ntb_transport.c

/*
 * This file is provided under a dual BSD/GPLv2 license.  When using or
 *   redistributing this file, you may do so under either license.
 *
 *   GPL LICENSE SUMMARY
 *
 *   Copyright(c) 2012 Intel Corporation. All rights reserved.
 *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
 *
 *   This program is free software; you can redistribute it and/or modify
 *   it under the terms of version 2 of the GNU General Public License as
 *   published by the Free Software Foundation.
 *
 *   BSD LICENSE
 *
 *   Copyright(c) 2012 Intel Corporation. All rights reserved.
 *   Copyright (C) 2015 EMC Corporation. All Rights Reserved.
 *
 *   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 copy
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * PCIe NTB Transport Linux driver
 *
 * Contact Information:
 * Jon Mason <jon.mason@intel.com>
 */
#include <linux/debugfs.h>
#include <linux/delay.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/uaccess.h>
#include "linux/ntb.h"
#include "linux/ntb_transport.h"

#define NTB_TRANSPORT_VERSION	4
#define NTB_TRANSPORT_VER	"4"
#define NTB_TRANSPORT_NAME	"ntb_transport"
#define NTB_TRANSPORT_DESC	"Software Queue-Pair Transport over NTB"

MODULE_DESCRIPTION(NTB_TRANSPORT_DESC);
MODULE_VERSION(NTB_TRANSPORT_VER);
MODULE_LICENSE("Dual BSD/GPL");
MODULE_AUTHOR("Intel Corporation");

static unsigned long max_mw_size;
module_param(max_mw_size, ulong, 0644);
MODULE_PARM_DESC(max_mw_size, "Limit size of large memory windows");

static unsigned int transport_mtu = 0x10000;
module_param(transport_mtu, uint, 0644);
MODULE_PARM_DESC(transport_mtu, "Maximum size of NTB transport packets");

static unsigned char max_num_clients;
module_param(max_num_clients, byte, 0644);
MODULE_PARM_DESC(max_num_clients, "Maximum number of NTB transport clients");

static unsigned int copy_bytes = 1024;
module_param(copy_bytes, uint, 0644);
MODULE_PARM_DESC(copy_bytes, "Threshold under which NTB will use the CPU to copy instead of DMA");

static bool use_dma;
module_param(use_dma, bool, 0644);
MODULE_PARM_DESC(use_dma, "Use DMA engine to perform large data copy");

static struct dentry *nt_debugfs_dir;

struct ntb_queue_entry {
	/* ntb_queue list reference */
	struct list_head entry;
	/* pointers to data to be transferred */
	void *cb_data;
	void *buf;
	unsigned int len;
	unsigned int flags;

	struct ntb_transport_qp *qp;
	union {
		struct ntb_payload_header __iomem *tx_hdr;
		struct ntb_payload_header *rx_hdr;
	};
	unsigned int index;
};

struct ntb_rx_info {
	unsigned int entry;
};

struct ntb_transport_qp {
	struct ntb_transport_ctx *transport;
	struct ntb_dev *ndev;
	void *cb_data;
	struct dma_chan *tx_dma_chan;
	struct dma_chan *rx_dma_chan;

	bool client_ready;
	bool link_is_up;
	bool active;

	u8 qp_num;	/* Only 64 QP's are allowed.  0-63 */
	u64 qp_bit;

	struct ntb_rx_info __iomem *rx_info;
	struct ntb_rx_info *remote_rx_info;

	void (*tx_handler)(struct ntb_transport_qp *qp, void *qp_data,
			   void *data, int len);
	struct list_head tx_free_q;
	spinlock_t ntb_tx_free_q_lock;
	void __iomem *tx_mw;
	dma_addr_t tx_mw_phys;
	unsigned int tx_index;
	unsigned int tx_max_entry;
	unsigned int tx_max_frame;

	void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
			   void *data, int len);
	struct list_head rx_post_q;
	struct list_head rx_pend_q;
	struct list_head rx_free_q;
	/* ntb_rx_q_lock: synchronize access to rx_XXXX_q */
	spinlock_t ntb_rx_q_lock;
	void *rx_buff;
	unsigned int rx_index;
	unsigned int rx_max_entry;
	unsigned int rx_max_frame;
	dma_cookie_t last_cookie;
	struct tasklet_struct rxc_db_work;

	void (*event_handler)(void *data, int status);
	struct delayed_work link_work;
	struct work_struct link_cleanup;

	struct dentry *debugfs_dir;
	struct dentry *debugfs_stats;

	/* Stats */
	u64 rx_bytes;
	u64 rx_pkts;
	u64 rx_ring_empty;
	u64 rx_err_no_buf;
	u64 rx_err_oflow;
	u64 rx_err_ver;
	u64 rx_memcpy;
	u64 rx_async;
	u64 dma_rx_prep_err;
	u64 tx_bytes;
	u64 tx_pkts;
	u64 tx_ring_full;
	u64 tx_err_no_buf;
	u64 tx_memcpy;
	u64 tx_async;
	u64 dma_tx_prep_err;
};

struct ntb_transport_mw {
	phys_addr_t phys_addr;
	resource_size_t phys_size;
	resource_size_t xlat_align;
	resource_size_t xlat_align_size;
	void __iomem *vbase;
	size_t xlat_size;
	size_t buff_size;
	void *virt_addr;
	dma_addr_t dma_addr;
};

struct ntb_transport_client_dev {
	struct list_head entry;
	struct ntb_transport_ctx *nt;
	struct device dev;
};

struct ntb_transport_ctx {
	struct list_head entry;
	struct list_head client_devs;

	struct ntb_dev *ndev;

	struct ntb_transport_mw *mw_vec;
	struct ntb_transport_qp *qp_vec;
	unsigned int mw_count;
	unsigned int qp_count;
	u64 qp_bitmap;
	u64 qp_bitmap_free;

	bool link_is_up;
	struct delayed_work link_work;
	struct work_struct link_cleanup;

	struct dentry *debugfs_node_dir;
};

enum {
	DESC_DONE_FLAG = BIT(0),
	LINK_DOWN_FLAG = BIT(1),
};

struct ntb_payload_header {
	unsigned int ver;
	unsigned int len;
	unsigned int flags;
};

enum {
	VERSION = 0,
	QP_LINKS,
	NUM_QPS,
	NUM_MWS,
	MW0_SZ_HIGH,
	MW0_SZ_LOW,
	MW1_SZ_HIGH,
	MW1_SZ_LOW,
	MAX_SPAD,
};

#define dev_client_dev(__dev) \
	container_of((__dev), struct ntb_transport_client_dev, dev)

#define drv_client(__drv) \
	container_of((__drv), struct ntb_transport_client, driver)

#define QP_TO_MW(nt, qp)	((qp) % nt->mw_count)
#define NTB_QP_DEF_NUM_ENTRIES	100
#define NTB_LINK_DOWN_TIMEOUT	10
#define DMA_RETRIES		20
#define DMA_OUT_RESOURCE_TO	50

static void ntb_transport_rxc_db(unsigned long data);
static const struct ntb_ctx_ops ntb_transport_ops;
static struct ntb_client ntb_transport_client;

static int ntb_transport_bus_match(struct device *dev,
				   struct device_driver *drv)
{
	return !strncmp(dev_name(dev), drv->name, strlen(drv->name));
}

static int ntb_transport_bus_probe(struct device *dev)
{
	const struct ntb_transport_client *client;
	int rc = -EINVAL;

	get_device(dev);

	client = drv_client(dev->driver);
	rc = client->probe(dev);
	if (rc)
		put_device(dev);

	return rc;
}

static int ntb_transport_bus_remove(struct device *dev)
{
	const struct ntb_transport_client *client;

	client = drv_client(dev->driver);
	client->remove(dev);

	put_device(dev);

	return 0;
}

static struct bus_type ntb_transport_bus = {
	.name = "ntb_transport",
	.match = ntb_transport_bus_match,
	.probe = ntb_transport_bus_probe,
	.remove = ntb_transport_bus_remove,
};

static LIST_HEAD(ntb_transport_list);

static int ntb_bus_init(struct ntb_transport_ctx *nt)
{
	list_add_tail(&nt->entry, &ntb_transport_list);
	return 0;
}

static void ntb_bus_remove(struct ntb_transport_ctx *nt)
{
	struct ntb_transport_client_dev *client_dev, *cd;

	list_for_each_entry_safe(client_dev, cd, &nt->client_devs, entry) {
		dev_err(client_dev->dev.parent, "%s still attached to bus, removing\n",
			dev_name(&client_dev->dev));
		list_del(&client_dev->entry);
		device_unregister(&client_dev->dev);
	}

	list_del(&nt->entry);
}

static void ntb_transport_client_release(struct device *dev)
{
	struct ntb_transport_client_dev *client_dev;

	client_dev = dev_client_dev(dev);
	kfree(client_dev);
}

/**
 * ntb_transport_unregister_client_dev - Unregister NTB client device
 * @device_name: Name of NTB client device
 *
 * Unregister an NTB client device with the NTB transport layer
 */
void ntb_transport_unregister_client_dev(char *device_name)
{
	struct ntb_transport_client_dev *client, *cd;
	struct ntb_transport_ctx *nt;

	list_for_each_entry(nt, &ntb_transport_list, entry)
		list_for_each_entry_safe(client, cd, &nt->client_devs, entry)
			if (!strncmp(dev_name(&client->dev), device_name,
				     strlen(device_name))) {
				list_del(&client->entry);
				device_unregister(&client->dev);
			}
}
EXPORT_SYMBOL_GPL(ntb_transport_unregister_client_dev);

/**
 * ntb_transport_register_client_dev - Register NTB client device
 * @device_name: Name of NTB client device
 *
 * Register an NTB client device with the NTB transport layer
 */
int ntb_transport_register_client_dev(char *device_name)
{
	struct ntb_transport_client_dev *client_dev;
	struct ntb_transport_ctx *nt;
	int node;
	int rc, i = 0;

	if (list_empty(&ntb_transport_list))
		return -ENODEV;

	list_for_each_entry(nt, &ntb_transport_list, entry) {
		struct device *dev;

		node = dev_to_node(&nt->ndev->dev);

		client_dev = kzalloc_node(sizeof(*client_dev),
					  GFP_KERNEL, node);
		if (!client_dev) {
			rc = -ENOMEM;
			goto err;
		}

		dev = &client_dev->dev;

		/* setup and register client devices */
		dev_set_name(dev, "%s%d", device_name, i);
		dev->bus = &ntb_transport_bus;
		dev->release = ntb_transport_client_release;
		dev->parent = &nt->ndev->dev;

		rc = device_register(dev);
		if (rc) {
			kfree(client_dev);
			goto err;
		}

		list_add_tail(&client_dev->entry, &nt->client_devs);
		i++;
	}

	return 0;

err:
	ntb_transport_unregister_client_dev(device_name);

	return rc;
}
EXPORT_SYMBOL_GPL(ntb_transport_register_client_dev);

/**
 * ntb_transport_register_client - Register NTB client driver
 * @drv: NTB client driver to be registered
 *
 * Register an NTB client driver with the NTB transport layer
 *
 * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
 */
int ntb_transport_register_client(struct ntb_transport_client *drv)
{
	drv->driver.bus = &ntb_transport_bus;

	if (list_empty(&ntb_transport_list))
		return -ENODEV;

	return driver_register(&drv->driver);
}
EXPORT_SYMBOL_GPL(ntb_transport_register_client);

/**
 * ntb_transport_unregister_client - Unregister NTB client driver
 * @drv: NTB client driver to be unregistered
 *
 * Unregister an NTB client driver with the NTB transport layer
 *
 * RETURNS: An appropriate -ERRNO error value on error, or zero for success.
 */
void ntb_transport_unregister_client(struct ntb_transport_client *drv)
{
	driver_unregister(&drv->driver);
}
EXPORT_SYMBOL_GPL(ntb_transport_unregister_client);

static ssize_t debugfs_read(struct file *filp, char __user *ubuf, size_t count,
			    loff_t *offp)
{
	struct ntb_transport_qp *qp;
	char *buf;
	ssize_t ret, out_offset, out_count;

	qp = filp->private_data;

	if (!qp || !qp->link_is_up)
		return 0;

	out_count = 1000;

	buf = kmalloc(out_count, GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	out_offset = 0;
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "\nNTB QP stats:\n\n");
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_bytes - \t%llu\n", qp->rx_bytes);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_pkts - \t%llu\n", qp->rx_pkts);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_memcpy - \t%llu\n", qp->rx_memcpy);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_async - \t%llu\n", qp->rx_async);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_ring_empty - %llu\n", qp->rx_ring_empty);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_err_no_buf - %llu\n", qp->rx_err_no_buf);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_err_oflow - \t%llu\n", qp->rx_err_oflow);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_err_ver - \t%llu\n", qp->rx_err_ver);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_buff - \t0x%p\n", qp->rx_buff);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_index - \t%u\n", qp->rx_index);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "rx_max_entry - \t%u\n\n", qp->rx_max_entry);

	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_bytes - \t%llu\n", qp->tx_bytes);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_pkts - \t%llu\n", qp->tx_pkts);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_memcpy - \t%llu\n", qp->tx_memcpy);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_async - \t%llu\n", qp->tx_async);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_ring_full - \t%llu\n", qp->tx_ring_full);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_err_no_buf - %llu\n", qp->tx_err_no_buf);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_mw - \t0x%p\n", qp->tx_mw);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_index (H) - \t%u\n", qp->tx_index);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "RRI (T) - \t%u\n",
			       qp->remote_rx_info->entry);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "tx_max_entry - \t%u\n", qp->tx_max_entry);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "free tx - \t%u\n",
			       ntb_transport_tx_free_entry(qp));
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "DMA tx prep err - \t%llu\n",
			       qp->dma_tx_prep_err);
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "DMA rx prep err - \t%llu\n",
			       qp->dma_rx_prep_err);

	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "\n");
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "Using TX DMA - \t%s\n",
			       qp->tx_dma_chan ? "Yes" : "No");
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "Using RX DMA - \t%s\n",
			       qp->rx_dma_chan ? "Yes" : "No");
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "QP Link - \t%s\n",
			       qp->link_is_up ? "Up" : "Down");
	out_offset += snprintf(buf + out_offset, out_count - out_offset,
			       "\n");

	if (out_offset > out_count)
		out_offset = out_count;

	ret = simple_read_from_buffer(ubuf, count, offp, buf, out_offset);
	kfree(buf);
	return ret;
}

static const struct file_operations ntb_qp_debugfs_stats = {
	.owner = THIS_MODULE,
	.open = simple_open,
	.read = debugfs_read,
};

static void ntb_list_add(spinlock_t *lock, struct list_head *entry,
			 struct list_head *list)
{
	unsigned long flags;

	spin_lock_irqsave(lock, flags);
	list_add_tail(entry, list);
	spin_unlock_irqrestore(lock, flags);
}

static struct ntb_queue_entry *ntb_list_rm(spinlock_t *lock,
					   struct list_head *list)
{
	struct ntb_queue_entry *entry;
	unsigned long flags;

	spin_lock_irqsave(lock, flags);
	if (list_empty(list)) {
		entry = NULL;
		goto out;
	}
	entry = list_first_entry(list, struct ntb_queue_entry, entry);
	list_del(&entry->entry);

out:
	spin_unlock_irqrestore(lock, flags);

	return entry;
}

static struct ntb_queue_entry *ntb_list_mv(spinlock_t *lock,
					   struct list_head *list,
					   struct list_head *to_list)
{
	struct ntb_queue_entry *entry;
	unsigned long flags;

	spin_lock_irqsave(lock, flags);

	if (list_empty(list)) {
		entry = NULL;
	} else {
		entry = list_first_entry(list, struct ntb_queue_entry, entry);
		list_move_tail(&entry->entry, to_list);
	}

	spin_unlock_irqrestore(lock, flags);

	return entry;
}

static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
				     unsigned int qp_num)
{
	struct ntb_transport_qp *qp = &nt->qp_vec[qp_num];
	struct ntb_transport_mw *mw;
	unsigned int rx_size, num_qps_mw;
	unsigned int mw_num, mw_count, qp_count;
	unsigned int i;

	mw_count = nt->mw_count;
	qp_count = nt->qp_count;

	mw_num = QP_TO_MW(nt, qp_num);
	mw = &nt->mw_vec[mw_num];

	if (!mw->virt_addr)
		return -ENOMEM;

	if (qp_count % mw_count && mw_num + 1 < qp_count / mw_count)
		num_qps_mw = qp_count / mw_count + 1;
	else
		num_qps_mw = qp_count / mw_count;

	rx_size = (unsigned int)mw->xlat_size / num_qps_mw;
	qp->rx_buff = mw->virt_addr + rx_size * (qp_num / mw_count);
	rx_size -= sizeof(struct ntb_rx_info);

	qp->remote_rx_info = qp->rx_buff + rx_size;

	/* Due to housekeeping, there must be atleast 2 buffs */
	qp->rx_max_frame = min(transport_mtu, rx_size / 2);
	qp->rx_max_entry = rx_size / qp->rx_max_frame;
	qp->rx_index = 0;

	qp->remote_rx_info->entry = qp->rx_max_entry - 1;

	/* setup the hdr offsets with 0's */
	for (i = 0; i < qp->rx_max_entry; i++) {
		void *offset = (qp->rx_buff + qp->rx_max_frame * (i + 1) -
				sizeof(struct ntb_payload_header));
		memset(offset, 0, sizeof(struct ntb_payload_header));
	}

	qp->rx_pkts = 0;
	qp->tx_pkts = 0;
	qp->tx_index = 0;

	return 0;
}

static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw)
{
	struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
	struct pci_dev *pdev = nt->ndev->pdev;

	if (!mw->virt_addr)
		return;

	ntb_mw_clear_trans(nt->ndev, num_mw);
	dma_free_coherent(&pdev->dev, mw->buff_size,
			  mw->virt_addr, mw->dma_addr);
	mw->xlat_size = 0;
	mw->buff_size = 0;
	mw->virt_addr = NULL;
}

static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
		      resource_size_t size)
{
	struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
	struct pci_dev *pdev = nt->ndev->pdev;
	size_t xlat_size, buff_size;
	int rc;

	if (!size)
		return -EINVAL;

	xlat_size = round_up(size, mw->xlat_align_size);
	buff_size = round_up(size, mw->xlat_align);

	/* No need to re-setup */
	if (mw->xlat_size == xlat_size)
		return 0;

	if (mw->buff_size)
		ntb_free_mw(nt, num_mw);

	/* Alloc memory for receiving data.  Must be aligned */
	mw->xlat_size = xlat_size;
	mw->buff_size = buff_size;

	mw->virt_addr = dma_alloc_coherent(&pdev->dev, buff_size,
					   &mw->dma_addr, GFP_KERNEL);
	if (!mw->virt_addr) {
		mw->xlat_size = 0;
		mw->buff_size = 0;
		dev_err(&pdev->dev, "Unable to alloc MW buff of size %zu\n",
			buff_size);
		return -ENOMEM;
	}

	/*
	 * we must ensure that the memory address allocated is BAR size
	 * aligned in order for the XLAT register to take the value. This
	 * is a requirement of the hardware. It is recommended to setup CMA
	 * for BAR sizes equal or greater than 4MB.
	 */
	if (!IS_ALIGNED(mw->dma_addr, mw->xlat_align)) {
		dev_err(&pdev->dev, "DMA memory %pad is not aligned\n",
			&mw->dma_addr);
		ntb_free_mw(nt, num_mw);
		return -ENOMEM;
	}

	/* Notify HW the memory location of the receive buffer */
	rc = ntb_mw_set_trans(nt->ndev, num_mw, mw->dma_addr, mw->xlat_size);
	if (rc) {
		dev_err(&pdev->dev, "Unable to set mw%d translation", num_mw);
		ntb_free_mw(nt, num_mw);
		return -EIO;
	}

	return 0;
}

static void ntb_qp_link_down_reset(struct ntb_transport_qp *qp)
{
	qp->link_is_up = false;
	qp->active = false;

	qp->tx_index = 0;
	qp->rx_index = 0;
	qp->rx_bytes = 0;
	qp->rx_pkts = 0;
	qp->rx_ring_empty = 0;
	qp->rx_err_no_buf = 0;
	qp->rx_err_oflow = 0;
	qp->rx_err_ver = 0;
	qp->rx_memcpy = 0;
	qp->rx_async = 0;
	qp->tx_bytes = 0;
	qp->tx_pkts = 0;
	qp->tx_ring_full = 0;
	qp->tx_err_no_buf = 0;
	qp->tx_memcpy = 0;
	qp->tx_async = 0;
	qp->dma_tx_prep_err = 0;
	qp->dma_rx_prep_err = 0;
}

static void ntb_qp_link_cleanup(struct ntb_transport_qp *qp)
{
	struct ntb_transport_ctx *nt = qp->transport;
	struct pci_dev *pdev = nt->ndev->pdev;

	dev_info(&pdev->dev, "qp %d: Link Cleanup\n", qp->qp_num);

	cancel_delayed_work_sync(&qp->link_work);
	ntb_qp_link_down_reset(qp);

	if (qp->event_handler)
		qp->event_handler(qp->cb_data, qp->link_is_up);
}

static void ntb_qp_link_cleanup_work(struct work_struct *work)
{
	struct ntb_transport_qp *qp = container_of(work,
						   struct ntb_transport_qp,
						   link_cleanup);
	struct ntb_transport_ctx *nt = qp->transport;

	ntb_qp_link_cleanup(qp);

	if (nt->link_is_up)
		schedule_delayed_work(&qp->link_work,
				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}

static void ntb_qp_link_down(struct ntb_transport_qp *qp)
{
	schedule_work(&qp->link_cleanup);
}

static void ntb_transport_link_cleanup(struct ntb_transport_ctx *nt)
{
	struct ntb_transport_qp *qp;
	u64 qp_bitmap_alloc;
	int i;

	qp_bitmap_alloc = nt->qp_bitmap & ~nt->qp_bitmap_free;

	/* Pass along the info to any clients */
	for (i = 0; i < nt->qp_count; i++)
		if (qp_bitmap_alloc & BIT_ULL(i)) {
			qp = &nt->qp_vec[i];
			ntb_qp_link_cleanup(qp);
			cancel_work_sync(&qp->link_cleanup);
			cancel_delayed_work_sync(&qp->link_work);
		}

	if (!nt->link_is_up)
		cancel_delayed_work_sync(&nt->link_work);

	/* The scratchpad registers keep the values if the remote side
	 * goes down, blast them now to give them a sane value the next
	 * time they are accessed
	 */
	for (i = 0; i < MAX_SPAD; i++)
		ntb_spad_write(nt->ndev, i, 0);
}

static void ntb_transport_link_cleanup_work(struct work_struct *work)
{
	struct ntb_transport_ctx *nt =
		container_of(work, struct ntb_transport_ctx, link_cleanup);

	ntb_transport_link_cleanup(nt);
}

static void ntb_transport_event_callback(void *data)
{
	struct ntb_transport_ctx *nt = data;

	if (ntb_link_is_up(nt->ndev, NULL, NULL) == 1)
		schedule_delayed_work(&nt->link_work, 0);
	else
		schedule_work(&nt->link_cleanup);
}

static void ntb_transport_link_work(struct work_struct *work)
{
	struct ntb_transport_ctx *nt =
		container_of(work, struct ntb_transport_ctx, link_work.work);
	struct ntb_dev *ndev = nt->ndev;
	struct pci_dev *pdev = ndev->pdev;
	resource_size_t size;
	u32 val;
	int rc = 0, i, spad;

	/* send the local info, in the opposite order of the way we read it */
	for (i = 0; i < nt->mw_count; i++) {
		size = nt->mw_vec[i].phys_size;

		if (max_mw_size && size > max_mw_size)
			size = max_mw_size;

		spad = MW0_SZ_HIGH + (i * 2);
		ntb_peer_spad_write(ndev, spad, upper_32_bits(size));

		spad = MW0_SZ_LOW + (i * 2);
		ntb_peer_spad_write(ndev, spad, lower_32_bits(size));
	}

	ntb_peer_spad_write(ndev, NUM_MWS, nt->mw_count);

	ntb_peer_spad_write(ndev, NUM_QPS, nt->qp_count);

	ntb_peer_spad_write(ndev, VERSION, NTB_TRANSPORT_VERSION);

	/* Query the remote side for its info */
	val = ntb_spad_read(ndev, VERSION);
	dev_dbg(&pdev->dev, "Remote version = %d\n", val);
	if (val != NTB_TRANSPORT_VERSION)
		goto out;

	val = ntb_spad_read(ndev, NUM_QPS);
	dev_dbg(&pdev->dev, "Remote max number of qps = %d\n", val);
	if (val != nt->qp_count)
		goto out;

	val = ntb_spad_read(ndev, NUM_MWS);
	dev_dbg(&pdev->dev, "Remote number of mws = %d\n", val);
	if (val != nt->mw_count)
		goto out;

	for (i = 0; i < nt->mw_count; i++) {
		u64 val64;

		val = ntb_spad_read(ndev, MW0_SZ_HIGH + (i * 2));
		val64 = (u64)val << 32;

		val = ntb_spad_read(ndev, MW0_SZ_LOW + (i * 2));
		val64 |= val;

		dev_dbg(&pdev->dev, "Remote MW%d size = %#llx\n", i, val64);

		rc = ntb_set_mw(nt, i, val64);
		if (rc)
			goto out1;
	}

	nt->link_is_up = true;

	for (i = 0; i < nt->qp_count; i++) {
		struct ntb_transport_qp *qp = &nt->qp_vec[i];

		ntb_transport_setup_qp_mw(nt, i);

		if (qp->client_ready)
			schedule_delayed_work(&qp->link_work, 0);
	}

	return;

out1:
	for (i = 0; i < nt->mw_count; i++)
		ntb_free_mw(nt, i);

	/* if there's an actual failure, we should just bail */
	if (rc < 0) {
		ntb_link_disable(ndev);
		return;
	}

out:
	if (ntb_link_is_up(ndev, NULL, NULL) == 1)
		schedule_delayed_work(&nt->link_work,
				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
}

static void ntb_qp_link_work(struct work_struct *work)
{
	struct ntb_transport_qp *qp = container_of(work,
						   struct ntb_transport_qp,
						   link_work.work);
	struct pci_dev *pdev = qp->ndev->pdev;
	struct ntb_transport_ctx *nt = qp->transport;
	int val;