IB/hfi1: Move rvt_cq_wc struct into uapi directory

The rvt_cq_wc struct elements are shared between rdmavt and the providers
but not in uapi directory.  As per the comment in
https://marc.info/?l=linux-rdma&m=152296522708522&w=2 The hfi1 driver and
the rdma core driver are not using shared structures in the uapi
directory.

In that case, move rvt_cq_wc struct into the rvt-abi.h header file and
create a rvt_k_cq_w for the kernel completion queue.

Signed-off-by: Kamenee Arumugam <kamenee.arumugam@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

1 files changed, 123 insertions, 69 deletions

diff --git a/drivers/infiniband/sw/rdmavt/cq.c b/drivers/infiniband/sw/rdmavt/cq.c
index b46714a92b7a..2602ad8b8cb0 100644
--- a/drivers/infiniband/sw/rdmavt/cq.c
+++ b/drivers/infiniband/sw/rdmavt/cq.c
@@ -63,19 +63,33 @@ static struct workqueue_struct *comp_vector_wq;
  */
 void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 {
-	struct rvt_cq_wc *wc;
+	struct ib_uverbs_wc *uqueue = NULL;
+	struct ib_wc *kqueue = NULL;
+	struct rvt_cq_wc *u_wc = NULL;
+	struct rvt_k_cq_wc *k_wc = NULL;
 	unsigned long flags;
 	u32 head;
 	u32 next;
+	u32 tail;
 
 	spin_lock_irqsave(&cq->lock, flags);
 
+	if (cq->ip) {
+		u_wc = cq->queue;
+		uqueue = &u_wc->uqueue[0];
+		head = RDMA_READ_UAPI_ATOMIC(u_wc->head);
+		tail = RDMA_READ_UAPI_ATOMIC(u_wc->tail);
+	} else {
+		k_wc = cq->kqueue;
+		kqueue = &k_wc->kqueue[0];
+		head = k_wc->head;
+		tail = k_wc->tail;
+	}
+
 	/*
-	 * Note that the head pointer might be writable by user processes.
-	 * Take care to verify it is a sane value.
+	 * Note that the head pointer might be writable by
+	 * user processes.Take care to verify it is a sane value.
 	 */
-	wc = cq->queue;
-	head = wc->head;
 	if (head >= (unsigned)cq->ibcq.cqe) {
 		head = cq->ibcq.cqe;
 		next = 0;
@@ -83,7 +97,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		next = head + 1;
 	}
 
-	if (unlikely(next == wc->tail)) {
+	if (unlikely(next == tail)) {
 		spin_unlock_irqrestore(&cq->lock, flags);
 		if (cq->ibcq.event_handler) {
 			struct ib_event ev;
@@ -96,27 +110,27 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		return;
 	}
 	trace_rvt_cq_enter(cq, entry, head);
-	if (cq->ip) {
-		wc->uqueue[head].wr_id = entry->wr_id;
-		wc->uqueue[head].status = entry->status;
-		wc->uqueue[head].opcode = entry->opcode;
-		wc->uqueue[head].vendor_err = entry->vendor_err;
-		wc->uqueue[head].byte_len = entry->byte_len;
-		wc->uqueue[head].ex.imm_data = entry->ex.imm_data;
-		wc->uqueue[head].qp_num = entry->qp->qp_num;
-		wc->uqueue[head].src_qp = entry->src_qp;
-		wc->uqueue[head].wc_flags = entry->wc_flags;
-		wc->uqueue[head].pkey_index = entry->pkey_index;
-		wc->uqueue[head].slid = ib_lid_cpu16(entry->slid);
-		wc->uqueue[head].sl = entry->sl;
-		wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits;
-		wc->uqueue[head].port_num = entry->port_num;
+	if (uqueue) {
+		uqueue[head].wr_id = entry->wr_id;
+		uqueue[head].status = entry->status;
+		uqueue[head].opcode = entry->opcode;
+		uqueue[head].vendor_err = entry->vendor_err;
+		uqueue[head].byte_len = entry->byte_len;
+		uqueue[head].ex.imm_data = entry->ex.imm_data;
+		uqueue[head].qp_num = entry->qp->qp_num;
+		uqueue[head].src_qp = entry->src_qp;
+		uqueue[head].wc_flags = entry->wc_flags;
+		uqueue[head].pkey_index = entry->pkey_index;
+		uqueue[head].slid = ib_lid_cpu16(entry->slid);
+		uqueue[head].sl = entry->sl;
+		uqueue[head].dlid_path_bits = entry->dlid_path_bits;
+		uqueue[head].port_num = entry->port_num;
 		/* Make sure entry is written before the head index. */
-		smp_wmb();
+		RDMA_WRITE_UAPI_ATOMIC(u_wc->head, next);
 	} else {
-		wc->kqueue[head] = *entry;
+		kqueue[head] = *entry;
+		k_wc->head = next;
 	}
-	wc->head = next;
 
 	if (cq->notify == IB_CQ_NEXT_COMP ||
 	    (cq->notify == IB_CQ_SOLICITED &&
@@ -179,8 +193,9 @@ int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 {
 	struct ib_device *ibdev = ibcq->device;
 	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
-	struct rvt_cq *cq = container_of(ibcq, struct rvt_cq, ibcq);
-	struct rvt_cq_wc *wc;
+	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
+	struct rvt_cq_wc *u_wc = NULL;
+	struct rvt_k_cq_wc *k_wc = NULL;
 	u32 sz;
 	unsigned int entries = attr->cqe;
 	int comp_vector = attr->comp_vector;
@@ -204,22 +219,28 @@ int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	 * We need to use vmalloc() in order to support mmap and large
 	 * numbers of entries.
 	 */
-	sz = sizeof(*wc);
-	if (udata && udata->outlen >= sizeof(__u64))
-		sz += sizeof(struct ib_uverbs_wc) * (entries + 1);
-	else
-		sz += sizeof(struct ib_wc) * (entries + 1);
-	wc = udata ?
-		vmalloc_user(sz) :
-		vzalloc_node(sz, rdi->dparms.node);
-	if (!wc)
-		return -ENOMEM;
+	if (udata && udata->outlen >= sizeof(__u64)) {
+		sz = sizeof(struct ib_uverbs_wc) * (entries + 1);
+		sz += sizeof(*u_wc);
+		u_wc = vmalloc_user(sz);
+		if (!u_wc)
+			return -ENOMEM;
+	} else {
+		sz = sizeof(struct ib_wc) * (entries + 1);
+		sz += sizeof(*k_wc);
+		k_wc = vzalloc_node(sz, rdi->dparms.node);
+		if (!k_wc)
+			return -ENOMEM;
+	}
+
 	/*
 	 * Return the address of the WC as the offset to mmap.
 	 * See rvt_mmap() for details.
 	 */
 	if (udata && udata->outlen >= sizeof(__u64)) {
-		cq->ip = rvt_create_mmap_info(rdi, sz, udata, wc);
+		int err;
+
+		cq->ip = rvt_create_mmap_info(rdi, sz, udata, u_wc);
 		if (!cq->ip) {
 			err = -ENOMEM;
 			goto bail_wc;
@@ -264,7 +285,10 @@ int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 	cq->notify = RVT_CQ_NONE;
 	spin_lock_init(&cq->lock);
 	INIT_WORK(&cq->comptask, send_complete);
-	cq->queue = wc;
+	if (u_wc)
+		cq->queue = u_wc;
+	else
+		cq->kqueue = k_wc;
 
 	trace_rvt_create_cq(cq, attr);
 	return 0;
@@ -272,7 +296,8 @@ int rvt_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr,
 bail_ip:
 	kfree(cq->ip);
 bail_wc:
-	vfree(wc);
+	vfree(u_wc);
+	vfree(k_wc);
 	return err;
 }
 
@@ -322,9 +347,16 @@ int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags)
 	if (cq->notify != IB_CQ_NEXT_COMP)
 		cq->notify = notify_flags & IB_CQ_SOLICITED_MASK;
 
-	if ((notify_flags & IB_CQ_REPORT_MISSED_EVENTS) &&
-	    cq->queue->head != cq->queue->tail)
-		ret = 1;
+	if (notify_flags & IB_CQ_REPORT_MISSED_EVENTS) {
+		if (cq->queue) {
+			if (RDMA_READ_UAPI_ATOMIC(cq->queue->head) !=
+				RDMA_READ_UAPI_ATOMIC(cq->queue->tail))
+				ret = 1;
+		} else {
+			if (cq->kqueue->head != cq->kqueue->tail)
+				ret = 1;
+		}
+	}
 
 	spin_unlock_irqrestore(&cq->lock, flags);
 
@@ -340,12 +372,14 @@ int rvt_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_flags)
 int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 {
 	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
-	struct rvt_cq_wc *old_wc;
-	struct rvt_cq_wc *wc;
 	u32 head, tail, n;
 	int ret;
 	u32 sz;
 	struct rvt_dev_info *rdi = cq->rdi;
+	struct rvt_cq_wc *u_wc = NULL;
+	struct rvt_cq_wc *old_u_wc = NULL;
+	struct rvt_k_cq_wc *k_wc = NULL;
+	struct rvt_k_cq_wc *old_k_wc = NULL;
 
 	if (cqe < 1 || cqe > rdi->dparms.props.max_cqe)
 		return -EINVAL;
@@ -353,17 +387,19 @@ int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 	/*
 	 * Need to use vmalloc() if we want to support large #s of entries.
 	 */
-	sz = sizeof(*wc);
-	if (udata && udata->outlen >= sizeof(__u64))
-		sz += sizeof(struct ib_uverbs_wc) * (cqe + 1);
-	else
-		sz += sizeof(struct ib_wc) * (cqe + 1);
-	wc = udata ?
-		vmalloc_user(sz) :
-		vzalloc_node(sz, rdi->dparms.node);
-	if (!wc)
-		return -ENOMEM;
-
+	if (udata && udata->outlen >= sizeof(__u64)) {
+		sz = sizeof(struct ib_uverbs_wc) * (cqe + 1);
+		sz += sizeof(*u_wc);
+		u_wc = vmalloc_user(sz);
+		if (!u_wc)
+			return -ENOMEM;
+	} else {
+		sz = sizeof(struct ib_wc) * (cqe + 1);
+		sz += sizeof(*k_wc);
+		k_wc = vzalloc_node(sz, rdi->dparms.node);
+		if (!k_wc)
+			return -ENOMEM;
+	}
 	/* Check that we can write the offset to mmap. */
 	if (udata && udata->outlen >= sizeof(__u64)) {
 		__u64 offset = 0;
@@ -378,11 +414,18 @@ int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 	 * Make sure head and tail are sane since they
 	 * might be user writable.
 	 */
-	old_wc = cq->queue;
-	head = old_wc->head;
+	if (u_wc) {
+		old_u_wc = cq->queue;
+		head = RDMA_READ_UAPI_ATOMIC(old_u_wc->head);
+		tail = RDMA_READ_UAPI_ATOMIC(old_u_wc->tail);
+	} else {
+		old_k_wc = cq->kqueue;
+		head = old_k_wc->head;
+		tail = old_k_wc->tail;
+	}
+
 	if (head > (u32)cq->ibcq.cqe)
 		head = (u32)cq->ibcq.cqe;
-	tail = old_wc->tail;
 	if (tail > (u32)cq->ibcq.cqe)
 		tail = (u32)cq->ibcq.cqe;
 	if (head < tail)
@@ -394,27 +437,36 @@ int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 		goto bail_unlock;
 	}
 	for (n = 0; tail != head; n++) {
-		if (cq->ip)
-			wc->uqueue[n] = old_wc->uqueue[tail];
+		if (u_wc)
+			u_wc->uqueue[n] = old_u_wc->uqueue[tail];
 		else
-			wc->kqueue[n] = old_wc->kqueue[tail];
+			k_wc->kqueue[n] = old_k_wc->kqueue[tail];
 		if (tail == (u32)cq->ibcq.cqe)
 			tail = 0;
 		else
 			tail++;
 	}
 	cq->ibcq.cqe = cqe;
-	wc->head = n;
-	wc->tail = 0;
-	cq->queue = wc;
+	if (u_wc) {
+		RDMA_WRITE_UAPI_ATOMIC(u_wc->head, n);
+		RDMA_WRITE_UAPI_ATOMIC(u_wc->tail, 0);
+		cq->queue = u_wc;
+	} else {
+		k_wc->head = n;
+		k_wc->tail = 0;
+		cq->kqueue = k_wc;
+	}
 	spin_unlock_irq(&cq->lock);
 
-	vfree(old_wc);
+	if (u_wc)
+		vfree(old_u_wc);
+	else
+		vfree(old_k_wc);
 
 	if (cq->ip) {
 		struct rvt_mmap_info *ip = cq->ip;
 
-		rvt_update_mmap_info(rdi, ip, sz, wc);
+		rvt_update_mmap_info(rdi, ip, sz, u_wc);
 
 		/*
 		 * Return the offset to mmap.
@@ -438,7 +490,9 @@ int rvt_resize_cq(struct ib_cq *ibcq, int cqe, struct ib_udata *udata)
 bail_unlock:
 	spin_unlock_irq(&cq->lock);
 bail_free:
-	vfree(wc);
+	vfree(u_wc);
+	vfree(k_wc);
+
 	return ret;
 }
 
@@ -456,7 +510,7 @@ bail_free:
 int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 {
 	struct rvt_cq *cq = ibcq_to_rvtcq(ibcq);
-	struct rvt_cq_wc *wc;
+	struct rvt_k_cq_wc *wc;
 	unsigned long flags;
 	int npolled;
 	u32 tail;
@@ -467,7 +521,7 @@ int rvt_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry)
 
 	spin_lock_irqsave(&cq->lock, flags);
 
-	wc = cq->queue;
+	wc = cq->kqueue;
 	tail = wc->tail;
 	if (tail > (u32)cq->ibcq.cqe)
 		tail = (u32)cq->ibcq.cqe;