scsi: hisi_sas: optimise the usage of DQ locking

In the DQ tasklet processing it is not necessary to take the DQ lock, as
there is no contention between adding slots to the CQ and removing slots
from the matching DQ.

In addition, since we run each DQ in a separate tasklet context, there
would be no possible contention between DQ processing running for the
same queue in parallel.

It is still necessary to take hisi_hba lock when free'ing slots.
Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

drivers/scsi/hisi_sas/hisi_sas_v2_hw.c

@@ -3151,14 +3151,12 @@ static void cq_tasklet_v2_hw(unsigned long val)
 	struct hisi_sas_complete_v2_hdr *complete_queue;
 	u32 rd_point = cq->rd_point, wr_point, dev_id;
 	int queue = cq->id;
-	struct hisi_sas_dq *dq = &hisi_hba->dq[queue];
 
 	if (unlikely(hisi_hba->reject_stp_links_msk))
 		phys_try_accept_stp_links_v2_hw(hisi_hba);
 
 	complete_queue = hisi_hba->complete_hdr[queue];
 
-	spin_lock(&dq->lock);
 	wr_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_WR_PTR +
 				   (0x14 * queue));
 
@@ -3208,7 +3206,6 @@ static void cq_tasklet_v2_hw(unsigned long val)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
-	spin_unlock(&dq->lock);
 }
 
 static irqreturn_t cq_interrupt_v2_hw(int irq_no, void *p)

drivers/scsi/hisi_sas/hisi_sas_v3_hw.c

@@ -1721,11 +1721,9 @@ static void cq_tasklet_v3_hw(unsigned long val)
 	struct hisi_sas_complete_v3_hdr *complete_queue;
 	u32 rd_point = cq->rd_point, wr_point;
 	int queue = cq->id;
-	struct hisi_sas_dq *dq = &hisi_hba->dq[queue];
 
 	complete_queue = hisi_hba->complete_hdr[queue];
 
-	spin_lock(&dq->lock);
 	wr_point = hisi_sas_read32(hisi_hba, COMPL_Q_0_WR_PTR +
 				   (0x14 * queue));
 
@@ -1752,7 +1750,6 @@ static void cq_tasklet_v3_hw(unsigned long val)
 	/* update rd_point */
 	cq->rd_point = rd_point;
 	hisi_sas_write32(hisi_hba, COMPL_Q_0_RD_PTR + (0x14 * queue), rd_point);
-	spin_unlock(&dq->lock);
 }
 
 static irqreturn_t cq_interrupt_v3_hw(int irq_no, void *p)