Re: [PATCH v2 2/7] iommu/vt-d: Multiple descriptors per qi_submit_sync()

[Lu Baolu <baolu.lu@linux.intel.com>]

On 2020/4/15 16:18, Tian, Kevin wrote:
>> From: Lu Baolu<baolu.lu@linux.intel.com>
>> Sent: Wednesday, April 15, 2020 1:26 PM
>>
>> Extend qi_submit_sync() function to support multiple descriptors.
>>
>> Signed-off-by: Jacob Pan<jacob.jun.pan@linux.intel.com>
>> Signed-off-by: Lu Baolu<baolu.lu@linux.intel.com>
>> ---
>>   drivers/iommu/dmar.c        | 39 +++++++++++++++++++++++--------------
>>   include/linux/intel-iommu.h |  1 +
>>   2 files changed, 25 insertions(+), 15 deletions(-)
>>
>> diff --git a/drivers/iommu/dmar.c b/drivers/iommu/dmar.c
>> index bb42177e2369..61d049e91f84 100644
>> --- a/drivers/iommu/dmar.c
>> +++ b/drivers/iommu/dmar.c
>> @@ -1157,12 +1157,11 @@ static inline void reclaim_free_desc(struct
>> q_inval *qi)
>>   	}
>>   }
>>
>> -static int qi_check_fault(struct intel_iommu *iommu, int index)
>> +static int qi_check_fault(struct intel_iommu *iommu, int index, int
>> wait_index)
>>   {
>>   	u32 fault;
>>   	int head, tail;
>>   	struct q_inval *qi = iommu->qi;
>> -	int wait_index = (index + 1) % QI_LENGTH;
>>   	int shift = qi_shift(iommu);
>>
>>   	if (qi->desc_status[wait_index] == QI_ABORT)
>> @@ -1234,12 +1233,12 @@ static int qi_check_fault(struct intel_iommu
>> *iommu, int index)
>>   int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
>>   		   unsigned int count, unsigned long options)
>>   {
>> -	int rc;
>>   	struct q_inval *qi = iommu->qi;
>> -	int offset, shift, length;
>>   	struct qi_desc wait_desc;
>>   	int wait_index, index;
>>   	unsigned long flags;
>> +	int offset, shift;
>> +	int rc, i;
>>
>>   	if (!qi)
>>   		return 0;
>> @@ -1248,32 +1247,41 @@ int qi_submit_sync(struct intel_iommu *iommu,
>> struct qi_desc *desc,
>>   	rc = 0;
>>
>>   	raw_spin_lock_irqsave(&qi->q_lock, flags);
>> -	while (qi->free_cnt < 3) {
>> +	/*
>> +	 * Check if we have enough empty slots in the queue to submit,
>> +	 * the calculation is based on:
>> +	 * # of desc + 1 wait desc + 1 space between head and tail
>> +	 */
>> +	while (qi->free_cnt < count + 2) {
>>   		raw_spin_unlock_irqrestore(&qi->q_lock, flags);
>>   		cpu_relax();
>>   		raw_spin_lock_irqsave(&qi->q_lock, flags);
>>   	}
>>
>>   	index = qi->free_head;
>> -	wait_index = (index + 1) % QI_LENGTH;
>> +	wait_index = (index + count) % QI_LENGTH;
>>   	shift = qi_shift(iommu);
>> -	length = 1 << shift;
>>
>> -	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;
>> +	for (i = 0; i < count; i++) {
>> +		offset = ((index + i) % QI_LENGTH) << shift;
>> +		memcpy(qi->desc + offset, &desc[i], 1 << shift);
>> +		qi->desc_status[(index + i) % QI_LENGTH] = QI_IN_USE;
>> +	}
> what about doing one memcpy and leave the loop only for updating
> qi status?
> 

One memcpy might cross the table boundary.

Best regards,
baolu