Merge tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:
   - AMD adds some more upcoming HW platforms
   - Intel made Meteorlake stable and started adding Lunarlake
   - nouveau has a bunch of display rework in prepartion for the NVIDIA
     GSP firmware support
   - msm adds a7xx support
   - habanalabs has finished migration to accel subsystem

  Detail summary:

  kernel:
   - add initial vmemdup-user-array

  core:
   - fix platform remove() to return void
   - drm_file owner updated to reflect owner
   - move size calcs to drm buddy allocator
   - let GPUVM build as a module
   - allow variable number of run-queues in scheduler

  edid:
   - handle bad h/v sync_end in EDIDs

  panfrost:
   - add Boris as maintainer

  fbdev:
   - use fb_ops helpers more
   - only allow logo use from fbcon
   - rename fb_pgproto to pgprot_framebuffer
   - add HPD state to drm_connector_oob_hotplug_event
   - convert to fbdev i/o mem helpers

  i915:
   - Enable meteorlake by default
   - Early Xe2 LPD/Lunarlake display enablement
   - Rework subplatforms into IP version checks
   - GuC based TLB invalidation for Meteorlake
   - Display rework for future Xe driver integration
   - LNL FBC features
   - LNL display feature capability reads
   - update recommended fw versions for DG2+
   - drop fastboot module parameter
   - added deviceid for Arrowlake-S
   - drop preproduction workarounds
   - don't disable preemption for resets
   - cleanup inlines in headers
   - PXP firmware loading fix
   - Fix sg list lengths
   - DSC PPS state readout/verification
   - Add more RPL P/U PCI IDs
   - Add new DG2-G12 stepping
   - DP enhanced framing support to state checker
   - Improve shared link bandwidth management
   - stop using GEM macros in display code
   - refactor related code into display code
   - locally enable W=1 warnings
   - remove PSR watchdog timers on LNL

  amdgpu:
   - RAS/FRU EEPROM updatse
   - IP discovery updatses
   - GC 11.5 support
   - DCN 3.5 support
   - VPE 6.1 support
   - NBIO 7.11 support
   - DML2 support
   - lots of IP updates
   - use flexible arrays for bo list handling
   - W=1 fixes
   - Enable seamless boot in more cases
   - Enable context type property for HDMI
   - Rework GPUVM TLB flushing
   - VCN IB start/size alignment fixes

  amdkfd:
   - GC 10/11 fixes
   - GC 11.5 support
   - use partial migration in GPU faults

  radeon:
   - W=1 Fixes
   - fix some possible buffer overflow/NULL derefs

  nouveau:
   - update uapi for NO_PREFETCH
   - scheduler/fence fixes
   - rework suspend/resume for GSP-RM
   - rework display in preparation for GSP-RM

  habanalabs:
   - uapi: expose tsc clock
   - uapi: block access to eventfd through control device
   - uapi: force dma-buf export to PAGE_SIZE alignments
   - complete move to accel subsystem
   - move firmware interface include files
   - perform hard reset on PCIe AXI drain event
   - optimise user interrupt handling

  msm:
   - DP: use existing helpers for DPCD
   - DPU: interrupts reworked
   - gpu: a7xx (a730/a740) support
   - decouple msm_drv from kms for headless devices

  mediatek:
   - MT8188 dsi/dp/edp support
   - DDP GAMMA - 12 bit LUT support
   - connector dynamic selection capability

  rockchip:
   - rv1126 mipi-dsi/vop support
   - add planar formats

  ast:
   - rename constants

  panels:
   - Mitsubishi AA084XE01
   - JDI LPM102A188A
   - LTK050H3148W-CTA6

  ivpu:
   - power management fixes

  qaic:
   - add detach slice bo api

  komeda:
   - add NV12 writeback

  tegra:
   - support NVSYNC/NHSYNC
   - host1x suspend fixes

  ili9882t:
   - separate into own driver"

* tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm: (1803 commits)
  drm/amdgpu: Remove unused variables from amdgpu_show_fdinfo
  drm/amdgpu: Remove duplicate fdinfo fields
  drm/amd/amdgpu: avoid to disable gfxhub interrupt when driver is unloaded
  drm/amdgpu: Add EXT_COHERENT support for APU and NUMA systems
  drm/amdgpu: Retrieve CE count from ce_count_lo_chip in EccInfo table
  drm/amdgpu: Identify data parity error corrected in replay mode
  drm/amdgpu: Fix typo in IP discovery parsing
  drm/amd/display: fix S/G display enablement
  drm/amdxcp: fix amdxcp unloads incompletely
  drm/amd/amdgpu: fix the GPU power print error in pm info
  drm/amdgpu: Use pcie domain of xcc acpi objects
  drm/amd: check num of link levels when update pcie param
  drm/amdgpu: Add a read to GFX v9.4.3 ring test
  drm/amd/pm: call smu_cmn_get_smc_version in is_mode1_reset_supported.
  drm/amdgpu: get RAS poison status from DF v4_6_2
  drm/amdgpu: Use discovery table's subrevision
  drm/amd/display: 3.2.256
  drm/amd/display: add interface to query SubVP status
  drm/amd/display: Read before writing Backlight Mode Set Register
  drm/amd/display: Disable SYMCLK32_SE RCO on DCN314
  ...

1 files changed, 61 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
index 997a073e2409..28ad463cf5c9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mca.h
@@ -21,6 +21,26 @@
 #ifndef __AMDGPU_MCA_H__
 #define __AMDGPU_MCA_H__
 
+#include "amdgpu_ras.h"
+
+#define MCA_MAX_REGS_COUNT	(16)
+
+enum amdgpu_mca_ip {
+	AMDGPU_MCA_IP_UNKNOW = -1,
+	AMDGPU_MCA_IP_PSP = 0,
+	AMDGPU_MCA_IP_SDMA,
+	AMDGPU_MCA_IP_GC,
+	AMDGPU_MCA_IP_SMU,
+	AMDGPU_MCA_IP_MP5,
+	AMDGPU_MCA_IP_UMC,
+	AMDGPU_MCA_IP_COUNT,
+};
+
+enum amdgpu_mca_error_type {
+	AMDGPU_MCA_ERROR_TYPE_UE = 0,
+	AMDGPU_MCA_ERROR_TYPE_CE,
+};
+
 struct amdgpu_mca_ras_block {
 	struct amdgpu_ras_block_object ras_block;
 };
@@ -34,6 +54,36 @@ struct amdgpu_mca {
 	struct amdgpu_mca_ras mp0;
 	struct amdgpu_mca_ras mp1;
 	struct amdgpu_mca_ras mpio;
+	const struct amdgpu_mca_smu_funcs *mca_funcs;
+};
+
+struct mca_bank_info {
+	int socket_id;
+	int aid;
+	int hwid;
+	int mcatype;
+};
+
+struct mca_bank_entry {
+	int idx;
+	enum amdgpu_mca_error_type type;
+	enum amdgpu_mca_ip ip;
+	struct mca_bank_info info;
+	uint64_t regs[MCA_MAX_REGS_COUNT];
+};
+
+struct amdgpu_mca_smu_funcs {
+	int max_ue_count;
+	int max_ce_count;
+	int (*mca_set_debug_mode)(struct amdgpu_device *adev, bool enable);
+	int (*mca_get_error_count)(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+				   enum amdgpu_mca_error_type type, uint32_t *count);
+	int (*mca_get_valid_mca_count)(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
+				       uint32_t *count);
+	int (*mca_get_mca_entry)(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
+				 int idx, struct mca_bank_entry *entry);
+	int (*mca_get_ras_mca_idx_array)(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+					 enum amdgpu_mca_error_type type, int *idx_array, int *idx_array_size);
 };
 
 void amdgpu_mca_query_correctable_error_count(struct amdgpu_device *adev,
@@ -53,4 +103,15 @@ void amdgpu_mca_query_ras_error_count(struct amdgpu_device *adev,
 int amdgpu_mca_mp0_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_mca_mp1_ras_sw_init(struct amdgpu_device *adev);
 int amdgpu_mca_mpio_ras_sw_init(struct amdgpu_device *adev);
+
+void amdgpu_mca_smu_init_funcs(struct amdgpu_device *adev, const struct amdgpu_mca_smu_funcs *mca_funcs);
+int amdgpu_mca_smu_set_debug_mode(struct amdgpu_device *adev, bool enable);
+int amdgpu_mca_smu_get_valid_mca_count(struct amdgpu_device *adev, enum amdgpu_mca_error_type type, uint32_t *count);
+int amdgpu_mca_smu_get_error_count(struct amdgpu_device *adev, enum amdgpu_ras_block blk,
+				   enum amdgpu_mca_error_type type, uint32_t *count);
+int amdgpu_mca_smu_get_mca_entry(struct amdgpu_device *adev, enum amdgpu_mca_error_type type,
+				 int idx, struct mca_bank_entry *entry);
+
+void amdgpu_mca_smu_debugfs_init(struct amdgpu_device *adev, struct dentry *root);
+
 #endif