Re: [PATCH 11/12] device-dax: Add dis-contiguous resource support

[Joao Martins <joao.m.martins@oracle.com>]

On 3/24/20 4:12 PM, Joao Martins wrote:
> On 3/23/20 11:55 PM, Dan Williams wrote:
>>  static ssize_t dev_dax_resize(struct dax_region *dax_region,
>>  		struct dev_dax *dev_dax, resource_size_t size)
>>  {
>>  	resource_size_t avail = dax_region_avail_size(dax_region), to_alloc;
>> -	resource_size_t dev_size = range_len(&dev_dax->range);
>> +	resource_size_t dev_size = dev_dax_size(dev_dax);
>>  	struct resource *region_res = &dax_region->res;
>>  	struct device *dev = &dev_dax->dev;
>> -	const char *name = dev_name(dev);
>>  	struct resource *res, *first;
>> +	resource_size_t alloc = 0;
>> +	int rc;
>>  
>>  	if (dev->driver)
>>  		return -EBUSY;
>> @@ -684,38 +766,47 @@ static ssize_t dev_dax_resize(struct dax_region *dax_region,
>>  	 * allocating a new resource.
>>  	 */
>>  	first = region_res->child;
>> -	if (!first)
>> -		return __alloc_dev_dax_range(dev_dax, dax_region->res.start,
>> -				to_alloc);
> 
> You probably want to retain the condition above?
> 
> Otherwise it removes the ability to create new devices or resizing it , once we
> have zero-ed the last one.
> 

A quick unit test that I had stashed here to help explain what I mean:

	cd /sys/bus/dax/devices
	# dax0.0 is the only dax device in the corresponding dax_region
	echo dax0.0 > dax0.0/driver/unbind
	echo 0 > dax0.0/size
	# Shouldn't fail but returns -ENOSPC despite having
	# the full region available
	cat $(readlink -f dax0.0/../dax_region/available_size) > dax0.0/size

>> -	for (res = first; to_alloc && res; res = res->sibling) {
>> +retry:
>> +	rc = -ENOSPC;
>> +	for (res = first; res; res = res->sibling) {
>>  		struct resource *next = res->sibling;
>> -		resource_size_t free;
>>  
>>  		/* space at the beginning of the region */
>> -		free = 0;
>> -		if (res == first && res->start > dax_region->res.start)
>> -			free = res->start - dax_region->res.start;
>> -		if (free >= to_alloc && dev_size == 0)
>> -			return __alloc_dev_dax_range(dev_dax,
>> -					dax_region->res.start, to_alloc);
>> -
>> -		free = 0;
>> +		if (res == first && res->start > dax_region->res.start) {
>> +			alloc = min(res->start - dax_region->res.start,
>> +					to_alloc);
>> +			rc = __alloc_dev_dax_range(dev_dax,
>> +					dax_region->res.start, alloc);
>> +			break;
>> +		}
>> +
>> +		alloc = 0;
>>  		/* space between allocations */
>>  		if (next && next->start > res->end + 1)
>> -			free = next->start - res->end + 1;
>> +			alloc = min(next->start - (res->end + 1), to_alloc);
>>  
>>  		/* space at the end of the region */
>> -		if (free < to_alloc && !next && res->end < region_res->end)
>> -			free = region_res->end - res->end;
>> -
>> -		if (free >= to_alloc && strcmp(name, res->name) == 0)
>> -			return __adjust_dev_dax_range(dev_dax, res,
>> -					resource_size(res) + to_alloc);
>> -		else if (free >= to_alloc && dev_size == 0)
>> -			return __alloc_dev_dax_range(dev_dax, res->end + 1,
>> -					to_alloc);
>> +		if (!alloc && !next && res->end < region_res->end)
>> +			alloc = min(region_res->end - res->end, to_alloc);
>> +
>> +		if (!alloc)
>> +			continue;
>> +
>> +		if (adjust_ok(dev_dax, res)) {
>> +			rc = __adjust_dev_dax_range(dev_dax, res,
>> +					resource_size(res) + alloc);
>> +			break;
>> +		}
>> +		rc = __alloc_dev_dax_range(dev_dax, res->end + 1,
>> +				alloc);
> 
> I am wondering if we should switch to:
> 
> 	if (adjust_ok(...))
> 		rc = __adjust_dev_dax_range(...);
> 	else
> 		rc = __alloc_dev_dax_range(...);
> 
> And then a debug print at the end depicting whether and how did we grabbed
> space? Something like:
> 
> 	dev_dbg(&dev_dax->dev, "%s(%d) %d", action, location, rc);
> 
> Assuming we set @location to its values when we allocate space at the end,
> beginning or middle; and @action to whether we adjusted up/down or allocated new
> range.
> 
> Essentially, something similar to namespaces scan_allocate() just to help
> troubleshoot?
> 
> Regards,
>  Joao
> 
_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org