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, 15 insertions, 14 deletions

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
index 0d53f6067422..f933bd231fb9 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v11.c
@@ -26,6 +26,7 @@
 #include "kfd_device_queue_manager.h"
 #include "ivsrcid/vmc/irqsrcs_vmc_1_0.h"
 #include "kfd_smi_events.h"
+#include "kfd_debug.h"
 
 /*
  * GFX11 SQ Interrupts
@@ -187,7 +188,7 @@ static void print_sq_intr_info_error(uint32_t context_id0, uint32_t context_id1)
 		REG_GET_FIELD(context_id0, SQ_INTERRUPT_WORD_ERROR_CTXID1, WGP_ID));
 }
 
-static void event_interrupt_poison_consumption_v11(struct kfd_dev *dev,
+static void event_interrupt_poison_consumption_v11(struct kfd_node *dev,
 				uint16_t pasid, uint16_t source_id)
 {
 	int ret = -EINVAL;
@@ -225,7 +226,7 @@ static void event_interrupt_poison_consumption_v11(struct kfd_dev *dev,
 		amdgpu_amdkfd_ras_poison_consumption_handler(dev->adev, true);
 }
 
-static bool event_interrupt_isr_v11(struct kfd_dev *dev,
+static bool event_interrupt_isr_v11(struct kfd_node *dev,
 					const uint32_t *ih_ring_entry,
 					uint32_t *patched_ihre,
 					bool *patched_flag)
@@ -238,7 +239,7 @@ static bool event_interrupt_isr_v11(struct kfd_dev *dev,
 	client_id = SOC15_CLIENT_ID_FROM_IH_ENTRY(ih_ring_entry);
 	/* Only handle interrupts from KFD VMIDs */
 	vmid = SOC15_VMID_FROM_IH_ENTRY(ih_ring_entry);
-	if (/*!KFD_IRQ_IS_FENCE(client_id, source_id) &&*/
+	if (!KFD_IRQ_IS_FENCE(client_id, source_id) &&
 	    (vmid < dev->vm_info.first_vmid_kfd ||
 	    vmid > dev->vm_info.last_vmid_kfd))
 		return false;
@@ -267,19 +268,19 @@ static bool event_interrupt_isr_v11(struct kfd_dev *dev,
 		source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG ||
 		source_id == SOC15_INTSRC_CP_BAD_OPCODE ||
 		source_id == SOC21_INTSRC_SDMA_TRAP ||
-		/* KFD_IRQ_IS_FENCE(client_id, source_id) || */
+		KFD_IRQ_IS_FENCE(client_id, source_id) ||
 		(((client_id == SOC21_IH_CLIENTID_VMC) ||
 		 ((client_id == SOC21_IH_CLIENTID_GFX) &&
 		  (source_id == UTCL2_1_0__SRCID__FAULT))) &&
 		  !amdgpu_no_queue_eviction_on_vm_fault);
 }
 
-static void event_interrupt_wq_v11(struct kfd_dev *dev,
+static void event_interrupt_wq_v11(struct kfd_node *dev,
 					const uint32_t *ih_ring_entry)
 {
 	uint16_t source_id, client_id, ring_id, pasid, vmid;
 	uint32_t context_id0, context_id1;
-	uint8_t sq_int_enc, sq_int_errtype, sq_int_priv;
+	uint8_t sq_int_enc, sq_int_priv, sq_int_errtype;
 	struct kfd_vm_fault_info info = {0};
 	struct kfd_hsa_memory_exception_data exception_data;
 
@@ -312,9 +313,9 @@ static void event_interrupt_wq_v11(struct kfd_dev *dev,
 		exception_data.failure.ReadOnly = info.prot_write ? 1 : 0;
 		exception_data.failure.imprecise = 0;
 
-		/*kfd_set_dbg_ev_from_interrupt(dev, pasid, -1,
+		kfd_set_dbg_ev_from_interrupt(dev, pasid, -1,
 					      KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION),
-					      &exception_data, sizeof(exception_data));*/
+					      &exception_data, sizeof(exception_data));
 		kfd_smi_event_update_vmfault(dev, pasid);
 
 	/* GRBM, SDMA, SE, PMM */
@@ -324,11 +325,11 @@ static void event_interrupt_wq_v11(struct kfd_dev *dev,
 		/* CP */
 		if (source_id == SOC15_INTSRC_CP_END_OF_PIPE)
 			kfd_signal_event_interrupt(pasid, context_id0, 32);
-		/*else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
+		else if (source_id == SOC15_INTSRC_CP_BAD_OPCODE)
 			kfd_set_dbg_ev_from_interrupt(dev, pasid,
 				KFD_CTXID0_DOORBELL_ID(context_id0),
 				KFD_EC_MASK(KFD_CTXID0_CP_BAD_OP_ECODE(context_id0)),
-				NULL, 0);*/
+				NULL, 0);
 
 		/* SDMA */
 		else if (source_id == SOC21_INTSRC_SDMA_TRAP)
@@ -350,11 +351,11 @@ static void event_interrupt_wq_v11(struct kfd_dev *dev,
 				print_sq_intr_info_inst(context_id0, context_id1);
 				sq_int_priv = REG_GET_FIELD(context_id0,
 						SQ_INTERRUPT_WORD_WAVE_CTXID0, PRIV);
-				/*if (sq_int_priv && (kfd_set_dbg_ev_from_interrupt(dev, pasid,
+				if (sq_int_priv && (kfd_set_dbg_ev_from_interrupt(dev, pasid,
 						KFD_CTXID0_DOORBELL_ID(context_id0),
 						KFD_CTXID0_TRAP_CODE(context_id0),
 						NULL, 0)))
-					return;*/
+					return;
 				break;
 			case SQ_INTERRUPT_WORD_ENCODING_ERROR:
 				print_sq_intr_info_error(context_id0, context_id1);
@@ -373,8 +374,8 @@ static void event_interrupt_wq_v11(struct kfd_dev *dev,
 			kfd_signal_event_interrupt(pasid, context_id0 & 0xffffff, 24);
 		}
 
-	/*} else if (KFD_IRQ_IS_FENCE(client_id, source_id)) {
-		kfd_process_close_interrupt_drain(pasid);*/
+	} else if (KFD_IRQ_IS_FENCE(client_id, source_id)) {
+		kfd_process_close_interrupt_drain(pasid);
 	}
 }