[RFC PATCH v4 16/38] NTB: ntb_transport: Move TX memory window setup into setup_qp_mw()

Historically both TX and RX have assumed the same per-QP MW slice
(tx_max_entry == remote rx_max_entry), while those are calculated
separately in different places (pre and post the link-up negotiation
point). This has been safe because nt->link_is_up is never set to true
unless the pre-determined qp_count are the same among them, and qp_count
is typically limited to nt->mw_count, which should be carefully
configured by admin.

However, setup_qp_mw can actually split mw and handle multi-qps in one
MW properly, so qp_count needs not to be limited by nt->mw_count. Once
we relax the limitation, pre-determined qp_count can differ among host
side and endpoint, and link-up negotiation can easily fail.

Move the TX MW configuration (per-QP offset and size) into
ntb_transport_setup_qp_mw() so that both RX and TX layout decisions are
centralized in a single helper. ntb_transport_init_queue() now deals
only with per-QP software state, not with MW layout.

This keeps the previous behavior, while preparing for relaxing the
qp_count limitation and improving readability.

No functional change is intended.

Signed-off-by: Koichiro Den <[email protected]>
---
 drivers/ntb/ntb_transport.c | 76 ++++++++++++++++---------------------
 1 file changed, 32 insertions(+), 44 deletions(-)

diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index d5a544bf8fd6..57a21f2daac6 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -569,7 +569,10 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
 	struct ntb_transport_mw *mw;
 	struct ntb_dev *ndev = nt->ndev;
 	struct ntb_queue_entry *entry;
-	unsigned int rx_size, num_qps_mw;
+	phys_addr_t mw_base;
+	resource_size_t mw_size;
+	unsigned int rx_size, tx_size, num_qps_mw;
+	u64 qp_offset;
 	unsigned int mw_num, mw_count, qp_count;
 	unsigned int i;
 	int node;
@@ -588,13 +591,38 @@ static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
 	else
 		num_qps_mw = qp_count / mw_count;
 
-	rx_size = (unsigned int)mw->xlat_size / num_qps_mw;
-	qp->rx_buff = mw->virt_addr + rx_size * (qp_num / mw_count);
-	rx_size -= sizeof(struct ntb_rx_info);
+	mw_base = nt->mw_vec[mw_num].phys_addr;
+	mw_size = nt->mw_vec[mw_num].phys_size;
+
+	if (mw_size > mw->xlat_size)
+		mw_size = mw->xlat_size;
+	if (max_mw_size && mw_size > max_mw_size)
+		mw_size = max_mw_size;
+
+	tx_size = (unsigned int)mw_size / num_qps_mw;
+	qp_offset = tx_size * (qp_num / mw_count);
+
+	qp->rx_buff = mw->virt_addr + qp_offset;
+
+	qp->tx_mw_size = tx_size;
+	qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
+	if (!qp->tx_mw)
+		return -EINVAL;
+
+	qp->tx_mw_phys = mw_base + qp_offset;
+	if (!qp->tx_mw_phys)
+		return -EINVAL;
 
+	rx_size = tx_size;
+	rx_size -= sizeof(struct ntb_rx_info);
 	qp->remote_rx_info = qp->rx_buff + rx_size;
 
+	tx_size -= sizeof(struct ntb_rx_info);
+	qp->rx_info = qp->tx_mw + tx_size;
+
 	/* Due to housekeeping, there must be atleast 2 buffs */
+	qp->tx_max_frame = min(transport_mtu, tx_size / 2);
+	qp->tx_max_entry = tx_size / qp->tx_max_frame;
 	qp->rx_max_frame = min(transport_mtu, rx_size / 2);
 	qp->rx_max_entry = rx_size / qp->rx_max_frame;
 	qp->rx_index = 0;
@@ -1132,16 +1160,6 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
 				    unsigned int qp_num)
 {
 	struct ntb_transport_qp *qp;
-	phys_addr_t mw_base;
-	resource_size_t mw_size;
-	unsigned int num_qps_mw, tx_size;
-	unsigned int mw_num, mw_count, qp_count;
-	u64 qp_offset;
-
-	mw_count = nt->mw_count;
-	qp_count = nt->qp_count;
-
-	mw_num = QP_TO_MW(nt, qp_num);
 
 	qp = &nt->qp_vec[qp_num];
 	qp->qp_num = qp_num;
@@ -1151,36 +1169,6 @@ static int ntb_transport_init_queue(struct ntb_transport_ctx *nt,
 	qp->event_handler = NULL;
 	ntb_qp_link_context_reset(qp);
 
-	if (mw_num < qp_count % mw_count)
-		num_qps_mw = qp_count / mw_count + 1;
-	else
-		num_qps_mw = qp_count / mw_count;
-
-	mw_base = nt->mw_vec[mw_num].phys_addr;
-	mw_size = nt->mw_vec[mw_num].phys_size;
-
-	if (max_mw_size && mw_size > max_mw_size)
-		mw_size = max_mw_size;
-
-	tx_size = (unsigned int)mw_size / num_qps_mw;
-	qp_offset = tx_size * (qp_num / mw_count);
-
-	qp->tx_mw_size = tx_size;
-	qp->tx_mw = nt->mw_vec[mw_num].vbase + qp_offset;
-	if (!qp->tx_mw)
-		return -EINVAL;
-
-	qp->tx_mw_phys = mw_base + qp_offset;
-	if (!qp->tx_mw_phys)
-		return -EINVAL;
-
-	tx_size -= sizeof(struct ntb_rx_info);
-	qp->rx_info = qp->tx_mw + tx_size;
-
-	/* Due to housekeeping, there must be atleast 2 buffs */
-	qp->tx_max_frame = min(transport_mtu, tx_size / 2);
-	qp->tx_max_entry = tx_size / qp->tx_max_frame;
-
 	if (nt->debugfs_node_dir) {
 		char debugfs_name[8];
 
-- 
2.51.0