Re: [PATCH 1/2] scsi: ufs: Add Multi-Circular Queue support

[Bart Van Assche <bvanassche@acm.org>]

On 7/23/22 14:23, Avri Altman wrote:
>>   static inline
>> -void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag)
>> +void ufshcd_send_command(struct ufs_hba *hba, struct ufshcd_lrb *lrbp,
>> +                        struct ufs_hw_queue *hwq)
>>   {
>> -       struct ufshcd_lrb *lrbp = &hba->lrb[task_tag];
>>          unsigned long flags;
>>
>>          lrbp->issue_time_stamp = ktime_get();
>>          lrbp->compl_time_stamp = ktime_set(0, 0);
>> -       ufshcd_add_command_trace(hba, task_tag, UFS_CMD_SEND);
>> +       ufshcd_add_command_trace(hba, lrbp, UFS_CMD_SEND);
>>          ufshcd_clk_scaling_start_busy(hba);
>>          if (unlikely(ufshcd_should_inform_monitor(hba, lrbp)))
>>                  ufshcd_start_monitor(hba, lrbp);
>>
>> -       spin_lock_irqsave(&hba->outstanding_lock, flags);
>> -       if (hba->vops && hba->vops->setup_xfer_req)
>> -               hba->vops->setup_xfer_req(hba, task_tag, !!lrbp->cmd);
>> -       __set_bit(task_tag, &hba->outstanding_reqs);
>> -       ufshcd_writel(hba, 1 << task_tag,
>> REG_UTP_TRANSFER_REQ_DOOR_BELL);
>> -       spin_unlock_irqrestore(&hba->outstanding_lock, flags);
>> +       if (is_mcq_enabled(hba)) {
>> +               int utrd_size = sizeof(struct utp_transfer_req_desc);
 >
> Maybe we can map some designated ops, so all those if (is_mcq) can be avoided in the data-path.
> Also maybe we can constify sizeof(struct utp_transfer_req_desc) which is used now few times.

Hi Avri,

Since conditional branches are significantly faster than indirect 
function calls I'm fine with keeping the if (is_mcq) conditionals.

Thanks,

Bart.