X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=drivers%2Fnet%2Fixgb%2Fixgb_main.c;h=a083a9189230d8f0a3dda97f7b3eba485862f1d1;hb=refs%2Fheads%2Fvserver;hp=cfd67d812f0db4094fd86d35e205873d0ac5b5e6;hpb=43bc926fffd92024b46cafaf7350d669ba9ca884;p=linux-2.6.git diff --git a/drivers/net/ixgb/ixgb_main.c b/drivers/net/ixgb/ixgb_main.c index cfd67d812..a083a9189 100644 --- a/drivers/net/ixgb/ixgb_main.c +++ b/drivers/net/ixgb/ixgb_main.c @@ -1,49 +1,33 @@ /******************************************************************************* - - Copyright(c) 1999 - 2005 Intel Corporation. All rights reserved. - - 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 + Intel PRO/10GbE Linux driver + Copyright(c) 1999 - 2006 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope 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. - - The full GNU General Public License is included in this distribution in the - file called LICENSE. - + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + Contact Information: Linux NICS + e1000-devel Mailing List Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 *******************************************************************************/ #include "ixgb.h" -/* Change Log - * 1.0.96 04/19/05 - * - Make needlessly global code static -- bunk@stusta.de - * - ethtool cleanup -- shemminger@osdl.org - * - Support for MODULE_VERSION -- linville@tuxdriver.com - * - add skb_header_cloned check to the tso path -- herbert@apana.org.au - * 1.0.88 01/05/05 - * - include fix to the condition that determines when to quit NAPI - Robert Olsson - * - use netif_poll_{disable/enable} to synchronize between NAPI and i/f up/down - * 1.0.84 10/26/04 - * - reset buffer_info->dma in Tx resource cleanup logic - * 1.0.83 10/12/04 - * - sparse cleanup - shemminger@osdl.org - * - fix tx resource cleanup logic - */ - char ixgb_driver_name[] = "ixgb"; static char ixgb_driver_string[] = "Intel(R) PRO/10GbE Network Driver"; @@ -52,9 +36,9 @@ static char ixgb_driver_string[] = "Intel(R) PRO/10GbE Network Driver"; #else #define DRIVERNAPI "-NAPI" #endif -#define DRV_VERSION "1.0.100-k2"DRIVERNAPI +#define DRV_VERSION "1.0.126-k2"DRIVERNAPI char ixgb_driver_version[] = DRV_VERSION; -static char ixgb_copyright[] = "Copyright (c) 1999-2005 Intel Corporation."; +static char ixgb_copyright[] = "Copyright (c) 1999-2006 Intel Corporation."; /* ixgb_pci_tbl - PCI Device ID Table * @@ -67,6 +51,8 @@ static char ixgb_copyright[] = "Copyright (c) 1999-2005 Intel Corporation."; static struct pci_device_id ixgb_pci_tbl[] = { {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, + {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX_CX4, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX_SR, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, {INTEL_VENDOR_ID, IXGB_DEVICE_ID_82597EX_LR, @@ -107,7 +93,7 @@ static int ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev); static struct net_device_stats *ixgb_get_stats(struct net_device *netdev); static int ixgb_change_mtu(struct net_device *netdev, int new_mtu); static int ixgb_set_mac(struct net_device *netdev, void *p); -static irqreturn_t ixgb_intr(int irq, void *data, struct pt_regs *regs); +static irqreturn_t ixgb_intr(int irq, void *data); static boolean_t ixgb_clean_tx_irq(struct ixgb_adapter *adapter); #ifdef CONFIG_IXGB_NAPI @@ -120,7 +106,7 @@ static boolean_t ixgb_clean_rx_irq(struct ixgb_adapter *adapter); static void ixgb_alloc_rx_buffers(struct ixgb_adapter *adapter); void ixgb_set_ethtool_ops(struct net_device *netdev); static void ixgb_tx_timeout(struct net_device *dev); -static void ixgb_tx_timeout_task(struct net_device *dev); +static void ixgb_tx_timeout_task(struct work_struct *work); static void ixgb_vlan_rx_register(struct net_device *netdev, struct vlan_group *grp); static void ixgb_vlan_rx_add_vid(struct net_device *netdev, uint16_t vid); @@ -132,15 +118,26 @@ static void ixgb_restore_vlan(struct ixgb_adapter *adapter); static void ixgb_netpoll(struct net_device *dev); #endif -/* Exported from other modules */ +static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev, + enum pci_channel_state state); +static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev); +static void ixgb_io_resume (struct pci_dev *pdev); +/* Exported from other modules */ extern void ixgb_check_options(struct ixgb_adapter *adapter); +static struct pci_error_handlers ixgb_err_handler = { + .error_detected = ixgb_io_error_detected, + .slot_reset = ixgb_io_slot_reset, + .resume = ixgb_io_resume, +}; + static struct pci_driver ixgb_driver = { .name = ixgb_driver_name, .id_table = ixgb_pci_tbl, .probe = ixgb_probe, .remove = __devexit_p(ixgb_remove), + .err_handler = &ixgb_err_handler }; MODULE_AUTHOR("Intel Corporation, "); @@ -148,13 +145,18 @@ MODULE_DESCRIPTION("Intel(R) PRO/10GbE Network Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); +#define DEFAULT_DEBUG_LEVEL_SHIFT 3 +static int debug = DEFAULT_DEBUG_LEVEL_SHIFT; +module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); + /* some defines for controlling descriptor fetches in h/w */ -#define RXDCTL_WTHRESH_DEFAULT 16 /* chip writes back at this many or RXT0 */ -#define RXDCTL_PTHRESH_DEFAULT 0 /* chip considers prefech below - * this */ -#define RXDCTL_HTHRESH_DEFAULT 0 /* chip will only prefetch if tail - * is pushed this many descriptors - * from head */ +#define RXDCTL_WTHRESH_DEFAULT 15 /* chip writes back at this many or RXT0 */ +#define RXDCTL_PTHRESH_DEFAULT 0 /* chip considers prefech below + * this */ +#define RXDCTL_HTHRESH_DEFAULT 0 /* chip will only prefetch if tail + * is pushed this many descriptors + * from head */ /** * ixgb_init_module - Driver Registration Routine @@ -171,7 +173,7 @@ ixgb_init_module(void) printk(KERN_INFO "%s\n", ixgb_copyright); - return pci_module_init(&ixgb_driver); + return pci_register_driver(&ixgb_driver); } module_init(ixgb_init_module); @@ -196,7 +198,7 @@ module_exit(ixgb_exit_module); * @adapter: board private structure **/ -static inline void +static void ixgb_irq_disable(struct ixgb_adapter *adapter) { atomic_inc(&adapter->irq_sem); @@ -210,7 +212,7 @@ ixgb_irq_disable(struct ixgb_adapter *adapter) * @adapter: board private structure **/ -static inline void +static void ixgb_irq_enable(struct ixgb_adapter *adapter) { if(atomic_dec_and_test(&adapter->irq_sem)) { @@ -231,6 +233,7 @@ ixgb_up(struct ixgb_adapter *adapter) /* hardware has been reset, we need to reload some things */ + ixgb_rar_set(hw, netdev->dev_addr, 0); ixgb_set_multi(netdev); ixgb_restore_vlan(adapter); @@ -240,6 +243,9 @@ ixgb_up(struct ixgb_adapter *adapter) ixgb_configure_rx(adapter); ixgb_alloc_rx_buffers(adapter); + /* disable interrupts and get the hardware into a known state */ + IXGB_WRITE_REG(&adapter->hw, IMC, 0xffffffff); + #ifdef CONFIG_PCI_MSI { boolean_t pcix = (IXGB_READ_REG(&adapter->hw, STATUS) & @@ -249,7 +255,7 @@ ixgb_up(struct ixgb_adapter *adapter) if (!pcix) adapter->have_msi = FALSE; else if((err = pci_enable_msi(adapter->pdev))) { - printk (KERN_ERR + DPRINTK(PROBE, ERR, "Unable to allocate MSI interrupt Error: %d\n", err); adapter->have_msi = FALSE; /* proceed to try to request regular interrupt */ @@ -258,12 +264,12 @@ ixgb_up(struct ixgb_adapter *adapter) #endif if((err = request_irq(adapter->pdev->irq, &ixgb_intr, - SA_SHIRQ | SA_SAMPLE_RANDOM, - netdev->name, netdev))) + IRQF_SHARED | IRQF_SAMPLE_RANDOM, + netdev->name, netdev))) { + DPRINTK(PROBE, ERR, + "Unable to allocate interrupt Error: %d\n", err); return err; - - /* disable interrupts and get the hardware into a known state */ - IXGB_WRITE_REG(&adapter->hw, IMC, 0xffffffff); + } if((hw->max_frame_size != max_frame) || (hw->max_frame_size != @@ -285,11 +291,12 @@ ixgb_up(struct ixgb_adapter *adapter) } mod_timer(&adapter->watchdog_timer, jiffies); - ixgb_irq_enable(adapter); #ifdef CONFIG_IXGB_NAPI netif_poll_enable(netdev); #endif + ixgb_irq_enable(adapter); + return 0; } @@ -326,7 +333,7 @@ ixgb_reset(struct ixgb_adapter *adapter) ixgb_adapter_stop(&adapter->hw); if(!ixgb_init_hw(&adapter->hw)) - IXGB_DBG("ixgb_init_hw failed.\n"); + DPRINTK(PROBE, ERR, "ixgb_init_hw failed.\n"); } /** @@ -363,7 +370,8 @@ ixgb_probe(struct pci_dev *pdev, } else { if((err = pci_set_dma_mask(pdev, DMA_32BIT_MASK)) || (err = pci_set_consistent_dma_mask(pdev, DMA_32BIT_MASK))) { - IXGB_ERR("No usable DMA configuration, aborting\n"); + printk(KERN_ERR + "ixgb: No usable DMA configuration, aborting\n"); goto err_dma_mask; } pci_using_dac = 0; @@ -388,6 +396,7 @@ ixgb_probe(struct pci_dev *pdev, adapter->netdev = netdev; adapter->pdev = pdev; adapter->hw.back = adapter; + adapter->msg_enable = netif_msg_init(debug, DEFAULT_DEBUG_LEVEL_SHIFT); mmio_start = pci_resource_start(pdev, BAR_0); mmio_len = pci_resource_len(pdev, BAR_0); @@ -416,7 +425,7 @@ ixgb_probe(struct pci_dev *pdev, netdev->change_mtu = &ixgb_change_mtu; ixgb_set_ethtool_ops(netdev); netdev->tx_timeout = &ixgb_tx_timeout; - netdev->watchdog_timeo = HZ; + netdev->watchdog_timeo = 5 * HZ; #ifdef CONFIG_IXGB_NAPI netdev->poll = &ixgb_clean; netdev->weight = 64; @@ -428,6 +437,7 @@ ixgb_probe(struct pci_dev *pdev, netdev->poll_controller = ixgb_netpoll; #endif + strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); netdev->mem_start = mmio_start; netdev->mem_end = mmio_start + mmio_len; netdev->base_addr = adapter->hw.io_base; @@ -449,6 +459,9 @@ ixgb_probe(struct pci_dev *pdev, #ifdef NETIF_F_TSO netdev->features |= NETIF_F_TSO; #endif +#ifdef NETIF_F_LLTX + netdev->features |= NETIF_F_LLTX; +#endif if(pci_using_dac) netdev->features |= NETIF_F_HIGHDMA; @@ -456,7 +469,7 @@ ixgb_probe(struct pci_dev *pdev, /* make sure the EEPROM is good */ if(!ixgb_validate_eeprom_checksum(&adapter->hw)) { - printk(KERN_ERR "The EEPROM Checksum Is Not Valid\n"); + DPRINTK(PROBE, ERR, "The EEPROM Checksum Is Not Valid\n"); err = -EIO; goto err_eeprom; } @@ -465,6 +478,7 @@ ixgb_probe(struct pci_dev *pdev, memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); if(!is_valid_ether_addr(netdev->perm_addr)) { + DPRINTK(PROBE, ERR, "Invalid MAC Address\n"); err = -EIO; goto err_eeprom; } @@ -475,9 +489,9 @@ ixgb_probe(struct pci_dev *pdev, adapter->watchdog_timer.function = &ixgb_watchdog; adapter->watchdog_timer.data = (unsigned long)adapter; - INIT_WORK(&adapter->tx_timeout_task, - (void (*)(void *))ixgb_tx_timeout_task, netdev); + INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task); + strcpy(netdev->name, "eth%d"); if((err = register_netdev(netdev))) goto err_register; @@ -486,8 +500,7 @@ ixgb_probe(struct pci_dev *pdev, netif_carrier_off(netdev); netif_stop_queue(netdev); - printk(KERN_INFO "%s: Intel(R) PRO/10GbE Network Connection\n", - netdev->name); + DPRINTK(PROBE, INFO, "Intel(R) PRO/10GbE Network Connection\n"); ixgb_check_options(adapter); /* reset the hardware with the new settings */ @@ -557,17 +570,17 @@ ixgb_sw_init(struct ixgb_adapter *adapter) hw->subsystem_vendor_id = pdev->subsystem_vendor; hw->subsystem_id = pdev->subsystem_device; - adapter->rx_buffer_len = IXGB_RXBUFFER_2048; - hw->max_frame_size = netdev->mtu + ENET_HEADER_SIZE + ENET_FCS_LENGTH; + adapter->rx_buffer_len = hw->max_frame_size; if((hw->device_id == IXGB_DEVICE_ID_82597EX) - ||(hw->device_id == IXGB_DEVICE_ID_82597EX_LR) - ||(hw->device_id == IXGB_DEVICE_ID_82597EX_SR)) + || (hw->device_id == IXGB_DEVICE_ID_82597EX_CX4) + || (hw->device_id == IXGB_DEVICE_ID_82597EX_LR) + || (hw->device_id == IXGB_DEVICE_ID_82597EX_SR)) hw->mac_type = ixgb_82597; else { /* should never have loaded on this device */ - printk(KERN_ERR "ixgb: unsupported device id\n"); + DPRINTK(PROBE, ERR, "unsupported device id\n"); } /* enable flow control to be programmed */ @@ -665,6 +678,8 @@ ixgb_setup_tx_resources(struct ixgb_adapter *adapter) size = sizeof(struct ixgb_buffer) * txdr->count; txdr->buffer_info = vmalloc(size); if(!txdr->buffer_info) { + DPRINTK(PROBE, ERR, + "Unable to allocate transmit descriptor ring memory\n"); return -ENOMEM; } memset(txdr->buffer_info, 0, size); @@ -677,6 +692,8 @@ ixgb_setup_tx_resources(struct ixgb_adapter *adapter) txdr->desc = pci_alloc_consistent(pdev, txdr->size, &txdr->dma); if(!txdr->desc) { vfree(txdr->buffer_info); + DPRINTK(PROBE, ERR, + "Unable to allocate transmit descriptor memory\n"); return -ENOMEM; } memset(txdr->desc, 0, txdr->size); @@ -750,6 +767,8 @@ ixgb_setup_rx_resources(struct ixgb_adapter *adapter) size = sizeof(struct ixgb_buffer) * rxdr->count; rxdr->buffer_info = vmalloc(size); if(!rxdr->buffer_info) { + DPRINTK(PROBE, ERR, + "Unable to allocate receive descriptor ring\n"); return -ENOMEM; } memset(rxdr->buffer_info, 0, size); @@ -763,6 +782,8 @@ ixgb_setup_rx_resources(struct ixgb_adapter *adapter) if(!rxdr->desc) { vfree(rxdr->buffer_info); + DPRINTK(PROBE, ERR, + "Unable to allocate receive descriptors\n"); return -ENOMEM; } memset(rxdr->desc, 0, rxdr->size); @@ -794,21 +815,14 @@ ixgb_setup_rctl(struct ixgb_adapter *adapter) rctl |= IXGB_RCTL_SECRC; - switch (adapter->rx_buffer_len) { - case IXGB_RXBUFFER_2048: - default: + if (adapter->rx_buffer_len <= IXGB_RXBUFFER_2048) rctl |= IXGB_RCTL_BSIZE_2048; - break; - case IXGB_RXBUFFER_4096: + else if (adapter->rx_buffer_len <= IXGB_RXBUFFER_4096) rctl |= IXGB_RCTL_BSIZE_4096; - break; - case IXGB_RXBUFFER_8192: + else if (adapter->rx_buffer_len <= IXGB_RXBUFFER_8192) rctl |= IXGB_RCTL_BSIZE_8192; - break; - case IXGB_RXBUFFER_16384: + else if (adapter->rx_buffer_len <= IXGB_RXBUFFER_16384) rctl |= IXGB_RCTL_BSIZE_16384; - break; - } IXGB_WRITE_REG(&adapter->hw, RCTL, rctl); } @@ -898,22 +912,25 @@ ixgb_free_tx_resources(struct ixgb_adapter *adapter) adapter->tx_ring.desc = NULL; } -static inline void +static void ixgb_unmap_and_free_tx_resource(struct ixgb_adapter *adapter, struct ixgb_buffer *buffer_info) { struct pci_dev *pdev = adapter->pdev; - if(buffer_info->dma) { - pci_unmap_page(pdev, - buffer_info->dma, - buffer_info->length, - PCI_DMA_TODEVICE); - buffer_info->dma = 0; - } - if(buffer_info->skb) { + + if (buffer_info->dma) + pci_unmap_page(pdev, buffer_info->dma, buffer_info->length, + PCI_DMA_TODEVICE); + + if (buffer_info->skb) dev_kfree_skb_any(buffer_info->skb); - buffer_info->skb = NULL; - } + + buffer_info->skb = NULL; + buffer_info->dma = 0; + buffer_info->time_stamp = 0; + /* these fields must always be initialized in tx + * buffer_info->length = 0; + * buffer_info->next_to_watch = 0; */ } /** @@ -1112,8 +1129,8 @@ ixgb_watchdog(unsigned long data) if(adapter->hw.link_up) { if(!netif_carrier_ok(netdev)) { - printk(KERN_INFO "ixgb: %s NIC Link is Up %d Mbps %s\n", - netdev->name, 10000, "Full Duplex"); + DPRINTK(LINK, INFO, + "NIC Link is Up 10000 Mbps Full Duplex\n"); adapter->link_speed = 10000; adapter->link_duplex = FULL_DUPLEX; netif_carrier_on(netdev); @@ -1123,9 +1140,7 @@ ixgb_watchdog(unsigned long data) if(netif_carrier_ok(netdev)) { adapter->link_speed = 0; adapter->link_duplex = 0; - printk(KERN_INFO - "ixgb: %s NIC Link is Down\n", - netdev->name); + DPRINTK(LINK, INFO, "NIC Link is Down\n"); netif_carrier_off(netdev); netif_stop_queue(netdev); @@ -1158,7 +1173,7 @@ ixgb_watchdog(unsigned long data) #define IXGB_TX_FLAGS_VLAN 0x00000002 #define IXGB_TX_FLAGS_TSO 0x00000004 -static inline int +static int ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) { #ifdef NETIF_F_TSO @@ -1168,7 +1183,8 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) uint16_t ipcse, tucse, mss; int err; - if(likely(skb_shinfo(skb)->tso_size)) { + if (likely(skb_is_gso(skb))) { + struct ixgb_buffer *buffer_info; if (skb_header_cloned(skb)) { err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); if (err) @@ -1176,7 +1192,7 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) } hdr_len = ((skb->h.raw - skb->data) + (skb->h.th->doff << 2)); - mss = skb_shinfo(skb)->tso_size; + mss = skb_shinfo(skb)->gso_size; skb->nh.iph->tot_len = 0; skb->nh.iph->check = 0; skb->h.th->check = ~csum_tcpudp_magic(skb->nh.iph->saddr, @@ -1191,6 +1207,8 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) i = adapter->tx_ring.next_to_use; context_desc = IXGB_CONTEXT_DESC(adapter->tx_ring, i); + buffer_info = &adapter->tx_ring.buffer_info[i]; + WARN_ON(buffer_info->dma != 0); context_desc->ipcss = ipcss; context_desc->ipcso = ipcso; @@ -1220,19 +1238,22 @@ ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) return 0; } -static inline boolean_t +static boolean_t ixgb_tx_csum(struct ixgb_adapter *adapter, struct sk_buff *skb) { struct ixgb_context_desc *context_desc; unsigned int i; uint8_t css, cso; - if(likely(skb->ip_summed == CHECKSUM_HW)) { + if(likely(skb->ip_summed == CHECKSUM_PARTIAL)) { + struct ixgb_buffer *buffer_info; css = skb->h.raw - skb->data; - cso = (skb->h.raw + skb->csum) - skb->data; + cso = css + skb->csum_offset; i = adapter->tx_ring.next_to_use; context_desc = IXGB_CONTEXT_DESC(adapter->tx_ring, i); + buffer_info = &adapter->tx_ring.buffer_info[i]; + WARN_ON(buffer_info->dma != 0); context_desc->tucss = css; context_desc->tucso = cso; @@ -1258,7 +1279,7 @@ ixgb_tx_csum(struct ixgb_adapter *adapter, struct sk_buff *skb) #define IXGB_MAX_TXD_PWR 14 #define IXGB_MAX_DATA_PER_TXD (1<len; unsigned int offset = 0, size, count = 0, i; + unsigned int mss = skb_shinfo(skb)->gso_size; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; unsigned int f; @@ -1276,14 +1298,21 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, while(len) { buffer_info = &tx_ring->buffer_info[i]; - size = min(len, IXGB_MAX_JUMBO_FRAME_SIZE); + size = min(len, IXGB_MAX_DATA_PER_TXD); + /* Workaround for premature desc write-backs + * in TSO mode. Append 4-byte sentinel desc */ + if (unlikely(mss && !nr_frags && size == len && size > 8)) + size -= 4; + buffer_info->length = size; + WARN_ON(buffer_info->dma != 0); buffer_info->dma = pci_map_single(adapter->pdev, skb->data + offset, size, PCI_DMA_TODEVICE); buffer_info->time_stamp = jiffies; + buffer_info->next_to_watch = 0; len -= size; offset += size; @@ -1300,7 +1329,14 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, while(len) { buffer_info = &tx_ring->buffer_info[i]; - size = min(len, IXGB_MAX_JUMBO_FRAME_SIZE); + size = min(len, IXGB_MAX_DATA_PER_TXD); + + /* Workaround for premature desc write-backs + * in TSO mode. Append 4-byte sentinel desc */ + if (unlikely(mss && !nr_frags && size == len + && size > 8)) + size -= 4; + buffer_info->length = size; buffer_info->dma = pci_map_page(adapter->pdev, @@ -1309,6 +1345,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, size, PCI_DMA_TODEVICE); buffer_info->time_stamp = jiffies; + buffer_info->next_to_watch = 0; len -= size; offset += size; @@ -1323,7 +1360,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, return count; } -static inline void +static void ixgb_tx_queue(struct ixgb_adapter *adapter, int count, int vlan_id,int tx_flags) { struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; @@ -1374,11 +1411,43 @@ ixgb_tx_queue(struct ixgb_adapter *adapter, int count, int vlan_id,int tx_flags) IXGB_WRITE_REG(&adapter->hw, TDT, i); } +static int __ixgb_maybe_stop_tx(struct net_device *netdev, int size) +{ + struct ixgb_adapter *adapter = netdev_priv(netdev); + struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; + + netif_stop_queue(netdev); + /* Herbert's original patch had: + * smp_mb__after_netif_stop_queue(); + * but since that doesn't exist yet, just open code it. */ + smp_mb(); + + /* We need to check again in a case another CPU has just + * made room available. */ + if (likely(IXGB_DESC_UNUSED(tx_ring) < size)) + return -EBUSY; + + /* A reprieve! */ + netif_start_queue(netdev); + ++adapter->restart_queue; + return 0; +} + +static int ixgb_maybe_stop_tx(struct net_device *netdev, + struct ixgb_desc_ring *tx_ring, int size) +{ + if (likely(IXGB_DESC_UNUSED(tx_ring) >= size)) + return 0; + return __ixgb_maybe_stop_tx(netdev, size); +} + + /* Tx Descriptors needed, worst case */ #define TXD_USE_COUNT(S) (((S) >> IXGB_MAX_TXD_PWR) + \ (((S) & (IXGB_MAX_DATA_PER_TXD - 1)) ? 1 : 0)) -#define DESC_NEEDED TXD_USE_COUNT(IXGB_MAX_DATA_PER_TXD) + \ - MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1 +#define DESC_NEEDED TXD_USE_COUNT(IXGB_MAX_DATA_PER_TXD) /* skb->date */ + \ + MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1 /* for context */ \ + + 1 /* one more needed for sentinel TSO workaround */ static int ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) @@ -1395,13 +1464,27 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) return 0; } +#ifdef NETIF_F_LLTX + local_irq_save(flags); + if (!spin_trylock(&adapter->tx_lock)) { + /* Collision - tell upper layer to requeue */ + local_irq_restore(flags); + return NETDEV_TX_LOCKED; + } +#else spin_lock_irqsave(&adapter->tx_lock, flags); - if(unlikely(IXGB_DESC_UNUSED(&adapter->tx_ring) < DESC_NEEDED)) { +#endif + + if (unlikely(ixgb_maybe_stop_tx(netdev, &adapter->tx_ring, + DESC_NEEDED))) { netif_stop_queue(netdev); spin_unlock_irqrestore(&adapter->tx_lock, flags); - return 1; + return NETDEV_TX_BUSY; } + +#ifndef NETIF_F_LLTX spin_unlock_irqrestore(&adapter->tx_lock, flags); +#endif if(adapter->vlgrp && vlan_tx_tag_present(skb)) { tx_flags |= IXGB_TX_FLAGS_VLAN; @@ -1413,10 +1496,13 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) tso = ixgb_tso(adapter, skb); if (tso < 0) { dev_kfree_skb_any(skb); +#ifdef NETIF_F_LLTX + spin_unlock_irqrestore(&adapter->tx_lock, flags); +#endif return NETDEV_TX_OK; } - if (tso) + if (likely(tso)) tx_flags |= IXGB_TX_FLAGS_TSO; else if(ixgb_tx_csum(adapter, skb)) tx_flags |= IXGB_TX_FLAGS_CSUM; @@ -1426,7 +1512,14 @@ ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) netdev->trans_start = jiffies; - return 0; +#ifdef NETIF_F_LLTX + /* Make sure there is space in the ring for the next send. */ + ixgb_maybe_stop_tx(netdev, &adapter->tx_ring, DESC_NEEDED); + + spin_unlock_irqrestore(&adapter->tx_lock, flags); + +#endif + return NETDEV_TX_OK; } /** @@ -1444,10 +1537,12 @@ ixgb_tx_timeout(struct net_device *netdev) } static void -ixgb_tx_timeout_task(struct net_device *netdev) +ixgb_tx_timeout_task(struct work_struct *work) { - struct ixgb_adapter *adapter = netdev_priv(netdev); + struct ixgb_adapter *adapter = + container_of(work, struct ixgb_adapter, tx_timeout_task); + adapter->tx_timeout_count++; ixgb_down(adapter, TRUE); ixgb_up(adapter); } @@ -1486,28 +1581,15 @@ ixgb_change_mtu(struct net_device *netdev, int new_mtu) if((max_frame < IXGB_MIN_ENET_FRAME_SIZE_WITHOUT_FCS + ENET_FCS_LENGTH) || (max_frame > IXGB_MAX_JUMBO_FRAME_SIZE + ENET_FCS_LENGTH)) { - IXGB_ERR("Invalid MTU setting\n"); + DPRINTK(PROBE, ERR, "Invalid MTU setting %d\n", new_mtu); return -EINVAL; } - if((max_frame <= IXGB_MAX_ENET_FRAME_SIZE_WITHOUT_FCS + ENET_FCS_LENGTH) - || (max_frame <= IXGB_RXBUFFER_2048)) { - adapter->rx_buffer_len = IXGB_RXBUFFER_2048; - - } else if(max_frame <= IXGB_RXBUFFER_4096) { - adapter->rx_buffer_len = IXGB_RXBUFFER_4096; - - } else if(max_frame <= IXGB_RXBUFFER_8192) { - adapter->rx_buffer_len = IXGB_RXBUFFER_8192; - - } else { - adapter->rx_buffer_len = IXGB_RXBUFFER_16384; - } + adapter->rx_buffer_len = max_frame; netdev->mtu = new_mtu; - if(old_max_frame != max_frame && netif_running(netdev)) { - + if ((old_max_frame != max_frame) && netif_running(netdev)) { ixgb_down(adapter, TRUE); ixgb_up(adapter); } @@ -1524,6 +1606,11 @@ void ixgb_update_stats(struct ixgb_adapter *adapter) { struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + + /* Prevent stats update while adapter is being reset */ + if (pdev->error_state && pdev->error_state != pci_channel_io_normal) + return; if((netdev->flags & IFF_PROMISC) || (netdev->flags & IFF_ALLMULTI) || (netdev->mc_count > IXGB_MAX_NUM_MULTICAST_ADDRESSES)) { @@ -1645,11 +1732,10 @@ ixgb_update_stats(struct ixgb_adapter *adapter) * ixgb_intr - Interrupt Handler * @irq: interrupt number * @data: pointer to a network interface device structure - * @pt_regs: CPU registers structure **/ static irqreturn_t -ixgb_intr(int irq, void *data, struct pt_regs *regs) +ixgb_intr(int irq, void *data) { struct net_device *netdev = data; struct ixgb_adapter *adapter = netdev_priv(netdev); @@ -1765,23 +1851,43 @@ ixgb_clean_tx_irq(struct ixgb_adapter *adapter) tx_ring->next_to_clean = i; - spin_lock(&adapter->tx_lock); - if(cleaned && netif_queue_stopped(netdev) && netif_carrier_ok(netdev) && - (IXGB_DESC_UNUSED(tx_ring) > IXGB_TX_QUEUE_WAKE)) { - - netif_wake_queue(netdev); + if (unlikely(netif_queue_stopped(netdev))) { + spin_lock(&adapter->tx_lock); + if (netif_queue_stopped(netdev) && netif_carrier_ok(netdev) && + (IXGB_DESC_UNUSED(tx_ring) >= DESC_NEEDED)) + netif_wake_queue(netdev); + spin_unlock(&adapter->tx_lock); } - spin_unlock(&adapter->tx_lock); if(adapter->detect_tx_hung) { /* detect a transmit hang in hardware, this serializes the * check with the clearing of time_stamp and movement of i */ adapter->detect_tx_hung = FALSE; - if(tx_ring->buffer_info[i].dma && - time_after(jiffies, tx_ring->buffer_info[i].time_stamp + HZ) + if (tx_ring->buffer_info[eop].dma && + time_after(jiffies, tx_ring->buffer_info[eop].time_stamp + HZ) && !(IXGB_READ_REG(&adapter->hw, STATUS) & - IXGB_STATUS_TXOFF)) + IXGB_STATUS_TXOFF)) { + /* detected Tx unit hang */ + DPRINTK(DRV, ERR, "Detected Tx Unit Hang\n" + " TDH <%x>\n" + " TDT <%x>\n" + " next_to_use <%x>\n" + " next_to_clean <%x>\n" + "buffer_info[next_to_clean]\n" + " time_stamp <%lx>\n" + " next_to_watch <%x>\n" + " jiffies <%lx>\n" + " next_to_watch.status <%x>\n", + IXGB_READ_REG(&adapter->hw, TDH), + IXGB_READ_REG(&adapter->hw, TDT), + tx_ring->next_to_use, + tx_ring->next_to_clean, + tx_ring->buffer_info[eop].time_stamp, + eop, + jiffies, + eop_desc->status); netif_stop_queue(netdev); + } } return cleaned; @@ -1794,7 +1900,7 @@ ixgb_clean_tx_irq(struct ixgb_adapter *adapter) * @sk_buff: socket buffer with received data **/ -static inline void +static void ixgb_rx_checksum(struct ixgb_adapter *adapter, struct ixgb_rx_desc *rx_desc, struct sk_buff *skb) @@ -1858,6 +1964,7 @@ ixgb_clean_rx_irq(struct ixgb_adapter *adapter) #endif status = rx_desc->status; skb = buffer_info->skb; + buffer_info->skb = NULL; prefetch(skb->data); @@ -1902,6 +2009,25 @@ ixgb_clean_rx_irq(struct ixgb_adapter *adapter) goto rxdesc_done; } + /* code added for copybreak, this should improve + * performance for small packets with large amounts + * of reassembly being done in the stack */ +#define IXGB_CB_LENGTH 256 + if (length < IXGB_CB_LENGTH) { + struct sk_buff *new_skb = + netdev_alloc_skb(netdev, length + NET_IP_ALIGN); + if (new_skb) { + skb_reserve(new_skb, NET_IP_ALIGN); + memcpy(new_skb->data - NET_IP_ALIGN, + skb->data - NET_IP_ALIGN, + length + NET_IP_ALIGN); + /* save the skb in buffer_info as good */ + buffer_info->skb = skb; + skb = new_skb; + } + } + /* end copybreak code */ + /* Good Receive */ skb_put(skb, length); @@ -1931,7 +2057,6 @@ ixgb_clean_rx_irq(struct ixgb_adapter *adapter) rxdesc_done: /* clean up descriptor, might be written over by hw */ rx_desc->status = 0; - buffer_info->skb = NULL; /* use prefetched values */ rx_desc = next_rxd; @@ -1971,12 +2096,18 @@ ixgb_alloc_rx_buffers(struct ixgb_adapter *adapter) /* leave three descriptors unused */ while(--cleancount > 2) { - rx_desc = IXGB_RX_DESC(*rx_ring, i); - - skb = dev_alloc_skb(adapter->rx_buffer_len + NET_IP_ALIGN); + /* recycle! its good for you */ + skb = buffer_info->skb; + if (skb) { + skb_trim(skb, 0); + goto map_skb; + } - if(unlikely(!skb)) { + skb = netdev_alloc_skb(netdev, adapter->rx_buffer_len + + NET_IP_ALIGN); + if (unlikely(!skb)) { /* Better luck next round */ + adapter->alloc_rx_buff_failed++; break; } @@ -1986,37 +2117,38 @@ ixgb_alloc_rx_buffers(struct ixgb_adapter *adapter) */ skb_reserve(skb, NET_IP_ALIGN); - skb->dev = netdev; - buffer_info->skb = skb; buffer_info->length = adapter->rx_buffer_len; - buffer_info->dma = - pci_map_single(pdev, - skb->data, - adapter->rx_buffer_len, - PCI_DMA_FROMDEVICE); +map_skb: + buffer_info->dma = pci_map_single(pdev, + skb->data, + adapter->rx_buffer_len, + PCI_DMA_FROMDEVICE); + rx_desc = IXGB_RX_DESC(*rx_ring, i); rx_desc->buff_addr = cpu_to_le64(buffer_info->dma); /* guarantee DD bit not set now before h/w gets descriptor * this is the rest of the workaround for h/w double * writeback. */ rx_desc->status = 0; - if((i & ~(num_group_tail_writes- 1)) == i) { - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). */ - wmb(); - - IXGB_WRITE_REG(&adapter->hw, RDT, i); - } if(++i == rx_ring->count) i = 0; buffer_info = &rx_ring->buffer_info[i]; } - rx_ring->next_to_use = i; + if (likely(rx_ring->next_to_use != i)) { + rx_ring->next_to_use = i; + if (unlikely(i-- == 0)) + i = (rx_ring->count - 1); + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, such + * as IA-64). */ + wmb(); + IXGB_WRITE_REG(&adapter->hw, RDT, i); + } } /** @@ -2122,12 +2254,106 @@ ixgb_restore_vlan(struct ixgb_adapter *adapter) static void ixgb_netpoll(struct net_device *dev) { - struct ixgb_adapter *adapter = dev->priv; + struct ixgb_adapter *adapter = netdev_priv(dev); disable_irq(adapter->pdev->irq); - ixgb_intr(adapter->pdev->irq, dev, NULL); + ixgb_intr(adapter->pdev->irq, dev); enable_irq(adapter->pdev->irq); } #endif +/** + * ixgb_io_error_detected() - called when PCI error is detected + * @pdev pointer to pci device with error + * @state pci channel state after error + * + * This callback is called by the PCI subsystem whenever + * a PCI bus error is detected. + */ +static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev, + enum pci_channel_state state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgb_adapter *adapter = netdev_priv(netdev); + + if(netif_running(netdev)) + ixgb_down(adapter, TRUE); + + pci_disable_device(pdev); + + /* Request a slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * ixgb_io_slot_reset - called after the pci bus has been reset. + * @pdev pointer to pci device with error + * + * This callback is called after the PCI buss has been reset. + * Basically, this tries to restart the card from scratch. + * This is a shortened version of the device probe/discovery code, + * it resembles the first-half of the ixgb_probe() routine. + */ +static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgb_adapter *adapter = netdev_priv(netdev); + + if(pci_enable_device(pdev)) { + DPRINTK(PROBE, ERR, "Cannot re-enable PCI device after reset.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + + /* Perform card reset only on one instance of the card */ + if (0 != PCI_FUNC (pdev->devfn)) + return PCI_ERS_RESULT_RECOVERED; + + pci_set_master(pdev); + + netif_carrier_off(netdev); + netif_stop_queue(netdev); + ixgb_reset(adapter); + + /* Make sure the EEPROM is good */ + if(!ixgb_validate_eeprom_checksum(&adapter->hw)) { + DPRINTK(PROBE, ERR, "After reset, the EEPROM checksum is not valid.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + ixgb_get_ee_mac_addr(&adapter->hw, netdev->dev_addr); + memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); + + if(!is_valid_ether_addr(netdev->perm_addr)) { + DPRINTK(PROBE, ERR, "After reset, invalid MAC address.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * ixgb_io_resume - called when its OK to resume normal operations + * @pdev pointer to pci device with error + * + * The error recovery driver tells us that its OK to resume + * normal operation. Implementation resembles the second-half + * of the ixgb_probe() routine. + */ +static void ixgb_io_resume (struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgb_adapter *adapter = netdev_priv(netdev); + + pci_set_master(pdev); + + if(netif_running(netdev)) { + if(ixgb_up(adapter)) { + printk ("ixgb: can't bring device back up after reset\n"); + return; + } + } + + netif_device_attach(netdev); + mod_timer(&adapter->watchdog_timer, jiffies); +} + /* ixgb_main.c */