Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com

1 files changed, 80 insertions, 6 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
index 18250845a989..29a2d0499b67 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager_v9.c
@@ -34,6 +34,9 @@ static int pm_map_process_v9(struct packet_manager *pm,
 {
 	struct pm4_mes_map_process *packet;
 	uint64_t vm_page_table_base_addr = qpd->page_table_base;
+	struct kfd_node *kfd = pm->dqm->dev;
+	struct kfd_process_device *pdd =
+			container_of(qpd, struct kfd_process_device, qpd);
 
 	packet = (struct pm4_mes_map_process *)buffer;
 	memset(buffer, 0, sizeof(struct pm4_mes_map_process));
@@ -49,6 +52,12 @@ static int pm_map_process_v9(struct packet_manager *pm,
 	packet->bitfields14.sdma_enable = 1;
 	packet->bitfields14.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
 
+	if (kfd->dqm->trap_debug_vmid && pdd->process->debug_trap_enabled &&
+			pdd->process->runtime_info.runtime_state == DEBUG_RUNTIME_STATE_ENABLED) {
+		packet->bitfields2.debug_vmid = kfd->dqm->trap_debug_vmid;
+		packet->bitfields2.new_debug = 1;
+	}
+
 	packet->sh_mem_config = qpd->sh_mem_config;
 	packet->sh_mem_bases = qpd->sh_mem_bases;
 	if (qpd->tba_addr) {
@@ -79,6 +88,10 @@ static int pm_map_process_aldebaran(struct packet_manager *pm,
 {
 	struct pm4_mes_map_process_aldebaran *packet;
 	uint64_t vm_page_table_base_addr = qpd->page_table_base;
+	struct kfd_dev *kfd = pm->dqm->dev->kfd;
+	struct kfd_process_device *pdd =
+			container_of(qpd, struct kfd_process_device, qpd);
+	int i;
 
 	packet = (struct pm4_mes_map_process_aldebaran *)buffer;
 	memset(buffer, 0, sizeof(struct pm4_mes_map_process_aldebaran));
@@ -93,6 +106,16 @@ static int pm_map_process_aldebaran(struct packet_manager *pm,
 	packet->bitfields14.num_oac = qpd->num_oac;
 	packet->bitfields14.sdma_enable = 1;
 	packet->bitfields14.num_queues = (qpd->is_debug) ? 0 : qpd->queue_count;
+	packet->spi_gdbg_per_vmid_cntl = pdd->spi_dbg_override |
+						pdd->spi_dbg_launch_mode;
+
+	if (pdd->process->debug_trap_enabled) {
+		for (i = 0; i < kfd->device_info.num_of_watch_points; i++)
+			packet->tcp_watch_cntl[i] = pdd->watch_points[i];
+
+		packet->bitfields2.single_memops =
+				!!(pdd->process->dbg_flags & KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP);
+	}
 
 	packet->sh_mem_config = qpd->sh_mem_config;
 	packet->sh_mem_bases = qpd->sh_mem_bases;
@@ -119,7 +142,7 @@ static int pm_runlist_v9(struct packet_manager *pm, uint32_t *buffer,
 	struct pm4_mes_runlist *packet;
 
 	int concurrent_proc_cnt = 0;
-	struct kfd_dev *kfd = pm->dqm->dev;
+	struct kfd_node *kfd = pm->dqm->dev;
 
 	/* Determine the number of processes to map together to HW:
 	 * it can not exceed the number of VMIDs available to the
@@ -220,13 +243,24 @@ static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 	case KFD_QUEUE_TYPE_SDMA:
 	case KFD_QUEUE_TYPE_SDMA_XGMI:
 		use_static = false; /* no static queues under SDMA */
-		if (q->properties.sdma_engine_id < 2 && !pm_use_ext_eng(q->device))
+		if (q->properties.sdma_engine_id < 2 &&
+		    !pm_use_ext_eng(q->device->kfd))
 			packet->bitfields2.engine_sel = q->properties.sdma_engine_id +
 				engine_sel__mes_map_queues__sdma0_vi;
 		else {
-			packet->bitfields2.extended_engine_sel =
-				extended_engine_sel__mes_map_queues__sdma0_to_7_sel;
-			packet->bitfields2.engine_sel = q->properties.sdma_engine_id;
+			/*
+			 * For GFX9.4.3, SDMA engine id can be greater than 8.
+			 * For such cases, set extended_engine_sel to 2 and
+			 * ensure engine_sel lies between 0-7.
+			 */
+			if (q->properties.sdma_engine_id >= 8)
+				packet->bitfields2.extended_engine_sel =
+					extended_engine_sel__mes_map_queues__sdma8_to_15_sel;
+			else
+				packet->bitfields2.extended_engine_sel =
+					extended_engine_sel__mes_map_queues__sdma0_to_7_sel;
+
+			packet->bitfields2.engine_sel = q->properties.sdma_engine_id % 8;
 		}
 		break;
 	default:
@@ -251,6 +285,41 @@ static int pm_map_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 	return 0;
 }
 
+static int pm_set_grace_period_v9(struct packet_manager *pm,
+		uint32_t *buffer,
+		uint32_t grace_period)
+{
+	struct pm4_mec_write_data_mmio *packet;
+	uint32_t reg_offset = 0;
+	uint32_t reg_data = 0;
+
+	pm->dqm->dev->kfd2kgd->build_grace_period_packet_info(
+			pm->dqm->dev->adev,
+			pm->dqm->wait_times,
+			grace_period,
+			&reg_offset,
+			&reg_data);
+
+	if (grace_period == USE_DEFAULT_GRACE_PERIOD)
+		reg_data = pm->dqm->wait_times;
+
+	packet = (struct pm4_mec_write_data_mmio *)buffer;
+	memset(buffer, 0, sizeof(struct pm4_mec_write_data_mmio));
+
+	packet->header.u32All = pm_build_pm4_header(IT_WRITE_DATA,
+					sizeof(struct pm4_mec_write_data_mmio));
+
+	packet->bitfields2.dst_sel  = dst_sel___write_data__mem_mapped_register;
+	packet->bitfields2.addr_incr =
+			addr_incr___write_data__do_not_increment_address;
+
+	packet->bitfields3.dst_mmreg_addr = reg_offset;
+
+	packet->data = reg_data;
+
+	return 0;
+}
+
 static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 			enum kfd_unmap_queues_filter filter,
 			uint32_t filter_param, bool reset)
@@ -263,7 +332,8 @@ static int pm_unmap_queues_v9(struct packet_manager *pm, uint32_t *buffer,
 	packet->header.u32All = pm_build_pm4_header(IT_UNMAP_QUEUES,
 					sizeof(struct pm4_mes_unmap_queues));
 
-	packet->bitfields2.extended_engine_sel = pm_use_ext_eng(pm->dqm->dev) ?
+	packet->bitfields2.extended_engine_sel =
+				pm_use_ext_eng(pm->dqm->dev->kfd) ?
 		extended_engine_sel__mes_unmap_queues__sdma0_to_7_sel :
 		extended_engine_sel__mes_unmap_queues__legacy_engine_sel;
 
@@ -333,6 +403,7 @@ const struct packet_manager_funcs kfd_v9_pm_funcs = {
 	.set_resources		= pm_set_resources_v9,
 	.map_queues		= pm_map_queues_v9,
 	.unmap_queues		= pm_unmap_queues_v9,
+	.set_grace_period       = pm_set_grace_period_v9,
 	.query_status		= pm_query_status_v9,
 	.release_mem		= NULL,
 	.map_process_size	= sizeof(struct pm4_mes_map_process),
@@ -340,6 +411,7 @@ const struct packet_manager_funcs kfd_v9_pm_funcs = {
 	.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),
+	.set_grace_period_size  = sizeof(struct pm4_mec_write_data_mmio),
 	.query_status_size	= sizeof(struct pm4_mes_query_status),
 	.release_mem_size	= 0,
 };
@@ -350,6 +422,7 @@ const struct packet_manager_funcs kfd_aldebaran_pm_funcs = {
 	.set_resources		= pm_set_resources_v9,
 	.map_queues		= pm_map_queues_v9,
 	.unmap_queues		= pm_unmap_queues_v9,
+	.set_grace_period       = pm_set_grace_period_v9,
 	.query_status		= pm_query_status_v9,
 	.release_mem		= NULL,
 	.map_process_size	= sizeof(struct pm4_mes_map_process_aldebaran),
@@ -357,6 +430,7 @@ const struct packet_manager_funcs kfd_aldebaran_pm_funcs = {
 	.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),
+	.set_grace_period_size  = sizeof(struct pm4_mec_write_data_mmio),
 	.query_status_size	= sizeof(struct pm4_mes_query_status),
 	.release_mem_size	= 0,
 };