diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 4a03a24348f4..7975f8e157df 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -989,6 +989,8 @@ struct amdgpu_device { char product_number[16]; char product_name[32]; char serial[16]; + + struct amdgpu_autodump autodump; }; static inline struct amdgpu_device *amdgpu_ttm_adev(struct ttm_bo_device *bdev) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c index 1a4894fa3693..d33cb344be69 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c @@ -27,7 +27,7 @@ #include #include #include - +#include #include #include "amdgpu.h" @@ -74,7 +74,81 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev, return 0; } +int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev) +{ #if defined(CONFIG_DEBUG_FS) + unsigned long timeout = 600 * HZ; + int ret; + + wake_up_interruptible(&adev->autodump.gpu_hang); + + ret = wait_for_completion_interruptible_timeout(&adev->autodump.dumping, timeout); + if (ret == 0) { + pr_err("autodump: timeout, move on to gpu recovery\n"); + return -ETIMEDOUT; + } +#endif + return 0; +} + +#if defined(CONFIG_DEBUG_FS) + +static int amdgpu_debugfs_autodump_open(struct inode *inode, struct file *file) +{ + struct amdgpu_device *adev = inode->i_private; + int ret; + + file->private_data = adev; + + mutex_lock(&adev->lock_reset); + if (adev->autodump.dumping.done) { + reinit_completion(&adev->autodump.dumping); + ret = 0; + } else { + ret = -EBUSY; + } + mutex_unlock(&adev->lock_reset); + + return ret; +} + +static int amdgpu_debugfs_autodump_release(struct inode *inode, struct file *file) +{ + struct amdgpu_device *adev = file->private_data; + + complete_all(&adev->autodump.dumping); + return 0; +} + +static unsigned int amdgpu_debugfs_autodump_poll(struct file *file, struct poll_table_struct *poll_table) +{ + struct amdgpu_device *adev = file->private_data; + + poll_wait(file, &adev->autodump.gpu_hang, poll_table); + + if (adev->in_gpu_reset) + return POLLIN | POLLRDNORM | POLLWRNORM; + + return 0; +} + +static const struct file_operations autodump_debug_fops = { + .owner = THIS_MODULE, + .open = amdgpu_debugfs_autodump_open, + .poll = amdgpu_debugfs_autodump_poll, + .release = amdgpu_debugfs_autodump_release, +}; + +static void amdgpu_debugfs_autodump_init(struct amdgpu_device *adev) +{ + init_completion(&adev->autodump.dumping); + complete_all(&adev->autodump.dumping); + init_waitqueue_head(&adev->autodump.gpu_hang); + + debugfs_create_file("amdgpu_autodump", 0600, + adev->ddev->primary->debugfs_root, + adev, &autodump_debug_fops); +} /** * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes @@ -1434,6 +1508,8 @@ int amdgpu_debugfs_init(struct amdgpu_device *adev) amdgpu_ras_debugfs_create_all(adev); + amdgpu_debugfs_autodump_init(adev); + return amdgpu_debugfs_add_files(adev, amdgpu_debugfs_list, ARRAY_SIZE(amdgpu_debugfs_list)); } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h index de12d1101526..2803884d338d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h @@ -31,6 +31,11 @@ struct amdgpu_debugfs { unsigned num_files; }; +struct amdgpu_autodump { + struct completion dumping; + struct wait_queue_head gpu_hang; +}; + int amdgpu_debugfs_regs_init(struct amdgpu_device *adev); int amdgpu_debugfs_init(struct amdgpu_device *adev); void amdgpu_debugfs_fini(struct amdgpu_device *adev); @@ -40,3 +45,4 @@ int amdgpu_debugfs_add_files(struct amdgpu_device *adev, int amdgpu_debugfs_fence_init(struct amdgpu_device *adev); int amdgpu_debugfs_firmware_init(struct amdgpu_device *adev); int amdgpu_debugfs_gem_init(struct amdgpu_device *adev); +int amdgpu_debugfs_wait_dump(struct amdgpu_device *adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index cc41e8f5ad14..545beebcf43e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3927,6 +3927,8 @@ static int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev, int i, r = 0; bool need_full_reset = *need_full_reset_arg; + amdgpu_debugfs_wait_dump(adev); + /* block all schedulers and reset given job's ring */ for (i = 0; i < AMDGPU_MAX_RINGS; ++i) { struct amdgpu_ring *ring = adev->rings[i];