Merge tag 'amd-drm-next-6.8-2023-12-01' of https://gitlab.freedesktop…

….org/agd5f/linux into drm-next

amd-drm-next-6.8-2023-12-01:

amdgpu:
- Add new 64 bit sequence number infrastructure.
  This will ultimately be used for user queue synchronization.
- GPUVM updates
- Misc code cleanups
- RAS updates
- DCN 3.5 updates
- Rework PCIe link speed handling
- Document GPU reset types
- DMUB fixes
- eDP fixes
- NBIO 7.9 updates
- NBIO 7.11 updates
- SubVP updates
- DCN 3.1.4 fixes
- ABM fixes
- AGP aperture fix
- DCN 3.1.5 fix
- Fix some potential error path memory leaks
- Enable PCIe PMEs
- Add XGMI, PCIe state dumping for aqua vanjaram
- GFX11 golden register updates
- Misc display fixes

amdkfd:
- Migrate TLB flushing logic to amdgpu
- Trap handler fixes
- Fix restore workers handling on suspend and reset
- Fix possible memory leak in pqm_uninit()

radeon:
- Fix some possible overflows in command buffer checking
- Check for errors in ring_lock

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20231201181743.5313-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

Documentation/gpu/amdgpu/display/dc-debug.rst

@@ -75,3 +75,44 @@ change in real-time by using something like::
 
 When reporting a bug related to DC, consider attaching this log before and
 after you reproduce the bug.
+
+DMUB Firmware Debug
+===================
+
+Sometimes, dmesg logs aren't enough. This is especially true if a feature is
+implemented primarily in DMUB firmware. In such cases, all we see in dmesg when
+an issue arises is some generic timeout error. So, to get more relevant
+information, we can trace DMUB commands by enabling the relevant bits in
+`amdgpu_dm_dmub_trace_mask`.
+
+Currently, we support the tracing of the following groups:
+
+Trace Groups
+------------
+
+.. csv-table::
+   :header-rows: 1
+   :widths: 1, 1
+   :file: ./trace-groups-table.csv
+
+**Note: Not all ASICs support all of the listed trace groups**
+
+So, to enable just PSR tracing you can use the following command::
+
+  # echo 0x8020 > /sys/kernel/debug/dri/0/amdgpu_dm_dmub_trace_mask
+
+Then, you need to enable logging trace events to the buffer, which you can do
+using the following::
+
+  # echo 1 > /sys/kernel/debug/dri/0/amdgpu_dm_dmcub_trace_event_en
+
+Lastly, after you are able to reproduce the issue you are trying to debug,
+you can disable tracing and read the trace log by using the following::
+
+  # echo 0 > /sys/kernel/debug/dri/0/amdgpu_dm_dmcub_trace_event_en
+  # cat /sys/kernel/debug/dri/0/amdgpu_dm_dmub_tracebuffer
+
+So, when reporting bugs related to features such as PSR and ABM, consider
+enabling the relevant bits in the mask before reproducing the issue and
+attach the log that you obtain from the trace buffer in any bug reports that you
+create.

Documentation/gpu/amdgpu/display/trace-groups-table.csv

@@ -0,0 +1,29 @@
+Name, Mask Value
+INFO, 0x1
+IRQ SVC, 0x2
+VBIOS, 0x4
+REGISTER, 0x8
+PHY DBG, 0x10
+PSR, 0x20
+AUX, 0x40
+SMU, 0x80
+MALL, 0x100
+ABM, 0x200
+ALPM, 0x400
+TIMER, 0x800
+HW LOCK MGR, 0x1000
+INBOX1, 0x2000
+PHY SEQ, 0x4000
+PSR STATE, 0x8000
+ZSTATE, 0x10000
+TRANSMITTER CTL, 0x20000
+PANEL CNTL, 0x40000
+FAMS, 0x80000
+DPIA, 0x100000
+SUBVP, 0x200000
+INBOX0, 0x400000
+SDP, 0x4000000
+REPLAY, 0x8000000
+REPLAY RESIDENCY, 0x20000000
+CURSOR INFO, 0x80000000
+IPS, 0x100000000

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -80,7 +80,7 @@ amdgpu-y += amdgpu_device.o amdgpu_doorbell_mgr.o amdgpu_kms.o \
 	amdgpu_umc.o smu_v11_0_i2c.o amdgpu_fru_eeprom.o amdgpu_rap.o \
 	amdgpu_fw_attestation.o amdgpu_securedisplay.o \
 	amdgpu_eeprom.o amdgpu_mca.o amdgpu_psp_ta.o amdgpu_lsdma.o \
-	amdgpu_ring_mux.o amdgpu_xcp.o
+	amdgpu_ring_mux.o amdgpu_xcp.o amdgpu_seq64.o
 
 amdgpu-$(CONFIG_PROC_FS) += amdgpu_fdinfo.o
 

drivers/gpu/drm/amd/amdgpu/amdgpu.h

@@ -109,6 +109,8 @@
 #include "amdgpu_mca.h"
 #include "amdgpu_ras.h"
 #include "amdgpu_xcp.h"
+#include "amdgpu_seq64.h"
+#include "amdgpu_reg_state.h"
 
 #define MAX_GPU_INSTANCE		64
 
@@ -468,6 +470,7 @@ struct amdgpu_fpriv {
 	struct amdgpu_vm	vm;
 	struct amdgpu_bo_va	*prt_va;
 	struct amdgpu_bo_va	*csa_va;
+	struct amdgpu_bo_va	*seq64_va;
 	struct mutex		bo_list_lock;
 	struct idr		bo_list_handles;
 	struct amdgpu_ctx_mgr	ctx_mgr;
@@ -506,6 +509,31 @@ struct amdgpu_allowed_register_entry {
 	bool grbm_indexed;
 };
 
+/**
+ * enum amd_reset_method - Methods for resetting AMD GPU devices
+ *
+ * @AMD_RESET_METHOD_NONE: The device will not be reset.
+ * @AMD_RESET_LEGACY: Method reserved for SI, CIK and VI ASICs.
+ * @AMD_RESET_MODE0: Reset the entire ASIC. Not currently available for the
+ *                   any device.
+ * @AMD_RESET_MODE1: Resets all IP blocks on the ASIC (SDMA, GFX, VCN, etc.)
+ *                   individually. Suitable only for some discrete GPU, not
+ *                   available for all ASICs.
+ * @AMD_RESET_MODE2: Resets a lesser level of IPs compared to MODE1. Which IPs
+ *                   are reset depends on the ASIC. Notably doesn't reset IPs
+ *                   shared with the CPU on APUs or the memory controllers (so
+ *                   VRAM is not lost). Not available on all ASICs.
+ * @AMD_RESET_BACO: BACO (Bus Alive, Chip Off) method powers off and on the card
+ *                  but without powering off the PCI bus. Suitable only for
+ *                  discrete GPUs.
+ * @AMD_RESET_PCI: Does a full bus reset using core Linux subsystem PCI reset
+ *                 and does a secondary bus reset or FLR, depending on what the
+ *                 underlying hardware supports.
+ *
+ * Methods available for AMD GPU driver for resetting the device. Not all
+ * methods are suitable for every device. User can override the method using
+ * module parameter `reset_method`.
+ */
 enum amd_reset_method {
 	AMD_RESET_METHOD_NONE = -1,
 	AMD_RESET_METHOD_LEGACY = 0,
@@ -585,6 +613,10 @@ struct amdgpu_asic_funcs {
 				  const struct amdgpu_video_codecs **codecs);
 	/* encode "> 32bits" smn addressing */
 	u64 (*encode_ext_smn_addressing)(int ext_id);
+
+	ssize_t (*get_reg_state)(struct amdgpu_device *adev,
+				 enum amdgpu_reg_state reg_state, void *buf,
+				 size_t max_size);
 };
 
 /*
@@ -986,6 +1018,9 @@ struct amdgpu_device {
 	/* GDS */
 	struct amdgpu_gds		gds;
 
+	/* for userq and VM fences */
+	struct amdgpu_seq64		seq64;
+
 	/* KFD */
 	struct amdgpu_kfd_dev		kfd;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c

@@ -547,7 +547,7 @@ int amdgpu_amdkfd_get_xgmi_bandwidth_mbytes(struct amdgpu_device *dst,
 	struct amdgpu_device *adev = dst, *peer_adev;
 	int num_links;
 
-	if (adev->asic_type != CHIP_ALDEBARAN)
+	if (amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(9, 4, 2))
 		return 0;
 
 	if (src)
@@ -710,35 +710,6 @@ bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 	return false;
 }
 
-int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct amdgpu_device *adev,
-				     uint16_t vmid)
-{
-	if (adev->family == AMDGPU_FAMILY_AI) {
-		int i;
-
-		for_each_set_bit(i, adev->vmhubs_mask, AMDGPU_MAX_VMHUBS)
-			amdgpu_gmc_flush_gpu_tlb(adev, vmid, i, 0);
-	} else {
-		amdgpu_gmc_flush_gpu_tlb(adev, vmid, AMDGPU_GFXHUB(0), 0);
-	}
-
-	return 0;
-}
-
-int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
-				      uint16_t pasid,
-				      enum TLB_FLUSH_TYPE flush_type,
-				      uint32_t inst)
-{
-	bool all_hub = false;
-
-	if (adev->family == AMDGPU_FAMILY_AI ||
-	    adev->family == AMDGPU_FAMILY_RV)
-		all_hub = true;
-
-	return amdgpu_gmc_flush_gpu_tlb_pasid(adev, pasid, flush_type, all_hub, inst);
-}
-
 bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev)
 {
 	return adev->have_atomics_support;

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h

@@ -162,11 +162,6 @@ int amdgpu_amdkfd_submit_ib(struct amdgpu_device *adev,
 				uint32_t *ib_cmd, uint32_t ib_len);
 void amdgpu_amdkfd_set_compute_idle(struct amdgpu_device *adev, bool idle);
 bool amdgpu_amdkfd_have_atomics_support(struct amdgpu_device *adev);
-int amdgpu_amdkfd_flush_gpu_tlb_vmid(struct amdgpu_device *adev,
-				uint16_t vmid);
-int amdgpu_amdkfd_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
-				uint16_t pasid, enum TLB_FLUSH_TYPE flush_type,
-				uint32_t inst);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_arcturus.c

@@ -200,7 +200,7 @@ int kgd_arcturus_hqd_sdma_dump(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+6+7+10)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gc_9_4_3.c

@@ -141,7 +141,7 @@ static int kgd_gfx_v9_4_3_hqd_sdma_dump(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32(addr);         \
 	} while (0)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c

@@ -214,7 +214,7 @@ static int kgd_hqd_dump(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32(addr);		\
 	} while (0)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
@@ -301,7 +301,7 @@ static int kgd_hqd_sdma_dump(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+4)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c

@@ -238,7 +238,7 @@ static int kgd_hqd_dump(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32(addr);		\
 	} while (0)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
@@ -324,7 +324,7 @@ static int kgd_hqd_sdma_dump(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+4+2+3+7)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

@@ -363,7 +363,7 @@ int kgd_gfx_v9_hqd_dump(struct amdgpu_device *adev,
 		(*dump)[i++][1] = RREG32(addr);		\
 	} while (0)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;
 
@@ -460,7 +460,7 @@ static int kgd_hqd_sdma_dump(struct amdgpu_device *adev,
 #undef HQD_N_REGS
 #define HQD_N_REGS (19+6+7+10)
 
-	*dump = kmalloc_array(HQD_N_REGS * 2, sizeof(uint32_t), GFP_KERNEL);
+	*dump = kmalloc_array(HQD_N_REGS, sizeof(**dump), GFP_KERNEL);
 	if (*dump == NULL)
 		return -ENOMEM;