From 7f9e5c48c1078507747434d4c182ab10925bf98a Mon Sep 17 00:00:00 2001
From: David Dillow <dillowda@ornl.gov>
Date: Mon, 17 Jan 2011 02:09:44 +0000
Subject: IB: Increase DMA max_segment_size on Mellanox hardware

By default, each device is assumed to be able only handle 64 KB chunks
during DMA. By giving the segment size a larger value, the block layer
will coalesce more S/G entries together for SRP, allowing larger
requests with the same sg_tablesize setting.  The block layer is the
only direct user of it, though a few IOMMU drivers reference it as
well for their *_map_sg coalescing code. pci-gart_64 on x86, and a
smattering on on sparc, powerpc, and ia64.

Since other IB protocols could potentially see larger segments with
this, let's check those:

 - iSER is fine, because you limit your maximum request size to 512
   KB, so we'll never overrun the page vector in struct iser_page_vec
   (128 entries currently). It is independent of the DMA segment size,
   and handles multi-page segments already.

 - IPoIB is fine, as it maps each page individually, and doesn't use
   ib_dma_map_sg().

 - RDS appears to do the right thing and has no dependencies on DMA
   segment size, but I don't claim to have done a complete audit.

 - NFSoRDMA and 9p are OK -- they do not use ib_dma_map_sg(), so they
   doesn't care about the coalescing.

 - Lustre's ko2iblnd does not care about coalescing -- it properly
   walks the returned sg list.

This patch ups the value on Mellanox hardware to 1 GB, which matches
reported firmware limits on mlx4.

Signed-off-by: David Dillow <dillowda@ornl.gov>
Signed-off-by: Roland Dreier <roland@purestorage.com>
---
 drivers/net/mlx4/main.c | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 2765a3ce9c24..c83501122d77 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -1109,6 +1109,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 		}
 	}
 
+	/* Allow large DMA segments, up to the firmware limit of 1 GB */
+	dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024);
+
 	priv = kzalloc(sizeof *priv, GFP_KERNEL);
 	if (!priv) {
 		dev_err(&pdev->dev, "Device struct alloc failed, "
-- 
cgit v1.2.3


From 0b7ca5a928e2271bbc225e9e1ac1f22e9fbee54f Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Tue, 22 Mar 2011 22:37:47 +0000
Subject: mlx4: Changing interrupt scheme

Adding a pool of MSI-X vectors and EQs that can be used explicitly by mlx4_core
customers (mlx4_ib, mlx4_en). The consumers will assign their own names to the
interrupt vectors. Those vectors are not opened at mlx4 device initialization,
opened by demand.
Changed the max number of possible EQs according to the new scheme, no longer relies on
on number of cores.
The new functionality is exposed through mlx4_assign_eq() and mlx4_release_eq().
Customers that do not use the new API will get completion vectors as before.

Signed-off-by: Markuze Alex <markuze@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mlx4/cq.c       |   2 +-
 drivers/net/mlx4/eq.c       | 107 +++++++++++++++++++++++++++++++++++++++++---
 drivers/net/mlx4/main.c     |  20 +++++++--
 drivers/net/mlx4/mlx4.h     |   6 +++
 drivers/net/mlx4/profile.c  |   4 +-
 include/linux/mlx4/device.h |   8 ++++
 6 files changed, 134 insertions(+), 13 deletions(-)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index 7cd34e9c7c7e..bd8ef9f2fa71 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -198,7 +198,7 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 	u64 mtt_addr;
 	int err;
 
-	if (vector >= dev->caps.num_comp_vectors)
+	if (vector > dev->caps.num_comp_vectors + dev->caps.comp_pool)
 		return -EINVAL;
 
 	cq->vector = vector;
diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c
index 552d0fce6f67..506cfd0372ec 100644
--- a/drivers/net/mlx4/eq.c
+++ b/drivers/net/mlx4/eq.c
@@ -42,7 +42,7 @@
 #include "fw.h"
 
 enum {
-	MLX4_IRQNAME_SIZE	= 64
+	MLX4_IRQNAME_SIZE	= 32
 };
 
 enum {
@@ -317,8 +317,8 @@ static int mlx4_num_eq_uar(struct mlx4_dev *dev)
 	 * we need to map, take the difference of highest index and
 	 * the lowest index we'll use and add 1.
 	 */
-	return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs) / 4 -
-		dev->caps.reserved_eqs / 4 + 1;
+	return (dev->caps.num_comp_vectors + 1 + dev->caps.reserved_eqs +
+		 dev->caps.comp_pool)/4 - dev->caps.reserved_eqs/4 + 1;
 }
 
 static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq)
@@ -496,16 +496,32 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 static void mlx4_free_irqs(struct mlx4_dev *dev)
 {
 	struct mlx4_eq_table *eq_table = &mlx4_priv(dev)->eq_table;
-	int i;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int	i, vec;
 
 	if (eq_table->have_irq)
 		free_irq(dev->pdev->irq, dev);
+
 	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
 		if (eq_table->eq[i].have_irq) {
 			free_irq(eq_table->eq[i].irq, eq_table->eq + i);
 			eq_table->eq[i].have_irq = 0;
 		}
 
+	for (i = 0; i < dev->caps.comp_pool; i++) {
+		/*
+		 * Freeing the assigned irq's
+		 * all bits should be 0, but we need to validate
+		 */
+		if (priv->msix_ctl.pool_bm & 1ULL << i) {
+			/* NO need protecting*/
+			vec = dev->caps.num_comp_vectors + 1 + i;
+			free_irq(priv->eq_table.eq[vec].irq,
+				 &priv->eq_table.eq[vec]);
+		}
+	}
+
+
 	kfree(eq_table->irq_names);
 }
 
@@ -578,7 +594,8 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 		(priv->eq_table.inta_pin < 32 ? 4 : 0);
 
 	priv->eq_table.irq_names =
-		kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1),
+		kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1 +
+					     dev->caps.comp_pool),
 			GFP_KERNEL);
 	if (!priv->eq_table.irq_names) {
 		err = -ENOMEM;
@@ -601,6 +618,22 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 	if (err)
 		goto err_out_comp;
 
+	/*if additional completion vectors poolsize is 0 this loop will not run*/
+	for (i = dev->caps.num_comp_vectors + 1;
+	      i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i) {
+
+		err = mlx4_create_eq(dev, dev->caps.num_cqs -
+					  dev->caps.reserved_cqs +
+					  MLX4_NUM_SPARE_EQE,
+				     (dev->flags & MLX4_FLAG_MSI_X) ? i : 0,
+				     &priv->eq_table.eq[i]);
+		if (err) {
+			--i;
+			goto err_out_unmap;
+		}
+	}
+
+
 	if (dev->flags & MLX4_FLAG_MSI_X) {
 		const char *eq_name;
 
@@ -686,7 +719,7 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
 
 	mlx4_free_irqs(dev);
 
-	for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i)
+	for (i = 0; i < dev->caps.num_comp_vectors + dev->caps.comp_pool + 1; ++i)
 		mlx4_free_eq(dev, &priv->eq_table.eq[i]);
 
 	mlx4_unmap_clr_int(dev);
@@ -743,3 +776,65 @@ int mlx4_test_interrupts(struct mlx4_dev *dev)
 	return err;
 }
 EXPORT_SYMBOL(mlx4_test_interrupts);
+
+int mlx4_assign_eq(struct mlx4_dev *dev, char* name, int * vector)
+{
+
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int vec = 0, err = 0, i;
+
+	spin_lock(&priv->msix_ctl.pool_lock);
+	for (i = 0; !vec && i < dev->caps.comp_pool; i++) {
+		if (~priv->msix_ctl.pool_bm & 1ULL << i) {
+			priv->msix_ctl.pool_bm |= 1ULL << i;
+			vec = dev->caps.num_comp_vectors + 1 + i;
+			snprintf(priv->eq_table.irq_names +
+					vec * MLX4_IRQNAME_SIZE,
+					MLX4_IRQNAME_SIZE, "%s", name);
+			err = request_irq(priv->eq_table.eq[vec].irq,
+					  mlx4_msi_x_interrupt, 0,
+					  &priv->eq_table.irq_names[vec<<5],
+					  priv->eq_table.eq + vec);
+			if (err) {
+				/*zero out bit by fliping it*/
+				priv->msix_ctl.pool_bm ^= 1 << i;
+				vec = 0;
+				continue;
+				/*we dont want to break here*/
+			}
+			eq_set_ci(&priv->eq_table.eq[vec], 1);
+		}
+	}
+	spin_unlock(&priv->msix_ctl.pool_lock);
+
+	if (vec) {
+		*vector = vec;
+	} else {
+		*vector = 0;
+		err = (i == dev->caps.comp_pool) ? -ENOSPC : err;
+	}
+	return err;
+}
+EXPORT_SYMBOL(mlx4_assign_eq);
+
+void mlx4_release_eq(struct mlx4_dev *dev, int vec)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	/*bm index*/
+	int i = vec - dev->caps.num_comp_vectors - 1;
+
+	if (likely(i >= 0)) {
+		/*sanity check , making sure were not trying to free irq's
+		  Belonging to a legacy EQ*/
+		spin_lock(&priv->msix_ctl.pool_lock);
+		if (priv->msix_ctl.pool_bm & 1ULL << i) {
+			free_irq(priv->eq_table.eq[vec].irq,
+				 &priv->eq_table.eq[vec]);
+			priv->msix_ctl.pool_bm &= ~(1ULL << i);
+		}
+		spin_unlock(&priv->msix_ctl.pool_lock);
+	}
+
+}
+EXPORT_SYMBOL(mlx4_release_eq);
+
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 2765a3ce9c24..517ca34f5b37 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -969,13 +969,15 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct msix_entry *entries;
-	int nreq;
+	int nreq = min_t(int, dev->caps.num_ports *
+			 min_t(int, num_online_cpus() + 1, MAX_MSIX_P_PORT)
+				+ MSIX_LEGACY_SZ, MAX_MSIX);
 	int err;
 	int i;
 
 	if (msi_x) {
 		nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
-			     num_possible_cpus() + 1);
+			     nreq);
 		entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
 		if (!entries)
 			goto no_msi;
@@ -998,7 +1000,15 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 			goto no_msi;
 		}
 
-		dev->caps.num_comp_vectors = nreq - 1;
+		if (nreq <
+		    MSIX_LEGACY_SZ + dev->caps.num_ports * MIN_MSIX_P_PORT) {
+			/*Working in legacy mode , all EQ's shared*/
+			dev->caps.comp_pool           = 0;
+			dev->caps.num_comp_vectors = nreq - 1;
+		} else {
+			dev->caps.comp_pool           = nreq - MSIX_LEGACY_SZ;
+			dev->caps.num_comp_vectors = MSIX_LEGACY_SZ - 1;
+		}
 		for (i = 0; i < nreq; ++i)
 			priv->eq_table.eq[i].irq = entries[i].vector;
 
@@ -1010,6 +1020,7 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
 
 no_msi:
 	dev->caps.num_comp_vectors = 1;
+	dev->caps.comp_pool	   = 0;
 
 	for (i = 0; i < 2; ++i)
 		priv->eq_table.eq[i].irq = dev->pdev->irq;
@@ -1151,6 +1162,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_close;
 
+	priv->msix_ctl.pool_bm = 0;
+	spin_lock_init(&priv->msix_ctl.pool_lock);
+
 	mlx4_enable_msi_x(dev);
 
 	err = mlx4_setup_hca(dev);
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 0da5bb7285b4..67ee8dacae79 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -282,6 +282,11 @@ struct mlx4_sense {
 	struct delayed_work	sense_poll;
 };
 
+struct mlx4_msix_ctl {
+	u64		pool_bm;
+	spinlock_t	pool_lock;
+};
+
 struct mlx4_priv {
 	struct mlx4_dev		dev;
 
@@ -313,6 +318,7 @@ struct mlx4_priv {
 	struct mlx4_port_info	port[MLX4_MAX_PORTS + 1];
 	struct mlx4_sense       sense;
 	struct mutex		port_mutex;
+	struct mlx4_msix_ctl	msix_ctl;
 };
 
 static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
diff --git a/drivers/net/mlx4/profile.c b/drivers/net/mlx4/profile.c
index e749f82865fe..b967647d0c76 100644
--- a/drivers/net/mlx4/profile.c
+++ b/drivers/net/mlx4/profile.c
@@ -107,9 +107,7 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	profile[MLX4_RES_AUXC].num    = request->num_qp;
 	profile[MLX4_RES_SRQ].num     = request->num_srq;
 	profile[MLX4_RES_CQ].num      = request->num_cq;
-	profile[MLX4_RES_EQ].num      = min_t(unsigned, dev_cap->max_eqs,
-					      dev_cap->reserved_eqs +
-					      num_possible_cpus() + 1);
+	profile[MLX4_RES_EQ].num      = min_t(unsigned, dev_cap->max_eqs, MAX_MSIX);
 	profile[MLX4_RES_DMPT].num    = request->num_mpt;
 	profile[MLX4_RES_CMPT].num    = MLX4_NUM_CMPTS;
 	profile[MLX4_RES_MTT].num     = request->num_mtt;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 049214642036..78380823d827 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -39,6 +39,11 @@
 
 #include <asm/atomic.h>
 
+#define MAX_MSIX_P_PORT		17
+#define MAX_MSIX		64
+#define MSIX_LEGACY_SZ		4
+#define MIN_MSIX_P_PORT		5
+
 enum {
 	MLX4_FLAG_MSI_X		= 1 << 0,
 	MLX4_FLAG_OLD_PORT_CMDS	= 1 << 1,
@@ -223,6 +228,7 @@ struct mlx4_caps {
 	int			num_eqs;
 	int			reserved_eqs;
 	int			num_comp_vectors;
+	int			comp_pool;
 	int			num_mpts;
 	int			num_mtt_segs;
 	int			mtts_per_seg;
@@ -526,5 +532,7 @@ void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
 int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr);
 int mlx4_SYNC_TPT(struct mlx4_dev *dev);
 int mlx4_test_interrupts(struct mlx4_dev *dev);
+int mlx4_assign_eq(struct mlx4_dev *dev, char* name , int* vector);
+void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
 #endif /* MLX4_DEVICE_H */
-- 
cgit v1.2.3


From 14c07b1358ede1664652bb9b28d9ace5fe6f7f92 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Tue, 22 Mar 2011 22:37:59 +0000
Subject: mlx4: Wake on LAN support

The driver queries the FW for WOL support.
Ethtool get/set_wol is implemented accordingly.
Only magic packets are supported at the time.

Signed-off-by: Igor Yarovinsky <igory@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mlx4/en_ethtool.c | 62 +++++++++++++++++++++++++++++++++++++++++--
 drivers/net/mlx4/fw.c         | 20 ++++++++++++++
 drivers/net/mlx4/fw.h         |  1 +
 drivers/net/mlx4/main.c       |  1 +
 drivers/net/mlx4/mlx4_en.h    |  7 +++++
 include/linux/mlx4/device.h   |  4 +++
 6 files changed, 93 insertions(+), 2 deletions(-)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/net/mlx4/en_ethtool.c b/drivers/net/mlx4/en_ethtool.c
index 8cfe8586ed2d..c1f351f6ae57 100644
--- a/drivers/net/mlx4/en_ethtool.c
+++ b/drivers/net/mlx4/en_ethtool.c
@@ -131,8 +131,65 @@ static void mlx4_en_set_msglevel(struct net_device *dev, u32 val)
 static void mlx4_en_get_wol(struct net_device *netdev,
 			    struct ethtool_wolinfo *wol)
 {
-	wol->supported = 0;
-	wol->wolopts = 0;
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	int err = 0;
+	u64 config = 0;
+
+	if (!priv->mdev->dev->caps.wol) {
+		wol->supported = 0;
+		wol->wolopts = 0;
+		return;
+	}
+
+	err = mlx4_wol_read(priv->mdev->dev, &config, priv->port);
+	if (err) {
+		en_err(priv, "Failed to get WoL information\n");
+		return;
+	}
+
+	if (config & MLX4_EN_WOL_MAGIC)
+		wol->supported = WAKE_MAGIC;
+	else
+		wol->supported = 0;
+
+	if (config & MLX4_EN_WOL_ENABLED)
+		wol->wolopts = WAKE_MAGIC;
+	else
+		wol->wolopts = 0;
+}
+
+static int mlx4_en_set_wol(struct net_device *netdev,
+			    struct ethtool_wolinfo *wol)
+{
+	struct mlx4_en_priv *priv = netdev_priv(netdev);
+	u64 config = 0;
+	int err = 0;
+
+	if (!priv->mdev->dev->caps.wol)
+		return -EOPNOTSUPP;
+
+	if (wol->supported & ~WAKE_MAGIC)
+		return -EINVAL;
+
+	err = mlx4_wol_read(priv->mdev->dev, &config, priv->port);
+	if (err) {
+		en_err(priv, "Failed to get WoL info, unable to modify\n");
+		return err;
+	}
+
+	if (wol->wolopts & WAKE_MAGIC) {
+		config |= MLX4_EN_WOL_DO_MODIFY | MLX4_EN_WOL_ENABLED |
+				MLX4_EN_WOL_MAGIC;
+	} else {
+		config &= ~(MLX4_EN_WOL_ENABLED | MLX4_EN_WOL_MAGIC);
+		config |= MLX4_EN_WOL_DO_MODIFY;
+	}
+
+	err = mlx4_wol_write(priv->mdev->dev, config, priv->port);
+	if (err)
+		en_err(priv, "Failed to set WoL information\n");
+
+	return err;
 }
 
 static int mlx4_en_get_sset_count(struct net_device *dev, int sset)
@@ -442,6 +499,7 @@ const struct ethtool_ops mlx4_en_ethtool_ops = {
 	.get_ethtool_stats = mlx4_en_get_ethtool_stats,
 	.self_test = mlx4_en_self_test,
 	.get_wol = mlx4_en_get_wol,
+	.set_wol = mlx4_en_set_wol,
 	.get_msglevel = mlx4_en_get_msglevel,
 	.set_msglevel = mlx4_en_set_msglevel,
 	.get_coalesce = mlx4_en_get_coalesce,
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index 5de1db897835..fd1c51b6197a 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -276,6 +276,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev_cap->udp_rss = field & 0x1;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_ETH_UC_LOOPBACK_OFFSET);
 	dev_cap->loopback_support = field & 0x1;
+	dev_cap->wol = field & 0x40;
 	MLX4_GET(dev_cap->flags, outbox, QUERY_DEV_CAP_FLAGS_OFFSET);
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_RSVD_UAR_OFFSET);
 	dev_cap->reserved_uars = field >> 4;
@@ -908,3 +909,22 @@ int mlx4_NOP(struct mlx4_dev *dev)
 	/* Input modifier of 0x1f means "finish as soon as possible." */
 	return mlx4_cmd(dev, 0, 0x1f, 0, MLX4_CMD_NOP, 100);
 }
+
+#define MLX4_WOL_SETUP_MODE (5 << 28)
+int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port)
+{
+	u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
+
+	return mlx4_cmd_imm(dev, 0, config, in_mod, 0x3,
+			    MLX4_CMD_MOD_STAT_CFG, MLX4_CMD_TIME_CLASS_A);
+}
+EXPORT_SYMBOL_GPL(mlx4_wol_read);
+
+int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port)
+{
+	u32 in_mod = MLX4_WOL_SETUP_MODE | port << 8;
+
+	return mlx4_cmd(dev, config, in_mod, 0x1, MLX4_CMD_MOD_STAT_CFG,
+					MLX4_CMD_TIME_CLASS_A);
+}
+EXPORT_SYMBOL_GPL(mlx4_wol_write);
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index 65cc72eb899d..f7b9cc2d1b2a 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -80,6 +80,7 @@ struct mlx4_dev_cap {
 	u16 stat_rate_support;
 	int udp_rss;
 	int loopback_support;
+	int wol;
 	u32 flags;
 	int reserved_uars;
 	int uar_size;
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 517ca34f5b37..42d4fb477870 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -227,6 +227,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
 	dev->caps.udp_rss	     = dev_cap->udp_rss;
 	dev->caps.loopback_support   = dev_cap->loopback_support;
+	dev->caps.wol		     = dev_cap->wol;
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 
 	dev->caps.log_num_macs  = log_num_mac;
diff --git a/drivers/net/mlx4/mlx4_en.h b/drivers/net/mlx4/mlx4_en.h
index 2db245fcd84b..07aea8d0beeb 100644
--- a/drivers/net/mlx4/mlx4_en.h
+++ b/drivers/net/mlx4/mlx4_en.h
@@ -479,6 +479,13 @@ struct mlx4_en_priv {
 	int mc_addrs_cnt;
 	struct mlx4_en_stat_out_mbox hw_stats;
 	int vids[128];
+	bool wol;
+};
+
+enum mlx4_en_wol {
+	MLX4_EN_WOL_MAGIC = (1ULL << 61),
+	MLX4_EN_WOL_ENABLED = (1ULL << 62),
+	MLX4_EN_WOL_DO_MODIFY = (1ULL << 63),
 };
 
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 78380823d827..2460356d2c72 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -251,6 +251,7 @@ struct mlx4_caps {
 	u16			stat_rate_support;
 	int			udp_rss;
 	int			loopback_support;
+	int			wol;
 	u8			port_width_cap[MLX4_MAX_PORTS + 1];
 	int			max_gso_sz;
 	int                     reserved_qps_cnt[MLX4_NUM_QP_REGION];
@@ -535,4 +536,7 @@ int mlx4_test_interrupts(struct mlx4_dev *dev);
 int mlx4_assign_eq(struct mlx4_dev *dev, char* name , int* vector);
 void mlx4_release_eq(struct mlx4_dev *dev, int vec);
 
+int mlx4_wol_read(struct mlx4_dev *dev, u64 *config, int port);
+int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port);
+
 #endif /* MLX4_DEVICE_H */
-- 
cgit v1.2.3


From 725c89997e03d71b09ea3c17c997da0712b9d835 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Tue, 22 Mar 2011 22:38:07 +0000
Subject: mlx4_en: Reporting HW revision in ethtool -i

HW revision is derived from device ID and rev id.

Signed-off-by: Eugenia Emantayev <eugenia@mellanox.co.il>
Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c |  1 -
 drivers/net/mlx4/en_ethtool.c     | 15 ++++++++++++++-
 drivers/net/mlx4/main.c           |  2 ++
 drivers/net/mlx4/mlx4_en.h        |  3 +++
 include/linux/mlx4/device.h       |  2 +-
 5 files changed, 20 insertions(+), 3 deletions(-)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index c7a6213c6996..66e3eecfd0db 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -721,7 +721,6 @@ static int init_node_data(struct mlx4_ib_dev *dev)
 	if (err)
 		goto out;
 
-	dev->dev->rev_id = be32_to_cpup((__be32 *) (out_mad->data + 32));
 	memcpy(&dev->ib_dev.node_guid, out_mad->data + 12, 8);
 
 out:
diff --git a/drivers/net/mlx4/en_ethtool.c b/drivers/net/mlx4/en_ethtool.c
index c1f351f6ae57..62ace6c72b42 100644
--- a/drivers/net/mlx4/en_ethtool.c
+++ b/drivers/net/mlx4/en_ethtool.c
@@ -45,7 +45,20 @@ mlx4_en_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *drvinfo)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 
-	sprintf(drvinfo->driver, DRV_NAME " (%s)", mdev->dev->board_id);
+	switch (mdev->dev->rev_id) {
+	case 0xa0:
+		if (dev->dev_id >= MLX4_EN_CX3_LOW_ID && dev->dev_id <= MLX4_EN_CX3_HIGH_ID)
+			sprintf(drvinfo->driver, DRV_NAME " (%s_CX-3)", mdev->dev->board_id);
+		else
+			sprintf(drvinfo->driver, DRV_NAME " (%s_CX)", mdev->dev->board_id);
+		break;
+	case 0xb0:
+		sprintf(drvinfo->driver, DRV_NAME " (%s_CX-2)", mdev->dev->board_id);
+		break;
+	default:
+		sprintf(drvinfo->driver, DRV_NAME " (%s)", mdev->dev->board_id);
+		break;
+	}
 	strncpy(drvinfo->version, DRV_VERSION " (" DRV_RELDATE ")", 32);
 	sprintf(drvinfo->fw_version, "%d.%d.%d",
 		(u16) (mdev->dev->caps.fw_ver >> 32),
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 42d4fb477870..5bebb8800ab2 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -1139,6 +1139,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
 
+	pci_read_config_byte(pdev, PCI_REVISION_ID, &dev->rev_id);
+
 	/*
 	 * Now reset the HCA before we touch the PCI capabilities or
 	 * attempt a firmware command, since a boot ROM may have left
diff --git a/drivers/net/mlx4/mlx4_en.h b/drivers/net/mlx4/mlx4_en.h
index 07aea8d0beeb..ad4df66750bc 100644
--- a/drivers/net/mlx4/mlx4_en.h
+++ b/drivers/net/mlx4/mlx4_en.h
@@ -216,6 +216,9 @@ struct mlx4_en_tx_desc {
 
 #define MLX4_EN_USE_SRQ		0x01000000
 
+#define MLX4_EN_CX3_LOW_ID	0x1000
+#define MLX4_EN_CX3_HIGH_ID	0x1005
+
 struct mlx4_en_rx_alloc {
 	struct page *page;
 	u16 offset;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 2460356d2c72..fe2a3a3f046c 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -422,7 +422,7 @@ struct mlx4_dev {
 	unsigned long		flags;
 	struct mlx4_caps	caps;
 	struct radix_tree_root	qp_table_tree;
-	u32			rev_id;
+	u8			rev_id;
 	char			board_id[MLX4_BOARD_ID_LEN];
 };
 
-- 
cgit v1.2.3


From 0345584e0b8be3735a950d17c7e463db20c6ce27 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Tue, 22 Mar 2011 22:38:17 +0000
Subject: mlx4: generalization of multicast steering.

The same packet steering mechanism would be used both for IB and Ethernet,
Both multicasts and unicasts.
This commit prepares the general infrastructure for this.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/infiniband/hw/mlx4/main.c |  10 ++--
 drivers/net/mlx4/en_main.c        |   2 +-
 drivers/net/mlx4/fw.c             |   2 +
 drivers/net/mlx4/fw.h             |   2 +
 drivers/net/mlx4/main.c           |   2 +
 drivers/net/mlx4/mcg.c            | 113 ++++++++++++++++++++++++++------------
 include/linux/mlx4/device.h       |  14 ++++-
 7 files changed, 102 insertions(+), 43 deletions(-)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 66e3eecfd0db..fbe1973f77b0 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -625,7 +625,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 
 	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw,
 				    !!(mqp->flags & MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
-				    MLX4_PROTOCOL_IB);
+				    MLX4_PROT_IB_IPV6);
 	if (err)
 		return err;
 
@@ -636,7 +636,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	return 0;
 
 err_add:
-	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROTOCOL_IB);
+	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
 	return err;
 }
 
@@ -666,7 +666,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	struct mlx4_ib_gid_entry *ge;
 
 	err = mlx4_multicast_detach(mdev->dev,
-				    &mqp->mqp, gid->raw, MLX4_PROTOCOL_IB);
+				    &mqp->mqp, gid->raw, MLX4_PROT_IB_IPV6);
 	if (err)
 		return err;
 
@@ -953,7 +953,7 @@ static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event
 	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
 		oldnd = iboe->netdevs[port - 1];
 		iboe->netdevs[port - 1] =
-			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROTOCOL_EN, port);
+			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
 		if (oldnd != iboe->netdevs[port - 1]) {
 			if (iboe->netdevs[port - 1])
 				netdev_added(ibdev, port);
@@ -1206,7 +1206,7 @@ static struct mlx4_interface mlx4_ib_interface = {
 	.add		= mlx4_ib_add,
 	.remove		= mlx4_ib_remove,
 	.event		= mlx4_ib_event,
-	.protocol	= MLX4_PROTOCOL_IB
+	.protocol	= MLX4_PROT_IB_IPV6
 };
 
 static int __init mlx4_ib_init(void)
diff --git a/drivers/net/mlx4/en_main.c b/drivers/net/mlx4/en_main.c
index 29aaa4303991..9317b61a75b8 100644
--- a/drivers/net/mlx4/en_main.c
+++ b/drivers/net/mlx4/en_main.c
@@ -296,7 +296,7 @@ static struct mlx4_interface mlx4_en_interface = {
 	.remove		= mlx4_en_remove,
 	.event		= mlx4_en_event,
 	.get_dev	= mlx4_en_get_netdev,
-	.protocol	= MLX4_PROTOCOL_EN,
+	.protocol	= MLX4_PROT_ETH,
 };
 
 static int __init mlx4_en_init(void)
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index fd1c51b6197a..7813913b6d0f 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -274,6 +274,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev_cap->stat_rate_support = stat_rate;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_UDP_RSS_OFFSET);
 	dev_cap->udp_rss = field & 0x1;
+	dev_cap->vep_uc_steering = field & 0x2;
+	dev_cap->vep_mc_steering = field & 0x4;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_ETH_UC_LOOPBACK_OFFSET);
 	dev_cap->loopback_support = field & 0x1;
 	dev_cap->wol = field & 0x40;
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index f7b9cc2d1b2a..88003ebc6185 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -80,6 +80,8 @@ struct mlx4_dev_cap {
 	u16 stat_rate_support;
 	int udp_rss;
 	int loopback_support;
+	int vep_uc_steering;
+	int vep_mc_steering;
 	int wol;
 	u32 flags;
 	int reserved_uars;
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 5bebb8800ab2..da0da281d830 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -227,6 +227,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
 	dev->caps.udp_rss	     = dev_cap->udp_rss;
 	dev->caps.loopback_support   = dev_cap->loopback_support;
+	dev->caps.vep_uc_steering    = dev_cap->vep_uc_steering;
+	dev->caps.vep_mc_steering    = dev_cap->vep_mc_steering;
 	dev->caps.wol		     = dev_cap->wol;
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 
diff --git a/drivers/net/mlx4/mcg.c b/drivers/net/mlx4/mcg.c
index 79cf42db2ea9..b103ad23bd84 100644
--- a/drivers/net/mlx4/mcg.c
+++ b/drivers/net/mlx4/mcg.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/string.h>
+#include <linux/etherdevice.h>
 
 #include <linux/mlx4/cmd.h>
 
@@ -50,28 +51,28 @@ struct mlx4_mgm {
 
 static const u8 zero_gid[16];	/* automatically initialized to 0 */
 
-static int mlx4_READ_MCG(struct mlx4_dev *dev, int index,
-			 struct mlx4_cmd_mailbox *mailbox)
+static int mlx4_READ_ENTRY(struct mlx4_dev *dev, int index,
+			   struct mlx4_cmd_mailbox *mailbox)
 {
 	return mlx4_cmd_box(dev, 0, mailbox->dma, index, 0, MLX4_CMD_READ_MCG,
 			    MLX4_CMD_TIME_CLASS_A);
 }
 
-static int mlx4_WRITE_MCG(struct mlx4_dev *dev, int index,
-			  struct mlx4_cmd_mailbox *mailbox)
+static int mlx4_WRITE_ENTRY(struct mlx4_dev *dev, int index,
+			    struct mlx4_cmd_mailbox *mailbox)
 {
 	return mlx4_cmd(dev, mailbox->dma, index, 0, MLX4_CMD_WRITE_MCG,
 			MLX4_CMD_TIME_CLASS_A);
 }
 
-static int mlx4_MGID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
-			  u16 *hash)
+static int mlx4_GID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
+			 u16 *hash, u8 op_mod)
 {
 	u64 imm;
 	int err;
 
-	err = mlx4_cmd_imm(dev, mailbox->dma, &imm, 0, 0, MLX4_CMD_MGID_HASH,
-			   MLX4_CMD_TIME_CLASS_A);
+	err = mlx4_cmd_imm(dev, mailbox->dma, &imm, 0, op_mod,
+			   MLX4_CMD_MGID_HASH, MLX4_CMD_TIME_CLASS_A);
 
 	if (!err)
 		*hash = imm;
@@ -94,15 +95,17 @@ static int mlx4_MGID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox
  * If no AMGM exists for given gid, *index = -1, *prev = index of last
  * entry in hash chain and *mgm holds end of hash chain.
  */
-static int find_mgm(struct mlx4_dev *dev,
-		    u8 *gid, enum mlx4_protocol protocol,
-		    struct mlx4_cmd_mailbox *mgm_mailbox,
-		    u16 *hash, int *prev, int *index)
+static int find_entry(struct mlx4_dev *dev, u8 port,
+		      u8 *gid, enum mlx4_protocol prot,
+		      enum mlx4_steer_type steer,
+		      struct mlx4_cmd_mailbox *mgm_mailbox,
+		      u16 *hash, int *prev, int *index)
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_mgm *mgm = mgm_mailbox->buf;
 	u8 *mgid;
 	int err;
+	u8 op_mod = (prot == MLX4_PROT_ETH) ? !!(dev->caps.vep_mc_steering) : 0;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -111,7 +114,7 @@ static int find_mgm(struct mlx4_dev *dev,
 
 	memcpy(mgid, gid, 16);
 
-	err = mlx4_MGID_HASH(dev, mailbox, hash);
+	err = mlx4_GID_HASH(dev, mailbox, hash, op_mod);
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	if (err)
 		return err;
@@ -123,11 +126,11 @@ static int find_mgm(struct mlx4_dev *dev,
 	*prev  = -1;
 
 	do {
-		err = mlx4_READ_MCG(dev, *index, mgm_mailbox);
+		err = mlx4_READ_ENTRY(dev, *index, mgm_mailbox);
 		if (err)
 			return err;
 
-		if (!memcmp(mgm->gid, zero_gid, 16)) {
+		if (!(be32_to_cpu(mgm->members_count) & 0xffffff)) {
 			if (*index != *hash) {
 				mlx4_err(dev, "Found zero MGID in AMGM.\n");
 				err = -EINVAL;
@@ -136,7 +139,7 @@ static int find_mgm(struct mlx4_dev *dev,
 		}
 
 		if (!memcmp(mgm->gid, gid, 16) &&
-		    be32_to_cpu(mgm->members_count) >> 30 == protocol)
+		    be32_to_cpu(mgm->members_count) >> 30 == prot)
 			return err;
 
 		*prev = *index;
@@ -147,8 +150,9 @@ static int find_mgm(struct mlx4_dev *dev,
 	return err;
 }
 
-int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-			  int block_mcast_loopback, enum mlx4_protocol protocol)
+int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  int block_mcast_loopback, enum mlx4_protocol prot,
+			  enum mlx4_steer_type steer)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cmd_mailbox *mailbox;
@@ -159,6 +163,7 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	int link = 0;
 	int i;
 	int err;
+	u8 port = gid[5];
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -166,13 +171,13 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	mgm = mailbox->buf;
 
 	mutex_lock(&priv->mcg_table.mutex);
-
-	err = find_mgm(dev, gid, protocol, mailbox, &hash, &prev, &index);
+	err = find_entry(dev, port, gid, prot, steer,
+			 mailbox, &hash, &prev, &index);
 	if (err)
 		goto out;
 
 	if (index != -1) {
-		if (!memcmp(mgm->gid, zero_gid, 16))
+		if (!(be32_to_cpu(mgm->members_count) & 0xffffff))
 			memcpy(mgm->gid, gid, 16);
 	} else {
 		link = 1;
@@ -209,22 +214,22 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	else
 		mgm->qp[members_count++] = cpu_to_be32(qp->qpn & MGM_QPN_MASK);
 
-	mgm->members_count = cpu_to_be32(members_count | (u32) protocol << 30);
+	mgm->members_count = cpu_to_be32(members_count | (u32) prot << 30);
 
-	err = mlx4_WRITE_MCG(dev, index, mailbox);
+	err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 	if (err)
 		goto out;
 
 	if (!link)
 		goto out;
 
-	err = mlx4_READ_MCG(dev, prev, mailbox);
+	err = mlx4_READ_ENTRY(dev, prev, mailbox);
 	if (err)
 		goto out;
 
 	mgm->next_gid_index = cpu_to_be32(index << 6);
 
-	err = mlx4_WRITE_MCG(dev, prev, mailbox);
+	err = mlx4_WRITE_ENTRY(dev, prev, mailbox);
 	if (err)
 		goto out;
 
@@ -242,10 +247,9 @@ out:
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx4_multicast_attach);
 
-int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
-			  enum mlx4_protocol protocol)
+int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  enum mlx4_protocol prot, enum mlx4_steer_type steer)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_cmd_mailbox *mailbox;
@@ -255,6 +259,7 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	int prev, index;
 	int i, loc;
 	int err;
+	u8 port = gid[5];
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -263,7 +268,8 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 
 	mutex_lock(&priv->mcg_table.mutex);
 
-	err = find_mgm(dev, gid, protocol, mailbox, &hash, &prev, &index);
+	err = find_entry(dev, port, gid, prot, steer,
+			 mailbox, &hash, &prev, &index);
 	if (err)
 		goto out;
 
@@ -285,12 +291,12 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	}
 
 
-	mgm->members_count = cpu_to_be32(--members_count | (u32) protocol << 30);
+	mgm->members_count = cpu_to_be32(--members_count | (u32) prot << 30);
 	mgm->qp[loc]       = mgm->qp[i - 1];
 	mgm->qp[i - 1]     = 0;
 
 	if (i != 1) {
-		err = mlx4_WRITE_MCG(dev, index, mailbox);
+		err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 		goto out;
 	}
 
@@ -298,13 +304,13 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 		/* Remove entry from MGM */
 		int amgm_index = be32_to_cpu(mgm->next_gid_index) >> 6;
 		if (amgm_index) {
-			err = mlx4_READ_MCG(dev, amgm_index, mailbox);
+			err = mlx4_READ_ENTRY(dev, amgm_index, mailbox);
 			if (err)
 				goto out;
 		} else
 			memset(mgm->gid, 0, 16);
 
-		err = mlx4_WRITE_MCG(dev, index, mailbox);
+		err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 		if (err)
 			goto out;
 
@@ -319,13 +325,13 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	} else {
 		/* Remove entry from AMGM */
 		int cur_next_index = be32_to_cpu(mgm->next_gid_index) >> 6;
-		err = mlx4_READ_MCG(dev, prev, mailbox);
+		err = mlx4_READ_ENTRY(dev, prev, mailbox);
 		if (err)
 			goto out;
 
 		mgm->next_gid_index = cpu_to_be32(cur_next_index << 6);
 
-		err = mlx4_WRITE_MCG(dev, prev, mailbox);
+		err = mlx4_WRITE_ENTRY(dev, prev, mailbox);
 		if (err)
 			goto out;
 
@@ -343,6 +349,43 @@ out:
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	return err;
 }
+
+
+int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  int block_mcast_loopback, enum mlx4_protocol prot)
+{
+	enum mlx4_steer_type steer;
+
+	steer = (is_valid_ether_addr(&gid[10])) ? MLX4_UC_STEER : MLX4_MC_STEER;
+
+	if (prot == MLX4_PROT_ETH && !dev->caps.vep_mc_steering)
+		return 0;
+
+	if (prot == MLX4_PROT_ETH)
+		gid[7] |= (steer << 1);
+
+	return mlx4_qp_attach_common(dev, qp, gid,
+				     block_mcast_loopback, prot,
+				     steer);
+}
+EXPORT_SYMBOL_GPL(mlx4_multicast_attach);
+
+int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  enum mlx4_protocol prot)
+{
+	enum mlx4_steer_type steer;
+
+	steer = (is_valid_ether_addr(&gid[10])) ? MLX4_UC_STEER : MLX4_MC_STEER;
+
+	if (prot == MLX4_PROT_ETH && !dev->caps.vep_mc_steering)
+		return 0;
+
+	if (prot == MLX4_PROT_ETH) {
+		gid[7] |= (steer << 1);
+	}
+
+	return mlx4_qp_detach_common(dev, qp, gid, prot, steer);
+}
 EXPORT_SYMBOL_GPL(mlx4_multicast_detach);
 
 int mlx4_init_mcg_table(struct mlx4_dev *dev)
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index fe2a3a3f046c..ebda939b9fc3 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -150,8 +150,10 @@ enum {
 };
 
 enum mlx4_protocol {
-	MLX4_PROTOCOL_IB,
-	MLX4_PROTOCOL_EN,
+	MLX4_PROT_IB_IPV6 = 0,
+	MLX4_PROT_ETH,
+	MLX4_PROT_IB_IPV4,
+	MLX4_PROT_FCOE
 };
 
 enum {
@@ -178,6 +180,12 @@ enum mlx4_special_vlan_idx {
 	MLX4_VLAN_REGULAR
 };
 
+enum mlx4_steer_type {
+	MLX4_MC_STEER = 0,
+	MLX4_UC_STEER,
+	MLX4_NUM_STEERS
+};
+
 enum {
 	MLX4_NUM_FEXCH          = 64 * 1024,
 };
@@ -251,6 +259,8 @@ struct mlx4_caps {
 	u16			stat_rate_support;
 	int			udp_rss;
 	int			loopback_support;
+	int			vep_uc_steering;
+	int			vep_mc_steering;
 	int			wol;
 	u8			port_width_cap[MLX4_MAX_PORTS + 1];
 	int			max_gso_sz;
-- 
cgit v1.2.3


From b12d93d63c3217f0ec923ff938b12a744e242ffa Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Tue, 22 Mar 2011 22:38:24 +0000
Subject: mlx4: Add support for promiscuous mode in the new steering model.

For Ethernet mode only,
When we want to register QP as promiscuous, it must be added to all the
existing steering entries and also to the default one.
The promiscuous QP might also be on of "real" QPs,
which means we need to monitor every entry to avoid duplicates and ensure
we close an entry when all it has is promiscuous QPs.
Same mechanism both for unicast and multicast.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mlx4/main.c |  63 +++++-
 drivers/net/mlx4/mcg.c  | 535 +++++++++++++++++++++++++++++++++++++++++++++++-
 drivers/net/mlx4/mlx4.h |  33 +++
 3 files changed, 620 insertions(+), 11 deletions(-)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index da0da281d830..c8e276138f81 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -1063,6 +1063,59 @@ static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
 	device_remove_file(&info->dev->pdev->dev, &info->port_attr);
 }
 
+static int mlx4_init_steering(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int num_entries = dev->caps.num_ports;
+	int i, j;
+
+	priv->steer = kzalloc(sizeof(struct mlx4_steer) * num_entries, GFP_KERNEL);
+	if (!priv->steer)
+		return -ENOMEM;
+
+	for (i = 0; i < num_entries; i++) {
+		for (j = 0; j < MLX4_NUM_STEERS; j++) {
+			INIT_LIST_HEAD(&priv->steer[i].promisc_qps[j]);
+			INIT_LIST_HEAD(&priv->steer[i].steer_entries[j]);
+		}
+		INIT_LIST_HEAD(&priv->steer[i].high_prios);
+	}
+	return 0;
+}
+
+static void mlx4_clear_steering(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_steer_index *entry, *tmp_entry;
+	struct mlx4_promisc_qp *pqp, *tmp_pqp;
+	int num_entries = dev->caps.num_ports;
+	int i, j;
+
+	for (i = 0; i < num_entries; i++) {
+		for (j = 0; j < MLX4_NUM_STEERS; j++) {
+			list_for_each_entry_safe(pqp, tmp_pqp,
+						 &priv->steer[i].promisc_qps[j],
+						 list) {
+				list_del(&pqp->list);
+				kfree(pqp);
+			}
+			list_for_each_entry_safe(entry, tmp_entry,
+						 &priv->steer[i].steer_entries[j],
+						 list) {
+				list_del(&entry->list);
+				list_for_each_entry_safe(pqp, tmp_pqp,
+							 &entry->duplicates,
+							 list) {
+					list_del(&pqp->list);
+					kfree(pqp);
+				}
+				kfree(entry);
+			}
+		}
+	}
+	kfree(priv->steer);
+}
+
 static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct mlx4_priv *priv;
@@ -1172,6 +1225,10 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	mlx4_enable_msi_x(dev);
 
+	err = mlx4_init_steering(dev);
+	if (err)
+		goto err_free_eq;
+
 	err = mlx4_setup_hca(dev);
 	if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X)) {
 		dev->flags &= ~MLX4_FLAG_MSI_X;
@@ -1180,7 +1237,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	}
 
 	if (err)
-		goto err_free_eq;
+		goto err_steer;
 
 	for (port = 1; port <= dev->caps.num_ports; port++) {
 		err = mlx4_init_port_info(dev, port);
@@ -1213,6 +1270,9 @@ err_port:
 	mlx4_cleanup_pd_table(dev);
 	mlx4_cleanup_uar_table(dev);
 
+err_steer:
+	mlx4_clear_steering(dev);
+
 err_free_eq:
 	mlx4_free_eq_table(dev);
 
@@ -1272,6 +1332,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 		iounmap(priv->kar);
 		mlx4_uar_free(dev, &priv->driver_uar);
 		mlx4_cleanup_uar_table(dev);
+		mlx4_clear_steering(dev);
 		mlx4_free_eq_table(dev);
 		mlx4_close_hca(dev);
 		mlx4_cmd_cleanup(dev);
diff --git a/drivers/net/mlx4/mcg.c b/drivers/net/mlx4/mcg.c
index b103ad23bd84..e71372aa9cc4 100644
--- a/drivers/net/mlx4/mcg.c
+++ b/drivers/net/mlx4/mcg.c
@@ -41,14 +41,6 @@
 #define MGM_QPN_MASK       0x00FFFFFF
 #define MGM_BLCK_LB_BIT    30
 
-struct mlx4_mgm {
-	__be32			next_gid_index;
-	__be32			members_count;
-	u32			reserved[2];
-	u8			gid[16];
-	__be32			qp[MLX4_QP_PER_MGM];
-};
-
 static const u8 zero_gid[16];	/* automatically initialized to 0 */
 
 static int mlx4_READ_ENTRY(struct mlx4_dev *dev, int index,
@@ -65,6 +57,16 @@ static int mlx4_WRITE_ENTRY(struct mlx4_dev *dev, int index,
 			MLX4_CMD_TIME_CLASS_A);
 }
 
+static int mlx4_WRITE_PROMISC(struct mlx4_dev *dev, u8 vep_num, u8 port, u8 steer,
+			      struct mlx4_cmd_mailbox *mailbox)
+{
+	u32 in_mod;
+
+	in_mod = (u32) vep_num << 24 | (u32) port << 16 | steer << 1;
+	return mlx4_cmd(dev, mailbox->dma, in_mod, 0x1,
+			MLX4_CMD_WRITE_MCG, MLX4_CMD_TIME_CLASS_A);
+}
+
 static int mlx4_GID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 			 u16 *hash, u8 op_mod)
 {
@@ -80,6 +82,457 @@ static int mlx4_GID_HASH(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
 	return err;
 }
 
+static struct mlx4_promisc_qp *get_promisc_qp(struct mlx4_dev *dev, u8 pf_num,
+					      enum mlx4_steer_type steer,
+					      u32 qpn)
+{
+	struct mlx4_steer *s_steer = &mlx4_priv(dev)->steer[pf_num];
+	struct mlx4_promisc_qp *pqp;
+
+	list_for_each_entry(pqp, &s_steer->promisc_qps[steer], list) {
+		if (pqp->qpn == qpn)
+			return pqp;
+	}
+	/* not found */
+	return NULL;
+}
+
+/*
+ * Add new entry to steering data structure.
+ * All promisc QPs should be added as well
+ */
+static int new_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+			      enum mlx4_steer_type steer,
+			      unsigned int index, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_mgm *mgm;
+	u32 members_count;
+	struct mlx4_steer_index *new_entry;
+	struct mlx4_promisc_qp *pqp;
+	struct mlx4_promisc_qp *dqp;
+	u32 prot;
+	int err;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	new_entry = kzalloc(sizeof *new_entry, GFP_KERNEL);
+	if (!new_entry)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&new_entry->duplicates);
+	new_entry->index = index;
+	list_add_tail(&new_entry->list, &s_steer->steer_entries[steer]);
+
+	/* If the given qpn is also a promisc qp,
+	 * it should be inserted to duplicates list
+	 */
+	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	if (pqp) {
+		dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
+		if (!dqp) {
+			err = -ENOMEM;
+			goto out_alloc;
+		}
+		dqp->qpn = qpn;
+		list_add_tail(&dqp->list, &new_entry->duplicates);
+	}
+
+	/* if no promisc qps for this vep, we are done */
+	if (list_empty(&s_steer->promisc_qps[steer]))
+		return 0;
+
+	/* now need to add all the promisc qps to the new
+	 * steering entry, as they should also receive the packets
+	 * destined to this address */
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = -ENOMEM;
+		goto out_alloc;
+	}
+	mgm = mailbox->buf;
+
+	err = mlx4_READ_ENTRY(dev, index, mailbox);
+	if (err)
+		goto out_mailbox;
+
+	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
+	prot = be32_to_cpu(mgm->members_count) >> 30;
+	list_for_each_entry(pqp, &s_steer->promisc_qps[steer], list) {
+		/* don't add already existing qpn */
+		if (pqp->qpn == qpn)
+			continue;
+		if (members_count == MLX4_QP_PER_MGM) {
+			/* out of space */
+			err = -ENOMEM;
+			goto out_mailbox;
+		}
+
+		/* add the qpn */
+		mgm->qp[members_count++] = cpu_to_be32(pqp->qpn & MGM_QPN_MASK);
+	}
+	/* update the qps count and update the entry with all the promisc qps*/
+	mgm->members_count = cpu_to_be32(members_count | (prot << 30));
+	err = mlx4_WRITE_ENTRY(dev, index, mailbox);
+
+out_mailbox:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	if (!err)
+		return 0;
+out_alloc:
+	if (dqp) {
+		list_del(&dqp->list);
+		kfree(&dqp);
+	}
+	list_del(&new_entry->list);
+	kfree(new_entry);
+	return err;
+}
+
+/* update the data structures with existing steering entry */
+static int existing_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+				   enum mlx4_steer_type steer,
+				   unsigned int index, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_steer_index *tmp_entry, *entry = NULL;
+	struct mlx4_promisc_qp *pqp;
+	struct mlx4_promisc_qp *dqp;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	if (!pqp)
+		return 0; /* nothing to do */
+
+	list_for_each_entry(tmp_entry, &s_steer->steer_entries[steer], list) {
+		if (tmp_entry->index == index) {
+			entry = tmp_entry;
+			break;
+		}
+	}
+	if (unlikely(!entry)) {
+		mlx4_warn(dev, "Steering entry at index %x is not registered\n", index);
+		return -EINVAL;
+	}
+
+	/* the given qpn is listed as a promisc qpn
+	 * we need to add it as a duplicate to this entry
+	 * for future refernce */
+	list_for_each_entry(dqp, &entry->duplicates, list) {
+		if (qpn == dqp->qpn)
+			return 0; /* qp is already duplicated */
+	}
+
+	/* add the qp as a duplicate on this index */
+	dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
+	if (!dqp)
+		return -ENOMEM;
+	dqp->qpn = qpn;
+	list_add_tail(&dqp->list, &entry->duplicates);
+
+	return 0;
+}
+
+/* Check whether a qpn is a duplicate on steering entry
+ * If so, it should not be removed from mgm */
+static bool check_duplicate_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+				  enum mlx4_steer_type steer,
+				  unsigned int index, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_steer_index *tmp_entry, *entry = NULL;
+	struct mlx4_promisc_qp *dqp, *tmp_dqp;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	/* if qp is not promisc, it cannot be duplicated */
+	if (!get_promisc_qp(dev, pf_num, steer, qpn))
+		return false;
+
+	/* The qp is promisc qp so it is a duplicate on this index
+	 * Find the index entry, and remove the duplicate */
+	list_for_each_entry(tmp_entry, &s_steer->steer_entries[steer], list) {
+		if (tmp_entry->index == index) {
+			entry = tmp_entry;
+			break;
+		}
+	}
+	if (unlikely(!entry)) {
+		mlx4_warn(dev, "Steering entry for index %x is not registered\n", index);
+		return false;
+	}
+	list_for_each_entry_safe(dqp, tmp_dqp, &entry->duplicates, list) {
+		if (dqp->qpn == qpn) {
+			list_del(&dqp->list);
+			kfree(dqp);
+		}
+	}
+	return true;
+}
+
+/* I a steering entry contains only promisc QPs, it can be removed. */
+static bool can_remove_steering_entry(struct mlx4_dev *dev, u8 vep_num, u8 port,
+				      enum mlx4_steer_type steer,
+				      unsigned int index, u32 tqpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_mgm *mgm;
+	struct mlx4_steer_index *entry = NULL, *tmp_entry;
+	u32 qpn;
+	u32 members_count;
+	bool ret = false;
+	int i;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return false;
+	mgm = mailbox->buf;
+
+	if (mlx4_READ_ENTRY(dev, index, mailbox))
+		goto out;
+	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
+	for (i = 0;  i < members_count; i++) {
+		qpn = be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK;
+		if (!get_promisc_qp(dev, pf_num, steer, qpn) && qpn != tqpn) {
+			/* the qp is not promisc, the entry can't be removed */
+			goto out;
+		}
+	}
+	 /* All the qps currently registered for this entry are promiscuous,
+	  * Checking for duplicates */
+	ret = true;
+	list_for_each_entry_safe(entry, tmp_entry, &s_steer->steer_entries[steer], list) {
+		if (entry->index == index) {
+			if (list_empty(&entry->duplicates)) {
+				list_del(&entry->list);
+				kfree(entry);
+			} else {
+				/* This entry contains duplicates so it shouldn't be removed */
+				ret = false;
+				goto out;
+			}
+		}
+	}
+
+out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return ret;
+}
+
+static int add_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+			  enum mlx4_steer_type steer, u32 qpn)
+{
+	struct mlx4_steer *s_steer;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_mgm *mgm;
+	struct mlx4_steer_index *entry;
+	struct mlx4_promisc_qp *pqp;
+	struct mlx4_promisc_qp *dqp;
+	u32 members_count;
+	u32 prot;
+	int i;
+	bool found;
+	int last_index;
+	int err;
+	u8 pf_num;
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+
+	mutex_lock(&priv->mcg_table.mutex);
+
+	if (get_promisc_qp(dev, pf_num, steer, qpn)) {
+		err = 0;  /* Noting to do, already exists */
+		goto out_mutex;
+	}
+
+	pqp = kmalloc(sizeof *pqp, GFP_KERNEL);
+	if (!pqp) {
+		err = -ENOMEM;
+		goto out_mutex;
+	}
+	pqp->qpn = qpn;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = -ENOMEM;
+		goto out_alloc;
+	}
+	mgm = mailbox->buf;
+
+	/* the promisc qp needs to be added for each one of the steering
+	 * entries, if it already exists, needs to be added as a duplicate
+	 * for this entry */
+	list_for_each_entry(entry, &s_steer->steer_entries[steer], list) {
+		err = mlx4_READ_ENTRY(dev, entry->index, mailbox);
+		if (err)
+			goto out_mailbox;
+
+		members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
+		prot = be32_to_cpu(mgm->members_count) >> 30;
+		found = false;
+		for (i = 0; i < members_count; i++) {
+			if ((be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK) == qpn) {
+				/* Entry already exists, add to duplicates */
+				dqp = kmalloc(sizeof *dqp, GFP_KERNEL);
+				if (!dqp)
+					goto out_mailbox;
+				dqp->qpn = qpn;
+				list_add_tail(&dqp->list, &entry->duplicates);
+				found = true;
+			}
+		}
+		if (!found) {
+			/* Need to add the qpn to mgm */
+			if (members_count == MLX4_QP_PER_MGM) {
+				/* entry is full */
+				err = -ENOMEM;
+				goto out_mailbox;
+			}
+			mgm->qp[members_count++] = cpu_to_be32(qpn & MGM_QPN_MASK);
+			mgm->members_count = cpu_to_be32(members_count | (prot << 30));
+			err = mlx4_WRITE_ENTRY(dev, entry->index, mailbox);
+			if (err)
+				goto out_mailbox;
+		}
+		last_index = entry->index;
+	}
+
+	/* add the new qpn to list of promisc qps */
+	list_add_tail(&pqp->list, &s_steer->promisc_qps[steer]);
+	/* now need to add all the promisc qps to default entry */
+	memset(mgm, 0, sizeof *mgm);
+	members_count = 0;
+	list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list)
+		mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
+	mgm->members_count = cpu_to_be32(members_count | MLX4_PROT_ETH << 30);
+
+	err = mlx4_WRITE_PROMISC(dev, vep_num, port, steer, mailbox);
+	if (err)
+		goto out_list;
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	mutex_unlock(&priv->mcg_table.mutex);
+	return 0;
+
+out_list:
+	list_del(&pqp->list);
+out_mailbox:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+out_alloc:
+	kfree(pqp);
+out_mutex:
+	mutex_unlock(&priv->mcg_table.mutex);
+	return err;
+}
+
+static int remove_promisc_qp(struct mlx4_dev *dev, u8 vep_num, u8 port,
+			     enum mlx4_steer_type steer, u32 qpn)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_steer *s_steer;
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_mgm *mgm;
+	struct mlx4_steer_index *entry;
+	struct mlx4_promisc_qp *pqp;
+	struct mlx4_promisc_qp *dqp;
+	u32 members_count;
+	bool found;
+	bool back_to_list = false;
+	int loc, i;
+	int err;
+	u8 pf_num;
+
+	pf_num = (dev->caps.num_ports == 1) ? vep_num : (vep_num << 1) | (port - 1);
+	s_steer = &mlx4_priv(dev)->steer[pf_num];
+	mutex_lock(&priv->mcg_table.mutex);
+
+	pqp = get_promisc_qp(dev, pf_num, steer, qpn);
+	if (unlikely(!pqp)) {
+		mlx4_warn(dev, "QP %x is not promiscuous QP\n", qpn);
+		/* nothing to do */
+		err = 0;
+		goto out_mutex;
+	}
+
+	/*remove from list of promisc qps */
+	list_del(&pqp->list);
+	kfree(pqp);
+
+	/* set the default entry not to include the removed one */
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		err = -ENOMEM;
+		back_to_list = true;
+		goto out_list;
+	}
+	mgm = mailbox->buf;
+	members_count = 0;
+	list_for_each_entry(dqp, &s_steer->promisc_qps[steer], list)
+		mgm->qp[members_count++] = cpu_to_be32(dqp->qpn & MGM_QPN_MASK);
+	mgm->members_count = cpu_to_be32(members_count | MLX4_PROT_ETH << 30);
+
+	err = mlx4_WRITE_PROMISC(dev, vep_num, port, steer, mailbox);
+	if (err)
+		goto out_mailbox;
+
+	/* remove the qp from all the steering entries*/
+	list_for_each_entry(entry, &s_steer->steer_entries[steer], list) {
+		found = false;
+		list_for_each_entry(dqp, &entry->duplicates, list) {
+			if (dqp->qpn == qpn) {
+				found = true;
+				break;
+			}
+		}
+		if (found) {
+			/* a duplicate, no need to change the mgm,
+			 * only update the duplicates list */
+			list_del(&dqp->list);
+			kfree(dqp);
+		} else {
+			err = mlx4_READ_ENTRY(dev, entry->index, mailbox);
+				if (err)
+					goto out_mailbox;
+			members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
+			for (loc = -1, i = 0; i < members_count; ++i)
+				if ((be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK) == qpn)
+					loc = i;
+
+			mgm->members_count = cpu_to_be32(--members_count |
+							 (MLX4_PROT_ETH << 30));
+			mgm->qp[loc] = mgm->qp[i - 1];
+			mgm->qp[i - 1] = 0;
+
+			err = mlx4_WRITE_ENTRY(dev, entry->index, mailbox);
+				if (err)
+					goto out_mailbox;
+		}
+
+	}
+
+out_mailbox:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+out_list:
+	if (back_to_list)
+		list_add_tail(&pqp->list, &s_steer->promisc_qps[steer]);
+out_mutex:
+	mutex_unlock(&priv->mcg_table.mutex);
+	return err;
+}
+
 /*
  * Caller must hold MCG table semaphore.  gid and mgm parameters must
  * be properly aligned for command interface.
@@ -164,6 +617,7 @@ int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	int i;
 	int err;
 	u8 port = gid[5];
+	u8 new_entry = 0;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -177,8 +631,10 @@ int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 		goto out;
 
 	if (index != -1) {
-		if (!(be32_to_cpu(mgm->members_count) & 0xffffff))
+		if (!(be32_to_cpu(mgm->members_count) & 0xffffff)) {
+			new_entry = 1;
 			memcpy(mgm->gid, gid, 16);
+		}
 	} else {
 		link = 1;
 
@@ -234,6 +690,14 @@ int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 		goto out;
 
 out:
+	if (prot == MLX4_PROT_ETH) {
+		/* manage the steering entry for promisc mode */
+		if (new_entry)
+			new_steering_entry(dev, 0, port, steer, index, qp->qpn);
+		else
+			existing_steering_entry(dev, 0, port, steer,
+						index, qp->qpn);
+	}
 	if (err && link && index != -1) {
 		if (index < dev->caps.num_mgms)
 			mlx4_warn(dev, "Got AMGM index %d < %d",
@@ -260,6 +724,7 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	int i, loc;
 	int err;
 	u8 port = gid[5];
+	bool removed_entry = false;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
 	if (IS_ERR(mailbox))
@@ -279,6 +744,11 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 		goto out;
 	}
 
+	/* if this pq is also a promisc qp, it shouldn't be removed */
+	if (prot == MLX4_PROT_ETH &&
+	    check_duplicate_entry(dev, 0, port, steer, index, qp->qpn))
+		goto out;
+
 	members_count = be32_to_cpu(mgm->members_count) & 0xffffff;
 	for (loc = -1, i = 0; i < members_count; ++i)
 		if ((be32_to_cpu(mgm->qp[i]) & MGM_QPN_MASK) == qp->qpn)
@@ -295,11 +765,16 @@ int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	mgm->qp[loc]       = mgm->qp[i - 1];
 	mgm->qp[i - 1]     = 0;
 
-	if (i != 1) {
+	if (prot == MLX4_PROT_ETH)
+		removed_entry = can_remove_steering_entry(dev, 0, port, steer, index, qp->qpn);
+	if (i != 1 && (prot != MLX4_PROT_ETH || !removed_entry)) {
 		err = mlx4_WRITE_ENTRY(dev, index, mailbox);
 		goto out;
 	}
 
+	/* We are going to delete the entry, members count should be 0 */
+	mgm->members_count = cpu_to_be32((u32) prot << 30);
+
 	if (prev == -1) {
 		/* Remove entry from MGM */
 		int amgm_index = be32_to_cpu(mgm->next_gid_index) >> 6;
@@ -388,6 +863,46 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 }
 EXPORT_SYMBOL_GPL(mlx4_multicast_detach);
 
+
+int mlx4_multicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+
+	return add_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_add);
+
+int mlx4_multicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+
+	return remove_promisc_qp(dev, 0, port, MLX4_MC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_multicast_promisc_remove);
+
+int mlx4_unicast_promisc_add(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+
+	return add_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_add);
+
+int mlx4_unicast_promisc_remove(struct mlx4_dev *dev, u32 qpn, u8 port)
+{
+	if (!dev->caps.vep_mc_steering)
+		return 0;
+
+	return remove_promisc_qp(dev, 0, port, MLX4_UC_STEER, qpn);
+}
+EXPORT_SYMBOL_GPL(mlx4_unicast_promisc_remove);
+
 int mlx4_init_mcg_table(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 67ee8dacae79..1513a91b4bd4 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -162,6 +162,27 @@ struct mlx4_fw {
 	u8			catas_bar;
 };
 
+#define MGM_QPN_MASK       0x00FFFFFF
+#define MGM_BLCK_LB_BIT    30
+
+struct mlx4_promisc_qp {
+	struct list_head list;
+	u32 qpn;
+};
+
+struct mlx4_steer_index {
+	struct list_head list;
+	unsigned int index;
+	struct list_head duplicates;
+};
+
+struct mlx4_mgm {
+	__be32			next_gid_index;
+	__be32			members_count;
+	u32			reserved[2];
+	u8			gid[16];
+	__be32			qp[MLX4_QP_PER_MGM];
+};
 struct mlx4_cmd {
 	struct pci_pool	       *pool;
 	void __iomem	       *hcr;
@@ -287,6 +308,12 @@ struct mlx4_msix_ctl {
 	spinlock_t	pool_lock;
 };
 
+struct mlx4_steer {
+	struct list_head promisc_qps[MLX4_NUM_STEERS];
+	struct list_head steer_entries[MLX4_NUM_STEERS];
+	struct list_head high_prios;
+};
+
 struct mlx4_priv {
 	struct mlx4_dev		dev;
 
@@ -319,6 +346,7 @@ struct mlx4_priv {
 	struct mlx4_sense       sense;
 	struct mutex		port_mutex;
 	struct mlx4_msix_ctl	msix_ctl;
+	struct mlx4_steer	*steer;
 };
 
 static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
@@ -409,4 +437,9 @@ void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
 int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port);
 int mlx4_get_port_ib_caps(struct mlx4_dev *dev, u8 port, __be32 *caps);
 
+int mlx4_qp_detach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  enum mlx4_protocol prot, enum mlx4_steer_type steer);
+int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
+			  int block_mcast_loopback, enum mlx4_protocol prot,
+			  enum mlx4_steer_type steer);
 #endif /* MLX4_H */
-- 
cgit v1.2.3


From c1b43dca137f2154845122417fba86d4bae67182 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.co.il>
Date: Tue, 22 Mar 2011 22:38:41 +0000
Subject: mlx4: Add blue flame support for kernel consumers

Using blue flame can improve latency by allowing the HW to more efficiently
access the WQE. This patch presents two functions that are used to allocate or
release HW resources for using blue flame; the caller need to supply a struct
mlx4_bf object when allocating resources. Consumers that make use of this API
should post doorbells to the UAR object pointed by the initialized struct
mlx4_bf;

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mlx4/main.c     | 31 +++++++++++++++
 drivers/net/mlx4/mlx4.h     |  3 ++
 drivers/net/mlx4/pd.c       | 94 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mlx4/device.h | 13 +++++++
 include/linux/mlx4/qp.h     |  1 +
 5 files changed, 142 insertions(+)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index c8e276138f81..05c5671749aa 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -39,6 +39,7 @@
 #include <linux/pci.h>
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
+#include <linux/io-mapping.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -721,8 +722,31 @@ static void mlx4_free_icms(struct mlx4_dev *dev)
 	mlx4_free_icm(dev, priv->fw.aux_icm, 0);
 }
 
+static int map_bf_area(struct mlx4_dev *dev)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	resource_size_t bf_start;
+	resource_size_t bf_len;
+	int err = 0;
+
+	bf_start = pci_resource_start(dev->pdev, 2) + (dev->caps.num_uars << PAGE_SHIFT);
+	bf_len = pci_resource_len(dev->pdev, 2) - (dev->caps.num_uars << PAGE_SHIFT);
+	priv->bf_mapping = io_mapping_create_wc(bf_start, bf_len);
+	if (!priv->bf_mapping)
+		err = -ENOMEM;
+
+	return err;
+}
+
+static void unmap_bf_area(struct mlx4_dev *dev)
+{
+	if (mlx4_priv(dev)->bf_mapping)
+		io_mapping_free(mlx4_priv(dev)->bf_mapping);
+}
+
 static void mlx4_close_hca(struct mlx4_dev *dev)
 {
+	unmap_bf_area(dev);
 	mlx4_CLOSE_HCA(dev, 0);
 	mlx4_free_icms(dev);
 	mlx4_UNMAP_FA(dev);
@@ -775,6 +799,9 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 		goto err_stop_fw;
 	}
 
+	if (map_bf_area(dev))
+		mlx4_dbg(dev, "Failed to map blue flame area\n");
+
 	init_hca.log_uar_sz = ilog2(dev->caps.num_uars);
 
 	err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size);
@@ -805,6 +832,7 @@ err_free_icm:
 	mlx4_free_icms(dev);
 
 err_stop_fw:
+	unmap_bf_area(dev);
 	mlx4_UNMAP_FA(dev);
 	mlx4_free_icm(dev, priv->fw.fw_icm, 0);
 
@@ -1196,6 +1224,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	pci_read_config_byte(pdev, PCI_REVISION_ID, &dev->rev_id);
 
+	INIT_LIST_HEAD(&priv->bf_list);
+	mutex_init(&priv->bf_mutex);
+
 	/*
 	 * Now reset the HCA before we touch the PCI capabilities or
 	 * attempt a firmware command, since a boot ROM may have left
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index d8bb4418581b..bc9a21657a4f 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -353,6 +353,9 @@ struct mlx4_priv {
 	struct mutex		port_mutex;
 	struct mlx4_msix_ctl	msix_ctl;
 	struct mlx4_steer	*steer;
+	struct list_head	bf_list;
+	struct mutex		bf_mutex;
+	struct io_mapping	*bf_mapping;
 };
 
 static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
diff --git a/drivers/net/mlx4/pd.c b/drivers/net/mlx4/pd.c
index c4988d6bd5b2..5210a0f31413 100644
--- a/drivers/net/mlx4/pd.c
+++ b/drivers/net/mlx4/pd.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/io-mapping.h>
 
 #include <asm/page.h>
 
@@ -77,6 +78,7 @@ int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar)
 		return -ENOMEM;
 
 	uar->pfn = (pci_resource_start(dev->pdev, 2) >> PAGE_SHIFT) + uar->index;
+	uar->map = NULL;
 
 	return 0;
 }
@@ -88,6 +90,98 @@ void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar)
 }
 EXPORT_SYMBOL_GPL(mlx4_uar_free);
 
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_uar *uar;
+	int err = 0;
+	int idx;
+
+	if (!priv->bf_mapping)
+		return -ENOMEM;
+
+	mutex_lock(&priv->bf_mutex);
+	if (!list_empty(&priv->bf_list))
+		uar = list_entry(priv->bf_list.next, struct mlx4_uar, bf_list);
+	else {
+		uar = kmalloc(sizeof *uar, GFP_KERNEL);
+		if (!uar) {
+			err = -ENOMEM;
+			goto out;
+		}
+		err = mlx4_uar_alloc(dev, uar);
+		if (err)
+			goto free_kmalloc;
+
+		uar->map = ioremap(uar->pfn << PAGE_SHIFT, PAGE_SIZE);
+		if (!uar->map) {
+			err = -ENOMEM;
+			goto free_uar;
+		}
+
+		uar->bf_map = io_mapping_map_wc(priv->bf_mapping, uar->index << PAGE_SHIFT);
+		if (!uar->bf_map) {
+			err = -ENOMEM;
+			goto unamp_uar;
+		}
+		uar->free_bf_bmap = 0;
+		list_add(&uar->bf_list, &priv->bf_list);
+	}
+
+	bf->uar = uar;
+	idx = ffz(uar->free_bf_bmap);
+	uar->free_bf_bmap |= 1 << idx;
+	bf->uar = uar;
+	bf->offset = 0;
+	bf->buf_size = dev->caps.bf_reg_size / 2;
+	bf->reg = uar->bf_map + idx * dev->caps.bf_reg_size;
+	if (uar->free_bf_bmap == (1 << dev->caps.bf_regs_per_page) - 1)
+		list_del_init(&uar->bf_list);
+
+	goto out;
+
+unamp_uar:
+	bf->uar = NULL;
+	iounmap(uar->map);
+
+free_uar:
+	mlx4_uar_free(dev, uar);
+
+free_kmalloc:
+	kfree(uar);
+
+out:
+	mutex_unlock(&priv->bf_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_bf_alloc);
+
+void mlx4_bf_free(struct mlx4_dev *dev, struct mlx4_bf *bf)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	int idx;
+
+	if (!bf->uar || !bf->uar->bf_map)
+		return;
+
+	mutex_lock(&priv->bf_mutex);
+	idx = (bf->reg - bf->uar->bf_map) / dev->caps.bf_reg_size;
+	bf->uar->free_bf_bmap &= ~(1 << idx);
+	if (!bf->uar->free_bf_bmap) {
+		if (!list_empty(&bf->uar->bf_list))
+			list_del(&bf->uar->bf_list);
+
+		io_mapping_unmap(bf->uar->bf_map);
+		iounmap(bf->uar->map);
+		mlx4_uar_free(dev, bf->uar);
+		kfree(bf->uar);
+	} else if (list_empty(&bf->uar->bf_list))
+		list_add(&bf->uar->bf_list, &priv->bf_list);
+
+	mutex_unlock(&priv->bf_mutex);
+}
+EXPORT_SYMBOL_GPL(mlx4_bf_free);
+
 int mlx4_init_uar_table(struct mlx4_dev *dev)
 {
 	if (dev->caps.num_uars <= 128) {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 56fa5e1cd6d4..8985768e2c0d 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -351,6 +351,17 @@ struct mlx4_fmr {
 struct mlx4_uar {
 	unsigned long		pfn;
 	int			index;
+	struct list_head	bf_list;
+	unsigned		free_bf_bmap;
+	void __iomem	       *map;
+	void __iomem	       *bf_map;
+};
+
+struct mlx4_bf {
+	unsigned long		offset;
+	int			buf_size;
+	struct mlx4_uar	       *uar;
+	void __iomem	       *reg;
 };
 
 struct mlx4_cq {
@@ -478,6 +489,8 @@ void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn);
 
 int mlx4_uar_alloc(struct mlx4_dev *dev, struct mlx4_uar *uar);
 void mlx4_uar_free(struct mlx4_dev *dev, struct mlx4_uar *uar);
+int mlx4_bf_alloc(struct mlx4_dev *dev, struct mlx4_bf *bf);
+void mlx4_bf_free(struct mlx4_dev *dev, struct mlx4_bf *bf);
 
 int mlx4_mtt_init(struct mlx4_dev *dev, int npages, int page_shift,
 		  struct mlx4_mtt *mtt);
diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h
index 0eeb2a1a867c..9e9eb21056ca 100644
--- a/include/linux/mlx4/qp.h
+++ b/include/linux/mlx4/qp.h
@@ -303,6 +303,7 @@ struct mlx4_wqe_data_seg {
 
 enum {
 	MLX4_INLINE_ALIGN	= 64,
+	MLX4_INLINE_SEG		= 1 << 31,
 };
 
 struct mlx4_wqe_inline_seg {
-- 
cgit v1.2.3


From ab6dc30da55d262c54ae12e47e4a2e4372e39fbf Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Wed, 6 Apr 2011 23:24:42 +0000
Subject: mlx4: Sensing link type at device initialization

When bringing the port up, performing a SENSE_PORT command
To try and check to which physical link type (IB or Ethernet) the physical
port is connected.
In case there is no valid link partner, the port will come up as its
supported default.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/mlx4/main.c  | 5 +++++
 drivers/net/mlx4/mlx4.h  | 2 ++
 drivers/net/mlx4/sense.c | 4 ++--
 3 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'drivers/net/mlx4/main.c')

diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 62fa7eec5f0c..3814fc9b1145 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -944,6 +944,10 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 	}
 
 	for (port = 1; port <= dev->caps.num_ports; port++) {
+		enum mlx4_port_type port_type = 0;
+		mlx4_SENSE_PORT(dev, port, &port_type);
+		if (port_type)
+			dev->caps.port_type[port] = port_type;
 		ib_port_default_caps = 0;
 		err = mlx4_get_port_ib_caps(dev, port, &ib_port_default_caps);
 		if (err)
@@ -958,6 +962,7 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 			goto err_mcg_table_free;
 		}
 	}
+	mlx4_set_port_mask(dev);
 
 	return 0;
 
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index c1e0e5f1bcdb..dd7d745fbab4 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -431,6 +431,8 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
 
 void mlx4_handle_catas_err(struct mlx4_dev *dev);
 
+int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
+		    enum mlx4_port_type *type);
 void mlx4_do_sense_ports(struct mlx4_dev *dev,
 			 enum mlx4_port_type *stype,
 			 enum mlx4_port_type *defaults);
diff --git a/drivers/net/mlx4/sense.c b/drivers/net/mlx4/sense.c
index 015fbe785c13..e2337a7411d9 100644
--- a/drivers/net/mlx4/sense.c
+++ b/drivers/net/mlx4/sense.c
@@ -38,8 +38,8 @@
 
 #include "mlx4.h"
 
-static int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
-			   enum mlx4_port_type *type)
+int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
+		    enum mlx4_port_type *type)
 {
 	u64 out_param;
 	int err = 0;
-- 
cgit v1.2.3