[PATCH net-next 2/6] net: mana: Query device capabilities and configure MSI-X sharing for EQs

[Long Li]

When querying the device, adjust the max number of queues to allow
dedicated MSI-X vectors for each vPort. The number of queues per vPort
is clamped to no less than 16. MSI-X sharing among vPorts is disabled
by default and is only enabled when there are not enough MSI-X vectors
for dedicated allocation.

Rename mana_query_device_cfg() to mana_gd_query_device_cfg() as it is
used at GDMA device probe time for querying device capabilities.

Signed-off-by: Long Li <longli@xxxxxxxxxxxxx>
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 66 ++++++++++++++++---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 36 +++++-----
 include/net/mana/gdma.h                       | 13 +++-
 3 files changed, 91 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 0055c231acf6..62e3a2eb68e0 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -107,6 +107,9 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
 	struct gdma_context *gc = pci_get_drvdata(pdev);
 	struct gdma_query_max_resources_resp resp = {};
 	struct gdma_general_req req = {};
+	unsigned int max_num_queues;
+	u8 bm_hostmode;
+	u16 num_ports;
 	int err;
 
 	mana_gd_init_req_hdr(&req.hdr, GDMA_QUERY_MAX_RESOURCES,
@@ -152,6 +155,40 @@ static int mana_gd_query_max_resources(struct pci_dev *pdev)
 	if (gc->max_num_queues > gc->num_msix_usable - 1)
 		gc->max_num_queues = gc->num_msix_usable - 1;
 
+	err = mana_gd_query_device_cfg(gc, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
+				       MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
+	if (err)
+		return err;
+
+	if (!num_ports)
+		return -EINVAL;
+
+	/*
+	 * Adjust gc->max_num_queues returned from the SOC to allow dedicated MSIx
+	 * for each vPort. Reduce max_num_queues to no less than 16 if necessary
+	 */
+	max_num_queues = (gc->num_msix_usable - 1) / num_ports;
+	max_num_queues = roundup_pow_of_two(max(max_num_queues, 1U));
+	if (max_num_queues < 16)
+		max_num_queues = 16;
+
+	/*
+	 * Use dedicated MSIx for EQs whenever possible, use MSIx sharing for
+	 * Ethernet EQs when (max_num_queues * num_ports > num_msix_usable - 1)
+	 */
+	max_num_queues = min(gc->max_num_queues, max_num_queues);
+	if (max_num_queues * num_ports > gc->num_msix_usable - 1)
+		gc->msi_sharing = true;
+
+	/* If MSI is shared, use max allowed value */
+	if (gc->msi_sharing)
+		gc->max_num_queues_vport = min(gc->num_msix_usable - 1, gc->max_num_queues);
+	else
+		gc->max_num_queues_vport = max_num_queues;
+
+	dev_info(gc->dev, "MSI sharing mode %d max queues %d\n",
+		 gc->msi_sharing, gc->max_num_queues);
+
 	return 0;
 }
 
@@ -1802,6 +1839,7 @@ static int mana_gd_setup_hwc_irqs(struct pci_dev *pdev)
 		/* Need 1 interrupt for HWC */
 		max_irqs = min(num_online_cpus(), MANA_MAX_NUM_QUEUES) + 1;
 		min_irqs = 2;
+		gc->msi_sharing = true;
 	}
 
 	nvec = pci_alloc_irq_vectors(pdev, min_irqs, max_irqs, PCI_IRQ_MSIX);
@@ -1880,6 +1918,8 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev)
 
 	pci_free_irq_vectors(pdev);
 
+	bitmap_free(gc->msi_bitmap);
+	gc->msi_bitmap = NULL;
 	gc->max_num_msix = 0;
 	gc->num_msix_usable = 0;
 }
@@ -1911,20 +1951,30 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	if (err)
 		goto destroy_hwc;
 
-	err = mana_gd_query_max_resources(pdev);
+	err = mana_gd_detect_devices(pdev);
 	if (err)
 		goto destroy_hwc;
 
-	err = mana_gd_setup_remaining_irqs(pdev);
-	if (err) {
-		dev_err(gc->dev, "Failed to setup remaining IRQs: %d", err);
-		goto destroy_hwc;
-	}
-
-	err = mana_gd_detect_devices(pdev);
+	err = mana_gd_query_max_resources(pdev);
 	if (err)
 		goto destroy_hwc;
 
+	if (!gc->msi_sharing) {
+		gc->msi_bitmap = bitmap_zalloc(gc->num_msix_usable, GFP_KERNEL);
+		if (!gc->msi_bitmap) {
+			err = -ENOMEM;
+			goto destroy_hwc;
+		}
+		/* Set bit for HWC */
+		set_bit(0, gc->msi_bitmap);
+	} else {
+		err = mana_gd_setup_remaining_irqs(pdev);
+		if (err) {
+			dev_err(gc->dev, "Failed to setup remaining IRQs: %d", err);
+			goto destroy_hwc;
+		}
+	}
+
 	dev_dbg(&pdev->dev, "mana gdma setup successful\n");
 	return 0;
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 566e45a66adf..1e65670feb17 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1002,10 +1002,9 @@ static int mana_init_port_context(struct mana_port_context *apc)
 	return !apc->rxqs ? -ENOMEM : 0;
 }
 
-static int mana_send_request(struct mana_context *ac, void *in_buf,
-			     u32 in_len, void *out_buf, u32 out_len)
+static int gdma_mana_send_request(struct gdma_context *gc, void *in_buf,
+				  u32 in_len, void *out_buf, u32 out_len)
 {
-	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 	struct gdma_resp_hdr *resp = out_buf;
 	struct gdma_req_hdr *req = in_buf;
 	struct device *dev = gc->dev;
@@ -1039,6 +1038,14 @@ static int mana_send_request(struct mana_context *ac, void *in_buf,
 	return 0;
 }
 
+static int mana_send_request(struct mana_context *ac, void *in_buf,
+			     u32 in_len, void *out_buf, u32 out_len)
+{
+	struct gdma_context *gc = ac->gdma_dev->gdma_context;
+
+	return gdma_mana_send_request(gc, in_buf, in_len, out_buf, out_len);
+}
+
 static int mana_verify_resp_hdr(const struct gdma_resp_hdr *resp_hdr,
 				const enum mana_command_code expected_code,
 				const u32 min_size)
@@ -1172,11 +1179,10 @@ static void mana_pf_deregister_filter(struct mana_port_context *apc)
 			   err, resp.hdr.status);
 }
 
-static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
-				 u32 proto_minor_ver, u32 proto_micro_ver,
-				 u16 *max_num_vports, u8 *bm_hostmode)
+int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver,
+			     u32 proto_minor_ver, u32 proto_micro_ver,
+			     u16 *max_num_vports, u8 *bm_hostmode)
 {
-	struct gdma_context *gc = ac->gdma_dev->gdma_context;
 	struct mana_query_device_cfg_resp resp = {};
 	struct mana_query_device_cfg_req req = {};
 	struct device *dev = gc->dev;
@@ -1191,7 +1197,7 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 	req.proto_minor_ver = proto_minor_ver;
 	req.proto_micro_ver = proto_micro_ver;
 
-	err = mana_send_request(ac, &req, sizeof(req), &resp, sizeof(resp));
+	err = gdma_mana_send_request(gc, &req, sizeof(req), &resp, sizeof(resp));
 	if (err) {
 		dev_err(dev, "Failed to query config: %d", err);
 		return err;
@@ -1219,8 +1225,6 @@ static int mana_query_device_cfg(struct mana_context *ac, u32 proto_major_ver,
 	else
 		*bm_hostmode = 0;
 
-	debugfs_create_u16("adapter-MTU", 0400, gc->mana_pci_debugfs, &gc->adapter_mtu);
-
 	return 0;
 }
 
@@ -3334,7 +3338,7 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	int err;
 
 	ndev = alloc_etherdev_mq(sizeof(struct mana_port_context),
-				 gc->max_num_queues);
+				 gc->max_num_queues_vport);
 	if (!ndev)
 		return -ENOMEM;
 
@@ -3343,8 +3347,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	apc = netdev_priv(ndev);
 	apc->ac = ac;
 	apc->ndev = ndev;
-	apc->max_queues = gc->max_num_queues;
-	apc->num_queues = gc->max_num_queues;
+	apc->max_queues = gc->max_num_queues_vport;
+	apc->num_queues = gc->max_num_queues_vport;
 	apc->tx_queue_size = DEF_TX_BUFFERS_PER_QUEUE;
 	apc->rx_queue_size = DEF_RX_BUFFERS_PER_QUEUE;
 	apc->port_handle = INVALID_MANA_HANDLE;
@@ -3596,13 +3600,15 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 		gd->driver_data = ac;
 	}
 
-	err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
-				    MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
+	err = mana_gd_query_device_cfg(gc, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
+				       MANA_MICRO_VERSION, &num_ports, &bm_hostmode);
 	if (err)
 		goto out;
 
 	ac->bm_hostmode = bm_hostmode;
 
+	debugfs_create_u16("adapter-MTU", 0400, gc->mana_pci_debugfs, &gc->adapter_mtu);
+
 	if (!resuming) {
 		ac->num_ports = num_ports;
 
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 766f4fb25e26..477b751f124e 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -392,8 +392,10 @@ struct gdma_context {
 	struct device		*dev;
 	struct dentry		*mana_pci_debugfs;
 
-	/* Per-vPort max number of queues */
+	/* Hardware max number of queues */
 	unsigned int		max_num_queues;
+	/* Per-vPort max number of queues */
+	unsigned int		max_num_queues_vport;
 	unsigned int		max_num_msix;
 	unsigned int		num_msix_usable;
 	struct xarray		irq_contexts;
@@ -438,6 +440,12 @@ struct gdma_context {
 	struct workqueue_struct *service_wq;
 
 	unsigned long		flags;
+
+	/* Indicate if this device is sharing MSI for EQs on MANA */
+	bool msi_sharing;
+
+	/* Bitmap tracks where MSI is allocated when it is not shared for EQs */
+	unsigned long *msi_bitmap;
 };
 
 static inline bool mana_gd_is_mana(struct gdma_dev *gd)
@@ -999,4 +1007,7 @@ int mana_gd_resume(struct pci_dev *pdev);
 
 bool mana_need_log(struct gdma_context *gc, int err);
 
+int mana_gd_query_device_cfg(struct gdma_context *gc, u32 proto_major_ver,
+			     u32 proto_minor_ver, u32 proto_micro_ver,
+			     u16 *max_num_vports, u8 *bm_hostmode);
 #endif /* _GDMA_H */
-- 
2.43.0