diff options
Diffstat (limited to 'common/recipes-kernel/linux/linux-yocto-4.14.71/4251-drm-amdkfd-Implement-hw_exception-work-thread-to-han.patch')
| -rw-r--r-- | common/recipes-kernel/linux/linux-yocto-4.14.71/4251-drm-amdkfd-Implement-hw_exception-work-thread-to-han.patch | 134 |
1 files changed, 134 insertions, 0 deletions
diff --git a/common/recipes-kernel/linux/linux-yocto-4.14.71/4251-drm-amdkfd-Implement-hw_exception-work-thread-to-han.patch b/common/recipes-kernel/linux/linux-yocto-4.14.71/4251-drm-amdkfd-Implement-hw_exception-work-thread-to-han.patch new file mode 100644 index 00000000..2e680162 --- /dev/null +++ b/common/recipes-kernel/linux/linux-yocto-4.14.71/4251-drm-amdkfd-Implement-hw_exception-work-thread-to-han.patch @@ -0,0 +1,134 @@ +From 22f128a6d675e2eb759b07ee3eaeb0d56e2f0b48 Mon Sep 17 00:00:00 2001 +From: Shaoyun Liu <Shaoyun.Liu@amd.com> +Date: Thu, 5 Apr 2018 15:01:40 -0400 +Subject: [PATCH 4251/5725] drm/amdkfd: Implement hw_exception work thread to + handle hws hang + +Change-Id: I021fe1e875baa4242c5347e02559a414937dfa96 +Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com> +Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com> +--- + drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 4 +--- + .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 22 +++++++++++++++++++++- + .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.h | 4 ++++ + 3 files changed, 26 insertions(+), 4 deletions(-) + +diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +index a242208..d1a18c9 100644 +--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c ++++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +@@ -137,10 +137,8 @@ static int kfd_open(struct inode *inode, struct file *filep) + if (IS_ERR(process)) + return PTR_ERR(process); + +- if (kfd_is_locked()) { +- kfd_unref_process(process); ++ if (kfd_is_locked()) + return -EAGAIN; +- } + + dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n", + process->pasid, process->is_32bit_user_mode); +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 b0c159a..82c7dbe 100644 +--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c ++++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c +@@ -60,6 +60,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm, + static void deallocate_sdma_queue(struct device_queue_manager *dqm, + unsigned int sdma_queue_id); + ++static void kfd_process_hw_exception(struct work_struct *work); ++ + static inline + enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type) + { +@@ -1021,6 +1023,8 @@ static int initialize_cpsch(struct device_queue_manager *dqm) + dqm->active_runlist = false; + dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1; + ++ INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception); ++ + return 0; + } + +@@ -1053,6 +1057,8 @@ static int start_cpsch(struct device_queue_manager *dqm) + init_interrupts(dqm); + + mutex_lock(&dqm->lock); ++ /* clear hang status when driver try to start the hw scheduler */ ++ dqm->is_hws_hang = false; + execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0); + mutex_unlock(&dqm->lock); + +@@ -1268,6 +1274,8 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm, + { + int retval = 0; + ++ if (dqm->is_hws_hang) ++ return -EIO; + if (!dqm->active_runlist) + return retval; + +@@ -1306,9 +1314,13 @@ static int execute_queues_cpsch(struct device_queue_manager *dqm, + { + int retval; + ++ if (dqm->is_hws_hang) ++ return -EIO; + retval = unmap_queues_cpsch(dqm, filter, filter_param); + if (retval) { + pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n"); ++ dqm->is_hws_hang = true; ++ schedule_work(&dqm->hw_exception_work); + return retval; + } + +@@ -1590,7 +1602,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, + } + + retval = execute_queues_cpsch(dqm, filter, 0); +- if (retval || qpd->reset_wavefronts) { ++ if ((!dqm->is_hws_hang) && (retval || qpd->reset_wavefronts)) { + pr_warn("Resetting wave fronts (cpsch) on dev %p\n", dqm->dev); + dbgdev_wave_reset_wavefronts(dqm->dev, qpd->pqm->process); + qpd->reset_wavefronts = false; +@@ -1611,6 +1623,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm, + + out: + mutex_unlock(&dqm->lock); ++ + return retval; + } + +@@ -1744,6 +1757,13 @@ int kfd_process_vm_fault(struct device_queue_manager *dqm, + return ret; + } + ++static void kfd_process_hw_exception(struct work_struct *work) ++{ ++ struct device_queue_manager *dqm = container_of(work, ++ struct device_queue_manager, hw_exception_work); ++ dqm->dev->kfd2kgd->gpu_recover(dqm->dev->kgd); ++} ++ + #if defined(CONFIG_DEBUG_FS) + + static void seq_reg_dump(struct seq_file *m, +diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +index 978458a..3f17e5e 100644 +--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h ++++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h +@@ -195,6 +195,10 @@ struct device_queue_manager { + struct kfd_mem_obj *fence_mem; + bool active_runlist; + int sched_policy; ++ ++ /* hw exception */ ++ bool is_hws_hang; ++ struct work_struct hw_exception_work; + }; + + void device_queue_manager_init_cik( +-- +2.7.4 + |