Merge branch 'k.o/for-4.13-rc' into k.o/for-next

Merging our (hopefully) final -rc pull branch into our for-next branch
because some of our pending patches won't apply cleanly without having
the -rc patches in our tree.
Signed-off-by: Doug Ledford <dledford@redhat.com>

drivers/infiniband/core/addr.c

@@ -61,6 +61,7 @@ struct addr_req {
 	void (*callback)(int status, struct sockaddr *src_addr,
 			 struct rdma_dev_addr *addr, void *context);
 	unsigned long timeout;
+	struct delayed_work work;
 	int status;
 	u32 seq;
 };
@@ -293,7 +294,7 @@ int rdma_translate_ip(const struct sockaddr *addr,
 }
 EXPORT_SYMBOL(rdma_translate_ip);
 
-static void set_timeout(unsigned long time)
+static void set_timeout(struct delayed_work *delayed_work, unsigned long time)
 {
 	unsigned long delay;
 
@@ -301,7 +302,7 @@ static void set_timeout(unsigned long time)
 	if ((long)delay < 0)
 		delay = 0;
 
-	mod_delayed_work(addr_wq, &work, delay);
+	mod_delayed_work(addr_wq, delayed_work, delay);
 }
 
 static void queue_req(struct addr_req *req)
@@ -316,8 +317,7 @@ static void queue_req(struct addr_req *req)
 
 	list_add(&req->list, &temp_req->list);
 
-	if (req_list.next == &req->list)
-		set_timeout(req->timeout);
+	set_timeout(&req->work, req->timeout);
 	mutex_unlock(&lock);
 }
 
@@ -572,6 +572,37 @@ static int addr_resolve(struct sockaddr *src_in,
 	return ret;
 }
 
+static void process_one_req(struct work_struct *_work)
+{
+	struct addr_req *req;
+	struct sockaddr *src_in, *dst_in;
+
+	mutex_lock(&lock);
+	req = container_of(_work, struct addr_req, work.work);
+
+	if (req->status == -ENODATA) {
+		src_in = (struct sockaddr *)&req->src_addr;
+		dst_in = (struct sockaddr *)&req->dst_addr;
+		req->status = addr_resolve(src_in, dst_in, req->addr,
+					   true, req->seq);
+		if (req->status && time_after_eq(jiffies, req->timeout)) {
+			req->status = -ETIMEDOUT;
+		} else if (req->status == -ENODATA) {
+			/* requeue the work for retrying again */
+			set_timeout(&req->work, req->timeout);
+			mutex_unlock(&lock);
+			return;
+		}
+	}
+	list_del(&req->list);
+	mutex_unlock(&lock);
+
+	req->callback(req->status, (struct sockaddr *)&req->src_addr,
+		req->addr, req->context);
+	put_client(req->client);
+	kfree(req);
+}
+
 static void process_req(struct work_struct *work)
 {
 	struct addr_req *req, *temp_req;
@@ -589,20 +620,23 @@ static void process_req(struct work_struct *work)
 						   true, req->seq);
 			if (req->status && time_after_eq(jiffies, req->timeout))
 				req->status = -ETIMEDOUT;
-			else if (req->status == -ENODATA)
+			else if (req->status == -ENODATA) {
+				set_timeout(&req->work, req->timeout);
 				continue;
 			}
+		}
 		list_move_tail(&req->list, &done_list);
 	}
 
-	if (!list_empty(&req_list)) {
-		req = list_entry(req_list.next, struct addr_req, list);
-		set_timeout(req->timeout);
-	}
 	mutex_unlock(&lock);
 
 	list_for_each_entry_safe(req, temp_req, &done_list, list) {
 		list_del(&req->list);
+		/* It is safe to cancel other work items from this work item
+		 * because at a time there can be only one work item running
+		 * with this single threaded work queue.
+		 */
+		cancel_delayed_work(&req->work);
 		req->callback(req->status, (struct sockaddr *) &req->src_addr,
 			req->addr, req->context);
 		put_client(req->client);
@@ -645,6 +679,7 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
 	req->context = context;
 	req->client = client;
 	atomic_inc(&client->refcount);
+	INIT_DELAYED_WORK(&req->work, process_one_req);
 	req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq);
 
 	req->status = addr_resolve(src_in, dst_in, addr, true, req->seq);
@@ -699,7 +734,7 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr)
 			req->status = -ECANCELED;
 			req->timeout = jiffies;
 			list_move(&req->list, &req_list);
-			set_timeout(req->timeout);
+			set_timeout(&req->work, req->timeout);
 			break;
 		}
 	}
@@ -805,9 +840,8 @@ static int netevent_callback(struct notifier_block *self, unsigned long event,
 	if (event == NETEVENT_NEIGH_UPDATE) {
 		struct neighbour *neigh = ctx;
 
-		if (neigh->nud_state & NUD_VALID) {
-			set_timeout(jiffies);
-		}
+		if (neigh->nud_state & NUD_VALID)
+			set_timeout(&work, jiffies);
 	}
 	return 0;
 }
@@ -818,7 +852,7 @@ static struct notifier_block nb = {
 
 int addr_init(void)
 {
-	addr_wq = alloc_workqueue("ib_addr", WQ_MEM_RECLAIM, 0);
+	addr_wq = alloc_ordered_workqueue("ib_addr", WQ_MEM_RECLAIM);
 	if (!addr_wq)
 		return -ENOMEM;
 

drivers/infiniband/core/device.c

@@ -572,10 +572,11 @@ void ib_unregister_device(struct ib_device *device)
 	}
 	up_read(&lists_rwsem);
 
-	mutex_unlock(&device_mutex);
-
 	ib_device_unregister_rdmacg(device);
 	ib_device_unregister_sysfs(device);
+
+	mutex_unlock(&device_mutex);
+
 	ib_cache_cleanup_one(device);
 
 	ib_security_destroy_port_pkey_list(device);

drivers/infiniband/core/uverbs_cmd.c

@@ -1158,7 +1158,7 @@ ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file,
 			    int out_len)
 {
 	struct ib_uverbs_resize_cq	cmd;
-	struct ib_uverbs_resize_cq_resp	resp;
+	struct ib_uverbs_resize_cq_resp	resp = {};
 	struct ib_udata                 udata;
 	struct ib_cq			*cq;
 	int				ret = -EINVAL;

drivers/infiniband/core/uverbs_main.c

@@ -250,6 +250,7 @@ void ib_uverbs_release_file(struct kref *ref)
 	if (atomic_dec_and_test(&file->device->refcount))
 		ib_uverbs_comp_dev(file->device);
 
+	kobject_put(&file->device->kobj);
 	kfree(file);
 }
 
@@ -917,7 +918,6 @@ static int ib_uverbs_open(struct inode *inode, struct file *filp)
 static int ib_uverbs_close(struct inode *inode, struct file *filp)
 {
 	struct ib_uverbs_file *file = filp->private_data;
-	struct ib_uverbs_device *dev = file->device;
 
 	mutex_lock(&file->cleanup_mutex);
 	if (file->ucontext) {
@@ -939,7 +939,6 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp)
 			 ib_uverbs_release_async_event_file);
 
 	kref_put(&file->ref, ib_uverbs_release_file);
-	kobject_put(&dev->kobj);
 
 	return 0;
 }
@@ -1154,7 +1153,6 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 		kref_get(&file->ref);
 		mutex_unlock(&uverbs_dev->lists_mutex);
 
-		ib_uverbs_event_handler(&file->event_handler, &event);
 
 		mutex_lock(&file->cleanup_mutex);
 		ucontext = file->ucontext;
@@ -1171,6 +1169,7 @@ static void ib_uverbs_free_hw_resources(struct ib_uverbs_device *uverbs_dev,
 			 * for example due to freeing the resources
 			 * (e.g mmput).
 			 */
+			ib_uverbs_event_handler(&file->event_handler, &event);
 			ib_dev->disassociate_ucontext(ucontext);
 			mutex_lock(&file->cleanup_mutex);
 			ib_uverbs_cleanup_ucontext(file, ucontext, true);

drivers/infiniband/core/verbs.c

@@ -895,7 +895,6 @@ static const struct {
 } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = {
 	[IB_QPS_RESET] = {
 		[IB_QPS_RESET] = { .valid = 1 },
-		[IB_QPS_ERR] =   { .valid = 1 },
 		[IB_QPS_INIT]  = {
 			.valid = 1,
 			.req_param = {

drivers/infiniband/hw/cxgb4/mem.c

@@ -661,7 +661,7 @@ struct ib_mr *c4iw_alloc_mr(struct ib_pd *pd,
 	rhp = php->rhp;
 
 	if (mr_type != IB_MR_TYPE_MEM_REG ||
-	    max_num_sg > t4_max_fr_depth(&rhp->rdev.lldi.ulptx_memwrite_dsgl &&
+	    max_num_sg > t4_max_fr_depth(rhp->rdev.lldi.ulptx_memwrite_dsgl &&
 					 use_dsgl))
 		return ERR_PTR(-EINVAL);
 

drivers/infiniband/hw/hns/hns_roce_ah.c

@@ -64,8 +64,10 @@ struct ib_ah *hns_roce_create_ah(struct ib_pd *ibpd,
 	} else {
 		u8 *dmac = rdma_ah_retrieve_dmac(ah_attr);
 
-		if (!dmac)
+		if (!dmac) {
+			kfree(ah);
 			return ERR_PTR(-EINVAL);
+		}
 		memcpy(ah->av.mac, dmac, ETH_ALEN);
 	}
 

drivers/infiniband/hw/hns/hns_roce_hw_v1.c

@@ -733,7 +733,7 @@ static int hns_roce_v1_rsv_lp_qp(struct hns_roce_dev *hr_dev)
 			continue;
 
 		free_mr->mr_free_qp[i] = hns_roce_v1_create_lp_qp(hr_dev, pd);
-		if (IS_ERR(free_mr->mr_free_qp[i])) {
+		if (!free_mr->mr_free_qp[i]) {
 			dev_err(dev, "Create loop qp failed!\n");
 			goto create_lp_qp_failed;
 		}

drivers/infiniband/hw/i40iw/i40iw_ctrl.c

@@ -130,20 +130,32 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_commit_buf(
 	u64 base = 0;
 	u32 i, j;
 	u32 k = 0;
-	u32 low;
 
 	/* copy base values in obj_info */
-	for (i = I40IW_HMC_IW_QP, j = 0;
-			i <= I40IW_HMC_IW_PBLE; i++, j += 8) {
+	for (i = I40IW_HMC_IW_QP, j = 0; i <= I40IW_HMC_IW_PBLE; i++, j += 8) {
+		if ((i == I40IW_HMC_IW_SRQ) ||
+			(i == I40IW_HMC_IW_FSIMC) ||
+			(i == I40IW_HMC_IW_FSIAV)) {
+			info[i].base = 0;
+			info[i].cnt = 0;
+			continue;
+		}
 		get_64bit_val(buf, j, &temp);
 		info[i].base = RS_64_1(temp, 32) * 512;
 		if (info[i].base > base) {
 			base = info[i].base;
 			k = i;
 		}
-		low = (u32)(temp);
-		if (low)
-			info[i].cnt = low;
+		if (i == I40IW_HMC_IW_APBVT_ENTRY) {
+			info[i].cnt = 1;
+			continue;
+		}
+		if (i == I40IW_HMC_IW_QP)
+			info[i].cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS);
+		else if (i == I40IW_HMC_IW_CQ)
+			info[i].cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS);
+		else
+			info[i].cnt = (u32)(temp);
 	}
 	size = info[k].cnt * info[k].size + info[k].base;
 	if (size & 0x1FFFFF)
@@ -154,6 +166,31 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_commit_buf(
 	return 0;
 }
 
+/**
+ * i40iw_sc_decode_fpm_query() - Decode a 64 bit value into max count and size
+ * @buf: ptr to fpm query buffer
+ * @buf_idx: index into buf
+ * @info: ptr to i40iw_hmc_obj_info struct
+ * @rsrc_idx: resource index into info
+ *
+ * Decode a 64 bit value from fpm query buffer into max count and size
+ */
+static u64 i40iw_sc_decode_fpm_query(u64 *buf,
+					    u32 buf_idx,
+					    struct i40iw_hmc_obj_info *obj_info,
+					    u32 rsrc_idx)
+{
+	u64 temp;
+	u32 size;
+
+	get_64bit_val(buf, buf_idx, &temp);
+	obj_info[rsrc_idx].max_cnt = (u32)temp;
+	size = (u32)RS_64_1(temp, 32);
+	obj_info[rsrc_idx].size = LS_64_1(1, size);
+
+	return temp;
+}
+
 /**
  * i40iw_sc_parse_fpm_query_buf() - parses fpm query buffer
  * @buf: ptr to fpm query buffer
@@ -168,9 +205,9 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_query_buf(
 				struct i40iw_hmc_info *hmc_info,
 				struct i40iw_hmc_fpm_misc *hmc_fpm_misc)
 {
-	u64 temp;
 	struct i40iw_hmc_obj_info *obj_info;
-	u32 i, j, size;
+	u64 temp;
+	u32 size;
 	u16 max_pe_sds;
 
 	obj_info = hmc_info->hmc_obj;
@@ -185,41 +222,52 @@ static enum i40iw_status_code i40iw_sc_parse_fpm_query_buf(
 	hmc_fpm_misc->max_sds = max_pe_sds;
 	hmc_info->sd_table.sd_cnt = max_pe_sds + hmc_info->first_sd_index;
 
-	for (i = I40IW_HMC_IW_QP, j = 8;
-	     i <= I40IW_HMC_IW_ARP; i++, j += 8) {
-		get_64bit_val(buf, j, &temp);
-		if (i == I40IW_HMC_IW_QP)
-			obj_info[i].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS);
-		else if (i == I40IW_HMC_IW_CQ)
-			obj_info[i].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS);
-		else
-			obj_info[i].max_cnt = (u32)temp;
-
+	get_64bit_val(buf, 8, &temp);
+	obj_info[I40IW_HMC_IW_QP].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_QPS);
 	size = (u32)RS_64_1(temp, 32);
-		obj_info[i].size = ((u64)1 << size);
-	}
-	for (i = I40IW_HMC_IW_MR, j = 48;
-			i <= I40IW_HMC_IW_PBLE; i++, j += 8) {
-		get_64bit_val(buf, j, &temp);
-		obj_info[i].max_cnt = (u32)temp;
+	obj_info[I40IW_HMC_IW_QP].size = LS_64_1(1, size);
+
+	get_64bit_val(buf, 16, &temp);
+	obj_info[I40IW_HMC_IW_CQ].max_cnt = (u32)RS_64(temp, I40IW_QUERY_FPM_MAX_CQS);
 	size = (u32)RS_64_1(temp, 32);
-		obj_info[i].size = LS_64_1(1, size);
-	}
+	obj_info[I40IW_HMC_IW_CQ].size = LS_64_1(1, size);
+
+	i40iw_sc_decode_fpm_query(buf, 32, obj_info, I40IW_HMC_IW_HTE);
+	i40iw_sc_decode_fpm_query(buf, 40, obj_info, I40IW_HMC_IW_ARP);
+
+	obj_info[I40IW_HMC_IW_APBVT_ENTRY].size = 8192;
+	obj_info[I40IW_HMC_IW_APBVT_ENTRY].max_cnt = 1;
+
+	i40iw_sc_decode_fpm_query(buf, 48, obj_info, I40IW_HMC_IW_MR);
+	i40iw_sc_decode_fpm_query(buf, 56, obj_info, I40IW_HMC_IW_XF);
 
-	get_64bit_val(buf, 120, &temp);
-	hmc_fpm_misc->max_ceqs = (u8)RS_64(temp, I40IW_QUERY_FPM_MAX_CEQS);
-	get_64bit_val(buf, 120, &temp);
-	hmc_fpm_misc->ht_multiplier = RS_64(temp, I40IW_QUERY_FPM_HTMULTIPLIER);
-	get_64bit_val(buf, 120, &temp);
-	hmc_fpm_misc->timer_bucket = RS_64(temp, I40IW_QUERY_FPM_TIMERBUCKET);
 	get_64bit_val(buf, 64, &temp);
+	obj_info[I40IW_HMC_IW_XFFL].max_cnt = (u32)temp;
+	obj_info[I40IW_HMC_IW_XFFL].size = 4;
 	hmc_fpm_misc->xf_block_size = RS_64(temp, I40IW_QUERY_FPM_XFBLOCKSIZE);
 	if (!hmc_fpm_misc->xf_block_size)
 		return I40IW_ERR_INVALID_SIZE;
+
+	i40iw_sc_decode_fpm_query(buf, 72, obj_info, I40IW_HMC_IW_Q1);
+
 	get_64bit_val(buf, 80, &temp);
+	obj_info[I40IW_HMC_IW_Q1FL].max_cnt = (u32)temp;
+	obj_info[I40IW_HMC_IW_Q1FL].size = 4;
 	hmc_fpm_misc->q1_block_size = RS_64(temp, I40IW_QUERY_FPM_Q1BLOCKSIZE);
 	if (!hmc_fpm_misc->q1_block_size)
 		return I40IW_ERR_INVALID_SIZE;
+
+	i40iw_sc_decode_fpm_query(buf, 88, obj_info, I40IW_HMC_IW_TIMER);
+
+	get_64bit_val(buf, 112, &temp);
+	obj_info[I40IW_HMC_IW_PBLE].max_cnt = (u32)temp;
+	obj_info[I40IW_HMC_IW_PBLE].size = 8;
+
+	get_64bit_val(buf, 120, &temp);
+	hmc_fpm_misc->max_ceqs = (u8)RS_64(temp, I40IW_QUERY_FPM_MAX_CEQS);
+	hmc_fpm_misc->ht_multiplier = RS_64(temp, I40IW_QUERY_FPM_HTMULTIPLIER);
+	hmc_fpm_misc->timer_bucket = RS_64(temp, I40IW_QUERY_FPM_TIMERBUCKET);
+
 	return 0;
 }
 
@@ -3392,13 +3440,6 @@ enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev, u8 hmc_fn_
 		hmc_info->sd_table.sd_entry = virt_mem.va;
 	}
 
-	/* fill size of objects which are fixed */
-	hmc_info->hmc_obj[I40IW_HMC_IW_XFFL].size = 4;
-	hmc_info->hmc_obj[I40IW_HMC_IW_Q1FL].size = 4;
-	hmc_info->hmc_obj[I40IW_HMC_IW_PBLE].size = 8;
-	hmc_info->hmc_obj[I40IW_HMC_IW_APBVT_ENTRY].size = 8192;
-	hmc_info->hmc_obj[I40IW_HMC_IW_APBVT_ENTRY].max_cnt = 1;
-
 	return ret_code;
 }
 
@@ -4840,7 +4881,7 @@ void i40iw_vsi_stats_free(struct i40iw_sc_vsi *vsi)
 {
 	u8 fcn_id = vsi->fcn_id;
 
-	if ((vsi->stats_fcn_id_alloc) && (fcn_id != I40IW_INVALID_FCN_ID))
+	if (vsi->stats_fcn_id_alloc && fcn_id < I40IW_MAX_STATS_COUNT)
 		vsi->dev->fcn_id_array[fcn_id] = false;
 	i40iw_hw_stats_stop_timer(vsi);
 }

drivers/infiniband/hw/i40iw/i40iw_d.h

@@ -1507,8 +1507,8 @@ enum {
 	I40IW_CQ0_ALIGNMENT_MASK =		(256 - 1),
 	I40IW_HOST_CTX_ALIGNMENT_MASK =		(4 - 1),
 	I40IW_SHADOWAREA_MASK =			(128 - 1),
-	I40IW_FPM_QUERY_BUF_ALIGNMENT_MASK =	0,
-	I40IW_FPM_COMMIT_BUF_ALIGNMENT_MASK =	0
+	I40IW_FPM_QUERY_BUF_ALIGNMENT_MASK =	(4 - 1),
+	I40IW_FPM_COMMIT_BUF_ALIGNMENT_MASK =	(4 - 1)
 };
 
 enum i40iw_alignment {

drivers/infiniband/hw/i40iw/i40iw_puda.c

@@ -685,7 +685,7 @@ static enum i40iw_status_code i40iw_puda_cq_create(struct i40iw_puda_rsrc *rsrc)
 	cqsize = rsrc->cq_size * (sizeof(struct i40iw_cqe));
 	tsize = cqsize + sizeof(struct i40iw_cq_shadow_area);
 	ret = i40iw_allocate_dma_mem(dev->hw, &rsrc->cqmem, tsize,
-				     I40IW_CQ0_ALIGNMENT_MASK);
+				     I40IW_CQ0_ALIGNMENT);
 	if (ret)
 		return ret;
 

drivers/infiniband/hw/i40iw/i40iw_status.h

@@ -62,7 +62,7 @@ enum i40iw_status_code {
 	I40IW_ERR_INVALID_ALIGNMENT = -23,
 	I40IW_ERR_FLUSHED_QUEUE = -24,
 	I40IW_ERR_INVALID_PUSH_PAGE_INDEX = -25,
-	I40IW_ERR_INVALID_IMM_DATA_SIZE = -26,
+	I40IW_ERR_INVALID_INLINE_DATA_SIZE = -26,
 	I40IW_ERR_TIMEOUT = -27,
 	I40IW_ERR_OPCODE_MISMATCH = -28,
 	I40IW_ERR_CQP_COMPL_ERROR = -29,

drivers/infiniband/hw/i40iw/i40iw_uk.c

@@ -435,7 +435,7 @@ static enum i40iw_status_code i40iw_inline_rdma_write(struct i40iw_qp_uk *qp,
 
 	op_info = &info->op.inline_rdma_write;
 	if (op_info->len > I40IW_MAX_INLINE_DATA_SIZE)
-		return I40IW_ERR_INVALID_IMM_DATA_SIZE;
+		return I40IW_ERR_INVALID_INLINE_DATA_SIZE;
 
 	ret_code = i40iw_inline_data_size_to_wqesize(op_info->len, &wqe_size);
 	if (ret_code)
@@ -511,7 +511,7 @@ static enum i40iw_status_code i40iw_inline_send(struct i40iw_qp_uk *qp,
 
 	op_info = &info->op.inline_send;
 	if (op_info->len > I40IW_MAX_INLINE_DATA_SIZE)
-		return I40IW_ERR_INVALID_IMM_DATA_SIZE;
+		return I40IW_ERR_INVALID_INLINE_DATA_SIZE;
 
 	ret_code = i40iw_inline_data_size_to_wqesize(op_info->len, &wqe_size);
 	if (ret_code)
@@ -784,7 +784,7 @@ static enum i40iw_status_code i40iw_cq_poll_completion(struct i40iw_cq_uk *cq,
 	get_64bit_val(cqe, 0, &qword0);
 	get_64bit_val(cqe, 16, &qword2);
 
-	info->tcp_seq_num = (u8)RS_64(qword0, I40IWCQ_TCPSEQNUM);
+	info->tcp_seq_num = (u32)RS_64(qword0, I40IWCQ_TCPSEQNUM);
 
 	info->qp_id = (u32)RS_64(qword2, I40IWCQ_QPID);
 
@@ -1187,7 +1187,7 @@ enum i40iw_status_code i40iw_inline_data_size_to_wqesize(u32 data_size,
 							 u8 *wqe_size)
 {
 	if (data_size > I40IW_MAX_INLINE_DATA_SIZE)
-		return I40IW_ERR_INVALID_IMM_DATA_SIZE;
+		return I40IW_ERR_INVALID_INLINE_DATA_SIZE;
 
 	if (data_size <= 16)
 		*wqe_size = I40IW_QP_WQE_MIN_SIZE;

drivers/infiniband/hw/vmw_pvrdma/pvrdma_cq.c

@@ -65,13 +65,28 @@ int pvrdma_req_notify_cq(struct ib_cq *ibcq,
 	struct pvrdma_dev *dev = to_vdev(ibcq->device);
 	struct pvrdma_cq *cq = to_vcq(ibcq);
 	u32 val = cq->cq_handle;
+	unsigned long flags;
+	int has_data = 0;
 
 	val |= (notify_flags & IB_CQ_SOLICITED_MASK) == IB_CQ_SOLICITED ?
 		PVRDMA_UAR_CQ_ARM_SOL : PVRDMA_UAR_CQ_ARM;
 
+	spin_lock_irqsave(&cq->cq_lock, flags);
+
 	pvrdma_write_uar_cq(dev, val);
 
-	return 0;
+	if (notify_flags & IB_CQ_REPORT_MISSED_EVENTS) {
+		unsigned int head;
+
+		has_data = pvrdma_idx_ring_has_data(&cq->ring_state->rx,
+						    cq->ibcq.cqe, &head);
+		if (unlikely(has_data == PVRDMA_INVALID_IDX))
+			dev_err(&dev->pdev->dev, "CQ ring state invalid\n");
+	}
+
+	spin_unlock_irqrestore(&cq->cq_lock, flags);
+
+	return has_data;
 }
 
 /**

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -336,6 +336,7 @@ struct ipoib_dev_priv {
 	unsigned long flags;
 
 	struct rw_semaphore vlan_rwsem;
+	struct mutex mcast_mutex;
 
 	struct rb_root  path_tree;
 	struct list_head path_list;

drivers/infiniband/ulp/ipoib/ipoib_cm.c

@@ -511,7 +511,6 @@ static int ipoib_cm_rx_handler(struct ib_cm_id *cm_id,
 	case IB_CM_REQ_RECEIVED:
 		return ipoib_cm_req_handler(cm_id, event);
 	case IB_CM_DREQ_RECEIVED:
-		p = cm_id->context;
 		ib_send_cm_drep(cm_id, NULL, 0);
 		/* Fall through */
 	case IB_CM_REJ_RECEIVED:

drivers/infiniband/ulp/ipoib/ipoib_ethtool.c

@@ -52,7 +52,8 @@ static const struct ipoib_stats ipoib_gstrings_stats[] = {
 	IPOIB_NETDEV_STAT(tx_bytes),
 	IPOIB_NETDEV_STAT(tx_errors),
 	IPOIB_NETDEV_STAT(rx_dropped),
-	IPOIB_NETDEV_STAT(tx_dropped)
+	IPOIB_NETDEV_STAT(tx_dropped),
+	IPOIB_NETDEV_STAT(multicast),
 };
 
 #define IPOIB_GLOBAL_STATS_LEN	ARRAY_SIZE(ipoib_gstrings_stats)

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -256,6 +256,8 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 
 	++dev->stats.rx_packets;
 	dev->stats.rx_bytes += skb->len;
+	if (skb->pkt_type == PACKET_MULTICAST)
+		dev->stats.multicast++;
 
 	skb->dev = dev;
 	if ((dev->features & NETIF_F_RXCSUM) &&
@@ -709,6 +711,27 @@ static int recvs_pending(struct net_device *dev)
 	return pending;
 }
 
+static void check_qp_movement_and_print(struct ipoib_dev_priv *priv,
+					struct ib_qp *qp,
+					enum ib_qp_state new_state)
+{
+	struct ib_qp_attr qp_attr;
+	struct ib_qp_init_attr query_init_attr;
+	int ret;
+
+	ret = ib_query_qp(qp, &qp_attr, IB_QP_STATE, &query_init_attr);
+	if (ret) {
+		ipoib_warn(priv, "%s: Failed to query QP\n", __func__);
+		return;
+	}
+	/* print according to the new-state and the previous state.*/
+	if (new_state == IB_QPS_ERR && qp_attr.qp_state == IB_QPS_RESET)
+		ipoib_dbg(priv, "Failed modify QP, IB_QPS_RESET to IB_QPS_ERR, acceptable\n");
+	else
+		ipoib_warn(priv, "Failed to modify QP to state: %d from state: %d\n",
+			   new_state, qp_attr.qp_state);
+}
+
 int ipoib_ib_dev_stop_default(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
@@ -728,7 +751,7 @@ int ipoib_ib_dev_stop_default(struct net_device *dev)
 	 */
 	qp_attr.qp_state = IB_QPS_ERR;
 	if (ib_modify_qp(priv->qp, &qp_attr, IB_QP_STATE))
-		ipoib_warn(priv, "Failed to modify QP to ERROR state\n");
+		check_qp_movement_and_print(priv, priv->qp, IB_QPS_ERR);
 
 	/* Wait for all sends and receives to complete */
 	begin = jiffies;

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -1559,6 +1559,7 @@ static void ipoib_flush_neighs(struct ipoib_dev_priv *priv)
 	int i, wait_flushed = 0;
 
 	init_completion(&priv->ntbl.flushed);
+	set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
 
 	spin_lock_irqsave(&priv->lock, flags);
 
@@ -1603,7 +1604,6 @@ static void ipoib_neigh_hash_uninit(struct net_device *dev)
 
 	ipoib_dbg(priv, "ipoib_neigh_hash_uninit\n");
 	init_completion(&priv->ntbl.deleted);
-	set_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
 
 	/* Stop GC if called at init fail need to cancel work */
 	stopped = test_and_set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
@@ -1846,6 +1846,7 @@ static const struct net_device_ops ipoib_netdev_ops_vf = {
 	.ndo_tx_timeout		 = ipoib_timeout,
 	.ndo_set_rx_mode	 = ipoib_set_mcast_list,
 	.ndo_get_iflink		 = ipoib_get_iflink,
+	.ndo_get_stats64	 = ipoib_get_stats,
 };
 
 void ipoib_setup_common(struct net_device *dev)
@@ -1876,6 +1877,7 @@ static void ipoib_build_priv(struct net_device *dev)
 	priv->dev = dev;
 	spin_lock_init(&priv->lock);
 	init_rwsem(&priv->vlan_rwsem);
+	mutex_init(&priv->mcast_mutex);
 
 	INIT_LIST_HEAD(&priv->path_list);
 	INIT_LIST_HEAD(&priv->child_intfs);
@@ -2172,14 +2174,14 @@ static struct net_device *ipoib_add_port(const char *format,
 	priv->dev->dev_id = port - 1;
 
 	result = ib_query_port(hca, port, &attr);
-	if (!result)
-		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
-	else {
+	if (result) {
 		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
 		       hca->name, port);
 		goto device_init_failed;
 	}
 
+	priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
+
 	/* MTU will be reset when mcast join happens */
 	priv->dev->mtu  = IPOIB_UD_MTU(priv->max_ib_mtu);
 	priv->mcast_mtu  = priv->admin_mtu = priv->dev->mtu;
@@ -2210,12 +2212,14 @@ static struct net_device *ipoib_add_port(const char *format,
 		printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
 		       hca->name, port, result);
 		goto device_init_failed;
-	} else
-		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+	}
+
+	memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw,
+	       sizeof(union ib_gid));
 	set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
 
 	result = ipoib_dev_init(priv->dev, hca, port);
-	if (result < 0) {
+	if (result) {
 		printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n",
 		       hca->name, port, result);
 		goto device_init_failed;
@@ -2364,6 +2368,7 @@ static int __init ipoib_init_module(void)
 	ipoib_sendq_size = max3(ipoib_sendq_size, 2 * MAX_SEND_CQE, IPOIB_MIN_QUEUE_SIZE);
 #ifdef CONFIG_INFINIBAND_IPOIB_CM
 	ipoib_max_conn_qp = min(ipoib_max_conn_qp, IPOIB_CM_MAX_CONN_QP);
+	ipoib_max_conn_qp = max(ipoib_max_conn_qp, 0);
 #endif
 
 	/*

drivers/infiniband/ulp/ipoib/ipoib_multicast.c

@@ -684,15 +684,10 @@ void ipoib_mcast_start_thread(struct net_device *dev)
 int ipoib_mcast_stop_thread(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(dev);
-	unsigned long flags;
 
 	ipoib_dbg_mcast(priv, "stopping multicast thread\n");
 
-	spin_lock_irqsave(&priv->lock, flags);
-	cancel_delayed_work(&priv->mcast_task);
-	spin_unlock_irqrestore(&priv->lock, flags);
-
-	flush_workqueue(priv->wq);
+	cancel_delayed_work_sync(&priv->mcast_task);
 
 	return 0;
 }
@@ -748,6 +743,14 @@ void ipoib_mcast_remove_list(struct list_head *remove_list)
 {
 	struct ipoib_mcast *mcast, *tmcast;
 
+	/*
+	 * make sure the in-flight joins have finished before we attempt
+	 * to leave
+	 */
+	list_for_each_entry_safe(mcast, tmcast, remove_list, list)
+		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
+			wait_for_completion(&mcast->done);
+
 	list_for_each_entry_safe(mcast, tmcast, remove_list, list) {
 		ipoib_mcast_leave(mcast->dev, mcast);
 		ipoib_mcast_free(mcast);
@@ -838,6 +841,7 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 	struct ipoib_mcast *mcast, *tmcast;
 	unsigned long flags;
 
+	mutex_lock(&priv->mcast_mutex);
 	ipoib_dbg_mcast(priv, "flushing multicast list\n");
 
 	spin_lock_irqsave(&priv->lock, flags);
@@ -856,15 +860,8 @@ void ipoib_mcast_dev_flush(struct net_device *dev)
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
 	ipoib_mcast_remove_list(&remove_list);
+	mutex_unlock(&priv->mcast_mutex);
 }
 
 static int ipoib_mcast_addr_is_valid(const u8 *addr, const u8 *broadcast)
@@ -982,14 +979,6 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 	netif_addr_unlock(dev);
 	local_irq_restore(flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
 	ipoib_mcast_remove_list(&remove_list);
 
 	/*