ibmveth.c

来自「linux 内核源代码」· C语言 代码 · 共 1,549 行 · 第 1/3 页

/**************************************************************************/
/*                                                                        */
/* IBM eServer i/pSeries Virtual Ethernet Device Driver                   */
/* Copyright (C) 2003 IBM Corp.                                           */
/*  Originally written by Dave Larson ([e-mail])                */
/*  Maintained by Santiago Leon ([e-mail])                       */
/*                                                                        */
/*  This program is free software; you can redistribute it and/or modify  */
/*  it under the terms of the GNU General Public License as published by  */
/*  the Free Software Foundation; either version 2 of the License, or     */
/*  (at your option) any later version.                                   */
/*                                                                        */
/*  This program is distributed in the hope that it will be useful,       */
/*  but WITHOUT ANY WARRANTY; without even the implied warranty of        */
/*  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the         */
/*  GNU General Public License for more details.                          */
/*                                                                        */
/*  You should have received a copy of the GNU General Public License     */
/*  along with this program; if not, write to the Free Software           */
/*  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  */
/*                                                                   USA  */
/*                                                                        */
/* This module contains the implementation of a virtual ethernet device   */
/* for use with IBM i/pSeries LPAR Linux.  It utilizes the logical LAN    */
/* option of the RS/6000 Platform Architechture to interface with virtual */
/* ethernet NICs that are presented to the partition by the hypervisor.   */
/*                                                                        */
/**************************************************************************/
/*
  TODO:
  - add support for sysfs
  - possibly remove procfs support
*/

#include <linux/module.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/ioport.h>
#include <linux/dma-mapping.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/mm.h>
#include <linux/ethtool.h>
#include <linux/proc_fs.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <net/net_namespace.h>
#include <asm/semaphore.h>
#include <asm/hvcall.h>
#include <asm/atomic.h>
#include <asm/vio.h>
#include <asm/uaccess.h>
#include <linux/seq_file.h>

#include "ibmveth.h"

#undef DEBUG

#define ibmveth_printk(fmt, args...) \
  printk(KERN_DEBUG "%s: " fmt, __FILE__, ## args)

#define ibmveth_error_printk(fmt, args...) \
  printk(KERN_ERR "(%s:%3.3d ua:%x) ERROR: " fmt, __FILE__, __LINE__ , adapter->vdev->unit_address, ## args)

#ifdef DEBUG
#define ibmveth_debug_printk_no_adapter(fmt, args...) \
  printk(KERN_DEBUG "(%s:%3.3d): " fmt, __FILE__, __LINE__ , ## args)
#define ibmveth_debug_printk(fmt, args...) \
  printk(KERN_DEBUG "(%s:%3.3d ua:%x): " fmt, __FILE__, __LINE__ , adapter->vdev->unit_address, ## args)
#define ibmveth_assert(expr) \
  if(!(expr)) {                                   \
    printk(KERN_DEBUG "assertion failed (%s:%3.3d ua:%x): %s\n", __FILE__, __LINE__, adapter->vdev->unit_address, #expr); \
    BUG(); \
  }
#else
#define ibmveth_debug_printk_no_adapter(fmt, args...)
#define ibmveth_debug_printk(fmt, args...)
#define ibmveth_assert(expr)
#endif

static int ibmveth_open(struct net_device *dev);
static int ibmveth_close(struct net_device *dev);
static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
static int ibmveth_poll(struct napi_struct *napi, int budget);
static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *dev);
static void ibmveth_set_multicast_list(struct net_device *dev);
static int ibmveth_change_mtu(struct net_device *dev, int new_mtu);
static void ibmveth_proc_register_driver(void);
static void ibmveth_proc_unregister_driver(void);
static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter);
static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter);
static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance);
static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter);
static struct kobj_type ktype_veth_pool;

#ifdef CONFIG_PROC_FS
#define IBMVETH_PROC_DIR "ibmveth"
static struct proc_dir_entry *ibmveth_proc_dir;
#endif

static const char ibmveth_driver_name[] = "ibmveth";
static const char ibmveth_driver_string[] = "IBM i/pSeries Virtual Ethernet Driver";
#define ibmveth_driver_version "1.03"

MODULE_AUTHOR("Santiago Leon <[e-mail]>");
MODULE_DESCRIPTION("IBM i/pSeries Virtual Ethernet Driver");
MODULE_LICENSE("GPL");
MODULE_VERSION(ibmveth_driver_version);

struct ibmveth_stat {
	char name[ETH_GSTRING_LEN];
	int offset;
};

#define IBMVETH_STAT_OFF(stat) offsetof(struct ibmveth_adapter, stat)
#define IBMVETH_GET_STAT(a, off) *((u64 *)(((unsigned long)(a)) + off))

struct ibmveth_stat ibmveth_stats[] = {
	{ "replenish_task_cycles", IBMVETH_STAT_OFF(replenish_task_cycles) },
	{ "replenish_no_mem", IBMVETH_STAT_OFF(replenish_no_mem) },
	{ "replenish_add_buff_failure", IBMVETH_STAT_OFF(replenish_add_buff_failure) },
	{ "replenish_add_buff_success", IBMVETH_STAT_OFF(replenish_add_buff_success) },
	{ "rx_invalid_buffer", IBMVETH_STAT_OFF(rx_invalid_buffer) },
	{ "rx_no_buffer", IBMVETH_STAT_OFF(rx_no_buffer) },
	{ "tx_map_failed", IBMVETH_STAT_OFF(tx_map_failed) },
	{ "tx_send_failed", IBMVETH_STAT_OFF(tx_send_failed) },
};

/* simple methods of getting data from the current rxq entry */
static inline u32 ibmveth_rxq_flags(struct ibmveth_adapter *adapter)
{
	return adapter->rx_queue.queue_addr[adapter->rx_queue.index].flags_off;
}

static inline int ibmveth_rxq_toggle(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_TOGGLE) >> IBMVETH_RXQ_TOGGLE_SHIFT;
}

static inline int ibmveth_rxq_pending_buffer(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_toggle(adapter) == adapter->rx_queue.toggle);
}

static inline int ibmveth_rxq_buffer_valid(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_VALID);
}

static inline int ibmveth_rxq_frame_offset(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_OFF_MASK);
}

static inline int ibmveth_rxq_frame_length(struct ibmveth_adapter *adapter)
{
	return (adapter->rx_queue.queue_addr[adapter->rx_queue.index].length);
}

static inline int ibmveth_rxq_csum_good(struct ibmveth_adapter *adapter)
{
	return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_CSUM_GOOD);
}

/* setup the initial settings for a buffer pool */
static void ibmveth_init_buffer_pool(struct ibmveth_buff_pool *pool, u32 pool_index, u32 pool_size, u32 buff_size, u32 pool_active)
{
	pool->size = pool_size;
	pool->index = pool_index;
	pool->buff_size = buff_size;
	pool->threshold = pool_size / 2;
	pool->active = pool_active;
}

/* allocate and setup an buffer pool - called during open */
static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool)
{
	int i;

	pool->free_map = kmalloc(sizeof(u16) * pool->size, GFP_KERNEL);

	if(!pool->free_map) {
		return -1;
	}

	pool->dma_addr = kmalloc(sizeof(dma_addr_t) * pool->size, GFP_KERNEL);
	if(!pool->dma_addr) {
		kfree(pool->free_map);
		pool->free_map = NULL;
		return -1;
	}

	pool->skbuff = kmalloc(sizeof(void*) * pool->size, GFP_KERNEL);

	if(!pool->skbuff) {
		kfree(pool->dma_addr);
		pool->dma_addr = NULL;

		kfree(pool->free_map);
		pool->free_map = NULL;
		return -1;
	}

	memset(pool->skbuff, 0, sizeof(void*) * pool->size);
	memset(pool->dma_addr, 0, sizeof(dma_addr_t) * pool->size);

	for(i = 0; i < pool->size; ++i) {
		pool->free_map[i] = i;
	}

	atomic_set(&pool->available, 0);
	pool->producer_index = 0;
	pool->consumer_index = 0;

	return 0;
}

/* replenish the buffers for a pool.  note that we don't need to
 * skb_reserve these since they are used for incoming...
 */
static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struct ibmveth_buff_pool *pool)
{
	u32 i;
	u32 count = pool->size - atomic_read(&pool->available);
	u32 buffers_added = 0;

	mb();

	for(i = 0; i < count; ++i) {
		struct sk_buff *skb;
		unsigned int free_index, index;
		u64 correlator;
		union ibmveth_buf_desc desc;
		unsigned long lpar_rc;
		dma_addr_t dma_addr;

		skb = alloc_skb(pool->buff_size, GFP_ATOMIC);

		if(!skb) {
			ibmveth_debug_printk("replenish: unable to allocate skb\n");
			adapter->replenish_no_mem++;
			break;
		}

		free_index = pool->consumer_index;
		pool->consumer_index = (pool->consumer_index + 1) % pool->size;
		index = pool->free_map[free_index];

		ibmveth_assert(index != IBM_VETH_INVALID_MAP);
		ibmveth_assert(pool->skbuff[index] == NULL);

		dma_addr = dma_map_single(&adapter->vdev->dev, skb->data,
				pool->buff_size, DMA_FROM_DEVICE);

		pool->free_map[free_index] = IBM_VETH_INVALID_MAP;
		pool->dma_addr[index] = dma_addr;
		pool->skbuff[index] = skb;

		correlator = ((u64)pool->index << 32) | index;
		*(u64*)skb->data = correlator;

		desc.fields.flags_len = IBMVETH_BUF_VALID | pool->buff_size;
		desc.fields.address = dma_addr;

		lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc);

		if(lpar_rc != H_SUCCESS) {
			pool->free_map[free_index] = index;
			pool->skbuff[index] = NULL;
			if (pool->consumer_index == 0)
				pool->consumer_index = pool->size - 1;
			else
				pool->consumer_index--;
			dma_unmap_single(&adapter->vdev->dev,
					pool->dma_addr[index], pool->buff_size,
					DMA_FROM_DEVICE);
			dev_kfree_skb_any(skb);
			adapter->replenish_add_buff_failure++;
			break;
		} else {
			buffers_added++;
			adapter->replenish_add_buff_success++;
		}
	}

	mb();
	atomic_add(buffers_added, &(pool->available));
}

/* replenish routine */
static void ibmveth_replenish_task(struct ibmveth_adapter *adapter)
{
	int i;

	adapter->replenish_task_cycles++;

	for(i = 0; i < IbmVethNumBufferPools; i++)
		if(adapter->rx_buff_pool[i].active)
			ibmveth_replenish_buffer_pool(adapter,
						     &adapter->rx_buff_pool[i]);

	adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8);
}

/* empty and free ana buffer pool - also used to do cleanup in error paths */
static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, struct ibmveth_buff_pool *pool)
{
	int i;

	kfree(pool->free_map);
	pool->free_map = NULL;

	if(pool->skbuff && pool->dma_addr) {
		for(i = 0; i < pool->size; ++i) {
			struct sk_buff *skb = pool->skbuff[i];
			if(skb) {
				dma_unmap_single(&adapter->vdev->dev,
						 pool->dma_addr[i],
						 pool->buff_size,
						 DMA_FROM_DEVICE);
				dev_kfree_skb_any(skb);
				pool->skbuff[i] = NULL;
			}
		}
	}

	if(pool->dma_addr) {
		kfree(pool->dma_addr);
		pool->dma_addr = NULL;
	}

	if(pool->skbuff) {
		kfree(pool->skbuff);
		pool->skbuff = NULL;
	}
}

/* remove a buffer from a pool */
static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, u64 correlator)
{
	unsigned int pool  = correlator >> 32;
	unsigned int index = correlator & 0xffffffffUL;
	unsigned int free_index;
	struct sk_buff *skb;

	ibmveth_assert(pool < IbmVethNumBufferPools);
	ibmveth_assert(index < adapter->rx_buff_pool[pool].size);

	skb = adapter->rx_buff_pool[pool].skbuff[index];

	ibmveth_assert(skb != NULL);

	adapter->rx_buff_pool[pool].skbuff[index] = NULL;

	dma_unmap_single(&adapter->vdev->dev,
			 adapter->rx_buff_pool[pool].dma_addr[index],
			 adapter->rx_buff_pool[pool].buff_size,
			 DMA_FROM_DEVICE);

	free_index = adapter->rx_buff_pool[pool].producer_index;
	adapter->rx_buff_pool[pool].producer_index
		= (adapter->rx_buff_pool[pool].producer_index + 1)
		% adapter->rx_buff_pool[pool].size;
	adapter->rx_buff_pool[pool].free_map[free_index] = index;

	mb();

	atomic_dec(&(adapter->rx_buff_pool[pool].available));
}

/* get the current buffer on the rx queue */
static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *adapter)
{
	u64 correlator = adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator;
	unsigned int pool = correlator >> 32;
	unsigned int index = correlator & 0xffffffffUL;

	ibmveth_assert(pool < IbmVethNumBufferPools);
	ibmveth_assert(index < adapter->rx_buff_pool[pool].size);

	return adapter->rx_buff_pool[pool].skbuff[index];
}

/* recycle the current buffer on the rx queue */
static void ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter)
{
	u32 q_index = adapter->rx_queue.index;
	u64 correlator = adapter->rx_queue.queue_addr[q_index].correlator;
	unsigned int pool = correlator >> 32;
	unsigned int index = correlator & 0xffffffffUL;
	union ibmveth_buf_desc desc;
	unsigned long lpar_rc;

	ibmveth_assert(pool < IbmVethNumBufferPools);
	ibmveth_assert(index < adapter->rx_buff_pool[pool].size);

	if(!adapter->rx_buff_pool[pool].active) {
		ibmveth_rxq_harvest_buffer(adapter);
		ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[pool]);
		return;
	}

	desc.fields.flags_len = IBMVETH_BUF_VALID |
		adapter->rx_buff_pool[pool].buff_size;
	desc.fields.address = adapter->rx_buff_pool[pool].dma_addr[index];

	lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, desc.desc);

	if(lpar_rc != H_SUCCESS) {
		ibmveth_debug_printk("h_add_logical_lan_buffer failed during recycle rc=%ld", lpar_rc);
		ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);
	}

	if(++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
		adapter->rx_queue.index = 0;
		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
	}
}

static void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter)
{
	ibmveth_remove_buffer_from_pool(adapter, adapter->rx_queue.queue_addr[adapter->rx_queue.index].correlator);

	if(++adapter->rx_queue.index == adapter->rx_queue.num_slots) {
		adapter->rx_queue.index = 0;
		adapter->rx_queue.toggle = !adapter->rx_queue.toggle;
	}
}

static void ibmveth_cleanup(struct ibmveth_adapter *adapter)
{
	int i;

	if(adapter->buffer_list_addr != NULL) {
		if(!dma_mapping_error(adapter->buffer_list_dma)) {
			dma_unmap_single(&adapter->vdev->dev,
					adapter->buffer_list_dma, 4096,
					DMA_BIDIRECTIONAL);
			adapter->buffer_list_dma = DMA_ERROR_CODE;
		}
		free_page((unsigned long)adapter->buffer_list_addr);
		adapter->buffer_list_addr = NULL;
	}

	if(adapter->filter_list_addr != NULL) {
		if(!dma_mapping_error(adapter->filter_list_dma)) {
			dma_unmap_single(&adapter->vdev->dev,
					adapter->filter_list_dma, 4096,
					DMA_BIDIRECTIONAL);
			adapter->filter_list_dma = DMA_ERROR_CODE;
		}
		free_page((unsigned long)adapter->filter_list_addr);
		adapter->filter_list_addr = NULL;
	}

	if(adapter->rx_queue.queue_addr != NULL) {
		if(!dma_mapping_error(adapter->rx_queue.queue_dma)) {
			dma_unmap_single(&adapter->vdev->dev,
					adapter->rx_queue.queue_dma,
					adapter->rx_queue.queue_len,
					DMA_BIDIRECTIONAL);
			adapter->rx_queue.queue_dma = DMA_ERROR_CODE;
		}
		kfree(adapter->rx_queue.queue_addr);
		adapter->rx_queue.queue_addr = NULL;
	}

	for(i = 0; i<IbmVethNumBufferPools; i++)
		if (adapter->rx_buff_pool[i].active)
			ibmveth_free_buffer_pool(adapter,
						 &adapter->rx_buff_pool[i]);
}

static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter,
        union ibmveth_buf_desc rxq_desc, u64 mac_address)
{
	int rc, try_again = 1;

	/* After a kexec the adapter will still be open, so our attempt to
	* open it will fail. So if we get a failure we free the adapter and
	* try again, but only once. */
retry:
	rc = h_register_logical_lan(adapter->vdev->unit_address,
				    adapter->buffer_list_dma, rxq_desc.desc,
				    adapter->filter_list_dma, mac_address);

	if (rc != H_SUCCESS && try_again) {
		do {
			rc = h_free_logical_lan(adapter->vdev->unit_address);
		} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));

		try_again = 0;
		goto retry;
	}

	return rc;
}

static int ibmveth_open(struct net_device *netdev)
{
	struct ibmveth_adapter *adapter = netdev->priv;
	u64 mac_address = 0;
	int rxq_entries = 1;
	unsigned long lpar_rc;
	int rc;
	union ibmveth_buf_desc rxq_desc;
	int i;

	ibmveth_debug_printk("open starting\n");

	napi_enable(&adapter->napi);

	for(i = 0; i<IbmVethNumBufferPools; i++)