diff options
Diffstat (limited to 'drivers/net/ibmveth.c')
| -rw-r--r-- | drivers/net/ibmveth.c | 1031 |
1 files changed, 528 insertions, 503 deletions
diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index 2602852cc55..c454b45ca7e 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -1,122 +1,84 @@ -/**************************************************************************/ -/* */ -/* IBM eServer i/pSeries Virtual Ethernet Device Driver */ -/* Copyright (C) 2003 IBM Corp. */ -/* Originally written by Dave Larson (larson1@us.ibm.com) */ -/* Maintained by Santiago Leon (santil@us.ibm.com) */ -/* */ -/* 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 -*/ + * IBM Power Virtual Ethernet Device Driver + * + * 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. + * + * Copyright (C) IBM Corporation, 2003, 2010 + * + * Authors: Dave Larson <larson1@us.ibm.com> + * Santiago Leon <santil@linux.vnet.ibm.com> + * Brian King <brking@linux.vnet.ibm.com> + * Robert Jennings <rcj@linux.vnet.ibm.com> + * Anton Blanchard <anton@au.ibm.com> + */ #include <linux/module.h> #include <linux/moduleparam.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/pm.h> #include <linux/ethtool.h> -#include <linux/proc_fs.h> #include <linux/in.h> #include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/slab.h> -#include <net/net_namespace.h> #include <asm/hvcall.h> #include <asm/atomic.h> #include <asm/vio.h> #include <asm/iommu.h> -#include <asm/uaccess.h> #include <asm/firmware.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 unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev); -static struct kobj_type ktype_veth_pool; +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" +static const char ibmveth_driver_string[] = "IBM Power Virtual Ethernet Driver"; +#define ibmveth_driver_version "1.04" -MODULE_AUTHOR("Santiago Leon <santil@us.ibm.com>"); -MODULE_DESCRIPTION("IBM i/pSeries Virtual Ethernet Driver"); +MODULE_AUTHOR("Santiago Leon <santil@linux.vnet.ibm.com>"); +MODULE_DESCRIPTION("IBM Power Virtual Ethernet Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(ibmveth_driver_version); +static unsigned int tx_copybreak __read_mostly = 128; +module_param(tx_copybreak, uint, 0644); +MODULE_PARM_DESC(tx_copybreak, + "Maximum size of packet that is copied to a new buffer on transmit"); + +static unsigned int rx_copybreak __read_mostly = 128; +module_param(rx_copybreak, uint, 0644); +MODULE_PARM_DESC(rx_copybreak, + "Maximum size of packet that is copied to a new buffer on receive"); + +static unsigned int rx_flush __read_mostly = 0; +module_param(rx_flush, uint, 0644); +MODULE_PARM_DESC(rx_flush, "Flush receive buffers before use"); + struct ibmveth_stat { char name[ETH_GSTRING_LEN]; int offset; @@ -128,12 +90,16 @@ struct ibmveth_stat { 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) }, + { "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) }, + { "fw_enabled_ipv4_csum", IBMVETH_STAT_OFF(fw_ipv4_csum_support) }, + { "fw_enabled_ipv6_csum", IBMVETH_STAT_OFF(fw_ipv6_csum_support) }, }; /* simple methods of getting data from the current rxq entry */ @@ -144,41 +110,44 @@ static inline u32 ibmveth_rxq_flags(struct ibmveth_adapter *adapter) static inline int ibmveth_rxq_toggle(struct ibmveth_adapter *adapter) { - return (ibmveth_rxq_flags(adapter) & IBMVETH_RXQ_TOGGLE) >> IBMVETH_RXQ_TOGGLE_SHIFT; + 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); + 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); + 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); + 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); + 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); + 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) +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->threshold = pool_size * 7 / 8; pool->active = pool_active; } @@ -189,12 +158,11 @@ static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool) pool->free_map = kmalloc(sizeof(u16) * pool->size, GFP_KERNEL); - if(!pool->free_map) { + if (!pool->free_map) return -1; - } pool->dma_addr = kmalloc(sizeof(dma_addr_t) * pool->size, GFP_KERNEL); - if(!pool->dma_addr) { + if (!pool->dma_addr) { kfree(pool->free_map); pool->free_map = NULL; return -1; @@ -202,7 +170,7 @@ static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool) pool->skbuff = kcalloc(pool->size, sizeof(void *), GFP_KERNEL); - if(!pool->skbuff) { + if (!pool->skbuff) { kfree(pool->dma_addr); pool->dma_addr = NULL; @@ -213,9 +181,8 @@ static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool) memset(pool->dma_addr, 0, sizeof(dma_addr_t) * pool->size); - for(i = 0; i < pool->size; ++i) { + for (i = 0; i < pool->size; ++i) pool->free_map[i] = i; - } atomic_set(&pool->available, 0); pool->producer_index = 0; @@ -224,10 +191,19 @@ static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool) return 0; } +static inline void ibmveth_flush_buffer(void *addr, unsigned long length) +{ + unsigned long offset; + + for (offset = 0; offset < length; offset += SMP_CACHE_BYTES) + asm("dcbfl %0,%1" :: "b" (addr), "r" (offset)); +} + /* 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) +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); @@ -240,23 +216,26 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc mb(); - for(i = 0; i < count; ++i) { + for (i = 0; i < count; ++i) { union ibmveth_buf_desc desc; - skb = alloc_skb(pool->buff_size, GFP_ATOMIC); + skb = netdev_alloc_skb(adapter->netdev, pool->buff_size); - if(!skb) { - ibmveth_debug_printk("replenish: unable to allocate skb\n"); + if (!skb) { + netdev_dbg(adapter->netdev, + "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; + pool->consumer_index++; + if (pool->consumer_index >= pool->size) + pool->consumer_index = 0; index = pool->free_map[free_index]; - ibmveth_assert(index != IBM_VETH_INVALID_MAP); - ibmveth_assert(pool->skbuff[index] == NULL); + BUG_ON(index == IBM_VETH_INVALID_MAP); + BUG_ON(pool->skbuff[index] != NULL); dma_addr = dma_map_single(&adapter->vdev->dev, skb->data, pool->buff_size, DMA_FROM_DEVICE); @@ -269,16 +248,23 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc pool->skbuff[index] = skb; correlator = ((u64)pool->index << 32) | index; - *(u64*)skb->data = correlator; + *(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 (rx_flush) { + unsigned int len = min(pool->buff_size, + adapter->netdev->mtu + + IBMVETH_BUFF_OH); + ibmveth_flush_buffer(skb->data, len); + } + lpar_rc = h_add_logical_lan_buffer(adapter->vdev->unit_address, + desc.desc); - if (lpar_rc != H_SUCCESS) + if (lpar_rc != H_SUCCESS) { goto failure; - else { + } else { buffers_added++; adapter->replenish_add_buff_success++; } @@ -313,26 +299,31 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) adapter->replenish_task_cycles++; - for (i = (IbmVethNumBufferPools - 1); i >= 0; i--) - if(adapter->rx_buff_pool[i].active) - ibmveth_replenish_buffer_pool(adapter, - &adapter->rx_buff_pool[i]); + for (i = (IBMVETH_NUM_BUFF_POOLS - 1); i >= 0; i--) { + struct ibmveth_buff_pool *pool = &adapter->rx_buff_pool[i]; + + if (pool->active && + (atomic_read(&pool->available) < pool->threshold)) + ibmveth_replenish_buffer_pool(adapter, pool); + } - adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8); + 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) +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) { + if (pool->skbuff && pool->dma_addr) { + for (i = 0; i < pool->size; ++i) { struct sk_buff *skb = pool->skbuff[i]; - if(skb) { + if (skb) { dma_unmap_single(&adapter->vdev->dev, pool->dma_addr[i], pool->buff_size, @@ -343,31 +334,32 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, struct ibm } } - if(pool->dma_addr) { + if (pool->dma_addr) { kfree(pool->dma_addr); pool->dma_addr = NULL; } - if(pool->skbuff) { + 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) +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); + BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS); + BUG_ON(index >= adapter->rx_buff_pool[pool].size); skb = adapter->rx_buff_pool[pool].skbuff[index]; - ibmveth_assert(skb != NULL); + BUG_ON(skb == NULL); adapter->rx_buff_pool[pool].skbuff[index] = NULL; @@ -377,9 +369,10 @@ static void ibmveth_remove_buffer_from_pool(struct ibmveth_adapter *adapter, u64 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].producer_index++; + if (adapter->rx_buff_pool[pool].producer_index >= + adapter->rx_buff_pool[pool].size) + adapter->rx_buff_pool[pool].producer_index = 0; adapter->rx_buff_pool[pool].free_map[free_index] = index; mb(); @@ -394,8 +387,8 @@ static inline struct sk_buff *ibmveth_rxq_get_buffer(struct ibmveth_adapter *ada unsigned int pool = correlator >> 32; unsigned int index = correlator & 0xffffffffUL; - ibmveth_assert(pool < IbmVethNumBufferPools); - ibmveth_assert(index < adapter->rx_buff_pool[pool].size); + BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS); + BUG_ON(index >= adapter->rx_buff_pool[pool].size); return adapter->rx_buff_pool[pool].skbuff[index]; } @@ -410,10 +403,10 @@ static void ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter) union ibmveth_buf_desc desc; unsigned long lpar_rc; - ibmveth_assert(pool < IbmVethNumBufferPools); - ibmveth_assert(index < adapter->rx_buff_pool[pool].size); + BUG_ON(pool >= IBMVETH_NUM_BUFF_POOLS); + BUG_ON(index >= adapter->rx_buff_pool[pool].size); - if(!adapter->rx_buff_pool[pool].active) { + if (!adapter->rx_buff_pool[pool].active) { ibmveth_rxq_harvest_buffer(adapter); ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[pool]); return; @@ -425,12 +418,13 @@ static void ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter) 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); + if (lpar_rc != H_SUCCESS) { + netdev_dbg(adapter->netdev, "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) { + if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) { adapter->rx_queue.index = 0; adapter->rx_queue.toggle = !adapter->rx_queue.toggle; } @@ -440,7 +434,7 @@ 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) { + if (++adapter->rx_queue.index == adapter->rx_queue.num_slots) { adapter->rx_queue.index = 0; adapter->rx_queue.toggle = !adapter->rx_queue.toggle; } @@ -451,7 +445,7 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) int i; struct device *dev = &adapter->vdev->dev; - if(adapter->buffer_list_addr != NULL) { + if (adapter->buffer_list_addr != NULL) { if (!dma_mapping_error(dev, adapter->buffer_list_dma)) { dma_unmap_single(dev, adapter->buffer_list_dma, 4096, DMA_BIDIRECTIONAL); @@ -461,7 +455,7 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) adapter->buffer_list_addr = NULL; } - if(adapter->filter_list_addr != NULL) { + if (adapter->filter_list_addr != NULL) { if (!dma_mapping_error(dev, adapter->filter_list_dma)) { dma_unmap_single(dev, adapter->filter_list_dma, 4096, DMA_BIDIRECTIONAL); @@ -471,7 +465,7 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) adapter->filter_list_addr = NULL; } - if(adapter->rx_queue.queue_addr != NULL) { + if (adapter->rx_queue.queue_addr != NULL) { if (!dma_mapping_error(dev, adapter->rx_queue.queue_dma)) { dma_unmap_single(dev, adapter->rx_queue.queue_dma, @@ -483,7 +477,7 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) adapter->rx_queue.queue_addr = NULL; } - for(i = 0; i<IbmVethNumBufferPools; i++) + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) if (adapter->rx_buff_pool[i].active) ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[i]); @@ -506,9 +500,11 @@ static int ibmveth_register_logical_lan(struct ibmveth_adapter *adapter, { 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. */ + /* + * 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, @@ -537,31 +533,32 @@ static int ibmveth_open(struct net_device *netdev) int i; struct device *dev; - ibmveth_debug_printk("open starting\n"); + netdev_dbg(netdev, "open starting\n"); napi_enable(&adapter->napi); - for(i = 0; i<IbmVethNumBufferPools; i++) + for(i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) rxq_entries += adapter->rx_buff_pool[i].size; adapter->buffer_list_addr = (void*) get_zeroed_page(GFP_KERNEL); adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL); - if(!adapter->buffer_list_addr || !adapter->filter_list_addr) { - ibmveth_error_printk("unable to allocate filter or buffer list pages\n"); - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return -ENOMEM; + if (!adapter->buffer_list_addr || !adapter->filter_list_addr) { + netdev_err(netdev, "unable to allocate filter or buffer list " + "pages\n"); + rc = -ENOMEM; + goto err_out; } - adapter->rx_queue.queue_len = sizeof(struct ibmveth_rx_q_entry) * rxq_entries; - adapter->rx_queue.queue_addr = kmalloc(adapter->rx_queue.queue_len, GFP_KERNEL); + adapter->rx_queue.queue_len = sizeof(struct ibmveth_rx_q_entry) * + rxq_entries; + adapter->rx_queue.queue_addr = kmalloc(adapter->rx_queue.queue_len, + GFP_KERNEL); - if(!adapter->rx_queue.queue_addr) { - ibmveth_error_printk("unable to allocate rx queue pages\n"); - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return -ENOMEM; + if (!adapter->rx_queue.queue_addr) { + netdev_err(netdev, "unable to allocate rx queue pages\n"); + rc = -ENOMEM; + goto err_out; } dev = &adapter->vdev->dev; @@ -577,10 +574,10 @@ static int ibmveth_open(struct net_device *netdev) if ((dma_mapping_error(dev, adapter->buffer_list_dma)) || (dma_mapping_error(dev, adapter->filter_list_dma)) || (dma_mapping_error(dev, adapter->rx_queue.queue_dma))) { - ibmveth_error_printk("unable to map filter or buffer list pages\n"); - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return -ENOMEM; + netdev_err(netdev, "unable to map filter or buffer list " + "pages\n"); + rc = -ENOMEM; + goto err_out; } adapter->rx_queue.index = 0; @@ -590,79 +587,86 @@ static int ibmveth_open(struct net_device *netdev) memcpy(&mac_address, netdev->dev_addr, netdev->addr_len); mac_address = mac_address >> 16; - rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | adapter->rx_queue.queue_len; + rxq_desc.fields.flags_len = IBMVETH_BUF_VALID | + adapter->rx_queue.queue_len; rxq_desc.fields.address = adapter->rx_queue.queue_dma; - ibmveth_debug_printk("buffer list @ 0x%p\n", adapter->buffer_list_addr); - ibmveth_debug_printk("filter list @ 0x%p\n", adapter->filter_list_addr); - ibmveth_debug_printk("receive q @ 0x%p\n", adapter->rx_queue.queue_addr); + netdev_dbg(netdev, "buffer list @ 0x%p\n", adapter->buffer_list_addr); + netdev_dbg(netdev, "filter list @ 0x%p\n", adapter->filter_list_addr); + netdev_dbg(netdev, "receive q @ 0x%p\n", adapter->rx_queue.queue_addr); h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE); lpar_rc = ibmveth_register_logical_lan(adapter, rxq_desc, mac_address); - if(lpar_rc != H_SUCCESS) { - ibmveth_error_printk("h_register_logical_lan failed with %ld\n", lpar_rc); - ibmveth_error_printk("buffer TCE:0x%llx filter TCE:0x%llx rxq desc:0x%llx MAC:0x%llx\n", + if (lpar_rc != H_SUCCESS) { + netdev_err(netdev, "h_register_logical_lan failed with %ld\n", + lpar_rc); + netdev_err(netdev, "buffer TCE:0x%llx filter TCE:0x%llx rxq " + "desc:0x%llx MAC:0x%llx\n", adapter->buffer_list_dma, adapter->filter_list_dma, rxq_desc.desc, mac_address); - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return -ENONET; + rc = -ENONET; + goto err_out; } - for(i = 0; i<IbmVethNumBufferPools; i++) { - if(!adapter->rx_buff_pool[i].active) + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { + if (!adapter->rx_buff_pool[i].active) continue; if (ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[i])) { - ibmveth_error_printk("unable to alloc pool\n"); + netdev_err(netdev, "unable to alloc pool\n"); adapter->rx_buff_pool[i].active = 0; - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return -ENOMEM ; + rc = -ENOMEM; + goto err_out; } } - ibmveth_debug_printk("registering irq 0x%x\n", netdev->irq); - if((rc = request_irq(netdev->irq, ibmveth_interrupt, 0, netdev->name, netdev)) != 0) { - ibmveth_error_printk("unable to request irq 0x%x, rc %d\n", netdev->irq, rc); + netdev_dbg(netdev, "registering irq 0x%x\n", netdev->irq); + rc = request_irq(netdev->irq, ibmveth_interrupt, 0, netdev->name, + netdev); + if (rc != 0) { + netdev_err(netdev, "unable to request irq 0x%x, rc %d\n", + netdev->irq, rc); do { rc = h_free_logical_lan(adapter->vdev->unit_address); } while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY)); - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return rc; + goto err_out; } adapter->bounce_buffer = kmalloc(netdev->mtu + IBMVETH_BUFF_OH, GFP_KERNEL); if (!adapter->bounce_buffer) { - ibmveth_error_printk("unable to allocate bounce buffer\n"); - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return -ENOMEM; + netdev_err(netdev, "unable to allocate bounce buffer\n"); + rc = -ENOMEM; + goto err_out_free_irq; } adapter->bounce_buffer_dma = dma_map_single(&adapter->vdev->dev, adapter->bounce_buffer, netdev->mtu + IBMVETH_BUFF_OH, DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, adapter->bounce_buffer_dma)) { - ibmveth_error_printk("unable to map bounce buffer\n"); - ibmveth_cleanup(adapter); - napi_disable(&adapter->napi); - return -ENOMEM; + netdev_err(netdev, "unable to map bounce buffer\n"); + rc = -ENOMEM; + goto err_out_free_irq; } - ibmveth_debug_printk("initial replenish cycle\n"); + netdev_dbg(netdev, "initial replenish cycle\n"); ibmveth_interrupt(netdev->irq, netdev); netif_start_queue(netdev); - ibmveth_debug_printk("open complete\n"); + netdev_dbg(netdev, "open complete\n"); return 0; + +err_out_free_irq: + free_irq(netdev->irq, netdev); +err_out: + ibmveth_cleanup(adapter); + napi_disable(&adapter->napi); + return rc; } static int ibmveth_close(struct net_device *netdev) @@ -670,7 +674,7 @@ static int ibmveth_close(struct net_device *netdev) struct ibmveth_adapter *adapter = netdev_priv(netdev); long lpar_rc; - ibmveth_debug_printk("close starting\n"); + netdev_dbg(netdev, "close starting\n"); napi_disable(&adapter->napi); @@ -683,26 +687,29 @@ static int ibmveth_close(struct net_device *netdev) lpar_rc = h_free_logical_lan(adapter->vdev->unit_address); } while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY)); - if(lpar_rc != H_SUCCESS) - { - ibmveth_error_printk("h_free_logical_lan failed with %lx, continuing with close\n", - lpar_rc); + if (lpar_rc != H_SUCCESS) { + netdev_err(netdev, "h_free_logical_lan failed with %lx, " + "continuing with close\n", lpar_rc); } free_irq(netdev->irq, netdev); - adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8); + adapter->rx_no_buffer = *(u64 *)(((char *)adapter->buffer_list_addr) + + 4096 - 8); ibmveth_cleanup(adapter); - ibmveth_debug_printk("close complete\n"); + netdev_dbg(netdev, "close complete\n"); return 0; } -static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) { - cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE); - cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg | ADVERTISED_FIBRE); +static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | + SUPPORTED_FIBRE); + cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg | + ADVERTISED_FIBRE); cmd->speed = SPEED_1000; cmd->duplex = DUPLEX_FULL; cmd->port = PORT_FIBRE; @@ -714,12 +721,16 @@ static int netdev_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) return 0; } -static void netdev_get_drvinfo (struct net_device *dev, struct ethtool_drvinfo *info) { +static void netdev_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ strncpy(info->driver, ibmveth_driver_name, sizeof(info->driver) - 1); - strncpy(info->version, ibmveth_driver_version, sizeof(info->version) - 1); + strncpy(info->version, ibmveth_driver_version, + sizeof(info->version) - 1); } -static u32 netdev_get_link(struct net_device *dev) { +static u32 netdev_get_link(struct net_device *dev) +{ return 1; } @@ -727,18 +738,20 @@ static void ibmveth_set_rx_csum_flags(struct net_device *dev, u32 data) { struct ibmveth_adapter *adapter = netdev_priv(dev); - if (data) + if (data) { adapter->rx_csum = 1; - else { + } else { /* - * Since the ibmveth firmware interface does not have the concept of - * separate tx/rx checksum offload enable, if rx checksum is disabled - * we also have to disable tx checksum offload. Once we disable rx - * checksum offload, we are no longer allowed to send tx buffers that - * are not properly checksummed. + * Since the ibmveth firmware interface does not have the + * concept of separate tx/rx checksum offload enable, if rx + * checksum is disabled we also have to disable tx checksum + * offload. Once we disable rx checksum offload, we are no + * longer allowed to send tx buffers that are not properly + * checksummed. */ adapter->rx_csum = 0; dev->features &= ~NETIF_F_IP_CSUM; + dev->features &= ~NETIF_F_IPV6_CSUM; } } @@ -747,10 +760,15 @@ static void ibmveth_set_tx_csum_flags(struct net_device *dev, u32 data) struct ibmveth_adapter *adapter = netdev_priv(dev); if (data) { - dev->features |= NETIF_F_IP_CSUM; + if (adapter->fw_ipv4_csum_support) + dev->features |= NETIF_F_IP_CSUM; + if (adapter->fw_ipv6_csum_support) + dev->features |= NETIF_F_IPV6_CSUM; adapter->rx_csum = 1; - } else + } else { dev->features &= ~NETIF_F_IP_CSUM; + dev->features &= ~NETIF_F_IPV6_CSUM; + } } static int ibmveth_set_csum_offload(struct net_device *dev, u32 data, @@ -758,7 +776,8 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data, { struct ibmveth_adapter *adapter = netdev_priv(dev); unsigned long set_attr, clr_attr, ret_attr; - long ret; + unsigned long set_attr6, clr_attr6; + long ret, ret6; int rc1 = 0, rc2 = 0; int restart = 0; @@ -772,10 +791,13 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data, set_attr = 0; clr_attr = 0; - if (data) + if (data) { set_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM; - else + set_attr6 = IBMVETH_ILLAN_IPV6_TCP_CSUM; + } else { clr_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM; + clr_attr6 = IBMVETH_ILLAN_IPV6_TCP_CSUM; + } ret = h_illan_attributes(adapter->vdev->unit_address, 0, 0, &ret_attr); @@ -786,18 +808,39 @@ static int ibmveth_set_csum_offload(struct net_device *dev, u32 data, set_attr, &ret_attr); if (ret != H_SUCCESS) { - rc1 = -EIO; - ibmveth_error_printk("unable to change checksum offload settings." - " %d rc=%ld\n", data, ret); + netdev_err(dev, "unable to change IPv4 checksum " + "offload settings. %d rc=%ld\n", + data, ret); ret = h_illan_attributes(adapter->vdev->unit_address, set_attr, clr_attr, &ret_attr); + } else { + adapter->fw_ipv4_csum_support = data; + } + + ret6 = h_illan_attributes(adapter->vdev->unit_address, + clr_attr6, set_attr6, &ret_attr); + + if (ret6 != H_SUCCESS) { + netdev_err(dev, "unable to change IPv6 checksum " + "offload settings. %d rc=%ld\n", + data, ret); + + ret = h_illan_attributes(adapter->vdev->unit_address, + set_attr6, clr_attr6, + &ret_attr); } else + adapter->fw_ipv6_csum_support = data; + + if (ret == H_SUCCESS || ret6 == H_SUCCESS) done(dev, data); + else + rc1 = -EIO; } else { rc1 = -EIO; - ibmveth_error_printk("unable to change checksum offload settings." - " %d rc=%ld ret_attr=%lx\n", data, ret, ret_attr); + netdev_err(dev, "unable to change checksum offload settings." + " %d rc=%ld ret_attr=%lx\n", data, ret, + ret_attr); } if (restart) @@ -821,13 +864,14 @@ static int ibmveth_set_tx_csum(struct net_device *dev, u32 data) struct ibmveth_adapter *adapter = netdev_priv(dev); int rc = 0; - if (data && (dev->features & NETIF_F_IP_CSUM)) + if (data && (dev->features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) return 0; - if (!data && !(dev->features & NETIF_F_IP_CSUM)) + if (!data && !(dev->features & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM))) return 0; if (data && !adapter->rx_csum) - rc = ibmveth_set_csum_offload(dev, data, ibmveth_set_tx_csum_flags); + rc = ibmveth_set_csum_offload(dev, data, + ibmveth_set_tx_csum_flags); else ibmveth_set_tx_csum_flags(dev, data); @@ -881,6 +925,7 @@ static const struct ethtool_ops netdev_ethtool_ops = { .get_strings = ibmveth_get_strings, .get_sset_count = ibmveth_get_sset_count, .get_ethtool_stats = ibmveth_get_ethtool_stats, + .set_sg = ethtool_op_set_sg, }; static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) @@ -890,129 +935,216 @@ static int ibmveth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) #define page_offset(v) ((unsigned long)(v) & ((1 << 12) - 1)) -static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, - struct net_device *netdev) +static int ibmveth_send(struct ibmveth_adapter *adapter, + union ibmveth_buf_desc *descs) { - struct ibmveth_adapter *adapter = netdev_priv(netdev); - union ibmveth_buf_desc desc; - unsigned long lpar_rc; unsigned long correlator; - unsigned long flags; unsigned int retry_count; - unsigned int tx_dropped = 0; - unsigned int tx_bytes = 0; - unsigned int tx_packets = 0; - unsigned int tx_send_failed = 0; - unsigned int tx_map_failed = 0; - int used_bounce = 0; - unsigned long data_dma_addr; + unsigned long ret; + + /* + * The retry count sets a maximum for the number of broadcast and + * multicast destinations within the system. + */ + retry_count = 1024; + correlator = 0; + do { + ret = h_send_logical_lan(adapter->vdev->unit_address, + descs[0].desc, descs[1].desc, + descs[2].desc, descs[3].desc, + descs[4].desc, descs[5].desc, + correlator, &correlator); + } while ((ret == H_BUSY) && (retry_count--)); - desc.fields.flags_len = IBMVETH_BUF_VALID | skb->len; + if (ret != H_SUCCESS && ret != H_DROPPED) { + netdev_err(adapter->netdev, "tx: h_send_logical_lan failed " + "with rc=%ld\n", ret); + return 1; + } + + return 0; +} +static netdev_tx_t ibmveth_start_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct ibmveth_adapter *adapter = netdev_priv(netdev); + unsigned int desc_flags; + union ibmveth_buf_desc descs[6]; + int last, i; + int force_bounce = 0; + + /* + * veth handles a maximum of 6 segments including the header, so + * we have to linearize the skb if there are more than this. + */ + if (skb_shinfo(skb)->nr_frags > 5 && __skb_linearize(skb)) { + netdev->stats.tx_dropped++; + goto out; + } + + /* veth can't checksum offload UDP */ if (skb->ip_summed == CHECKSUM_PARTIAL && - ip_hdr(skb)->protocol != IPPROTO_TCP && skb_checksum_help(skb)) { - ibmveth_error_printk("tx: failed to checksum packet\n"); - tx_dropped++; + ((skb->protocol == htons(ETH_P_IP) && + ip_hdr(skb)->protocol != IPPROTO_TCP) || + (skb->protocol == htons(ETH_P_IPV6) && + ipv6_hdr(skb)->nexthdr != IPPROTO_TCP)) && + skb_checksum_help(skb)) { + + netdev_err(netdev, "tx: failed to checksum packet\n"); + netdev->stats.tx_dropped++; goto out; } + desc_flags = IBMVETH_BUF_VALID; + if (skb->ip_summed == CHECKSUM_PARTIAL) { - unsigned char *buf = skb_transport_header(skb) + skb->csum_offset; + unsigned char *buf = skb_transport_header(skb) + + skb->csum_offset; - desc.fields.flags_len |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD); + desc_flags |= (IBMVETH_BUF_NO_CSUM | IBMVETH_BUF_CSUM_GOOD); /* Need to zero out the checksum */ buf[0] = 0; buf[1] = 0; } - data_dma_addr = dma_map_single(&adapter->vdev->dev, skb->data, - skb->len, DMA_TO_DEVICE); - if (dma_mapping_error(&adapter->vdev->dev, data_dma_addr)) { - if (!firmware_has_feature(FW_FEATURE_CMO)) - ibmveth_error_printk("tx: unable to map xmit buffer\n"); +retry_bounce: + memset(descs, 0, sizeof(descs)); + + /* + * If a linear packet is below the rx threshold then + * copy it into the static bounce buffer. This avoids the + * cost of a TCE insert and remove. + */ + if (force_bounce || (!skb_is_nonlinear(skb) && + (skb->len < tx_copybreak))) { skb_copy_from_linear_data(skb, adapter->bounce_buffer, skb->len); - desc.fields.address = adapter->bounce_buffer_dma; - tx_map_failed++; - used_bounce = 1; - wmb(); - } else - desc.fields.address = data_dma_addr; - - /* send the frame. Arbitrarily set retrycount to 1024 */ - correlator = 0; - retry_count = 1024; - do { - lpar_rc = h_send_logical_lan(adapter->vdev->unit_address, - desc.desc, 0, 0, 0, 0, 0, - correlator, &correlator); - } while ((lpar_rc == H_BUSY) && (retry_count--)); - - if(lpar_rc != H_SUCCESS && lpar_rc != H_DROPPED) { - ibmveth_error_printk("tx: h_send_logical_lan failed with rc=%ld\n", lpar_rc); - ibmveth_error_printk("tx: valid=%d, len=%d, address=0x%08x\n", - (desc.fields.flags_len & IBMVETH_BUF_VALID) ? 1 : 0, - skb->len, desc.fields.address); - tx_send_failed++; - tx_dropped++; - } else { - tx_packets++; - tx_bytes += skb->len; - netdev->trans_start = jiffies; /* NETIF_F_LLTX driver :( */ + + descs[0].fields.flags_len = desc_flags | skb->len; + descs[0].fields.address = adapter->bounce_buffer_dma; + + if (ibmveth_send(adapter, descs)) { + adapter->tx_send_failed++; + netdev->stats.tx_dropped++; + } else { + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += skb->len; + } + + goto out; + } + + /* Map the header */ + descs[0].fields.address = dma_map_single(&adapter->vdev->dev, skb->data, + skb_headlen(skb), + DMA_TO_DEVICE); + if (dma_mapping_error(&adapter->vdev->dev, descs[0].fields.address)) + goto map_failed; + + descs[0].fields.flags_len = desc_flags | skb_headlen(skb); + + /* Map the frags */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + unsigned long dma_addr; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + + dma_addr = dma_map_page(&adapter->vdev->dev, frag->page, + frag->page_offset, frag->size, + DMA_TO_DEVICE); + + if (dma_mapping_error(&adapter->vdev->dev, dma_addr)) + goto map_failed_frags; + + descs[i+1].fields.flags_len = desc_flags | frag->size; + descs[i+1].fields.address = dma_addr; } - if (!used_bounce) - dma_unmap_single(&adapter->vdev->dev, data_dma_addr, - skb->len, DMA_TO_DEVICE); + if (ibmveth_send(adapter, descs)) { + adapter->tx_send_failed++; + netdev->stats.tx_dropped++; + } else { + netdev->stats.tx_packets++; + netdev->stats.tx_bytes += skb->len; + } -out: spin_lock_irqsave(&adapter->stats_lock, flags); - netdev->stats.tx_dropped += tx_dropped; - netdev->stats.tx_bytes += tx_bytes; - netdev->stats.tx_packets += tx_packets; - adapter->tx_send_failed += tx_send_failed; - adapter->tx_map_failed += tx_map_failed; - spin_unlock_irqrestore(&adapter->stats_lock, flags); + for (i = 0; i < skb_shinfo(skb)->nr_frags + 1; i++) + dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address, + descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK, + DMA_TO_DEVICE); +out: dev_kfree_skb(skb); return NETDEV_TX_OK; + +map_failed_frags: + last = i+1; + for (i = 0; i < last; i++) + dma_unmap_page(&adapter->vdev->dev, descs[i].fields.address, + descs[i].fields.flags_len & IBMVETH_BUF_LEN_MASK, + DMA_TO_DEVICE); + +map_failed: + if (!firmware_has_feature(FW_FEATURE_CMO)) + netdev_err(netdev, "tx: unable to map xmit buffer\n"); + adapter->tx_map_failed++; + skb_linearize(skb); + force_bounce = 1; + goto retry_bounce; } static int ibmveth_poll(struct napi_struct *napi, int budget) { - struct ibmveth_adapter *adapter = container_of(napi, struct ibmveth_adapter, napi); + struct ibmveth_adapter *adapter = + container_of(napi, struct ibmveth_adapter, napi); struct net_device *netdev = adapter->netdev; int frames_processed = 0; unsigned long lpar_rc; - restart_poll: +restart_poll: do { - struct sk_buff *skb; - if (!ibmveth_rxq_pending_buffer(adapter)) break; - rmb(); + smp_rmb(); if (!ibmveth_rxq_buffer_valid(adapter)) { wmb(); /* suggested by larson1 */ adapter->rx_invalid_buffer++; - ibmveth_debug_printk("recycling invalid buffer\n"); + netdev_dbg(netdev, "recycling invalid buffer\n"); ibmveth_rxq_recycle_buffer(adapter); } else { + struct sk_buff *skb, *new_skb; int length = ibmveth_rxq_frame_length(adapter); int offset = ibmveth_rxq_frame_offset(adapter); int csum_good = ibmveth_rxq_csum_good(adapter); skb = ibmveth_rxq_get_buffer(adapter); - if (csum_good) - skb->ip_summed = CHECKSUM_UNNECESSARY; - ibmveth_rxq_harvest_buffer(adapter); + new_skb = NULL; + if (length < rx_copybreak) + new_skb = netdev_alloc_skb(netdev, length); + + if (new_skb) { + skb_copy_to_linear_data(new_skb, + skb->data + offset, + length); + if (rx_flush) + ibmveth_flush_buffer(skb->data, + length + offset); + skb = new_skb; + ibmveth_rxq_recycle_buffer(adapter); + } else { + ibmveth_rxq_harvest_buffer(adapter); + skb_reserve(skb, offset); + } - skb_reserve(skb, offset); skb_put(skb, length); skb->protocol = eth_type_trans(skb, netdev); + if (csum_good) + skb->ip_summed = CHECKSUM_UNNECESSARY; + netif_receive_skb(skb); /* send it up */ netdev->stats.rx_packets++; @@ -1030,7 +1162,7 @@ static int ibmveth_poll(struct napi_struct *napi, int budget) lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_ENABLE); - ibmveth_assert(lpar_rc == H_SUCCESS); + BUG_ON(lpar_rc != H_SUCCESS); napi_complete(napi); @@ -1054,7 +1186,7 @@ static irqreturn_t ibmveth_interrupt(int irq, void *dev_instance) if (napi_schedule_prep(&adapter->napi)) { lpar_rc = h_vio_signal(adapter->vdev->unit_address, VIO_IRQ_DISABLE); - ibmveth_assert(lpar_rc == H_SUCCESS); + BUG_ON(lpar_rc != H_SUCCESS); __napi_schedule(&adapter->napi); } return IRQ_HANDLED; @@ -1071,8 +1203,9 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) IbmVethMcastEnableRecv | IbmVethMcastDisableFiltering, 0); - if(lpar_rc != H_SUCCESS) { - ibmveth_error_printk("h_multicast_ctrl rc=%ld when entering promisc mode\n", lpar_rc); + if (lpar_rc != H_SUCCESS) { + netdev_err(netdev, "h_multicast_ctrl rc=%ld when " + "entering promisc mode\n", lpar_rc); } } else { struct netdev_hw_addr *ha; @@ -1082,19 +1215,23 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) IbmVethMcastDisableFiltering | IbmVethMcastClearFilterTable, 0); - if(lpar_rc != H_SUCCESS) { - ibmveth_error_printk("h_multicast_ctrl rc=%ld when attempting to clear filter table\n", lpar_rc); + if (lpar_rc != H_SUCCESS) { + netdev_err(netdev, "h_multicast_ctrl rc=%ld when " + "attempting to clear filter table\n", + lpar_rc); } /* add the addresses to the filter table */ netdev_for_each_mc_addr(ha, netdev) { - // add the multicast address to the filter table + /* add the multicast address to the filter table */ unsigned long mcast_addr = 0; memcpy(((char *)&mcast_addr)+2, ha->addr, 6); lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address, IbmVethMcastAddFilter, mcast_addr); - if(lpar_rc != H_SUCCESS) { - ibmveth_error_printk("h_multicast_ctrl rc=%ld when adding an entry to the filter table\n", lpar_rc); + if (lpar_rc != H_SUCCESS) { + netdev_err(netdev, "h_multicast_ctrl rc=%ld " + "when adding an entry to the filter " + "table\n", lpar_rc); } } @@ -1102,8 +1239,9 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) lpar_rc = h_multicast_ctrl(adapter->vdev->unit_address, IbmVethMcastEnableFiltering, 0); - if(lpar_rc != H_SUCCESS) { - ibmveth_error_printk("h_multicast_ctrl rc=%ld when enabling filtering\n", lpar_rc); + if (lpar_rc != H_SUCCESS) { + netdev_err(netdev, "h_multicast_ctrl rc=%ld when " + "enabling filtering\n", lpar_rc); } } } @@ -1113,49 +1251,47 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) struct ibmveth_adapter *adapter = netdev_priv(dev); struct vio_dev *viodev = adapter->vdev; int new_mtu_oh = new_mtu + IBMVETH_BUFF_OH; - int i; + int i, rc; + int need_restart = 0; - if (new_mtu < IBMVETH_MAX_MTU) + if (new_mtu < IBMVETH_MIN_MTU) return -EINVAL; - for (i = 0; i < IbmVethNumBufferPools; i++) + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) break; - if (i == IbmVethNumBufferPools) + if (i == IBMVETH_NUM_BUFF_POOLS) return -EINVAL; /* Deactivate all the buffer pools so that the next loop can activate only the buffer pools necessary to hold the new MTU */ - for (i = 0; i < IbmVethNumBufferPools; i++) - if (adapter->rx_buff_pool[i].active) { - ibmveth_free_buffer_pool(adapter, - &adapter->rx_buff_pool[i]); - adapter->rx_buff_pool[i].active = 0; - } + if (netif_running(adapter->netdev)) { + need_restart = 1; + adapter->pool_config = 1; + ibmveth_close(adapter->netdev); + adapter->pool_config = 0; + } /* Look for an active buffer pool that can hold the new MTU */ - for(i = 0; i<IbmVethNumBufferPools; i++) { + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { adapter->rx_buff_pool[i].active = 1; if (new_mtu_oh < adapter->rx_buff_pool[i].buff_size) { - if (netif_running(adapter->netdev)) { - adapter->pool_config = 1; - ibmveth_close(adapter->netdev); - adapter->pool_config = 0; - dev->mtu = new_mtu; - vio_cmo_set_dev_desired(viodev, - ibmveth_get_desired_dma - (viodev)); - return ibmveth_open(adapter->netdev); - } dev->mtu = new_mtu; vio_cmo_set_dev_desired(viodev, ibmveth_get_desired_dma (viodev)); + if (need_restart) { + return ibmveth_open(adapter->netdev); + } return 0; } } + + if (need_restart && (rc = ibmveth_open(adapter->netdev))) + return rc; + return -EINVAL; } @@ -1192,7 +1328,7 @@ static unsigned long ibmveth_get_desired_dma(struct vio_dev *vdev) ret = IBMVETH_BUFF_LIST_SIZE + IBMVETH_FILT_LIST_SIZE; ret += IOMMU_PAGE_ALIGN(netdev->mtu); - for (i = 0; i < IbmVethNumBufferPools; i++) { + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { /* add the size of the active receive buffers */ if (adapter->rx_buff_pool[i].active) ret += @@ -1221,41 +1357,36 @@ static const struct net_device_ops ibmveth_netdev_ops = { #endif }; -static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) +static int __devinit ibmveth_probe(struct vio_dev *dev, + const struct vio_device_id *id) { int rc, i; - long ret; struct net_device *netdev; struct ibmveth_adapter *adapter; - unsigned long set_attr, ret_attr; - unsigned char *mac_addr_p; unsigned int *mcastFilterSize_p; + dev_dbg(&dev->dev, "entering ibmveth_probe for UA 0x%x\n", + dev->unit_address); - ibmveth_debug_printk_no_adapter("entering ibmveth_probe for UA 0x%x\n", - dev->unit_address); - - mac_addr_p = (unsigned char *) vio_get_attribute(dev, - VETH_MAC_ADDR, NULL); - if(!mac_addr_p) { - printk(KERN_ERR "(%s:%3.3d) ERROR: Can't find VETH_MAC_ADDR " - "attribute\n", __FILE__, __LINE__); - return 0; + mac_addr_p = (unsigned char *)vio_get_attribute(dev, VETH_MAC_ADDR, + NULL); + if (!mac_addr_p) { + dev_err(&dev->dev, "Can't find VETH_MAC_ADDR attribute\n"); + return -EINVAL; } - mcastFilterSize_p = (unsigned int *) vio_get_attribute(dev, + mcastFilterSize_p = (unsigned int *)vio_get_attribute(dev, VETH_MCAST_FILTER_SIZE, NULL); - if(!mcastFilterSize_p) { - printk(KERN_ERR "(%s:%3.3d) ERROR: Can't find " - "VETH_MCAST_FILTER_SIZE attribute\n", - __FILE__, __LINE__); - return 0; + if (!mcastFilterSize_p) { + dev_err(&dev->dev, "Can't find VETH_MCAST_FILTER_SIZE " + "attribute\n"); + return -EINVAL; } netdev = alloc_etherdev(sizeof(struct ibmveth_adapter)); - if(!netdev) + if (!netdev) return -ENOMEM; adapter = netdev_priv(netdev); @@ -1263,19 +1394,19 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_ adapter->vdev = dev; adapter->netdev = netdev; - adapter->mcastFilterSize= *mcastFilterSize_p; + adapter->mcastFilterSize = *mcastFilterSize_p; adapter->pool_config = 0; netif_napi_add(netdev, &adapter->napi, ibmveth_poll, 16); - /* Some older boxes running PHYP non-natively have an OF that - returns a 8-byte local-mac-address field (and the first - 2 bytes have to be ignored) while newer boxes' OF return - a 6-byte field. Note that IEEE 1275 specifies that - local-mac-address must be a 6-byte field. - The RPA doc specifies that the first byte must be 10b, so - we'll just look for it to solve this 8 vs. 6 byte field issue */ - + /* + * Some older boxes running PHYP non-natively have an OF that returns + * a 8-byte local-mac-address field (and the first 2 bytes have to be + * ignored) while newer boxes' OF return a 6-byte field. Note that + * IEEE 1275 specifies that local-mac-address must be a 6-byte field. + * The RPA doc specifies that the first byte must be 10b, so we'll + * just look for it to solve this 8 vs. 6 byte field issue + */ if ((*mac_addr_p & 0x3) != 0x02) mac_addr_p += 2; @@ -1286,12 +1417,11 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_ netdev->netdev_ops = &ibmveth_netdev_ops; netdev->ethtool_ops = &netdev_ethtool_ops; SET_NETDEV_DEV(netdev, &dev->dev); - netdev->features |= NETIF_F_LLTX; - spin_lock_init(&adapter->stats_lock); + netdev->features |= NETIF_F_SG; memcpy(netdev->dev_addr, &adapter->mac_addr, netdev->addr_len); - for(i = 0; i<IbmVethNumBufferPools; i++) { + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { struct kobject *kobj = &adapter->rx_buff_pool[i].kobj; int error; @@ -1304,41 +1434,25 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_ kobject_uevent(kobj, KOBJ_ADD); } - ibmveth_debug_printk("adapter @ 0x%p\n", adapter); + netdev_dbg(netdev, "adapter @ 0x%p\n", adapter); adapter->buffer_list_dma = DMA_ERROR_CODE; adapter->filter_list_dma = DMA_ERROR_CODE; adapter->rx_queue.queue_dma = DMA_ERROR_CODE; - ibmveth_debug_printk("registering netdev...\n"); - - ret = h_illan_attributes(dev->unit_address, 0, 0, &ret_attr); - - if (ret == H_SUCCESS && !(ret_attr & IBMVETH_ILLAN_ACTIVE_TRUNK) && - !(ret_attr & IBMVETH_ILLAN_TRUNK_PRI_MASK) && - (ret_attr & IBMVETH_ILLAN_PADDED_PKT_CSUM)) { - set_attr = IBMVETH_ILLAN_IPV4_TCP_CSUM; - - ret = h_illan_attributes(dev->unit_address, 0, set_attr, &ret_attr); + netdev_dbg(netdev, "registering netdev...\n"); - if (ret == H_SUCCESS) { - adapter->rx_csum = 1; - netdev->features |= NETIF_F_IP_CSUM; - } else - ret = h_illan_attributes(dev->unit_address, set_attr, 0, &ret_attr); - } + ibmveth_set_csum_offload(netdev, 1, ibmveth_set_tx_csum_flags); rc = register_netdev(netdev); - if(rc) { - ibmveth_debug_printk("failed to register netdev rc=%d\n", rc); + if (rc) { + netdev_dbg(netdev, "failed to register netdev rc=%d\n", rc); free_netdev(netdev); return rc; } - ibmveth_debug_printk("registered\n"); - - ibmveth_proc_register_adapter(adapter); + netdev_dbg(netdev, "registered\n"); return 0; } @@ -1349,114 +1463,23 @@ static int __devexit ibmveth_remove(struct vio_dev *dev) struct ibmveth_adapter *adapter = netdev_priv(netdev); int i; - for(i = 0; i<IbmVethNumBufferPools; i++) + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) kobject_put(&adapter->rx_buff_pool[i].kobj); unregister_netdev(netdev); - ibmveth_proc_unregister_adapter(adapter); - free_netdev(netdev); dev_set_drvdata(&dev->dev, NULL); return 0; } -#ifdef CONFIG_PROC_FS -static void ibmveth_proc_register_driver(void) -{ - ibmveth_proc_dir = proc_mkdir(IBMVETH_PROC_DIR, init_net.proc_net); - if (ibmveth_proc_dir) { - } -} - -static void ibmveth_proc_unregister_driver(void) -{ - remove_proc_entry(IBMVETH_PROC_DIR, init_net.proc_net); -} - -static int ibmveth_show(struct seq_file *seq, void *v) -{ - struct ibmveth_adapter *adapter = seq->private; - char *current_mac = (char *) adapter->netdev->dev_addr; - char *firmware_mac = (char *) &adapter->mac_addr; - - seq_printf(seq, "%s %s\n\n", ibmveth_driver_string, ibmveth_driver_version); - - seq_printf(seq, "Unit Address: 0x%x\n", adapter->vdev->unit_address); - seq_printf(seq, "Current MAC: %pM\n", current_mac); - seq_printf(seq, "Firmware MAC: %pM\n", firmware_mac); - - seq_printf(seq, "\nAdapter Statistics:\n"); - seq_printf(seq, " TX: vio_map_single failres: %lld\n", adapter->tx_map_failed); - seq_printf(seq, " send failures: %lld\n", adapter->tx_send_failed); - seq_printf(seq, " RX: replenish task cycles: %lld\n", adapter->replenish_task_cycles); - seq_printf(seq, " alloc_skb_failures: %lld\n", adapter->replenish_no_mem); - seq_printf(seq, " add buffer failures: %lld\n", adapter->replenish_add_buff_failure); - seq_printf(seq, " invalid buffers: %lld\n", adapter->rx_invalid_buffer); - seq_printf(seq, " no buffers: %lld\n", adapter->rx_no_buffer); - - return 0; -} - -static int ibmveth_proc_open(struct inode *inode, struct file *file) -{ - return single_open(file, ibmveth_show, PDE(inode)->data); -} - -static const struct file_operations ibmveth_proc_fops = { - .owner = THIS_MODULE, - .open = ibmveth_proc_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, -}; - -static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter) -{ - struct proc_dir_entry *entry; - if (ibmveth_proc_dir) { - char u_addr[10]; - sprintf(u_addr, "%x", adapter->vdev->unit_address); - entry = proc_create_data(u_addr, S_IFREG, ibmveth_proc_dir, - &ibmveth_proc_fops, adapter); - if (!entry) - ibmveth_error_printk("Cannot create adapter proc entry"); - } -} - -static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter) -{ - if (ibmveth_proc_dir) { - char u_addr[10]; - sprintf(u_addr, "%x", adapter->vdev->unit_address); - remove_proc_entry(u_addr, ibmveth_proc_dir); - } -} - -#else /* CONFIG_PROC_FS */ -static void ibmveth_proc_register_adapter(struct ibmveth_adapter *adapter) -{ -} - -static void ibmveth_proc_unregister_adapter(struct ibmveth_adapter *adapter) -{ -} -static void ibmveth_proc_register_driver(void) -{ -} - -static void ibmveth_proc_unregister_driver(void) -{ -} -#endif /* CONFIG_PROC_FS */ - static struct attribute veth_active_attr; static struct attribute veth_num_attr; static struct attribute veth_size_attr; -static ssize_t veth_pool_show(struct kobject * kobj, - struct attribute * attr, char * buf) +static ssize_t veth_pool_show(struct kobject *kobj, + struct attribute *attr, char *buf) { struct ibmveth_buff_pool *pool = container_of(kobj, struct ibmveth_buff_pool, @@ -1471,8 +1494,8 @@ static ssize_t veth_pool_show(struct kobject * kobj, return 0; } -static ssize_t veth_pool_store(struct kobject * kobj, struct attribute * attr, -const char * buf, size_t count) +static ssize_t veth_pool_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) { struct ibmveth_buff_pool *pool = container_of(kobj, struct ibmveth_buff_pool, @@ -1486,8 +1509,9 @@ const char * buf, size_t count) if (attr == &veth_active_attr) { if (value && !pool->active) { if (netif_running(netdev)) { - if(ibmveth_alloc_buffer_pool(pool)) { - ibmveth_error_printk("unable to alloc pool\n"); + if (ibmveth_alloc_buffer_pool(pool)) { + netdev_err(netdev, + "unable to alloc pool\n"); return -ENOMEM; } pool->active = 1; @@ -1496,14 +1520,15 @@ const char * buf, size_t count) adapter->pool_config = 0; if ((rc = ibmveth_open(netdev))) return rc; - } else + } else { pool->active = 1; + } } else if (!value && pool->active) { int mtu = netdev->mtu + IBMVETH_BUFF_OH; int i; /* Make sure there is a buffer pool with buffers that can hold a packet of the size of the MTU */ - for (i = 0; i < IbmVethNumBufferPools; i++) { + for (i = 0; i < IBMVETH_NUM_BUFF_POOLS; i++) { if (pool == &adapter->rx_buff_pool[i]) continue; if (!adapter->rx_buff_pool[i].active) @@ -1512,8 +1537,8 @@ const char * buf, size_t count) break; } - if (i == IbmVethNumBufferPools) { - ibmveth_error_printk("no active pool >= MTU\n"); + if (i == IBMVETH_NUM_BUFF_POOLS) { + netdev_err(netdev, "no active pool >= MTU\n"); return -EPERM; } @@ -1528,9 +1553,9 @@ const char * buf, size_t count) pool->active = 0; } } else if (attr == &veth_num_attr) { - if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) + if (value <= 0 || value > IBMVETH_MAX_POOL_COUNT) { return -EINVAL; - else { + } else { if (netif_running(netdev)) { adapter->pool_config = 1; ibmveth_close(netdev); @@ -1538,13 +1563,14 @@ const char * buf, size_t count) pool->size = value; if ((rc = ibmveth_open(netdev))) return rc; - } else + } else { pool->size = value; + } } } else if (attr == &veth_size_attr) { - if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) + if (value <= IBMVETH_BUFF_OH || value > IBMVETH_MAX_BUF_SIZE) { return -EINVAL; - else { + } else { if (netif_running(netdev)) { adapter->pool_config = 1; ibmveth_close(netdev); @@ -1552,8 +1578,9 @@ const char * buf, size_t count) pool->buff_size = value; if ((rc = ibmveth_open(netdev))) return rc; - } else + } else { pool->buff_size = value; + } } } @@ -1563,16 +1590,16 @@ const char * buf, size_t count) } -#define ATTR(_name, _mode) \ - struct attribute veth_##_name##_attr = { \ - .name = __stringify(_name), .mode = _mode, \ - }; +#define ATTR(_name, _mode) \ + struct attribute veth_##_name##_attr = { \ + .name = __stringify(_name), .mode = _mode, \ + }; static ATTR(active, 0644); static ATTR(num, 0644); static ATTR(size, 0644); -static struct attribute * veth_pool_attrs[] = { +static struct attribute *veth_pool_attrs[] = { &veth_active_attr, &veth_num_attr, &veth_size_attr, @@ -1597,7 +1624,7 @@ static int ibmveth_resume(struct device *dev) return 0; } -static struct vio_device_id ibmveth_device_table[] __devinitdata= { +static struct vio_device_id ibmveth_device_table[] __devinitdata = { { "network", "IBM,l-lan"}, { "", "" } }; @@ -1621,9 +1648,8 @@ static struct vio_driver ibmveth_driver = { static int __init ibmveth_module_init(void) { - ibmveth_printk("%s: %s %s\n", ibmveth_driver_name, ibmveth_driver_string, ibmveth_driver_version); - - ibmveth_proc_register_driver(); + printk(KERN_DEBUG "%s: %s %s\n", ibmveth_driver_name, + ibmveth_driver_string, ibmveth_driver_version); return vio_register_driver(&ibmveth_driver); } @@ -1631,7 +1657,6 @@ static int __init ibmveth_module_init(void) static void __exit ibmveth_module_exit(void) { vio_unregister_driver(&ibmveth_driver); - ibmveth_proc_unregister_driver(); } module_init(ibmveth_module_init); |