From 0abe791e94033b727f2b55670c2966f3d3d3cf70 Mon Sep 17 00:00:00 2001 From: Santiago Leon Date: Wed, 26 Oct 2005 10:46:53 -0600 Subject: [PATCH] ibmveth fix bonding This patch updates dev->trans_start and dev->last_rx so that the ibmveth driver can be used with the ARP monitor in the bonding driver. Signed-off-by: Santiago Leon Signed-off-by: Jeff Garzik --- drivers/net/ibmveth.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'drivers/net/ibmveth.c') diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index a2c4dd4fb22..5617bec7fd5 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -725,6 +725,7 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) } else { adapter->stats.tx_packets++; adapter->stats.tx_bytes += skb->len; + netdev->trans_start = jiffies; } do { @@ -776,6 +777,7 @@ static int ibmveth_poll(struct net_device *netdev, int *budget) adapter->stats.rx_packets++; adapter->stats.rx_bytes += length; frames_processed++; + netdev->last_rx = jiffies; } } else { more_work = 0; -- cgit v1.2.3 From b6d35182fe62e57d368062adcc880ca35119d88e Mon Sep 17 00:00:00 2001 From: Santiago Leon Date: Wed, 26 Oct 2005 10:47:01 -0600 Subject: [PATCH] ibmveth fix buffer pool management This patch changes the way the ibmveth driver handles the receive buffers. The old code mallocs and maps all the buffers in the pools regardless of MTU size and it also limits the number of buffer pools to three. This patch makes the driver malloc and map the buffers necessary to support the current MTU. It also changes the hardcoded names of the buffer pool number, size, and elements to arrays to make it easier to change (with the hope of making them runtime parameters in the future). Signed-off-by: Santiago Leon Signed-off-by: Jeff Garzik --- drivers/net/ibmveth.c | 102 ++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 74 insertions(+), 28 deletions(-) (limited to 'drivers/net/ibmveth.c') diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index 5617bec7fd5..d985b804a76 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -97,6 +97,7 @@ 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); static inline void ibmveth_schedule_replenishing(struct ibmveth_adapter*); +static inline void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter); #ifdef CONFIG_PROC_FS #define IBMVETH_PROC_DIR "net/ibmveth" @@ -181,6 +182,7 @@ static int ibmveth_alloc_buffer_pool(struct ibmveth_buff_pool *pool) atomic_set(&pool->available, 0); pool->producer_index = 0; pool->consumer_index = 0; + pool->active = 0; return 0; } @@ -258,9 +260,14 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc /* 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)); + int i; + + for(i = 0; i < IbmVethNumBufferPools; i++) + if(adapter->rx_buff_pool[i].active && + (atomic_read(&adapter->rx_buff_pool[i].available) < + adapter->rx_buff_pool[i].threshold)) + return 1; + return 0; } /* kick the replenish tasklet if we need replenishing and it isn't already running */ @@ -275,11 +282,14 @@ static inline void ibmveth_schedule_replenishing(struct ibmveth_adapter *adapter /* replenish tasklet routine */ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) { + int i; + 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]); + 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); @@ -321,6 +331,7 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, struct ibm kfree(pool->skbuff); pool->skbuff = NULL; } + pool->active = 0; } /* remove a buffer from a pool */ @@ -379,6 +390,12 @@ static void ibmveth_rxq_recycle_buffer(struct ibmveth_adapter *adapter) 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.desc = 0; desc.fields.valid = 1; desc.fields.length = adapter->rx_buff_pool[pool].buff_size; @@ -409,6 +426,8 @@ static inline void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter) 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, @@ -443,26 +462,24 @@ static void ibmveth_cleanup(struct ibmveth_adapter *adapter) adapter->rx_queue.queue_addr = NULL; } - ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[0]); - ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[1]); - ibmveth_free_buffer_pool(adapter, &adapter->rx_buff_pool[2]); + for(i = 0; irx_buff_pool[i]); } static int ibmveth_open(struct net_device *netdev) { struct ibmveth_adapter *adapter = netdev->priv; u64 mac_address = 0; - int rxq_entries; + int rxq_entries = 1; unsigned long lpar_rc; int rc; union ibmveth_buf_desc rxq_desc; + int i; ibmveth_debug_printk("open starting\n"); - rxq_entries = - adapter->rx_buff_pool[0].size + - adapter->rx_buff_pool[1].size + - adapter->rx_buff_pool[2].size + 1; + for(i = 0; irx_buff_pool[i].size; adapter->buffer_list_addr = (void*) get_zeroed_page(GFP_KERNEL); adapter->filter_list_addr = (void*) get_zeroed_page(GFP_KERNEL); @@ -502,14 +519,8 @@ static int ibmveth_open(struct net_device *netdev) adapter->rx_queue.num_slots = rxq_entries; adapter->rx_queue.toggle = 1; - if(ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[0]) || - ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[1]) || - ibmveth_alloc_buffer_pool(&adapter->rx_buff_pool[2])) - { - ibmveth_error_printk("unable to allocate buffer pools\n"); - ibmveth_cleanup(adapter); - return -ENOMEM; - } + /* call change_mtu to init the buffer pools based in initial mtu */ + ibmveth_change_mtu(netdev, netdev->mtu); memcpy(&mac_address, netdev->dev_addr, netdev->addr_len); mac_address = mac_address >> 16; @@ -885,17 +896,52 @@ static void ibmveth_set_multicast_list(struct net_device *netdev) static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) { - if ((new_mtu < 68) || (new_mtu > (1<<20))) + struct ibmveth_adapter *adapter = dev->priv; + int i; + int prev_smaller = 1; + + if ((new_mtu < 68) || + (new_mtu > (pool_size[IbmVethNumBufferPools-1]) - IBMVETH_BUFF_OH)) return -EINVAL; + + for(i = 0; i (pool_size[i] - IBMVETH_BUFF_OH)) { + activate = 1; + prev_smaller= 1; + } else { + if (prev_smaller) + activate = 1; + prev_smaller= 0; + } + + if (activate && !adapter->rx_buff_pool[i].active) { + struct ibmveth_buff_pool *pool = + &adapter->rx_buff_pool[i]; + if(ibmveth_alloc_buffer_pool(pool)) { + ibmveth_error_printk("unable to alloc pool\n"); + return -ENOMEM; + } + adapter->rx_buff_pool[i].active = 1; + } else if (!activate && adapter->rx_buff_pool[i].active) { + adapter->rx_buff_pool[i].active = 0; + h_free_logical_lan_buffer(adapter->vdev->unit_address, + (u64)pool_size[i]); + } + + } + + + ibmveth_schedule_replenishing(adapter); dev->mtu = new_mtu; return 0; } static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_id *id) { - int rc; + int rc, i; struct net_device *netdev; - struct ibmveth_adapter *adapter; + struct ibmveth_adapter *adapter = NULL; unsigned char *mac_addr_p; unsigned int *mcastFilterSize_p; @@ -965,9 +1011,9 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_ memcpy(&netdev->dev_addr, &adapter->mac_addr, netdev->addr_len); - ibmveth_init_buffer_pool(&adapter->rx_buff_pool[0], 0, IbmVethPool0DftCnt, IbmVethPool0DftSize); - ibmveth_init_buffer_pool(&adapter->rx_buff_pool[1], 1, IbmVethPool1DftCnt, IbmVethPool1DftSize); - ibmveth_init_buffer_pool(&adapter->rx_buff_pool[2], 2, IbmVethPool2DftCnt, IbmVethPool2DftSize); + for(i = 0; irx_buff_pool[i], i, + pool_count[i], pool_size[i]); ibmveth_debug_printk("adapter @ 0x%p\n", adapter); -- cgit v1.2.3 From e2adbcb480992de8a01acf9218e8bbd9b507fc6f Mon Sep 17 00:00:00 2001 From: Santiago Leon Date: Wed, 26 Oct 2005 10:47:08 -0600 Subject: [PATCH] ibmveth fix buffer replenishing This patch removes the allocation of RX skb's buffers from a workqueue to be called directly at RX processing time. This change was suggested by Dave Miller when the driver was starving the RX buffers and deadlocking under heavy traffic: > Allocating RX SKBs via tasklet is, IMHO, the worst way to > do it. It is no surprise that there are starvation cases. > > If tasklets or work queues get delayed in any way, you lose, > and it's very easy for a card to catch up with the driver RX'ing > packets very fast, no matter how aggressive you make the > replenishing. By the time you detect that you need to be > "more aggressive" it is already too late. > The only pseudo-reliable way is to allocate at RX processing time. > Signed-off-by: Santiago Leon Signed-off-by: Jeff Garzik --- drivers/net/ibmveth.c | 48 ++++++++---------------------------------------- 1 file changed, 8 insertions(+), 40 deletions(-) (limited to 'drivers/net/ibmveth.c') diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index d985b804a76..aea1598b225 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -96,7 +96,6 @@ 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); -static inline void ibmveth_schedule_replenishing(struct ibmveth_adapter*); static inline void ibmveth_rxq_harvest_buffer(struct ibmveth_adapter *adapter); #ifdef CONFIG_PROC_FS @@ -257,29 +256,7 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc atomic_add(buffers_added, &(pool->available)); } -/* check if replenishing is needed. */ -static inline int ibmveth_is_replenishing_needed(struct ibmveth_adapter *adapter) -{ - int i; - - for(i = 0; i < IbmVethNumBufferPools; i++) - if(adapter->rx_buff_pool[i].active && - (atomic_read(&adapter->rx_buff_pool[i].available) < - adapter->rx_buff_pool[i].threshold)) - return 1; - return 0; -} - -/* 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); - } -} - -/* replenish tasklet routine */ +/* replenish routine */ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) { int i; @@ -292,10 +269,6 @@ static void ibmveth_replenish_task(struct ibmveth_adapter *adapter) &adapter->rx_buff_pool[i]); adapter->rx_no_buffer = *(u64*)(((char*)adapter->buffer_list_addr) + 4096 - 8); - - atomic_inc(&adapter->not_replenishing); - - ibmveth_schedule_replenishing(adapter); } /* empty and free ana buffer pool - also used to do cleanup in error paths */ @@ -563,10 +536,10 @@ static int ibmveth_open(struct net_device *netdev) return rc; } - netif_start_queue(netdev); + ibmveth_debug_printk("initial replenish cycle\n"); + ibmveth_replenish_task(adapter); - ibmveth_debug_printk("scheduling initial replenish cycle\n"); - ibmveth_schedule_replenishing(adapter); + netif_start_queue(netdev); ibmveth_debug_printk("open complete\n"); @@ -584,9 +557,6 @@ static int ibmveth_close(struct net_device *netdev) free_irq(netdev->irq, netdev); - cancel_delayed_work(&adapter->replenish_task); - flush_scheduled_work(); - do { lpar_rc = h_free_logical_lan(adapter->vdev->unit_address); } while (H_isLongBusy(lpar_rc) || (lpar_rc == H_Busy)); @@ -795,7 +765,7 @@ static int ibmveth_poll(struct net_device *netdev, int *budget) } } while(more_work && (frames_processed < max_frames_to_process)); - ibmveth_schedule_replenishing(adapter); + ibmveth_replenish_task(adapter); if(more_work) { /* more work to do - return that we are not done yet */ @@ -931,8 +901,10 @@ static int ibmveth_change_mtu(struct net_device *dev, int new_mtu) } + /* kick the interrupt handler so that the new buffer pools get + replenished or deallocated */ + ibmveth_interrupt(dev->irq, dev, NULL); - ibmveth_schedule_replenishing(adapter); dev->mtu = new_mtu; return 0; } @@ -1017,14 +989,10 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_ ibmveth_debug_printk("adapter @ 0x%p\n", adapter); - INIT_WORK(&adapter->replenish_task, (void*)ibmveth_replenish_task, (void*)adapter); - adapter->buffer_list_dma = DMA_ERROR_CODE; adapter->filter_list_dma = DMA_ERROR_CODE; adapter->rx_queue.queue_dma = DMA_ERROR_CODE; - atomic_set(&adapter->not_replenishing, 1); - ibmveth_debug_printk("registering netdev...\n"); rc = register_netdev(netdev); -- cgit v1.2.3 From 60296d9e4be1cd9e096f7804ce6e839e0cbd97cf Mon Sep 17 00:00:00 2001 From: Santiago Leon Date: Wed, 26 Oct 2005 10:47:16 -0600 Subject: [PATCH] ibmveth lockless TX This patch adds the lockless TX feature to the ibmveth driver. The hypervisor has its own locking so the only change that is necessary is to protect the statistics counters. Signed-off-by: Santiago Leon Signed-off-by: Jeff Garzik --- drivers/net/ibmveth.c | 44 +++++++++++++++++++++++++++++--------------- 1 file changed, 29 insertions(+), 15 deletions(-) (limited to 'drivers/net/ibmveth.c') diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index aea1598b225..987bcba0188 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -621,12 +621,18 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) unsigned long lpar_rc; int nfrags = 0, curfrag; 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; + if ((skb_shinfo(skb)->nr_frags + 1) > IbmVethMaxSendFrags) { - adapter->stats.tx_dropped++; - dev_kfree_skb(skb); - return 0; + tx_dropped++; + goto out; } memset(&desc, 0, sizeof(desc)); @@ -645,10 +651,9 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) if(dma_mapping_error(desc[0].fields.address)) { ibmveth_error_printk("tx: unable to map initial fragment\n"); - adapter->tx_map_failed++; - adapter->stats.tx_dropped++; - dev_kfree_skb(skb); - return 0; + tx_map_failed++; + tx_dropped++; + goto out; } curfrag = nfrags; @@ -665,8 +670,8 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) if(dma_mapping_error(desc[curfrag+1].fields.address)) { ibmveth_error_printk("tx: unable to map fragment %d\n", curfrag); - adapter->tx_map_failed++; - adapter->stats.tx_dropped++; + tx_map_failed++; + tx_dropped++; /* Free all the mappings we just created */ while(curfrag < nfrags) { dma_unmap_single(&adapter->vdev->dev, @@ -675,8 +680,7 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) DMA_TO_DEVICE); curfrag++; } - dev_kfree_skb(skb); - return 0; + goto out; } } @@ -701,11 +705,11 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) ibmveth_error_printk("tx: desc[%i] valid=%d, len=%d, address=0x%d\n", i, desc[i].fields.valid, desc[i].fields.length, desc[i].fields.address); } - adapter->tx_send_failed++; - adapter->stats.tx_dropped++; + tx_send_failed++; + tx_dropped++; } else { - adapter->stats.tx_packets++; - adapter->stats.tx_bytes += skb->len; + tx_packets++; + tx_bytes += skb->len; netdev->trans_start = jiffies; } @@ -715,6 +719,14 @@ static int ibmveth_start_xmit(struct sk_buff *skb, struct net_device *netdev) desc[nfrags].fields.length, DMA_TO_DEVICE); } while(--nfrags >= 0); +out: spin_lock_irqsave(&adapter->stats_lock, flags); + adapter->stats.tx_dropped += tx_dropped; + adapter->stats.tx_bytes += tx_bytes; + adapter->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); + dev_kfree_skb(skb); return 0; } @@ -980,6 +992,8 @@ static int __devinit ibmveth_probe(struct vio_dev *dev, const struct vio_device_ netdev->ethtool_ops = &netdev_ethtool_ops; netdev->change_mtu = ibmveth_change_mtu; SET_NETDEV_DEV(netdev, &dev->dev); + netdev->features |= NETIF_F_LLTX; + spin_lock_init(&adapter->stats_lock); memcpy(&netdev->dev_addr, &adapter->mac_addr, netdev->addr_len); -- cgit v1.2.3 From 82702d37a559cf94fe238cd3f8ef63cf7fa699a9 Mon Sep 17 00:00:00 2001 From: Santiago Leon Date: Wed, 26 Oct 2005 10:47:23 -0600 Subject: [PATCH] ibmveth fix failed addbuf This patch fixes a bug that happens when the hypervisor can't add a buffer. The old code wrote IBM_VETH_INVALID_MAP into the free_map array, so next time the index was used, a ibmveth_assert() caught it and called BUG(). The patch writes the right value into the free_map array so that the index can be reused. Signed-off-by: Santiago Leon Signed-off-by: Jeff Garzik --- drivers/net/ibmveth.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'drivers/net/ibmveth.c') diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index 987bcba0188..f5819527ec9 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -237,7 +237,7 @@ static void ibmveth_replenish_buffer_pool(struct ibmveth_adapter *adapter, struc 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->free_map[free_index] = index; pool->skbuff[index] = NULL; pool->consumer_index--; dma_unmap_single(&adapter->vdev->dev, -- cgit v1.2.3 From b4558ea93d66a43f7990d26f145fd4c54a01c9bf Mon Sep 17 00:00:00 2001 From: Jesper Juhl Date: Fri, 28 Oct 2005 16:53:13 -0400 Subject: drivers/net: Remove pointless checks for NULL prior to calling kfree() --- drivers/net/ibmveth.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'drivers/net/ibmveth.c') diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c index f5819527ec9..36da54ad2b7 100644 --- a/drivers/net/ibmveth.c +++ b/drivers/net/ibmveth.c @@ -276,10 +276,8 @@ static void ibmveth_free_buffer_pool(struct ibmveth_adapter *adapter, struct ibm { int i; - if(pool->free_map) { - kfree(pool->free_map); - pool->free_map = NULL; - } + kfree(pool->free_map); + pool->free_map = NULL; if(pool->skbuff && pool->dma_addr) { for(i = 0; i < pool->size; ++i) { -- cgit v1.2.3