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, 54 insertions, 29 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 5aa75f72caa1..31fec5e70d13 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -46,15 +46,33 @@ static void update_cu_mask(struct mqd_manager *mm, void *mqd,
 {
 	struct v11_compute_mqd *m;
 	uint32_t se_mask[KFD_MAX_NUM_SE] = {0};
+	bool has_wa_flag = minfo && (minfo->update_flag & (UPDATE_FLAG_DBG_WA_ENABLE |
+			UPDATE_FLAG_DBG_WA_DISABLE));
 
-	if (!minfo || (minfo->update_flag != UPDATE_FLAG_CU_MASK) ||
-	    !minfo->cu_mask.ptr)
+	if (!minfo || !(has_wa_flag || minfo->cu_mask.ptr))
 		return;
 
+	m = get_mqd(mqd);
+
+	if (has_wa_flag) {
+		uint32_t wa_mask = minfo->update_flag == UPDATE_FLAG_DBG_WA_ENABLE ?
+						0xffff : 0xffffffff;
+
+		m->compute_static_thread_mgmt_se0 = wa_mask;
+		m->compute_static_thread_mgmt_se1 = wa_mask;
+		m->compute_static_thread_mgmt_se2 = wa_mask;
+		m->compute_static_thread_mgmt_se3 = wa_mask;
+		m->compute_static_thread_mgmt_se4 = wa_mask;
+		m->compute_static_thread_mgmt_se5 = wa_mask;
+		m->compute_static_thread_mgmt_se6 = wa_mask;
+		m->compute_static_thread_mgmt_se7 = wa_mask;
+
+		return;
+	}
+
 	mqd_symmetrically_map_cu_mask(mm,
 		minfo->cu_mask.ptr, minfo->cu_mask.count, se_mask);
 
-	m = get_mqd(mqd);
 	m->compute_static_thread_mgmt_se0 = se_mask[0];
 	m->compute_static_thread_mgmt_se1 = se_mask[1];
 	m->compute_static_thread_mgmt_se2 = se_mask[2];
@@ -81,7 +99,7 @@ static void set_priority(struct v11_compute_mqd *m, struct queue_properties *q)
 	m->cp_hqd_queue_priority = q->priority;
 }
 
-static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
+static struct kfd_mem_obj *allocate_mqd(struct kfd_node *node,
 		struct queue_properties *q)
 {
 	struct kfd_mem_obj *mqd_mem_obj;
@@ -91,12 +109,12 @@ static struct kfd_mem_obj *allocate_mqd(struct kfd_dev *kfd,
 	 * MES write to areas beyond MQD size. So allocate
 	 * 1 PAGE_SIZE memory for MQD is MES is enabled.
 	 */
-	if (kfd->shared_resources.enable_mes)
+	if (node->kfd->shared_resources.enable_mes)
 		size = PAGE_SIZE;
 	else
 		size = sizeof(struct v11_compute_mqd);
 
-	if (kfd_gtt_sa_allocate(kfd, size, &mqd_mem_obj))
+	if (kfd_gtt_sa_allocate(node, size, &mqd_mem_obj))
 		return NULL;
 
 	return mqd_mem_obj;
@@ -109,11 +127,12 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	uint64_t addr;
 	struct v11_compute_mqd *m;
 	int size;
+	uint32_t wa_mask = q->is_dbg_wa ? 0xffff : 0xffffffff;
 
 	m = (struct v11_compute_mqd *) mqd_mem_obj->cpu_ptr;
 	addr = mqd_mem_obj->gpu_addr;
 
-	if (mm->dev->shared_resources.enable_mes)
+	if (mm->dev->kfd->shared_resources.enable_mes)
 		size = PAGE_SIZE;
 	else
 		size = sizeof(struct v11_compute_mqd);
@@ -122,14 +141,15 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 
 	m->header = 0xC0310800;
 	m->compute_pipelinestat_enable = 1;
-	m->compute_static_thread_mgmt_se0 = 0xFFFFFFFF;
-	m->compute_static_thread_mgmt_se1 = 0xFFFFFFFF;
-	m->compute_static_thread_mgmt_se2 = 0xFFFFFFFF;
-	m->compute_static_thread_mgmt_se3 = 0xFFFFFFFF;
-	m->compute_static_thread_mgmt_se4 = 0xFFFFFFFF;
-	m->compute_static_thread_mgmt_se5 = 0xFFFFFFFF;
-	m->compute_static_thread_mgmt_se6 = 0xFFFFFFFF;
-	m->compute_static_thread_mgmt_se7 = 0xFFFFFFFF;
+
+	m->compute_static_thread_mgmt_se0 = wa_mask;
+	m->compute_static_thread_mgmt_se1 = wa_mask;
+	m->compute_static_thread_mgmt_se2 = wa_mask;
+	m->compute_static_thread_mgmt_se3 = wa_mask;
+	m->compute_static_thread_mgmt_se4 = wa_mask;
+	m->compute_static_thread_mgmt_se5 = wa_mask;
+	m->compute_static_thread_mgmt_se6 = wa_mask;
+	m->compute_static_thread_mgmt_se7 = wa_mask;
 
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
@@ -143,6 +163,11 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_QUANTUM__QUANTUM_SCALE__SHIFT |
 			1 << CP_HQD_QUANTUM__QUANTUM_DURATION__SHIFT;
 
+	/* Set cp_hqd_hq_scheduler0 bit 14 to 1 to have the CP set up the
+	 * DISPATCH_PTR.  This is required for the kfd debugger
+	 */
+	m->cp_hqd_hq_status0 = 1 << 14;
+
 	/*
 	 * GFX11 RS64 CPFW version >= 509 supports PCIe atomics support
 	 * acknowledgment.
@@ -155,7 +180,7 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 			1 << CP_HQD_AQL_CONTROL__CONTROL0__SHIFT;
 	}
 
-	if (mm->dev->cwsr_enabled) {
+	if (mm->dev->kfd->cwsr_enabled) {
 		m->cp_hqd_persistent_state |=
 			(1 << CP_HQD_PERSISTENT_STATE__QSWITCH_MODE__SHIFT);
 		m->cp_hqd_ctx_save_base_addr_lo =
@@ -184,7 +209,7 @@ static int load_mqd(struct mqd_manager *mm, void *mqd,
 
 	r = mm->dev->kfd2kgd->hqd_load(mm->dev->adev, mqd, pipe_id, queue_id,
 					  (uint32_t __user *)p->write_ptr,
-					  wptr_shift, 0, mms);
+					  wptr_shift, 0, mms, 0);
 	return r;
 }
 
@@ -243,7 +268,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 		m->cp_hqd_pq_doorbell_control |=
 			1 << CP_HQD_PQ_DOORBELL_CONTROL__DOORBELL_BIF_DROP__SHIFT;
 	}
-	if (mm->dev->cwsr_enabled)
+	if (mm->dev->kfd->cwsr_enabled)
 		m->cp_hqd_ctx_save_control = 0;
 
 	update_cu_mask(mm, mqd, minfo);
@@ -260,12 +285,13 @@ static uint32_t read_doorbell_id(void *mqd)
 }
 
 static int get_wave_state(struct mqd_manager *mm, void *mqd,
+			  struct queue_properties *q,
 			  void __user *ctl_stack,
 			  u32 *ctl_stack_used_size,
 			  u32 *save_area_used_size)
 {
 	struct v11_compute_mqd *m;
-	/*struct mqd_user_context_save_area_header header;*/
+	struct kfd_context_save_area_header header;
 
 	m = get_mqd(mqd);
 
@@ -283,16 +309,15 @@ static int get_wave_state(struct mqd_manager *mm, void *mqd,
 	 * it's part of the context save area that is already
 	 * accessible to user mode
 	 */
-/*
-	header.control_stack_size = *ctl_stack_used_size;
-	header.wave_state_size = *save_area_used_size;
+	header.wave_state.control_stack_size = *ctl_stack_used_size;
+	header.wave_state.wave_state_size = *save_area_used_size;
 
-	header.wave_state_offset = m->cp_hqd_wg_state_offset;
-	header.control_stack_offset = m->cp_hqd_cntl_stack_offset;
+	header.wave_state.wave_state_offset = m->cp_hqd_wg_state_offset;
+	header.wave_state.control_stack_offset = m->cp_hqd_cntl_stack_offset;
 
-	if (copy_to_user(ctl_stack, &header, sizeof(header)))
+	if (copy_to_user(ctl_stack, &header, sizeof(header.wave_state)))
 		return -EFAULT;
-*/
+
 	return 0;
 }
 
@@ -319,7 +344,7 @@ static void init_mqd_sdma(struct mqd_manager *mm, void **mqd,
 
 	m = (struct v11_sdma_mqd *) mqd_mem_obj->cpu_ptr;
 
-	if (mm->dev->shared_resources.enable_mes)
+	if (mm->dev->kfd->shared_resources.enable_mes)
 		size = PAGE_SIZE;
 	else
 		size = sizeof(struct v11_sdma_mqd);
@@ -387,7 +412,7 @@ static int debugfs_show_mqd_sdma(struct seq_file *m, void *data)
 #endif
 
 struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
-		struct kfd_dev *dev)
+		struct kfd_node *dev)
 {
 	struct mqd_manager *mqd;
 
@@ -463,7 +488,7 @@ struct mqd_manager *mqd_manager_init_v11(enum KFD_MQD_TYPE type,
 		 * To allocate SDMA MQDs by generic functions
 		 * when MES is enabled.
 		 */
-		if (dev->shared_resources.enable_mes) {
+		if (dev->kfd->shared_resources.enable_mes) {
 			mqd->allocate_mqd = allocate_mqd;
 			mqd->free_mqd = kfd_free_mqd_cp;
 		}