Merge tag 'drm-next-2023-03-03-1' of git://anongit.freedesktop.org/dr…

…m/drm

Pull drm fixes from Dave Airlie:
 "fbdev:
   - fix uninit var in error path

  shmem:
   - revert unGPLing an export

  i915:
   - Don't use stolen memory or BAR mappings for ring buffers with LLC
   - Add inverted backlight quirk for HP 14-r206nv
   - Fix GSI offset for MCR lookups
   - GVT fixes (memleak, debugfs attributes, kconfig, typos)

  amdgpu:
   - SMU 13 fixes
   - Enable TMZ for GC 10.3.6
   - Misc display fixes
   - Buddy allocator fixes
   - GC 11 fixes
   - S0ix fix
   - INFO IOCTL queries for GC 11
   - VCN harvest fixes for SR-IOV
   - UMC 8.10 RAS fixes
   - Don't restrict bpc to 8
   - NBIO 7.5 fix
   - Allow freesync on PCon for more devices

  amdkfd:
   - SDMA fix
   - Illegal memory access fix"

* tag 'drm-next-2023-03-03-1' of git://anongit.freedesktop.org/drm/drm: (45 commits)
  drm/amdgpu/vcn: fix compilation issue with legacy gcc
  drm/amd/display: Extend Freesync over PCon support for more devices
  Revert "drm/amd/display: Do not set DRR on pipe commit"
  drm/amd/display: fix shift-out-of-bounds in CalculateVMAndRowBytes
  drm/amd/display: Ext displays with dock can't recognized after resume
  drm/amdgpu: fix ttm_bo calltrace warning in psp_hw_fini
  drm/amdgpu: remove unused variable ring
  drm/amd/display: fix dm irq error message in gpu recover
  drm/amd: Fix initialization for nbio 7.5.1
  drm/amd/display: Don't restrict bpc to 8 bpc
  drm/amdgpu: Make umc_v8_10_convert_error_address static and remove unused variable
  drm/radeon: Fix eDP for single-display iMac11,2
  drm/shmem-helper: Revert accidental non-GPL export
  drm: omapdrm: Do not use helper unininitialized in omap_fbdev_init()
  drm/amd/pm: downgrade log level upon SMU IF version mismatch
  drm/amdgpu: Add ecc info query interface for umc v8_10
  drm/amdgpu: Add convert_error_address function for umc v8_10
  drm/amdgpu: add bad_page_threshold check in ras_eeprom_check_err
  drm/amdgpu: change default behavior of bad_page_threshold parameter
  drm/amdgpu: exclude duplicate pages from UMC RAS UE count
  ...

drivers/gpu/drm/amd/amdgpu/Kconfig

@@ -6,6 +6,7 @@ config DRM_AMDGPU
 	select FW_LOADER
 	select DRM_DISPLAY_DP_HELPER
 	select DRM_DISPLAY_HDMI_HELPER
+	select DRM_DISPLAY_HDCP_HELPER
 	select DRM_DISPLAY_HELPER
 	select DRM_KMS_HELPER
 	select DRM_SCHED

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

@@ -1073,6 +1073,9 @@ bool amdgpu_acpi_is_s0ix_active(struct amdgpu_device *adev)
 	    (pm_suspend_target_state != PM_SUSPEND_TO_IDLE))
 		return false;
 
+	if (adev->asic_type < CHIP_RAVEN)
+		return false;
+
 	/*
 	 * If ACPI_FADT_LOW_POWER_S0 is not set in the FADT, it is generally
 	 * risky to do any special firmware-related preparations for entering

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

@@ -107,9 +107,12 @@
  * - 3.50.0 - Update AMDGPU_INFO_DEV_INFO IOCTL for minimum engine and memory clock
  *            Update AMDGPU_INFO_SENSOR IOCTL for PEAK_PSTATE engine and memory clock
  *   3.51.0 - Return the PCIe gen and lanes from the INFO ioctl
+ *   3.52.0 - Add AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD, add device_info fields:
+ *            tcp_cache_size, num_sqc_per_wgp, sqc_data_cache_size, sqc_inst_cache_size,
+ *            gl1c_cache_size, gl2c_cache_size, mall_size, enabled_rb_pipes_mask_hi
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	51
+#define KMS_DRIVER_MINOR	52
 #define KMS_DRIVER_PATCHLEVEL	0
 
 unsigned int amdgpu_vram_limit = UINT_MAX;
@@ -921,7 +924,7 @@ module_param_named(reset_method, amdgpu_reset_method, int, 0444);
  * result in the GPU entering bad status when the number of total
  * faulty pages by ECC exceeds the threshold value.
  */
-MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = auto(default value), 0 = disable bad page retirement, -2 = ignore bad page threshold)");
+MODULE_PARM_DESC(bad_page_threshold, "Bad page threshold(-1 = ignore threshold (default value), 0 = disable bad page retirement, -2 = driver sets threshold)");
 module_param_named(bad_page_threshold, amdgpu_bad_page_threshold, int, 0444);
 
 MODULE_PARM_DESC(num_kcq, "number of kernel compute queue user want to setup (8 if set to greater than 8 or less than 0, only affect gfx 8+)");
@@ -2414,8 +2417,10 @@ static int amdgpu_pmops_suspend(struct device *dev)
 
 	if (amdgpu_acpi_is_s0ix_active(adev))
 		adev->in_s0ix = true;
-	else
+	else if (amdgpu_acpi_is_s3_active(adev))
 		adev->in_s3 = true;
+	if (!adev->in_s0ix && !adev->in_s3)
+		return 0;
 	return amdgpu_device_suspend(drm_dev, true);
 }
 
@@ -2436,6 +2441,9 @@ static int amdgpu_pmops_resume(struct device *dev)
 	struct amdgpu_device *adev = drm_to_adev(drm_dev);
 	int r;
 
+	if (!adev->in_s0ix && !adev->in_s3)
+		return 0;
+
 	/* Avoids registers access if device is physically gone */
 	if (!pci_device_is_present(adev->pdev))
 		adev->no_hw_access = true;

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

@@ -178,6 +178,8 @@ struct amdgpu_gfx_config {
 	uint32_t num_sc_per_sh;
 	uint32_t num_packer_per_sc;
 	uint32_t pa_sc_tile_steering_override;
+	/* Whether texture coordinate truncation is conformant. */
+	bool ta_cntl2_truncate_coord_mode;
 	uint64_t tcc_disabled_mask;
 	uint32_t gc_num_tcp_per_sa;
 	uint32_t gc_num_sdp_interface;

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

@@ -552,6 +552,7 @@ void amdgpu_gmc_tmz_set(struct amdgpu_device *adev)
 	case IP_VERSION(10, 3, 2):
 	case IP_VERSION(10, 3, 4):
 	case IP_VERSION(10, 3, 5):
+	case IP_VERSION(10, 3, 6):
 	/* VANGOGH */
 	case IP_VERSION(10, 3, 1):
 	/* YELLOW_CARP*/

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

@@ -808,6 +808,8 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION;
 		if (amdgpu_is_tmz(adev))
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_TMZ;
+		if (adev->gfx.config.ta_cntl2_truncate_coord_mode)
+			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD;
 
 		vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;
 		vm_size -= AMDGPU_VA_RESERVED_SIZE;
@@ -865,6 +867,15 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 ? 4 :
 			adev->pm.pcie_mlw_mask & CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 ? 2 : 1;
 
+		dev_info->tcp_cache_size = adev->gfx.config.gc_tcp_l1_size;
+		dev_info->num_sqc_per_wgp = adev->gfx.config.gc_num_sqc_per_wgp;
+		dev_info->sqc_data_cache_size = adev->gfx.config.gc_l1_data_cache_size_per_sqc;
+		dev_info->sqc_inst_cache_size = adev->gfx.config.gc_l1_instruction_cache_size_per_sqc;
+		dev_info->gl1c_cache_size = adev->gfx.config.gc_gl1c_size_per_instance *
+					    adev->gfx.config.gc_gl1c_per_sa;
+		dev_info->gl2c_cache_size = adev->gfx.config.gc_gl2c_per_gpu;
+		dev_info->mall_size = adev->gmc.mall_size;
+
 		ret = copy_to_user(out, dev_info,
 				   min((size_t)size, sizeof(*dev_info))) ? -EFAULT : 0;
 		kfree(dev_info);

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

@@ -139,7 +139,7 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 
 		if (flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)
 			places[c].lpfn = visible_pfn;
-		else
+		else if (adev->gmc.real_vram_size != adev->gmc.visible_vram_size)
 			places[c].flags |= TTM_PL_FLAG_TOPDOWN;
 
 		if (flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)

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

@@ -1683,7 +1683,7 @@ static int psp_hdcp_initialize(struct psp_context *psp)
 	psp->hdcp_context.context.mem_context.shared_mem_size = PSP_HDCP_SHARED_MEM_SIZE;
 	psp->hdcp_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA;
 
-	if (!psp->hdcp_context.context.initialized) {
+	if (!psp->hdcp_context.context.mem_context.shared_buf) {
 		ret = psp_ta_init_shared_buf(psp, &psp->hdcp_context.context.mem_context);
 		if (ret)
 			return ret;
@@ -1750,7 +1750,7 @@ static int psp_dtm_initialize(struct psp_context *psp)
 	psp->dtm_context.context.mem_context.shared_mem_size = PSP_DTM_SHARED_MEM_SIZE;
 	psp->dtm_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA;
 
-	if (!psp->dtm_context.context.initialized) {
+	if (!psp->dtm_context.context.mem_context.shared_buf) {
 		ret = psp_ta_init_shared_buf(psp, &psp->dtm_context.context.mem_context);
 		if (ret)
 			return ret;
@@ -1818,7 +1818,7 @@ static int psp_rap_initialize(struct psp_context *psp)
 	psp->rap_context.context.mem_context.shared_mem_size = PSP_RAP_SHARED_MEM_SIZE;
 	psp->rap_context.context.ta_load_type = GFX_CMD_ID_LOAD_TA;
 
-	if (!psp->rap_context.context.initialized) {
+	if (!psp->rap_context.context.mem_context.shared_buf) {
 		ret = psp_ta_init_shared_buf(psp, &psp->rap_context.context.mem_context);
 		if (ret)
 			return ret;

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

@@ -176,7 +176,7 @@ static int amdgpu_reserve_page_direct(struct amdgpu_device *adev, uint64_t addre
 	if (amdgpu_bad_page_threshold != 0) {
 		amdgpu_ras_add_bad_pages(adev, err_data.err_addr,
 					 err_data.err_addr_cnt);
-		amdgpu_ras_save_bad_pages(adev);
+		amdgpu_ras_save_bad_pages(adev, NULL);
 	}
 
 	dev_warn(adev->dev, "WARNING: THIS IS ONLY FOR TEST PURPOSES AND WILL CORRUPT RAS EEPROM\n");
@@ -2084,22 +2084,32 @@ int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 /*
  * write error record array to eeprom, the function should be
  * protected by recovery_lock
+ * new_cnt: new added UE count, excluding reserved bad pages, can be NULL
  */
-int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev)
+int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
+		unsigned long *new_cnt)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 	struct ras_err_handler_data *data;
 	struct amdgpu_ras_eeprom_control *control;
 	int save_count;
 
-	if (!con || !con->eh_data)
+	if (!con || !con->eh_data) {
+		if (new_cnt)
+			*new_cnt = 0;
+
 		return 0;
+	}
 
 	mutex_lock(&con->recovery_lock);
 	control = &con->eeprom_control;
 	data = con->eh_data;
 	save_count = data->count - control->ras_num_recs;
 	mutex_unlock(&con->recovery_lock);
+
+	if (new_cnt)
+		*new_cnt = save_count / adev->umc.retire_unit;
+
 	/* only new entries are saved */
 	if (save_count > 0) {
 		if (amdgpu_ras_eeprom_append(control,
@@ -2186,11 +2196,12 @@ static void amdgpu_ras_validate_threshold(struct amdgpu_device *adev,
 	/*
 	 * Justification of value bad_page_cnt_threshold in ras structure
 	 *
-	 * Generally, -1 <= amdgpu_bad_page_threshold <= max record length
-	 * in eeprom, and introduce two scenarios accordingly.
+	 * Generally, 0 <= amdgpu_bad_page_threshold <= max record length
+	 * in eeprom or amdgpu_bad_page_threshold == -2, introduce two
+	 * scenarios accordingly.
 	 *
 	 * Bad page retirement enablement:
-	 *    - If amdgpu_bad_page_threshold = -1,
+	 *    - If amdgpu_bad_page_threshold = -2,
 	 *      bad_page_cnt_threshold = typical value by formula.
 	 *
 	 *    - When the value from user is 0 < amdgpu_bad_page_threshold <

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

@@ -547,7 +547,8 @@ int amdgpu_ras_query_error_count(struct amdgpu_device *adev,
 int amdgpu_ras_add_bad_pages(struct amdgpu_device *adev,
 		struct eeprom_table_record *bps, int pages);
 
-int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev);
+int amdgpu_ras_save_bad_pages(struct amdgpu_device *adev,
+		unsigned long *new_cnt);
 
 static inline enum ta_ras_block
 amdgpu_ras_block_to_ta(enum amdgpu_ras_block block) {

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

@@ -417,7 +417,8 @@ bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev)
 {
 	struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
 
-	if (!__is_ras_eeprom_supported(adev))
+	if (!__is_ras_eeprom_supported(adev) ||
+	    !amdgpu_bad_page_threshold)
 		return false;
 
 	/* skip check eeprom table for VEGA20 Gaming */
@@ -428,10 +429,18 @@ bool amdgpu_ras_eeprom_check_err_threshold(struct amdgpu_device *adev)
 			return false;
 
 	if (con->eeprom_control.tbl_hdr.header == RAS_TABLE_HDR_BAD) {
-		dev_warn(adev->dev, "This GPU is in BAD status.");
-		dev_warn(adev->dev, "Please retire it or set a larger "
-			 "threshold value when reloading driver.\n");
-		return true;
+		if (amdgpu_bad_page_threshold == -1) {
+			dev_warn(adev->dev, "RAS records:%d exceed threshold:%d",
+				con->eeprom_control.ras_num_recs, con->bad_page_cnt_threshold);
+			dev_warn(adev->dev,
+				"But GPU can be operated due to bad_page_threshold = -1.\n");
+			return false;
+		} else {
+			dev_warn(adev->dev, "This GPU is in BAD status.");
+			dev_warn(adev->dev, "Please retire it or set a larger "
+				 "threshold value when reloading driver.\n");
+			return true;
+		}
 	}
 
 	return false;
@@ -1191,8 +1200,8 @@ int amdgpu_ras_eeprom_init(struct amdgpu_ras_eeprom_control *control,
 		} else {
 			dev_err(adev->dev, "RAS records:%d exceed threshold:%d",
 				control->ras_num_recs, ras->bad_page_cnt_threshold);
-			if (amdgpu_bad_page_threshold == -2) {
-				dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -2.");
+			if (amdgpu_bad_page_threshold == -1) {
+				dev_warn(adev->dev, "GPU will be initialized due to bad_page_threshold = -1.");
 				res = 0;
 			} else {
 				*exceed_err_limit = true;

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

@@ -68,7 +68,7 @@ int amdgpu_umc_page_retirement_mca(struct amdgpu_device *adev,
 	if (amdgpu_bad_page_threshold != 0) {
 		amdgpu_ras_add_bad_pages(adev, err_data.err_addr,
 						err_data.err_addr_cnt);
-		amdgpu_ras_save_bad_pages(adev);
+		amdgpu_ras_save_bad_pages(adev, NULL);
 	}
 
 out:
@@ -147,7 +147,7 @@ static int amdgpu_umc_do_page_retirement(struct amdgpu_device *adev,
 			err_data->err_addr_cnt) {
 			amdgpu_ras_add_bad_pages(adev, err_data->err_addr,
 						err_data->err_addr_cnt);
-			amdgpu_ras_save_bad_pages(adev);
+			amdgpu_ras_save_bad_pages(adev, &(err_data->ue_count));
 
 			amdgpu_dpm_send_hbm_bad_pages_num(adev, con->eeprom_control.ras_num_recs);
 

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

@@ -74,6 +74,8 @@ struct amdgpu_umc {
 
 	/* UMC regiser per channel offset */
 	uint32_t channel_offs;
+	/* how many pages are retired in one UE */
+	uint32_t retire_unit;
 	/* channel index table of interleaved memory */
 	const uint32_t *channel_idx_tbl;
 	struct ras_common_if *ras_if;

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

@@ -453,7 +453,8 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
 		/* Limit maximum size to 2GiB due to SG table limitations */
 		size = min(remaining_size, 2ULL << 30);
 
-		if (size >= (u64)pages_per_block << PAGE_SHIFT)
+		if ((size >= (u64)pages_per_block << PAGE_SHIFT) &&
+				!(size & (((u64)pages_per_block << PAGE_SHIFT) - 1)))
 			min_block_size = (u64)pages_per_block << PAGE_SHIFT;
 
 		cur_size = size;