diff options
| author | Yong Zhao <yong.zhao@amd.com> | 2018-07-11 22:33:05 -0400 |
|---|---|---|
| committer | Oded Gabbay <oded.gabbay@gmail.com> | 2018-07-11 22:33:05 -0400 |
| commit | 0e9a860c72ec387140a0feb4b8d9a6d0004e9316 (patch) | |
| tree | 4b3df7d853733bfd541427fdbff2f956310dde55 /drivers | |
| parent | a29ec470b19e58044005973301f233e0b20ed8c4 (diff) | |
drm/amdkfd: Introduce KFD module parameter halt_if_hws_hang
This avoids triggering a GPU reset or otherwise changing the HW
state. Instead KFD will hang, which allows HW debugging tools to
analyze the problem.
Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 7 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_module.c | 4 | ||||
| -rw-r--r-- | drivers/gpu/drm/amd/amdkfd/kfd_priv.h | 5 |
3 files changed, 16 insertions, 0 deletions
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c index 32e93b53e7e8..5d05d125c3c1 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c @@ -1217,6 +1217,13 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr, while (*fence_addr != fence_value) { if (time_after(jiffies, end_jiffies)) { pr_err("qcm fence wait loop timeout expired\n"); + /* In HWS case, this is used to halt the driver thread + * in order not to mess up CP states before doing + * scandumps for FW debugging. + */ + while (halt_if_hws_hang) + schedule(); + return -ETIME; } schedule(); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c index ee7bf07db472..3a8c15ad0c64 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c @@ -92,6 +92,10 @@ MODULE_PARM_DESC(noretry, static int amdkfd_init_completed; +int halt_if_hws_hang; +module_param(halt_if_hws_hang, int, 0644); +MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)"); + int kgd2kfd_init(unsigned int interface_version, const struct kgd2kfd_calls **g2f) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h index d9bf70b52857..8473e7b3dcc2 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h @@ -144,6 +144,11 @@ extern int ignore_crat; */ extern int vega10_noretry; +/* + * Halt if HWS hang is detected + */ +extern int halt_if_hws_hang; + /** * enum kfd_sched_policy * |