Merge tag 'amd-drm-next-6.3-2023-01-20' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.3-2023-01-20:

amdgpu:
- Secure display fixes
- Fix scaling
- Misc code cleanups
- Display BW alloc logic updates
- DCN 3.2 fixes
- Fix power reporting on certain firmwares for CZN/RN
- SR-IOV fixes
- Link training cleanup and code rework
- HDCP fixes
- Reserved VMID fix
- Documentation updates
- Colorspace fixes
- RAS updates
- GC11.0 fixes
- VCN instance harvesting fixes
- DCN 3.1.4/5 workarounds for S/G displays
- Add PCIe info to the INFO IOCTL

amdkfd:
- XNACK fix

UAPI:
- Add PCIe gen/lanes info to the amdgpu INFO IOCTL
  Nesa ultimately plans to use this to make decisions about buffer placement optimizations
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20790

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230120234523.7610-1-alexander.deucher@amd.com

Author: airlied

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

@@ -1,8 +1,10 @@
-Product Name, Code Reference, DCN/DCE version, GC version, VCE/UVD/VCN version, SDMA version
-Radeon R* Graphics, CARRIZO/STONEY, DCE 11, 8, VCE 3 / UVD 6, 3
-Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN/PICASSO, DCN 1.0, 9.1.0, VCN 1.0, 4.1.0
-Ryzen 4000 series, RENOIR, DCN 2.1, 9.3, VCN 2.2, 4.1.2
-Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN2, DCN 1.0, 9.2.2, VCN 1.0.1, 4.1.1
-SteamDeck, VANGOGH, DCN 3.0.1, 10.3.1, VCN 3.1.0, 5.2.1
-Ryzen 5000 series, GREEN SARDINE, DCN 2.1, 9.3, VCN 2.2, 4.1.1
-Ryzen 6000 Zen, YELLOW CARP, 3.1.2, 10.3.3, VCN 3.1.1, 5.2.3
+Product Name, Code Reference, DCN/DCE version, GC version, VCE/UVD/VCN version, SDMA version, MP0 version
+Radeon R* Graphics, CARRIZO/STONEY, DCE 11, 8, VCE 3 / UVD 6, 3, n/a
+Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN/PICASSO, DCN 1.0, 9.1.0, VCN 1.0, 4.1.0, 10.0.0
+Ryzen 4000 series, RENOIR, DCN 2.1, 9.3, VCN 2.2, 4.1.2, 11.0.3
+Ryzen 3000 series / AMD Ryzen Embedded V1*/R1* with Radeon Vega Gfx, RAVEN2, DCN 1.0, 9.2.2, VCN 1.0.1, 4.1.1, 10.0.1
+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, YELLOW CARP / Rembrandt / Rembrandt+, 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 7x20 series, Mendocino, 3.1.6, 10.3.7, 3.1.1, 5.2.7, 13.0.8

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

@@ -22,3 +22,5 @@ AMD Radeon RX 6800(XT) /6900(XT) /W6800, SIENNA_CICHLID, DCN 3.0.0, 10.3.0, VCN
 AMD Radeon RX 6700 XT / 6800M / 6700M, NAVY_FLOUNDER, DCN 3.0.0, 10.3.2, VCN 3.0.0, 5.2.2
 AMD Radeon RX 6600(XT) /6600M /W6600 /W6600M, DIMGREY_CAVEFISH, DCN 3.0.2, 10.3.4, VCN 3.0.16, 5.2.4
 AMD Radeon RX 6500M /6300M /W6500M /W6300M, BEIGE_GOBY, DCN 3.0.3, 10.3.5, VCN 3.0.33, 5.2.5
+AMD Radeon RX 7900 XT /XTX, , DCN 3.2.0, 11.0.0, VCN 4.0.0, 6.0.0
+AMD Radeon RX 7600M (XT) /7700S /7600S, , DCN 3.2.1, 11.0.2, VCN 4.0.4, 6.0.2

Documentation/gpu/amdgpu/driver-misc.rst

@@ -37,7 +37,7 @@ Accelerated Processing Units (APU) Info
 
 .. csv-table::
    :header-rows: 1
-   :widths: 3, 2, 2, 1, 1, 1
+   :widths: 3, 2, 2, 1, 1, 1, 1
    :file: ./apu-asic-info-table.csv
 
 Discrete GPU Info

drivers/gpu/drm/amd/amdgpu/Makefile

@@ -137,6 +137,7 @@ amdgpu-y += \
 	gfx_v10_0.o \
 	imu_v11_0.o \
 	gfx_v11_0.o \
+	gfx_v11_0_3.o \
 	imu_v11_0_3.o
 
 # add async DMA block

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

@@ -2076,6 +2076,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct pci_dev *parent;
 	int i, r;
+	bool total;
 
 	amdgpu_device_enable_virtual_display(adev);
 
@@ -2159,6 +2160,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev) && adev->asic_type == CHIP_SIENNA_CICHLID)
 		adev->pm.pp_feature &= ~PP_OVERDRIVE_MASK;
 
+	total = true;
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if ((amdgpu_ip_block_mask & (1 << i)) == 0) {
 			DRM_ERROR("disabled ip block: %d <%s>\n",
@@ -2172,7 +2174,7 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 				} else if (r) {
 					DRM_ERROR("early_init of IP block <%s> failed %d\n",
 						  adev->ip_blocks[i].version->funcs->name, r);
-					return r;
+					total = false;
 				} else {
 					adev->ip_blocks[i].status.valid = true;
 				}
@@ -2203,6 +2205,8 @@ static int amdgpu_device_ip_early_init(struct amdgpu_device *adev)
 
 		}
 	}
+	if (!total)
+		return -ENODEV;
 
 	adev->cg_flags &= amdgpu_cg_mask;
 	adev->pg_flags &= amdgpu_pg_mask;
@@ -5854,8 +5858,8 @@ void amdgpu_device_invalidate_hdp(struct amdgpu_device *adev,
 int amdgpu_in_reset(struct amdgpu_device *adev)
 {
 	return atomic_read(&adev->reset_domain->in_gpu_reset);
-	}
-	
+}
+
 /**
  * amdgpu_device_halt() - bring hardware to some kind of halt state
  *

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

@@ -106,9 +106,10 @@
  * - 3.49.0 - Add gang submit into CS IOCTL
  * - 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
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	50
+#define KMS_DRIVER_MINOR	51
 #define KMS_DRIVER_PATCHLEVEL	0
 
 unsigned int amdgpu_vram_limit = UINT_MAX;

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

@@ -156,6 +156,9 @@ static bool amdgpu_gfx_is_compute_multipipe_capable(struct amdgpu_device *adev)
 		return amdgpu_compute_multipipe == 1;
 	}
 
+	if (adev->ip_versions[GC_HWIP][0] > IP_VERSION(9, 0, 0))
+		return true;
+
 	/* FIXME: spreading the queues across pipes causes perf regressions
 	 * on POLARIS11 compute workloads */
 	if (adev->asic_type == CHIP_POLARIS11)
@@ -696,6 +699,50 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r
 	return r;
 }
 
+int amdgpu_gfx_ras_sw_init(struct amdgpu_device *adev)
+{
+	int err = 0;
+	struct amdgpu_gfx_ras *ras = NULL;
+
+	/* adev->gfx.ras is NULL, which means gfx does not
+	 * support ras function, then do nothing here.
+	 */
+	if (!adev->gfx.ras)
+		return 0;
+
+	ras = adev->gfx.ras;
+
+	err = amdgpu_ras_register_ras_block(adev, &ras->ras_block);
+	if (err) {
+		dev_err(adev->dev, "Failed to register gfx ras block!\n");
+		return err;
+	}
+
+	strcpy(ras->ras_block.ras_comm.name, "gfx");
+	ras->ras_block.ras_comm.block = AMDGPU_RAS_BLOCK__GFX;
+	ras->ras_block.ras_comm.type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE;
+	adev->gfx.ras_if = &ras->ras_block.ras_comm;
+
+	/* If not define special ras_late_init function, use gfx default ras_late_init */
+	if (!ras->ras_block.ras_late_init)
+		ras->ras_block.ras_late_init = amdgpu_ras_block_late_init;
+
+	/* If not defined special ras_cb function, use default ras_cb */
+	if (!ras->ras_block.ras_cb)
+		ras->ras_block.ras_cb = amdgpu_gfx_process_ras_data_cb;
+
+	return 0;
+}
+
+int amdgpu_gfx_poison_consumption_handler(struct amdgpu_device *adev,
+						struct amdgpu_iv_entry *entry)
+{
+	if (adev->gfx.ras && adev->gfx.ras->poison_consumption_handler)
+		return adev->gfx.ras->poison_consumption_handler(adev, entry);
+
+	return 0;
+}
+
 int amdgpu_gfx_process_ras_data_cb(struct amdgpu_device *adev,
 		void *err_data,
 		struct amdgpu_iv_entry *entry)

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

@@ -210,6 +210,11 @@ struct amdgpu_gfx_ras {
 	struct amdgpu_ras_block_object  ras_block;
 	void (*enable_watchdog_timer)(struct amdgpu_device *adev);
 	bool (*query_utcl2_poison_status)(struct amdgpu_device *adev);
+	int (*rlc_gc_fed_irq)(struct amdgpu_device *adev,
+				struct amdgpu_irq_src *source,
+				struct amdgpu_iv_entry *entry);
+	int (*poison_consumption_handler)(struct amdgpu_device *adev,
+						struct amdgpu_iv_entry *entry);
 };
 
 struct amdgpu_gfx_funcs {
@@ -323,6 +328,7 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_inst_irq;
 	struct amdgpu_irq_src		cp_ecc_error_irq;
 	struct amdgpu_irq_src		sq_irq;
+	struct amdgpu_irq_src		rlc_gc_fed_irq;
 	struct sq_work			sq_work;
 
 	/* gfx status */
@@ -432,4 +438,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v);
 int amdgpu_gfx_get_num_kcq(struct amdgpu_device *adev);
 void amdgpu_gfx_cp_init_microcode(struct amdgpu_device *adev, uint32_t ucode_id);
 
+int amdgpu_gfx_ras_sw_init(struct amdgpu_device *adev);
+int amdgpu_gfx_poison_consumption_handler(struct amdgpu_device *adev,
+						struct amdgpu_iv_entry *entry);
 #endif

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

@@ -497,6 +497,7 @@ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
 	    !--id_mgr->reserved_use_count) {
 		/* give the reserved ID back to normal round robin */
 		list_add(&id_mgr->reserved->list, &id_mgr->ids_lru);
+		id_mgr->reserved = NULL;
 	}
 	vm->reserved_vmid[vmhub] = false;
 	mutex_unlock(&id_mgr->lock);

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

@@ -161,8 +161,14 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	struct dma_fence *f;
 	unsigned i;
 
-	/* use sched fence if available */
-	f = job->base.s_fence ? &job->base.s_fence->finished :  &job->hw_fence;
+	/* Check if any fences where initialized */
+	if (job->base.s_fence && job->base.s_fence->finished.ops)
+		f = &job->base.s_fence->finished;
+	else if (job->hw_fence.ops)
+		f = &job->hw_fence;
+	else
+		f = NULL;
+
 	for (i = 0; i < job->num_ibs; ++i)
 		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
 }