[PATCH] drm/amdgpu: Add autodump debugfs node for gpu reset (v2)

[Christian König]

Am 24.04.20 um 10:49 schrieb jianzh at amd.com:
> From: Jiange Zhao <Jiange.Zhao at amd.com>
>
> When GPU got timeout, it would notify an interested part
> of an opportunity to dump info before actual GPU reset.
>
> A usermode app would open 'autodump' node under debugfs system
> and poll() for readable/writable. When a GPU reset is due,
> amdgpu would notify usermode app through wait_queue_head and give
> it 10 minutes to dump info.
>
> After usermode app has done its work, this 'autodump' node is closed.
> On node closure, amdgpu gets to know the dump is done through
> the completion that is triggered in release().
>
> There is no write or read callback because necessary info can be
> obtained through dmesg and umr. Messages back and forth between
> usermode app and amdgpu are unnecessary.
>
> v2: (1) changed 'registered' to 'app_listening'
>      (2) add a mutex in open() to prevent race condition

May I pick this one up and modify it a bit?

There is still a race which needs to be fixed and it is a bit hard to 
explain what's going wrong here.

Christian.

>
> Signed-off-by: Jiange Zhao <Jiange.Zhao at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu.h         | 10 +++
>   drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c | 92 ++++++++++++++++++++-
>   drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h |  1 +
>   drivers/gpu/drm/amd/amdgpu/amdgpu_device.c  |  2 +
>   4 files changed, 104 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> index bc1e0fd71a09..34b8ce9fba47 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
> @@ -724,6 +724,14 @@ struct amd_powerplay {
>   	const struct amd_pm_funcs *pp_funcs;
>   };
>   
> +struct amdgpu_autodump {
> +	bool				app_listening;
> +	struct completion		completed;
> +	struct dentry			*dentry;
> +	struct wait_queue_head		gpu_hang_wait;
> +	struct mutex			mutex;
> +};
> +
>   #define AMDGPU_RESET_MAGIC_NUM 64
>   #define AMDGPU_MAX_DF_PERFMONS 4
>   struct amdgpu_device {
> @@ -990,6 +998,8 @@ 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..693bfcaad312 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.c
> @@ -27,7 +27,7 @@
>   #include <linux/pci.h>
>   #include <linux/uaccess.h>
>   #include <linux/pm_runtime.h>
> -
> +#include <linux/poll.h>
>   #include <drm/drm_debugfs.h>
>   
>   #include "amdgpu.h"
> @@ -74,8 +74,96 @@ 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 tmo = 600*HZ;
> +	int ret;
> +
> +	if (!adev->autodump.app_listening)
> +		return 0;
> +
> +	wake_up_interruptible(&adev->autodump.gpu_hang_wait);
> +
> +	ret = wait_for_completion_interruptible_timeout(&adev->autodump.completed, tmo);
> +	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)
> +{
> +	int ret = 0;
> +	struct amdgpu_device *adev;
> +
> +	ret = simple_open(inode, file);
> +	if (ret)
> +		return ret;
> +
> +	adev = file->private_data;
> +
> +	mutex_lock(&adev->autodump.mutex);
> +	if (adev->autodump.app_listening == true) {
> +		ret = -EBUSY;
> +	} else {
> +		adev->autodump.app_listening = true;
> +	}
> +	mutex_unlock(&adev->autodump.mutex);
> +
> +	return ret;
> +}
> +
> +static int amdgpu_debugfs_autodump_release(struct inode *inode, struct file *file)
> +{
> +	struct amdgpu_device *adev = file->private_data;
> +
> +	complete(&adev->autodump.completed);
> +	adev->autodump.app_listening = false;
> +
> +	return 0;
> +}
> +
> +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_wait, 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 int amdgpu_debugfs_autodump_init(struct amdgpu_device *adev)
> +{
> +	struct dentry *entry;
> +
> +	init_completion(&adev->autodump.completed);
> +	init_waitqueue_head(&adev->autodump.gpu_hang_wait);
> +	mutex_init(&adev->autodump.mutex);
> +	adev->autodump.app_listening = false;
> +
> +	entry = debugfs_create_file("autodump", 0600,
> +			adev->ddev->primary->debugfs_root,
> +			adev, &autodump_debug_fops);
> +	adev->autodump.dentry = entry;
> +
> +	return 0;
> +}
> +
>   /**
>    * amdgpu_debugfs_process_reg_op - Handle MMIO register reads/writes
>    *
> @@ -1434,6 +1522,8 @@ 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..9428940a696d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_debugfs.h
> @@ -40,3 +40,4 @@ 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 3d601d5dd5af..44e54ea7af0f 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -3915,6 +3915,8 @@ 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];