Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull infiniband updates from Roland Dreier:
 "Main batch of InfiniBand/RDMA changes for 3.15:

   - The biggest change is core API extensions and mlx5 low-level driver
     support for handling DIF/DIX-style protection information, and the
     addition of PI support to the iSER initiator.  Target support will
     be arriving shortly through the SCSI target tree.

   - A nice simplification to the "umem" memory pinning library now that
     we have chained sg lists.  Kudos to Yishai Hadas for realizing our
     code didn't have to be so crazy.

   - Another nice simplification to the sg wrappers used by qib, ipath
     and ehca to handle their mapping of memory to adapter.

   - The usual batch of fixes to bugs found by static checkers etc.
     from intrepid people like Dan Carpenter and Yann Droneaud.

   - A large batch of cxgb4, ocrdma, qib driver updates"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (102 commits)
  RDMA/ocrdma: Unregister inet notifier when unloading ocrdma
  RDMA/ocrdma: Fix warnings about pointer <-> integer casts
  RDMA/ocrdma: Code clean-up
  RDMA/ocrdma: Display FW version
  RDMA/ocrdma: Query controller information
  RDMA/ocrdma: Support non-embedded mailbox commands
  RDMA/ocrdma: Handle CQ overrun error
  RDMA/ocrdma: Display proper value for max_mw
  RDMA/ocrdma: Use non-zero tag in SRQ posting
  RDMA/ocrdma: Memory leak fix in ocrdma_dereg_mr()
  RDMA/ocrdma: Increment abi version count
  RDMA/ocrdma: Update version string
  be2net: Add abi version between be2net and ocrdma
  RDMA/ocrdma: ABI versioning between ocrdma and be2net
  RDMA/ocrdma: Allow DPP QP creation
  RDMA/ocrdma: Read ASIC_ID register to select asic_gen
  RDMA/ocrdma: SQ and RQ doorbell offset clean up
  RDMA/ocrdma: EQ full catastrophe avoidance
  RDMA/cxgb4: Disable DSGL use by default
  RDMA/cxgb4: rx_data() needs to hold the ep mutex
  ...

7 files changed, 785 insertions, 84 deletions

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index b1705ce6eb8..62bb6b49dc1 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -366,6 +366,38 @@ static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
 	mlx5_buf_free(&dev->mdev, &buf->buf);
 }
 
+static void get_sig_err_item(struct mlx5_sig_err_cqe *cqe,
+			     struct ib_sig_err *item)
+{
+	u16 syndrome = be16_to_cpu(cqe->syndrome);
+
+#define GUARD_ERR   (1 << 13)
+#define APPTAG_ERR  (1 << 12)
+#define REFTAG_ERR  (1 << 11)
+
+	if (syndrome & GUARD_ERR) {
+		item->err_type = IB_SIG_BAD_GUARD;
+		item->expected = be32_to_cpu(cqe->expected_trans_sig) >> 16;
+		item->actual = be32_to_cpu(cqe->actual_trans_sig) >> 16;
+	} else
+	if (syndrome & REFTAG_ERR) {
+		item->err_type = IB_SIG_BAD_REFTAG;
+		item->expected = be32_to_cpu(cqe->expected_reftag);
+		item->actual = be32_to_cpu(cqe->actual_reftag);
+	} else
+	if (syndrome & APPTAG_ERR) {
+		item->err_type = IB_SIG_BAD_APPTAG;
+		item->expected = be32_to_cpu(cqe->expected_trans_sig) & 0xffff;
+		item->actual = be32_to_cpu(cqe->actual_trans_sig) & 0xffff;
+	} else {
+		pr_err("Got signature completion error with bad syndrome %04x\n",
+		       syndrome);
+	}
+
+	item->sig_err_offset = be64_to_cpu(cqe->err_offset);
+	item->key = be32_to_cpu(cqe->mkey);
+}
+
 static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 			 struct mlx5_ib_qp **cur_qp,
 			 struct ib_wc *wc)
@@ -375,6 +407,9 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	struct mlx5_cqe64 *cqe64;
 	struct mlx5_core_qp *mqp;
 	struct mlx5_ib_wq *wq;
+	struct mlx5_sig_err_cqe *sig_err_cqe;
+	struct mlx5_core_mr *mmr;
+	struct mlx5_ib_mr *mr;
 	uint8_t opcode;
 	uint32_t qpn;
 	u16 wqe_ctr;
@@ -475,6 +510,33 @@ repoll:
 			}
 		}
 		break;
+	case MLX5_CQE_SIG_ERR:
+		sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64;
+
+		read_lock(&dev->mdev.priv.mr_table.lock);
+		mmr = __mlx5_mr_lookup(&dev->mdev,
+				       mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey)));
+		if (unlikely(!mmr)) {
+			read_unlock(&dev->mdev.priv.mr_table.lock);
+			mlx5_ib_warn(dev, "CQE@CQ %06x for unknown MR %6x\n",
+				     cq->mcq.cqn, be32_to_cpu(sig_err_cqe->mkey));
+			return -EINVAL;
+		}
+
+		mr = to_mibmr(mmr);
+		get_sig_err_item(sig_err_cqe, &mr->sig->err_item);
+		mr->sig->sig_err_exists = true;
+		mr->sig->sigerr_count++;
+
+		mlx5_ib_warn(dev, "CQN: 0x%x Got SIGERR on key: 0x%x err_type %x err_offset %llx expected %x actual %x\n",
+			     cq->mcq.cqn, mr->sig->err_item.key,
+			     mr->sig->err_item.err_type,
+			     mr->sig->err_item.sig_err_offset,
+			     mr->sig->err_item.expected,
+			     mr->sig->err_item.actual);
+
+		read_unlock(&dev->mdev.priv.mr_table.lock);
+		goto repoll;
 	}
 
 	return 0;
diff --git a/drivers/infiniband/hw/mlx5/doorbell.c b/drivers/infiniband/hw/mlx5/doorbell.c
index 256a23344f2..ece028fc47d 100644
--- a/drivers/infiniband/hw/mlx5/doorbell.c
+++ b/drivers/infiniband/hw/mlx5/doorbell.c
@@ -47,7 +47,6 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
 			struct mlx5_db *db)
 {
 	struct mlx5_ib_user_db_page *page;
-	struct ib_umem_chunk *chunk;
 	int err = 0;
 
 	mutex_lock(&context->db_page_mutex);
@@ -75,8 +74,7 @@ int mlx5_ib_db_map_user(struct mlx5_ib_ucontext *context, unsigned long virt,
 	list_add(&page->list, &context->db_page_list);
 
 found:
-	chunk = list_entry(page->umem->chunk_list.next, struct ib_umem_chunk, list);
-	db->dma		= sg_dma_address(chunk->page_list) + (virt & ~PAGE_MASK);
+	db->dma = sg_dma_address(page->umem->sg_head.sgl) + (virt & ~PAGE_MASK);
 	db->u.user_page = page;
 	++page->refcnt;
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index bf900579ac0..fa6dc870ada 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -273,6 +273,15 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	if (flags & MLX5_DEV_CAP_FLAG_XRC)
 		props->device_cap_flags |= IB_DEVICE_XRC;
 	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
+	if (flags & MLX5_DEV_CAP_FLAG_SIG_HAND_OVER) {
+		props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER;
+		/* At this stage no support for signature handover */
+		props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 |
+				      IB_PROT_T10DIF_TYPE_2 |
+				      IB_PROT_T10DIF_TYPE_3;
+		props->sig_guard_cap = IB_GUARD_T10DIF_CRC |
+				       IB_GUARD_T10DIF_CSUM;
+	}
 
 	props->vendor_id	   = be32_to_cpup((__be32 *)(out_mad->data + 36)) &
 		0xffffff;
@@ -1423,12 +1432,15 @@ static int init_one(struct pci_dev *pdev,
 	dev->ib_dev.get_dma_mr		= mlx5_ib_get_dma_mr;
 	dev->ib_dev.reg_user_mr		= mlx5_ib_reg_user_mr;
 	dev->ib_dev.dereg_mr		= mlx5_ib_dereg_mr;
+	dev->ib_dev.destroy_mr		= mlx5_ib_destroy_mr;
 	dev->ib_dev.attach_mcast	= mlx5_ib_mcg_attach;
 	dev->ib_dev.detach_mcast	= mlx5_ib_mcg_detach;
 	dev->ib_dev.process_mad		= mlx5_ib_process_mad;
+	dev->ib_dev.create_mr		= mlx5_ib_create_mr;
 	dev->ib_dev.alloc_fast_reg_mr	= mlx5_ib_alloc_fast_reg_mr;
 	dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list;
 	dev->ib_dev.free_fast_reg_page_list  = mlx5_ib_free_fast_reg_page_list;
+	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
 
 	if (mdev->caps.flags & MLX5_DEV_CAP_FLAG_XRC) {
 		dev->ib_dev.alloc_xrcd = mlx5_ib_alloc_xrcd;
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 3a5322870b9..8499aec94db 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -44,16 +44,17 @@
 void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 			int *ncont, int *order)
 {
-	struct ib_umem_chunk *chunk;
 	unsigned long tmp;
 	unsigned long m;
-	int i, j, k;
+	int i, k;
 	u64 base = 0;
 	int p = 0;
 	int skip;
 	int mask;
 	u64 len;
 	u64 pfn;
+	struct scatterlist *sg;
+	int entry;
 
 	addr = addr >> PAGE_SHIFT;
 	tmp = (unsigned long)addr;
@@ -61,32 +62,31 @@ void mlx5_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift,
 	skip = 1 << m;
 	mask = skip - 1;
 	i = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; j++) {
-			len = sg_dma_len(&chunk->page_list[j]) >> PAGE_SHIFT;
-			pfn = sg_dma_address(&chunk->page_list[j]) >> PAGE_SHIFT;
-			for (k = 0; k < len; k++) {
-				if (!(i & mask)) {
-					tmp = (unsigned long)pfn;
-					m = min(m, find_first_bit(&tmp, sizeof(tmp)));
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		pfn = sg_dma_address(sg) >> PAGE_SHIFT;
+		for (k = 0; k < len; k++) {
+			if (!(i & mask)) {
+				tmp = (unsigned long)pfn;
+				m = min(m, find_first_bit(&tmp, sizeof(tmp)));
+				skip = 1 << m;
+				mask = skip - 1;
+				base = pfn;
+				p = 0;
+			} else {
+				if (base + p != pfn) {
+					tmp = (unsigned long)p;
+					m = find_first_bit(&tmp, sizeof(tmp));
 					skip = 1 << m;
 					mask = skip - 1;
 					base = pfn;
 					p = 0;
-				} else {
-					if (base + p != pfn) {
-						tmp = (unsigned long)p;
-						m = find_first_bit(&tmp, sizeof(tmp));
-						skip = 1 << m;
-						mask = skip - 1;
-						base = pfn;
-						p = 0;
-					}
 				}
-				p++;
-				i++;
 			}
+			p++;
+			i++;
 		}
+	}
 
 	if (i) {
 		m = min_t(unsigned long, ilog2(roundup_pow_of_two(i)), m);
@@ -112,32 +112,32 @@ void mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct ib_umem *umem,
 {
 	int shift = page_shift - PAGE_SHIFT;
 	int mask = (1 << shift) - 1;
-	struct ib_umem_chunk *chunk;
-	int i, j, k;
+	int i, k;
 	u64 cur = 0;
 	u64 base;
 	int len;
+	struct scatterlist *sg;
+	int entry;
 
 	i = 0;
-	list_for_each_entry(chunk, &umem->chunk_list, list)
-		for (j = 0; j < chunk->nmap; j++) {
-			len = sg_dma_len(&chunk->page_list[j]) >> PAGE_SHIFT;
-			base = sg_dma_address(&chunk->page_list[j]);
-			for (k = 0; k < len; k++) {
-				if (!(i & mask)) {
-					cur = base + (k << PAGE_SHIFT);
-					if (umr)
-						cur |= 3;
+	for_each_sg(umem->sg_head.sgl, sg, umem->nmap, entry) {
+		len = sg_dma_len(sg) >> PAGE_SHIFT;
+		base = sg_dma_address(sg);
+		for (k = 0; k < len; k++) {
+			if (!(i & mask)) {
+				cur = base + (k << PAGE_SHIFT);
+				if (umr)
+					cur |= 3;
 
-					pas[i >> shift] = cpu_to_be64(cur);
-					mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
-						    i >> shift, be64_to_cpu(pas[i >> shift]));
-				}  else
-					mlx5_ib_dbg(dev, "=====> 0x%llx\n",
-						    base + (k << PAGE_SHIFT));
-				i++;
-			}
+				pas[i >> shift] = cpu_to_be64(cur);
+				mlx5_ib_dbg(dev, "pas[%d] 0x%llx\n",
+					    i >> shift, be64_to_cpu(pas[i >> shift]));
+			}  else
+				mlx5_ib_dbg(dev, "=====> 0x%llx\n",
+					    base + (k << PAGE_SHIFT));
+			i++;
 		}
+	}
 }
 
 int mlx5_ib_get_buf_offset(u64 addr, int page_shift, u32 *offset)
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index 389e3196577..50541586e0a 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -189,6 +189,9 @@ struct mlx5_ib_qp {
 
 	int			create_type;
 	u32			pa_lkey;
+
+	/* Store signature errors */
+	bool			signature_en;
 };
 
 struct mlx5_ib_cq_buf {
@@ -265,6 +268,7 @@ struct mlx5_ib_mr {
 	enum ib_wc_status	status;
 	struct mlx5_ib_dev     *dev;
 	struct mlx5_create_mkey_mbox_out out;
+	struct mlx5_core_sig_ctx    *sig;
 };
 
 struct mlx5_ib_fast_reg_page_list {
@@ -396,6 +400,11 @@ static inline struct mlx5_ib_qp *to_mibqp(struct mlx5_core_qp *mqp)
 	return container_of(mqp, struct mlx5_ib_qp, mqp);
 }
 
+static inline struct mlx5_ib_mr *to_mibmr(struct mlx5_core_mr *mmr)
+{
+	return container_of(mmr, struct mlx5_ib_mr, mmr);
+}
+
 static inline struct mlx5_ib_pd *to_mpd(struct ib_pd *ibpd)
 {
 	return container_of(ibpd, struct mlx5_ib_pd, ibpd);
@@ -495,6 +504,9 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 				  u64 virt_addr, int access_flags,
 				  struct ib_udata *udata);
 int mlx5_ib_dereg_mr(struct ib_mr *ibmr);
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr);
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+				struct ib_mr_init_attr *mr_init_attr);
 struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 					int max_page_list_len);
 struct ib_fast_reg_page_list *mlx5_ib_alloc_fast_reg_page_list(struct ib_device *ibdev,
@@ -530,6 +542,8 @@ int mlx5_mr_cache_init(struct mlx5_ib_dev *dev);
 int mlx5_mr_cache_cleanup(struct mlx5_ib_dev *dev);
 int mlx5_mr_ib_cont_pages(struct ib_umem *umem, u64 addr, int *count, int *shift);
 void mlx5_umr_cq_handler(struct ib_cq *cq, void *cq_context);
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+			    struct ib_mr_status *mr_status);
 
 static inline void init_query_mad(struct ib_smp *mad)
 {
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 7c95ca1f0c2..81392b26d07 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -992,6 +992,122 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr)
 	return 0;
 }
 
+struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
+				struct ib_mr_init_attr *mr_init_attr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(pd->device);
+	struct mlx5_create_mkey_mbox_in *in;
+	struct mlx5_ib_mr *mr;
+	int access_mode, err;
+	int ndescs = roundup(mr_init_attr->max_reg_descriptors, 4);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	in = kzalloc(sizeof(*in), GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	in->seg.status = 1 << 6; /* free */
+	in->seg.xlt_oct_size = cpu_to_be32(ndescs);
+	in->seg.qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
+	in->seg.flags_pd = cpu_to_be32(to_mpd(pd)->pdn);
+	access_mode = MLX5_ACCESS_MODE_MTT;
+
+	if (mr_init_attr->flags & IB_MR_SIGNATURE_EN) {
+		u32 psv_index[2];
+
+		in->seg.flags_pd = cpu_to_be32(be32_to_cpu(in->seg.flags_pd) |
+							   MLX5_MKEY_BSF_EN);
+		in->seg.bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+		mr->sig = kzalloc(sizeof(*mr->sig), GFP_KERNEL);
+		if (!mr->sig) {
+			err = -ENOMEM;
+			goto err_free_in;
+		}
+
+		/* create mem & wire PSVs */
+		err = mlx5_core_create_psv(&dev->mdev, to_mpd(pd)->pdn,
+					   2, psv_index);
+		if (err)
+			goto err_free_sig;
+
+		access_mode = MLX5_ACCESS_MODE_KLM;
+		mr->sig->psv_memory.psv_idx = psv_index[0];
+		mr->sig->psv_wire.psv_idx = psv_index[1];
+
+		mr->sig->sig_status_checked = true;
+		mr->sig->sig_err_exists = false;
+		/* Next UMR, Arm SIGERR */
+		++mr->sig->sigerr_count;
+	}
+
+	in->seg.flags = MLX5_PERM_UMR_EN | access_mode;
+	err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in, sizeof(*in),
+				    NULL, NULL, NULL);
+	if (err)
+		goto err_destroy_psv;
+
+	mr->ibmr.lkey = mr->mmr.key;
+	mr->ibmr.rkey = mr->mmr.key;
+	mr->umem = NULL;
+	kfree(in);
+
+	return &mr->ibmr;
+
+err_destroy_psv:
+	if (mr->sig) {
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_memory.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+				     mr->sig->psv_memory.psv_idx);
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_wire.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+				     mr->sig->psv_wire.psv_idx);
+	}
+err_free_sig:
+	kfree(mr->sig);
+err_free_in:
+	kfree(in);
+err_free:
+	kfree(mr);
+	return ERR_PTR(err);
+}
+
+int mlx5_ib_destroy_mr(struct ib_mr *ibmr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibmr->device);
+	struct mlx5_ib_mr *mr = to_mmr(ibmr);
+	int err;
+
+	if (mr->sig) {
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_memory.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy mem psv %d\n",
+				     mr->sig->psv_memory.psv_idx);
+		if (mlx5_core_destroy_psv(&dev->mdev,
+					  mr->sig->psv_wire.psv_idx))
+			mlx5_ib_warn(dev, "failed to destroy wire psv %d\n",
+				     mr->sig->psv_wire.psv_idx);
+		kfree(mr->sig);
+	}
+
+	err = mlx5_core_destroy_mkey(&dev->mdev, &mr->mmr);
+	if (err) {
+		mlx5_ib_warn(dev, "failed to destroy mkey 0x%x (%d)\n",
+			     mr->mmr.key, err);
+		return err;
+	}
+
+	kfree(mr);
+
+	return err;
+}
+
 struct ib_mr *mlx5_ib_alloc_fast_reg_mr(struct ib_pd *pd,
 					int max_page_list_len)
 {
@@ -1077,3 +1193,44 @@ void mlx5_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list)
 	kfree(mfrpl->ibfrpl.page_list);
 	kfree(mfrpl);
 }
+
+int mlx5_ib_check_mr_status(struct ib_mr *ibmr, u32 check_mask,
+			    struct ib_mr_status *mr_status)
+{
+	struct mlx5_ib_mr *mmr = to_mmr(ibmr);
+	int ret = 0;
+
+	if (check_mask & ~IB_MR_CHECK_SIG_STATUS) {
+		pr_err("Invalid status check mask\n");
+		ret = -EINVAL;
+		goto done;
+	}
+
+	mr_status->fail_status = 0;
+	if (check_mask & IB_MR_CHECK_SIG_STATUS) {
+		if (!mmr->sig) {
+			ret = -EINVAL;
+			pr_err("signature status check requested on a non-signature enabled MR\n");
+			goto done;
+		}
+
+		mmr->sig->sig_status_checked = true;
+		if (!mmr->sig->sig_err_exists)
+			goto done;
+
+		if (ibmr->lkey == mmr->sig->err_item.key)
+			memcpy(&mr_status->sig_err, &mmr->sig->err_item,
+			       sizeof(mr_status->sig_err));
+		else {
+			mr_status->sig_err.err_type = IB_SIG_BAD_GUARD;
+			mr_status->sig_err.sig_err_offset = 0;
+			mr_status->sig_err.key = mmr->sig->err_item.key;
+		}
+
+		mmr->sig->sig_err_exists = false;
+		mr_status->fail_status |= IB_MR_CHECK_SIG_STATUS;
+	}
+
+done:
+	return ret;
+}
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 7dfe8a1c84c..ae788d27b93 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -256,8 +256,11 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
 	}
 
 	size += attr->cap.max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-
-	return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
+	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN &&
+	    ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB) < MLX5_SIG_WQE_SIZE)
+			return MLX5_SIG_WQE_SIZE;
+	else
+		return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
 }
 
 static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
@@ -284,6 +287,9 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 		sizeof(struct mlx5_wqe_inline_seg);
 	attr->cap.max_inline_data = qp->max_inline_data;
 
+	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN)
+		qp->signature_en = true;
+
 	wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size);
 	qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB;
 	if (qp->sq.wqe_cnt > dev->mdev.caps.max_wqes) {
@@ -665,7 +671,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	int err;
 
 	uuari = &dev->mdev.priv.uuari;
-	if (init_attr->create_flags)
+	if (init_attr->create_flags & ~IB_QP_CREATE_SIGNATURE_EN)
 		return -EINVAL;
 
 	if (init_attr->qp_type == MLX5_IB_QPT_REG_UMR)
@@ -1771,6 +1777,27 @@ static __be64 frwr_mkey_mask(void)
 	return cpu_to_be64(result);
 }
 
+static __be64 sig_mkey_mask(void)
+{
+	u64 result;
+
+	result = MLX5_MKEY_MASK_LEN		|
+		MLX5_MKEY_MASK_PAGE_SIZE	|
+		MLX5_MKEY_MASK_START_ADDR	|
+		MLX5_MKEY_MASK_EN_SIGERR	|
+		MLX5_MKEY_MASK_EN_RINVAL	|
+		MLX5_MKEY_MASK_KEY		|
+		MLX5_MKEY_MASK_LR		|
+		MLX5_MKEY_MASK_LW		|
+		MLX5_MKEY_MASK_RR		|
+		MLX5_MKEY_MASK_RW		|
+		MLX5_MKEY_MASK_SMALL_FENCE	|
+		MLX5_MKEY_MASK_FREE		|
+		MLX5_MKEY_MASK_BSF_EN;
+
+	return cpu_to_be64(result);
+}
+
 static void set_frwr_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 				 struct ib_send_wr *wr, int li)
 {
@@ -1826,7 +1853,7 @@ static u8 get_umr_flags(int acc)
 	       (acc & IB_ACCESS_REMOTE_WRITE  ? MLX5_PERM_REMOTE_WRITE : 0) |
 	       (acc & IB_ACCESS_REMOTE_READ   ? MLX5_PERM_REMOTE_READ  : 0) |
 	       (acc & IB_ACCESS_LOCAL_WRITE   ? MLX5_PERM_LOCAL_WRITE  : 0) |
-		MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN | MLX5_ACCESS_MODE_MTT;
+		MLX5_PERM_LOCAL_READ | MLX5_PERM_UMR_EN;
 }
 
 static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
@@ -1838,7 +1865,8 @@ static void set_mkey_segment(struct mlx5_mkey_seg *seg, struct ib_send_wr *wr,
 		return;
 	}
 
-	seg->flags = get_umr_flags(wr->wr.fast_reg.access_flags);
+	seg->flags = get_umr_flags(wr->wr.fast_reg.access_flags) |
+		     MLX5_ACCESS_MODE_MTT;
 	*writ = seg->flags & (MLX5_PERM_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE);
 	seg->qpn_mkey7_0 = cpu_to_be32((wr->wr.fast_reg.rkey & 0xff) | 0xffffff00);
 	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL);
@@ -1954,6 +1982,342 @@ static int set_data_inl_seg(struct mlx5_ib_qp *qp, struct ib_send_wr *wr,
 	return 0;
 }
 
+static u16 prot_field_size(enum ib_signature_type type)
+{
+	switch (type) {
+	case IB_SIG_TYPE_T10_DIF:
+		return MLX5_DIF_SIZE;
+	default:
+		return 0;
+	}
+}
+
+static u8 bs_selector(int block_size)
+{
+	switch (block_size) {
+	case 512:	    return 0x1;
+	case 520:	    return 0x2;
+	case 4096:	    return 0x3;
+	case 4160:	    return 0x4;
+	case 1073741824:    return 0x5;
+	default:	    return 0;
+	}
+}
+
+static int format_selector(struct ib_sig_attrs *attr,
+			   struct ib_sig_domain *domain,
+			   int *selector)
+{
+
+#define FORMAT_DIF_NONE		0
+#define FORMAT_DIF_CRC_INC	8
+#define FORMAT_DIF_CRC_NO_INC	12
+#define FORMAT_DIF_CSUM_INC	13
+#define FORMAT_DIF_CSUM_NO_INC	14
+
+	switch (domain->sig.dif.type) {
+	case IB_T10DIF_NONE:
+		/* No DIF */
+		*selector = FORMAT_DIF_NONE;
+		break;
+	case IB_T10DIF_TYPE1: /* Fall through */
+	case IB_T10DIF_TYPE2:
+		switch (domain->sig.dif.bg_type) {
+		case IB_T10DIF_CRC:
+			*selector = FORMAT_DIF_CRC_INC;
+			break;
+		case IB_T10DIF_CSUM:
+			*selector = FORMAT_DIF_CSUM_INC;
+			break;
+		default:
+			return 1;
+		}
+		break;
+	case IB_T10DIF_TYPE3:
+		switch (domain->sig.dif.bg_type) {
+		case IB_T10DIF_CRC:
+			*selector = domain->sig.dif.type3_inc_reftag ?
+					   FORMAT_DIF_CRC_INC :
+					   FORMAT_DIF_CRC_NO_INC;
+			break;
+		case IB_T10DIF_CSUM:
+			*selector = domain->sig.dif.type3_inc_reftag ?
+					   FORMAT_DIF_CSUM_INC :
+					   FORMAT_DIF_CSUM_NO_INC;
+			break;
+		default:
+			return 1;
+		}
+		break;
+	default:
+		return 1;
+	}
+
+	return 0;
+}
+
+static int mlx5_set_bsf(struct ib_mr *sig_mr,
+			struct ib_sig_attrs *sig_attrs,
+			struct mlx5_bsf *bsf, u32 data_size)
+{
+	struct mlx5_core_sig_ctx *msig = to_mmr(sig_mr)->sig;
+	struct mlx5_bsf_basic *basic = &bsf->basic;
+	struct ib_sig_domain *mem = &sig_attrs->mem;
+	struct ib_sig_domain *wire = &sig_attrs->wire;
+	int ret, selector;
+
+	switch (sig_attrs->mem.sig_type) {
+	case IB_SIG_TYPE_T10_DIF:
+		if (sig_attrs->wire.sig_type != IB_SIG_TYPE_T10_DIF)
+			return -EINVAL;
+
+		/* Input domain check byte mask */
+		basic->check_byte_mask = sig_attrs->check_mask;
+		if (mem->sig.dif.pi_interval == wire->sig.dif.pi_interval &&
+		    mem->sig.dif.type == wire->sig.dif.type) {
+			/* Same block structure */
+			basic->bsf_size_sbs = 1 << 4;
+			if (mem->sig.dif.bg_type == wire->sig.dif.bg_type)
+				basic->wire.copy_byte_mask = 0xff;
+			else
+				basic->wire.copy_byte_mask = 0x3f;
+		} else
+			basic->wire.bs_selector = bs_selector(wire->sig.dif.pi_interval);
+
+		basic->mem.bs_selector = bs_selector(mem->sig.dif.pi_interval);
+		basic->raw_data_size = cpu_to_be32(data_size);
+
+		ret = format_selector(sig_attrs, mem, &selector);
+		if (ret)
+			return -EINVAL;
+		basic->m_bfs_psv = cpu_to_be32(selector << 24 |
+					       msig->psv_memory.psv_idx);
+
+		ret = format_selector(sig_attrs, wire, &selector);
+		if (ret)
+			return -EINVAL;
+		basic->w_bfs_psv = cpu_to_be32(selector << 24 |
+					       msig->psv_wire.psv_idx);
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int set_sig_data_segment(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+				void **seg, int *size)
+{
+	struct ib_sig_attrs *sig_attrs = wr->wr.sig_handover.sig_attrs;
+	struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+	struct mlx5_bsf *bsf;
+	u32 data_len = wr->sg_list->length;
+	u32 data_key = wr->sg_list->lkey;
+	u64 data_va = wr->sg_list->addr;
+	int ret;
+	int wqe_size;
+
+	if (!wr->wr.sig_handover.prot) {
+		/**
+		 * Source domain doesn't contain signature information
+		 * So need construct:
+		 *                  ------------------
+		 *                 |     data_klm     |
+		 *                  ------------------
+		 *                 |       BSF        |
+		 *                  ------------------
+		 **/
+		struct mlx5_klm *data_klm = *seg;
+
+		data_klm->bcount = cpu_to_be32(data_len);
+		data_klm->key = cpu_to_be32(data_key);
+		data_klm->va = cpu_to_be64(data_va);
+		wqe_size = ALIGN(sizeof(*data_klm), 64);
+	} else {
+		/**
+		 * Source domain contains signature information
+		 * So need construct a strided block format:
+		 *               ---------------------------
+		 *              |     stride_block_ctrl     |
+		 *               ---------------------------
+		 *              |          data_klm         |
+		 *               ---------------------------
+		 *              |          prot_klm         |
+		 *               ---------------------------
+		 *              |             BSF           |
+		 *               ---------------------------
+		 **/
+		struct mlx5_stride_block_ctrl_seg *sblock_ctrl;
+		struct mlx5_stride_block_entry *data_sentry;
+		struct mlx5_stride_block_entry *prot_sentry;
+		u32 prot_key = wr->wr.sig_handover.prot->lkey;
+		u64 prot_va = wr->wr.sig_handover.prot->addr;
+		u16 block_size = sig_attrs->mem.sig.dif.pi_interval;
+		int prot_size;
+
+		sblock_ctrl = *seg;
+		data_sentry = (void *)sblock_ctrl + sizeof(*sblock_ctrl);
+		prot_sentry = (void *)data_sentry + sizeof(*data_sentry);
+
+		prot_size = prot_field_size(sig_attrs->mem.sig_type);
+		if (!prot_size) {
+			pr_err("Bad block size given: %u\n", block_size);
+			return -EINVAL;
+		}
+		sblock_ctrl->bcount_per_cycle = cpu_to_be32(block_size +
+							    prot_size);
+		sblock_ctrl->op = cpu_to_be32(MLX5_STRIDE_BLOCK_OP);
+		sblock_ctrl->repeat_count = cpu_to_be32(data_len / block_size);
+		sblock_ctrl->num_entries = cpu_to_be16(2);
+
+		data_sentry->bcount = cpu_to_be16(block_size);
+		data_sentry->key = cpu_to_be32(data_key);
+		data_sentry->va = cpu_to_be64(data_va);
+		prot_sentry->bcount = cpu_to_be16(prot_size);
+		prot_sentry->key = cpu_to_be32(prot_key);
+
+		if (prot_key == data_key && prot_va == data_va) {
+			/**
+			 * The data and protection are interleaved
+			 * in a single memory region
+			 **/
+			prot_sentry->va = cpu_to_be64(data_va + block_size);
+			prot_sentry->stride = cpu_to_be16(block_size + prot_size);
+			data_sentry->stride = prot_sentry->stride;
+		} else {
+			/* The data and protection are two different buffers */
+			prot_sentry->va = cpu_to_be64(prot_va);
+			data_sentry->stride = cpu_to_be16(block_size);
+			prot_sentry->stride = cpu_to_be16(prot_size);
+		}
+		wqe_size = ALIGN(sizeof(*sblock_ctrl) + sizeof(*data_sentry) +
+				 sizeof(*prot_sentry), 64);
+	}
+
+	*seg += wqe_size;
+	*size += wqe_size / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	bsf = *seg;
+	ret = mlx5_set_bsf(sig_mr, sig_attrs, bsf, data_len);
+	if (ret)
+		return -EINVAL;
+
+	*seg += sizeof(*bsf);
+	*size += sizeof(*bsf) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	return 0;
+}
+
+static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
+				 struct ib_send_wr *wr, u32 nelements,
+				 u32 length, u32 pdn)
+{
+	struct ib_mr *sig_mr = wr->wr.sig_handover.sig_mr;
+	u32 sig_key = sig_mr->rkey;
+	u8 sigerr = to_mmr(sig_mr)->sig->sigerr_count & 1;
+
+	memset(seg, 0, sizeof(*seg));
+
+	seg->flags = get_umr_flags(wr->wr.sig_handover.access_flags) |
+				   MLX5_ACCESS_MODE_KLM;
+	seg->qpn_mkey7_0 = cpu_to_be32((sig_key & 0xff) | 0xffffff00);
+	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL | sigerr << 26 |
+				    MLX5_MKEY_BSF_EN | pdn);
+	seg->len = cpu_to_be64(length);
+	seg->xlt_oct_size = cpu_to_be32(be16_to_cpu(get_klm_octo(nelements)));
+	seg->bsfs_octo_size = cpu_to_be32(MLX5_MKEY_BSF_OCTO_SIZE);
+}
+
+static void set_sig_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
+				struct ib_send_wr *wr, u32 nelements)
+{
+	memset(umr, 0, sizeof(*umr));
+
+	umr->flags = MLX5_FLAGS_INLINE | MLX5_FLAGS_CHECK_FREE;
+	umr->klm_octowords = get_klm_octo(nelements);
+	umr->bsf_octowords = cpu_to_be16(MLX5_MKEY_BSF_OCTO_SIZE);
+	umr->mkey_mask = sig_mkey_mask();
+}
+
+
+static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
+			  void **seg, int *size)
+{
+	struct mlx5_ib_mr *sig_mr = to_mmr(wr->wr.sig_handover.sig_mr);
+	u32 pdn = get_pd(qp)->pdn;
+	u32 klm_oct_size;
+	int region_len, ret;
+
+	if (unlikely(wr->num_sge != 1) ||
+	    unlikely(wr->wr.sig_handover.access_flags &
+		     IB_ACCESS_REMOTE_ATOMIC) ||
+	    unlikely(!sig_mr->sig) || unlikely(!qp->signature_en) ||
+	    unlikely(!sig_mr->sig->sig_status_checked))
+		return -EINVAL;
+
+	/* length of the protected region, data + protection */
+	region_len = wr->sg_list->length;
+	if (wr->wr.sig_handover.prot)
+		region_len += wr->wr.sig_handover.prot->length;
+
+	/**
+	 * KLM octoword size - if protection was provided
+	 * then we use strided block format (3 octowords),
+	 * else we use single KLM (1 octoword)
+	 **/
+	klm_oct_size = wr->wr.sig_handover.prot ? 3 : 1;
+
+	set_sig_umr_segment(*seg, wr, klm_oct_size);
+	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
+	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	set_sig_mkey_segment(*seg, wr, klm_oct_size, region_len, pdn);
+	*seg += sizeof(struct mlx5_mkey_seg);
+	*size += sizeof(struct mlx5_mkey_seg) / 16;
+	if (unlikely((*seg == qp->sq.qend)))
+		*seg = mlx5_get_send_wqe(qp, 0);
+
+	ret = set_sig_data_segment(wr, qp, seg, size);
+	if (ret)
+		return ret;
+
+	sig_mr->sig->sig_status_checked = false;
+	return 0;
+}
+
+static int set_psv_wr(struct ib_sig_domain *domain,
+		      u32 psv_idx, void **seg, int *size)
+{
+	struct mlx5_seg_set_psv *psv_seg = *seg;
+
+	memset(psv_seg, 0, sizeof(*psv_seg));
+	psv_seg->psv_num = cpu_to_be32(psv_idx);
+	switch (domain->sig_type) {
+	case IB_SIG_TYPE_T10_DIF:
+		psv_seg->transient_sig = cpu_to_be32(domain->sig.dif.bg << 16 |
+						     domain->sig.dif.app_tag);
+		psv_seg->ref_tag = cpu_to_be32(domain->sig.dif.ref_tag);
+
+		*seg += sizeof(*psv_seg);
+		*size += sizeof(*psv_seg) / 16;
+		break;
+
+	default:
+		pr_err("Bad signature type given.\n");
+		return 1;
+	}
+
+	return 0;
+}
+
 static int set_frwr_li_wr(void **seg, struct ib_send_wr *wr, int *size,
 			  struct mlx5_core_dev *mdev, struct mlx5_ib_pd *pd, struct mlx5_ib_qp *qp)
 {
@@ -2041,6 +2405,59 @@ static u8 get_fence(u8 fence, struct ib_send_wr *wr)
 	}
 }
 
+static int begin_wqe(struct mlx5_ib_qp *qp, void **seg,
+		     struct mlx5_wqe_ctrl_seg **ctrl,
+		     struct ib_send_wr *wr, int *idx,
+		     int *size, int nreq)
+{
+	int err = 0;
+
+	if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
+		err = -ENOMEM;
+		return err;
+	}
+
+	*idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
+	*seg = mlx5_get_send_wqe(qp, *idx);
+	*ctrl = *seg;
+	*(uint32_t *)(*seg + 8) = 0;
+	(*ctrl)->imm = send_ieth(wr);
+	(*ctrl)->fm_ce_se = qp->sq_signal_bits |
+		(wr->send_flags & IB_SEND_SIGNALED ?
+		 MLX5_WQE_CTRL_CQ_UPDATE : 0) |
+		(wr->send_flags & IB_SEND_SOLICITED ?
+		 MLX5_WQE_CTRL_SOLICITED : 0);
+
+	*seg += sizeof(**ctrl);
+	*size = sizeof(**ctrl) / 16;
+
+	return err;
+}
+
+static void finish_wqe(struct mlx5_ib_qp *qp,
+		       struct mlx5_wqe_ctrl_seg *ctrl,
+		       u8 size, unsigned idx, u64 wr_id,
+		       int nreq, u8 fence, u8 next_fence,
+		       u32 mlx5_opcode)
+{
+	u8 opmod = 0;
+
+	ctrl->opmod_idx_opcode = cpu_to_be32(((u32)(qp->sq.cur_post) << 8) |
+					     mlx5_opcode | ((u32)opmod << 24));
+	ctrl->qpn_ds = cpu_to_be32(size | (qp->mqp.qpn << 8));
+	ctrl->fm_ce_se |= fence;
+	qp->fm_cache = next_fence;
+	if (unlikely(qp->wq_sig))
+		ctrl->signature = wq_sig(ctrl);
+
+	qp->sq.wrid[idx] = wr_id;
+	qp->sq.w_list[idx].opcode = mlx5_opcode;
+	qp->sq.wqe_head[idx] = qp->sq.head + nreq;
+	qp->sq.cur_post += DIV_ROUND_UP(size * 16, MLX5_SEND_WQE_BB);
+	qp->sq.w_list[idx].next = qp->sq.cur_post;
+}
+
+
 int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		      struct ib_send_wr **bad_wr)
 {
@@ -2048,13 +2465,13 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx5_core_dev *mdev = &dev->mdev;
 	struct mlx5_ib_qp *qp = to_mqp(ibqp);
+	struct mlx5_ib_mr *mr;
 	struct mlx5_wqe_data_seg *dpseg;
 	struct mlx5_wqe_xrc_seg *xrc;
 	struct mlx5_bf *bf = qp->bf;
 	int uninitialized_var(size);
 	void *qend = qp->sq.qend;
 	unsigned long flags;
-	u32 mlx5_opcode;
 	unsigned idx;
 	int err = 0;
 	int inl = 0;
@@ -2063,7 +2480,6 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	int nreq;
 	int i;
 	u8 next_fence = 0;
-	u8 opmod = 0;
 	u8 fence;
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
@@ -2076,36 +2492,23 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			goto out;
 		}
 
-		if (unlikely(mlx5_wq_overflow(&qp->sq, nreq, qp->ibqp.send_cq))) {
+		fence = qp->fm_cache;
+		num_sge = wr->num_sge;
+		if (unlikely(num_sge > qp->sq.max_gs)) {
 			mlx5_ib_warn(dev, "\n");
 			err = -ENOMEM;
 			*bad_wr = wr;
 			goto out;
 		}
 
-		fence = qp->fm_cache;
-		num_sge = wr->num_sge;
-		if (unlikely(num_sge > qp->sq.max_gs)) {
+		err = begin_wqe(qp, &seg, &ctrl, wr, &idx, &size, nreq);
+		if (err) {
 			mlx5_ib_warn(dev, "\n");
 			err = -ENOMEM;
 			*bad_wr = wr;
 			goto out;
 		}
 
-		idx = qp->sq.cur_post & (qp->sq.wqe_cnt - 1);
-		seg = mlx5_get_send_wqe(qp, idx);
-		ctrl = seg;
-		*(uint32_t *)(seg + 8) = 0;
-		ctrl->imm = send_ieth(wr);
-		ctrl->fm_ce_se = qp->sq_signal_bits |
-			(wr->send_flags & IB_SEND_SIGNALED ?
-			 MLX5_WQE_CTRL_CQ_UPDATE : 0) |
-			(wr->send_flags & IB_SEND_SOLICITED ?
-			 MLX5_WQE_CTRL_SOLICITED : 0);
-
-		seg += sizeof(*ctrl);
-		size = sizeof(*ctrl) / 16;
-
 		switch (ibqp->qp_type) {
 		case IB_QPT_XRC_INI:
 			xrc = seg;
@@ -2158,6 +2561,73 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 				num_sge = 0;
 				break;
 
+			case IB_WR_REG_SIG_MR:
+				qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR;
+				mr = to_mmr(wr->wr.sig_handover.sig_mr);
+
+				ctrl->imm = cpu_to_be32(mr->ibmr.rkey);
+				err = set_sig_umr_wr(wr, qp, &seg, &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_UMR);
+				/*
+				 * SET_PSV WQEs are not signaled and solicited
+				 * on error
+				 */
+				wr->send_flags &= ~IB_SEND_SIGNALED;
+				wr->send_flags |= IB_SEND_SOLICITED;
+				err = begin_wqe(qp, &seg, &ctrl, wr,
+						&idx, &size, nreq);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					err = -ENOMEM;
+					*bad_wr = wr;
+					goto out;
+				}
+
+				err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->mem,
+						 mr->sig->psv_memory.psv_idx, &seg,
+						 &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_SET_PSV);
+				err = begin_wqe(qp, &seg, &ctrl, wr,
+						&idx, &size, nreq);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					err = -ENOMEM;
+					*bad_wr = wr;
+					goto out;
+				}
+
+				next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+				err = set_psv_wr(&wr->wr.sig_handover.sig_attrs->wire,
+						 mr->sig->psv_wire.psv_idx, &seg,
+						 &size);
+				if (err) {
+					mlx5_ib_warn(dev, "\n");
+					*bad_wr = wr;
+					goto out;
+				}
+
+				finish_wqe(qp, ctrl, size, idx, wr->wr_id,
+					   nreq, get_fence(fence, wr),
+					   next_fence, MLX5_OPCODE_SET_PSV);
+				num_sge = 0;
+				goto skip_psv;
+
 			default:
 				break;
 			}
@@ -2238,22 +2708,10 @@ int mlx5_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			}
 		}
 
-		mlx5_opcode = mlx5_ib_opcode[wr->opcode];
-		ctrl->opmod_idx_opcode = cpu_to_be32(((u32)(qp->sq.cur_post) << 8)	|
-						     mlx5_opcode			|
-						     ((u32)opmod << 24));
-		ctrl->qpn_ds = cpu_to_be32(size | (qp->mqp.qpn << 8));
-		ctrl->fm_ce_se |= get_fence(fence, wr);
-		qp->fm_cache = next_fence;
-		if (unlikely(qp->wq_sig))
-			ctrl->signature = wq_sig(ctrl);
-
-		qp->sq.wrid[idx] = wr->wr_id;
-		qp->sq.w_list[idx].opcode = mlx5_opcode;
-		qp->sq.wqe_head[idx] = qp->sq.head + nreq;
-		qp->sq.cur_post += DIV_ROUND_UP(size * 16, MLX5_SEND_WQE_BB);
-		qp->sq.w_list[idx].next = qp->sq.cur_post;
-
+		finish_wqe(qp, ctrl, size, idx, wr->wr_id, nreq,
+			   get_fence(fence, wr), next_fence,
+			   mlx5_ib_opcode[wr->opcode]);
+skip_psv:
 		if (0)
 			dump_wqe(qp, idx, size);
 	}