ibmveth.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 1,157 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:
  - remove frag processing code - no longer needed
  - add support for sysfs
  - possibly remove procfs support
*/

#include <linux/config.h>
#include <linux/module.h>
#include <linux/version.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 <asm/semaphore.h>
#include <asm/hvcall.h>
#include <asm/atomic.h>
#include <asm/iommu.h>
#include <asm/vio.h>
#include <asm/uaccess.h>
#include <linux/seq_file.h>

#include "ibmveth.h"

#define DEBUG 1

#define ibmveth_printk(fmt, args...) \
  printk(KERN_INFO "%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 net_device *dev, int *budget);
static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *dev);
static struct net_device_stats *ibmveth_get_stats(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, struct pt_regs *regs);

#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 "1.02"

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

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

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

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

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

/* 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)
{
	pool->size = pool_size;
	pool->index = pool_index;
	pool->buff_size = buff_size;
	pool->threshold = pool_size / 2;
}

/* 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->size;
		index = pool->free_map[free_index];
	
		ibmveth_assert(index != IBM_VETH_INVALID_MAP);
		ibmveth_assert(pool->skbuff[index] == NULL);

		dma_addr = vio_map_single(adapter->vdev, 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.desc = 0;
		desc.fields.valid = 1;
		desc.fields.length = 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] = IBM_VETH_INVALID_MAP;
			pool->skbuff[index] = NULL;
			pool->consumer_index--;
			vio_unmap_single(adapter->vdev, 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));
}

/* check if replenishing is needed.  */
static inline int ibmveth_is_replenishing_needed(struct ibmveth_adapter *adapter)
{
	return ((atomic_read(&adapter->rx_buff_pool[0].available) < adapter->rx_buff_pool[0].threshold) ||
		(atomic_read(&adapter->rx_buff_pool[1].available) < adapter->rx_buff_pool[1].threshold) ||
		(atomic_read(&adapter->rx_buff_pool[2].available) < adapter->rx_buff_pool[2].threshold));
}

/* replenish tasklet routine */
static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) 
{
	adapter->replenish_task_cycles++;

	ibmveth_replenish_buffer_pool(adapter, &adapter->rx_buff_pool[0]);
	ibmveth_replenish_buffer_pool(adapter, &adapter->rx_buff_pool[1]);
	ibmveth_replenish_buffer_pool(adapter, &adapter->rx_buff_pool[2]);

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

	atomic_inc(&adapter->not_replenishing);
}

/* kick the replenish tasklet if we need replenishing and it isn't already running */
static inline void ibmveth_schedule_replenishing(struct ibmveth_adapter *adapter)
{
	if(ibmveth_is_replenishing_needed(adapter) && 
	   (atomic_dec_if_positive(&adapter->not_replenishing) == 0)) {	
		schedule_work(&adapter->replenish_task);
	}
}

/* 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;

	if(pool->free_map) {
		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) {
				vio_unmap_single(adapter->vdev,
						 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;

	vio_unmap_single(adapter->vdev,
			 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].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);

	desc.desc = 0;
	desc.fields.valid = 1;
	desc.fields.length = 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);
	}