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, 19 insertions, 16 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
index f413898dda37..c46bc6aa4f48 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_4_2.c
@@ -132,7 +132,8 @@ static int sdma_v4_4_2_init_microcode(struct amdgpu_device *adev)
 	int ret, i;
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
-		if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 2)) {
+		if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) ==
+		    IP_VERSION(4, 4, 2)) {
 			ret = amdgpu_sdma_init_microcode(adev, 0, true);
 			break;
 		} else {
@@ -154,13 +155,13 @@ static int sdma_v4_4_2_init_microcode(struct amdgpu_device *adev)
  */
 static uint64_t sdma_v4_4_2_ring_get_rptr(struct amdgpu_ring *ring)
 {
-	u64 *rptr;
+	u64 rptr;
 
 	/* XXX check if swapping is necessary on BE */
-	rptr = ((u64 *)&ring->adev->wb.wb[ring->rptr_offs]);
+	rptr = READ_ONCE(*((u64 *)&ring->adev->wb.wb[ring->rptr_offs]));
 
-	DRM_DEBUG("rptr before shift == 0x%016llx\n", *rptr);
-	return ((*rptr) >> 2);
+	DRM_DEBUG("rptr before shift == 0x%016llx\n", rptr);
+	return rptr >> 2;
 }
 
 /**
@@ -1231,7 +1232,7 @@ static void sdma_v4_4_2_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t re
 
 static bool sdma_v4_4_2_fw_support_paging_queue(struct amdgpu_device *adev)
 {
-	switch (adev->ip_versions[SDMA0_HWIP][0]) {
+	switch (amdgpu_ip_version(adev, SDMA0_HWIP, 0)) {
 	case IP_VERSION(4, 4, 2):
 		return false;
 	default:
@@ -1245,10 +1246,8 @@ static int sdma_v4_4_2_early_init(void *handle)
 	int r;
 
 	r = sdma_v4_4_2_init_microcode(adev);
-	if (r) {
-		DRM_ERROR("Failed to load sdma firmware!\n");
+	if (r)
 		return r;
-	}
 
 	/* TODO: Page queue breaks driver reload under SRIOV */
 	if (sdma_v4_4_2_fw_support_paging_queue(adev))
@@ -1277,11 +1276,8 @@ static int sdma_v4_4_2_late_init(void *handle)
 		.cb = sdma_v4_4_2_process_ras_data_cb,
 	};
 #endif
-	if (!amdgpu_persistent_edc_harvesting_supported(adev)) {
-		if (adev->sdma.ras && adev->sdma.ras->ras_block.hw_ops &&
-		    adev->sdma.ras->ras_block.hw_ops->reset_ras_error_count)
-			adev->sdma.ras->ras_block.hw_ops->reset_ras_error_count(adev);
-	}
+	if (!amdgpu_persistent_edc_harvesting_supported(adev))
+		amdgpu_ras_reset_error_count(adev, AMDGPU_RAS_BLOCK__SDMA);
 
 	return 0;
 }
@@ -1401,7 +1397,7 @@ static int sdma_v4_4_2_sw_fini(void *handle)
 			amdgpu_ring_fini(&adev->sdma.instance[i].page);
 	}
 
-	if (adev->ip_versions[SDMA0_HWIP][0] == IP_VERSION(4, 4, 2))
+	if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(4, 4, 2))
 		amdgpu_sdma_destroy_inst_ctx(adev, true);
 	else
 		amdgpu_sdma_destroy_inst_ctx(adev, false);
@@ -2131,6 +2127,11 @@ static void sdma_v4_4_2_inst_query_ras_error_count(struct amdgpu_device *adev,
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_err_status;
 	uint32_t sdma_dev_inst = GET_INST(SDMA0, sdma_inst);
+	unsigned long ue_count = 0;
+	struct amdgpu_smuio_mcm_config_info mcm_info = {
+		.socket_id = adev->smuio.funcs->get_socket_id(adev),
+		.die_id = adev->sdma.instance[sdma_inst].aid_id,
+	};
 
 	/* sdma v4_4_2 doesn't support query ce counts */
 	amdgpu_ras_inst_query_ras_error_count(adev,
@@ -2140,7 +2141,9 @@ static void sdma_v4_4_2_inst_query_ras_error_count(struct amdgpu_device *adev,
 					ARRAY_SIZE(sdma_v4_4_2_ras_memory_list),
 					sdma_dev_inst,
 					AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
-					&err_data->ue_count);
+					&ue_count);
+
+	amdgpu_ras_error_statistic_ue_count(err_data, &mcm_info, ue_count);
 }
 
 static void sdma_v4_4_2_query_ras_error_count(struct amdgpu_device *adev,