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

Pull rdma updates from Jason Gunthorpe:
 "Small cycle, with some typical driver updates:

   - General code tidying in siw, hfi1, idrdma, usnic, hns rtrs and
     bnxt_re

   - Many small siw cleanups without an overeaching theme

   - Debugfs stats for hns

   - Fix a TX queue timeout in IPoIB and missed locking of the mcast
     list

   - Support more features of P7 devices in bnxt_re including a new work
     submission protocol

   - CQ interrupts for MANA

   - netlink stats for erdma

   - EFA multipath PCI support

   - Fix Incorrect MR invalidation in iser"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (66 commits)
  RDMA/bnxt_re: Fix error code in bnxt_re_create_cq()
  RDMA/efa: Add EFA query MR support
  IB/iser: Prevent invalidating wrong MR
  RDMA/erdma: Add hardware statistics support
  RDMA/erdma: Introduce dma pool for hardware responses of CMDQ requests
  IB/iser: iscsi_iser.h: fix kernel-doc warning and spellos
  RDMA/mana_ib: Add CQ interrupt support for RAW QP
  RDMA/mana_ib: query device capabilities
  RDMA/mana_ib: register RDMA device with GDMA
  RDMA/bnxt_re: Fix the sparse warnings
  RDMA/bnxt_re: Fix the offset for GenP7 adapters for user applications
  RDMA/bnxt_re: Share a page to expose per CQ info with userspace
  RDMA/bnxt_re: Add UAPI to share a page with user space
  IB/ipoib: Fix mcast list locking
  RDMA/mlx5: Expose register c0 for RDMA device
  net/mlx5: E-Switch, expose eswitch manager vport
  net/mlx5: Manage ICM type of SW encap
  RDMA/mlx5: Support handling of SW encap ICM area
  net/mlx5: Introduce indirect-sw-encap ICM properties
  RDMA/bnxt_re: Adds MSN table capability for Gen P7 adapters
  ...

5 files changed, 159 insertions, 2 deletions

diff --git a/drivers/infiniband/hw/erdma/erdma.h b/drivers/infiniband/hw/erdma/erdma.h
index f190111840e9..5df401a30cb9 100644
--- a/drivers/infiniband/hw/erdma/erdma.h
+++ b/drivers/infiniband/hw/erdma/erdma.h
@@ -212,6 +212,8 @@ struct erdma_dev {
 
 	atomic_t num_ctx;
 	struct list_head cep_list;
+
+	struct dma_pool *resp_pool;
 };
 
 static inline void *get_queue_entry(void *qbuf, u32 idx, u32 depth, u32 shift)
diff --git a/drivers/infiniband/hw/erdma/erdma_hw.h b/drivers/infiniband/hw/erdma/erdma_hw.h
index a155519a862f..3212a1222760 100644
--- a/drivers/infiniband/hw/erdma/erdma_hw.h
+++ b/drivers/infiniband/hw/erdma/erdma_hw.h
@@ -144,6 +144,7 @@ enum CMDQ_COMMON_OPCODE {
 	CMDQ_OPCODE_DESTROY_EQ = 1,
 	CMDQ_OPCODE_QUERY_FW_INFO = 2,
 	CMDQ_OPCODE_CONF_MTU = 3,
+	CMDQ_OPCODE_GET_STATS = 4,
 	CMDQ_OPCODE_CONF_DEVICE = 5,
 	CMDQ_OPCODE_ALLOC_DB = 8,
 	CMDQ_OPCODE_FREE_DB = 9,
@@ -355,6 +356,44 @@ struct erdma_cmdq_reflush_req {
 	u32 rq_pi;
 };
 
+#define ERDMA_HW_RESP_SIZE 256
+
+struct erdma_cmdq_query_req {
+	u64 hdr;
+	u32 rsvd;
+	u32 index;
+
+	u64 target_addr;
+	u32 target_length;
+};
+
+#define ERDMA_HW_RESP_MAGIC 0x5566
+
+struct erdma_cmdq_query_resp_hdr {
+	u16 magic;
+	u8 ver;
+	u8 length;
+
+	u32 index;
+	u32 rsvd[2];
+};
+
+struct erdma_cmdq_query_stats_resp {
+	struct erdma_cmdq_query_resp_hdr hdr;
+
+	u64 tx_req_cnt;
+	u64 tx_packets_cnt;
+	u64 tx_bytes_cnt;
+	u64 tx_drop_packets_cnt;
+	u64 tx_bps_meter_drop_packets_cnt;
+	u64 tx_pps_meter_drop_packets_cnt;
+	u64 rx_packets_cnt;
+	u64 rx_bytes_cnt;
+	u64 rx_drop_packets_cnt;
+	u64 rx_bps_meter_drop_packets_cnt;
+	u64 rx_pps_meter_drop_packets_cnt;
+};
+
 /* cap qword 0 definition */
 #define ERDMA_CMD_DEV_CAP_MAX_CQE_MASK GENMASK_ULL(47, 40)
 #define ERDMA_CMD_DEV_CAP_FLAGS_MASK GENMASK_ULL(31, 24)
diff --git a/drivers/infiniband/hw/erdma/erdma_main.c b/drivers/infiniband/hw/erdma/erdma_main.c
index 0880c79a978c..472939172f0c 100644
--- a/drivers/infiniband/hw/erdma/erdma_main.c
+++ b/drivers/infiniband/hw/erdma/erdma_main.c
@@ -172,14 +172,30 @@ static int erdma_device_init(struct erdma_dev *dev, struct pci_dev *pdev)
 {
 	int ret;
 
+	dev->resp_pool = dma_pool_create("erdma_resp_pool", &pdev->dev,
+					 ERDMA_HW_RESP_SIZE, ERDMA_HW_RESP_SIZE,
+					 0);
+	if (!dev->resp_pool)
+		return -ENOMEM;
+
 	ret = dma_set_mask_and_coherent(&pdev->dev,
 					DMA_BIT_MASK(ERDMA_PCI_WIDTH));
 	if (ret)
-		return ret;
+		goto destroy_pool;
 
 	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 
 	return 0;
+
+destroy_pool:
+	dma_pool_destroy(dev->resp_pool);
+
+	return ret;
+}
+
+static void erdma_device_uninit(struct erdma_dev *dev)
+{
+	dma_pool_destroy(dev->resp_pool);
 }
 
 static void erdma_hw_reset(struct erdma_dev *dev)
@@ -273,7 +289,7 @@ static int erdma_probe_dev(struct pci_dev *pdev)
 
 	err = erdma_request_vectors(dev);
 	if (err)
-		goto err_iounmap_func_bar;
+		goto err_uninit_device;
 
 	err = erdma_comm_irq_init(dev);
 	if (err)
@@ -314,6 +330,9 @@ err_uninit_comm_irq:
 err_free_vectors:
 	pci_free_irq_vectors(dev->pdev);
 
+err_uninit_device:
+	erdma_device_uninit(dev);
+
 err_iounmap_func_bar:
 	devm_iounmap(&pdev->dev, dev->func_bar);
 
@@ -339,6 +358,7 @@ static void erdma_remove_dev(struct pci_dev *pdev)
 	erdma_aeq_destroy(dev);
 	erdma_comm_irq_uninit(dev);
 	pci_free_irq_vectors(dev->pdev);
+	erdma_device_uninit(dev);
 
 	devm_iounmap(&pdev->dev, dev->func_bar);
 	pci_release_selected_regions(pdev, ERDMA_BAR_MASK);
@@ -448,6 +468,7 @@ static const struct ib_device_ops erdma_device_ops = {
 	.driver_id = RDMA_DRIVER_ERDMA,
 	.uverbs_abi_ver = ERDMA_ABI_VERSION,
 
+	.alloc_hw_port_stats = erdma_alloc_hw_port_stats,
 	.alloc_mr = erdma_ib_alloc_mr,
 	.alloc_pd = erdma_alloc_pd,
 	.alloc_ucontext = erdma_alloc_ucontext,
@@ -459,6 +480,7 @@ static const struct ib_device_ops erdma_device_ops = {
 	.destroy_cq = erdma_destroy_cq,
 	.destroy_qp = erdma_destroy_qp,
 	.get_dma_mr = erdma_get_dma_mr,
+	.get_hw_stats = erdma_get_hw_stats,
 	.get_port_immutable = erdma_get_port_immutable,
 	.iw_accept = erdma_accept,
 	.iw_add_ref = erdma_qp_get_ref,
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
index c317947563fb..23dfc01603f8 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
@@ -1708,3 +1708,93 @@ void erdma_port_event(struct erdma_dev *dev, enum ib_event_type reason)
 
 	ib_dispatch_event(&event);
 }
+
+enum counters {
+	ERDMA_STATS_TX_REQS_CNT,
+	ERDMA_STATS_TX_PACKETS_CNT,
+	ERDMA_STATS_TX_BYTES_CNT,
+	ERDMA_STATS_TX_DISABLE_DROP_CNT,
+	ERDMA_STATS_TX_BPS_METER_DROP_CNT,
+	ERDMA_STATS_TX_PPS_METER_DROP_CNT,
+
+	ERDMA_STATS_RX_PACKETS_CNT,
+	ERDMA_STATS_RX_BYTES_CNT,
+	ERDMA_STATS_RX_DISABLE_DROP_CNT,
+	ERDMA_STATS_RX_BPS_METER_DROP_CNT,
+	ERDMA_STATS_RX_PPS_METER_DROP_CNT,
+
+	ERDMA_STATS_MAX
+};
+
+static const struct rdma_stat_desc erdma_descs[] = {
+	[ERDMA_STATS_TX_REQS_CNT].name = "tx_reqs_cnt",
+	[ERDMA_STATS_TX_PACKETS_CNT].name = "tx_packets_cnt",
+	[ERDMA_STATS_TX_BYTES_CNT].name = "tx_bytes_cnt",
+	[ERDMA_STATS_TX_DISABLE_DROP_CNT].name = "tx_disable_drop_cnt",
+	[ERDMA_STATS_TX_BPS_METER_DROP_CNT].name = "tx_bps_limit_drop_cnt",
+	[ERDMA_STATS_TX_PPS_METER_DROP_CNT].name = "tx_pps_limit_drop_cnt",
+	[ERDMA_STATS_RX_PACKETS_CNT].name = "rx_packets_cnt",
+	[ERDMA_STATS_RX_BYTES_CNT].name = "rx_bytes_cnt",
+	[ERDMA_STATS_RX_DISABLE_DROP_CNT].name = "rx_disable_drop_cnt",
+	[ERDMA_STATS_RX_BPS_METER_DROP_CNT].name = "rx_bps_limit_drop_cnt",
+	[ERDMA_STATS_RX_PPS_METER_DROP_CNT].name = "rx_pps_limit_drop_cnt",
+};
+
+struct rdma_hw_stats *erdma_alloc_hw_port_stats(struct ib_device *device,
+						u32 port_num)
+{
+	return rdma_alloc_hw_stats_struct(erdma_descs, ERDMA_STATS_MAX,
+					  RDMA_HW_STATS_DEFAULT_LIFESPAN);
+}
+
+static int erdma_query_hw_stats(struct erdma_dev *dev,
+				struct rdma_hw_stats *stats)
+{
+	struct erdma_cmdq_query_stats_resp *resp;
+	struct erdma_cmdq_query_req req;
+	dma_addr_t dma_addr;
+	int err;
+
+	erdma_cmdq_build_reqhdr(&req.hdr, CMDQ_SUBMOD_COMMON,
+				CMDQ_OPCODE_GET_STATS);
+
+	resp = dma_pool_zalloc(dev->resp_pool, GFP_KERNEL, &dma_addr);
+	if (!resp)
+		return -ENOMEM;
+
+	req.target_addr = dma_addr;
+	req.target_length = ERDMA_HW_RESP_SIZE;
+
+	err = erdma_post_cmd_wait(&dev->cmdq, &req, sizeof(req), NULL, NULL);
+	if (err)
+		goto out;
+
+	if (resp->hdr.magic != ERDMA_HW_RESP_MAGIC) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	memcpy(&stats->value[0], &resp->tx_req_cnt,
+	       sizeof(u64) * stats->num_counters);
+
+out:
+	dma_pool_free(dev->resp_pool, resp, dma_addr);
+
+	return err;
+}
+
+int erdma_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+		       u32 port, int index)
+{
+	struct erdma_dev *dev = to_edev(ibdev);
+	int ret;
+
+	if (port == 0)
+		return 0;
+
+	ret = erdma_query_hw_stats(dev, stats);
+	if (ret)
+		return ret;
+
+	return stats->num_counters;
+}
diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.h b/drivers/infiniband/hw/erdma/erdma_verbs.h
index eb9c0f92fb6f..db6018529ccc 100644
--- a/drivers/infiniband/hw/erdma/erdma_verbs.h
+++ b/drivers/infiniband/hw/erdma/erdma_verbs.h
@@ -361,5 +361,9 @@ int erdma_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 		    unsigned int *sg_offset);
 void erdma_port_event(struct erdma_dev *dev, enum ib_event_type reason);
 void erdma_set_mtu(struct erdma_dev *dev, u32 mtu);
+struct rdma_hw_stats *erdma_alloc_hw_port_stats(struct ib_device *device,
+						u32 port_num);
+int erdma_get_hw_stats(struct ib_device *ibdev, struct rdma_hw_stats *stats,
+		       u32 port, int index);
 
 #endif