Re: [PATCH 10/15] habanalabs: add device reset support

[Mike Rapoport <rppt@linux.ibm.com>]

On Wed, Jan 23, 2019 at 02:00:52AM +0200, Oded Gabbay wrote:
> This patch adds support for doing various on-the-fly reset of Goya.
> 
> The driver supports two types of resets:
> 1. soft-reset
> 2. hard-reset
> 
> Soft-reset is done when the device detects a timeout of a command
> submission that was given to the device. The soft-reset process only resets
> the engines that are relevant for the submission of compute jobs, i.e. the
> DMA channels, the TPCs and the MME. The purpose is to bring the device as
> fast as possible to a working state.
> 
> Hard-reset is done in several cases:
> 1. After soft-reset is done but the device is not responding
> 2. When fatal errors occur inside the device, e.g. ECC error
> 3. When the driver is removed
> 
> Hard-reset performs a reset of the entire chip except for the PCI
> controller and the PLLs. It is a much longer process then soft-reset but it
> helps to recover the device without the need to reboot the Host.
> 
> After hard-reset, the driver will restore the max power attribute and in
> case of manual power management, the frequencies that were set.
> 
> This patch also adds two entries to the sysfs, which allows the root user
> to initiate a soft or hard reset.
> 
> Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
> ---
>  drivers/misc/habanalabs/command_buffer.c  |  11 +-
>  drivers/misc/habanalabs/device.c          | 308 +++++++++++++++++++++-
>  drivers/misc/habanalabs/goya/goya.c       | 201 ++++++++++++++
>  drivers/misc/habanalabs/goya/goya_hwmgr.c |  18 +-
>  drivers/misc/habanalabs/habanalabs.h      |  35 +++
>  drivers/misc/habanalabs/habanalabs_drv.c  |   9 +-
>  drivers/misc/habanalabs/hwmon.c           |   4 +-
>  drivers/misc/habanalabs/irq.c             |  31 +++
>  drivers/misc/habanalabs/sysfs.c           | 120 ++++++++-
>  9 files changed, 712 insertions(+), 25 deletions(-)
> 
> diff --git a/drivers/misc/habanalabs/command_buffer.c b/drivers/misc/habanalabs/command_buffer.c
> index 535ed6cc5bda..700c6da01188 100644
> --- a/drivers/misc/habanalabs/command_buffer.c
> +++ b/drivers/misc/habanalabs/command_buffer.c
> @@ -81,9 +81,10 @@ int hl_cb_create(struct hl_device *hdev, struct hl_cb_mgr *mgr,
>  	bool alloc_new_cb = true;
>  	int rc;
>  
> -	if (hdev->disabled) {
> +	if ((hdev->disabled) || ((atomic_read(&hdev->in_reset)) &&
> +					(ctx_id != HL_KERNEL_ASID_ID))) {
>  		dev_warn_ratelimited(hdev->dev,
> -			"Device is disabled !!! Can't create new CBs\n");
> +			"Device is disabled or in reset !!! Can't create new CBs\n");
>  		rc = -EBUSY;
>  		goto out_err;
>  	}
> @@ -187,6 +188,12 @@ int hl_cb_ioctl(struct hl_fpriv *hpriv, void *data)
>  	u64 handle;
>  	int rc;
>  
> +	if (hdev->hard_reset_pending) {
> +		dev_crit_ratelimited(hdev->dev,
> +			"Device HARD reset pending !!! Please close FD\n");
> +		return -ENODEV;
> +	}

Probably this check should be done at the top-level ioctl()? 
And, what will happen if the devices performs hard reset, but the used
keeps the file descriptor open?

> +
>  	switch (args->in.op) {
>  	case HL_CB_OP_CREATE:
>  		rc = hl_cb_create(hdev, &hpriv->cb_mgr, args->in.cb_size,
> diff --git a/drivers/misc/habanalabs/device.c b/drivers/misc/habanalabs/device.c
> index ff7b610f18c4..00fde57ce823 100644
> --- a/drivers/misc/habanalabs/device.c
> +++ b/drivers/misc/habanalabs/device.c
> @@ -188,6 +188,7 @@ static int device_early_init(struct hl_device *hdev)
>  
>  	mutex_init(&hdev->device_open);
>  	mutex_init(&hdev->send_cpu_message_lock);
> +	atomic_set(&hdev->in_reset, 0);
>  	atomic_set(&hdev->fd_open_cnt, 0);
>  
>  	return 0;
> @@ -238,6 +239,27 @@ static void set_freq_to_low_job(struct work_struct *work)
>  			usecs_to_jiffies(HL_PLL_LOW_JOB_FREQ_USEC));
>  }
>  
> +static void hl_device_heartbeat(struct work_struct *work)
> +{
> +	struct hl_device *hdev = container_of(work, struct hl_device,
> +						work_heartbeat.work);
> +
> +	if ((hdev->disabled) || (atomic_read(&hdev->in_reset)))
> +		goto reschedule;
> +
> +	if (!hdev->asic_funcs->send_heartbeat(hdev))
> +		goto reschedule;

AFAIU, asic_funcs->send_heartbeat() it set once at init time. The work
should not be scheduled it it's NULL, I suppose.

> +
> +	dev_err(hdev->dev, "Device heartbeat failed !!!\n");
> +	hl_device_reset(hdev, true, false);
> +
> +	return;
> +
> +reschedule:
> +	schedule_delayed_work(&hdev->work_heartbeat,
> +			usecs_to_jiffies(HL_HEARTBEAT_PER_USEC));
> +}
> +
>  /**
>   * device_late_init - do late stuff initialization for the habanalabs device
>   *
> @@ -273,6 +295,12 @@ static int device_late_init(struct hl_device *hdev)
>  	schedule_delayed_work(&hdev->work_freq,
>  			usecs_to_jiffies(HL_PLL_LOW_JOB_FREQ_USEC));
>  
> +	if (hdev->heartbeat) {
> +		INIT_DELAYED_WORK(&hdev->work_heartbeat, hl_device_heartbeat);
> +		schedule_delayed_work(&hdev->work_heartbeat,
> +				usecs_to_jiffies(HL_HEARTBEAT_PER_USEC));
> +	}
> +
>  	hdev->late_init_done = true;
>  
>  	return 0;
> @@ -290,6 +318,8 @@ static void device_late_fini(struct hl_device *hdev)
>  		return;
>  
>  	cancel_delayed_work_sync(&hdev->work_freq);
> +	if (hdev->heartbeat)
> +		cancel_delayed_work_sync(&hdev->work_heartbeat);
>  
>  	if (hdev->asic_funcs->late_fini)
>  		hdev->asic_funcs->late_fini(hdev);
> @@ -397,6 +427,254 @@ int hl_device_resume(struct hl_device *hdev)
>  	return 0;
>  }
>  
> +static void hl_device_hard_reset_pending(struct work_struct *work)
> +{
> +	struct hl_device_reset_work *device_reset_work =
> +		container_of(work, struct hl_device_reset_work, reset_work);
> +	struct hl_device *hdev = device_reset_work->hdev;
> +	u16 pending_cnt = HL_PENDING_RESET_PER_SEC;
> +	struct task_struct *task = NULL;
> +
> +	/* Flush all processes that are inside hl_open */
> +	mutex_lock(&hdev->device_open);
> +
> +	while ((atomic_read(&hdev->fd_open_cnt)) && (pending_cnt)) {
> +
> +		pending_cnt--;
> +
> +		dev_info(hdev->dev,
> +			"Can't HARD reset, waiting for user to close FD\n");
> +		ssleep(1);
> +	}
> +
> +	if (atomic_read(&hdev->fd_open_cnt)) {
> +		task = get_pid_task(hdev->user_ctx->hpriv->taskpid,
> +					PIDTYPE_PID);
> +		if (task) {
> +			dev_info(hdev->dev, "Killing user processes\n");
> +			send_sig(SIGKILL, task, 1);

Shouldn't the user get a chance for cleanup?

> +			msleep(100);
> +
> +			put_task_struct(task);
> +		}
> +	}
> +
> +	mutex_unlock(&hdev->device_open);
> +
> +	hl_device_reset(hdev, true, true);
> +
> +	kfree(device_reset_work);
> +}
> +

[ ... ]

> diff --git a/drivers/misc/habanalabs/goya/goya_hwmgr.c b/drivers/misc/habanalabs/goya/goya_hwmgr.c
> index 866d1774b2e4..9482dbb2e03a 100644
> --- a/drivers/misc/habanalabs/goya/goya_hwmgr.c
> +++ b/drivers/misc/habanalabs/goya/goya_hwmgr.c
> @@ -38,7 +38,7 @@ static ssize_t mme_clk_show(struct device *dev, struct device_attribute *attr,
>  	struct hl_device *hdev = dev_get_drvdata(dev);
>  	long value;
>  
> -	if (hdev->disabled)
> +	if ((hdev->disabled) || (atomic_read(&hdev->in_reset)))
>  		return -ENODEV;
>  
>  	value = hl_get_frequency(hdev, MME_PLL, false);
> @@ -57,7 +57,7 @@ static ssize_t mme_clk_store(struct device *dev, struct device_attribute *attr,
>  	int rc;
>  	long value;
>  
> -	if (hdev->disabled) {
> +	if ((hdev->disabled) || (atomic_read(&hdev->in_reset))) {

There are quite a few of those, maybe split this check to a helper
function?

>  		count = -ENODEV;
>  		goto fail;
>  	}
> @@ -87,7 +87,7 @@ static ssize_t tpc_clk_show(struct device *dev, struct device_attribute *attr,
>  	struct hl_device *hdev = dev_get_drvdata(dev);
>  	long value;
>  
> -	if (hdev->disabled)
> +	if ((hdev->disabled) || (atomic_read(&hdev->in_reset)))
>  		return -ENODEV;
>  
>  	value = hl_get_frequency(hdev, TPC_PLL, false);
> @@ -106,7 +106,7 @@ static ssize_t tpc_clk_store(struct device *dev, struct device_attribute *attr,
>  	int rc;
>  	long value;
>  
> -	if (hdev->disabled) {
> +	if ((hdev->disabled) || (atomic_read(&hdev->in_reset))) {
>  		count = -ENODEV;
>  		goto fail;
>  	}

-- 
Sincerely yours,
Mike.