[PATCH v2 10/11] lpfc: Add missing memory barrier

[PATCH v2 10/11] lpfc: Add missing memory barrier

[James Smart]

On loosely ordered memory systems (PPC for example), the WQE elements
were being updated in memory, but not necessarily flushed before the
separate doorbell was written to hw which would cause hw to dma the
WQE element. Thus, the hardware occasionally received partially
updated WQE data.

Add the memory barrier after updating the WQE memory.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
---
v2:
  revised for checkpatch warning - comment before wmb()

 drivers/scsi/lpfc/lpfc_sli.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index d0ffcf3..5c8663f 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -120,6 +120,8 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe *wqe)
 	if (q->phba->sli3_options & LPFC_SLI4_PHWQ_ENABLED)
 		bf_set(wqe_wqid, &wqe->generic.wqe_com, q->queue_id);
 	lpfc_sli_pcimem_bcopy(wqe, temp_wqe, q->entry_size);
+	/* ensure WQE bcopy flushed before doorbell write */
+	wmb();
 
 	/* Update the host index before invoking device */
 	host_index = q->host_index;
-- 
2.5.0

Re: [PATCH v2 10/11] lpfc: Add missing memory barrier

[Hannes Reinecke]

On 12/20/2016 12:07 AM, James Smart wrote:
> 
> On loosely ordered memory systems (PPC for example), the WQE elements
> were being updated in memory, but not necessarily flushed before the
> separate doorbell was written to hw which would cause hw to dma the
> WQE element. Thus, the hardware occasionally received partially
> updated WQE data.
> 
> Add the memory barrier after updating the WQE memory.
> 
> Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
> Signed-off-by: James Smart <james.smart@broadcom.com>
> ---
> v2:
>   revised for checkpatch warning - comment before wmb()
> 
>  drivers/scsi/lpfc/lpfc_sli.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
> index d0ffcf3..5c8663f 100644
> --- a/drivers/scsi/lpfc/lpfc_sli.c
> +++ b/drivers/scsi/lpfc/lpfc_sli.c
> @@ -120,6 +120,8 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe *wqe)
>  	if (q->phba->sli3_options & LPFC_SLI4_PHWQ_ENABLED)
>  		bf_set(wqe_wqid, &wqe->generic.wqe_com, q->queue_id);
>  	lpfc_sli_pcimem_bcopy(wqe, temp_wqe, q->entry_size);
> +	/* ensure WQE bcopy flushed before doorbell write */
> +	wmb();
>  
>  	/* Update the host index before invoking device */
>  	host_index = q->host_index;
> 
Reviewed-by: Hannes Reinecke <hare@suse.com>

Cheers,

Hannes
-- 
Dr. Hannes Reinecke		   Teamlead Storage & Networking
hare@suse.de			               +49 911 74053 688
SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: F. Imendörffer, J. Smithard, J. Guild, D. Upmanyu, G. Norton
HRB 21284 (AG Nürnberg)

Re: [PATCH v2 10/11] lpfc: Add missing memory barrier

[Mauricio Faria de Oliveira]

On 12/19/2016 09:07 PM, James Smart wrote:
> On loosely ordered memory systems (PPC for example), the WQE elements
> were being updated in memory, but not necessarily flushed before the
> separate doorbell was written to hw which would cause hw to dma the
> WQE element. Thus, the hardware occasionally received partially
> updated WQE data.
>
> Add the memory barrier after updating the WQE memory.

Reviewed-by: Mauricio Faria de Oliveira <mauricfo@linux.vnet.ibm.com>

Martin, may you please flag this patch for stable?

Thank you,

-- 
Mauricio Faria de Oliveira
IBM Linux Technology Center