Merge tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "This is the main pull request for the drm subsystems for 6.10.

  In drivers the main thing is a new driver for ARM Mali firmware based
  GPUs, otherwise there are a lot of changes to amdgpu/xe/i915/msm and
  scattered changes to everything else.

  In the core a bunch of headers and Kconfig was refactored, along with
  the addition of a new panic handler which is meant to provide a user
  friendly message when a panic happens and graphical display is
  enabled.

  New drivers:
   - panthor: ARM Mali/Immortalis CSF-based GPU driver

  Core:
   - add a CONFIG_DRM_WERROR option
   - make more headers self-contained
   - grab resv lock in pin/unpin
   - fix vmap resv locking
   - EDID/eDP panel matching
   - Kconfig cleanups
   - DT sound bindings
   - Add SIZE_HINTS property for cursor planes
   - Add struct drm_edid_product_id and helpers.
   - Use drm device based logging in more drm functions.
   - drop seq_file.h from a bunch of places
   - use drm_edid driver conversions

  dp:
   - DP Tunnel documentation
   - MST read sideband cap
   - Adaptive sync SDP prep work

  ttm:
   - improve placement for TTM BOs in idle/busy handling

  panic:
   - Fixes for drm-panic, and option to test it.
   - Add drm panic to simpledrm, mgag200, imx, ast

  bridge:
   - improve init ordering
   - adv7511: allow GPIO pin sharing
   - tc358775: add tc358675 support

  panel:
   - AUO B120XAN01.0
   - Samsung s6e3fa7
   - BOE NT116WHM-N44
   - CMN N116BCA-EA1,
   - CrystalClear CMT430B19N00
   - Startek KD050HDFIA020-C020A
   - powertip PH128800T006-ZHC01
   - Innolux G121X1-L03
   - LG sw43408
   - Khadas TS050 V2
   - EDO RM69380 OLED
   - CSOT MNB601LS1-1

  amdgpu:
   - HDCP/ODM/RAS fixes
   - Devcoredump improvements
   - Expose VCN activity via sysfs
   - SMY 13.0.x updates
   - Enable fast updates on DCN 3.1.4
   - Add dclk and vclk reporting on additional devices
   - Add ACA RAS infrastructure
   - Implement TLB flush fence
   - EEPROM handling fixes
   - SMUIO 14.0.2 support
   - SMU 14.0.1 Updates
   - SMU 14.0.2 support
   - Sync page table freeing with TLB flushes
   - DML2 refactor
   - DC debug improvements
   - DCN 3.5.x Updates
   - GPU reset fixes
   - HDP fix for second GFX pipe on GC 10.x
   - Enable secondary GFX pipe on GC 10.3
   - Refactor and clean up BACO/BOCO/BAMACO handling
   - Remove invalid TTM resource start check
   - UAF fix in VA IOCTL
   - GPUVM page fault redirection to secondary IH rings for IH 6.x
   - Initial support for mapping kernel queues via MES
   - Fix VRAM memory accounting

  amdkfd:
   - MQD handling cleanup
   - Preemption handling fixes for XCDs
   - TLB flush fix for GC 9.4.2
   - Properly clean up workqueue during module unload
   - Fix memory leak process create failure
   - Range check CP bad op exception targets to avoid reporting invalid exceptions to userspace
   - Fix eviction fence handling
   - Fix leak in GPU memory allocation failure case
   - DMABuf import handling fix
   - Enable SQ watchpoint for gfx10

  i915:
   - Adding new DG2 PCI ID
   - add context hints for GT frequency
   - enable only one CCS for compute workloads
   - new workarounds
   - Fix UAF on destroy against retire race and remove two earlier partial fixes
   - Limit the reserved VM space to only the platforms that need it
   - Fix gt reset with GuC submission is disable
   - Add and use gt_to_guc() wrapper

  i915/xe display:
   - Lunar Lake display enabling, including cdclk and other refactors
   - BIOS/VBT/opregion related refactor
   - Digital port related refactor/clean-up
   - Fix 2s boot time regression on DP panel replay init
   - Remove duplication on audio enable/disable on SDVO and g4x+ DP
   - Disable AuxCCS framebuffers if built for Xe
   - Make crtc disable more atomic
   - Increase DP idle pattern wait timeout to 2ms
   - Start using container_of_const() for some extra const safety
   - Fix Jasper Lake boot freeze
   - Enable MST mode for 128b/132b single-stream sideband
   - Enable Adaptive Sync SDP Support for DP
   - Fix MTL supported DP rates - removal of UHBR13.5
   - PLL refactoring
   - Limit eDP MSO pipe only for display version 20
   - More display refactor towards independence from i915 dev_priv
   - Convert i915/xe fbdev to DRM client
   - More initial work to make display code more independent from i915

  xe:
   - improved error capture
   - clean up some uAPI leftovers
   - devcoredump update
   - Add BMG mocs table
   - Handle GSCCS ER interrupt
   - Implement xe2- and GuC workarounds
   - struct xe_device cleanup
   - Hwmon updates
   - Add LRC parsing for more GPU instruction
   - Increase VM_BIND number of per-ioctl Ops
   - drm/xe: Add XE_BO_GGTT_INVALIDATE flag
   - Initial development for SR-IOV support
   - Add new PCI IDs to DG2 platform
   - Move userptr over to start using hmm_range_fault

  msm:
   - Switched to generating register header files during build process
     instead of shipping pre-generated headers
   - Merged DPU and MDP4 format databases.
   - DP:
     - Stop using compat string to distinguish DP and eDP cases
     - Added support for X Elite platform (X1E80100)
     - Reworked DP aux/audio support
     - Added SM6350 DP to the bindings
   - GPU:
     - a7xx perfcntr reg fixes
     - MAINTAINERS updates
     - a750 devcoredump support

  radeon:
   - Silence UBSAN warnings related to flexible arrays

  nouveau:
   - move some uAPI objects to uapi headers

  omapdrm:
   - console fix

  ast:
   - add i2c polling

  qaic:
   - add debugfs entries

  exynos:
   - fix platform_driver .owner
   - drop cleanup code

  mediatek:
   - Use devm_platform_get_and_ioremap_resource() in mtk_hdmi_ddc_probe()
   - Add GAMMA 12-bit LUT support for MT8188
   - Rename mtk_drm_* to mtk_*
   - Drop driver owner initialization
   - Correct calculation formula of PHY Timing"

* tag 'drm-next-2024-05-15' of https://gitlab.freedesktop.org/drm/kernel: (1477 commits)
  drm/xe/ads: Use flexible-array
  drm/xe: Use ordered WQ for G2H handler
  drm/msm/gen_header: allow skipping the validation
  drm/msm/a6xx: Cleanup indexed regs const'ness
  drm/msm: Add devcoredump support for a750
  drm/msm: Adjust a7xx GBIF debugbus dumping
  drm/msm: Update a6xx registers XML
  drm/msm: Fix imported a750 snapshot header for upstream
  drm/msm: Import a750 snapshot registers from kgsl
  MAINTAINERS: Add Konrad Dybcio as a reviewer for the Adreno driver
  MAINTAINERS: Add a separate entry for Qualcomm Adreno GPU drivers
  drm/msm/a6xx: Avoid a nullptr dereference when speedbin setting fails
  drm/msm/adreno: fix CP cycles stat retrieval on a7xx
  drm/msm/a7xx: allow writing to CP_BV counter selection registers
  drm: zynqmp_dpsub: Always register bridge
  Revert "drm/bridge: ti-sn65dsi83: Fix enable error path"
  drm/fb_dma: Add checks in drm_fb_dma_get_scanout_buffer()
  drm/fbdev-generic: Do not set physical framebuffer address
  drm/panthor: Fix the FW reset logic
  drm/panthor: Make sure we handle 'unknown group state' case properly
  ...

1 files changed, 114 insertions, 19 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
index 20436f81856a..540e0f066b26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_umc.c
@@ -21,10 +21,13 @@
  *
  */
 
+#include <linux/sort.h>
 #include "amdgpu.h"
 #include "umc_v6_7.h"
 #define MAX_UMC_POISON_POLLING_TIME_SYNC   20  //ms
 
+#define MAX_UMC_HASH_STRING_SIZE  256
+
 static int amdgpu_umc_convert_error_address(struct amdgpu_device *adev,
 				    struct ras_err_data *err_data, uint64_t err_addr,
 				    uint32_t ch_inst, uint32_t umc_inst)
@@ -63,6 +66,8 @@ int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev,
 		goto out_fini_err_data;
 	}
 
+	err_data.err_addr_len = adev->umc.max_ras_err_cnt_per_query;
+
 	/*
 	 * Translate UMC channel address to Physical address
 	 */
@@ -86,7 +91,7 @@ out_fini_err_data:
 	return ret;
 }
 
-static void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
+void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
 			void *ras_error_status)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
@@ -118,6 +123,8 @@ static void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
 			if(!err_data->err_addr)
 				dev_warn(adev->dev, "Failed to alloc memory for "
 						"umc error address record!\n");
+			else
+				err_data->err_addr_len = adev->umc.max_ras_err_cnt_per_query;
 
 			/* umc query_ras_error_address is also responsible for clearing
 			 * error status
@@ -143,6 +150,8 @@ static void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
 			if(!err_data->err_addr)
 				dev_warn(adev->dev, "Failed to alloc memory for "
 						"umc error address record!\n");
+			else
+				err_data->err_addr_len = adev->umc.max_ras_err_cnt_per_query;
 
 			/* umc query_ras_error_address is also responsible for clearing
 			 * error status
@@ -170,6 +179,7 @@ static void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
 	}
 
 	kfree(err_data->err_addr);
+	err_data->err_addr = NULL;
 
 	mutex_unlock(&con->page_retirement_lock);
 }
@@ -177,7 +187,7 @@ static void amdgpu_umc_handle_bad_pages(struct amdgpu_device *adev,
 static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 		void *ras_error_status,
 		struct amdgpu_iv_entry *entry,
-		bool reset)
+		uint32_t reset)
 {
 	struct ras_err_data *err_data = (struct ras_err_data *)ras_error_status;
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
@@ -186,9 +196,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 	amdgpu_umc_handle_bad_pages(adev, ras_error_status);
 
 	if (err_data->ue_count && reset) {
-		/* use mode-2 reset for poison consumption */
-		if (!entry)
-			con->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE2_RESET;
+		con->gpu_reset_flags |= reset;
 		amdgpu_ras_reset_gpu(adev);
 	}
 
@@ -196,7 +204,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 }
 
 int amdgpu_umc_bad_page_polling_timeout(struct amdgpu_device *adev,
-			bool reset, uint32_t timeout_ms)
+			uint32_t reset, uint32_t timeout_ms)
 {
 	struct ras_err_data err_data;
 	struct ras_common_if head = {
@@ -238,16 +246,16 @@ int amdgpu_umc_bad_page_polling_timeout(struct amdgpu_device *adev,
 	if (reset) {
 		struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
-		/* use mode-2 reset for poison consumption */
-		con->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE2_RESET;
+		con->gpu_reset_flags |= reset;
 		amdgpu_ras_reset_gpu(adev);
 	}
 
 	return 0;
 }
 
-int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
-			enum amdgpu_ras_block block, bool reset)
+int amdgpu_umc_pasid_poison_handler(struct amdgpu_device *adev,
+			enum amdgpu_ras_block block, uint16_t pasid,
+			pasid_notify pasid_fn, void *data, uint32_t reset)
 {
 	int ret = AMDGPU_RAS_SUCCESS;
 
@@ -285,16 +293,14 @@ int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
 
 			amdgpu_ras_error_data_fini(&err_data);
 		} else {
-			if (reset) {
-				amdgpu_umc_bad_page_polling_timeout(adev,
-							reset, MAX_UMC_POISON_POLLING_TIME_SYNC);
-			} else {
 				struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
+				amdgpu_ras_put_poison_req(adev,
+					block, pasid, pasid_fn, data, reset);
+
 				atomic_inc(&con->page_retirement_req_cnt);
 
 				wake_up(&con->page_retirement_wq);
-			}
 		}
 	} else {
 		if (adev->virt.ops && adev->virt.ops->ras_poison_handler)
@@ -307,11 +313,19 @@ int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
 	return ret;
 }
 
+int amdgpu_umc_poison_handler(struct amdgpu_device *adev,
+			enum amdgpu_ras_block block, uint32_t reset)
+{
+	return amdgpu_umc_pasid_poison_handler(adev,
+				block, 0, NULL, NULL, reset);
+}
+
 int amdgpu_umc_process_ras_data_cb(struct amdgpu_device *adev,
 		void *ras_error_status,
 		struct amdgpu_iv_entry *entry)
 {
-	return amdgpu_umc_do_page_retirement(adev, ras_error_status, entry, true);
+	return amdgpu_umc_do_page_retirement(adev, ras_error_status, entry,
+				AMDGPU_RAS_GPU_RESET_MODE1_RESET);
 }
 
 int amdgpu_umc_ras_sw_init(struct amdgpu_device *adev)
@@ -388,14 +402,20 @@ int amdgpu_umc_process_ecc_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
-void amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
+int amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
 		uint64_t err_addr,
 		uint64_t retired_page,
 		uint32_t channel_index,
 		uint32_t umc_inst)
 {
-	struct eeprom_table_record *err_rec =
-		&err_data->err_addr[err_data->err_addr_cnt];
+	struct eeprom_table_record *err_rec;
+
+	if (!err_data ||
+	    !err_data->err_addr ||
+	    (err_data->err_addr_cnt >= err_data->err_addr_len))
+		return -EINVAL;
+
+	err_rec = &err_data->err_addr[err_data->err_addr_cnt];
 
 	err_rec->address = err_addr;
 	/* page frame address is saved */
@@ -407,6 +427,8 @@ void amdgpu_umc_fill_error_record(struct ras_err_data *err_data,
 	err_rec->mcumc_id = umc_inst;
 
 	err_data->err_addr_cnt++;
+
+	return 0;
 }
 
 int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
@@ -439,3 +461,76 @@ int amdgpu_umc_loop_channels(struct amdgpu_device *adev,
 
 	return 0;
 }
+
+int amdgpu_umc_update_ecc_status(struct amdgpu_device *adev,
+				uint64_t status, uint64_t ipid, uint64_t addr)
+{
+	if (adev->umc.ras->update_ecc_status)
+		return adev->umc.ras->update_ecc_status(adev,
+					status, ipid, addr);
+	return 0;
+}
+
+static int amdgpu_umc_uint64_cmp(const void *a, const void *b)
+{
+	uint64_t *addr_a = (uint64_t *)a;
+	uint64_t *addr_b = (uint64_t *)b;
+
+	if (*addr_a > *addr_b)
+		return 1;
+	else if (*addr_a < *addr_b)
+		return -1;
+	else
+		return 0;
+}
+
+/* Use string hash to avoid logging the same bad pages repeatedly */
+int amdgpu_umc_build_pages_hash(struct amdgpu_device *adev,
+		uint64_t *pfns, int len, uint64_t *val)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	char buf[MAX_UMC_HASH_STRING_SIZE] = {0};
+	int offset = 0, i = 0;
+	uint64_t hash_val;
+
+	if (!pfns || !len)
+		return -EINVAL;
+
+	sort(pfns, len, sizeof(uint64_t), amdgpu_umc_uint64_cmp, NULL);
+
+	for (i = 0; i < len; i++)
+		offset += snprintf(&buf[offset], sizeof(buf) - offset, "%llx", pfns[i]);
+
+	hash_val = siphash(buf, offset, &con->umc_ecc_log.ecc_key);
+
+	*val = hash_val;
+
+	return 0;
+}
+
+int amdgpu_umc_logs_ecc_err(struct amdgpu_device *adev,
+		struct radix_tree_root *ecc_tree, struct ras_ecc_err *ecc_err)
+{
+	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
+	struct ras_ecc_log_info *ecc_log;
+	int ret;
+
+	ecc_log = &con->umc_ecc_log;
+
+	mutex_lock(&ecc_log->lock);
+	ret = radix_tree_insert(ecc_tree, ecc_err->hash_index, ecc_err);
+	if (!ret) {
+		struct ras_err_pages *err_pages = &ecc_err->err_pages;
+		int i;
+
+		/* Reserve memory */
+		for (i = 0; i < err_pages->count; i++)
+			amdgpu_ras_reserve_page(adev, err_pages->pfn[i]);
+
+		radix_tree_tag_set(ecc_tree,
+			ecc_err->hash_index, UMC_ECC_NEW_DETECTED_TAG);
+	}
+	mutex_unlock(&ecc_log->lock);
+
+	return ret;
+}