Merge tag 'drm-next-2023-07-07' of git://anongit.freedesktop.org/drm/drm

Pull drm fixes from Dave Airlie:
 "Lots of fixes, mostly i915 and amdgpu. It's two weeks of i915, and I
  think three weeks of amdgpu.

  fbdev:
   - Fix module infos on sparc

  panel:
   - Fix mode on Starry-ili9882t

  i915:
   - Allow DC states along with PW2 only for PWB functionality [adlp+]
   - Fix SSC selection for MPLLA [mtl]
   - Use hw.adjusted mode when calculating io/fast wake times [psr]
   - Apply min softlimit correctly [guc/slpc]
   - Assign correct hdcp content type [hdcp]
   - Add missing forward declarations/includes to display power headers
   - Fix BDW PSR AUX CH data register offsets [psr]
   - Use mock device info for creating mock device

  amdgpu:
   - Misc cleanups
   - GFX 9.4.3 fixes
   - DEBUGFS build fix
   - Fix LPDDR5 reporting
   - ASPM fixes
   - DCN 3.1.4 fixes
   - DP MST fixes
   - DCN 3.2.x fixes
   - Display PSR TCON fixes
   - SMU 13.x fixes
   - RAS fixes
   - Vega12/20 SMU fixes
   - PSP flashing cleanup
   - GFX9 MCBP fixes
   - SR-IOV fixes
   - GPUVM clear mappings fix for always valid BOs
   - Add FAMS quirk for problematic monitor
   - Fix possible UAF
   - Better handle monentary temperature fluctuations
   - SDMA 4.4.2 fixes
   - Fencing fix"

* tag 'drm-next-2023-07-07' of git://anongit.freedesktop.org/drm/drm: (83 commits)
  drm/i915: use mock device info for creating mock device
  drm/i915/psr: Fix BDW PSR AUX CH data register offsets
  drm/amdgpu: Fix potential fence use-after-free v2
  drm/amd/pm: avoid unintentional shutdown due to temperature momentary fluctuation
  drm/amd/pm: expose swctf threshold setting for legacy powerplay
  drm/amd/display: 3.2.241
  drm/amd/display: Take full update path if number of planes changed
  drm/amd/display: Create debugging mechanism for Gaming FAMS
  drm/amd/display: Add monitor specific edid quirk
  drm/amd/display: For new fast update path, loop through each surface
  drm/amd/display: Remove Phantom Pipe Check When Calculating K1 and K2
  drm/amd/display: Limit new fast update path to addr and gamma / color
  drm/amd/display: Fix the delta clamping for shaper LUT
  drm/amdgpu: Keep non-psp path for partition switch
  drm/amd/display: program DPP shaper and 3D LUT if updated
  Revert "drm/amd/display: edp do not add non-edid timings"
  drm/amdgpu: share drm device for pci amdgpu device with 1st partition device
  drm/amd/pm: Add GFX v9.4.3 unique id to sysfs
  drm/amd/pm: Enable pp_feature attribute
  drm/amdgpu/vcn: Need to unpause dpg before stop dpg
  ...

arch/sparc/video/fbdev.c

@@ -21,3 +21,6 @@ int fb_is_primary_device(struct fb_info *info)
 	return 0;
 }
 EXPORT_SYMBOL(fb_is_primary_device);
+
+MODULE_DESCRIPTION("Sparc fbdev helpers");
+MODULE_LICENSE("GPL");

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

@@ -286,6 +286,9 @@ extern int amdgpu_user_partt_mode;
 #define AMDGPU_SMARTSHIFT_MAX_BIAS (100)
 #define AMDGPU_SMARTSHIFT_MIN_BIAS (-100)
 
+/* Extra time delay(in ms) to eliminate the influence of temperature momentary fluctuation */
+#define AMDGPU_SWCTF_EXTRA_DELAY		50
+
 struct amdgpu_xcp_mgr;
 struct amdgpu_device;
 struct amdgpu_irq_src;
@@ -1277,9 +1280,10 @@ int emu_soc_asic_init(struct amdgpu_device *adev);
 
 #define amdgpu_inc_vram_lost(adev) atomic_inc(&((adev)->vram_lost_counter));
 
-#define for_each_inst(i, inst_mask)                                            \
-	for (i = ffs(inst_mask) - 1; inst_mask;                                \
-	     inst_mask &= ~(1U << i), i = ffs(inst_mask) - 1)
+#define BIT_MASK_UPPER(i) ((i) >= BITS_PER_LONG ? 0 : ~0UL << (i))
+#define for_each_inst(i, inst_mask)        \
+	for (i = ffs(inst_mask); i-- != 0; \
+	     i = ffs(inst_mask & BIT_MASK_UPPER(i + 1)))
 
 #define MIN(X, Y) ((X) < (Y) ? (X) : (Y))
 

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

@@ -1791,6 +1791,15 @@ const struct attribute_group amdgpu_vbios_version_attr_group = {
 	.attrs = amdgpu_vbios_version_attrs
 };
 
+int amdgpu_atombios_sysfs_init(struct amdgpu_device *adev)
+{
+	if (adev->mode_info.atom_context)
+		return devm_device_add_group(adev->dev,
+					     &amdgpu_vbios_version_attr_group);
+
+	return 0;
+}
+
 /**
  * amdgpu_atombios_fini - free the driver info and callbacks for atombios
  *

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

@@ -217,5 +217,6 @@ int amdgpu_atombios_get_data_table(struct amdgpu_device *adev,
 
 void amdgpu_atombios_fini(struct amdgpu_device *adev);
 int amdgpu_atombios_init(struct amdgpu_device *adev);
+int amdgpu_atombios_sysfs_init(struct amdgpu_device *adev);
 
 #endif

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

@@ -327,10 +327,13 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = igp_info->v11.umachannelnumber;
 					if (!mem_channel_number)
 						mem_channel_number = 1;
-					/* channel width is 64 */
-					if (vram_width)
-						*vram_width = mem_channel_number * 64;
 					mem_type = igp_info->v11.memorytype;
+					if (mem_type == LpDdr5MemType)
+						mem_channel_width = 32;
+					else
+						mem_channel_width = 64;
+					if (vram_width)
+						*vram_width = mem_channel_number * mem_channel_width;
 					if (vram_type)
 						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
 					break;
@@ -345,10 +348,13 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 					mem_channel_number = igp_info->v21.umachannelnumber;
 					if (!mem_channel_number)
 						mem_channel_number = 1;
-					/* channel width is 64 */
-					if (vram_width)
-						*vram_width = mem_channel_number * 64;
 					mem_type = igp_info->v21.memorytype;
+					if (mem_type == LpDdr5MemType)
+						mem_channel_width = 32;
+					else
+						mem_channel_width = 64;
+					if (vram_width)
+						*vram_width = mem_channel_number * mem_channel_width;
 					if (vram_type)
 						*vram_type = convert_atom_mem_type_to_vram_type(adev, mem_type);
 					break;

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

@@ -136,9 +136,6 @@ static int amdgpu_cs_p1_user_fence(struct amdgpu_cs_parser *p,
 	bo = amdgpu_bo_ref(gem_to_amdgpu_bo(gobj));
 	p->uf_entry.priority = 0;
 	p->uf_entry.tv.bo = &bo->tbo;
-	/* One for TTM and two for the CS job */
-	p->uf_entry.tv.num_shared = 3;
-
 	drm_gem_object_put(gobj);
 
 	size = amdgpu_bo_size(bo);
@@ -912,15 +909,19 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	mutex_lock(&p->bo_list->bo_list_mutex);
 
-	/* One for TTM and one for the CS job */
+	/* One for TTM and one for each CS job */
 	amdgpu_bo_list_for_each_entry(e, p->bo_list)
-		e->tv.num_shared = 2;
+		e->tv.num_shared = 1 + p->gang_size;
+	p->uf_entry.tv.num_shared = 1 + p->gang_size;
 
 	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 
 	INIT_LIST_HEAD(&duplicates);
 	amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);
 
+	/* Two for VM updates, one for TTM and one for each CS job */
+	p->vm_pd.tv.num_shared = 3 + p->gang_size;
+
 	if (p->uf_entry.tv.bo && !ttm_to_amdgpu_bo(p->uf_entry.tv.bo)->parent)
 		list_add(&p->uf_entry.tv.head, &p->validated);
 
@@ -1653,15 +1654,15 @@ static int amdgpu_cs_wait_all_fences(struct amdgpu_device *adev,
 			continue;
 
 		r = dma_fence_wait_timeout(fence, true, timeout);
+		if (r > 0 && fence->error)
+			r = fence->error;
+
 		dma_fence_put(fence);
 		if (r < 0)
 			return r;
 
 		if (r == 0)
 			break;
-
-		if (fence->error)
-			return fence->error;
 	}
 
 	memset(wait, 0, sizeof(*wait));

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

@@ -2552,7 +2552,7 @@ static int amdgpu_device_ip_init(struct amdgpu_device *adev)
 			adev->ip_blocks[i].status.hw = true;
 
 			/* right after GMC hw init, we create CSA */
-			if (amdgpu_mcbp) {
+			if (adev->gfx.mcbp) {
 				r = amdgpu_allocate_static_csa(adev, &adev->virt.csa_obj,
 							       AMDGPU_GEM_DOMAIN_VRAM |
 							       AMDGPU_GEM_DOMAIN_GTT,
@@ -3673,6 +3673,23 @@ static const struct attribute *amdgpu_dev_attributes[] = {
 	NULL
 };
 
+static void amdgpu_device_set_mcbp(struct amdgpu_device *adev)
+{
+	if (amdgpu_mcbp == 1)
+		adev->gfx.mcbp = true;
+
+	if ((adev->ip_versions[GC_HWIP][0] >= IP_VERSION(9, 0, 0)) &&
+	    (adev->ip_versions[GC_HWIP][0] < IP_VERSION(10, 0, 0)) &&
+	    adev->gfx.num_gfx_rings)
+		adev->gfx.mcbp = true;
+
+	if (amdgpu_sriov_vf(adev))
+		adev->gfx.mcbp = true;
+
+	if (adev->gfx.mcbp)
+		DRM_INFO("MCBP is enabled\n");
+}
+
 /**
  * amdgpu_device_init - initialize the driver
  *
@@ -3824,9 +3841,6 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	DRM_INFO("register mmio base: 0x%08X\n", (uint32_t)adev->rmmio_base);
 	DRM_INFO("register mmio size: %u\n", (unsigned)adev->rmmio_size);
 
-	if (amdgpu_mcbp)
-		DRM_INFO("MCBP is enabled\n");
-
 	/*
 	 * Reset domain needs to be present early, before XGMI hive discovered
 	 * (if any) and intitialized to use reset sem and in_gpu reset flag
@@ -3852,6 +3866,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
+	amdgpu_device_set_mcbp(adev);
+
 	/* Get rid of things like offb */
 	r = drm_aperture_remove_conflicting_pci_framebuffers(adev->pdev, &amdgpu_kms_driver);
 	if (r)
@@ -4018,6 +4034,11 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	/* Get a log2 for easy divisions. */
 	adev->mm_stats.log2_max_MBps = ilog2(max(1u, max_MBps));
 
+	r = amdgpu_atombios_sysfs_init(adev);
+	if (r)
+		drm_err(&adev->ddev,
+			"registering atombios sysfs failed (%d).\n", r);
+
 	r = amdgpu_pm_sysfs_init(adev);
 	if (r)
 		DRM_ERROR("registering pm sysfs failed (%d).\n", r);

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

@@ -180,7 +180,7 @@ uint amdgpu_dc_feature_mask = 2;
 uint amdgpu_dc_debug_mask;
 uint amdgpu_dc_visual_confirm;
 int amdgpu_async_gfx_ring = 1;
-int amdgpu_mcbp;
+int amdgpu_mcbp = -1;
 int amdgpu_discovery = -1;
 int amdgpu_mes;
 int amdgpu_mes_kiq;
@@ -634,10 +634,10 @@ module_param_named(async_gfx_ring, amdgpu_async_gfx_ring, int, 0444);
 
 /**
  * DOC: mcbp (int)
- * It is used to enable mid command buffer preemption. (0 = disabled (default), 1 = enabled)
+ * It is used to enable mid command buffer preemption. (0 = disabled, 1 = enabled, -1 auto (default))
  */
 MODULE_PARM_DESC(mcbp,
-	"Enable Mid-command buffer preemption (0 = disabled (default), 1 = enabled)");
+	"Enable Mid-command buffer preemption (0 = disabled, 1 = enabled), -1 = auto (default)");
 module_param_named(mcbp, amdgpu_mcbp, int, 0444);
 
 /**
@@ -2899,12 +2899,10 @@ static struct pci_error_handlers amdgpu_pci_err_handler = {
 
 extern const struct attribute_group amdgpu_vram_mgr_attr_group;
 extern const struct attribute_group amdgpu_gtt_mgr_attr_group;
-extern const struct attribute_group amdgpu_vbios_version_attr_group;
 
 static const struct attribute_group *amdgpu_sysfs_groups[] = {
 	&amdgpu_vram_mgr_attr_group,
 	&amdgpu_gtt_mgr_attr_group,
-	&amdgpu_vbios_version_attr_group,
 	NULL,
 };
 

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

@@ -434,6 +434,7 @@ struct amdgpu_gfx {
 	uint16_t 			xcc_mask;
 	uint32_t			num_xcc_per_xcp;
 	struct mutex			partition_mutex;
+	bool				mcbp; /* mid command buffer preemption */
 };
 
 struct amdgpu_gfx_ras_reg_entry {

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

@@ -255,7 +255,8 @@ int amdgpu_jpeg_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *
 
 	if (amdgpu_ras_is_supported(adev, ras_block->block)) {
 		for (i = 0; i < adev->jpeg.num_jpeg_inst; ++i) {
-			if (adev->jpeg.harvest_config & (1 << i))
+			if (adev->jpeg.harvest_config & (1 << i) ||
+			    !adev->jpeg.inst[i].ras_poison_irq.funcs)
 				continue;
 
 			r = amdgpu_irq_get(adev, &adev->jpeg.inst[i].ras_poison_irq, 0);

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

@@ -805,7 +805,7 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 		dev_info->ids_flags = 0;
 		if (adev->flags & AMD_IS_APU)
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_FUSION;
-		if (amdgpu_mcbp)
+		if (adev->gfx.mcbp)
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_PREEMPTION;
 		if (amdgpu_is_tmz(adev))
 			dev_info->ids_flags |= AMDGPU_IDS_FLAGS_TMZ;
@@ -1247,7 +1247,7 @@ int amdgpu_driver_open_kms(struct drm_device *dev, struct drm_file *file_priv)
 		goto error_vm;
 	}
 
-	if (amdgpu_mcbp) {
+	if (adev->gfx.mcbp) {
 		uint64_t csa_addr = amdgpu_csa_vaddr(adev) & AMDGPU_GMC_HOLE_MASK;
 
 		r = amdgpu_map_static_csa(adev, &fpriv->vm, adev->virt.csa_obj,

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

@@ -839,6 +839,7 @@ static bool psp_skip_tmr(struct psp_context *psp)
 	case IP_VERSION(11, 0, 9):
 	case IP_VERSION(11, 0, 7):
 	case IP_VERSION(13, 0, 2):
+	case IP_VERSION(13, 0, 6):
 	case IP_VERSION(13, 0, 10):
 		return true;
 	default:
@@ -2039,6 +2040,8 @@ static int psp_securedisplay_initialize(struct psp_context *psp)
 		psp_securedisplay_parse_resp_status(psp, securedisplay_cmd->status);
 		dev_err(psp->adev->dev, "SECUREDISPLAY: query securedisplay TA failed. ret 0x%x\n",
 			securedisplay_cmd->securedisplay_out_message.query_ta.query_cmd_ret);
+		/* don't try again */
+		psp->securedisplay_context.context.bin_desc.size_bytes = 0;
 	}
 
 	return 0;
@@ -3703,7 +3706,6 @@ static DEVICE_ATTR(psp_vbflash_status, 0440, amdgpu_psp_vbflash_status, NULL);
 int amdgpu_psp_sysfs_init(struct amdgpu_device *adev)
 {
 	int ret = 0;
-	struct psp_context *psp = &adev->psp;
 
 	if (amdgpu_sriov_vf(adev))
 		return -EINVAL;
@@ -3712,10 +3714,6 @@ int amdgpu_psp_sysfs_init(struct amdgpu_device *adev)
 	case IP_VERSION(13, 0, 0):
 	case IP_VERSION(13, 0, 7):
 	case IP_VERSION(13, 0, 10):
-		if (!psp->adev) {
-			psp->adev = adev;
-			psp_v13_0_set_psp_funcs(psp);
-		}
 		ret = sysfs_create_bin_file(&adev->dev->kobj, &psp_vbflash_bin_attr);
 		if (ret)
 			dev_err(adev->dev, "Failed to create device file psp_vbflash");

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

@@ -116,13 +116,11 @@ static const struct file_operations amdgpu_rap_debugfs_ops = {
 
 void amdgpu_rap_debugfs_init(struct amdgpu_device *adev)
 {
-#if defined(CONFIG_DEBUG_FS)
 	struct drm_minor *minor = adev_to_drm(adev)->primary;
 
 	if (!adev->psp.rap_context.context.initialized)
 		return;
 
 	debugfs_create_file("rap_test", S_IWUSR, minor->debugfs_root,
 				adev, &amdgpu_rap_debugfs_ops);
-#endif
 }

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

@@ -2065,6 +2065,14 @@ static void amdgpu_ras_do_recovery(struct work_struct *work)
 				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE2_RESET;
 				reset_context.method = AMD_RESET_METHOD_MODE2;
 			}
+
+			/* Fatal error occurs in poison mode, mode1 reset is used to
+			 * recover gpu.
+			 */
+			if (ras->gpu_reset_flags & AMDGPU_RAS_GPU_RESET_MODE1_RESET) {
+				ras->gpu_reset_flags &= ~AMDGPU_RAS_GPU_RESET_MODE1_RESET;
+				set_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
+			}
 		}
 
 		amdgpu_device_gpu_recover(ras->adev, NULL, &reset_context);
@@ -2955,9 +2963,12 @@ void amdgpu_ras_global_ras_isr(struct amdgpu_device *adev)
 		return;
 
 	if (atomic_cmpxchg(&amdgpu_ras_in_intr, 0, 1) == 0) {
+		struct amdgpu_ras *ras = amdgpu_ras_get_context(adev);
+
 		dev_info(adev->dev, "uncorrectable hardware error"
 			"(ERREVENT_ATHUB_INTERRUPT) detected!\n");
 
+		ras->gpu_reset_flags |= AMDGPU_RAS_GPU_RESET_MODE1_RESET;
 		amdgpu_ras_reset_gpu(adev);
 	}
 }

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

@@ -340,6 +340,7 @@ enum amdgpu_ras_ret {
 #define AMDGPU_RAS_ERR_ADDRESS_VALID	(1 << 2)
 
 #define AMDGPU_RAS_GPU_RESET_MODE2_RESET  (0x1 << 0)
+#define AMDGPU_RAS_GPU_RESET_MODE1_RESET  (0x1 << 1)
 
 struct amdgpu_ras_err_status_reg_entry {
 	uint32_t hwip;

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

@@ -423,6 +423,9 @@ void amdgpu_sw_ring_ib_mark_offset(struct amdgpu_ring *ring, enum amdgpu_ring_mu
 	struct amdgpu_ring_mux *mux = &adev->gfx.muxer;
 	unsigned offset;
 
+	if (ring->hw_prio > AMDGPU_RING_PRIO_DEFAULT)
+		return;
+
 	offset = ring->wptr & ring->buf_mask;
 
 	amdgpu_ring_mux_ib_mark_offset(mux, ring, offset, type);

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

@@ -72,7 +72,7 @@ uint64_t amdgpu_sdma_get_csa_mc_addr(struct amdgpu_ring *ring,
 	int r;
 
 	/* don't enable OS preemption on SDMA under SRIOV */
-	if (amdgpu_sriov_vf(adev) || vmid == 0 || !amdgpu_mcbp)
+	if (amdgpu_sriov_vf(adev) || vmid == 0 || !adev->gfx.mcbp)
 		return 0;
 
 	if (ring->is_mes_queue) {

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

@@ -1198,7 +1198,8 @@ int amdgpu_vcn_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r
 
 	if (amdgpu_ras_is_supported(adev, ras_block->block)) {
 		for (i = 0; i < adev->vcn.num_vcn_inst; i++) {
-			if (adev->vcn.harvest_config & (1 << i))
+			if (adev->vcn.harvest_config & (1 << i) ||
+			    !adev->vcn.inst[i].ras_poison_irq.funcs)
 				continue;
 
 			r = amdgpu_irq_get(adev, &adev->vcn.inst[i].ras_poison_irq, 0);

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

@@ -66,9 +66,6 @@ void amdgpu_virt_init_setting(struct amdgpu_device *adev)
 	adev->cg_flags = 0;
 	adev->pg_flags = 0;
 
-	/* enable mcbp for sriov */
-	amdgpu_mcbp = 1;
-
 	/* Reduce kcq number to 2 to reduce latency */
 	if (amdgpu_num_kcq == -1)
 		amdgpu_num_kcq = 2;