3 files changed, 150 insertions, 59 deletions

diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index cafded2f9382..a00f915c5188 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -52,9 +52,33 @@ static int mana_hwc_verify_resp_msg(const struct hwc_caller_ctx *caller_ctx,
 	return 0;
 }
 
+static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
+				struct hwc_work_request *req)
+{
+	struct device *dev = hwc_rxq->hwc->dev;
+	struct gdma_sge *sge;
+	int err;
+
+	sge = &req->sge;
+	sge->address = (u64)req->buf_sge_addr;
+	sge->mem_key = hwc_rxq->msg_buf->gpa_mkey;
+	sge->size = req->buf_len;
+
+	memset(&req->wqe_req, 0, sizeof(struct gdma_wqe_request));
+	req->wqe_req.sgl = sge;
+	req->wqe_req.num_sge = 1;
+	req->wqe_req.client_data_unit = 0;
+
+	err = mana_gd_post_and_ring(hwc_rxq->gdma_wq, &req->wqe_req, NULL);
+	if (err)
+		dev_err(dev, "Failed to post WQE on HWC RQ: %d\n", err);
+	return err;
+}
+
 static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
-				 const struct gdma_resp_hdr *resp_msg)
+				 struct hwc_work_request *rx_req)
 {
+	const struct gdma_resp_hdr *resp_msg = rx_req->buf_va;
 	struct hwc_caller_ctx *ctx;
 	int err;
 
@@ -62,6 +86,7 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
 		      hwc->inflight_msg_res.map)) {
 		dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n",
 			resp_msg->response.hwc_msg_id);
+		mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
 		return;
 	}
 
@@ -75,30 +100,13 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
 	memcpy(ctx->output_buf, resp_msg, resp_len);
 out:
 	ctx->error = err;
-	complete(&ctx->comp_event);
-}
-
-static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
-				struct hwc_work_request *req)
-{
-	struct device *dev = hwc_rxq->hwc->dev;
-	struct gdma_sge *sge;
-	int err;
-
-	sge = &req->sge;
-	sge->address = (u64)req->buf_sge_addr;
-	sge->mem_key = hwc_rxq->msg_buf->gpa_mkey;
-	sge->size = req->buf_len;
 
-	memset(&req->wqe_req, 0, sizeof(struct gdma_wqe_request));
-	req->wqe_req.sgl = sge;
-	req->wqe_req.num_sge = 1;
-	req->wqe_req.client_data_unit = 0;
+	/* Must post rx wqe before complete(), otherwise the next rx may
+	 * hit no_wqe error.
+	 */
+	mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
 
-	err = mana_gd_post_and_ring(hwc_rxq->gdma_wq, &req->wqe_req, NULL);
-	if (err)
-		dev_err(dev, "Failed to post WQE on HWC RQ: %d\n", err);
-	return err;
+	complete(&ctx->comp_event);
 }
 
 static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
@@ -235,14 +243,12 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id,
 		return;
 	}
 
-	mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, resp);
+	mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req);
 
-	/* Do no longer use 'resp', because the buffer is posted to the HW
-	 * in the below mana_hwc_post_rx_wqe().
+	/* Can no longer use 'resp', because the buffer is posted to the HW
+	 * in mana_hwc_handle_resp() above.
 	 */
 	resp = NULL;
-
-	mana_hwc_post_rx_wqe(hwc_rxq, rx_req);
 }
 
 static void mana_hwc_tx_event_handler(void *ctx, u32 gdma_txq_id,
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 39f56973746d..c47266d1c7c2 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -511,7 +511,7 @@ static u16 mana_select_queue(struct net_device *ndev, struct sk_buff *skb,
 }
 
 /* Release pre-allocated RX buffers */
-static void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc)
+void mana_pre_dealloc_rxbufs(struct mana_port_context *mpc)
 {
 	struct device *dev;
 	int i;
@@ -608,7 +608,7 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
 	*datasize = mtu + ETH_HLEN;
 }
 
-static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
+int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_queues)
 {
 	struct device *dev;
 	struct page *page;
@@ -622,7 +622,7 @@ static int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu)
 
 	dev = mpc->ac->gdma_dev->gdma_context->dev;
 
-	num_rxb = mpc->num_queues * RX_BUFFERS_PER_QUEUE;
+	num_rxb = num_queues * mpc->rx_queue_size;
 
 	WARN(mpc->rxbufs_pre, "mana rxbufs_pre exists\n");
 	mpc->rxbufs_pre = kmalloc_array(num_rxb, sizeof(void *), GFP_KERNEL);
@@ -682,7 +682,7 @@ static int mana_change_mtu(struct net_device *ndev, int new_mtu)
 	int err;
 
 	/* Pre-allocate buffers to prevent failure in mana_attach later */
-	err = mana_pre_alloc_rxbufs(mpc, new_mtu);
+	err = mana_pre_alloc_rxbufs(mpc, new_mtu, mpc->num_queues);
 	if (err) {
 		netdev_err(ndev, "Insufficient memory for new MTU\n");
 		return err;
@@ -1872,10 +1872,12 @@ static void mana_destroy_txq(struct mana_port_context *apc)
 
 	for (i = 0; i < apc->num_queues; i++) {
 		napi = &apc->tx_qp[i].tx_cq.napi;
-		napi_synchronize(napi);
-		napi_disable(napi);
-		netif_napi_del(napi);
-
+		if (apc->tx_qp[i].txq.napi_initialized) {
+			napi_synchronize(napi);
+			napi_disable(napi);
+			netif_napi_del(napi);
+			apc->tx_qp[i].txq.napi_initialized = false;
+		}
 		mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
 
 		mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq);
@@ -1909,15 +1911,17 @@ static int mana_create_txq(struct mana_port_context *apc,
 		return -ENOMEM;
 
 	/*  The minimum size of the WQE is 32 bytes, hence
-	 *  MAX_SEND_BUFFERS_PER_QUEUE represents the maximum number of WQEs
+	 *  apc->tx_queue_size represents the maximum number of WQEs
 	 *  the SQ can store. This value is then used to size other queues
 	 *  to prevent overflow.
+	 *  Also note that the txq_size is always going to be MANA_PAGE_ALIGNED,
+	 *  as min val of apc->tx_queue_size is 128 and that would make
+	 *  txq_size 128*32 = 4096 and the other higher values of apc->tx_queue_size
+	 *  are always power of two
 	 */
-	txq_size = MAX_SEND_BUFFERS_PER_QUEUE * 32;
-	BUILD_BUG_ON(!MANA_PAGE_ALIGNED(txq_size));
+	txq_size = apc->tx_queue_size * 32;
 
-	cq_size = MAX_SEND_BUFFERS_PER_QUEUE * COMP_ENTRY_SIZE;
-	cq_size = MANA_PAGE_ALIGN(cq_size);
+	cq_size = apc->tx_queue_size * COMP_ENTRY_SIZE;
 
 	gc = gd->gdma_context;
 
@@ -1931,6 +1935,7 @@ static int mana_create_txq(struct mana_port_context *apc,
 		txq->ndev = net;
 		txq->net_txq = netdev_get_tx_queue(net, i);
 		txq->vp_offset = apc->tx_vp_offset;
+		txq->napi_initialized = false;
 		skb_queue_head_init(&txq->pending_skbs);
 
 		memset(&spec, 0, sizeof(spec));
@@ -1997,6 +2002,7 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 		netif_napi_add_tx(net, &cq->napi, mana_poll);
 		napi_enable(&cq->napi);
+		txq->napi_initialized = true;
 
 		mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
 	}
@@ -2008,7 +2014,7 @@ out:
 }
 
 static void mana_destroy_rxq(struct mana_port_context *apc,
-			     struct mana_rxq *rxq, bool validate_state)
+			     struct mana_rxq *rxq, bool napi_initialized)
 
 {
 	struct gdma_context *gc = apc->ac->gdma_dev->gdma_context;
@@ -2023,15 +2029,15 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 
 	napi = &rxq->rx_cq.napi;
 
-	if (validate_state)
+	if (napi_initialized) {
 		napi_synchronize(napi);
 
-	napi_disable(napi);
+		napi_disable(napi);
 
+		netif_napi_del(napi);
+	}
 	xdp_rxq_info_unreg(&rxq->xdp_rxq);
 
-	netif_napi_del(napi);
-
 	mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj);
 
 	mana_deinit_cq(apc, &rxq->rx_cq);
@@ -2155,10 +2161,11 @@ static int mana_push_wqe(struct mana_rxq *rxq)
 
 static int mana_create_page_pool(struct mana_rxq *rxq, struct gdma_context *gc)
 {
+	struct mana_port_context *mpc = netdev_priv(rxq->ndev);
 	struct page_pool_params pprm = {};
 	int ret;
 
-	pprm.pool_size = RX_BUFFERS_PER_QUEUE;
+	pprm.pool_size = mpc->rx_queue_size;
 	pprm.nid = gc->numa_node;
 	pprm.napi = &rxq->rx_cq.napi;
 	pprm.netdev = rxq->ndev;
@@ -2190,13 +2197,13 @@ static struct mana_rxq *mana_create_rxq(struct mana_port_context *apc,
 
 	gc = gd->gdma_context;
 
-	rxq = kzalloc(struct_size(rxq, rx_oobs, RX_BUFFERS_PER_QUEUE),
+	rxq = kzalloc(struct_size(rxq, rx_oobs, apc->rx_queue_size),
 		      GFP_KERNEL);
 	if (!rxq)
 		return NULL;
 
 	rxq->ndev = ndev;
-	rxq->num_rx_buf = RX_BUFFERS_PER_QUEUE;
+	rxq->num_rx_buf = apc->rx_queue_size;
 	rxq->rxq_idx = rxq_idx;
 	rxq->rxobj = INVALID_MANA_HANDLE;
 
@@ -2744,6 +2751,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc->ndev = ndev;
 	apc->max_queues = gc->max_num_queues;
 	apc->num_queues = gc->max_num_queues;
+	apc->tx_queue_size = DEF_TX_BUFFERS_PER_QUEUE;
+	apc->rx_queue_size = DEF_RX_BUFFERS_PER_QUEUE;
 	apc->port_handle = INVALID_MANA_HANDLE;
 	apc->pf_filter_handle = INVALID_MANA_HANDLE;
 	apc->port_idx = port_idx;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 146d5db1792f..dc3864377538 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -345,27 +345,101 @@ static int mana_set_channels(struct net_device *ndev,
 	struct mana_port_context *apc = netdev_priv(ndev);
 	unsigned int new_count = channels->combined_count;
 	unsigned int old_count = apc->num_queues;
-	int err, err2;
+	int err;
+
+	err = mana_pre_alloc_rxbufs(apc, ndev->mtu, new_count);
+	if (err) {
+		netdev_err(ndev, "Insufficient memory for new allocations");
+		return err;
+	}
 
 	err = mana_detach(ndev, false);
 	if (err) {
 		netdev_err(ndev, "mana_detach failed: %d\n", err);
-		return err;
+		goto out;
 	}
 
 	apc->num_queues = new_count;
 	err = mana_attach(ndev);
-	if (!err)
-		return 0;
+	if (err) {
+		apc->num_queues = old_count;
+		netdev_err(ndev, "mana_attach failed: %d\n", err);
+	}
+
+out:
+	mana_pre_dealloc_rxbufs(apc);
+	return err;
+}
+
+static void mana_get_ringparam(struct net_device *ndev,
+			       struct ethtool_ringparam *ring,
+			       struct kernel_ethtool_ringparam *kernel_ring,
+			       struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+
+	ring->rx_pending = apc->rx_queue_size;
+	ring->tx_pending = apc->tx_queue_size;
+	ring->rx_max_pending = MAX_RX_BUFFERS_PER_QUEUE;
+	ring->tx_max_pending = MAX_TX_BUFFERS_PER_QUEUE;
+}
+
+static int mana_set_ringparam(struct net_device *ndev,
+			      struct ethtool_ringparam *ring,
+			      struct kernel_ethtool_ringparam *kernel_ring,
+			      struct netlink_ext_ack *extack)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	u32 new_tx, new_rx;
+	u32 old_tx, old_rx;
+	int err;
 
-	netdev_err(ndev, "mana_attach failed: %d\n", err);
+	old_tx = apc->tx_queue_size;
+	old_rx = apc->rx_queue_size;
 
-	/* Try to roll it back to the old configuration. */
-	apc->num_queues = old_count;
-	err2 = mana_attach(ndev);
-	if (err2)
-		netdev_err(ndev, "mana re-attach failed: %d\n", err2);
+	if (ring->tx_pending < MIN_TX_BUFFERS_PER_QUEUE) {
+		NL_SET_ERR_MSG_FMT(extack, "tx:%d less than the min:%d", ring->tx_pending,
+				   MIN_TX_BUFFERS_PER_QUEUE);
+		return -EINVAL;
+	}
+
+	if (ring->rx_pending < MIN_RX_BUFFERS_PER_QUEUE) {
+		NL_SET_ERR_MSG_FMT(extack, "rx:%d less than the min:%d", ring->rx_pending,
+				   MIN_RX_BUFFERS_PER_QUEUE);
+		return -EINVAL;
+	}
+
+	new_rx = roundup_pow_of_two(ring->rx_pending);
+	new_tx = roundup_pow_of_two(ring->tx_pending);
+	netdev_info(ndev, "Using nearest power of 2 values for Txq:%d Rxq:%d\n",
+		    new_tx, new_rx);
+
+	/* pre-allocating new buffers to prevent failures in mana_attach() later */
+	apc->rx_queue_size = new_rx;
+	err = mana_pre_alloc_rxbufs(apc, ndev->mtu, apc->num_queues);
+	apc->rx_queue_size = old_rx;
+	if (err) {
+		netdev_err(ndev, "Insufficient memory for new allocations\n");
+		return err;
+	}
 
+	err = mana_detach(ndev, false);
+	if (err) {
+		netdev_err(ndev, "mana_detach failed: %d\n", err);
+		goto out;
+	}
+
+	apc->tx_queue_size = new_tx;
+	apc->rx_queue_size = new_rx;
+
+	err = mana_attach(ndev);
+	if (err) {
+		netdev_err(ndev, "mana_attach failed: %d\n", err);
+		apc->tx_queue_size = old_tx;
+		apc->rx_queue_size = old_rx;
+	}
+out:
+	mana_pre_dealloc_rxbufs(apc);
 	return err;
 }
 
@@ -380,4 +454,6 @@ const struct ethtool_ops mana_ethtool_ops = {
 	.set_rxfh		= mana_set_rxfh,
 	.get_channels		= mana_get_channels,
 	.set_channels		= mana_set_channels,
+	.get_ringparam          = mana_get_ringparam,
+	.set_ringparam          = mana_set_ringparam,
 };