Merge tag 'amd-drm-next-6.2-2022-11-18' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.2-2022-11-18:

amdgpu:
- SR-IOV fixes
- Clean up DC checks
- DCN 3.2.x fixes
- DCN 3.1.x fixes
- Don't enable degamma on asics which don't support it
- IP discovery fixes
- BACO fixes
- Fix vbios allocation handling when vkms is enabled
- Drop buggy tdr advanced mode GPU reset handling
- Fix the build when DCN is not set in kconfig
- MST DSC fixes
- Userptr fixes
- FRU and RAS EEPROM fixes
- VCN 4.x RAS support
- Aldrebaran CU occupancy reporting fix
- PSP ring cleanup

amdkfd:
- Memory limit fix
- Enable cooperative launch on gfx 10.3

amd-drm-next-6.2-2022-11-11:

amdgpu:
- SMU 13.x updates
- GPUVM TLB race fix
- DCN 3.1.4 updates
- DCN 3.2.x updates
- PSR fixes
- Kerneldoc fix
- Vega10 fan fix
- GPUVM locking fixes in error pathes
- BACO fix for Beige Goby
- EEPROM I2C address cleanup
- GFXOFF fix
- Fix DC memory leak in error pathes
- Flexible array updates
- Mtype fix for GPUVM PTEs
- Move Kconfig into amdgpu directory
- SR-IOV updates
- Fix possible memory leak in CS IOCTL error path

amdkfd:
- Fix possible memory overrun
- CRIU fixes

radeon:
- ACPI ref count fix
- HDA audio notifier support
- Move Kconfig into radeon directory

UAPI:
- Add new GEM_CREATE flags to help to transition more KFD functionality to the DRM UAPI.
  These are used internally in the driver to align location based memory coherency
  requirements from memory allocated in the KFD with how we manage GPUVM PTEs.  They
  are currently blocked in the GEM_CREATE IOCTL as we don't have a user right now.
  They are just used internally in the kernel driver for now for existing KFD memory
  allocations. So a change to the UAPI header, but no functional change in the UAPI.

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221118170807.6505-1-alexander.deucher@amd.com
Signed-off-by: Dave Airlie <airlied@redhat.com>

1 files changed, 70 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
index 897a5ce9c9da..403d054cf51b 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
@@ -31,6 +31,7 @@
 #include "soc15_hw_ip.h"
 #include "vcn_v2_0.h"
 #include "mmsch_v4_0.h"
+#include "vcn_v4_0.h"
 
 #include "vcn/vcn_4_0_0_offset.h"
 #include "vcn/vcn_4_0_0_sh_mask.h"
@@ -64,6 +65,7 @@ static int vcn_v4_0_set_powergating_state(void *handle,
 static int vcn_v4_0_pause_dpg_mode(struct amdgpu_device *adev,
         int inst_idx, struct dpg_pause_state *new_state);
 static void vcn_v4_0_unified_ring_set_wptr(struct amdgpu_ring *ring);
+static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev);
 
 /**
  * vcn_v4_0_early_init - set function pointers
@@ -84,6 +86,7 @@ static int vcn_v4_0_early_init(void *handle)
 
 	vcn_v4_0_set_unified_ring_funcs(adev);
 	vcn_v4_0_set_irq_funcs(adev);
+	vcn_v4_0_set_ras_funcs(adev);
 
 	return 0;
 }
@@ -132,6 +135,12 @@ static int vcn_v4_0_sw_init(void *handle)
 		if (r)
 			return r;
 
+		/* VCN POISON TRAP */
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_vcns[i],
+				VCN_4_0__SRCID_UVD_POISON, &adev->vcn.inst[i].irq);
+		if (r)
+			return r;
+
 		ring = &adev->vcn.inst[i].ring_enc[0];
 		ring->use_doorbell = true;
 		if (amdgpu_sriov_vf(adev))
@@ -296,6 +305,7 @@ static int vcn_v4_0_hw_fini(void *handle)
 			}
 		}
 
+		amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0);
 	}
 
 	return 0;
@@ -1939,6 +1949,9 @@ static int vcn_v4_0_process_interrupt(struct amdgpu_device *adev, struct amdgpu_
 	case VCN_4_0__SRCID__UVD_ENC_GENERAL_PURPOSE:
 		amdgpu_fence_process(&adev->vcn.inst[ip_instance].ring_enc[0]);
 		break;
+	case VCN_4_0__SRCID_UVD_POISON:
+		amdgpu_vcn_process_poison_irq(adev, source, entry);
+		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
@@ -2001,3 +2014,60 @@ const struct amdgpu_ip_block_version vcn_v4_0_ip_block =
 	.rev = 0,
 	.funcs = &vcn_v4_0_ip_funcs,
 };
+
+static uint32_t vcn_v4_0_query_poison_by_instance(struct amdgpu_device *adev,
+			uint32_t instance, uint32_t sub_block)
+{
+	uint32_t poison_stat = 0, reg_value = 0;
+
+	switch (sub_block) {
+	case AMDGPU_VCN_V4_0_VCPU_VCODEC:
+		reg_value = RREG32_SOC15(VCN, instance, regUVD_RAS_VCPU_VCODEC_STATUS);
+		poison_stat = REG_GET_FIELD(reg_value, UVD_RAS_VCPU_VCODEC_STATUS, POISONED_PF);
+		break;
+	default:
+		break;
+	}
+
+	if (poison_stat)
+		dev_info(adev->dev, "Poison detected in VCN%d, sub_block%d\n",
+			instance, sub_block);
+
+	return poison_stat;
+}
+
+static bool vcn_v4_0_query_ras_poison_status(struct amdgpu_device *adev)
+{
+	uint32_t inst, sub;
+	uint32_t poison_stat = 0;
+
+	for (inst = 0; inst < adev->vcn.num_vcn_inst; inst++)
+		for (sub = 0; sub < AMDGPU_VCN_V4_0_MAX_SUB_BLOCK; sub++)
+			poison_stat +=
+				vcn_v4_0_query_poison_by_instance(adev, inst, sub);
+
+	return !!poison_stat;
+}
+
+const struct amdgpu_ras_block_hw_ops vcn_v4_0_ras_hw_ops = {
+	.query_poison_status = vcn_v4_0_query_ras_poison_status,
+};
+
+static struct amdgpu_vcn_ras vcn_v4_0_ras = {
+	.ras_block = {
+		.hw_ops = &vcn_v4_0_ras_hw_ops,
+	},
+};
+
+static void vcn_v4_0_set_ras_funcs(struct amdgpu_device *adev)
+{
+	switch (adev->ip_versions[VCN_HWIP][0]) {
+	case IP_VERSION(4, 0, 0):
+		adev->vcn.ras = &vcn_v4_0_ras;
+		break;
+	default:
+		break;
+	}
+
+	amdgpu_vcn_set_ras_funcs(adev);
+}