[v5,15/16] ufs: core: mcq: Add completion support in poll

Message ID 9d638d7921db39e48de30d4913b28076fe86b6dd.1669176158.git.quic_asutoshd@quicinc.com
State New
Headers
Series [v5,01/16] ufs: core: Optimize duplicate code to read extended feature |

Commit Message

Asutosh Das Nov. 23, 2022, 4:10 a.m. UTC
  Complete cqe requests in poll. Assumption is that
several poll completion may happen in different CPUs
for the same completion queue. Hence a spin lock
protection is added.

Co-developed-by: Can Guo <quic_cang@quicinc.com>
Signed-off-by: Can Guo <quic_cang@quicinc.com>
Signed-off-by: Asutosh Das <quic_asutoshd@quicinc.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
---
 drivers/ufs/core/ufs-mcq.c     | 13 +++++++++++++
 drivers/ufs/core/ufshcd-priv.h |  2 ++
 drivers/ufs/core/ufshcd.c      |  7 +++++++
 include/ufs/ufshcd.h           |  2 ++
 4 files changed, 24 insertions(+)
  

Comments

Manivannan Sadhasivam Nov. 28, 2022, 5:02 p.m. UTC | #1
On Tue, Nov 22, 2022 at 08:10:28PM -0800, Asutosh Das wrote:
> Complete cqe requests in poll. Assumption is that
> several poll completion may happen in different CPUs
> for the same completion queue. Hence a spin lock
> protection is added.
> 
> Co-developed-by: Can Guo <quic_cang@quicinc.com>
> Signed-off-by: Can Guo <quic_cang@quicinc.com>
> Signed-off-by: Asutosh Das <quic_asutoshd@quicinc.com>

Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>

Thanks,
Mani

> Reviewed-by: Bart Van Assche <bvanassche@acm.org>
> ---
>  drivers/ufs/core/ufs-mcq.c     | 13 +++++++++++++
>  drivers/ufs/core/ufshcd-priv.h |  2 ++
>  drivers/ufs/core/ufshcd.c      |  7 +++++++
>  include/ufs/ufshcd.h           |  2 ++
>  4 files changed, 24 insertions(+)
> 
> diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
> index 365ad98..5311857 100644
> --- a/drivers/ufs/core/ufs-mcq.c
> +++ b/drivers/ufs/core/ufs-mcq.c
> @@ -387,6 +387,18 @@ unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
>  	return completed_reqs;
>  }
>  
> +unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
> +				       struct ufs_hw_queue *hwq)
> +{
> +	unsigned long completed_reqs;
> +
> +	spin_lock(&hwq->cq_lock);
> +	completed_reqs = ufshcd_mcq_poll_cqe_nolock(hba, hwq);
> +	spin_unlock(&hwq->cq_lock);
> +
> +	return completed_reqs;
> +}
> +
>  void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba)
>  {
>  	struct ufs_hw_queue *hwq;
> @@ -483,6 +495,7 @@ int ufshcd_mcq_init(struct ufs_hba *hba)
>  		hwq = &hba->uhq[i];
>  		hwq->max_entries = hba->nutrs;
>  		spin_lock_init(&hwq->sq_lock);
> +		spin_lock_init(&hwq->cq_lock);
>  	}
>  
>  	/* The very first HW queue serves device commands */
> diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h
> index c5b5bf3..73ce8a2 100644
> --- a/drivers/ufs/core/ufshcd-priv.h
> +++ b/drivers/ufs/core/ufshcd-priv.h
> @@ -75,6 +75,8 @@ unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
>  					 struct ufs_hw_queue *hwq);
>  struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba,
>  					   struct request *req);
> +unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
> +				       struct ufs_hw_queue *hwq);
>  
>  #define UFSHCD_MCQ_IO_QUEUE_OFFSET	1
>  #define SD_ASCII_STD true
> diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
> index 7fb7c5f..8416d42 100644
> --- a/drivers/ufs/core/ufshcd.c
> +++ b/drivers/ufs/core/ufshcd.c
> @@ -5453,6 +5453,13 @@ static int ufshcd_poll(struct Scsi_Host *shost, unsigned int queue_num)
>  	struct ufs_hba *hba = shost_priv(shost);
>  	unsigned long completed_reqs, flags;
>  	u32 tr_doorbell;
> +	struct ufs_hw_queue *hwq;
> +
> +	if (is_mcq_enabled(hba)) {
> +		hwq = &hba->uhq[queue_num + UFSHCD_MCQ_IO_QUEUE_OFFSET];
> +
> +		return ufshcd_mcq_poll_cqe_lock(hba, hwq);
> +	}
>  
>  	spin_lock_irqsave(&hba->outstanding_lock, flags);
>  	tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
> diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
> index d5fde64..a709391 100644
> --- a/include/ufs/ufshcd.h
> +++ b/include/ufs/ufshcd.h
> @@ -1069,6 +1069,7 @@ struct ufs_hba {
>   * @sq_lock: serialize submission queue access
>   * @cq_tail_slot: current slot to which CQ tail pointer is pointing
>   * @cq_head_slot: current slot to which CQ head pointer is pointing
> + * @cq_lock: Synchronize between multiple polling instances
>   */
>  struct ufs_hw_queue {
>  	void __iomem *mcq_sq_head;
> @@ -1086,6 +1087,7 @@ struct ufs_hw_queue {
>  	spinlock_t sq_lock;
>  	u32 cq_tail_slot;
>  	u32 cq_head_slot;
> +	spinlock_t cq_lock;
>  };
>  
>  static inline bool is_mcq_enabled(struct ufs_hba *hba)
> -- 
> 2.7.4
>
  

Patch

diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
index 365ad98..5311857 100644
--- a/drivers/ufs/core/ufs-mcq.c
+++ b/drivers/ufs/core/ufs-mcq.c
@@ -387,6 +387,18 @@  unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
 	return completed_reqs;
 }
 
+unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
+				       struct ufs_hw_queue *hwq)
+{
+	unsigned long completed_reqs;
+
+	spin_lock(&hwq->cq_lock);
+	completed_reqs = ufshcd_mcq_poll_cqe_nolock(hba, hwq);
+	spin_unlock(&hwq->cq_lock);
+
+	return completed_reqs;
+}
+
 void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba)
 {
 	struct ufs_hw_queue *hwq;
@@ -483,6 +495,7 @@  int ufshcd_mcq_init(struct ufs_hba *hba)
 		hwq = &hba->uhq[i];
 		hwq->max_entries = hba->nutrs;
 		spin_lock_init(&hwq->sq_lock);
+		spin_lock_init(&hwq->cq_lock);
 	}
 
 	/* The very first HW queue serves device commands */
diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h
index c5b5bf3..73ce8a2 100644
--- a/drivers/ufs/core/ufshcd-priv.h
+++ b/drivers/ufs/core/ufshcd-priv.h
@@ -75,6 +75,8 @@  unsigned long ufshcd_mcq_poll_cqe_nolock(struct ufs_hba *hba,
 					 struct ufs_hw_queue *hwq);
 struct ufs_hw_queue *ufshcd_mcq_req_to_hwq(struct ufs_hba *hba,
 					   struct request *req);
+unsigned long ufshcd_mcq_poll_cqe_lock(struct ufs_hba *hba,
+				       struct ufs_hw_queue *hwq);
 
 #define UFSHCD_MCQ_IO_QUEUE_OFFSET	1
 #define SD_ASCII_STD true
diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 7fb7c5f..8416d42 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -5453,6 +5453,13 @@  static int ufshcd_poll(struct Scsi_Host *shost, unsigned int queue_num)
 	struct ufs_hba *hba = shost_priv(shost);
 	unsigned long completed_reqs, flags;
 	u32 tr_doorbell;
+	struct ufs_hw_queue *hwq;
+
+	if (is_mcq_enabled(hba)) {
+		hwq = &hba->uhq[queue_num + UFSHCD_MCQ_IO_QUEUE_OFFSET];
+
+		return ufshcd_mcq_poll_cqe_lock(hba, hwq);
+	}
 
 	spin_lock_irqsave(&hba->outstanding_lock, flags);
 	tr_doorbell = ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
index d5fde64..a709391 100644
--- a/include/ufs/ufshcd.h
+++ b/include/ufs/ufshcd.h
@@ -1069,6 +1069,7 @@  struct ufs_hba {
  * @sq_lock: serialize submission queue access
  * @cq_tail_slot: current slot to which CQ tail pointer is pointing
  * @cq_head_slot: current slot to which CQ head pointer is pointing
+ * @cq_lock: Synchronize between multiple polling instances
  */
 struct ufs_hw_queue {
 	void __iomem *mcq_sq_head;
@@ -1086,6 +1087,7 @@  struct ufs_hw_queue {
 	spinlock_t sq_lock;
 	u32 cq_tail_slot;
 	u32 cq_head_slot;
+	spinlock_t cq_lock;
 };
 
 static inline bool is_mcq_enabled(struct ufs_hba *hba)