Merge branch 'cxgb4-next'

Hariprasad Shenai says:

====================
Trivial enhancements for cxgb4

This series adds a debug message if adapter isn't inserted in right PCI
slot. Changes naming conventions for iSCSI rx queues, use node info while
allocating rx queue and use napi_complete_done() api in napi handler.

This patch series has been created against net-next tree and includes
patches on cxgb4 driver.

We have included all the maintainers of respective drivers. Kindly review
the change and let us know in case of any review comments.

Thanks

V2: Dropped 'dcb_info' debug entry patch, since the same can be achieved
    using lldp tool.
    Based on review comments by Or Gerlitz <gerlitz.or@gmail.com> and
    David Miller.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 121 insertions, 43 deletions

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index e01e7228f607..3b59bc4038a6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -398,11 +398,10 @@ struct link_config {
 
 enum {
 	MAX_ETH_QSETS = 32,           /* # of Ethernet Tx/Rx queue sets */
-	MAX_OFLD_QSETS = 16,          /* # of offload Tx/Rx queue sets */
+	MAX_OFLD_QSETS = 16,          /* # of offload Tx, iscsi Rx queue sets */
 	MAX_CTRL_QUEUES = NCHAN,      /* # of control Tx queues */
 	MAX_RDMA_QUEUES = NCHAN,      /* # of streaming RDMA Rx queues */
 	MAX_RDMA_CIQS = 32,        /* # of  RDMA concentrator IQs */
-	MAX_ISCSI_QUEUES = NCHAN,     /* # of streaming iSCSI Rx queues */
 };
 
 enum {
@@ -420,7 +419,7 @@ enum {
 	INGQ_EXTRAS = 2,        /* firmware event queue and */
 				/*   forwarded interrupts */
 	MAX_INGQ = MAX_ETH_QSETS + MAX_OFLD_QSETS + MAX_RDMA_QUEUES
-		   + MAX_RDMA_CIQS + MAX_ISCSI_QUEUES + INGQ_EXTRAS,
+		   + MAX_RDMA_CIQS + INGQ_EXTRAS,
 };
 
 struct adapter;
@@ -639,7 +638,7 @@ struct sge {
 	struct sge_ctrl_txq ctrlq[MAX_CTRL_QUEUES];
 
 	struct sge_eth_rxq ethrxq[MAX_ETH_QSETS];
-	struct sge_ofld_rxq ofldrxq[MAX_OFLD_QSETS];
+	struct sge_ofld_rxq iscsirxq[MAX_OFLD_QSETS];
 	struct sge_ofld_rxq rdmarxq[MAX_RDMA_QUEUES];
 	struct sge_ofld_rxq rdmaciq[MAX_RDMA_CIQS];
 	struct sge_rspq fw_evtq ____cacheline_aligned_in_smp;
@@ -650,10 +649,10 @@ struct sge {
 	u16 max_ethqsets;           /* # of available Ethernet queue sets */
 	u16 ethqsets;               /* # of active Ethernet queue sets */
 	u16 ethtxq_rover;           /* Tx queue to clean up next */
-	u16 ofldqsets;              /* # of active offload queue sets */
+	u16 iscsiqsets;              /* # of active iSCSI queue sets */
 	u16 rdmaqs;                 /* # of available RDMA Rx queues */
 	u16 rdmaciqs;               /* # of available RDMA concentrator IQs */
-	u16 ofld_rxq[MAX_OFLD_QSETS];
+	u16 iscsi_rxq[MAX_OFLD_QSETS];
 	u16 rdma_rxq[MAX_RDMA_QUEUES];
 	u16 rdma_ciq[MAX_RDMA_CIQS];
 	u16 timer_val[SGE_NTIMERS];
@@ -679,7 +678,7 @@ struct sge {
 };
 
 #define for_each_ethrxq(sge, i) for (i = 0; i < (sge)->ethqsets; i++)
-#define for_each_ofldrxq(sge, i) for (i = 0; i < (sge)->ofldqsets; i++)
+#define for_each_iscsirxq(sge, i) for (i = 0; i < (sge)->iscsiqsets; i++)
 #define for_each_rdmarxq(sge, i) for (i = 0; i < (sge)->rdmaqs; i++)
 #define for_each_rdmaciq(sge, i) for (i = 0; i < (sge)->rdmaciqs; i++)
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 0d579b192350..62a343fc9c1a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2245,7 +2245,7 @@ static int sge_qinfo_show(struct seq_file *seq, void *v)
 {
 	struct adapter *adap = seq->private;
 	int eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
-	int iscsi_entries = DIV_ROUND_UP(adap->sge.ofldqsets, 4);
+	int iscsi_entries = DIV_ROUND_UP(adap->sge.iscsiqsets, 4);
 	int rdma_entries = DIV_ROUND_UP(adap->sge.rdmaqs, 4);
 	int ciq_entries = DIV_ROUND_UP(adap->sge.rdmaciqs, 4);
 	int ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
@@ -2331,10 +2331,10 @@ do { \
 
 	} else if (iscsi_idx < iscsi_entries) {
 		const struct sge_ofld_rxq *rx =
-			&adap->sge.ofldrxq[iscsi_idx * 4];
+			&adap->sge.iscsirxq[iscsi_idx * 4];
 		const struct sge_ofld_txq *tx =
 			&adap->sge.ofldtxq[iscsi_idx * 4];
-		int n = min(4, adap->sge.ofldqsets - 4 * iscsi_idx);
+		int n = min(4, adap->sge.iscsiqsets - 4 * iscsi_idx);
 
 		S("QType:", "iSCSI");
 		T("TxQ ID:", q.cntxt_id);
@@ -2454,7 +2454,7 @@ do { \
 static int sge_queue_entries(const struct adapter *adap)
 {
 	return DIV_ROUND_UP(adap->sge.ethqsets, 4) +
-	       DIV_ROUND_UP(adap->sge.ofldqsets, 4) +
+	       DIV_ROUND_UP(adap->sge.iscsiqsets, 4) +
 	       DIV_ROUND_UP(adap->sge.rdmaqs, 4) +
 	       DIV_ROUND_UP(adap->sge.rdmaciqs, 4) +
 	       DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 8490c845a815..2642593289d9 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -766,8 +766,8 @@ static void name_msix_vecs(struct adapter *adap)
 	}
 
 	/* offload queues */
-	for_each_ofldrxq(&adap->sge, i)
-		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-ofld%d",
+	for_each_iscsirxq(&adap->sge, i)
+		snprintf(adap->msix_info[msi_idx++].desc, n, "%s-iscsi%d",
 			 adap->port[0]->name, i);
 
 	for_each_rdmarxq(&adap->sge, i)
@@ -782,7 +782,7 @@ static void name_msix_vecs(struct adapter *adap)
 static int request_msix_queue_irqs(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
-	int err, ethqidx, ofldqidx = 0, rdmaqidx = 0, rdmaciqqidx = 0;
+	int err, ethqidx, iscsiqidx = 0, rdmaqidx = 0, rdmaciqqidx = 0;
 	int msi_index = 2;
 
 	err = request_irq(adap->msix_info[1].vec, t4_sge_intr_msix, 0,
@@ -799,11 +799,11 @@ static int request_msix_queue_irqs(struct adapter *adap)
 			goto unwind;
 		msi_index++;
 	}
-	for_each_ofldrxq(s, ofldqidx) {
+	for_each_iscsirxq(s, iscsiqidx) {
 		err = request_irq(adap->msix_info[msi_index].vec,
 				  t4_sge_intr_msix, 0,
 				  adap->msix_info[msi_index].desc,
-				  &s->ofldrxq[ofldqidx].rspq);
+				  &s->iscsirxq[iscsiqidx].rspq);
 		if (err)
 			goto unwind;
 		msi_index++;
@@ -835,9 +835,9 @@ unwind:
 	while (--rdmaqidx >= 0)
 		free_irq(adap->msix_info[--msi_index].vec,
 			 &s->rdmarxq[rdmaqidx].rspq);
-	while (--ofldqidx >= 0)
+	while (--iscsiqidx >= 0)
 		free_irq(adap->msix_info[--msi_index].vec,
-			 &s->ofldrxq[ofldqidx].rspq);
+			 &s->iscsirxq[iscsiqidx].rspq);
 	while (--ethqidx >= 0)
 		free_irq(adap->msix_info[--msi_index].vec,
 			 &s->ethrxq[ethqidx].rspq);
@@ -853,8 +853,9 @@ static void free_msix_queue_irqs(struct adapter *adap)
 	free_irq(adap->msix_info[1].vec, &s->fw_evtq);
 	for_each_ethrxq(s, i)
 		free_irq(adap->msix_info[msi_index++].vec, &s->ethrxq[i].rspq);
-	for_each_ofldrxq(s, i)
-		free_irq(adap->msix_info[msi_index++].vec, &s->ofldrxq[i].rspq);
+	for_each_iscsirxq(s, i)
+		free_irq(adap->msix_info[msi_index++].vec,
+			 &s->iscsirxq[i].rspq);
 	for_each_rdmarxq(s, i)
 		free_irq(adap->msix_info[msi_index++].vec, &s->rdmarxq[i].rspq);
 	for_each_rdmaciq(s, i)
@@ -1093,8 +1094,8 @@ freeout:	t4_free_sge_resources(adap);
 		}
 	}
 
-	j = s->ofldqsets / adap->params.nports; /* ofld queues per channel */
-	for_each_ofldrxq(s, i) {
+	j = s->iscsiqsets / adap->params.nports; /* iscsi queues per channel */
+	for_each_iscsirxq(s, i) {
 		err = t4_sge_alloc_ofld_txq(adap, &s->ofldtxq[i],
 					    adap->port[i / j],
 					    s->fw_evtq.cntxt_id);
@@ -1110,7 +1111,7 @@ freeout:	t4_free_sge_resources(adap);
 		msi_idx += nq; \
 } while (0)
 
-	ALLOC_OFLD_RXQS(s->ofldrxq, s->ofldqsets, j, s->ofld_rxq);
+	ALLOC_OFLD_RXQS(s->iscsirxq, s->iscsiqsets, j, s->iscsi_rxq);
 	ALLOC_OFLD_RXQS(s->rdmarxq, s->rdmaqs, 1, s->rdma_rxq);
 	j = s->rdmaciqs / adap->params.nports; /* rdmaq queues per channel */
 	ALLOC_OFLD_RXQS(s->rdmaciq, s->rdmaciqs, j, s->rdma_ciq);
@@ -2277,7 +2278,7 @@ static void disable_dbs(struct adapter *adap)
 
 	for_each_ethrxq(&adap->sge, i)
 		disable_txq_db(&adap->sge.ethtxq[i].q);
-	for_each_ofldrxq(&adap->sge, i)
+	for_each_iscsirxq(&adap->sge, i)
 		disable_txq_db(&adap->sge.ofldtxq[i].q);
 	for_each_port(adap, i)
 		disable_txq_db(&adap->sge.ctrlq[i].q);
@@ -2289,7 +2290,7 @@ static void enable_dbs(struct adapter *adap)
 
 	for_each_ethrxq(&adap->sge, i)
 		enable_txq_db(adap, &adap->sge.ethtxq[i].q);
-	for_each_ofldrxq(&adap->sge, i)
+	for_each_iscsirxq(&adap->sge, i)
 		enable_txq_db(adap, &adap->sge.ofldtxq[i].q);
 	for_each_port(adap, i)
 		enable_txq_db(adap, &adap->sge.ctrlq[i].q);
@@ -2359,7 +2360,7 @@ static void recover_all_queues(struct adapter *adap)
 
 	for_each_ethrxq(&adap->sge, i)
 		sync_txq_pidx(adap, &adap->sge.ethtxq[i].q);
-	for_each_ofldrxq(&adap->sge, i)
+	for_each_iscsirxq(&adap->sge, i)
 		sync_txq_pidx(adap, &adap->sge.ofldtxq[i].q);
 	for_each_port(adap, i)
 		sync_txq_pidx(adap, &adap->sge.ctrlq[i].q);
@@ -2443,10 +2444,10 @@ static void uld_attach(struct adapter *adap, unsigned int uld)
 		lli.nrxq = adap->sge.rdmaqs;
 		lli.nciq = adap->sge.rdmaciqs;
 	} else if (uld == CXGB4_ULD_ISCSI) {
-		lli.rxq_ids = adap->sge.ofld_rxq;
-		lli.nrxq = adap->sge.ofldqsets;
+		lli.rxq_ids = adap->sge.iscsi_rxq;
+		lli.nrxq = adap->sge.iscsiqsets;
 	}
-	lli.ntxq = adap->sge.ofldqsets;
+	lli.ntxq = adap->sge.iscsiqsets;
 	lli.nchan = adap->params.nports;
 	lli.nports = adap->params.nports;
 	lli.wr_cred = adap->params.ofldq_wr_cred;
@@ -4342,11 +4343,11 @@ static void cfg_queues(struct adapter *adap)
 		 * capped by the number of available cores.
 		 */
 		if (n10g) {
-			i = min_t(int, ARRAY_SIZE(s->ofldrxq),
+			i = min_t(int, ARRAY_SIZE(s->iscsirxq),
 				  num_online_cpus());
-			s->ofldqsets = roundup(i, adap->params.nports);
+			s->iscsiqsets = roundup(i, adap->params.nports);
 		} else
-			s->ofldqsets = adap->params.nports;
+			s->iscsiqsets = adap->params.nports;
 		/* For RDMA one Rx queue per channel suffices */
 		s->rdmaqs = adap->params.nports;
 		/* Try and allow at least 1 CIQ per cpu rounding down
@@ -4377,8 +4378,8 @@ static void cfg_queues(struct adapter *adap)
 	for (i = 0; i < ARRAY_SIZE(s->ofldtxq); i++)
 		s->ofldtxq[i].q.size = 1024;
 
-	for (i = 0; i < ARRAY_SIZE(s->ofldrxq); i++) {
-		struct sge_ofld_rxq *r = &s->ofldrxq[i];
+	for (i = 0; i < ARRAY_SIZE(s->iscsirxq); i++) {
+		struct sge_ofld_rxq *r = &s->iscsirxq[i];
 
 		init_rspq(adap, &r->rspq, 5, 1, 1024, 64);
 		r->rspq.uld = CXGB4_ULD_ISCSI;
@@ -4459,7 +4460,7 @@ static int enable_msix(struct adapter *adap)
 
 	want = s->max_ethqsets + EXTRA_VECS;
 	if (is_offload(adap)) {
-		want += s->rdmaqs + s->rdmaciqs + s->ofldqsets;
+		want += s->rdmaqs + s->rdmaciqs + s->iscsiqsets;
 		/* need nchan for each possible ULD */
 		ofld_need = 3 * nchan;
 	}
@@ -4498,13 +4499,13 @@ static int enable_msix(struct adapter *adap)
 		/* leftovers go to OFLD */
 		i = allocated - EXTRA_VECS - s->max_ethqsets -
 		    s->rdmaqs - s->rdmaciqs;
-		s->ofldqsets = (i / nchan) * nchan;  /* round down */
+		s->iscsiqsets = (i / nchan) * nchan;  /* round down */
 	}
 	for (i = 0; i < allocated; ++i)
 		adap->msix_info[i].vec = entries[i].vector;
 	dev_info(adap->pdev_dev, "%d MSI-X vectors allocated, "
 		 "nic %d iscsi %d rdma cpl %d rdma ciq %d\n",
-		 allocated, s->max_ethqsets, s->ofldqsets, s->rdmaqs,
+		 allocated, s->max_ethqsets, s->iscsiqsets, s->rdmaqs,
 		 s->rdmaciqs);
 
 	kfree(entries);
@@ -4532,6 +4533,79 @@ static int init_rss(struct adapter *adap)
 	return 0;
 }
 
+static int cxgb4_get_pcie_dev_link_caps(struct adapter *adap,
+					enum pci_bus_speed *speed,
+					enum pcie_link_width *width)
+{
+	u32 lnkcap1, lnkcap2;
+	int err1, err2;
+
+#define  PCIE_MLW_CAP_SHIFT 4   /* start of MLW mask in link capabilities */
+
+	*speed = PCI_SPEED_UNKNOWN;
+	*width = PCIE_LNK_WIDTH_UNKNOWN;
+
+	err1 = pcie_capability_read_dword(adap->pdev, PCI_EXP_LNKCAP,
+					  &lnkcap1);
+	err2 = pcie_capability_read_dword(adap->pdev, PCI_EXP_LNKCAP2,
+					  &lnkcap2);
+	if (!err2 && lnkcap2) { /* PCIe r3.0-compliant */
+		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
+			*speed = PCIE_SPEED_8_0GT;
+		else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB)
+			*speed = PCIE_SPEED_5_0GT;
+		else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB)
+			*speed = PCIE_SPEED_2_5GT;
+	}
+	if (!err1) {
+		*width = (lnkcap1 & PCI_EXP_LNKCAP_MLW) >> PCIE_MLW_CAP_SHIFT;
+		if (!lnkcap2) { /* pre-r3.0 */
+			if (lnkcap1 & PCI_EXP_LNKCAP_SLS_5_0GB)
+				*speed = PCIE_SPEED_5_0GT;
+			else if (lnkcap1 & PCI_EXP_LNKCAP_SLS_2_5GB)
+				*speed = PCIE_SPEED_2_5GT;
+		}
+	}
+
+	if (*speed == PCI_SPEED_UNKNOWN || *width == PCIE_LNK_WIDTH_UNKNOWN)
+		return err1 ? err1 : err2 ? err2 : -EINVAL;
+	return 0;
+}
+
+static void cxgb4_check_pcie_caps(struct adapter *adap)
+{
+	enum pcie_link_width width, width_cap;
+	enum pci_bus_speed speed, speed_cap;
+
+#define PCIE_SPEED_STR(speed) \
+	(speed == PCIE_SPEED_8_0GT ? "8.0GT/s" : \
+	 speed == PCIE_SPEED_5_0GT ? "5.0GT/s" : \
+	 speed == PCIE_SPEED_2_5GT ? "2.5GT/s" : \
+	 "Unknown")
+
+	if (cxgb4_get_pcie_dev_link_caps(adap, &speed_cap, &width_cap)) {
+		dev_warn(adap->pdev_dev,
+			 "Unable to determine PCIe device BW capabilities\n");
+		return;
+	}
+
+	if (pcie_get_minimum_link(adap->pdev, &speed, &width) ||
+	    speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN) {
+		dev_warn(adap->pdev_dev,
+			 "Unable to determine PCI Express bandwidth.\n");
+		return;
+	}
+
+	dev_info(adap->pdev_dev, "PCIe link speed is %s, device supports %s\n",
+		 PCIE_SPEED_STR(speed), PCIE_SPEED_STR(speed_cap));
+	dev_info(adap->pdev_dev, "PCIe link width is x%d, device supports x%d\n",
+		 width, width_cap);
+	if (speed < speed_cap || width < width_cap)
+		dev_info(adap->pdev_dev,
+			 "A slot with more lanes and/or higher speed is "
+			 "suggested for optimal performance.\n");
+}
+
 static void print_port_info(const struct net_device *dev)
 {
 	char buf[80];
@@ -4559,10 +4633,10 @@ static void print_port_info(const struct net_device *dev)
 		--bufp;
 	sprintf(bufp, "BASE-%s", t4_get_port_type_description(pi->port_type));
 
-	netdev_info(dev, "Chelsio %s rev %d %s %sNIC PCIe x%d%s%s\n",
+	netdev_info(dev, "Chelsio %s rev %d %s %sNIC %s\n",
 		    adap->params.vpd.id,
 		    CHELSIO_CHIP_RELEASE(adap->params.chip), buf,
-		    is_offload(adap) ? "R" : "", adap->params.pci.width, spd,
+		    is_offload(adap) ? "R" : "",
 		    (adap->flags & USING_MSIX) ? " MSI-X" :
 		    (adap->flags & USING_MSI) ? " MSI" : "");
 	netdev_info(dev, "S/N: %s, P/N: %s\n",
@@ -4908,6 +4982,9 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	else if (msi > 0 && pci_enable_msi(pdev) == 0)
 		adapter->flags |= USING_MSI;
 
+	/* check for PCI Express bandwidth capabiltites */
+	cxgb4_check_pcie_caps(adapter);
+
 	err = init_rss(adapter);
 	if (err)
 		goto out_free_dev;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 8d35ce317f67..5e3ffa73ee13 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -2288,7 +2288,7 @@ static int napi_rx_handler(struct napi_struct *napi, int budget)
 	if (likely(work_done < budget)) {
 		int timer_index;
 
-		napi_complete(napi);
+		napi_complete_done(napi, work_done);
 		timer_index = QINTR_TIMER_IDX_G(q->next_intr_params);
 
 		if (q->adaptive_rx) {
@@ -2555,7 +2555,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	iq->size = roundup(iq->size, 16);
 
 	iq->desc = alloc_ring(adap->pdev_dev, iq->size, iq->iqe_len, 0,
-			      &iq->phys_addr, NULL, 0, NUMA_NO_NODE);
+			      &iq->phys_addr, NULL, 0,
+			      dev_to_node(adap->pdev_dev));
 	if (!iq->desc)
 		return -ENOMEM;
 
@@ -2595,7 +2596,8 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 		fl->size = roundup(fl->size, 8);
 		fl->desc = alloc_ring(adap->pdev_dev, fl->size, sizeof(__be64),
 				      sizeof(struct rx_sw_desc), &fl->addr,
-				      &fl->sdesc, s->stat_len, NUMA_NO_NODE);
+				      &fl->sdesc, s->stat_len,
+				      dev_to_node(adap->pdev_dev));
 		if (!fl->desc)
 			goto fl_nomem;
 
@@ -2978,7 +2980,7 @@ void t4_free_sge_resources(struct adapter *adap)
 	}
 
 	/* clean up RDMA and iSCSI Rx queues */
-	t4_free_ofld_rxqs(adap, adap->sge.ofldqsets, adap->sge.ofldrxq);
+	t4_free_ofld_rxqs(adap, adap->sge.iscsiqsets, adap->sge.iscsirxq);
 	t4_free_ofld_rxqs(adap, adap->sge.rdmaqs, adap->sge.rdmarxq);
 	t4_free_ofld_rxqs(adap, adap->sge.rdmaciqs, adap->sge.rdmaciq);