Re: [PATCH v2 1/2] iommu/iova: Retry from last rb tree node if iova search fails

[Vijayanand Jitta]

On 9/18/2020 7:48 PM, Robin Murphy wrote:
> On 2020-08-20 13:49, vjitta@xxxxxxxxxxxxxx wrote:
>> From: Vijayanand Jitta <vjitta@xxxxxxxxxxxxxx>
>>
>> When ever a new iova alloc request comes iova is always searched
>> from the cached node and the nodes which are previous to cached
>> node. So, even if there is free iova space available in the nodes
>> which are next to the cached node iova allocation can still fail
>> because of this approach.
>>
>> Consider the following sequence of iova alloc and frees on
>> 1GB of iova space
>>
>> 1) alloc - 500MB
>> 2) alloc - 12MB
>> 3) alloc - 499MB
>> 4) free -  12MB which was allocated in step 2
>> 5) alloc - 13MB
>>
>> After the above sequence we will have 12MB of free iova space and
>> cached node will be pointing to the iova pfn of last alloc of 13MB
>> which will be the lowest iova pfn of that iova space. Now if we get an
>> alloc request of 2MB we just search from cached node and then look
>> for lower iova pfn's for free iova and as they aren't any, iova alloc
>> fails though there is 12MB of free iova space.
>>
>> To avoid such iova search failures do a retry from the last rb tree node
>> when iova search fails, this will search the entire tree and get an iova
>> if its available.
>>
>> Signed-off-by: Vijayanand Jitta <vjitta@xxxxxxxxxxxxxx>
>> ---
>>   drivers/iommu/iova.c | 23 +++++++++++++++++------
>>   1 file changed, 17 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
>> index 49fc01f..4e77116 100644
>> --- a/drivers/iommu/iova.c
>> +++ b/drivers/iommu/iova.c
>> @@ -184,8 +184,9 @@ static int __alloc_and_insert_iova_range(struct
>> iova_domain *iovad,
>>       struct rb_node *curr, *prev;
>>       struct iova *curr_iova;
>>       unsigned long flags;
>> -    unsigned long new_pfn;
>> +    unsigned long new_pfn, low_pfn_new;
>>       unsigned long align_mask = ~0UL;
>> +    unsigned long high_pfn = limit_pfn, low_pfn = iovad->start_pfn;
>>         if (size_aligned)
>>           align_mask <<= fls_long(size - 1);
>> @@ -198,15 +199,25 @@ static int __alloc_and_insert_iova_range(struct
>> iova_domain *iovad,
>>         curr = __get_cached_rbnode(iovad, limit_pfn);
>>       curr_iova = rb_entry(curr, struct iova, node);
>> +    low_pfn_new = curr_iova->pfn_hi + 1;
> 
> Could we call "low_pfn_new" something like "retry_pfn" instead? This
> code already has unavoidable readability struggles with so many
> different "pfn"s in play, so having two different meanings of "new"
> really doesn't help.
> 
> Other than that, I think this looks OK (IIRC it's basically what I
> originally suggested), so with the naming tweaked,
> 
> Reviewed-by: Robin Murphy <robin.murphy@xxxxxxx>
> 

Thanks for review, I have renamed it to retry_pfn in v4.

Thanks,
Vijay
>> +
>> +retry:
>>       do {
>> -        limit_pfn = min(limit_pfn, curr_iova->pfn_lo);
>> -        new_pfn = (limit_pfn - size) & align_mask;
>> +        high_pfn = min(high_pfn, curr_iova->pfn_lo);
>> +        new_pfn = (high_pfn - size) & align_mask;
>>           prev = curr;
>>           curr = rb_prev(curr);
>>           curr_iova = rb_entry(curr, struct iova, node);
>> -    } while (curr && new_pfn <= curr_iova->pfn_hi);
>> -
>> -    if (limit_pfn < size || new_pfn < iovad->start_pfn) {
>> +    } while (curr && new_pfn <= curr_iova->pfn_hi && new_pfn >=
>> low_pfn);
>> +
>> +    if (high_pfn < size || new_pfn < low_pfn) {
>> +        if (low_pfn == iovad->start_pfn && low_pfn_new < limit_pfn) {
>> +            high_pfn = limit_pfn;
>> +            low_pfn = low_pfn_new;
>> +            curr = &iovad->anchor.node;
>> +            curr_iova = rb_entry(curr, struct iova, node);
>> +            goto retry;
>> +        }
>>           iovad->max32_alloc_size = size;
>>           goto iova32_full;
>>       }
>>

-- 
QUALCOMM INDIA, on behalf of Qualcomm Innovation Center, Inc. is a
member of Code Aurora Forum, hosted by The Linux Foundation