drm/amdgpu: Present amdgpu_task_info in VM_FAULTS.

Extract and present the reposnsible process and thread when
VM_FAULT happens.

v2: Use getter and setter functions.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1bc02816989d74b400d4094da0e30cc6a5dd485b..9881a1e55df3e321df116fd5de3e39bae94f74ed 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -187,6 +187,10 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
        if (p->uf_entry.robj)
                p->job->uf_addr = uf_offset;
        kfree(chunk_array);
+
+       /* Use this opportunity to fill in task info for the vm */
+       amdgpu_vm_set_task_info(vm);
+
        return 0;
 
 free_all_kdata:

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1edbe6b477b56dc309a49eb1d5a2e68d11ffa8be..a86332f36c3e0bc267934971e3ee659aa7f087a3 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -44,7 +44,6 @@
 
 #include "amdgpu_atombios.h"
 
-
 static void gmc_v8_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v8_0_wait_for_idle(void *handle);
@@ -1447,8 +1446,13 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
                gmc_v8_0_set_fault_enable_default(adev, false);
 
        if (printk_ratelimit()) {
-               dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
-                       entry->src_id, entry->src_data[0]);
+               struct amdgpu_task_info task_info = { 0 };
+
+               amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
+               dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n",
+                       entry->src_id, entry->src_data[0], task_info.process_name,
+                       task_info.tgid, task_info.task_name, task_info.pid);
                dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
                        addr);
                dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3c0a85d4e4ab9b513ec2681ab199659bba6e1bf3..7f238149ba54ae7489458e73afcf7cfa38a5258d 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -257,11 +257,16 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
        }
 
        if (printk_ratelimit()) {
+               struct amdgpu_task_info task_info = { 0 };
+
+               amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
                dev_err(adev->dev,
-                       "[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n",
+                       "[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u, for process %s pid %d thread %s pid %d\n)\n",
                        entry->vmid_src ? "mmhub" : "gfxhub",
                        entry->src_id, entry->ring_id, entry->vmid,
-                       entry->pasid);
+                       entry->pasid, task_info.process_name, task_info.tgid,
+                       task_info.task_name, task_info.pid);
                dev_err(adev->dev, "  at page 0x%016llx from %d\n",
                        addr, entry->client_id);
                if (!amdgpu_sriov_vf(adev))