynamic_queues >_only; >> + >> +queue_sel__mes_unmap_queues__unmap_all_non_static_queues; >> break; >> default: >> WARN(1, "filter %d", mode); diff --git >>a/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers.h >>b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers.h >> index 97e5442..e50f73d 100644 >> --- a/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers.h >> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers.h >> @@ -41,99 +41,6 @@ union PM4_MES_TYPE_3_HEADER { >> }; >> #endif /* PM4_MES_HEADER_DEFINED */ >> >> -/* --------------------MES_SET_RESOURCES-------------------- */ >> - >> -#ifndef PM4_MES_SET_RESOURCES_DEFINED -#define >> PM4_MES_SET_RESOURCES_DEFINED -enum >set_resources_queue_type_enum { >> - queue_type__mes_set_resources__kernel_interface_queue_kiq = 0, >> - queue_type__mes_set_resources__hsa_interface_queue_hiq = 1, >> - queue_type__mes_set_resources__hsa_debug_interface_queue = 4 >> -}; >> - >> -struct pm4_set_resources { >> - union { >> - union PM4_MES_TYPE_3_HEADER header; /* header */ >> - uint32_t ordinal1; >> - }; >> - >> - union { >> - struct { >> - uint32_t vmid_mask:16; >> - uint32_t unmap_latency:8; >> - uint32_t reserved1:5; >> - enum set_resources_queue_type_enum >> queue_type:3; >> - } bitfields2; >> - uint32_t ordinal2; >> - }; >> - >> - uint32_t queue_mask_lo; >> - uint32_t queue_mask_hi; >> - uint32_t gws_mask_lo; >> - uint32_t gws_mask_hi; >> - >> - union { >> - struct { >> - uint32_t oac_mask:16; >> - uint32_t reserved2:16; >> - } bitfields7; >> - uint32_t ordinal7; >> - }; >> - >> - union { >> - struct { >> - uint32_t gds_heap_base:6; >> - uint32_t reserved3:5; >> - uint32_t gds_heap_size:6; >> - uint32_t reserved4:15; >> - } bitfields8; >> - uint32_t ordinal8; >> - }; >> - >> -}; >> -#endif >> - >> -/*--------------------MES_RUN_LIST-------------------- */ >> - >> -#ifndef PM4_MES_RUN_LIST_DEFINED >> -#define PM4_MES_RUN_LIST_DEFINED >> - >> -struct pm4_runlist { >> - union { >> - union PM4_MES_TYPE_3_HEADER header; /* header */ >> - uint32_t ordinal1; >> - }; >> - >> - union { >> - struct { >> - uint32_t reserved1:2; >> - uint32_t ib_base_lo:30; >> - } bitfields2; >> - uint32_t ordinal2; >> - }; >> - >> - union { >> - struct { >> - uint32_t ib_base_hi:16; >> - uint32_t reserved2:16; >> - } bitfields3; >> - uint32_t ordinal3; >> - }; >> - >> - union { >> - struct { >> - uint32_t ib_size:20; >> - uint32_t chain:1; >> - uint32_t offload_polling:1; >> - uint32_t reserved3:1; >> - uint32_t valid:1; >> - uint32_t reserved4:8; >> - } bitfields4; >> - uint32_t ordinal4; >> - }; >> - >> -}; >> -#endif >> >> /*--------------------MES_MAP_PROCESS-------------------- */ >> >> @@ -186,217 +93,58 @@ struct pm4_map_process { >> }; >> #endif >> >> -/*--------------------MES_MAP_QUEUES--------------------*/ >> - >> -#ifndef PM4_MES_MAP_QUEUES_DEFINED >> -#define PM4_MES_MAP_QUEUES_DEFINED >> -enum map_queues_queue_sel_enum { >> - queue_sel__mes_map_queues__map_to_specified_queue_slots = 0, >> - > queue_sel__mes_map_queues__map_to_hws_determined_queue_slots >= >> 1, >> - queue_sel__mes_map_queues__enable_process_queues = 2 -}; >> +#ifndef PM4_MES_MAP_PROCESS_DEFINED_KV_SCRATCH >> +#define PM4_MES_MAP_PROCESS_DEFINED_KV_SCRATCH >> >> -enum map_queues_vidmem_enum { >> - vidmem__mes_map_queues__uses_no_video_memory = 0, >> - vidmem__mes_map_queues__uses_video_memory = 1 -}; >> - >> -enum map_queues_alloc_format_enum { >> - alloc_format__mes_map_queues__one_per_pipe = 0, >> - alloc_format__mes_map_queues__all_on_one_pipe = 1 -}; >> - >> -enum map_queues_engine_sel_enum { >> - engine_sel__mes_map_queues__compute = 0, >> - engine_sel__mes_map_queues__sdma0 = 2, >> - engine_sel__mes_map_queues__sdma1 = 3 -}; >> - >> -struct pm4_map_queues { >> +struct pm4_map_process_scratch_kv { >> union { >> - union PM4_MES_TYPE_3_HEADER header; /* header */ >> - uint32_t ordinal1; >> - }; >> - >> - union { >> - struct { >> - uint32_t reserved1:4; >> - enum map_queues_queue_sel_enum queue_sel:2; >> - uint32_t reserved2:2; >> - uint32_t vmid:4; >> - uint32_t reserved3:4; >> - enum map_queues_vidmem_enum vidmem:2; >> - uint32_t reserved4:6; >> - enum map_queues_alloc_format_enum >>alloc_format:2; >> - enum map_queues_engine_sel_enum engine_sel:3; >> - uint32_t num_queues:3; >> - } bitfields2; >> - uint32_t ordinal2; >> - }; >> - >> - struct { >> - union { >> - struct { >> - uint32_t is_static:1; >> - uint32_t reserved5:1; >> - uint32_t doorbell_offset:21; >> - uint32_t reserved6:3; >> - uint32_t queue:6; >> - } bitfields3; >> - uint32_t ordinal3; >> - }; >> - >> - uint32_t mqd_addr_lo; >> - uint32_t mqd_addr_hi; >> - uint32_t wptr_addr_lo; >> - uint32_t wptr_addr_hi; >> - >> - } mes_map_queues_ordinals[1]; /* 1..N of these ordinal >>groups */ >> - >> -}; >> -#endif >> - >> -/*--------------------MES_QUERY_STATUS--------------------*/ >> - >> -#ifndef PM4_MES_QUERY_STATUS_DEFINED >> -#define PM4_MES_QUERY_STATUS_DEFINED >> -enum query_status_interrupt_sel_enum { >> - interrupt_sel__mes_query_status__completion_status = 0, >> - interrupt_sel__mes_query_status__process_status = 1, >> - interrupt_sel__mes_query_status__queue_status = 2 -}; >> - >> -enum query_status_command_enum { >> - command__mes_query_status__interrupt_only = 0, >> - command__mes_query_status__fence_only_immediate = 1, >> - command__mes_query_status__fence_only_after_write_ack = 2, >> - >>command__mes_query_status__fence_wait_for_write_ack_send_interrupt >= 3 >>-}; >> - >> -enum query_status_engine_sel_enum { >> - engine_sel__mes_query_status__compute = 0, >> - engine_sel__mes_query_status__sdma0_queue = 2, >> - engine_sel__mes_query_status__sdma1_queue = 3 -}; >> - >> -struct pm4_query_status { >> - union { >> - union PM4_MES_TYPE_3_HEADER header; /* header */ >> - uint32_t ordinal1; >> - }; >> - >> - union { >> - struct { >> - uint32_t context_id:28; >> - enum query_status_interrupt_sel_enum >>interrupt_sel:2; >> - enum query_status_command_enum command:2; >> - } bitfields2; >> - uint32_t ordinal2; >> + union PM4_MES_TYPE_3_HEADER header; /* header */ >> + uint32_t ordinal1; >> }; >> >> union { >> struct { >> uint32_t pasid:16; >> - uint32_t reserved1:16; >> - } bitfields3a; >> - struct { >> - uint32_t reserved2:2; >> - uint32_t doorbell_offset:21; >> - uint32_t reserved3:3; >> - enum query_status_engine_sel_enum >>engine_sel:3; >> - uint32_t reserved4:3; >> - } bitfields3b; >> - uint32_t ordinal3; >> - }; >> - >> - uint32_t addr_lo; >> - uint32_t addr_hi; >> - uint32_t data_lo; >> - uint32_t data_hi; >> -}; >> -#endif >> - >> -/*--------------------MES_UNMAP_QUEUES--------------------*/ >> - >> -#ifndef PM4_MES_UNMAP_QUEUES_DEFINED >> -#define PM4_MES_UNMAP_QUEUES_DEFINED >> -enum unmap_queues_action_enum { >> - action__mes_unmap_queues__preempt_queues = 0, >> - action__mes_unmap_queues__reset_queues = 1, >> - action__mes_unmap_queues__disable_process_queues = 2 -}; >> - >> -enum unmap_queues_queue_sel_enum { >> - >>queue_sel__mes_unmap_queues__perform_request_on_specified_queues >= 0, >> - > queue_sel__mes_unmap_queues__perform_request_on_pasid_queues = >>1, >> - >>queue_sel__mes_unmap_queues__perform_request_on_all_active_queue >s = 2, >> - >>queue_sel__mes_unmap_queues__perform_request_on_dynamic_queues >_only = 3 >>-}; >> - >> -enum unmap_queues_engine_sel_enum { >> - engine_sel__mes_unmap_queues__compute = 0, >> - engine_sel__mes_unmap_queues__sdma0 = 2, >> - engine_sel__mes_unmap_queues__sdma1 = 3 -}; >> - >> -struct pm4_unmap_queues { >> - union { >> - union PM4_MES_TYPE_3_HEADER header; /* header */ >> - uint32_t ordinal1; >> - }; >> - >> - union { >> - struct { >> - enum unmap_queues_action_enum action:2; >> - uint32_t reserved1:2; >> - enum unmap_queues_queue_sel_enum queue_sel:2; >> - uint32_t reserved2:20; >> - enum unmap_queues_engine_sel_enum >>engine_sel:3; >> - uint32_t num_queues:3; >> + uint32_t reserved1:8; >> + uint32_t diq_enable:1; >> + uint32_t process_quantum:7; >> } bitfields2; >> uint32_t ordinal2; >> }; >> >> union { >> struct { >> - uint32_t pasid:16; >> - uint32_t reserved3:16; >> - } bitfields3a; >> - struct { >> - uint32_t reserved4:2; >> - uint32_t doorbell_offset0:21; >> - uint32_t reserved5:9; >> - } bitfields3b; >> + uint32_t page_table_base:28; >> + uint32_t reserved2:4; >> + } bitfields3; >> uint32_t ordinal3; >> }; >> >> - union { >> - struct { >> - uint32_t reserved6:2; >> - uint32_t doorbell_offset1:21; >> - uint32_t reserved7:9; >> - } bitfields4; >> - uint32_t ordinal4; >> - }; >> - >> - union { >> - struct { >> - uint32_t reserved8:2; >> - uint32_t doorbell_offset2:21; >> - uint32_t reserved9:9; >> - } bitfields5; >> - uint32_t ordinal5; >> - }; >> + uint32_t reserved3; >> + uint32_t sh_mem_bases; >> + uint32_t sh_mem_config; >> + uint32_t sh_mem_ape1_base; >> + uint32_t sh_mem_ape1_limit; >> + uint32_t sh_hidden_private_base_vmid; >> + uint32_t reserved4; >> + uint32_t reserved5; >> + uint32_t gds_addr_lo; >> + uint32_t gds_addr_hi; >> >> union { >> struct { >> - uint32_t reserved10:2; >> - uint32_t doorbell_offset3:21; >> - uint32_t reserved11:9; >> - } bitfields6; >> - uint32_t ordinal6; >> + uint32_t num_gws:6; >> + uint32_t reserved6:2; >> + uint32_t num_oac:4; >> + uint32_t reserved7:4; >> + uint32_t gds_size:6; >> + uint32_t num_queues:10; >> + } bitfields14; >> + uint32_t ordinal14; >> }; >> >> + uint32_t completion_signal_lo32; uint32_t >> +completion_signal_hi32; >> }; >> #endif >> >> diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_vi.h >> b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_vi.h >> index c4eda6f..7c8d9b3 100644 >> --- a/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_vi.h >> +++ b/drivers/gpu/drm/amd/amdkfd/kfd_pm4_headers_vi.h >> @@ -126,9 +126,10 @@ struct pm4_mes_runlist { >> uint32_t ib_size:20; >> uint32_t chain:1; >> uint32_t offload_polling:1; >> - uint32_t reserved3:1; >> + uint32_t reserved2:1; >> uint32_t valid:1; >> - uint32_t reserved4:8; >> + uint32_t process_cnt:4; >> + uint32_t reserved3:4; >> } bitfields4; >> uint32_t ordinal4; >> }; >> @@ -143,8 +144,8 @@ struct pm4_mes_runlist { >> >> struct pm4_mes_map_process { >> union { >> - union PM4_MES_TYPE_3_HEADER header; /* >>header */ >> - uint32_t ordinal1; >> + union PM4_MES_TYPE_3_HEADER header; /* header */ >> + uint32_t ordinal1; >> }; >> >> union { >> @@ -155,36 +156,48 @@ struct pm4_mes_map_process { >> uint32_t process_quantum:7; >> } bitfields2; >> uint32_t ordinal2; >> -}; >> + }; >> >> union { >> struct { >> uint32_t page_table_base:28; >> - uint32_t reserved2:4; >> + uint32_t reserved3:4; >> } bitfields3; >> uint32_t ordinal3; >> }; >> >> + uint32_t reserved; >> + >> uint32_t sh_mem_bases; >> + uint32_t sh_mem_config; >> uint32_t sh_mem_ape1_base; >> uint32_t sh_mem_ape1_limit; >> - uint32_t sh_mem_config; >> + >> + uint32_t sh_hidden_private_base_vmid; >> + >> + uint32_t reserved2; >> + uint32_t reserved3; >> + >> uint32_t gds_addr_lo; >> uint32_t gds_addr_hi; >> >> union { >> struct { >> uint32_t num_gws:6; >> - uint32_t reserved3:2; >> + uint32_t reserved4:2; >> uint32_t num_oac:4; >> - uint32_t reserved4:4; >> + uint32_t reserved5:4; >> uint32_t gds_size:6; >> uint32_t num_queues:10; >> } bitfields10; >> uint32_t ordinal10; >> }; >> >> + uint32_t completion_signal_lo; >> + uint32_t completion_signal_hi; >> + >> }; >> + >> #endif >> >> /*--------------------MES_MAP_QUEUES--------------------*/ >> @@ -337,7 +350,7 @@ enum mes_unmap_queues_engine_sel_enum { >> engine_sel__mes_unmap_queues__sdmal = 3 >> }; >> >> -struct PM4_MES_UNMAP_QUEUES { >> +struct pm4_mes_unmap_queues { >> union { >> union PM4_MES_TYPE_3_HEADER header; /* >>header */ >> uint32_t ordinal1; @@ -397,4 +410,101 @@ >>struct PM4_MES_UNMAP_QUEUES { >> }; >> #endif >> >> +#ifndef PM4_MEC_RELEASE_MEM_DEFINED >> +#define PM4_MEC_RELEASE_MEM_DEFINED >> +enum RELEASE_MEM_event_index_enum { >> + event_index___release_mem__end_of_pipe = 5, >> + event_index___release_mem__shader_done = 6 }; >> + >> +enum RELEASE_MEM_cache_policy_enum { >> + cache_policy___release_mem__lru = 0, >> + cache_policy___release_mem__stream = 1, >> + cache_policy___release_mem__bypass = 2 }; >> + >> +enum RELEASE_MEM_dst_sel_enum { >> + dst_sel___release_mem__memory_controller = 0, >> + dst_sel___release_mem__tc_l2 = 1, >> + dst_sel___release_mem__queue_write_pointer_register = 2, >> + dst_sel___release_mem__queue_write_pointer_poll_mask_bit = 3 >> +}; >> + >> +enum RELEASE_MEM_int_sel_enum { >> + int_sel___release_mem__none = 0, >> + int_sel___release_mem__send_interrupt_only = 1, >> + int_sel___release_mem__send_interrupt_after_write_confirm = 2, >> + int_sel___release_mem__send_data_after_write_confirm = 3 }; >> + >> +enum RELEASE_MEM_data_sel_enum { >> + data_sel___release_mem__none = 0, >> + data_sel___release_mem__send_32_bit_low = 1, >> + data_sel___release_mem__send_64_bit_data = 2, >> + data_sel___release_mem__send_gpu_clock_counter = 3, >> + data_sel___release_mem__send_cp_perfcounter_hi_lo = 4, >> + data_sel___release_mem__store_gds_data_to_memory = 5 }; >> + >> +struct pm4_mec_release_mem { >> + union { >> + union PM4_MES_TYPE_3_HEADER header; /*header */ >> + unsigned int ordinal1; >> + }; >> + >> + union { >> + struct { >> + unsigned int event_type:6; >> + unsigned int reserved1:2; >> + enum RELEASE_MEM_event_index_enum >> +event_index:4; >> + unsigned int tcl1_vol_action_ena:1; >> + unsigned int tc_vol_action_ena:1; >> + unsigned int reserved2:1; >> + unsigned int tc_wb_action_ena:1; >> + unsigned int tcl1_action_ena:1; >> + unsigned int tc_action_ena:1; >> + unsigned int reserved3:6; >> + unsigned int atc:1; >> + enum RELEASE_MEM_cache_policy_enum >> +cache_policy:2; >> + unsigned int reserved4:5; >> + } bitfields2; >> + unsigned int ordinal2; >> + }; >> + >> + union { >> + struct { >> + unsigned int reserved5:16; >> + enum RELEASE_MEM_dst_sel_enum dst_sel:2; >> + unsigned int reserved6:6; >> + enum RELEASE_MEM_int_sel_enum int_sel:3; >> + unsigned int reserved7:2; >> + enum RELEASE_MEM_data_sel_enum data_sel:3; >> + } bitfields3; >> + unsigned int ordinal3; >> + }; >> + >> + union { >> + struct { >> + unsigned int reserved8:2; >> + unsigned int address_lo_32b:30; >> + } bitfields4; >> + struct { >> + unsigned int reserved9:3; >> + unsigned int address_lo_64b:29; >> + } bitfields5; >> + unsigned int ordinal4; >> + }; >> + >> + unsigned int address_hi; >> + >> + unsigned int data_lo; >> + >> + unsigned int data_hi; >> +}; >> +#endif >> + >> +enum { >> + CACHE_FLUSH_AND_INV_TS_EVENT = 0x00000014 }; >> + >> #endif >> -- >> 2.7.4 >> > >_______________________________________________ >amd-gfx mailing list >amd-gfx@lists.freedesktop.org >https://lists.freedesktop.org/mailman/listinfo/amd-gfx _______________________________________________ amd-gfx mailing list amd-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/amd-gfx