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

Pull rdma fixes from Doug Ledford:
 "A small collection of -rc fixes. Mostly. One API addition, but that's
  because we wanted to use it in a fix. There's also a bug fix that is
  going to render the 5.5 kernel's soft-RoCE driver incompatible with
  all soft-RoCE versions prior, but it's required to actually implement
  the protocol according to the RoCE spec and required in order for the
  soft-RoCE driver to be able to successfully work with actual RoCE
  hardware.

  Summary:

   - Update Steve Wise info

   - Fix for soft-RoCE crc calculations (will break back compatibility,
     but only with the soft-RoCE driver, which has had this bug since it
     was introduced and it is an on-the-wire bug, but will make
     soft-RoCE fully compatible with real RoCE hardware)

   - cma init fixup

   - counters oops fix

   - fix for mlx4 init/teardown sequence

   - fix for mkx5 steering rules

   - introduce a cleanup API, which isn't a fix, but we want to use it
     in the next fix

   - fix for mlx5 memory management that uses API in previous patch"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  IB/mlx5: Fix device memory flows
  IB/core: Introduce rdma_user_mmap_entry_insert_range() API
  IB/mlx5: Fix steering rule of drop and count
  IB/mlx4: Follow mirror sequence of device add during device removal
  RDMA/counter: Prevent auto-binding a QP which are not tracked with res
  rxe: correctly calculate iCRC for unaligned payloads
  Update mailmap info for Steve Wise
  RDMA/cma: add missed unregister_pernet_subsys in init failure

Author: torvalds

.mailmap

@@ -276,3 +276,5 @@ Gustavo Padovan <[email protected]>
 Gustavo Padovan <[email protected]>
 Changbin Du <[email protected]> <[email protected]>
 Changbin Du <[email protected]> <[email protected]>
+Steve Wise <[email protected]> <[email protected]>
+Steve Wise <[email protected]> <[email protected]>

drivers/infiniband/core/cma.c

@@ -4763,6 +4763,7 @@ static int __init cma_init(void)
 err:
 	unregister_netdevice_notifier(&cma_nb);
 	ib_sa_unregister_client(&sa_client);
+	unregister_pernet_subsys(&cma_pernet_operations);
 err_wq:
 	destroy_workqueue(cma_wq);
 	return ret;

drivers/infiniband/core/counters.c

@@ -286,6 +286,9 @@ int rdma_counter_bind_qp_auto(struct ib_qp *qp, u8 port)
 	struct rdma_counter *counter;
 	int ret;
 
+	if (!qp->res.valid)
+		return 0;
+
 	if (!rdma_is_port_valid(dev, port))
 		return -EINVAL;
 

drivers/infiniband/core/ib_core_uverbs.c

@@ -238,28 +238,32 @@ void rdma_user_mmap_entry_remove(struct rdma_user_mmap_entry *entry)
 EXPORT_SYMBOL(rdma_user_mmap_entry_remove);
 
 /**
- * rdma_user_mmap_entry_insert() - Insert an entry to the mmap_xa
+ * rdma_user_mmap_entry_insert_range() - Insert an entry to the mmap_xa
+ *					 in a given range.
  *
  * @ucontext: associated user context.
  * @entry: the entry to insert into the mmap_xa
  * @length: length of the address that will be mmapped
+ * @min_pgoff: minimum pgoff to be returned
+ * @max_pgoff: maximum pgoff to be returned
  *
  * This function should be called by drivers that use the rdma_user_mmap
  * interface for implementing their mmap syscall A database of mmap offsets is
  * handled in the core and helper functions are provided to insert entries
  * into the database and extract entries when the user calls mmap with the
- * given offset.  The function allocates a unique page offset that should be
- * provided to user, the user will use the offset to retrieve information such
- * as address to be mapped and how.
+ * given offset. The function allocates a unique page offset in a given range
+ * that should be provided to user, the user will use the offset to retrieve
+ * information such as address to be mapped and how.
  *
  * Return: 0 on success and -ENOMEM on failure
  */
-int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext,
-				struct rdma_user_mmap_entry *entry,
-				size_t length)
+int rdma_user_mmap_entry_insert_range(struct ib_ucontext *ucontext,
+				      struct rdma_user_mmap_entry *entry,
+				      size_t length, u32 min_pgoff,
+				      u32 max_pgoff)
 {
 	struct ib_uverbs_file *ufile = ucontext->ufile;
-	XA_STATE(xas, &ucontext->mmap_xa, 0);
+	XA_STATE(xas, &ucontext->mmap_xa, min_pgoff);
 	u32 xa_first, xa_last, npages;
 	int err;
 	u32 i;
@@ -285,7 +289,7 @@ int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext,
 	entry->npages = npages;
 	while (true) {
 		/* First find an empty index */
-		xas_find_marked(&xas, U32_MAX, XA_FREE_MARK);
+		xas_find_marked(&xas, max_pgoff, XA_FREE_MARK);
 		if (xas.xa_node == XAS_RESTART)
 			goto err_unlock;
 
@@ -332,4 +336,30 @@ int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext,
 	mutex_unlock(&ufile->umap_lock);
 	return -ENOMEM;
 }
+EXPORT_SYMBOL(rdma_user_mmap_entry_insert_range);
+
+/**
+ * rdma_user_mmap_entry_insert() - Insert an entry to the mmap_xa.
+ *
+ * @ucontext: associated user context.
+ * @entry: the entry to insert into the mmap_xa
+ * @length: length of the address that will be mmapped
+ *
+ * This function should be called by drivers that use the rdma_user_mmap
+ * interface for handling user mmapped addresses. The database is handled in
+ * the core and helper functions are provided to insert entries into the
+ * database and extract entries when the user calls mmap with the given offset.
+ * The function allocates a unique page offset that should be provided to user,
+ * the user will use the offset to retrieve information such as address to
+ * be mapped and how.
+ *
+ * Return: 0 on success and -ENOMEM on failure
+ */
+int rdma_user_mmap_entry_insert(struct ib_ucontext *ucontext,
+				struct rdma_user_mmap_entry *entry,
+				size_t length)
+{
+	return rdma_user_mmap_entry_insert_range(ucontext, entry, length, 0,
+						 U32_MAX);
+}
 EXPORT_SYMBOL(rdma_user_mmap_entry_insert);

drivers/infiniband/hw/mlx4/main.c

@@ -3018,16 +3018,17 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 	ibdev->ib_active = false;
 	flush_workqueue(wq);
 
-	mlx4_ib_close_sriov(ibdev);
-	mlx4_ib_mad_cleanup(ibdev);
-	ib_unregister_device(&ibdev->ib_dev);
-	mlx4_ib_diag_cleanup(ibdev);
 	if (ibdev->iboe.nb.notifier_call) {
 		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
 			pr_warn("failure unregistering notifier\n");
 		ibdev->iboe.nb.notifier_call = NULL;
 	}
 
+	mlx4_ib_close_sriov(ibdev);
+	mlx4_ib_mad_cleanup(ibdev);
+	ib_unregister_device(&ibdev->ib_dev);
+	mlx4_ib_diag_cleanup(ibdev);
+
 	mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
 			      ibdev->steer_qpn_count);
 	kfree(ibdev->ib_uc_qpns_bitmap);

drivers/infiniband/hw/mlx5/cmd.c

@@ -157,7 +157,7 @@ int mlx5_cmd_alloc_memic(struct mlx5_dm *dm, phys_addr_t *addr,
 	return -ENOMEM;
 }
 
-int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length)
+void mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length)
 {
 	struct mlx5_core_dev *dev = dm->dev;
 	u64 hw_start_addr = MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr);
@@ -175,15 +175,13 @@ int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length)
 	MLX5_SET(dealloc_memic_in, in, memic_size, length);
 
 	err =  mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+	if (err)
+		return;
 
-	if (!err) {
-		spin_lock(&dm->lock);
-		bitmap_clear(dm->memic_alloc_pages,
-			     start_page_idx, num_pages);
-		spin_unlock(&dm->lock);
-	}
-
-	return err;
+	spin_lock(&dm->lock);
+	bitmap_clear(dm->memic_alloc_pages,
+		     start_page_idx, num_pages);
+	spin_unlock(&dm->lock);
 }
 
 int mlx5_cmd_query_ext_ppcnt_counters(struct mlx5_core_dev *dev, void *out)

drivers/infiniband/hw/mlx5/cmd.h

@@ -46,7 +46,7 @@ int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev,
 				void *in, int in_size);
 int mlx5_cmd_alloc_memic(struct mlx5_dm *dm, phys_addr_t *addr,
 			 u64 length, u32 alignment);
-int mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length);
+void mlx5_cmd_dealloc_memic(struct mlx5_dm *dm, phys_addr_t addr, u64 length);
 void mlx5_cmd_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn, u16 uid);
 void mlx5_cmd_destroy_tir(struct mlx5_core_dev *dev, u32 tirn, u16 uid);
 void mlx5_cmd_destroy_tis(struct mlx5_core_dev *dev, u32 tisn, u16 uid);

drivers/infiniband/hw/mlx5/main.c

@@ -2074,6 +2074,24 @@ static int mlx5_ib_mmap_clock_info_page(struct mlx5_ib_dev *dev,
 			      virt_to_page(dev->mdev->clock_info));
 }
 
+static void mlx5_ib_mmap_free(struct rdma_user_mmap_entry *entry)
+{
+	struct mlx5_user_mmap_entry *mentry = to_mmmap(entry);
+	struct mlx5_ib_dev *dev = to_mdev(entry->ucontext->device);
+	struct mlx5_ib_dm *mdm;
+
+	switch (mentry->mmap_flag) {
+	case MLX5_IB_MMAP_TYPE_MEMIC:
+		mdm = container_of(mentry, struct mlx5_ib_dm, mentry);
+		mlx5_cmd_dealloc_memic(&dev->dm, mdm->dev_addr,
+				       mdm->size);
+		kfree(mdm);
+		break;
+	default:
+		WARN_ON(true);
+	}
+}
+
 static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 		    struct vm_area_struct *vma,
 		    struct mlx5_ib_ucontext *context)
@@ -2186,26 +2204,55 @@ static int uar_mmap(struct mlx5_ib_dev *dev, enum mlx5_ib_mmap_cmd cmd,
 	return err;
 }
 
-static int dm_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
+static int add_dm_mmap_entry(struct ib_ucontext *context,
+			     struct mlx5_ib_dm *mdm,
+			     u64 address)
+{
+	mdm->mentry.mmap_flag = MLX5_IB_MMAP_TYPE_MEMIC;
+	mdm->mentry.address = address;
+	return rdma_user_mmap_entry_insert_range(
+			context, &mdm->mentry.rdma_entry,
+			mdm->size,
+			MLX5_IB_MMAP_DEVICE_MEM << 16,
+			(MLX5_IB_MMAP_DEVICE_MEM << 16) + (1UL << 16) - 1);
+}
+
+static unsigned long mlx5_vma_to_pgoff(struct vm_area_struct *vma)
+{
+	unsigned long idx;
+	u8 command;
+
+	command = get_command(vma->vm_pgoff);
+	idx = get_extended_index(vma->vm_pgoff);
+
+	return (command << 16 | idx);
+}
+
+static int mlx5_ib_mmap_offset(struct mlx5_ib_dev *dev,
+			       struct vm_area_struct *vma,
+			       struct ib_ucontext *ucontext)
 {
-	struct mlx5_ib_ucontext *mctx = to_mucontext(context);
-	struct mlx5_ib_dev *dev = to_mdev(context->device);
-	u16 page_idx = get_extended_index(vma->vm_pgoff);
-	size_t map_size = vma->vm_end - vma->vm_start;
-	u32 npages = map_size >> PAGE_SHIFT;
+	struct mlx5_user_mmap_entry *mentry;
+	struct rdma_user_mmap_entry *entry;
+	unsigned long pgoff;
+	pgprot_t prot;
 	phys_addr_t pfn;
+	int ret;
 
-	if (find_next_zero_bit(mctx->dm_pages, page_idx + npages, page_idx) !=
-	    page_idx + npages)
+	pgoff = mlx5_vma_to_pgoff(vma);
+	entry = rdma_user_mmap_entry_get_pgoff(ucontext, pgoff);
+	if (!entry)
 		return -EINVAL;
 
-	pfn = ((dev->mdev->bar_addr +
-	      MLX5_CAP64_DEV_MEM(dev->mdev, memic_bar_start_addr)) >>
-	      PAGE_SHIFT) +
-	      page_idx;
-	return rdma_user_mmap_io(context, vma, pfn, map_size,
-				 pgprot_writecombine(vma->vm_page_prot),
-				 NULL);
+	mentry = to_mmmap(entry);
+	pfn = (mentry->address >> PAGE_SHIFT);
+	prot = pgprot_writecombine(vma->vm_page_prot);
+	ret = rdma_user_mmap_io(ucontext, vma, pfn,
+				entry->npages * PAGE_SIZE,
+				prot,
+				entry);
+	rdma_user_mmap_entry_put(&mentry->rdma_entry);
+	return ret;
 }
 
 static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vma)
@@ -2248,11 +2295,8 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	case MLX5_IB_MMAP_CLOCK_INFO:
 		return mlx5_ib_mmap_clock_info_page(dev, vma, context);
 
-	case MLX5_IB_MMAP_DEVICE_MEM:
-		return dm_mmap(ibcontext, vma);
-
 	default:
-		return -EINVAL;
+		return mlx5_ib_mmap_offset(dev, vma, ibcontext);
 	}
 
 	return 0;
@@ -2288,8 +2332,9 @@ static int handle_alloc_dm_memic(struct ib_ucontext *ctx,
 {
 	struct mlx5_dm *dm_db = &to_mdev(ctx->device)->dm;
 	u64 start_offset;
-	u32 page_idx;
+	u16 page_idx;
 	int err;
+	u64 address;
 
 	dm->size = roundup(attr->length, MLX5_MEMIC_BASE_SIZE);
 
@@ -2298,28 +2343,30 @@ static int handle_alloc_dm_memic(struct ib_ucontext *ctx,
 	if (err)
 		return err;
 
-	page_idx = (dm->dev_addr - pci_resource_start(dm_db->dev->pdev, 0) -
-		    MLX5_CAP64_DEV_MEM(dm_db->dev, memic_bar_start_addr)) >>
-		    PAGE_SHIFT;
+	address = dm->dev_addr & PAGE_MASK;
+	err = add_dm_mmap_entry(ctx, dm, address);
+	if (err)
+		goto err_dealloc;
 
+	page_idx = dm->mentry.rdma_entry.start_pgoff & 0xFFFF;
 	err = uverbs_copy_to(attrs,
 			     MLX5_IB_ATTR_ALLOC_DM_RESP_PAGE_INDEX,
-			     &page_idx, sizeof(page_idx));
+			     &page_idx,
+			     sizeof(page_idx));
 	if (err)
-		goto err_dealloc;
+		goto err_copy;
 
 	start_offset = dm->dev_addr & ~PAGE_MASK;
 	err = uverbs_copy_to(attrs,
 			     MLX5_IB_ATTR_ALLOC_DM_RESP_START_OFFSET,
 			     &start_offset, sizeof(start_offset));
 	if (err)
-		goto err_dealloc;
-
-	bitmap_set(to_mucontext(ctx)->dm_pages, page_idx,
-		   DIV_ROUND_UP(dm->size, PAGE_SIZE));
+		goto err_copy;
 
 	return 0;
 
+err_copy:
+	rdma_user_mmap_entry_remove(&dm->mentry.rdma_entry);
 err_dealloc:
 	mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
 
@@ -2423,23 +2470,13 @@ int mlx5_ib_dealloc_dm(struct ib_dm *ibdm, struct uverbs_attr_bundle *attrs)
 	struct mlx5_ib_ucontext *ctx = rdma_udata_to_drv_context(
 		&attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
 	struct mlx5_core_dev *dev = to_mdev(ibdm->device)->mdev;
-	struct mlx5_dm *dm_db = &to_mdev(ibdm->device)->dm;
 	struct mlx5_ib_dm *dm = to_mdm(ibdm);
-	u32 page_idx;
 	int ret;
 
 	switch (dm->type) {
 	case MLX5_IB_UAPI_DM_TYPE_MEMIC:
-		ret = mlx5_cmd_dealloc_memic(dm_db, dm->dev_addr, dm->size);
-		if (ret)
-			return ret;
-
-		page_idx = (dm->dev_addr - pci_resource_start(dev->pdev, 0) -
-			    MLX5_CAP64_DEV_MEM(dev, memic_bar_start_addr)) >>
-			    PAGE_SHIFT;
-		bitmap_clear(ctx->dm_pages, page_idx,
-			     DIV_ROUND_UP(dm->size, PAGE_SIZE));
-		break;
+		rdma_user_mmap_entry_remove(&dm->mentry.rdma_entry);
+		return 0;
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 		ret = mlx5_dm_sw_icm_dealloc(dev, MLX5_SW_ICM_TYPE_STEERING,
 					     dm->size, ctx->devx_uid, dm->dev_addr,
@@ -3544,10 +3581,6 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	}
 
 	INIT_LIST_HEAD(&handler->list);
-	if (dst) {
-		memcpy(&dest_arr[0], dst, sizeof(*dst));
-		dest_num++;
-	}
 
 	for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) {
 		err = parse_flow_attr(dev->mdev, spec,
@@ -3560,6 +3593,11 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 		ib_flow += ((union ib_flow_spec *)ib_flow)->size;
 	}
 
+	if (dst && !(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP)) {
+		memcpy(&dest_arr[0], dst, sizeof(*dst));
+		dest_num++;
+	}
+
 	if (!flow_is_multicast_only(flow_attr))
 		set_underlay_qp(dev, spec, underlay_qpn);
 
@@ -3600,10 +3638,8 @@ static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev,
 	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
-		if (!(flow_act.action & MLX5_FLOW_CONTEXT_ACTION_COUNT)) {
+		if (!dest_num)
 			rule_dst = NULL;
-			dest_num = 0;
-		}
 	} else {
 		if (is_egress)
 			flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_ALLOW;
@@ -6236,6 +6272,7 @@ static const struct ib_device_ops mlx5_ib_dev_ops = {
 	.map_mr_sg = mlx5_ib_map_mr_sg,
 	.map_mr_sg_pi = mlx5_ib_map_mr_sg_pi,
 	.mmap = mlx5_ib_mmap,
+	.mmap_free = mlx5_ib_mmap_free,
 	.modify_cq = mlx5_ib_modify_cq,
 	.modify_device = mlx5_ib_modify_device,
 	.modify_port = mlx5_ib_modify_port,