6 files changed, 165 insertions, 63 deletions
diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/infiniband/hw/ehca/ehca_classes.h
index 5d7b7855afb9..7fc35cf0cddf 100644
--- a/drivers/infiniband/hw/ehca/ehca_classes.h
+++ b/drivers/infiniband/hw/ehca/ehca_classes.h
@@ -128,6 +128,8 @@ struct ehca_shca {
 	/* MR pgsize: bit 0-3 means 4K, 64K, 1M, 16M respectively */
 	u32 hca_cap_mr_pgsize;
 	int max_mtu;
+	int max_num_qps;
+	int max_num_cqs;
 	atomic_t num_cqs;
 	atomic_t num_qps;
 };
@@ -161,7 +163,8 @@ struct ehca_mod_qp_parm {
 /* struct for tracking if cqes have been reported to the application */
 struct ehca_qmap_entry {
 	u16 app_wr_id;
-	u16 reported;
+	u8 reported;
+	u8 cqe_req;
 };
 
 struct ehca_queue_map {
@@ -169,6 +172,7 @@ struct ehca_queue_map {
 	unsigned int entries;
 	unsigned int tail;
 	unsigned int left_to_poll;
+	unsigned int next_wqe_idx;   /* Idx to first wqe to be flushed */
 };
 
 struct ehca_qp {
diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/infiniband/hw/ehca/ehca_cq.c
index 33647a95eb9a..2f4c28a30271 100644
--- a/drivers/infiniband/hw/ehca/ehca_cq.c
+++ b/drivers/infiniband/hw/ehca/ehca_cq.c
@@ -132,9 +132,9 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
 	if (cqe >= 0xFFFFFFFF - 64 - additional_cqe)
 		return ERR_PTR(-EINVAL);
 
-	if (!atomic_add_unless(&shca->num_cqs, 1, ehca_max_cq)) {
+	if (!atomic_add_unless(&shca->num_cqs, 1, shca->max_num_cqs)) {
 		ehca_err(device, "Unable to create CQ, max number of %i "
-			"CQs reached.", ehca_max_cq);
+			"CQs reached.", shca->max_num_cqs);
 		ehca_err(device, "To increase the maximum number of CQs "
 			"use the number_of_cqs module parameter.\n");
 		return ERR_PTR(-ENOSPC);
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/infiniband/hw/ehca/ehca_irq.c
index cb55be04442c..757035ea246f 100644
--- a/drivers/infiniband/hw/ehca/ehca_irq.c
+++ b/drivers/infiniband/hw/ehca/ehca_irq.c
@@ -359,36 +359,48 @@ static void notify_port_conf_change(struct ehca_shca *shca, int port_num)
 	*old_attr = new_attr;
 }
 
+/* replay modify_qp for sqps -- return 0 if all is well, 1 if AQP1 destroyed */
+static int replay_modify_qp(struct ehca_sport *sport)
+{
+	int aqp1_destroyed;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sport->mod_sqp_lock, flags);
+
+	aqp1_destroyed = !sport->ibqp_sqp[IB_QPT_GSI];
+
+	if (sport->ibqp_sqp[IB_QPT_SMI])
+		ehca_recover_sqp(sport->ibqp_sqp[IB_QPT_SMI]);
+	if (!aqp1_destroyed)
+		ehca_recover_sqp(sport->ibqp_sqp[IB_QPT_GSI]);
+
+	spin_unlock_irqrestore(&sport->mod_sqp_lock, flags);
+
+	return aqp1_destroyed;
+}
+
 static void parse_ec(struct ehca_shca *shca, u64 eqe)
 {
 	u8 ec   = EHCA_BMASK_GET(NEQE_EVENT_CODE, eqe);
 	u8 port = EHCA_BMASK_GET(NEQE_PORT_NUMBER, eqe);
 	u8 spec_event;
 	struct ehca_sport *sport = &shca->sport[port - 1];
-	unsigned long flags;
 
 	switch (ec) {
 	case 0x30: /* port availability change */
 		if (EHCA_BMASK_GET(NEQE_PORT_AVAILABILITY, eqe)) {
-			int suppress_event;
-			/* replay modify_qp for sqps */
-			spin_lock_irqsave(&sport->mod_sqp_lock, flags);
-			suppress_event = !sport->ibqp_sqp[IB_QPT_GSI];
-			if (sport->ibqp_sqp[IB_QPT_SMI])
-				ehca_recover_sqp(sport->ibqp_sqp[IB_QPT_SMI]);
-			if (!suppress_event)
-				ehca_recover_sqp(sport->ibqp_sqp[IB_QPT_GSI]);
-			spin_unlock_irqrestore(&sport->mod_sqp_lock, flags);
-
-			/* AQP1 was destroyed, ignore this event */
-			if (suppress_event)
-				break;
+			/* only replay modify_qp calls in autodetect mode;
+			 * if AQP1 was destroyed, the port is already down
+			 * again and we can drop the event.
+			 */
+			if (ehca_nr_ports < 0)
+				if (replay_modify_qp(sport))
+					break;
 
 			sport->port_state = IB_PORT_ACTIVE;
 			dispatch_port_event(shca, port, IB_EVENT_PORT_ACTIVE,
 					    "is active");
-			ehca_query_sma_attr(shca, port,
-					    &sport->saved_attr);
+			ehca_query_sma_attr(shca, port, &sport->saved_attr);
 		} else {
 			sport->port_state = IB_PORT_DOWN;
 			dispatch_port_event(shca, port, IB_EVENT_PORT_ERR,
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/infiniband/hw/ehca/ehca_main.c
index 598844d2edc9..bec7e0249358 100644
--- a/drivers/infiniband/hw/ehca/ehca_main.c
+++ b/drivers/infiniband/hw/ehca/ehca_main.c
@@ -44,6 +44,8 @@
 #include <linux/slab.h>
 #endif
 
+#include <linux/notifier.h>
+#include <linux/memory.h>
 #include "ehca_classes.h"
 #include "ehca_iverbs.h"
 #include "ehca_mrmw.h"
@@ -366,22 +368,23 @@ static int ehca_sense_attributes(struct ehca_shca *shca)
 			shca->hca_cap_mr_pgsize |= pgsize_map[i + 1];
 
 	/* Set maximum number of CQs and QPs to calculate EQ size */
-	if (ehca_max_qp == -1)
-		ehca_max_qp = min_t(int, rblock->max_qp, EHCA_MAX_NUM_QUEUES);
-	else if (ehca_max_qp < 1 || ehca_max_qp > rblock->max_qp) {
-		ehca_gen_err("Requested number of QPs is out of range (1 - %i) "
-			"specified by HW", rblock->max_qp);
-		ret = -EINVAL;
-		goto sense_attributes1;
+	if (shca->max_num_qps == -1)
+		shca->max_num_qps = min_t(int, rblock->max_qp,
+					  EHCA_MAX_NUM_QUEUES);
+	else if (shca->max_num_qps < 1 || shca->max_num_qps > rblock->max_qp) {
+		ehca_gen_warn("The requested number of QPs is out of range "
+			      "(1 - %i) specified by HW. Value is set to %i",
+			      rblock->max_qp, rblock->max_qp);
+		shca->max_num_qps = rblock->max_qp;
 	}
 
-	if (ehca_max_cq == -1)
-		ehca_max_cq = min_t(int, rblock->max_cq, EHCA_MAX_NUM_QUEUES);
-	else if (ehca_max_cq < 1 || ehca_max_cq > rblock->max_cq) {
-		ehca_gen_err("Requested number of CQs is out of range (1 - %i) "
-			"specified by HW", rblock->max_cq);
-		ret = -EINVAL;
-		goto sense_attributes1;
+	if (shca->max_num_cqs == -1)
+		shca->max_num_cqs = min_t(int, rblock->max_cq,
+					  EHCA_MAX_NUM_QUEUES);
+	else if (shca->max_num_cqs < 1 || shca->max_num_cqs > rblock->max_cq) {
+		ehca_gen_warn("The requested number of CQs is out of range "
+			      "(1 - %i) specified by HW. Value is set to %i",
+			      rblock->max_cq, rblock->max_cq);
 	}
 
 	/* query max MTU from first port -- it's the same for all ports */
@@ -733,9 +736,13 @@ static int __devinit ehca_probe(struct of_device *dev,
 		ehca_gen_err("Cannot allocate shca memory.");
 		return -ENOMEM;
 	}
+
 	mutex_init(&shca->modify_mutex);
 	atomic_set(&shca->num_cqs, 0);
 	atomic_set(&shca->num_qps, 0);
+	shca->max_num_qps = ehca_max_qp;
+	shca->max_num_cqs = ehca_max_cq;
+
 	for (i = 0; i < ARRAY_SIZE(shca->sport); i++)
 		spin_lock_init(&shca->sport[i].mod_sqp_lock);
 
@@ -755,7 +762,7 @@ static int __devinit ehca_probe(struct of_device *dev,
 		goto probe1;
 	}
 
-	eq_size = 2 * ehca_max_cq + 4 * ehca_max_qp;
+	eq_size = 2 * shca->max_num_cqs + 4 * shca->max_num_qps;
 	/* create event queues */
 	ret = ehca_create_eq(shca, &shca->eq, EHCA_EQ, eq_size);
 	if (ret) {
@@ -964,6 +971,40 @@ void ehca_poll_eqs(unsigned long data)
 	spin_unlock(&shca_list_lock);
 }
 
+static int ehca_mem_notifier(struct notifier_block *nb,
+			     unsigned long action, void *data)
+{
+	static unsigned long ehca_dmem_warn_time;
+
+	switch (action) {
+	case MEM_CANCEL_OFFLINE:
+	case MEM_CANCEL_ONLINE:
+	case MEM_ONLINE:
+	case MEM_OFFLINE:
+		return NOTIFY_OK;
+	case MEM_GOING_ONLINE:
+	case MEM_GOING_OFFLINE:
+		/* only ok if no hca is attached to the lpar */
+		spin_lock(&shca_list_lock);
+		if (list_empty(&shca_list)) {
+			spin_unlock(&shca_list_lock);
+			return NOTIFY_OK;
+		} else {
+			spin_unlock(&shca_list_lock);
+			if (printk_timed_ratelimit(&ehca_dmem_warn_time,
+						   30 * 1000))
+				ehca_gen_err("DMEM operations are not allowed"
+					     "in conjunction with eHCA");
+			return NOTIFY_BAD;
+		}
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block ehca_mem_nb = {
+	.notifier_call = ehca_mem_notifier,
+};
+
 static int __init ehca_module_init(void)
 {
 	int ret;
@@ -991,6 +1032,12 @@ static int __init ehca_module_init(void)
 		goto module_init2;
 	}
 
+	ret = register_memory_notifier(&ehca_mem_nb);
+	if (ret) {
+		ehca_gen_err("Failed registering memory add/remove notifier");
+		goto module_init3;
+	}
+
 	if (ehca_poll_all_eqs != 1) {
 		ehca_gen_err("WARNING!!!");
 		ehca_gen_err("It is possible to lose interrupts.");
@@ -1003,6 +1050,9 @@ static int __init ehca_module_init(void)
 
 	return 0;
 
+module_init3:
+	ibmebus_unregister_driver(&ehca_driver);
+
 module_init2:
 	ehca_destroy_slab_caches();
 
@@ -1018,6 +1068,8 @@ static void __exit ehca_module_exit(void)
 
 	ibmebus_unregister_driver(&ehca_driver);
 
+	unregister_memory_notifier(&ehca_mem_nb);
+
 	ehca_destroy_slab_caches();
 
 	ehca_destroy_comp_pool();
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/infiniband/hw/ehca/ehca_qp.c
index 4dbe2870e014..cadbf0cdd910 100644
--- a/drivers/infiniband/hw/ehca/ehca_qp.c
+++ b/drivers/infiniband/hw/ehca/ehca_qp.c
@@ -435,9 +435,13 @@ static void reset_queue_map(struct ehca_queue_map *qmap)
 {
 	int i;
 
-	qmap->tail = 0;
-	for (i = 0; i < qmap->entries; i++)
+	qmap->tail = qmap->entries - 1;
+	qmap->left_to_poll = 0;
+	qmap->next_wqe_idx = 0;
+	for (i = 0; i < qmap->entries; i++) {
 		qmap->map[i].reported = 1;
+		qmap->map[i].cqe_req = 0;
+	}
 }
 
 /*
@@ -465,9 +469,9 @@ static struct ehca_qp *internal_create_qp(
 	u32 swqe_size = 0, rwqe_size = 0, ib_qp_num;
 	unsigned long flags;
 
-	if (!atomic_add_unless(&shca->num_qps, 1, ehca_max_qp)) {
+	if (!atomic_add_unless(&shca->num_qps, 1, shca->max_num_qps)) {
 		ehca_err(pd->device, "Unable to create QP, max number of %i "
-			 "QPs reached.", ehca_max_qp);
+			 "QPs reached.", shca->max_num_qps);
 		ehca_err(pd->device, "To increase the maximum number of QPs "
 			 "use the number_of_qps module parameter.\n");
 		return ERR_PTR(-ENOSPC);
@@ -502,6 +506,12 @@ static struct ehca_qp *internal_create_qp(
 	if (init_attr->srq) {
 		my_srq = container_of(init_attr->srq, struct ehca_qp, ib_srq);
 
+		if (qp_type == IB_QPT_UC) {
+			ehca_err(pd->device, "UC with SRQ not supported");
+			atomic_dec(&shca->num_qps);
+			return ERR_PTR(-EINVAL);
+		}
+
 		has_srq = 1;
 		parms.ext_type = EQPT_SRQBASE;
 		parms.srq_qpn = my_srq->real_qp_num;
@@ -854,6 +864,11 @@ static struct ehca_qp *internal_create_qp(
 	if (qp_type == IB_QPT_GSI) {
 		h_ret = ehca_define_sqp(shca, my_qp, init_attr);
 		if (h_ret != H_SUCCESS) {
+			kfree(my_qp->mod_qp_parm);
+			my_qp->mod_qp_parm = NULL;
+			/* the QP pointer is no longer valid */
+			shca->sport[init_attr->port_num - 1].ibqp_sqp[qp_type] =
+				NULL;
 			ret = ehca2ib_return_code(h_ret);
 			goto create_qp_exit6;
 		}
@@ -1110,6 +1125,7 @@ static int calc_left_cqes(u64 wqe_p, struct ipz_queue *ipz_queue,
 	void *wqe_v;
 	u64 q_ofs;
 	u32 wqe_idx;
+	unsigned int tail_idx;
 
 	/* convert real to abs address */
 	wqe_p = wqe_p & (~(1UL << 63));
@@ -1122,12 +1138,17 @@ static int calc_left_cqes(u64 wqe_p, struct ipz_queue *ipz_queue,
 		return -EFAULT;
 	}
 
+	tail_idx = (qmap->tail + 1) % qmap->entries;
 	wqe_idx = q_ofs / ipz_queue->qe_size;
-	if (wqe_idx < qmap->tail)
-		qmap->left_to_poll = (qmap->entries - qmap->tail) + wqe_idx;
-	else
-		qmap->left_to_poll = wqe_idx - qmap->tail;
 
+	/* check all processed wqes, whether a cqe is requested or not */
+	while (tail_idx != wqe_idx) {
+		if (qmap->map[tail_idx].cqe_req)
+			qmap->left_to_poll++;
+		tail_idx = (tail_idx + 1) % qmap->entries;
+	}
+	/* save index in queue, where we have to start flushing */
+	qmap->next_wqe_idx = wqe_idx;
 	return 0;
 }
 
@@ -1174,10 +1195,14 @@ static int check_for_left_cqes(struct ehca_qp *my_qp, struct ehca_shca *shca)
 	} else {
 		spin_lock_irqsave(&my_qp->send_cq->spinlock, flags);
 		my_qp->sq_map.left_to_poll = 0;
+		my_qp->sq_map.next_wqe_idx = (my_qp->sq_map.tail + 1) %
+						my_qp->sq_map.entries;
 		spin_unlock_irqrestore(&my_qp->send_cq->spinlock, flags);
 
 		spin_lock_irqsave(&my_qp->recv_cq->spinlock, flags);
 		my_qp->rq_map.left_to_poll = 0;
+		my_qp->rq_map.next_wqe_idx = (my_qp->rq_map.tail + 1) %
+						my_qp->rq_map.entries;
 		spin_unlock_irqrestore(&my_qp->recv_cq->spinlock, flags);
 	}
 
diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/infiniband/hw/ehca/ehca_reqs.c
index 64928079eafa..00a648f4316c 100644
--- a/drivers/infiniband/hw/ehca/ehca_reqs.c
+++ b/drivers/infiniband/hw/ehca/ehca_reqs.c
@@ -179,6 +179,7 @@ static inline int ehca_write_swqe(struct ehca_qp *qp,
 
 	qmap_entry->app_wr_id = get_app_wr_id(send_wr->wr_id);
 	qmap_entry->reported = 0;
+	qmap_entry->cqe_req = 0;
 
 	switch (send_wr->opcode) {
 	case IB_WR_SEND:
@@ -203,8 +204,10 @@ static inline int ehca_write_swqe(struct ehca_qp *qp,
 
 	if ((send_wr->send_flags & IB_SEND_SIGNALED ||
 	    qp->init_attr.sq_sig_type == IB_SIGNAL_ALL_WR)
-	    && !hidden)
+	    && !hidden) {
 		wqe_p->wr_flag |= WQE_WRFLAG_REQ_SIGNAL_COM;
+		qmap_entry->cqe_req = 1;
+	}
 
 	if (send_wr->opcode == IB_WR_SEND_WITH_IMM ||
 	    send_wr->opcode == IB_WR_RDMA_WRITE_WITH_IMM) {
@@ -569,6 +572,7 @@ static int internal_post_recv(struct ehca_qp *my_qp,
 		qmap_entry = &my_qp->rq_map.map[rq_map_idx];
 		qmap_entry->app_wr_id = get_app_wr_id(cur_recv_wr->wr_id);
 		qmap_entry->reported = 0;
+		qmap_entry->cqe_req = 1;
 
 		wqe_cnt++;
 	} /* eof for cur_recv_wr */
@@ -706,27 +710,34 @@ repoll:
 		goto repoll;
 	wc->qp = &my_qp->ib_qp;
 
+	qmap_tail_idx = get_app_wr_id(cqe->work_request_id);
+	if (!(cqe->w_completion_flags & WC_SEND_RECEIVE_BIT))
+		/* We got a send completion. */
+		qmap = &my_qp->sq_map;
+	else
+		/* We got a receive completion. */
+		qmap = &my_qp->rq_map;
+
+	/* advance the tail pointer */
+	qmap->tail = qmap_tail_idx;
+
 	if (is_error) {
 		/*
 		 * set left_to_poll to 0 because in error state, we will not
 		 * get any additional CQEs
 		 */
-		ehca_add_to_err_list(my_qp, 1);
+		my_qp->sq_map.next_wqe_idx = (my_qp->sq_map.tail + 1) %
+						my_qp->sq_map.entries;
 		my_qp->sq_map.left_to_poll = 0;
+		ehca_add_to_err_list(my_qp, 1);
 
+		my_qp->rq_map.next_wqe_idx = (my_qp->rq_map.tail + 1) %
+						my_qp->rq_map.entries;
+		my_qp->rq_map.left_to_poll = 0;
 		if (HAS_RQ(my_qp))
 			ehca_add_to_err_list(my_qp, 0);
-		my_qp->rq_map.left_to_poll = 0;
 	}
 
-	qmap_tail_idx = get_app_wr_id(cqe->work_request_id);
-	if (!(cqe->w_completion_flags & WC_SEND_RECEIVE_BIT))
-		/* We got a send completion. */
-		qmap = &my_qp->sq_map;
-	else
-		/* We got a receive completion. */
-		qmap = &my_qp->rq_map;
-
 	qmap_entry = &qmap->map[qmap_tail_idx];
 	if (qmap_entry->reported) {
 		ehca_warn(cq->device, "Double cqe on qp_num=%#x",
@@ -738,10 +749,6 @@ repoll:
 	wc->wr_id = replace_wr_id(cqe->work_request_id, qmap_entry->app_wr_id);
 	qmap_entry->reported = 1;
 
-	/* this is a proper completion, we need to advance the tail pointer */
-	if (++qmap->tail == qmap->entries)
-		qmap->tail = 0;
-
 	/* if left_to_poll is decremented to 0, add the QP to the error list */
 	if (qmap->left_to_poll > 0) {
 		qmap->left_to_poll--;
@@ -805,13 +812,14 @@ static int generate_flush_cqes(struct ehca_qp *my_qp, struct ib_cq *cq,
 	else
 		qmap = &my_qp->rq_map;
 
-	qmap_entry = &qmap->map[qmap->tail];
+	qmap_entry = &qmap->map[qmap->next_wqe_idx];
 
 	while ((nr < num_entries) && (qmap_entry->reported == 0)) {
 		/* generate flush CQE */
+
 		memset(wc, 0, sizeof(*wc));
 
-		offset = qmap->tail * ipz_queue->qe_size;
+		offset = qmap->next_wqe_idx * ipz_queue->qe_size;
 		wqe = (struct ehca_wqe *)ipz_qeit_calc(ipz_queue, offset);
 		if (!wqe) {
 			ehca_err(cq->device, "Invalid wqe offset=%#lx on "
@@ -850,11 +858,12 @@ static int generate_flush_cqes(struct ehca_qp *my_qp, struct ib_cq *cq,
 
 		wc->qp = &my_qp->ib_qp;
 
-		/* mark as reported and advance tail pointer */
+		/* mark as reported and advance next_wqe pointer */
 		qmap_entry->reported = 1;
-		if (++qmap->tail == qmap->entries)
-			qmap->tail = 0;
-		qmap_entry = &qmap->map[qmap->tail];
+		qmap->next_wqe_idx++;
+		if (qmap->next_wqe_idx == qmap->entries)
+			qmap->next_wqe_idx = 0;
+		qmap_entry = &qmap->map[qmap->next_wqe_idx];
 
 		wc++; nr++;
 	}