IB/mlx5: Collect signature error completion

This commit takes care of the generated signature error CQE generated by the HW (if happened). The underlying mlx5 driver will handle signature error completions and will mark the relevant memory region as dirty. Once the consumer gets the completion for the transaction, it must check for signature errors on signature memory region using a new lightweight verb ib_check_mr_status(). In case the user doesn't check for signature error (i.e. doesn't call ib_check_mr_status() with status check IB_MR_CHECK_SIG_STATUS), the memory region cannot be used for another signature operation (REG_SIG_MR work request will fail). Signed-off-by: Sagi Grimberg <sagig@mellanox.com> Signed-off-by: Roland Dreier <roland@purestorage.com>
2014-02-23 14:19:12 +02:00
--- 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;
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1431,6 +1431,7 @@ static int init_one(struct pci_dev *pdev,
 	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;
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -400,6 +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);
@@ -537,6 +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)
 {
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1038,6 +1038,11 @@ struct ib_mr *mlx5_ib_create_mr(struct ib_pd *pd,
 		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;
@@ -1188,3 +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;
+}
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -1784,6 +1784,7 @@ static __be64 sig_mkey_mask(void)
 	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		|
@@ -2219,13 +2220,14 @@ static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
 {
 	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 |
+	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)));
@@ -2255,7 +2257,8 @@ static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 	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) || unlikely(!qp->signature_en) ||
+	    unlikely(!sig_mr->sig->sig_status_checked))
 		return -EINVAL;

 	/* length of the protected region, data + protection */
@@ -2286,6 +2289,7 @@ static int set_sig_umr_wr(struct ib_send_wr *wr, struct mlx5_ib_qp *qp,
 	if (ret)
 		return ret;

+	sig_mr->sig->sig_status_checked = false;
 	return 0;
 }