Merge tag 'amd-drm-next-6.11-2024-06-28' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.11-2024-06-28:

amdgpu:
- JPEG 5.x fixes
- More FW loading cleanups
- Misc code cleanups
- GC 12.x fixes
- ASPM fix
- DCN 4.0.1 updates
- SR-IOV fixes
- HDCP fix
- USB4 fixes
- Silence UBSAN warnings
- MES submission fixes
- Update documentation for new products
- DCC updates
- Initial ISP 4.x plumbing
- RAS fixes
- Misc small fixes

amdkfd:
- Fix missing unlock in error path for adding queues

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20240628213135.427214-1-alexander.deucher@amd.com

Author: danvet

Documentation/gpu/amdgpu/apu-asic-info-table.csv

@@ -7,7 +7,9 @@ SteamDeck, VANGOGH, DCN 3.0.1, 10.3.1, VCN 3.1.0, 5.2.1, 11.5.0
 Ryzen 5000 series / Ryzen 7x30 series, GREEN SARDINE / Cezanne / Barcelo / Barcelo-R, DCN 2.1, 9.3, VCN 2.2, 4.1.1, 12.0.1
 Ryzen 6000 series / Ryzen 7x35 series / Ryzen 7x36 series, YELLOW CARP / Rembrandt / Rembrandt-R, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3, 13.0.3
 Ryzen 7000 series (AM5), Raphael, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
+Ryzen 9000 series (AM5), Granite Ridge, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
 Ryzen 7x45 series (FL1), Dragon Range, 3.1.5, 10.3.6, 3.1.2, 5.2.6, 13.0.5
 Ryzen 7x20 series, Mendocino, 3.1.6, 10.3.7, 3.1.1, 5.2.7, 13.0.8
 Ryzen 7x40 series, Phoenix, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11
 Ryzen 8x40 series, Hawk Point, 3.1.4, 11.0.1 / 11.0.4, 4.0.2, 6.0.1, 13.0.4 / 13.0.11
+Ryzen AI 300 series, Strix Point, 3.5.0, 11.5.0, 4.0.5, 6.1.0, 14.0.0

drivers/gpu/drm/amd/amdgpu/Kconfig

@@ -71,6 +71,17 @@ config DRM_AMDGPU_USERPTR
 	  This option selects CONFIG_HMM and CONFIG_HMM_MIRROR if it
 	  isn't already selected to enabled full userptr support.
 
+config DRM_AMD_ISP
+	bool "Enable AMD Image Signal Processor IP support"
+	depends on DRM_AMDGPU
+	select MFD_CORE
+	select PM_GENERIC_DOMAINS if PM
+	help
+	Choose this option to enable ISP IP support for AMD SOCs.
+	This adds the ISP (Image Signal Processor) IP driver and wires
+	it up into the amdgpu driver.  It is required for cameras
+	on APUs which utilize mipi cameras.
+
 config DRM_AMDGPU_WERROR
 	bool "Force the compiler to throw an error instead of a warning when compiling"
 	depends on DRM_AMDGPU

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -323,4 +323,12 @@ amdgpu-y += $(AMD_DISPLAY_FILES)
 
 endif
 
+# add isp block
+ifneq ($(CONFIG_DRM_AMD_ISP),)
+amdgpu-y += \
+	amdgpu_isp.o \
+	isp_v4_1_0.o \
+	isp_v4_1_1.o
+endif
+
 obj-$(CONFIG_DRM_AMDGPU)+= amdgpu.o

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

@@ -112,6 +112,9 @@
 #include "amdgpu_xcp.h"
 #include "amdgpu_seq64.h"
 #include "amdgpu_reg_state.h"
+#if defined(CONFIG_DRM_AMD_ISP)
+#include "amdgpu_isp.h"
+#endif
 
 #define MAX_GPU_INSTANCE		64
 
@@ -221,7 +224,6 @@ extern int amdgpu_mes;
 extern int amdgpu_mes_log_enable;
 extern int amdgpu_mes_kiq;
 extern int amdgpu_uni_mes;
-extern int amdgpu_jpeg_test;
 extern int amdgpu_noretry;
 extern int amdgpu_force_asic_type;
 extern int amdgpu_smartshift_bias;
@@ -721,6 +723,7 @@ enum amd_hw_ip_block_type {
 	XGMI_HWIP,
 	DCI_HWIP,
 	PCIE_HWIP,
+	ISP_HWIP,
 	MAX_HWIP
 };
 
@@ -1018,7 +1021,6 @@ struct amdgpu_device {
 
 	/* jpeg */
 	struct amdgpu_jpeg		jpeg;
-	bool enable_jpeg_test;
 
 	/* vpe */
 	struct amdgpu_vpe		vpe;
@@ -1048,6 +1050,11 @@ struct amdgpu_device {
 	/* display related functionality */
 	struct amdgpu_display_manager dm;
 
+#if defined(CONFIG_DRM_AMD_ISP)
+	/* isp */
+	struct amdgpu_isp		isp;
+#endif
+
 	/* mes */
 	bool                            enable_mes;
 	bool                            enable_mes_kiq;

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

@@ -433,7 +433,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev,
 						mem_channel_number = vram_info->v30.channel_num;
 						mem_channel_width = vram_info->v30.channel_width;
 						if (vram_width)
-							*vram_width = mem_channel_number * (1 << mem_channel_width);
+							*vram_width = mem_channel_number * 16;
 						break;
 					default:
 						return -EINVAL;

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

@@ -5069,7 +5069,8 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 	struct amdgpu_hive_info *hive = NULL;
 
 	if (test_bit(AMDGPU_HOST_FLR, &reset_context->flags)) {
-		amdgpu_virt_ready_to_reset(adev);
+		if (!amdgpu_ras_get_fed_status(adev))
+			amdgpu_virt_ready_to_reset(adev);
 		amdgpu_virt_wait_reset(adev);
 		clear_bit(AMDGPU_HOST_FLR, &reset_context->flags);
 		r = amdgpu_virt_request_full_gpu(adev, true);
@@ -5837,6 +5838,12 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	/* Actual ASIC resets if needed.*/
 	/* Host driver will handle XGMI hive reset for SRIOV */
 	if (amdgpu_sriov_vf(adev)) {
+		if (amdgpu_ras_get_fed_status(adev) || amdgpu_virt_rcvd_ras_interrupt(adev)) {
+			dev_dbg(adev->dev, "Detected RAS error, wait for FLR completion\n");
+			amdgpu_ras_set_fed(adev, true);
+			set_bit(AMDGPU_HOST_FLR, &reset_context->flags);
+		}
+
 		r = amdgpu_device_reset_sriov(adev, reset_context);
 		if (AMDGPU_RETRY_SRIOV_RESET(r) && (retry_limit--) > 0) {
 			amdgpu_virt_release_full_gpu(adev, true);

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

@@ -106,6 +106,9 @@
 #include "jpeg_v5_0_0.h"
 
 #include "amdgpu_vpe.h"
+#if defined(CONFIG_DRM_AMD_ISP)
+#include "amdgpu_isp.h"
+#endif
 
 #define FIRMWARE_IP_DISCOVERY "amdgpu/ip_discovery.bin"
 MODULE_FIRMWARE(FIRMWARE_IP_DISCOVERY);
@@ -225,6 +228,7 @@ static int hw_id_map[MAX_HWIP] = {
 	[DCI_HWIP]	= DCI_HWID,
 	[PCIE_HWIP]	= PCIE_HWID,
 	[VPE_HWIP]	= VPE_HWID,
+	[ISP_HWIP]	= ISP_HWID,
 };
 
 static int amdgpu_discovery_read_binary_from_sysmem(struct amdgpu_device *adev, uint8_t *binary)
@@ -711,6 +715,12 @@ static void amdgpu_discovery_read_from_harvest_table(struct amdgpu_device *adev,
 			adev->sdma.sdma_mask &=
 				~(1U << harvest_info->list[i].number_instance);
 			break;
+#if defined(CONFIG_DRM_AMD_ISP)
+		case ISP_HWID:
+			adev->isp.harvest_config |=
+				~(1U << harvest_info->list[i].number_instance);
+			break;
+#endif
 		default:
 			break;
 		}
@@ -2294,8 +2304,6 @@ static int amdgpu_discovery_set_mm_ip_blocks(struct amdgpu_device *adev)
 		case IP_VERSION(5, 0, 0):
 			amdgpu_device_ip_block_add(adev, &vcn_v5_0_0_ip_block);
 			amdgpu_device_ip_block_add(adev, &jpeg_v5_0_0_ip_block);
-			if (amdgpu_jpeg_test)
-				adev->enable_jpeg_test = true;
 			break;
 		default:
 			dev_err(adev->dev,
@@ -2378,6 +2386,24 @@ static int amdgpu_discovery_set_umsch_mm_ip_blocks(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int amdgpu_discovery_set_isp_ip_blocks(struct amdgpu_device *adev)
+{
+#if defined(CONFIG_DRM_AMD_ISP)
+	switch (amdgpu_ip_version(adev, ISP_HWIP, 0)) {
+	case IP_VERSION(4, 1, 0):
+		amdgpu_device_ip_block_add(adev, &isp_v4_1_0_ip_block);
+		break;
+	case IP_VERSION(4, 1, 1):
+		amdgpu_device_ip_block_add(adev, &isp_v4_1_1_ip_block);
+		break;
+	default:
+		break;
+	}
+#endif
+
+	return 0;
+}
+
 int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 {
 	int r;
@@ -2904,6 +2930,9 @@ int amdgpu_discovery_set_ip_blocks(struct amdgpu_device *adev)
 	if (r)
 		return r;
 
+	r = amdgpu_discovery_set_isp_ip_blocks(adev);
+	if (r)
+		return r;
 	return 0;
 }
 

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

@@ -204,7 +204,6 @@ int amdgpu_force_asic_type = -1;
 int amdgpu_tmz = -1; /* auto */
 uint amdgpu_freesync_vid_mode;
 int amdgpu_reset_method = -1; /* auto */
-int amdgpu_jpeg_test;
 int amdgpu_num_kcq = -1;
 int amdgpu_smartshift_bias;
 int amdgpu_use_xgmi_p2p = 1;
@@ -940,9 +939,6 @@ module_param_named(freesync_video, amdgpu_freesync_vid_mode, uint, 0444);
 MODULE_PARM_DESC(reset_method, "GPU reset method (-1 = auto (default), 0 = legacy, 1 = mode0, 2 = mode1, 3 = mode2, 4 = baco/bamaco)");
 module_param_named(reset_method, amdgpu_reset_method, int, 0644);
 
-MODULE_PARM_DESC(jpeg_test, "jpeg test(0 = disable (default), 1 = enable)");
-module_param_named(jpeg_test, amdgpu_jpeg_test, int, 0444);
-
 /**
  * DOC: bad_page_threshold (int) Bad page threshold is specifies the
  * threshold value of faulty pages detected by RAS ECC, which may

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

@@ -343,11 +343,6 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 	if (args->in.domains & ~AMDGPU_GEM_DOMAIN_MASK)
 		return -EINVAL;
 
-	if ((flags & AMDGPU_GEM_CREATE_GFX12_DCC) &&
-	    ((amdgpu_ip_version(adev, GC_HWIP, 0) < IP_VERSION(12, 0, 0)) ||
-	     !(args->in.domains & AMDGPU_GEM_DOMAIN_VRAM)))
-		return -EINVAL;
-
 	if (!amdgpu_is_tmz(adev) && (flags & AMDGPU_GEM_CREATE_ENCRYPTED)) {
 		DRM_NOTE_ONCE("Cannot allocate secure buffer since TMZ is disabled\n");
 		return -EINVAL;

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

@@ -718,7 +718,11 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
 			ndw += kiq->pmf->invalidate_tlbs_size;
 
 		spin_lock(&adev->gfx.kiq[inst].ring_lock);
-		amdgpu_ring_alloc(ring, ndw);
+		r = amdgpu_ring_alloc(ring, ndw);
+		if (r) {
+			spin_unlock(&adev->gfx.kiq[inst].ring_lock);
+			goto error_unlock_reset;
+		}
 		if (adev->gmc.flush_tlb_needs_extra_type_2)
 			kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub);