drm/amdgpu: cache gpuvm fault information for gmc7+

Cache the current fault info in the vm struct.  This can be queried
by userspace later to help debug UMDs.

Cc: samuel.pitoiset@gmail.com
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Guchun Chen <guchun.chen@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

5 files changed, 19 insertions, 4 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
index 8e6e36279389..d8a4fddab9c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
@@ -149,6 +149,9 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
 
 		status = RREG32(hub->vm_l2_pro_fault_status);
 		WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
+
+		amdgpu_vm_update_fault_cache(adev, entry->pasid, addr, status,
+					     entry->vmid_src ? AMDGPU_MMHUB0(0) : AMDGPU_GFXHUB(0));
 	}
 
 	if (!printk_ratelimit())
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
index 07f50ca8d481..f4bb3886d1bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
@@ -119,6 +119,9 @@ static int gmc_v11_0_process_interrupt(struct amdgpu_device *adev,
 
 		status = RREG32(hub->vm_l2_pro_fault_status);
 		WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
+
+		amdgpu_vm_update_fault_cache(adev, entry->pasid, addr, status,
+					     entry->vmid_src ? AMDGPU_MMHUB0(0) : AMDGPU_GFXHUB(0));
 	}
 
 	if (printk_ratelimit()) {
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 3869cefab7bd..61ca1a82b651 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -1268,6 +1268,9 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 	if (!addr && !status)
 		return 0;
 
+	amdgpu_vm_update_fault_cache(adev, entry->pasid,
+				     ((u64)addr) << AMDGPU_GPU_PAGE_SHIFT, status, AMDGPU_GFXHUB(0));
+
 	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST)
 		gmc_v7_0_set_fault_enable_default(adev, false);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 4126172feb7f..fa59749c2aef 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -1436,6 +1436,9 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 	if (!addr && !status)
 		return 0;
 
+	amdgpu_vm_update_fault_cache(adev, entry->pasid,
+				     ((u64)addr) << AMDGPU_GPU_PAGE_SHIFT, status, AMDGPU_GFXHUB(0));
+
 	if (amdgpu_vm_fault_stop == AMDGPU_VM_FAULT_STOP_FIRST)
 		gmc_v8_0_set_fault_enable_default(adev, false);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 04edd61893c7..4e823e348c1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -553,6 +553,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	struct amdgpu_vmhub *hub;
 	const char *mmhub_cid;
 	const char *hub_name;
+	unsigned int vmhub;
 	u64 addr;
 	uint32_t cam_index = 0;
 	int ret, xcc_id = 0;
@@ -565,10 +566,10 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 
 	if (entry->client_id == SOC15_IH_CLIENTID_VMC) {
 		hub_name = "mmhub0";
-		hub = &adev->vmhub[AMDGPU_MMHUB0(node_id / 4)];
+		vmhub = AMDGPU_MMHUB0(node_id / 4);
 	} else if (entry->client_id == SOC15_IH_CLIENTID_VMC1) {
 		hub_name = "mmhub1";
-		hub = &adev->vmhub[AMDGPU_MMHUB1(0)];
+		vmhub = AMDGPU_MMHUB1(0);
 	} else {
 		hub_name = "gfxhub0";
 		if (adev->gfx.funcs->ih_node_to_logical_xcc) {
@@ -577,8 +578,9 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 			if (xcc_id < 0)
 				xcc_id = 0;
 		}
-		hub = &adev->vmhub[xcc_id];
+		vmhub = xcc_id;
 	}
+	hub = &adev->vmhub[vmhub];
 
 	if (retry_fault) {
 		if (adev->irq.retry_cam_enabled) {
@@ -624,7 +626,6 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	if (!printk_ratelimit())
 		return 0;
 
-
 	memset(&task_info, 0, sizeof(struct amdgpu_task_info));
 	amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
 
@@ -660,6 +661,8 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	rw = REG_GET_FIELD(status, VM_L2_PROTECTION_FAULT_STATUS, RW);
 	WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
 
+	amdgpu_vm_update_fault_cache(adev, entry->pasid, addr, status, vmhub);
+
 	dev_err(adev->dev,
 		"VM_L2_PROTECTION_FAULT_STATUS:0x%08X\n",
 		status);