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

…t/rdma/rdma

Pull rdma fixes from Jason Gunthorpe:
 "Things are looking pretty quiet here in RDMA, not too many bug fixes
  rolling in right now. The usual driver bug fixes and fixes for a
  couple of regressions introduced in 5.2:

   - Fix a race on bootup with RDMA device renaming and srp. SRP also
     needs to rename its internal sys files

   - Fix a memory leak in hns

   - Don't leak resources in efa on certain error unwinds

   - Don't panic in certain error unwinds in ib_register_device

   - Various small user visible bug fix patches for the hfi and efa
     drivers

   - Fix the 32 bit compilation break"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  RDMA/efa: Remove MAYEXEC flag check from mmap flow
  mlx5: avoid 64-bit division
  IB/hfi1: Validate page aligned for a given virtual address
  IB/{qib, hfi1, rdmavt}: Correct ibv_devinfo max_mr value
  IB/hfi1: Insure freeze_work work_struct is canceled on shutdown
  IB/rdmavt: Fix alloc_qpn() WARN_ON()
  RDMA/core: Fix panic when port_data isn't initialized
  RDMA/uverbs: Pass udata on uverbs error unwind
  RDMA/core: Clear out the udata before error unwind
  RDMA/hns: Fix PD memory leak for internal allocation
  RDMA/srp: Rename SRP sysfs name after IB device rename trigger

drivers/infiniband/core/device.c

@@ -409,27 +409,44 @@ static int rename_compat_devs(struct ib_device *device)
 
 int ib_device_rename(struct ib_device *ibdev, const char *name)
 {
+	unsigned long index;
+	void *client_data;
 	int ret;
 
 	down_write(&devices_rwsem);
 	if (!strcmp(name, dev_name(&ibdev->dev))) {
-		ret = 0;
-		goto out;
+		up_write(&devices_rwsem);
+		return 0;
 	}
 
 	if (__ib_device_get_by_name(name)) {
-		ret = -EEXIST;
-		goto out;
+		up_write(&devices_rwsem);
+		return -EEXIST;
 	}
 
 	ret = device_rename(&ibdev->dev, name);
-	if (ret)
-		goto out;
+	if (ret) {
+		up_write(&devices_rwsem);
+		return ret;
+	}
+
 	strlcpy(ibdev->name, name, IB_DEVICE_NAME_MAX);
 	ret = rename_compat_devs(ibdev);
-out:
-	up_write(&devices_rwsem);
-	return ret;
+
+	downgrade_write(&devices_rwsem);
+	down_read(&ibdev->client_data_rwsem);
+	xan_for_each_marked(&ibdev->client_data, index, client_data,
+			    CLIENT_DATA_REGISTERED) {
+		struct ib_client *client = xa_load(&clients, index);
+
+		if (!client || !client->rename)
+			continue;
+
+		client->rename(ibdev, client_data);
+	}
+	up_read(&ibdev->client_data_rwsem);
+	up_read(&devices_rwsem);
+	return 0;
 }
 
 static int alloc_name(struct ib_device *ibdev, const char *name)
@@ -474,14 +491,15 @@ static void ib_device_release(struct device *device)
 
 	free_netdevs(dev);
 	WARN_ON(refcount_read(&dev->refcount));
-	ib_cache_release_one(dev);
-	ib_security_release_port_pkey_list(dev);
-	xa_destroy(&dev->compat_devs);
-	xa_destroy(&dev->client_data);
-	if (dev->port_data)
+	if (dev->port_data) {
+		ib_cache_release_one(dev);
+		ib_security_release_port_pkey_list(dev);
 		kfree_rcu(container_of(dev->port_data, struct ib_port_data_rcu,
 				       pdata[0]),
 			  rcu_head);
+	}
+	xa_destroy(&dev->compat_devs);
+	xa_destroy(&dev->client_data);
 	kfree_rcu(dev, rcu_head);
 }
 
@@ -1935,6 +1953,9 @@ static void free_netdevs(struct ib_device *ib_dev)
 	unsigned long flags;
 	unsigned int port;
 
+	if (!ib_dev->port_data)
+		return;
+
 	rdma_for_each_port (ib_dev, port) {
 		struct ib_port_data *pdata = &ib_dev->port_data[port];
 		struct net_device *ndev;

drivers/infiniband/core/rdma_core.h

@@ -110,6 +110,8 @@ int uverbs_output_written(const struct uverbs_attr_bundle *bundle, size_t idx);
 void setup_ufile_idr_uobject(struct ib_uverbs_file *ufile);
 void release_ufile_idr_uobject(struct ib_uverbs_file *ufile);
 
+struct ib_udata *uverbs_get_cleared_udata(struct uverbs_attr_bundle *attrs);
+
 /*
  * This is the runtime description of the uverbs API, used by the syscall
  * machinery to validate and dispatch calls.

drivers/infiniband/core/uverbs_cmd.c

@@ -174,6 +174,17 @@ static int uverbs_request_finish(struct uverbs_req_iter *iter)
 	return 0;
 }
 
+/*
+ * When calling a destroy function during an error unwind we need to pass in
+ * the udata that is sanitized of all user arguments. Ie from the driver
+ * perspective it looks like no udata was passed.
+ */
+struct ib_udata *uverbs_get_cleared_udata(struct uverbs_attr_bundle *attrs)
+{
+	attrs->driver_udata = (struct ib_udata){};
+	return &attrs->driver_udata;
+}
+
 static struct ib_uverbs_completion_event_file *
 _ib_uverbs_lookup_comp_file(s32 fd, struct uverbs_attr_bundle *attrs)
 {
@@ -441,7 +452,7 @@ static int ib_uverbs_alloc_pd(struct uverbs_attr_bundle *attrs)
 	return uobj_alloc_commit(uobj, attrs);
 
 err_copy:
-	ib_dealloc_pd_user(pd, &attrs->driver_udata);
+	ib_dealloc_pd_user(pd, uverbs_get_cleared_udata(attrs));
 	pd = NULL;
 err_alloc:
 	kfree(pd);
@@ -644,7 +655,7 @@ static int ib_uverbs_open_xrcd(struct uverbs_attr_bundle *attrs)
 	}
 
 err_dealloc_xrcd:
-	ib_dealloc_xrcd(xrcd, &attrs->driver_udata);
+	ib_dealloc_xrcd(xrcd, uverbs_get_cleared_udata(attrs));
 
 err:
 	uobj_alloc_abort(&obj->uobject, attrs);
@@ -767,7 +778,7 @@ static int ib_uverbs_reg_mr(struct uverbs_attr_bundle *attrs)
 	return uobj_alloc_commit(uobj, attrs);
 
 err_copy:
-	ib_dereg_mr_user(mr, &attrs->driver_udata);
+	ib_dereg_mr_user(mr, uverbs_get_cleared_udata(attrs));
 
 err_put:
 	uobj_put_obj_read(pd);
@@ -1042,7 +1053,7 @@ static struct ib_ucq_object *create_cq(struct uverbs_attr_bundle *attrs,
 	return obj;
 
 err_cb:
-	ib_destroy_cq(cq);
+	ib_destroy_cq_user(cq, uverbs_get_cleared_udata(attrs));
 
 err_file:
 	if (ev_file)
@@ -1478,7 +1489,7 @@ static int create_qp(struct uverbs_attr_bundle *attrs,
 
 	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
 err_cb:
-	ib_destroy_qp(qp);
+	ib_destroy_qp_user(qp, uverbs_get_cleared_udata(attrs));
 
 err_put:
 	if (!IS_ERR(xrcd_uobj))
@@ -1611,7 +1622,7 @@ static int ib_uverbs_open_qp(struct uverbs_attr_bundle *attrs)
 	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
 
 err_destroy:
-	ib_destroy_qp(qp);
+	ib_destroy_qp_user(qp, uverbs_get_cleared_udata(attrs));
 err_xrcd:
 	uobj_put_read(xrcd_uobj);
 err_put:
@@ -2453,7 +2464,8 @@ static int ib_uverbs_create_ah(struct uverbs_attr_bundle *attrs)
 	return uobj_alloc_commit(uobj, attrs);
 
 err_copy:
-	rdma_destroy_ah(ah, RDMA_DESTROY_AH_SLEEPABLE);
+	rdma_destroy_ah_user(ah, RDMA_DESTROY_AH_SLEEPABLE,
+			     uverbs_get_cleared_udata(attrs));
 
 err_put:
 	uobj_put_obj_read(pd);
@@ -2964,7 +2976,7 @@ static int ib_uverbs_ex_create_wq(struct uverbs_attr_bundle *attrs)
 	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
 
 err_copy:
-	ib_destroy_wq(wq, &attrs->driver_udata);
+	ib_destroy_wq(wq, uverbs_get_cleared_udata(attrs));
 err_put_cq:
 	uobj_put_obj_read(cq);
 err_put_pd:
@@ -3464,7 +3476,7 @@ static int __uverbs_create_xsrq(struct uverbs_attr_bundle *attrs,
 	return uobj_alloc_commit(&obj->uevent.uobject, attrs);
 
 err_copy:
-	ib_destroy_srq_user(srq, &attrs->driver_udata);
+	ib_destroy_srq_user(srq, uverbs_get_cleared_udata(attrs));
 
 err_free:
 	kfree(srq);

drivers/infiniband/core/uverbs_std_types_cq.c

@@ -135,7 +135,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_CQ_CREATE)(
 
 	return 0;
 err_cq:
-	ib_destroy_cq(cq);
+	ib_destroy_cq_user(cq, uverbs_get_cleared_udata(attrs));
 
 err_event_file:
 	if (ev_file)

drivers/infiniband/core/uverbs_std_types_mr.c

@@ -148,7 +148,7 @@ static int UVERBS_HANDLER(UVERBS_METHOD_DM_MR_REG)(
 	return 0;
 
 err_dereg:
-	ib_dereg_mr_user(mr, &attrs->driver_udata);
+	ib_dereg_mr_user(mr, uverbs_get_cleared_udata(attrs));
 
 	return ret;
 }

drivers/infiniband/hw/efa/efa_verbs.c

@@ -1728,7 +1728,6 @@ int efa_mmap(struct ib_ucontext *ibucontext,
 		ibdev_dbg(&dev->ibdev, "Mapping executable pages is not permitted\n");
 		return -EPERM;
 	}
-	vma->vm_flags &= ~VM_MAYEXEC;
 
 	return __efa_mmap(dev, ucontext, vma, key, length);
 }

drivers/infiniband/hw/hfi1/chip.c

@@ -9850,6 +9850,7 @@ void hfi1_quiet_serdes(struct hfi1_pportdata *ppd)
 
 	/* disable the port */
 	clear_rcvctrl(dd, RCV_CTRL_RCV_PORT_ENABLE_SMASK);
+	cancel_work_sync(&ppd->freeze_work);
 }
 
 static inline int init_cpu_counters(struct hfi1_devdata *dd)

drivers/infiniband/hw/hfi1/user_exp_rcv.c

@@ -324,6 +324,9 @@ int hfi1_user_exp_rcv_setup(struct hfi1_filedata *fd,
 	u32 *tidlist = NULL;
 	struct tid_user_buf *tidbuf;
 
+	if (!PAGE_ALIGNED(tinfo->vaddr))
+		return -EINVAL;
+
 	tidbuf = kzalloc(sizeof(*tidbuf), GFP_KERNEL);
 	if (!tidbuf)
 		return -ENOMEM;

drivers/infiniband/hw/hfi1/verbs.c

@@ -1356,8 +1356,6 @@ static void hfi1_fill_device_attr(struct hfi1_devdata *dd)
 	rdi->dparms.props.max_cq = hfi1_max_cqs;
 	rdi->dparms.props.max_ah = hfi1_max_ahs;
 	rdi->dparms.props.max_cqe = hfi1_max_cqes;
-	rdi->dparms.props.max_mr = rdi->lkey_table.max;
-	rdi->dparms.props.max_fmr = rdi->lkey_table.max;
 	rdi->dparms.props.max_map_per_fmr = 32767;
 	rdi->dparms.props.max_pd = hfi1_max_pds;
 	rdi->dparms.props.max_qp_rd_atom = HFI1_MAX_RDMA_ATOMIC;

drivers/infiniband/hw/hns/hns_roce_hw_v1.c

@@ -899,6 +899,7 @@ static void hns_roce_v1_release_lp_qp(struct hns_roce_dev *hr_dev)
 		dev_err(dev, "Destroy cq for mr_free failed(%d)!\n", ret);
 
 	hns_roce_dealloc_pd(&free_mr->mr_free_pd->ibpd, NULL);
+	kfree(&free_mr->mr_free_pd->ibpd);
 }
 
 static int hns_roce_db_init(struct hns_roce_dev *hr_dev)

drivers/infiniband/hw/mlx5/cmd.c

@@ -190,12 +190,12 @@ int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
 			  u16 uid, phys_addr_t *addr, u32 *obj_id)
 {
 	struct mlx5_core_dev *dev = dm->dev;
-	u32 num_blocks = DIV_ROUND_UP(length, MLX5_SW_ICM_BLOCK_SIZE(dev));
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
 	u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {};
 	unsigned long *block_map;
 	u64 icm_start_addr;
 	u32 log_icm_size;
+	u32 num_blocks;
 	u32 max_blocks;
 	u64 block_idx;
 	void *sw_icm;
@@ -224,6 +224,8 @@ int mlx5_cmd_alloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
 		return -EINVAL;
 	}
 
+	num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >>
+		     MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
 	max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev));
 	spin_lock(&dm->lock);
 	block_idx = bitmap_find_next_zero_area(block_map,
@@ -266,13 +268,16 @@ int mlx5_cmd_dealloc_sw_icm(struct mlx5_dm *dm, int type, u64 length,
 			    u16 uid, phys_addr_t addr, u32 obj_id)
 {
 	struct mlx5_core_dev *dev = dm->dev;
-	u32 num_blocks = DIV_ROUND_UP(length, MLX5_SW_ICM_BLOCK_SIZE(dev));
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {};
 	u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {};
 	unsigned long *block_map;
+	u32 num_blocks;
 	u64 start_idx;
 	int err;
 
+	num_blocks = (length + MLX5_SW_ICM_BLOCK_SIZE(dev) - 1) >>
+		     MLX5_LOG_SW_ICM_BLOCK_SIZE(dev);
+
 	switch (type) {
 	case MLX5_IB_UAPI_DM_TYPE_STEERING_SW_ICM:
 		start_idx =

drivers/infiniband/hw/mlx5/main.c

@@ -2344,7 +2344,7 @@ static int handle_alloc_dm_sw_icm(struct ib_ucontext *ctx,
 	/* Allocation size must a multiple of the basic block size
 	 * and a power of 2.
 	 */
-	act_size = roundup(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dm_db->dev));
+	act_size = round_up(attr->length, MLX5_SW_ICM_BLOCK_SIZE(dm_db->dev));
 	act_size = roundup_pow_of_two(act_size);
 
 	dm->size = act_size;

drivers/infiniband/hw/qib/qib_verbs.c

@@ -1459,8 +1459,6 @@ static void qib_fill_device_attr(struct qib_devdata *dd)
 	rdi->dparms.props.max_cq = ib_qib_max_cqs;
 	rdi->dparms.props.max_cqe = ib_qib_max_cqes;
 	rdi->dparms.props.max_ah = ib_qib_max_ahs;
-	rdi->dparms.props.max_mr = rdi->lkey_table.max;
-	rdi->dparms.props.max_fmr = rdi->lkey_table.max;
 	rdi->dparms.props.max_map_per_fmr = 32767;
 	rdi->dparms.props.max_qp_rd_atom = QIB_MAX_RDMA_ATOMIC;
 	rdi->dparms.props.max_qp_init_rd_atom = 255;

drivers/infiniband/sw/rdmavt/mr.c

@@ -96,6 +96,8 @@ int rvt_driver_mr_init(struct rvt_dev_info *rdi)
 	for (i = 0; i < rdi->lkey_table.max; i++)
 		RCU_INIT_POINTER(rdi->lkey_table.table[i], NULL);
 
+	rdi->dparms.props.max_mr = rdi->lkey_table.max;
+	rdi->dparms.props.max_fmr = rdi->lkey_table.max;
 	return 0;
 }
 

drivers/infiniband/sw/rdmavt/qp.c

@@ -594,7 +594,8 @@ static int alloc_qpn(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
 			offset = qpt->incr | ((offset & 1) ^ 1);
 		}
 		/* there can be no set bits in low-order QoS bits */
-		WARN_ON(offset & (BIT(rdi->dparms.qos_shift) - 1));
+		WARN_ON(rdi->dparms.qos_shift > 1 &&
+			offset & ((BIT(rdi->dparms.qos_shift - 1) - 1) << 1));
 		qpn = mk_qpn(qpt, map, offset);
 	}
 

drivers/infiniband/ulp/srp/ib_srp.c

@@ -148,6 +148,7 @@ MODULE_PARM_DESC(ch_count,
 
 static void srp_add_one(struct ib_device *device);
 static void srp_remove_one(struct ib_device *device, void *client_data);
+static void srp_rename_dev(struct ib_device *device, void *client_data);
 static void srp_recv_done(struct ib_cq *cq, struct ib_wc *wc);
 static void srp_handle_qp_err(struct ib_cq *cq, struct ib_wc *wc,
 		const char *opname);
@@ -162,7 +163,8 @@ static struct workqueue_struct *srp_remove_wq;
 static struct ib_client srp_client = {
 	.name   = "srp",
 	.add    = srp_add_one,
-	.remove = srp_remove_one
+	.remove = srp_remove_one,
+	.rename = srp_rename_dev
 };
 
 static struct ib_sa_client srp_sa_client;
@@ -4112,6 +4114,20 @@ static struct srp_host *srp_add_port(struct srp_device *device, u8 port)
 	return NULL;
 }
 
+static void srp_rename_dev(struct ib_device *device, void *client_data)
+{
+	struct srp_device *srp_dev = client_data;
+	struct srp_host *host, *tmp_host;
+
+	list_for_each_entry_safe(host, tmp_host, &srp_dev->dev_list, list) {
+		char name[IB_DEVICE_NAME_MAX + 8];
+
+		snprintf(name, sizeof(name), "srp-%s-%d",
+			 dev_name(&device->dev), host->port);
+		device_rename(&host->dev, name);
+	}
+}
+
 static void srp_add_one(struct ib_device *device)
 {
 	struct srp_device *srp_dev;

include/rdma/ib_verbs.h

@@ -2698,6 +2698,7 @@ struct ib_client {
 	const char *name;
 	void (*add)   (struct ib_device *);
 	void (*remove)(struct ib_device *, void *client_data);
+	void (*rename)(struct ib_device *dev, void *client_data);
 
 	/* Returns the net_dev belonging to this ib_client and matching the
 	 * given parameters.