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

Pull rdma updates from Jason Gunthorpe:
 "Aside from the usual things this has an arch update for
  __iowrite64_copy() used by the RDMA drivers.

  This API was intended to generate large 64 byte MemWr TLPs on PCI.
  These days most processors had done this by just repeating writel() in
  a loop. S390 and some new ARM64 designs require a special helper to
  get this to generate.

   - Small improvements and fixes for erdma, efa, hfi1, bnxt_re

   - Fix a UAF crash after module unload on leaking restrack entry

   - Continue adding full RDMA support in mana with support for EQs,
     GID's and CQs

   - Improvements to the mkey cache in mlx5

   - DSCP traffic class support in hns and several bug fixes

   - Cap the maximum number of MADs in the receive queue to avoid OOM

   - Another batch of rxe bug fixes from large scale testing

   - __iowrite64_copy() optimizations for write combining MMIO memory

   - Remove NULL checks before dev_put/hold()

   - EFA support for receive with immediate

   - Fix a recent memleaking regression in a cma error path"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (70 commits)
  RDMA/cma: Fix kmemleak in rdma_core observed during blktests nvme/rdma use siw
  RDMA/IPoIB: Fix format truncation compilation errors
  bnxt_re: avoid shift undefined behavior in bnxt_qplib_alloc_init_hwq
  RDMA/efa: Support QP with unsolicited write w/ imm. receive
  IB/hfi1: Remove generic .ndo_get_stats64
  IB/hfi1: Do not use custom stat allocator
  RDMA/hfi1: Use RMW accessors for changing LNKCTL2
  RDMA/mana_ib: implement uapi for creation of rnic cq
  RDMA/mana_ib: boundary check before installing cq callbacks
  RDMA/mana_ib: introduce a helper to remove cq callbacks
  RDMA/mana_ib: create and destroy RNIC cqs
  RDMA/mana_ib: create EQs for RNIC CQs
  RDMA/core: Remove NULL check before dev_{put, hold}
  RDMA/ipoib: Remove NULL check before dev_{put, hold}
  RDMA/mlx5: Remove NULL check before dev_{put, hold}
  RDMA/mlx5: Track DCT, DCI and REG_UMR QPs as diver_detail resources.
  RDMA/core: Add an option to display driver-specific QPs in the rdmatool
  RDMA/efa: Add shutdown notifier
  RDMA/mana_ib: Fix missing ret value
  IB/mlx5: Use __iowrite64_copy() for write combining stores
  ...

5 files changed, 42 insertions, 3 deletions

diff --git a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
index 7377c8a9f4d5..4296662e59c3 100644
--- a/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
+++ b/drivers/infiniband/hw/efa/efa_admin_cmds_defs.h
@@ -110,7 +110,10 @@ struct efa_admin_create_qp_cmd {
 	 *    virtual (IOVA returned by MR registration)
 	 * 1 : rq_virt - If set, RQ ring base address is
 	 *    virtual (IOVA returned by MR registration)
-	 * 7:2 : reserved - MBZ
+	 * 2 : unsolicited_write_recv - If set, work requests
+	 *    will not be consumed for incoming RDMA write with
+	 *    immediate
+	 * 7:3 : reserved - MBZ
 	 */
 	u8 flags;
 
@@ -663,7 +666,9 @@ struct efa_admin_feature_device_attr_desc {
 	 *    polling is supported
 	 * 3 : rdma_write - If set, RDMA Write is supported
 	 *    on TX queues
-	 * 31:4 : reserved - MBZ
+	 * 4 : unsolicited_write_recv - If set, unsolicited
+	 *    write with imm. receive is supported
+	 * 31:5 : reserved - MBZ
 	 */
 	u32 device_caps;
 
@@ -1009,6 +1014,7 @@ struct efa_admin_host_info {
 /* create_qp_cmd */
 #define EFA_ADMIN_CREATE_QP_CMD_SQ_VIRT_MASK                BIT(0)
 #define EFA_ADMIN_CREATE_QP_CMD_RQ_VIRT_MASK                BIT(1)
+#define EFA_ADMIN_CREATE_QP_CMD_UNSOLICITED_WRITE_RECV_MASK BIT(2)
 
 /* modify_qp_cmd */
 #define EFA_ADMIN_MODIFY_QP_CMD_QP_STATE_MASK               BIT(0)
@@ -1044,6 +1050,7 @@ struct efa_admin_host_info {
 #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RNR_RETRY_MASK   BIT(1)
 #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_DATA_POLLING_128_MASK BIT(2)
 #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_WRITE_MASK  BIT(3)
+#define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_UNSOLICITED_WRITE_RECV_MASK BIT(4)
 
 /* create_eq_cmd */
 #define EFA_ADMIN_CREATE_EQ_CMD_ENTRY_SIZE_WORDS_MASK       GENMASK(4, 0)
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.c b/drivers/infiniband/hw/efa/efa_com_cmd.c
index d3398c7b0bd0..5b9c2b16df0e 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.c
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.c
@@ -32,6 +32,9 @@ int efa_com_create_qp(struct efa_com_dev *edev,
 			params->rq_depth;
 	create_qp_cmd.uar = params->uarn;
 
+	if (params->unsolicited_write_recv)
+		EFA_SET(&create_qp_cmd.flags, EFA_ADMIN_CREATE_QP_CMD_UNSOLICITED_WRITE_RECV, 1);
+
 	err = efa_com_cmd_exec(aq,
 			       (struct efa_admin_aq_entry *)&create_qp_cmd,
 			       sizeof(create_qp_cmd),
diff --git a/drivers/infiniband/hw/efa/efa_com_cmd.h b/drivers/infiniband/hw/efa/efa_com_cmd.h
index 720a99ba0f7d..9714105fcf7e 100644
--- a/drivers/infiniband/hw/efa/efa_com_cmd.h
+++ b/drivers/infiniband/hw/efa/efa_com_cmd.h
@@ -27,6 +27,7 @@ struct efa_com_create_qp_params {
 	u16 pd;
 	u16 uarn;
 	u8 qp_type;
+	u8 unsolicited_write_recv : 1;
 };
 
 struct efa_com_create_qp_result {
diff --git a/drivers/infiniband/hw/efa/efa_main.c b/drivers/infiniband/hw/efa/efa_main.c
index 5fa3603c80d8..d1a48f988f6c 100644
--- a/drivers/infiniband/hw/efa/efa_main.c
+++ b/drivers/infiniband/hw/efa/efa_main.c
@@ -671,11 +671,22 @@ static void efa_remove(struct pci_dev *pdev)
 	efa_remove_device(pdev);
 }
 
+static void efa_shutdown(struct pci_dev *pdev)
+{
+	struct efa_dev *dev = pci_get_drvdata(pdev);
+
+	efa_destroy_eqs(dev);
+	efa_com_dev_reset(&dev->edev, EFA_REGS_RESET_SHUTDOWN);
+	efa_free_irq(dev, &dev->admin_irq);
+	efa_disable_msix(dev);
+}
+
 static struct pci_driver efa_pci_driver = {
 	.name           = DRV_MODULE_NAME,
 	.id_table       = efa_pci_tbl,
 	.probe          = efa_probe,
 	.remove         = efa_remove,
+	.shutdown       = efa_shutdown,
 };
 
 module_pci_driver(efa_pci_driver);
diff --git a/drivers/infiniband/hw/efa/efa_verbs.c b/drivers/infiniband/hw/efa/efa_verbs.c
index 2f412db2edcd..8f7a13b79cdc 100644
--- a/drivers/infiniband/hw/efa/efa_verbs.c
+++ b/drivers/infiniband/hw/efa/efa_verbs.c
@@ -263,6 +263,9 @@ int efa_query_device(struct ib_device *ibdev,
 		if (EFA_DEV_CAP(dev, RDMA_WRITE))
 			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RDMA_WRITE;
 
+		if (EFA_DEV_CAP(dev, UNSOLICITED_WRITE_RECV))
+			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_UNSOLICITED_WRITE_RECV;
+
 		if (dev->neqs)
 			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS;
 
@@ -639,6 +642,7 @@ int efa_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
 	struct efa_ibv_create_qp cmd = {};
 	struct efa_qp *qp = to_eqp(ibqp);
 	struct efa_ucontext *ucontext;
+	u16 supported_efa_flags = 0;
 	int err;
 
 	ucontext = rdma_udata_to_drv_context(udata, struct efa_ucontext,
@@ -676,13 +680,23 @@ int efa_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
 		goto err_out;
 	}
 
-	if (cmd.comp_mask) {
+	if (cmd.comp_mask || !is_reserved_cleared(cmd.reserved_90)) {
 		ibdev_dbg(&dev->ibdev,
 			  "Incompatible ABI params, unknown fields in udata\n");
 		err = -EINVAL;
 		goto err_out;
 	}
 
+	if (EFA_DEV_CAP(dev, UNSOLICITED_WRITE_RECV))
+		supported_efa_flags |= EFA_CREATE_QP_WITH_UNSOLICITED_WRITE_RECV;
+
+	if (cmd.flags & ~supported_efa_flags) {
+		ibdev_dbg(&dev->ibdev, "Unsupported EFA QP create flags[%#x], supported[%#x]\n",
+			  cmd.flags, supported_efa_flags);
+		err = -EOPNOTSUPP;
+		goto err_out;
+	}
+
 	create_qp_params.uarn = ucontext->uarn;
 	create_qp_params.pd = to_epd(ibqp->pd)->pdn;
 
@@ -722,6 +736,9 @@ int efa_create_qp(struct ib_qp *ibqp, struct ib_qp_init_attr *init_attr,
 		create_qp_params.rq_base_addr = qp->rq_dma_addr;
 	}
 
+	if (cmd.flags & EFA_CREATE_QP_WITH_UNSOLICITED_WRITE_RECV)
+		create_qp_params.unsolicited_write_recv = true;
+
 	err = efa_com_create_qp(&dev->edev, &create_qp_params,
 				&create_qp_resp);
 	if (err)