Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IB/ehca: Reject dynamic memory add/remove when ehca adapter is present
  IB/ehca: Fix reported max number of QPs and CQs in systems with >1 adapter
  IPoIB: Set netdev offload features properly for child (VLAN) interfaces
  IPoIB: Clean up ethtool support
  mlx4_core: Add Ethernet PCI device IDs
  mlx4_en: Add driver for Mellanox ConnectX 10GbE NIC
  mlx4_core: Multiple port type support
  mlx4_core: Ethernet MAC/VLAN management
  mlx4_core: Get ethernet MTU and default address from firmware
  mlx4_core: Support multiple pre-reserved QP regions
  Update NetEffect maintainer emails to Intel emails
  RDMA/cxgb3: Remove cmid reference on tid allocation failures
  IB/mad: Use krealloc() to resize snoop table
  IPoIB: Always initialize poll_timer to avoid crash on unload
  IB/ehca: Don't allow creating UC QP with SRQ
  mlx4_core: Add QP range reservation support
  RDMA/ucma: Test ucma_alloc_multicast() return against NULL, not with IS_ERR()

24 files changed, 6148 insertions, 50 deletions

diff --git a/drivers/net/mlx4/Makefile b/drivers/net/mlx4/Makefile
index 0952a6528f5..a7a97bf998f 100644
--- a/drivers/net/mlx4/Makefile
+++ b/drivers/net/mlx4/Makefile
@@ -1,4 +1,9 @@
 obj-$(CONFIG_MLX4_CORE)		+= mlx4_core.o
 
 mlx4_core-y :=	alloc.o catas.o cmd.o cq.o eq.o fw.o icm.o intf.o main.o mcg.o \
-		mr.o pd.o profile.o qp.o reset.o srq.o
+		mr.o pd.o port.o profile.o qp.o reset.o srq.o
+
+obj-$(CONFIG_MLX4_EN)               += mlx4_en.o
+
+mlx4_en-y := 	en_main.o en_tx.o en_rx.o en_params.o en_port.o en_cq.o \
+		en_resources.o en_netdev.o
diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index b411b79d72a..ad95d5f7b63 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -48,13 +48,16 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap)
 
 	obj = find_next_zero_bit(bitmap->table, bitmap->max, bitmap->last);
 	if (obj >= bitmap->max) {
-		bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
+		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+				& bitmap->mask;
 		obj = find_first_zero_bit(bitmap->table, bitmap->max);
 	}
 
 	if (obj < bitmap->max) {
 		set_bit(obj, bitmap->table);
-		bitmap->last = (obj + 1) & (bitmap->max - 1);
+		bitmap->last = (obj + 1);
+		if (bitmap->last == bitmap->max)
+			bitmap->last = 0;
 		obj |= bitmap->top;
 	} else
 		obj = -1;
@@ -66,16 +69,90 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap)
 
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj)
 {
-	obj &= bitmap->max - 1;
+	mlx4_bitmap_free_range(bitmap, obj, 1);
+}
+
+static unsigned long find_aligned_range(unsigned long *bitmap,
+					u32 start, u32 nbits,
+					int len, int align)
+{
+	unsigned long end, i;
+
+again:
+	start = ALIGN(start, align);
+
+	while ((start < nbits) && test_bit(start, bitmap))
+		start += align;
+
+	if (start >= nbits)
+		return -1;
+
+	end = start+len;
+	if (end > nbits)
+		return -1;
+
+	for (i = start + 1; i < end; i++) {
+		if (test_bit(i, bitmap)) {
+			start = i + 1;
+			goto again;
+		}
+	}
+
+	return start;
+}
+
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
+{
+	u32 obj, i;
+
+	if (likely(cnt == 1 && align == 1))
+		return mlx4_bitmap_alloc(bitmap);
+
+	spin_lock(&bitmap->lock);
+
+	obj = find_aligned_range(bitmap->table, bitmap->last,
+				 bitmap->max, cnt, align);
+	if (obj >= bitmap->max) {
+		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+				& bitmap->mask;
+		obj = find_aligned_range(bitmap->table, 0, bitmap->max,
+					 cnt, align);
+	}
+
+	if (obj < bitmap->max) {
+		for (i = 0; i < cnt; i++)
+			set_bit(obj + i, bitmap->table);
+		if (obj == bitmap->last) {
+			bitmap->last = (obj + cnt);
+			if (bitmap->last >= bitmap->max)
+				bitmap->last = 0;
+		}
+		obj |= bitmap->top;
+	} else
+		obj = -1;
+
+	spin_unlock(&bitmap->lock);
+
+	return obj;
+}
+
+void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt)
+{
+	u32 i;
+
+	obj &= bitmap->max + bitmap->reserved_top - 1;
 
 	spin_lock(&bitmap->lock);
-	clear_bit(obj, bitmap->table);
+	for (i = 0; i < cnt; i++)
+		clear_bit(obj + i, bitmap->table);
 	bitmap->last = min(bitmap->last, obj);
-	bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
+	bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+			& bitmap->mask;
 	spin_unlock(&bitmap->lock);
 }
 
-int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved)
+int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
+		     u32 reserved_bot, u32 reserved_top)
 {
 	int i;
 
@@ -85,14 +162,16 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved
 
 	bitmap->last = 0;
 	bitmap->top  = 0;
-	bitmap->max  = num;
+	bitmap->max  = num - reserved_top;
 	bitmap->mask = mask;
+	bitmap->reserved_top = reserved_top;
 	spin_lock_init(&bitmap->lock);
-	bitmap->table = kzalloc(BITS_TO_LONGS(num) * sizeof (long), GFP_KERNEL);
+	bitmap->table = kzalloc(BITS_TO_LONGS(bitmap->max) *
+				sizeof (long), GFP_KERNEL);
 	if (!bitmap->table)
 		return -ENOMEM;
 
-	for (i = 0; i < reserved; ++i)
+	for (i = 0; i < reserved_bot; ++i)
 		set_bit(i, bitmap->table);
 
 	return 0;
diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index 9bb50e3f897..b7ad2829d67 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -300,7 +300,7 @@ int mlx4_init_cq_table(struct mlx4_dev *dev)
 	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
 
 	err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
-			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs);
+			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/en_cq.c b/drivers/net/mlx4/en_cq.c
new file mode 100644
index 00000000000..1368a8010af
--- /dev/null
+++ b/drivers/net/mlx4/en_cq.c
@@ -0,0 +1,146 @@
+/*
+ * Copyright (c) 2007 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/mlx4/cq.h>
+#include <linux/mlx4/qp.h>
+#include <linux/mlx4/cmd.h>
+
+#include "mlx4_en.h"
+
+static void mlx4_en_cq_event(struct mlx4_cq *cq, enum mlx4_event event)
+{
+	return;
+}
+
+
+int mlx4_en_create_cq(struct mlx4_en_priv *priv,
+		      struct mlx4_en_cq *cq,
+		      int entries, int ring, enum cq_type mode)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err;
+
+	cq->size = entries;
+	if (mode == RX)
+		cq->buf_size = cq->size * sizeof(struct mlx4_cqe);
+	else
+		cq->buf_size = sizeof(struct mlx4_cqe);
+
+	cq->ring = ring;
+	cq->is_tx = mode;
+	spin_lock_init(&cq->lock);
+
+	err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
+				cq->buf_size, 2 * PAGE_SIZE);
+	if (err)
+		return err;
+
+	err = mlx4_en_map_buffer(&cq->wqres.buf);
+	if (err)
+		mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
+
+	return err;
+}
+
+int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err;
+
+	cq->dev = mdev->pndev[priv->port];
+	cq->mcq.set_ci_db  = cq->wqres.db.db;
+	cq->mcq.arm_db     = cq->wqres.db.db + 1;
+	*cq->mcq.set_ci_db = 0;
+	*cq->mcq.arm_db    = 0;
+	cq->buf = (struct mlx4_cqe *) cq->wqres.buf.direct.buf;
+	memset(cq->buf, 0, cq->buf_size);
+
+	err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt, &mdev->priv_uar,
+			    cq->wqres.db.dma, &cq->mcq, cq->is_tx);
+	if (err)
+		return err;
+
+	cq->mcq.comp  = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq;
+	cq->mcq.event = mlx4_en_cq_event;
+
+	if (cq->is_tx) {
+		init_timer(&cq->timer);
+		cq->timer.function = mlx4_en_poll_tx_cq;
+		cq->timer.data = (unsigned long) cq;
+	} else {
+		netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64);
+		napi_enable(&cq->napi);
+	}
+
+	return 0;
+}
+
+void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+
+	mlx4_en_unmap_buffer(&cq->wqres.buf);
+	mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
+	cq->buf_size = 0;
+	cq->buf = NULL;
+}
+
+void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+{
+	struct mlx4_en_dev *mdev = priv->mdev;
+
+	if (cq->is_tx)
+		del_timer(&cq->timer);
+	else
+		napi_disable(&cq->napi);
+
+	mlx4_cq_free(mdev->dev, &cq->mcq);
+}
+
+/* Set rx cq moderation parameters */
+int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+{
+	return mlx4_cq_modify(priv->mdev->dev, &cq->mcq,
+			      cq->moder_cnt, cq->moder_time);
+}
+
+int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
+{
+	cq->armed = 1;
+	mlx4_cq_arm(&cq->mcq, MLX4_CQ_DB_REQ_NOT, priv->mdev->uar_map,
+		    &priv->mdev->uar_lock);
+
+	return 0;
+}
+
+
diff --git a/drivers/net/mlx4/en_main.c b/drivers/net/mlx4/en_main.c
new file mode 100644
index 00000000000..1b0eebf84f7
--- /dev/null
+++ b/drivers/net/mlx4/en_main.c
@@ -0,0 +1,254 @@
+/*
+ * Copyright (c) 2007 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/cpumask.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/netdevice.h>
+#include <linux/cpumask.h>
+
+#include <linux/mlx4/driver.h>
+#include <linux/mlx4/device.h>
+#include <linux/mlx4/cmd.h>
+
+#include "mlx4_en.h"
+
+MODULE_AUTHOR("Liran Liss, Yevgeny Petrilin");
+MODULE_DESCRIPTION("Mellanox ConnectX HCA Ethernet driver");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(DRV_VERSION " ("DRV_RELDATE")");
+
+static const char mlx4_en_version[] =
+	DRV_NAME ": Mellanox ConnectX HCA Ethernet driver v"
+	DRV_VERSION " (" DRV_RELDATE ")\n";
+
+static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
+			  enum mlx4_dev_event event, int port)
+{
+	struct mlx4_en_dev *mdev = (struct mlx4_en_dev *) endev_ptr;
+	struct mlx4_en_priv *priv;
+
+	if (!mdev->pndev[port])
+		return;
+
+	priv = netdev_priv(mdev->pndev[port]);
+	switch (event) {
+	case MLX4_DEV_EVENT_PORT_UP:
+	case MLX4_DEV_EVENT_PORT_DOWN:
+		/* To prevent races, we poll the link state in a separate
+		  task rather than changing it here */
+		priv->link_state = event;
+		queue_work(mdev->workqueue, &priv->linkstate_task);
+		break;
+
+	case MLX4_DEV_EVENT_CATASTROPHIC_ERROR:
+		mlx4_err(mdev, "Internal error detected, restarting device\n");
+		break;
+
+	default:
+		mlx4_warn(mdev, "Unhandled event: %d\n", event);
+	}
+}
+
+static void mlx4_en_remove(struct mlx4_dev *dev, void *endev_ptr)
+{
+	struct mlx4_en_dev *mdev = endev_ptr;
+	int i;
+
+	mutex_lock(&mdev->state_lock);
+	mdev->device_up = false;
+	mutex_unlock(&mdev->state_lock);
+
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
+		if (mdev->pndev[i])
+			mlx4_en_destroy_netdev(mdev->pndev[i]);
+
+	flush_workqueue(mdev->workqueue);
+	destroy_workqueue(mdev->workqueue);
+	mlx4_mr_free(dev, &mdev->mr);
+	mlx4_uar_free(dev, &mdev->priv_uar);
+	mlx4_pd_free(dev, mdev->priv_pdn);
+	kfree(mdev);
+}
+
+static void *mlx4_en_add(struct mlx4_dev *dev)
+{
+	static int mlx4_en_version_printed;
+	struct mlx4_en_dev *mdev;
+	int i;
+	int err;
+
+	if (!mlx4_en_version_printed) {
+		printk(KERN_INFO "%s", mlx4_en_version);
+		mlx4_en_version_printed++;
+	}
+
+	mdev = kzalloc(sizeof *mdev, GFP_KERNEL);
+	if (!mdev) {
+		dev_err(&dev->pdev->dev, "Device struct alloc failed, "
+			"aborting.\n");
+		err = -ENOMEM;
+		goto err_free_res;
+	}
+
+	if (mlx4_pd_alloc(dev, &mdev->priv_pdn))
+		goto err_free_dev;
+
+	if (mlx4_uar_alloc(dev, &mdev->priv_uar))
+		goto err_pd;
+
+	mdev->uar_map = ioremap(mdev->priv_uar.pfn << PAGE_SHIFT, PAGE_SIZE);
+	if (!mdev->uar_map)
+		goto err_uar;
+	spin_lock_init(&mdev->uar_lock);
+
+	mdev->dev = dev;
+	mdev->dma_device = &(dev->pdev->dev);
+	mdev->pdev = dev->pdev;
+	mdev->device_up = false;
+
+	mdev->LSO_support = !!(dev->caps.flags & (1 << 15));
+	if (!mdev->LSO_support)
+		mlx4_warn(mdev, "LSO not supported, please upgrade to later "
+				"FW version to enable LSO\n");
+
+	if (mlx4_mr_alloc(mdev->dev, mdev->priv_pdn, 0, ~0ull,
+			 MLX4_PERM_LOCAL_WRITE |  MLX4_PERM_LOCAL_READ,
+			 0, 0, &mdev->mr)) {
+		mlx4_err(mdev, "Failed allocating memory region\n");
+		goto err_uar;
+	}
+	if (mlx4_mr_enable(mdev->dev, &mdev->mr)) {
+		mlx4_err(mdev, "Failed enabling memory region\n");
+		goto err_mr;
+	}
+
+	/* Build device profile according to supplied module parameters */
+	err = mlx4_en_get_profile(mdev);
+	if (err) {
+		mlx4_err(mdev, "Bad module parameters, aborting.\n");
+		goto err_mr;
+	}
+
+	/* Configure wich ports to start according to module parameters */
+	mdev->port_cnt = 0;
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
+		mdev->port_cnt++;
+
+	/* If we did not receive an explicit number of Rx rings, default to
+	 * the number of completion vectors populated by the mlx4_core */
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+		mlx4_info(mdev, "Using %d tx rings for port:%d\n",
+			  mdev->profile.prof[i].tx_ring_num, i);
+		if (!mdev->profile.prof[i].rx_ring_num) {
+			mdev->profile.prof[i].rx_ring_num = 1;
+			mlx4_info(mdev, "Defaulting to %d rx rings for port:%d\n",
+				  1, i);
+		} else
+			mlx4_info(mdev, "Using %d rx rings for port:%d\n",
+				  mdev->profile.prof[i].rx_ring_num, i);
+	}
+
+	/* Create our own workqueue for reset/multicast tasks
+	 * Note: we cannot use the shared workqueue because of deadlocks caused
+	 *       by the rtnl lock */
+	mdev->workqueue = create_singlethread_workqueue("mlx4_en");
+	if (!mdev->workqueue) {
+		err = -ENOMEM;
+		goto err_close_nic;
+	}
+
+	/* At this stage all non-port specific tasks are complete:
+	 * mark the card state as up */
+	mutex_init(&mdev->state_lock);
+	mdev->device_up = true;
+
+	/* Setup ports */
+
+	/* Create a netdev for each port */
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+		mlx4_info(mdev, "Activating port:%d\n", i);
+		if (mlx4_en_init_netdev(mdev, i, &mdev->profile.prof[i])) {
+			mdev->pndev[i] = NULL;
+			goto err_free_netdev;
+		}
+	}
+	return mdev;
+
+
+err_free_netdev:
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH) {
+		if (mdev->pndev[i])
+			mlx4_en_destroy_netdev(mdev->pndev[i]);
+	}
+
+	mutex_lock(&mdev->state_lock);
+	mdev->device_up = false;
+	mutex_unlock(&mdev->state_lock);
+	flush_workqueue(mdev->workqueue);
+
+	/* Stop event queue before we drop down to release shared SW state */
+
+err_close_nic:
+	destroy_workqueue(mdev->workqueue);
+err_mr:
+	mlx4_mr_free(dev, &mdev->mr);
+err_uar:
+	mlx4_uar_free(dev, &mdev->priv_uar);
+err_pd:
+	mlx4_pd_free(dev, mdev->priv_pdn);
+err_free_dev:
+	kfree(mdev);
+err_free_res:
+	return NULL;
+}
+
+static struct mlx4_interface mlx4_en_interface = {
+	.add	= mlx4_en_add,
+	.remove	= mlx4_en_remove,
+	.event	= mlx4_en_event,
+};
+
+static int __init mlx4_en_init(void)
+{
+	return mlx4_register_interface(&mlx4_en_interface);
+}
+
+static void __exit mlx4_en_cleanup(void)
+{
+	mlx4_unregister_interface(&mlx4_en_interface);
+}
+
+module_init(mlx4_en_init);
+module_exit(mlx4_en_cleanup);
+
diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c
new file mode 100644
index 00000000000..a339afbeed3
--- /dev/null
+++ b/drivers/net/mlx4/en_netdev.c
@@ -0,0 +1,1088 @@
+/*
+ * Copyright (c) 2007 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/tcp.h>
+#include <linux/if_vlan.h>
+#include <linux/delay.h>
+
+#include <linux/mlx4/driver.h>
+#include <linux/mlx4/device.h>
+#include <linux/mlx4/cmd.h>
+#include <linux/mlx4/cq.h>
+
+#include "mlx4_en.h"
+#include "en_port.h"
+
+
+static void mlx4_en_vlan_rx_register(struct net_device *dev, struct vlan_group *grp)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err;
+
+	mlx4_dbg(HW, priv, "Registering VLAN group:%p\n", grp);
+	priv->vlgrp = grp;
+
+	mutex_lock(&mdev->state_lock);
+	if (mdev->device_up && priv->port_up) {
+		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, grp);
+		if (err)
+			mlx4_err(mdev, "Failed configuring VLAN filter\n");
+	}
+	mutex_unlock(&mdev->state_lock);
+}
+
+static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err;
+
+	if (!priv->vlgrp)
+		return;
+
+	mlx4_dbg(HW, priv, "adding VLAN:%d (vlgrp entry:%p)\n",
+		 vid, vlan_group_get_device(priv->vlgrp, vid));
+
+	/* Add VID to port VLAN filter */
+	mutex_lock(&mdev->state_lock);
+	if (mdev->device_up && priv->port_up) {
+		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, priv->vlgrp);
+		if (err)
+			mlx4_err(mdev, "Failed configuring VLAN filter\n");
+	}
+	mutex_unlock(&mdev->state_lock);
+}
+
+static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err;
+
+	if (!priv->vlgrp)
+		return;
+
+	mlx4_dbg(HW, priv, "Killing VID:%d (vlgrp:%p vlgrp "
+		 "entry:%p)\n", vid, priv->vlgrp,
+		 vlan_group_get_device(priv->vlgrp, vid));
+	vlan_group_set_device(priv->vlgrp, vid, NULL);
+
+	/* Remove VID from port VLAN filter */
+	mutex_lock(&mdev->state_lock);
+	if (mdev->device_up && priv->port_up) {
+		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, priv->vlgrp);
+		if (err)
+			mlx4_err(mdev, "Failed configuring VLAN filter\n");
+	}
+	mutex_unlock(&mdev->state_lock);
+}
+
+static u64 mlx4_en_mac_to_u64(u8 *addr)
+{
+	u64 mac = 0;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		mac <<= 8;
+		mac |= addr[i];
+	}
+	return mac;
+}
+
+static int mlx4_en_set_mac(struct net_device *dev, void *addr)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct sockaddr *saddr = addr;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	memcpy(dev->dev_addr, saddr->sa_data, ETH_ALEN);
+	priv->mac = mlx4_en_mac_to_u64(dev->dev_addr);
+	queue_work(mdev->workqueue, &priv->mac_task);
+	return 0;
+}
+
+static void mlx4_en_do_set_mac(struct work_struct *work)
+{
+	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+						 mac_task);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	int err = 0;
+
+	mutex_lock(&mdev->state_lock);
+	if (priv->port_up) {
+		/* Remove old MAC and insert the new one */
+		mlx4_unregister_mac(mdev->dev, priv->port, priv->mac_index);
+		err = mlx4_register_mac(mdev->dev, priv->port,
+					priv->mac, &priv->mac_index);
+		if (err)
+			mlx4_err(mdev, "Failed changing HW MAC address\n");
+	} else
+		mlx4_dbg(HW, priv, "Port is down, exiting...\n");
+
+	mutex_unlock(&mdev->state_lock);
+}
+
+static void mlx4_en_clear_list(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct dev_mc_list *plist = priv->mc_list;
+	struct dev_mc_list *next;
+
+	while (plist) {
+		next = plist->next;
+		kfree(plist);
+		plist = next;
+	}
+	priv->mc_list = NULL;
+}
+
+static void mlx4_en_cache_mclist(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct dev_mc_list *mclist;
+	struct dev_mc_list *tmp;
+	struct dev_mc_list *plist = NULL;
+
+	for (mclist = dev->mc_list; mclist; mclist = mclist->next) {
+		tmp = kmalloc(sizeof(struct dev_mc_list), GFP_ATOMIC);
+		if (!tmp) {
+			mlx4_err(mdev, "failed to allocate multicast list\n");
+			mlx4_en_clear_list(dev);
+			return;
+		}
+		memcpy(tmp, mclist, sizeof(struct dev_mc_list));
+		tmp->next = NULL;
+		if (plist)
+			plist->next = tmp;
+		else
+			priv->mc_list = tmp;
+		plist = tmp;
+	}
+}
+
+
+static void mlx4_en_set_multicast(struct net_device *dev)
+{
+	struct mlx4_en_priv *priv = netdev_priv(dev);
+
+	if (!priv->port_up)
+		return;
+
+	queue_work(priv->mdev->workqueue, &priv->mcast_task);
+}
+
+static void mlx4_en_do_set_multicast(struct work_struct *work)
+{
+	struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv,
+						 mcast_task);
+	struct mlx4_en_dev *mdev = priv->mdev;
+	struct net_device *dev = priv->dev;
+	struct dev_mc_list *mclist;
+	u64 mcast_addr = 0;
+	int err;
+
+	mutex_lock(&mdev->state_lock);
+	if (!mdev->device_up) {
+		mlx4_dbg(HW, priv, "Card is not up, ignoring "
+				   "multicast change.\n");
+		goto out;
+	}
+	if (!priv->port_up) {
+		mlx4_dbg(HW, priv, "Port is down, ignoring "
+				   "multicast change.\n");
+		goto out;
+	}
+
+	/*
+	 * Promsicuous mode: disable all filters
+	 */
+
+	if (dev->flags & IFF_PROMISC) {
+		if (!(priv->flags & MLX4_EN_FLAG_PROMISC)) {
+			if (netif_msg_rx_status(priv))
+				mlx4_warn(mdev, "Port:%d entering promiscuous mode\n",
+					  priv->port);
+			priv->flags |= MLX4_EN_FLAG_PROMISC;
+
+			/* Enable promiscouos mode */
+			err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port,
+						     priv->base_qpn, 1);
+			if (err)
+				mlx4_err(mdev, "Failed enabling "
+					 "promiscous mode\n");
+
+			/* Disable port multicast filter (unconditionally) */
+			err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
+						  0, MLX4_MCAST_DISABLE);
+			if (err)
+				mlx4_err(mdev, "Failed disabling "
+					 "multicast filter\n");
+
+			/* Disable port VLAN filter */
+			err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, NULL);
+			if (err)
+				mlx4_err(mdev, "Failed disabling "
+					 "VLAN filter\n");
+		}
+		goto out;
+	}
+
+	/*
+	 * Not in promiscous mode
+	 */
+
+	if (priv->flags & MLX4_EN_FLAG_PROMISC) {
+		if (netif_msg_rx_status(priv))
+			mlx4_warn(mdev, "Port:%d leaving promiscuous mode\n",
+				  priv->port);
+		priv->flags &= ~MLX4_EN_FLAG_PROMISC;
+
+		/* Disable promiscouos mode */
+		err = mlx4_SET_PORT_qpn_calc(mdev->dev, priv->port,
+					     priv->base_qpn, 0);
+		if (err)
+			mlx4_err(mdev, "Failed disabling promiscous mode\n");
+
+		/* Enable port VLAN filter */
+		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, priv->vlgrp);
+		if (err)
+			mlx4_err(mdev, "Failed enabling VLAN filter\n");
+	}
+
+	/* Enable/disable the multicast filter according to IFF_ALLMULTI */
+	if (dev->flags & IFF_ALLMULTI) {
+		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
+					  0, MLX4_MCAST_DISABLE);
+		if (err)
+			mlx4_err(mdev, "Failed disabling multicast filter\n");
+	} else {
+		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
+					  0, MLX4_MCAST_DISABLE);
+		if (err)
+			mlx4_err(mdev, "Failed disabling multicast filter\n");
+
+		/* Flush mcast filter and init it with broadcast address */
+		mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, ETH_BCAST,
+				    1, MLX4_MCAST_CONFIG);
+
+		/* Update multicast list - we cache all addresses so they won't
+		 * change while HW is updated holding the command semaphor */
+		netif_tx_lock_bh(dev);
+		mlx4_en_cache_mclist(dev);
+		netif_tx_unlock_bh(dev);
+		for (mclist = priv->mc_list; mclist; mclist = mclist->next) {
+			mcast_addr = mlx4_en_mac_to_u64(mclist->dmi_addr);
+			mlx4_SET_MCAST_FLTR(mdev->dev, priv->port,
+					    mcast_addr, 0, MLX4_MCAST_CONFIG);
+		}
+		err = mlx4_SET_MCAST_FLTR(mdev->dev, priv->port, 0,
+					  0, MLX4_MCAST_ENABLE);