Patch "IB/SRP: Avoid using IB_MR_TYPE_SG_GAPS" has been added to the 4.9-stable tree

This is a note to let you know that I've just added the patch titled

IB/SRP: Avoid using IB_MR_TYPE_SG_GAPS

to the 4.9-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary

The filename of the patch is:
ib-srp-avoid-using-ib_mr_type_sg_gaps.patch
and it can be found in the queue-4.9 subdirectory.

If you, or anyone else, feels it should not be added to the stable tree, please let <[email protected]> know about it.

From: Bart Van Assche <[email protected]>
Date: Tue, 14 Feb 2017 10:56:29 -0800
Subject: IB/SRP: Avoid using IB_MR_TYPE_SG_GAPS

From: Bart Van Assche <[email protected]>

commit d6c58dc40fec35ff6cdb350b53bce0fcf9143709 upstream.

Tests have shown that the following error message is reported when using SG-GAPS registration with an mlx5 adapter:

scsi host1: ib_srp: failed RECV status WR flushed (5) for CQE ffff880bd4270eb0
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 0f007806 2500002a ad9fafd1
scsi host1: ib_srp: reconnect succeeded
mlx5_0:dump_cqe:262:(pid 7369): dump error cqe
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 00000000 00000000 00000000
00000000 0f007806 25000032 00105dd0
scsi host1: ib_srp: failed FAST REG status memory management operation error (6) for CQE ffff880b92860138

Hence avoid using SG-GAPS memory registrations. Additionally, always configure the blk_queue_virt_boundary() to avoid to trigger a mapping failure when using adapters that support SG-GAPS (e.g. mlx5).

---
 drivers/infiniband/ulp/srp/ib_srp.c |   12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

@@ -366,7 +366,6 @@ static struct srp_fr_pool *srp_create_fr
 	struct srp_fr_desc *d;
 	struct ib_mr *mr;
 	int i, ret = -EINVAL;
-	enum ib_mr_type mr_type;
 
 	if (pool_size <= 0)
 		goto err;

@@ -380,13 +379,9 @@ static struct srp_fr_pool *srp_create_fr
 	spin_lock_init(&pool->lock);
 	INIT_LIST_HEAD(&pool->free_list);
 
-	if (device->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG)
-		mr_type = IB_MR_TYPE_SG_GAPS;
-	else
-		mr_type = IB_MR_TYPE_MEM_REG;
-
 	for (i = 0, d = &pool->desc[0]; i < pool->size; i++, d++) {
-		mr = ib_alloc_mr(pd, mr_type, max_page_list_len);
+		mr = ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG,
+				 max_page_list_len);
 		if (IS_ERR(mr)) {
 			ret = PTR_ERR(mr);
 			goto destroy_pool;

@@ -2652,9 +2647,8 @@ static int srp_slave_alloc(struct scsi_d
 	struct Scsi_Host *shost = sdev->host;
 	struct srp_target_port *target = host_to_target(shost);
 	struct srp_device *srp_dev = target->srp_host->srp_dev;
-	struct ib_device *ibdev = srp_dev->dev;
 
-	if (!(ibdev->attrs.device_cap_flags & IB_DEVICE_SG_GAPS_REG))
+	if (true)
 		blk_queue_virt_boundary(sdev->request_queue,
 					~srp_dev->mr_page_mask);
 

Patches currently in stable-queue which might be from [email protected] are

queue-4.9/ib-srp-avoid-that-duplicate-responses-trigger-a-kernel-bug.patch queue-4.9/ib-srp-fix-race-conditions-related-to-task-management.patch queue-4.9/ib-srp-avoid-using-ib_mr_type_sg_gaps.patch