diff options
98 files changed, 2850 insertions, 1167 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index 5b3f31f..5378511 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -312,3 +312,15 @@ When: 2.6.26 Why: Implementation became generic; users should now include linux/semaphore.h instead. Who: Matthew Wilcox <willy@linux.intel.com> + +--------------------------- + +What: SCTP_GET_PEER_ADDRS_NUM_OLD, SCTP_GET_PEER_ADDRS_OLD, + SCTP_GET_LOCAL_ADDRS_NUM_OLD, SCTP_GET_LOCAL_ADDRS_OLD +When: June 2009 +Why: A newer version of the options have been introduced in 2005 that + removes the limitions of the old API. The sctp library has been + converted to use these new options at the same time. Any user + space app that directly uses the old options should convert to using + the new options. +Who: Vlad Yasevich <vladislav.yasevich@hp.com> diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 17a6e46..72f6d52 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -548,8 +548,9 @@ icmp_echo_ignore_broadcasts - BOOLEAN icmp_ratelimit - INTEGER Limit the maximal rates for sending ICMP packets whose type matches icmp_ratemask (see below) to specific targets. - 0 to disable any limiting, otherwise the maximal rate in jiffies(1) - Default: 100 + 0 to disable any limiting, + otherwise the minimal space between responses in milliseconds. + Default: 1000 icmp_ratemask - INTEGER Mask made of ICMP types for which rates are being limited. @@ -1024,11 +1025,23 @@ max_addresses - INTEGER autoconfigured addresses. Default: 16 +disable_ipv6 - BOOLEAN + Disable IPv6 operation. + Default: FALSE (enable IPv6 operation) + +accept_dad - INTEGER + Whether to accept DAD (Duplicate Address Detection). + 0: Disable DAD + 1: Enable DAD (default) + 2: Enable DAD, and disable IPv6 operation if MAC-based duplicate + link-local address has been found. + icmp/*: ratelimit - INTEGER Limit the maximal rates for sending ICMPv6 packets. - 0 to disable any limiting, otherwise the maximal rate in jiffies(1) - Default: 100 + 0 to disable any limiting, + otherwise the minimal space between responses in milliseconds. + Default: 1000 IPv6 Update by: diff --git a/drivers/char/pcmcia/synclink_cs.c b/drivers/char/pcmcia/synclink_cs.c index 1dd0e99..fb2fb15 100644 --- a/drivers/char/pcmcia/synclink_cs.c +++ b/drivers/char/pcmcia/synclink_cs.c @@ -3886,9 +3886,8 @@ static bool rx_get_frame(MGSLPC_INFO *info) framesize = 0; #if SYNCLINK_GENERIC_HDLC { - struct net_device_stats *stats = hdlc_stats(info->netdev); - stats->rx_errors++; - stats->rx_frame_errors++; + info->netdev->stats.rx_errors++; + info->netdev->stats.rx_frame_errors++; } #endif } else @@ -4144,7 +4143,6 @@ static int hdlcdev_attach(struct net_device *dev, unsigned short encoding, static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) { MGSLPC_INFO *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; if (debug_level >= DEBUG_LEVEL_INFO) @@ -4159,8 +4157,8 @@ static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) info->tx_put = info->tx_count = skb->len; /* update network statistics */ - stats->tx_packets++; - stats->tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; /* done with socket buffer, so free it */ dev_kfree_skb(skb); @@ -4376,14 +4374,13 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void hdlcdev_tx_timeout(struct net_device *dev) { MGSLPC_INFO *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; if (debug_level >= DEBUG_LEVEL_INFO) printk("hdlcdev_tx_timeout(%s)\n",dev->name); - stats->tx_errors++; - stats->tx_aborted_errors++; + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; spin_lock_irqsave(&info->lock,flags); tx_stop(info); @@ -4416,27 +4413,26 @@ static void hdlcdev_rx(MGSLPC_INFO *info, char *buf, int size) { struct sk_buff *skb = dev_alloc_skb(size); struct net_device *dev = info->netdev; - struct net_device_stats *stats = hdlc_stats(dev); if (debug_level >= DEBUG_LEVEL_INFO) printk("hdlcdev_rx(%s)\n",dev->name); if (skb == NULL) { printk(KERN_NOTICE "%s: can't alloc skb, dropping packet\n", dev->name); - stats->rx_dropped++; + dev->stats.rx_dropped++; return; } - memcpy(skb_put(skb, size),buf,size); + memcpy(skb_put(skb, size), buf, size); - skb->protocol = hdlc_type_trans(skb, info->netdev); + skb->protocol = hdlc_type_trans(skb, dev); - stats->rx_packets++; - stats->rx_bytes += size; + dev->stats.rx_packets++; + dev->stats.rx_bytes += size; netif_rx(skb); - info->netdev->last_rx = jiffies; + dev->last_rx = jiffies; } /** diff --git a/drivers/char/synclink.c b/drivers/char/synclink.c index ac5080d..9d247d8 100644 --- a/drivers/char/synclink.c +++ b/drivers/char/synclink.c @@ -6640,9 +6640,8 @@ static bool mgsl_get_rx_frame(struct mgsl_struct *info) framesize = 0; #if SYNCLINK_GENERIC_HDLC { - struct net_device_stats *stats = hdlc_stats(info->netdev); - stats->rx_errors++; - stats->rx_frame_errors++; + info->netdev->stats.rx_errors++; + info->netdev->stats.rx_frame_errors++; } #endif } else @@ -7753,7 +7752,6 @@ static int hdlcdev_attach(struct net_device *dev, unsigned short encoding, static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) { struct mgsl_struct *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; if (debug_level >= DEBUG_LEVEL_INFO) @@ -7767,8 +7765,8 @@ static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) mgsl_load_tx_dma_buffer(info, skb->data, skb->len); /* update network statistics */ - stats->tx_packets++; - stats->tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; /* done with socket buffer, so free it */ dev_kfree_skb(skb); @@ -7984,14 +7982,13 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void hdlcdev_tx_timeout(struct net_device *dev) { struct mgsl_struct *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; if (debug_level >= DEBUG_LEVEL_INFO) printk("hdlcdev_tx_timeout(%s)\n",dev->name); - stats->tx_errors++; - stats->tx_aborted_errors++; + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; spin_lock_irqsave(&info->irq_spinlock,flags); usc_stop_transmitter(info); @@ -8024,27 +8021,27 @@ static void hdlcdev_rx(struct mgsl_struct *info, char *buf, int size) { struct sk_buff *skb = dev_alloc_skb(size); struct net_device *dev = info->netdev; - struct net_device_stats *stats = hdlc_stats(dev); if (debug_level >= DEBUG_LEVEL_INFO) - printk("hdlcdev_rx(%s)\n",dev->name); + printk("hdlcdev_rx(%s)\n", dev->name); if (skb == NULL) { - printk(KERN_NOTICE "%s: can't alloc skb, dropping packet\n", dev->name); - stats->rx_dropped++; + printk(KERN_NOTICE "%s: can't alloc skb, dropping packet\n", + dev->name); + dev->stats.rx_dropped++; return; } - memcpy(skb_put(skb, size),buf,size); + memcpy(skb_put(skb, size), buf, size); - skb->protocol = hdlc_type_trans(skb, info->netdev); + skb->protocol = hdlc_type_trans(skb, dev); - stats->rx_packets++; - stats->rx_bytes += size; + dev->stats.rx_packets++; + dev->stats.rx_bytes += size; netif_rx(skb); - info->netdev->last_rx = jiffies; + dev->last_rx = jiffies; } /** diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c index 55c1653..d88a607 100644 --- a/drivers/char/synclink_gt.c +++ b/drivers/char/synclink_gt.c @@ -1544,7 +1544,6 @@ static int hdlcdev_attach(struct net_device *dev, unsigned short encoding, static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) { struct slgt_info *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; DBGINFO(("%s hdlc_xmit\n", dev->name)); @@ -1557,8 +1556,8 @@ static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) tx_load(info, skb->data, skb->len); /* update network statistics */ - stats->tx_packets++; - stats->tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; /* done with socket buffer, so free it */ dev_kfree_skb(skb); @@ -1775,13 +1774,12 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void hdlcdev_tx_timeout(struct net_device *dev) { struct slgt_info *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; DBGINFO(("%s hdlcdev_tx_timeout\n", dev->name)); - stats->tx_errors++; - stats->tx_aborted_errors++; + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; spin_lock_irqsave(&info->lock,flags); tx_stop(info); @@ -1814,26 +1812,25 @@ static void hdlcdev_rx(struct slgt_info *info, char *buf, int size) { struct sk_buff *skb = dev_alloc_skb(size); struct net_device *dev = info->netdev; - struct net_device_stats *stats = hdlc_stats(dev); DBGINFO(("%s hdlcdev_rx\n", dev->name)); if (skb == NULL) { DBGERR(("%s: can't alloc skb, drop packet\n", dev->name)); - stats->rx_dropped++; + dev->stats.rx_dropped++; return; } - memcpy(skb_put(skb, size),buf,size); + memcpy(skb_put(skb, size), buf, size); - skb->protocol = hdlc_type_trans(skb, info->netdev); + skb->protocol = hdlc_type_trans(skb, dev); - stats->rx_packets++; - stats->rx_bytes += size; + dev->stats.rx_packets++; + dev->stats.rx_bytes += size; netif_rx(skb); - info->netdev->last_rx = jiffies; + dev->last_rx = jiffies; } /** @@ -4577,9 +4574,8 @@ check_again: #if SYNCLINK_GENERIC_HDLC if (framesize == 0) { - struct net_device_stats *stats = hdlc_stats(info->netdev); - stats->rx_errors++; - stats->rx_frame_errors++; + info->netdev->stats.rx_errors++; + info->netdev->stats.rx_frame_errors++; } #endif diff --git a/drivers/char/synclinkmp.c b/drivers/char/synclinkmp.c index bec54866..10241ed 100644 --- a/drivers/char/synclinkmp.c +++ b/drivers/char/synclinkmp.c @@ -1678,7 +1678,6 @@ static int hdlcdev_attach(struct net_device *dev, unsigned short encoding, static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) { SLMP_INFO *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; if (debug_level >= DEBUG_LEVEL_INFO) @@ -1692,8 +1691,8 @@ static int hdlcdev_xmit(struct sk_buff *skb, struct net_device *dev) tx_load_dma_buffer(info, skb->data, skb->len); /* update network statistics */ - stats->tx_packets++; - stats->tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; /* done with socket buffer, so free it */ dev_kfree_skb(skb); @@ -1909,14 +1908,13 @@ static int hdlcdev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static void hdlcdev_tx_timeout(struct net_device *dev) { SLMP_INFO *info = dev_to_port(dev); - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; if (debug_level >= DEBUG_LEVEL_INFO) printk("hdlcdev_tx_timeout(%s)\n",dev->name); - stats->tx_errors++; - stats->tx_aborted_errors++; + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; spin_lock_irqsave(&info->lock,flags); tx_stop(info); @@ -1949,27 +1947,27 @@ static void hdlcdev_rx(SLMP_INFO *info, char *buf, int size) { struct sk_buff *skb = dev_alloc_skb(size); struct net_device *dev = info->netdev; - struct net_device_stats *stats = hdlc_stats(dev); if (debug_level >= DEBUG_LEVEL_INFO) printk("hdlcdev_rx(%s)\n",dev->name); if (skb == NULL) { - printk(KERN_NOTICE "%s: can't alloc skb, dropping packet\n", dev->name); - stats->rx_dropped++; + printk(KERN_NOTICE "%s: can't alloc skb, dropping packet\n", + dev->name); + dev->stats.rx_dropped++; return; } - memcpy(skb_put(skb, size),buf,size); + memcpy(skb_put(skb, size), buf, size); - skb->protocol = hdlc_type_trans(skb, info->netdev); + skb->protocol = hdlc_type_trans(skb, dev); - stats->rx_packets++; - stats->rx_bytes += size; + dev->stats.rx_packets++; + dev->stats.rx_bytes += size; netif_rx(skb); - info->netdev->last_rx = jiffies; + dev->last_rx = jiffies; } /** @@ -4983,9 +4981,8 @@ CheckAgain: framesize = 0; #if SYNCLINK_GENERIC_HDLC { - struct net_device_stats *stats = hdlc_stats(info->netdev); - stats->rx_errors++; - stats->rx_frame_errors++; + info->netdev->stats.rx_errors++; + info->netdev->stats.rx_frame_errors++; } #endif } diff --git a/drivers/net/3c503.c b/drivers/net/3c503.c index 9c23336..900b0ff 100644 --- a/drivers/net/3c503.c +++ b/drivers/net/3c503.c @@ -149,7 +149,7 @@ el2_pio_probe(struct net_device *dev) #ifndef MODULE struct net_device * __init el2_probe(int unit) { - struct net_device *dev = alloc_ei_netdev(); + struct net_device *dev = alloc_eip_netdev(); int err; if (!dev) @@ -340,7 +340,7 @@ el2_probe1(struct net_device *dev, int ioaddr) dev->stop = &el2_close; dev->ethtool_ops = &netdev_ethtool_ops; #ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ei_poll; + dev->poll_controller = eip_poll; #endif retval = register_netdev(dev); @@ -386,7 +386,7 @@ el2_open(struct net_device *dev) outb_p(0x00, E33G_IDCFR); if (*irqp == probe_irq_off(cookie) /* It's a good IRQ line! */ && ((retval = request_irq(dev->irq = *irqp, - ei_interrupt, 0, dev->name, dev)) == 0)) + eip_interrupt, 0, dev->name, dev)) == 0)) break; } } while (*++irqp); @@ -395,13 +395,13 @@ el2_open(struct net_device *dev) return retval; } } else { - if ((retval = request_irq(dev->irq, ei_interrupt, 0, dev->name, dev))) { + if ((retval = request_irq(dev->irq, eip_interrupt, 0, dev->name, dev))) { return retval; } } el2_init_card(dev); - ei_open(dev); + eip_open(dev); return 0; } @@ -412,7 +412,7 @@ el2_close(struct net_device *dev) dev->irq = ei_status.saved_irq; outb(EGACFR_IRQOFF, E33G_GACFR); /* disable interrupts. */ - ei_close(dev); + eip_close(dev); return 0; } @@ -698,7 +698,7 @@ init_module(void) if (this_dev != 0) break; /* only autoprobe 1st one */ printk(KERN_NOTICE "3c503.c: Presently autoprobing (not recommended) for a single card.\n"); } - dev = alloc_ei_netdev(); + dev = alloc_eip_netdev(); if (!dev) break; dev->irq = irq[this_dev]; diff --git a/drivers/net/8390.h b/drivers/net/8390.h index cf020d4..8e209f5 100644 --- a/drivers/net/8390.h +++ b/drivers/net/8390.h @@ -30,8 +30,10 @@ extern int ei_debug; #ifdef CONFIG_NET_POLL_CONTROLLER extern void ei_poll(struct net_device *dev); +extern void eip_poll(struct net_device *dev); #endif +/* Without I/O delay - non ISA or later chips */ extern void NS8390_init(struct net_device *dev, int startp); extern int ei_open(struct net_device *dev); extern int ei_close(struct net_device *dev); @@ -42,6 +44,17 @@ static inline struct net_device *alloc_ei_netdev(void) return __alloc_ei_netdev(0); } +/* With I/O delay form */ +extern void NS8390p_init(struct net_device *dev, int startp); +extern int eip_open(struct net_device *dev); +extern int eip_close(struct net_device *dev); +extern irqreturn_t eip_interrupt(int irq, void *dev_id); +extern struct net_device *__alloc_eip_netdev(int size); +static inline struct net_device *alloc_eip_netdev(void) +{ + return __alloc_eip_netdev(0); +} + /* You have one of these per-board */ struct ei_device { const char *name; @@ -115,13 +128,14 @@ struct ei_device { /* * Only generate indirect loads given a machine that needs them. * - removed AMIGA_PCMCIA from this list, handled as ISA io now + * - the _p for generates no delay by default 8390p.c overrides this. */ #ifndef ei_inb #define ei_inb(_p) inb(_p) #define ei_outb(_v,_p) outb(_v,_p) -#define ei_inb_p(_p) inb_p(_p) -#define ei_outb_p(_v,_p) outb_p(_v,_p) +#define ei_inb_p(_p) inb(_p) +#define ei_outb_p(_v,_p) outb(_v,_p) #endif #ifndef EI_SHIFT diff --git a/drivers/net/8390p.c b/drivers/net/8390p.c new file mode 100644 index 0000000..71f1988 --- /dev/null +++ b/drivers/net/8390p.c @@ -0,0 +1,66 @@ +/* 8390 core for ISA devices needing bus delays */ + +static const char version[] = + "8390p.c:v1.10cvs 9/23/94 Donald Becker (becker@cesdis.gsfc.nasa.gov)\n"; + +#define ei_inb(_p) inb(_p) +#define ei_outb(_v,_p) outb(_v,_p) +#define ei_inb_p(_p) inb_p(_p) +#define ei_outb_p(_v,_p) outb_p(_v,_p) + +#include "lib8390.c" + +int eip_open(struct net_device *dev) +{ + return __ei_open(dev); +} + +int eip_close(struct net_device *dev) +{ + return __ei_close(dev); +} + +irqreturn_t eip_interrupt(int irq, void *dev_id) +{ + return __ei_interrupt(irq, dev_id); +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +void eip_poll(struct net_device *dev) +{ + __ei_poll(dev); +} +#endif + +struct net_device *__alloc_eip_netdev(int size) +{ + return ____alloc_ei_netdev(size); +} + +void NS8390p_init(struct net_device *dev, int startp) +{ + return __NS8390_init(dev, startp); +} + +EXPORT_SYMBOL(eip_open); +EXPORT_SYMBOL(eip_close); +EXPORT_SYMBOL(eip_interrupt); +#ifdef CONFIG_NET_POLL_CONTROLLER +EXPORT_SYMBOL(eip_poll); +#endif +EXPORT_SYMBOL(NS8390p_init); +EXPORT_SYMBOL(__alloc_eip_netdev); + +#if defined(MODULE) + +int init_module(void) +{ + return 0; +} + +void cleanup_module(void) +{ +} + +#endif /* MODULE */ +MODULE_LICENSE("GPL"); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index d85b9d0..8492591 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -2122,27 +2122,13 @@ config R8169 To compile this driver as a module, choose M here: the module will be called r8169. This is recommended. -config R8169_NAPI - bool "Use Rx Polling (NAPI) (EXPERIMENTAL)" - depends on R8169 && EXPERIMENTAL - help - NAPI is a new driver API designed to reduce CPU and interrupt load - when the driver is receiving lots of packets from the card. It is - still somewhat experimental and thus not yet enabled by default. - - If your estimated Rx load is 10kpps or more, or if the card will be - deployed on potentially unfriendly networks (e.g. in a firewall), - then say Y here. - - If in doubt, say N. - config R8169_VLAN bool "VLAN support" depends on R8169 && VLAN_8021Q ---help--- Say Y here for the r8169 driver to support the functions required by the kernel 802.1Q code. - + If in doubt, say Y. config SB1250_MAC diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 87703ff..4beb043 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -106,11 +106,11 @@ ifeq ($(CONFIG_FEC_MPC52xx_MDIO),y) endif obj-$(CONFIG_68360_ENET) += 68360enet.o obj-$(CONFIG_WD80x3) += wd.o 8390.o -obj-$(CONFIG_EL2) += 3c503.o 8390.o -obj-$(CONFIG_NE2000) += ne.o 8390.o -obj-$(CONFIG_NE2_MCA) += ne2.o 8390.o -obj-$(CONFIG_HPLAN) += hp.o 8390.o -obj-$(CONFIG_HPLAN_PLUS) += hp-plus.o 8390.o +obj-$(CONFIG_EL2) += 3c503.o 8390p.o +obj-$(CONFIG_NE2000) += ne.o 8390p.o +obj-$(CONFIG_NE2_MCA) += ne2.o 8390p.o +obj-$(CONFIG_HPLAN) += hp.o 8390p.o +obj-$(CONFIG_HPLAN_PLUS) += hp-plus.o 8390p.o obj-$(CONFIG_ULTRA) += smc-ultra.o 8390.o obj-$(CONFIG_ULTRAMCA) += smc-mca.o 8390.o obj-$(CONFIG_ULTRA32) += smc-ultra32.o 8390.o diff --git a/drivers/net/hp.c b/drivers/net/hp.c index c649a80..8281209 100644 --- a/drivers/net/hp.c +++ b/drivers/net/hp.c @@ -103,7 +103,7 @@ static int __init do_hp_probe(struct net_device *dev) #ifndef MODULE struct net_device * __init hp_probe(int unit) { - struct net_device *dev = alloc_ei_netdev(); + struct net_device *dev = alloc_eip_netdev(); int err; if (!dev) @@ -176,7 +176,7 @@ static int __init hp_probe1(struct net_device *dev, int ioaddr) outb_p(irqmap[irq] | HP_RUN, ioaddr + HP_CONFIGURE); outb_p( 0x00 | HP_RUN, ioaddr + HP_CONFIGURE); if (irq == probe_irq_off(cookie) /* It's a good IRQ line! */ - && request_irq (irq, ei_interrupt, 0, DRV_NAME, dev) == 0) { + && request_irq (irq, eip_interrupt, 0, DRV_NAME, dev) == 0) { printk(" selecting IRQ %d.\n", irq); dev->irq = *irqp; break; @@ -191,7 +191,7 @@ static int __init hp_probe1(struct net_device *dev, int ioaddr) } else { if (dev->irq == 2) dev->irq = 9; - if ((retval = request_irq(dev->irq, ei_interrupt, 0, DRV_NAME, dev))) { + if ((retval = request_irq(dev->irq, eip_interrupt, 0, DRV_NAME, dev))) { printk (" unable to get IRQ %d.\n", dev->irq); goto out; } @@ -202,7 +202,7 @@ static int __init hp_probe1(struct net_device *dev, int ioaddr) dev->open = &hp_open; dev->stop = &hp_close; #ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ei_poll; + dev->poll_controller = eip_poll; #endif ei_status.name = name; @@ -231,14 +231,14 @@ out: static int hp_open(struct net_device *dev) { - ei_open(dev); + eip_open(dev); return 0; } static int hp_close(struct net_device *dev) { - ei_close(dev); + eip_close(dev); return 0; } @@ -421,7 +421,7 @@ init_module(void) if (this_dev != 0) break; /* only autoprobe 1st one */ printk(KERN_NOTICE "hp.c: Presently autoprobing (not recommended) for a single card.\n"); } - dev = alloc_ei_netdev(); + dev = alloc_eip_netdev(); if (!dev) break; dev->irq = irq[this_dev]; diff --git a/drivers/net/igb/e1000_82575.c b/drivers/net/igb/e1000_82575.c index cda3ec8..2c8b910 100644 --- a/drivers/net/igb/e1000_82575.c +++ b/drivers/net/igb/e1000_82575.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007 Intel Corporation. + Copyright(c) 2007 - 2008 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, @@ -171,6 +171,10 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw) * for setting word_size. */ size += NVM_WORD_SIZE_BASE_SHIFT; + + /* EEPROM access above 16k is unsupported */ + if (size > 14) + size = 14; nvm->word_size = 1 << size; /* setup PHY parameters */ @@ -222,7 +226,7 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw) } /** - * e1000_acquire_phy_82575 - Acquire rights to access PHY + * igb_acquire_phy_82575 - Acquire rights to access PHY * @hw: pointer to the HW structure * * Acquire access rights to the correct PHY. This is a @@ -238,7 +242,7 @@ static s32 igb_acquire_phy_82575(struct e1000_hw *hw) } /** - * e1000_release_phy_82575 - Release rights to access PHY + * igb_release_phy_82575 - Release rights to access PHY * @hw: pointer to the HW structure * * A wrapper to release access rights to the correct PHY. This is a @@ -253,7 +257,7 @@ static void igb_release_phy_82575(struct e1000_hw *hw) } /** - * e1000_read_phy_reg_sgmii_82575 - Read PHY register using sgmii + * igb_read_phy_reg_sgmii_82575 - Read PHY register using sgmii * @hw: pointer to the HW structure * @offset: register offset to be read * @data: pointer to the read data @@ -268,7 +272,7 @@ static s32 igb_read_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, u32 i, i2ccmd = 0; if (offset > E1000_MAX_SGMII_PHY_REG_ADDR) { - hw_dbg(hw, "PHY Address %u is out of range\n", offset); + hw_dbg("PHY Address %u is out of range\n", offset); return -E1000_ERR_PARAM; } @@ -291,11 +295,11 @@ static s32 igb_read_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, break; } if (!(i2ccmd & E1000_I2CCMD_READY)) { - hw_dbg(hw, "I2CCMD Read did not complete\n"); + hw_dbg("I2CCMD Read did not complete\n"); return -E1000_ERR_PHY; } if (i2ccmd & E1000_I2CCMD_ERROR) { - hw_dbg(hw, "I2CCMD Error bit set\n"); + hw_dbg("I2CCMD Error bit set\n"); return -E1000_ERR_PHY; } @@ -306,7 +310,7 @@ static s32 igb_read_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, } /** - * e1000_write_phy_reg_sgmii_82575 - Write PHY register using sgmii + * igb_write_phy_reg_sgmii_82575 - Write PHY register using sgmii * @hw: pointer to the HW structure * @offset: register offset to write to * @data: data to write at register offset @@ -322,7 +326,7 @@ static s32 igb_write_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, u16 phy_data_swapped; if (offset > E1000_MAX_SGMII_PHY_REG_ADDR) { - hw_dbg(hw, "PHY Address %d is out of range\n", offset); + hw_dbg("PHY Address %d is out of range\n", offset); return -E1000_ERR_PARAM; } @@ -349,11 +353,11 @@ static s32 igb_write_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, break; } if (!(i2ccmd & E1000_I2CCMD_READY)) { - hw_dbg(hw, "I2CCMD Write did not complete\n"); + hw_dbg("I2CCMD Write did not complete\n"); return -E1000_ERR_PHY; } if (i2ccmd & E1000_I2CCMD_ERROR) { - hw_dbg(hw, "I2CCMD Error bit set\n"); + hw_dbg("I2CCMD Error bit set\n"); return -E1000_ERR_PHY; } @@ -361,10 +365,10 @@ static s32 igb_write_phy_reg_sgmii_82575(struct e1000_hw *hw, u32 offset, } /** - * e1000_get_phy_id_82575 - Retreive PHY addr and id + * igb_get_phy_id_82575 - Retrieve PHY addr and id * @hw: pointer to the HW structure * - * Retreives the PHY address and ID for both PHY's which do and do not use + * Retrieves the PHY address and ID for both PHY's which do and do not use * sgmi interface. **/ static s32 igb_get_phy_id_82575(struct e1000_hw *hw) @@ -393,9 +397,8 @@ static s32 igb_get_phy_id_82575(struct e1000_hw *hw) for (phy->addr = 1; phy->addr < 8; phy->addr++) { ret_val = igb_read_phy_reg_sgmii_82575(hw, PHY_ID1, &phy_id); if (ret_val == 0) { - hw_dbg(hw, "Vendor ID 0x%08X read at address %u\n", - phy_id, - phy->addr); + hw_dbg("Vendor ID 0x%08X read at address %u\n", + phy_id, phy->addr); /* * At the time of this writing, The M88 part is * the only supported SGMII PHY product. @@ -403,8 +406,7 @@ static s32 igb_get_phy_id_82575(struct e1000_hw *hw) if (phy_id == M88_VENDOR) break; } else { - hw_dbg(hw, "PHY address %u was unreadable\n", - phy->addr); + hw_dbg("PHY address %u was unreadable\n", phy->addr); } } @@ -422,7 +424,7 @@ out: } /** - * e1000_phy_hw_reset_sgmii_82575 - Performs a PHY reset + * igb_phy_hw_reset_sgmii_82575 - Performs a PHY reset * @hw: pointer to the HW structure * * Resets the PHY using the serial gigabit media independent interface. @@ -436,7 +438,7 @@ static s32 igb_phy_hw_reset_sgmii_82575(struct e1000_hw *hw) * available to us at this time. */ - hw_dbg(hw, "Soft resetting SGMII attached PHY...\n"); + hw_dbg("Soft resetting SGMII attached PHY...\n"); /* * SFP documentation requires the following to configure the SPF module @@ -453,7 +455,7 @@ out: } /** - * e1000_set_d0_lplu_state_82575 - Set Low Power Linkup D0 state + * igb_set_d0_lplu_state_82575 - Set Low Power Linkup D0 state * @hw: pointer to the HW structure * @active: true to enable LPLU, false to disable * @@ -471,34 +473,29 @@ static s32 igb_set_d0_lplu_state_82575(struct e1000_hw *hw, bool active) s32 ret_val; u16 data; - ret_val = hw->phy.ops.read_phy_reg(hw, IGP02E1000_PHY_POWER_MGMT, - &data); + ret_val = phy->ops.read_phy_reg(hw, IGP02E1000_PHY_POWER_MGMT, &data); if (ret_val) goto out; if (active) { data |= IGP02E1000_PM_D0_LPLU; - ret_val = hw->phy.ops.write_phy_reg(hw, - IGP02E1000_PHY_POWER_MGMT, - data); + ret_val = phy->ops.write_phy_reg(hw, IGP02E1000_PHY_POWER_MGMT, + data); if (ret_val) goto out; /* When LPLU is enabled, we should disable SmartSpeed */ - ret_val = hw->phy.ops.read_phy_reg(hw, - IGP01E1000_PHY_PORT_CONFIG, - &data); + ret_val = phy->ops.read_phy_reg(hw, IGP01E1000_PHY_PORT_CONFIG, + &data); data &= ~IGP01E1000_PSCFR_SMART_SPEED; - ret_val = hw->phy.ops.write_phy_reg(hw, - IGP01E1000_PHY_PORT_CONFIG, - data); + ret_val = phy->ops.write_phy_reg(hw, IGP01E1000_PHY_PORT_CONFIG, + data); if (ret_val) goto out; } else { data &= ~IGP02E1000_PM_D0_LPLU; - ret_val = hw->phy.ops.write_phy_reg(hw, - IGP02E1000_PHY_POWER_MGMT, - data); + ret_val = phy->ops.write_phy_reg(hw, IGP02E1000_PHY_POWER_MGMT, + data); /* * LPLU and SmartSpeed are mutually exclusive. LPLU is used * during Dx states where the power conservation is most @@ -506,29 +503,25 @@ static s32 igb_set_d0_lplu_state_82575(struct e1000_hw *hw, bool active) * SmartSpeed, so performance is maintained. */ if (phy->smart_speed == e1000_smart_speed_on) { - ret_val = hw->phy.ops.read_phy_reg(hw, - IGP01E1000_PHY_PORT_CONFIG, - &data); + ret_val = phy->ops.read_phy_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, &data); if (ret_val) goto out; data |= IGP01E1000_PSCFR_SMART_SPEED; - ret_val = hw->phy.ops.write_phy_reg(hw, - IGP01E1000_PHY_PORT_CONFIG, - data); + ret_val = phy->ops.write_phy_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, data); if (ret_val) goto out; } else if (phy->smart_speed == e1000_smart_speed_off) { - ret_val = hw->phy.ops.read_phy_reg(hw, - IGP01E1000_PHY_PORT_CONFIG, - &data); + ret_val = phy->ops.read_phy_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, &data); if (ret_val) goto out; data &= ~IGP01E1000_PSCFR_SMART_SPEED; - ret_val = hw->phy.ops.write_phy_reg(hw, - IGP01E1000_PHY_PORT_CONFIG, - data); + ret_val = phy->ops.write_phy_reg(hw, + IGP01E1000_PHY_PORT_CONFIG, data); if (ret_val) goto out; } @@ -539,10 +532,10 @@ out: } /** - * e1000_acquire_nvm_82575 - Request for access to EEPROM + * igb_acquire_nvm_82575 - Request for access to EEPROM * @hw: pointer to the HW structure * - * Acquire the necessary semaphores for exclussive access to the EEPROM. + * Acquire the necessary semaphores for exclusive access to the EEPROM. * Set the EEPROM access request bit and wait for EEPROM access grant bit. * Return successful if access grant bit set, else clear the request for * EEPROM access and return -E1000_ERR_NVM (-1). @@ -565,7 +558,7 @@ out: } /** - * e1000_release_nvm_82575 - Release exclusive access to EEPROM + * igb_release_nvm_82575 - Release exclusive access to EEPROM * @hw: pointer to the HW structure * * Stop any current commands to the EEPROM and clear the EEPROM request bit, @@ -578,7 +571,7 @@ static void igb_release_nvm_82575(struct e1000_hw *hw) } /** - * e1000_acquire_swfw_sync_82575 - Acquire SW/FW semaphore + * igb_acquire_swfw_sync_82575 - Acquire SW/FW semaphore * @hw: pointer to the HW structure * @mask: specifies which semaphore to acquire * @@ -613,7 +606,7 @@ static s32 igb_acquire_swfw_sync_82575(struct e1000_hw *hw, u16 mask) } if (i == timeout) { - hw_dbg(hw, "Can't access resource, SW_FW_SYNC timeout.\n"); + hw_dbg("Driver can't access resource, SW_FW_SYNC timeout.\n"); ret_val = -E1000_ERR_SWFW_SYNC; goto out; } @@ -628,7 +621,7 @@ out: } /** - * e1000_release_swfw_sync_82575 - Release SW/FW semaphore + * igb_release_swfw_sync_82575 - Release SW/FW semaphore * @hw: pointer to the HW structure * @mask: specifies which semaphore to acquire * @@ -650,7 +643,7 @@ static void igb_release_swfw_sync_82575(struct e1000_hw *hw, u16 mask) } /** - * e1000_get_cfg_done_82575 - Read config done bit + * igb_get_cfg_done_82575 - Read config done bit * @hw: pointer to the HW structure * * Read the management control register for the config done bit for @@ -675,7 +668,7 @@ static s32 igb_get_cfg_done_82575(struct e1000_hw *hw) timeout--; } if (!timeout) - hw_dbg(hw, "MNG configuration cycle has not completed.\n"); + hw_dbg("MNG configuration cycle has not completed.\n"); /* If EEPROM is not marked present, init the PHY manually */ if (((rd32(E1000_EECD) & E1000_EECD_PRES) == 0) && @@ -686,7 +679,7 @@ static s32 igb_get_cfg_done_82575(struct e1000_hw *hw) } /** - * e1000_check_for_link_82575 - Check for link + * igb_check_for_link_82575 - Check for link * @hw: pointer to the HW structure * * If sgmii is enabled, then use the pcs register to determine link, otherwise @@ -709,12 +702,12 @@ static s32 igb_check_for_link_82575(struct e1000_hw *hw) } /** - * e1000_get_pcs_speed_and_duplex_82575 - Retrieve current speed/duplex + * igb_get_pcs_speed_and_duplex_82575 - Retrieve current speed/duplex * @hw: pointer to the HW structure * @speed: stores the current speed * @duplex: stores the current duplex * - * Using the physical coding sub-layer (PCS), retreive the current speed and + * Using the physical coding sub-layer (PCS), retrieve the current speed and * duplex, then store the values in the pointers provided. **/ static s32 igb_get_pcs_speed_and_duplex_82575(struct e1000_hw *hw, u16 *speed, @@ -764,7 +757,7 @@ static s32 igb_get_pcs_speed_and_duplex_82575(struct e1000_hw *hw, u16 *speed, } /** - * e1000_rar_set_82575 - Set receive address register + * igb_rar_set_82575 - Set receive address register * @hw: pointer to the HW structure * @addr: pointer to the receive address * @index: receive address array register @@ -781,7 +774,7 @@ static void igb_rar_set_82575(struct e1000_hw *hw, u8 *addr, u32 index) } /** - * e1000_reset_hw_82575 - Reset hardware + * igb_reset_hw_82575 - Reset hardware * @hw: pointer to the HW structure * * This resets the hardware into a known state. This is a @@ -798,9 +791,9 @@ static s32 igb_reset_hw_82575(struct e1000_hw *hw) */ ret_val = igb_disable_pcie_master(hw); if (ret_val) - hw_dbg(hw, "PCI-E Master disable polling has failed.\n"); + hw_dbg("PCI-E Master disable polling has failed.\n"); - hw_dbg(hw, "Masking off all interrupts\n"); + hw_dbg("Masking off all interrupts\n"); wr32(E1000_IMC, 0xffffffff); wr32(E1000_RCTL, 0); @@ -811,7 +804,7 @@ static s32 igb_reset_hw_82575(struct e1000_hw *hw) ctrl = rd32(E1000_CTRL); - hw_dbg(hw, "Issuing a global reset to MAC\n"); + hw_dbg("Issuing a global reset to MAC\n"); wr32(E1000_CTRL, ctrl | E1000_CTRL_RST); ret_val = igb_get_auto_rd_done(hw); @@ -821,7 +814,7 @@ static s32 igb_reset_hw_82575(struct e1000_hw *hw) * return with an error. This can happen in situations * where there is no eeprom and prevents getting link. */ - hw_dbg(hw, "Auto Read Done did not complete\n"); + hw_dbg("Auto Read Done did not complete\n"); } /* If EEPROM is not present, run manual init scripts */ @@ -838,7 +831,7 @@ static s32 igb_reset_hw_82575(struct e1000_hw *hw) } /** - * e1000_init_hw_82575 - Initialize hardware + * igb_init_hw_82575 - Initialize hardware * @hw: pointer to the HW structure * * This inits the hardware readying it for operation. @@ -852,18 +845,18 @@ static s32 igb_init_hw_82575(struct e1000_hw *hw) /* Initialize identification LED */ ret_val = igb_id_led_init(hw); if (ret_val) { - hw_dbg(hw, "Error initializing identification LED\n"); + hw_dbg("Error initializing identification LED\n"); /* This is not fatal and we should not stop init due to this */ } /* Disabling VLAN filtering */ - hw_dbg(hw, "Initializing the IEEE VLAN\n"); + hw_dbg("Initializing the IEEE VLAN\n"); igb_clear_vfta(hw); /* Setup the receive address */ igb_init_rx_addrs(hw, rar_count); /* Zero out the Multicast HASH table */ - hw_dbg(hw, "Zeroing the MTA\n"); + hw_dbg("Zeroing the MTA\n"); for (i = 0; i < mac->mta_reg_count; i++) array_wr32(E1000_MTA, i, 0); @@ -882,7 +875,7 @@ static s32 igb_init_hw_82575(struct e1000_hw *hw) } /** - * e1000_setup_copper_link_82575 - Configure copper link settings + * igb_setup_copper_link_82575 - Configure copper link settings * @hw: pointer to the HW structure * * Configures the link for auto-neg or forced speed and duplex. Then we check @@ -933,10 +926,10 @@ static s32 igb_setup_copper_link_82575(struct e1000_hw *hw) * PHY will be set to 10H, 10F, 100H or 100F * depending on user settings. */ - hw_dbg(hw, "Forcing Speed and Duplex\n"); + hw_dbg("Forcing Speed and Duplex\n"); ret_val = igb_phy_force_speed_duplex(hw); if (ret_val) { - hw_dbg(hw, "Error Forcing Speed and Duplex\n"); + hw_dbg("Error Forcing Speed and Duplex\n"); goto out; } } @@ -949,20 +942,17 @@ static s32 igb_setup_copper_link_82575(struct e1000_hw *hw) * Check link status. Wait up to 100 microseconds for link to become * valid. */ - ret_val = igb_phy_has_link(hw, - COPPER_LINK_UP_LIMIT, - 10, - &link); + ret_val = igb_phy_has_link(hw, COPPER_LINK_UP_LIMIT, 10, &link); if (ret_val) goto out; if (link) { - hw_dbg(hw, "Valid link established!!!\n"); + hw_dbg("Valid link established!!!\n"); /* Config the MAC and PHY after link is up */ igb_config_collision_dist(hw); ret_val = igb_config_fc_after_link_up(hw); } else { - hw_dbg(hw, "Unable to establish link!!!\n"); + hw_dbg("Unable to establish link!!!\n"); } out: @@ -970,7 +960,7 @@ out: } /** - * e1000_setup_fiber_serdes_link_82575 - Setup link for fiber/serdes + * igb_setup_fiber_serdes_link_82575 - Setup link for fiber/serdes * @hw: pointer to the HW structure * * Configures speed and duplex for fiber and serdes links. @@ -1018,7 +1008,7 @@ static s32 igb_setup_fiber_serdes_link_82575(struct e1000_hw *hw) E1000_PCS_LCTL_FDV_FULL | /* SerDes Full duplex */ E1000_PCS_LCTL_AN_ENABLE | /* Enable Autoneg */ E1000_PCS_LCTL_AN_RESTART; /* Restart autoneg */ - hw_dbg(hw, "Configuring Autoneg; PCS_LCTL = 0x%08X\n", reg); + hw_dbg("Configuring Autoneg; PCS_LCTL = 0x%08X\n", reg); } else { /* Set PCS register for forced speed */ reg |= E1000_PCS_LCTL_FLV_LINK_UP | /* Force link up */ @@ -1026,7 +1016,7 @@ static s32 igb_setup_fiber_serdes_link_82575(struct e1000_hw *hw) E1000_PCS_LCTL_FDV_FULL | /* SerDes Full duplex */ E1000_PCS_LCTL_FSD | /* Force Speed */ E1000_PCS_LCTL_FORCE_LINK; /* Force Link */ - hw_dbg(hw, "Configuring Forced Link; PCS_LCTL = 0x%08X\n", reg); + hw_dbg("Configuring Forced Link; PCS_LCTL = 0x%08X\n", reg); } wr32(E1000_PCS_LCTL, reg); @@ -1034,7 +1024,7 @@ static s32 igb_setup_fiber_serdes_link_82575(struct e1000_hw *hw) } /** - * e1000_configure_pcs_link_82575 - Configure PCS link + * igb_configure_pcs_link_82575 - Configure PCS link * @hw: pointer to the HW structure * * Configure the physical coding sub-layer (PCS) link. The PCS link is @@ -1067,7 +1057,7 @@ static s32 igb_configure_pcs_link_82575(struct e1000_hw *hw) */ reg |= E1000_PCS_LCTL_AN_RESTART | E1000_PCS_LCTL_AN_ENABLE; } else { - /* Set PCS regiseter for forced speed */ + /* Set PCS register for forced speed */ /* Turn off bits for full duplex, speed, and autoneg */ reg &= ~(E1000_PCS_LCTL_FSV_1000 | @@ -1088,8 +1078,7 @@ static s32 igb_configure_pcs_link_82575(struct e1000_hw *hw) E1000_PCS_LCTL_FORCE_LINK | E1000_PCS_LCTL_FLV_LINK_UP; - hw_dbg(hw, - "Wrote 0x%08X to PCS_LCTL to configure forced link\n", + hw_dbg("Wrote 0x%08X to PCS_LCTL to configure forced link\n", reg); } wr32(E1000_PCS_LCTL, reg); @@ -1099,7 +1088,7 @@ out: } /** - * e1000_sgmii_active_82575 - Return sgmii state + * igb_sgmii_active_82575 - Return sgmii state * @hw: pointer to the HW structure * * 82575 silicon has a serialized gigabit media independent interface (sgmii) @@ -1125,7 +1114,7 @@ out: } /** - * e1000_reset_init_script_82575 - Inits HW defaults after reset + * igb_reset_init_script_82575 - Inits HW defaults after reset * @hw: pointer to the HW structure * * Inits recommended HW defaults after a reset when there is no EEPROM @@ -1134,7 +1123,7 @@ out: static s32 igb_reset_init_script_82575(struct e1000_hw *hw) { if (hw->mac.type == e1000_82575) { - hw_dbg(hw, "Running reset init script for 82575\n"); + hw_dbg("Running reset init script for 82575\n"); /* SerDes configuration via SERDESCTRL */ igb_write_8bit_ctrl_reg(hw, E1000_SCTL, 0x00, 0x0C); igb_write_8bit_ctrl_reg(hw, E1000_SCTL, 0x01, 0x78); @@ -1161,7 +1150,7 @@ static s32 igb_reset_init_script_82575(struct e1000_hw *hw) } /** - * e1000_read_mac_addr_82575 - Read device MAC address + * igb_read_mac_addr_82575 - Read device MAC address * @hw: pointer to the HW structure **/ static s32 igb_read_mac_addr_82575(struct e1000_hw *hw) @@ -1175,7 +1164,7 @@ static s32 igb_read_mac_addr_82575(struct e1000_hw *hw) } /** - * e1000_clear_hw_cntrs_82575 - Clear device specific hardware counters + * igb_clear_hw_cntrs_82575 - Clear device specific hardware counters * @hw: pointer to the HW structure * * Clears the hardware counters by reading the counter registers. @@ -1238,6 +1227,79 @@ static void igb_clear_hw_cntrs_82575(struct e1000_hw *hw) temp = rd32(E1000_SCVPC); } +/** + * igb_rx_fifo_flush_82575 - Clean rx fifo after RX enable + * @hw: pointer to the HW structure + * + * After rx enable if managability is enabled then there is likely some + * bad data at the start of the fifo and possibly in the DMA fifo. This + * function clears the fifos and flushes any packets that came in as rx was + * being enabled. + **/ +void igb_rx_fifo_flush_82575(struct e1000_hw *hw) +{ + u32 rctl, rlpml, rxdctl[4], rfctl, temp_rctl, rx_enabled; + int i, ms_wait; + + if (hw->mac.type != e1000_82575 || + !(rd32(E1000_MANC) & E1000_MANC_RCV_TCO_EN)) + return; + + /* Disable all RX queues */ + for (i = 0; i < 4; i++) { + rxdctl[i] = rd32(E1000_RXDCTL(i)); + wr32(E1000_RXDCTL(i), + rxdctl[i] & ~E1000_RXDCTL_QUEUE_ENABLE); + } + /* Poll all queues to verify they have shut down */ + for (ms_wait = 0; ms_wait < 10; ms_wait++) { + msleep(1); + rx_enabled = 0; + for (i = 0; i < 4; i++) + rx_enabled |= rd32(E1000_RXDCTL(i)); + if (!(rx_enabled & E1000_RXDCTL_QUEUE_ENABLE)) + break; + } + + if (ms_wait == 10) + hw_dbg("Queue disable timed out after 10ms\n"); + + /* Clear RLPML, RCTL.SBP, RFCTL.LEF, and set RCTL.LPE so that all + * incoming packets are rejected. Set enable and wait 2ms so that + * any packet that was coming in as RCTL.EN was set is flushed + */ + rfctl = rd32(E1000_RFCTL); + wr32(E1000_RFCTL, rfctl & ~E1000_RFCTL_LEF); + + rlpml = rd32(E1000_RLPML); + wr32(E1000_RLPML, 0); + + rctl = rd32(E1000_RCTL); + temp_rctl = rctl & ~(E1000_RCTL_EN | E1000_RCTL_SBP); + temp_rctl |= E1000_RCTL_LPE; + + wr32(E1000_RCTL, temp_rctl); + wr32(E1000_RCTL, temp_rctl | E1000_RCTL_EN); + wrfl(); + msleep(2); + + /* Enable RX queues that were previously enabled and restore our + * previous state + */ + for (i = 0; i < 4; i++) + wr32(E1000_RXDCTL(i), rxdctl[i]); + wr32(E1000_RCTL, rctl); + wrfl(); + + wr32(E1000_RLPML, rlpml); + wr32(E1000_RFCTL, rfctl); + + /* Flush receive errors generated by workaround */ + rd32(E1000_ROC); + rd32(E1000_RNBC); + rd32(E1000_MPC); +} + static struct e1000_mac_operations e1000_mac_ops_82575 = { .reset_hw = igb_reset_hw_82575, .init_hw = igb_init_hw_82575, diff --git a/drivers/net/igb/e1000_82575.h b/drivers/net/igb/e1000_82575.h index 76ea846..d78ad33 100644 --- a/drivers/net/igb/e1000_82575.h +++ b/drivers/net/igb/e1000_82575.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007 Intel Corporation. + Copyright(c) 2007 - 2008 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, @@ -28,6 +28,8 @@ #ifndef _E1000_82575_H_ #define _E1000_82575_H_ +extern void igb_rx_fifo_flush_82575(struct e1000_hw *hw); + #define E1000_RAR_ENTRIES_82575 16 /* SRRCTL bit definitions */ @@ -56,7 +58,7 @@ #define E1000_EIMS_RX_QUEUE E1000_EICR_RX_QUEUE #define E1000_EIMS_TX_QUEUE E1000_EICR_TX_QUEUE -/* Immediate Interrupt RX (A.K.A. Low Latency Interrupt) */ +/* Immediate Interrupt Rx (A.K.A. Low Latency Interrupt) */ /* Receive Descriptor - Advanced */ union e1000_adv_rx_desc { @@ -145,6 +147,6 @@ struct e1000_adv_tx_context_desc { -#define E1000_DCA_TXCTRL_TX_WB_RO_EN (1 << 11) /* TX Desc writeback RO bit */ +#define E1000_DCA_TXCTRL_TX_WB_RO_EN (1 << 11) /* Tx Desc writeback RO bit */ #endif diff --git a/drivers/net/igb/e1000_defines.h b/drivers/net/igb/e1000_defines.h index 8da9ffe..ed748dc 100644 --- a/drivers/net/igb/e1000_defines.h +++ b/drivers/net/igb/e1000_defines.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel(R) Gigabit Ethernet Linux driver - Copyright(c) 2007 Intel Corporation. + Copyright(c) 2007 - 2008 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, @@ -91,12 +91,12 @@ #define E1000_MAX_SGMII_PHY_REG_ADDR 255 #define E1000_I2CCMD_PHY_TIMEOUT 200 -/* Receive Decriptor bit definitions */ +/* Receive Descriptor bit definitions */ #define E1000_RXD_STAT_DD 0x01 /* Descriptor Done */ #define E1000_RXD_STAT_EOP 0x02 /* End of Packet */ #define E1000_RXD_STAT_IXSM 0x04 /* Ignore checksum */ #define E1000_RXD_STAT_VP 0x08 /* IEEE VLAN Packet */ -#define E1000_RXD_STAT_UDPCS 0x10 /* UDP xsum caculated */ +#define E1000_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ #define E1000_RXD_STAT_TCPCS 0x20 /* TCP xsum calculated */ #define E1000_RXD_STAT_DYNINT 0x800 /* Pkt caused INT via DYNINT */ #define E1000_RXD_ERR_CE 0x01 /* CRC Error */ @@ -340,6 +340,7 @@ #define E1000_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */ /* Header split receive */ +#define E1000_RFCTL_LEF 0x00040000 /* Collision related configuration parameters */ #define E1000_COLLISION_THRESHOLD 15 @@ -379,7 +380,7 @@ #define E1000_ICR_RXO 0x00000040 /* rx overrun */ #define E1000_ICR_RXT0 0x00000080 /* rx timer intr (ring 0) */ #define E1000_ICR_MDAC 0x00000200 /* MDIO access complete */ -#define E1000_ICR_RXCFG 0x00000400 /* RX /c/ ordered set */ +#define E1000_ICR_RXCFG 0x00000400 /* Rx /c/ ordered set */ #define E1000_ICR_GPI_EN0 0x00000800 /* GP Int 0 */ #define E1000_ICR_GPI_EN1 0x00001000 /* GP Int 1 */ #define E1000_ICR_GPI_EN2 0x00002000 /* GP Int 2 */ @@ -443,12 +444,6 @@ #define E1000_IMS_RXSEQ E1000_ICR_RXSEQ /* rx sequence error */ #define E1000_IMS_RXDMT0 E1000_ICR_RXDMT0 /* rx desc min. threshold */ #define E1000_IMS_RXT0 E1000_ICR_RXT0 /* rx timer intr */ -/* queue 0 Rx descriptor FIFO parity error */ -/* queue 0 Tx descriptor FIFO parity error */ -/* host arb read buffer parity error */ -/* packet buffer parity error */ -/* queue 1 Rx descriptor FIFO parity error */ -/* queue 1 Tx descriptor FIFO parity error */ /* Extended Interrupt Mask Set */ #define E1000_EIMS_TCP_TIMER E1000_EICR_TCP_TIMER /* TCP Timer */ @@ -457,12 +452,6 @@ /* Interrupt Cause Set */ #define E1000_ICS_LSC E1000_ICR_LSC /* Link Status Change */ #define E1000_ICS_RXDMT0 E1000_ICR_RXDMT0 /* rx desc min. threshold */ -/* queue 0 Rx descriptor FIFO parity error */ -/* queue 0 Tx descriptor FIFO parity error */ -/* host arb read buffer parity error */ -/* packet buffer parity error */ -/* queue 1 Rx descriptor FIFO parity error */ -/* queue 1 Tx descriptor FIFO parity error */ /* Extended Interrupt Cause Set */ @@ -567,7 +556,6 @@ /* 1000BASE-T Control Register */ #define CR_1000T_HD_CAPS 0x0100 /* Advertise 1000T HD capability */ #define CR_1000T_FD_CAPS 0x0200 /* Advertise 1000T FD capability */ - /* 0=DTE device */ #define CR_1000T_MS_VALUE 0x0800 /* 1=Configure PHY as Master */ /* 0=Configure PHY as Slave */ #define CR_1000T_MS_ENABLE 0x1000 /* 1=Master/Slave manual config value */ @@ -581,7 +569,7 @@ /* PHY 1000 MII Register/Bit Definitions */ /* PHY Registers defined by IEEE */ #define PHY_CONTROL 0x00 /* Control Register */ -#define PHY_STATUS 0x01 /* Status Regiser */ +#define PHY_STATUS 0x01 /* Status Register */ #define PHY_ID1 0x02 /* Phy Id Reg (word 1) */ #define PHY_ID2 0x03 /* Phy Id Reg (word 2) */ #define PHY_AUTONEG_ADV 0x04 /* Autoneg Advertisement */ @@ -708,8 +696,8 @@ /* Auto crossover enabled all speeds */ #define M88E1000_PSCR_AUTO_X_MODE 0x0060 /* - * 1=Enable Extended 10BASE-T distance (Lower 10BASE-T RX Threshold - * 0=Normal 10BASE-T RX Threshold + * 1=Enable Extended 10BASE-T distance (Lower 10BASE-T Rx Threshold + * 0=Normal 10BASE-T Rx Threshold */ /* 1=5-bit interface in 100BASE-TX, 0=MII interface in 100BASE-TX */ #define M88E1000_PSCR_ASSERT_CRS_ON_TX 0x0800 /* 1=Assert CRS on Transmit */ diff --git a/drivers/net/igb/e1000_hw.h b/drivers/net/igb/e1000_hw.h index 7b2c70a..746c3ea 100644 --- a/drivers/net/igb/e1000_hw.h +++ b/drivers/net/igb/e1000_hw.h @@ -586,14 +586,10 @@ struct e1000_hw { #ifdef DEBUG extern char *igb_get_hw_dev_name(struct e1000_hw *hw); -#define hw_dbg(hw, format, arg...) \ +#define hw_dbg(format, arg...) \ printk(KERN_DEBUG "%s: " format, igb_get_hw_dev_name(hw), ##arg) #else -static inline int __attribute__ ((format (printf, 2, 3))) -hw_dbg(struct e1000_hw *hw, const char *format, ...) -{ - return 0; -} +#define hw_dbg(format, arg...) #endif #endif diff --git a/drivers/net/igb/e1000_mac.c b/drivers/net/igb/e1000_mac.c index 3e84a3f..47ad2c4 100644 --- a/drivers/net/igb/e1000_mac.c +++ b/drivers/net/igb/e1000_mac.c @@ -39,7 +39,7 @@ static s32 igb_set_fc_watermarks(struct e1000_hw *hw); static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr); /** - * e1000_remove_device - Free device specific structure + * igb_remove_device - Free device specific structure * @hw: pointer to the HW structure * * If a device specific structure was allocated, this function will @@ -73,7 +73,7 @@ static s32 igb_read_pcie_cap_reg(struct e1000_hw *hw, u32 reg, u16 *value) } /** - * e1000_get_bus_info_pcie - Get PCIe bus information + * igb_get_bus_info_pcie - Get PCIe bus information * @hw: pointer to the HW structure * * Determines and stores the system bus information for a particular @@ -113,7 +113,7 @@ s32 igb_get_bus_info_pcie(struct e1000_hw *hw) } /** - * e1000_clear_vfta - Clear VLAN filter table + * igb_clear_vfta - Clear VLAN filter table * @hw: pointer to the HW structure * * Clears the register array which contains the VLAN filter table by @@ -130,7 +130,7 @@ void igb_clear_vfta(struct e1000_hw *hw) } /** - * e1000_write_vfta - Write value to VLAN filter table + * igb_write_vfta - Write value to VLAN filter table * @hw: pointer to the HW structure * @offset: register offset in VLAN filter table * @value: register value written to VLAN filter table @@ -145,7 +145,7 @@ void igb_write_vfta(struct e1000_hw *hw, u32 offset, u32 value) } /** - * e1000_init_rx_addrs - Initialize receive address's + * igb_init_rx_addrs - Initialize receive address's * @hw: pointer to the HW structure * @rar_count: receive address registers * @@ -158,12 +158,12 @@ void igb_init_rx_addrs(struct e1000_hw *hw, u16 rar_count) u32 i; /* Setup the receive address */ - hw_dbg(hw, "Programming MAC Address into RAR[0]\n"); + hw_dbg("Programming MAC Address into RAR[0]\n"); hw->mac.ops.rar_set(hw, hw->mac.addr, 0); /* Zero out the other (rar_entry_count - 1) receive addresses */ - hw_dbg(hw, "Clearing RAR[1-%u]\n", rar_count-1); + hw_dbg("Clearing RAR[1-%u]\n", rar_count-1); for (i = 1; i < rar_count; i++) { array_wr32(E1000_RA, (i << 1), 0); wrfl(); @@ -173,7 +173,7 @@ void igb_init_rx_addrs(struct e1000_hw *hw, u16 rar_count) } /** - * e1000_check_alt_mac_addr - Check for alternate MAC addr + * igb_check_alt_mac_addr - Check for alternate MAC addr * @hw: pointer to the HW structure * * Checks the nvm for an alternate MAC address. An alternate MAC address @@ -193,7 +193,7 @@ s32 igb_check_alt_mac_addr(struct e1000_hw *hw) ret_val = hw->nvm.ops.read_nvm(hw, NVM_ALT_MAC_ADDR_PTR, 1, &nvm_alt_mac_addr_offset); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } @@ -209,7 +209,7 @@ s32 igb_check_alt_mac_addr(struct e1000_hw *hw) offset = nvm_alt_mac_addr_offset + (i >> 1); ret_val = hw->nvm.ops.read_nvm(hw, offset, 1, &nvm_data); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } @@ -233,7 +233,7 @@ out: } /** - * e1000_rar_set - Set receive address register + * igb_rar_set - Set receive address register * @hw: pointer to the HW structure * @addr: pointer to the receive address * @index: receive address array register @@ -263,7 +263,7 @@ void igb_rar_set(struct e1000_hw *hw, u8 *addr, u32 index) } /** - * e1000_mta_set - Set multicast filter table address + * igb_mta_set - Set multicast filter table address * @hw: pointer to the HW structure * @hash_value: determines the MTA register and bit to set * @@ -298,7 +298,7 @@ static void igb_mta_set(struct e1000_hw *hw, u32 hash_value) } /** - * e1000_update_mc_addr_list - Update Multicast addresses + * igb_update_mc_addr_list - Update Multicast addresses * @hw: pointer to the HW structure * @mc_addr_list: array of multicast addresses to program * @mc_addr_count: number of multicast addresses to program @@ -336,7 +336,7 @@ void igb_update_mc_addr_list(struct e1000_hw *hw, } /* Clear the old settings from the MTA */ - hw_dbg(hw, "Clearing MTA\n"); + hw_dbg("Clearing MTA\n"); for (i = 0; i < hw->mac.mta_reg_count; i++) { array_wr32(E1000_MTA, i, 0); wrfl(); @@ -345,14 +345,14 @@ void igb_update_mc_addr_list(struct e1000_hw *hw, /* Load any remaining multicast addresses into the hash table. */ for (; mc_addr_count > 0; mc_addr_count--) { hash_value = igb_hash_mc_addr(hw, mc_addr_list); - hw_dbg(hw, "Hash value = 0x%03X\n", hash_value); + hw_dbg("Hash value = 0x%03X\n", hash_value); igb_mta_set(hw, hash_value); mc_addr_list += ETH_ALEN; } } /** - * e1000_hash_mc_addr - Generate a multicast hash value + * igb_hash_mc_addr - Generate a multicast hash value * @hw: pointer to the HW structure * @mc_addr: pointer to a multicast address * @@ -423,7 +423,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) } /** - * e1000_clear_hw_cntrs_base - Clear base hardware counters + * igb_clear_hw_cntrs_base - Clear base hardware counters * @hw: pointer to the HW structure * * Clears the base hardware counters by reading the counter registers. @@ -472,7 +472,7 @@ void igb_clear_hw_cntrs_base(struct e1000_hw *hw) } /** - * e1000_check_for_copper_link - Check for link (Copper) + * igb_check_for_copper_link - Check for link (Copper) * @hw: pointer to the HW structure * * Checks to see of the link status of the hardware has changed. If a @@ -540,14 +540,14 @@ s32 igb_check_for_copper_link(struct e1000_hw *hw) */ ret_val = igb_config_fc_after_link_up(hw); if (ret_val) - hw_dbg(hw, "Error configuring flow control\n"); + hw_dbg("Error configuring flow control\n"); out: return ret_val; } /** - * e1000_setup_link - Setup flow control and link settings + * igb_setup_link - Setup flow control and link settings * @hw: pointer to the HW structure * * Determines which flow control settings to use, then configures flow @@ -578,7 +578,7 @@ s32 igb_setup_link(struct e1000_hw *hw) */ hw->fc.original_type = hw->fc.type; - hw_dbg(hw, "After fix-ups FlowControl is now = %x\n", hw->fc.type); + hw_dbg("After fix-ups FlowControl is now = %x\n", hw->fc.type); /* Call the necessary media_type subroutine to configure the link. */ ret_val = hw->mac.ops.setup_physical_interface(hw); @@ -591,8 +591,7 @@ s32 igb_setup_link(struct e1000_hw *hw) * control is disabled, because it does not hurt anything to * initialize these registers. */ - hw_dbg(hw, - "Initializing the Flow Control address, type and timer regs\n"); + hw_dbg("Initializing the Flow Control address, type and timer regs\n"); wr32(E1000_FCT, FLOW_CONTROL_TYPE); wr32(E1000_FCAH, FLOW_CONTROL_ADDRESS_HIGH); wr32(E1000_FCAL, FLOW_CONTROL_ADDRESS_LOW); @@ -606,7 +605,7 @@ out: } /** - * e1000_config_collision_dist - Configure collision distance + * igb_config_collision_dist - Configure collision distance * @hw: pointer to the HW structure * * Configures the collision distance to the default value and is used @@ -627,7 +626,7 @@ void igb_config_collision_dist(struct e1000_hw *hw) } /** - * e1000_set_fc_watermarks - Set flow control high/low watermarks + * igb_set_fc_watermarks - Set flow control high/low watermarks * @hw: pointer to the HW structure * * Sets the flow control high/low threshold (watermark) registers. If @@ -665,7 +664,7 @@ static s32 igb_set_fc_watermarks(struct e1000_hw *hw) } /** - * e1000_set_default_fc - Set flow control default values + * igb_set_default_fc - Set flow control default values * @hw: pointer to the HW structure * * Read the EEPROM for the default values for flow control and store the @@ -689,7 +688,7 @@ static s32 igb_set_default_fc(struct e1000_hw *hw) &nvm_data); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } @@ -706,7 +705,7 @@ out: } /** - * e1000_force_mac_fc - Force the MAC's flow control settings + * igb_force_mac_fc - Force the MAC's flow control settings * @hw: pointer to the HW structure * * Force the MAC's flow control settings. Sets the TFCE and RFCE bits in the @@ -740,7 +739,7 @@ s32 igb_force_mac_fc(struct e1000_hw *hw) * 3: Both Rx and TX flow control (symmetric) is enabled. * other: No other values should be possible at this point. */ - hw_dbg(hw, "hw->fc.type = %u\n", hw->fc.type); + hw_dbg("hw->fc.type = %u\n", hw->fc.type); switch (hw->fc.type) { case e1000_fc_none: @@ -758,7 +757,7 @@ s32 igb_force_mac_fc(struct e1000_hw *hw) ctrl |= (E1000_CTRL_TFCE | E1000_CTRL_RFCE); break; default: - hw_dbg(hw, "Flow control param set incorrectly\n"); + hw_dbg("Flow control param set incorrectly\n"); ret_val = -E1000_ERR_CONFIG; goto out; } @@ -770,7 +769,7 @@ out: } /** - * e1000_config_fc_after_link_up - Configures flow control after link + * igb_config_fc_after_link_up - Configures flow control after link * @hw: pointer to the HW structure * * Checks the status of auto-negotiation after link up to ensure that the @@ -801,7 +800,7 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) } if (ret_val) { - hw_dbg(hw, "Error forcing flow control settings\n"); + hw_dbg("Error forcing flow control settings\n"); goto out; } @@ -827,7 +826,7 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) goto out; if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) { - hw_dbg(hw, "Copper PHY and Auto Neg " + hw_dbg("Copper PHY and Auto Neg " "has not completed.\n"); goto out; } @@ -893,11 +892,11 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) */ if (hw->fc.original_type == e1000_fc_full) { hw->fc.type = e1000_fc_full; - hw_dbg(hw, "Flow Control = FULL.\r\n"); + hw_dbg("Flow Control = FULL.\r\n"); } else { hw->fc.type = e1000_fc_rx_pause; - hw_dbg(hw, "Flow Control = " - "RX PAUSE frames only.\r\n"); + hw_dbg("Flow Control = " + "RX PAUSE frames only.\r\n"); } } /* @@ -913,7 +912,7 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { hw->fc.type = e1000_fc_tx_pause; - hw_dbg(hw, "Flow Control = TX PAUSE frames only.\r\n"); + hw_dbg("Flow Control = TX PAUSE frames only.\r\n"); } /* * For transmitting PAUSE frames ONLY. @@ -928,7 +927,7 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { hw->fc.type = e1000_fc_rx_pause; - hw_dbg(hw, "Flow Control = RX PAUSE frames only.\r\n"); + hw_dbg("Flow Control = RX PAUSE frames only.\r\n"); } /* * Per the IEEE spec, at this point flow control should be @@ -955,10 +954,10 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) hw->fc.original_type == e1000_fc_tx_pause) || hw->fc.strict_ieee) { hw->fc.type = e1000_fc_none; - hw_dbg(hw, "Flow Control = NONE.\r\n"); + hw_dbg("Flow Control = NONE.\r\n"); } else { hw->fc.type = e1000_fc_rx_pause; - hw_dbg(hw, "Flow Control = RX PAUSE frames only.\r\n"); + hw_dbg("Flow Control = RX PAUSE frames only.\r\n"); } /* @@ -968,7 +967,7 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) */ ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex); if (ret_val) { - hw_dbg(hw, "Error getting link speed and duplex\n"); + hw_dbg("Error getting link speed and duplex\n"); goto out; } @@ -981,7 +980,7 @@ s32 igb_config_fc_after_link_up(struct e1000_hw *hw) */ ret_val = igb_force_mac_fc(hw); if (ret_val) { - hw_dbg(hw, "Error forcing flow control settings\n"); + hw_dbg("Error forcing flow control settings\n"); goto out; } } @@ -991,7 +990,7 @@ out: } /** - * e1000_get_speed_and_duplex_copper - Retreive current speed/duplex + * igb_get_speed_and_duplex_copper - Retreive current speed/duplex * @hw: pointer to the HW structure * @speed: stores the current speed * @duplex: stores the current duplex @@ -1007,28 +1006,28 @@ s32 igb_get_speed_and_duplex_copper(struct e1000_hw *hw, u16 *speed, status = rd32(E1000_STATUS); if (status & E1000_STATUS_SPEED_1000) { *speed = SPEED_1000; - hw_dbg(hw, "1000 Mbs, "); + hw_dbg("1000 Mbs, "); } else if (status & E1000_STATUS_SPEED_100) { *speed = SPEED_100; - hw_dbg(hw, "100 Mbs, "); + hw_dbg("100 Mbs, "); } else { *speed = SPEED_10; - hw_dbg(hw, "10 Mbs, "); + hw_dbg("10 Mbs, "); } if (status & E1000_STATUS_FD) { *duplex = FULL_DUPLEX; - hw_dbg(hw, "Full Duplex\n"); + hw_dbg("Full Duplex\n"); } else { *duplex = HALF_DUPLEX; - hw_dbg(hw, "Half Duplex\n"); + hw_dbg("Half Duplex\n"); } return 0; } /** - * e1000_get_hw_semaphore - Acquire hardware semaphore + * igb_get_hw_semaphore - Acquire hardware semaphore * @hw: pointer to the HW structure * * Acquire the HW semaphore to access the PHY or NVM @@ -1051,7 +1050,7 @@ s32 igb_get_hw_semaphore(struct e1000_hw *hw) } if (i == timeout) { - hw_dbg(hw, "Driver can't access device - SMBI bit is set.\n"); + hw_dbg("Driver can't access device - SMBI bit is set.\n"); ret_val = -E1000_ERR_NVM; goto out; } @@ -1071,7 +1070,7 @@ s32 igb_get_hw_semaphore(struct e1000_hw *hw) if (i == timeout) { /* Release semaphores */ igb_put_hw_semaphore(hw); - hw_dbg(hw, "Driver can't access the NVM\n"); + hw_dbg("Driver can't access the NVM\n"); ret_val = -E1000_ERR_NVM; goto out; } @@ -1081,7 +1080,7 @@ out: } /** - * e1000_put_hw_semaphore - Release hardware semaphore + * igb_put_hw_semaphore - Release hardware semaphore * @hw: pointer to the HW structure * * Release hardware semaphore used to access the PHY or NVM @@ -1098,7 +1097,7 @@ void igb_put_hw_semaphore(struct e1000_hw *hw) } /** - * e1000_get_auto_rd_done - Check for auto read completion + * igb_get_auto_rd_done - Check for auto read completion * @hw: pointer to the HW structure * * Check EEPROM for Auto Read done bit. @@ -1117,7 +1116,7 @@ s32 igb_get_auto_rd_done(struct e1000_hw *hw) } if (i == AUTO_READ_DONE_TIMEOUT) { - hw_dbg(hw, "Auto read by HW from NVM has not completed.\n"); + hw_dbg("Auto read by HW from NVM has not completed.\n"); ret_val = -E1000_ERR_RESET; goto out; } @@ -1127,7 +1126,7 @@ out: } /** - * e1000_valid_led_default - Verify a valid default LED config + * igb_valid_led_default - Verify a valid default LED config * @hw: pointer to the HW structure * @data: pointer to the NVM (EEPROM) * @@ -1140,7 +1139,7 @@ static s32 igb_valid_led_default(struct e1000_hw *hw, u16 *data) ret_val = hw->nvm.ops.read_nvm(hw, NVM_ID_LED_SETTINGS, 1, data); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } @@ -1152,7 +1151,7 @@ out: } /** - * e1000_id_led_init - + * igb_id_led_init - * @hw: pointer to the HW structure * **/ @@ -1217,7 +1216,7 @@ out: } /** - * e1000_cleanup_led - Set LED config to default operation + * igb_cleanup_led - Set LED config to default operation * @hw: pointer to the HW structure * * Remove the current LED configuration and set the LED configuration @@ -1230,7 +1229,7 @@ s32 igb_cleanup_led(struct e1000_hw *hw) } /** - * e1000_blink_led - Blink LED + * igb_blink_led - Blink LED * @hw: pointer to the HW structure * * Blink the led's which are set to be on. @@ -1263,7 +1262,7 @@ s32 igb_blink_led(struct e1000_hw *hw) } /** - * e1000_led_off - Turn LED off + * igb_led_off - Turn LED off * @hw: pointer to the HW structure * * Turn LED off. @@ -1290,7 +1289,7 @@ s32 igb_led_off(struct e1000_hw *hw) } /** - * e1000_disable_pcie_master - Disables PCI-express master access + * igb_disable_pcie_master - Disables PCI-express master access * @hw: pointer to the HW structure * * Returns 0 (0) if successful, else returns -10 @@ -1322,7 +1321,7 @@ s32 igb_disable_pcie_master(struct e1000_hw *hw) } if (!timeout) { - hw_dbg(hw, "Master requests are pending.\n"); + hw_dbg("Master requests are pending.\n"); ret_val = -E1000_ERR_MASTER_REQUESTS_PENDING; goto out; } @@ -1332,7 +1331,7 @@ out: } /** - * e1000_reset_adaptive - Reset Adaptive Interframe Spacing + * igb_reset_adaptive - Reset Adaptive Interframe Spacing * @hw: pointer to the HW structure * * Reset the Adaptive Interframe Spacing throttle to default values. @@ -1342,7 +1341,7 @@ void igb_reset_adaptive(struct e1000_hw *hw) struct e1000_mac_info *mac = &hw->mac; if (!mac->adaptive_ifs) { - hw_dbg(hw, "Not in Adaptive IFS mode!\n"); + hw_dbg("Not in Adaptive IFS mode!\n"); goto out; } @@ -1361,7 +1360,7 @@ out: } /** - * e1000_update_adaptive - Update Adaptive Interframe Spacing + * igb_update_adaptive - Update Adaptive Interframe Spacing * @hw: pointer to the HW structure * * Update the Adaptive Interframe Spacing Throttle value based on the @@ -1372,7 +1371,7 @@ void igb_update_adaptive(struct e1000_hw *hw) struct e1000_mac_info *mac = &hw->mac; if (!mac->adaptive_ifs) { - hw_dbg(hw, "Not in Adaptive IFS mode!\n"); + hw_dbg("Not in Adaptive IFS mode!\n"); goto out; } @@ -1402,7 +1401,7 @@ out: } /** - * e1000_validate_mdi_setting - Verify MDI/MDIx settings + * igb_validate_mdi_setting - Verify MDI/MDIx settings * @hw: pointer to the HW structure * * Verify that when not using auto-negotitation that MDI/MDIx is correctly @@ -1413,7 +1412,7 @@ s32 igb_validate_mdi_setting(struct e1000_hw *hw) s32 ret_val = 0; if (!hw->mac.autoneg && (hw->phy.mdix == 0 || hw->phy.mdix == 3)) { - hw_dbg(hw, "Invalid MDI setting detected\n"); + hw_dbg("Invalid MDI setting detected\n"); hw->phy.mdix = 1; ret_val = -E1000_ERR_CONFIG; goto out; @@ -1424,7 +1423,7 @@ out: } /** - * e1000_write_8bit_ctrl_reg - Write a 8bit CTRL register + * igb_write_8bit_ctrl_reg - Write a 8bit CTRL register * @hw: pointer to the HW structure * @reg: 32bit register offset such as E1000_SCTL * @offset: register offset to write to @@ -1452,7 +1451,7 @@ s32 igb_write_8bit_ctrl_reg(struct e1000_hw *hw, u32 reg, break; } if (!(regvalue & E1000_GEN_CTL_READY)) { - hw_dbg(hw, "Reg %08x did not indicate ready\n", reg); + hw_dbg("Reg %08x did not indicate ready\n", reg); ret_val = -E1000_ERR_PHY; goto out; } @@ -1462,7 +1461,7 @@ out: } /** - * e1000_enable_mng_pass_thru - Enable processing of ARP's + * igb_enable_mng_pass_thru - Enable processing of ARP's * @hw: pointer to the HW structure * * Verifies the hardware needs to allow ARPs to be processed by the host. diff --git a/drivers/net/igb/e1000_nvm.c b/drivers/net/igb/e1000_nvm.c index 2897106..a84e4e4 100644 --- a/drivers/net/igb/e1000_nvm.c +++ b/drivers/net/igb/e1000_nvm.c @@ -32,7 +32,7 @@ #include "e1000_nvm.h" /** - * e1000_raise_eec_clk - Raise EEPROM clock + * igb_raise_eec_clk - Raise EEPROM clock * @hw: pointer to the HW structure * @eecd: pointer to the EEPROM * @@ -47,7 +47,7 @@ static void igb_raise_eec_clk(struct e1000_hw *hw, u32 *eecd) } /** - * e1000_lower_eec_clk - Lower EEPROM clock + * igb_lower_eec_clk - Lower EEPROM clock * @hw: pointer to the HW structure * @eecd: pointer to the EEPROM * @@ -62,7 +62,7 @@ static void igb_lower_eec_clk(struct e1000_hw *hw, u32 *eecd) } /** - * e1000_shift_out_eec_bits - Shift data bits our to the EEPROM + * igb_shift_out_eec_bits - Shift data bits our to the EEPROM * @hw: pointer to the HW structure * @data: data to send to the EEPROM * @count: number of bits to shift out @@ -105,7 +105,7 @@ static void igb_shift_out_eec_bits(struct e1000_hw *hw, u16 data, u16 count) } /** - * e1000_shift_in_eec_bits - Shift data bits in from the EEPROM + * igb_shift_in_eec_bits - Shift data bits in from the EEPROM * @hw: pointer to the HW structure * @count: number of bits to shift in * @@ -143,7 +143,7 @@ static u16 igb_shift_in_eec_bits(struct e1000_hw *hw, u16 count) } /** - * e1000_poll_eerd_eewr_done - Poll for EEPROM read/write completion + * igb_poll_eerd_eewr_done - Poll for EEPROM read/write completion * @hw: pointer to the HW structure * @ee_reg: EEPROM flag for polling * @@ -174,7 +174,7 @@ static s32 igb_poll_eerd_eewr_done(struct e1000_hw *hw, int ee_reg) } /** - * e1000_acquire_nvm - Generic request for access to EEPROM + * igb_acquire_nvm - Generic request for access to EEPROM * @hw: pointer to the HW structure * * Set the EEPROM access request bit and wait for EEPROM access grant bit. @@ -202,7 +202,7 @@ s32 igb_acquire_nvm(struct e1000_hw *hw) if (!timeout) { eecd &= ~E1000_EECD_REQ; wr32(E1000_EECD, eecd); - hw_dbg(hw, "Could not acquire NVM grant\n"); + hw_dbg("Could not acquire NVM grant\n"); ret_val = -E1000_ERR_NVM; } @@ -210,7 +210,7 @@ s32 igb_acquire_nvm(struct e1000_hw *hw) } /** - * e1000_standby_nvm - Return EEPROM to standby state + * igb_standby_nvm - Return EEPROM to standby state * @hw: pointer to the HW structure * * Return the EEPROM to a standby state. @@ -273,7 +273,7 @@ static void e1000_stop_nvm(struct e1000_hw *hw) } /** - * e1000_release_nvm - Release exclusive access to EEPROM + * igb_release_nvm - Release exclusive access to EEPROM * @hw: pointer to the HW structure * * Stop any current commands to the EEPROM and clear the EEPROM request bit. @@ -290,7 +290,7 @@ void igb_release_nvm(struct e1000_hw *hw) } /** - * e1000_ready_nvm_eeprom - Prepares EEPROM for read/write + * igb_ready_nvm_eeprom - Prepares EEPROM for read/write * @hw: pointer to the HW structure * * Setups the EEPROM for reading and writing. @@ -337,7 +337,7 @@ static s32 igb_ready_nvm_eeprom(struct e1000_hw *hw) } if (!timeout) { - hw_dbg(hw, "SPI NVM Status error\n"); + hw_dbg("SPI NVM Status error\n"); ret_val = -E1000_ERR_NVM; goto out; } @@ -348,7 +348,7 @@ out: } /** - * e1000_read_nvm_eerd - Reads EEPROM using EERD register + * igb_read_nvm_eerd - Reads EEPROM using EERD register * @hw: pointer to the HW structure * @offset: offset of word in the EEPROM to read * @words: number of words to read @@ -368,7 +368,7 @@ s32 igb_read_nvm_eerd(struct e1000_hw *hw, u16 offset, u16 words, u16 *data) */ if ((offset >= nvm->word_size) || (words > (nvm->word_size - offset)) || (words == 0)) { - hw_dbg(hw, "nvm parameter(s) out of bounds\n"); + hw_dbg("nvm parameter(s) out of bounds\n"); ret_val = -E1000_ERR_NVM; goto out; } @@ -391,7 +391,7 @@ out: } /** - * e1000_write_nvm_spi - Write to EEPROM using SPI + * igb_write_nvm_spi - Write to EEPROM using SPI * @hw: pointer to the HW structure * @offset: offset within the EEPROM to be written to * @words: number of words to write @@ -414,7 +414,7 @@ s32 igb_write_nvm_spi(struct e1000_hw *hw, u16 offset, u16 words, u16 *data) */ if ((offset >= nvm->word_size) || (words > (nvm->word_size - offset)) || (words == 0)) { - hw_dbg(hw, "nvm parameter(s) out of bounds\n"); + hw_dbg("nvm parameter(s) out of bounds\n"); ret_val = -E1000_ERR_NVM; goto out; } @@ -475,7 +475,7 @@ out: } /** - * e1000_read_part_num - Read device part number + * igb_read_part_num - Read device part number * @hw: pointer to the HW structure * @part_num: pointer to device part number * @@ -489,14 +489,14 @@ s32 igb_read_part_num(struct e1000_hw *hw, u32 *part_num) ret_val = hw->nvm.ops.read_nvm(hw, NVM_PBA_OFFSET_0, 1, &nvm_data); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } *part_num = (u32)(nvm_data << 16); ret_val = hw->nvm.ops.read_nvm(hw, NVM_PBA_OFFSET_1, 1, &nvm_data); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } *part_num |= nvm_data; @@ -506,7 +506,7 @@ out: } /** - * e1000_read_mac_addr - Read device MAC address + * igb_read_mac_addr - Read device MAC address * @hw: pointer to the HW structure * * Reads the device MAC address from the EEPROM and stores the value. @@ -522,7 +522,7 @@ s32 igb_read_mac_addr(struct e1000_hw *hw) offset = i >> 1; ret_val = hw->nvm.ops.read_nvm(hw, offset, 1, &nvm_data); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } hw->mac.perm_addr[i] = (u8)(nvm_data & 0xFF); @@ -541,7 +541,7 @@ out: } /** - * e1000_validate_nvm_checksum - Validate EEPROM checksum + * igb_validate_nvm_checksum - Validate EEPROM checksum * @hw: pointer to the HW structure * * Calculates the EEPROM checksum by reading/adding each word of the EEPROM @@ -556,14 +556,14 @@ s32 igb_validate_nvm_checksum(struct e1000_hw *hw) for (i = 0; i < (NVM_CHECKSUM_REG + 1); i++) { ret_val = hw->nvm.ops.read_nvm(hw, i, 1, &nvm_data); if (ret_val) { - hw_dbg(hw, "NVM Read Error\n"); + hw_dbg("NVM Read Error\n"); goto out; } checksum += nvm_data; } if (checksum != (u16) NVM_SUM) { - hw_dbg(hw, "NVM Checksum Invalid\n"); + hw_dbg("NVM Checksum Invalid\n"); ret_val = -E1000_ERR_NVM; goto out; } @@ -573,7 +573,7 @@ out: } /** - * e1000_update_nvm_checksum - Update EEPROM checksum + * igb_update_nvm_checksum - Update EEPROM checksum * @hw: pointer to the HW structure * * Updates the EEPROM checksum by reading/adding each word of the EEPROM @@ -589,7 +589,7 @@ s32 igb_update_nvm_checksum(struct e1000_hw *hw) for (i = 0; i < NVM_CHECKSUM_REG; i++) { ret_val = hw->nvm.ops.read_nvm(hw, i, 1, &nvm_data); if (ret_val) { - hw_dbg(hw, "NVM Read Error while updating checksum.\n"); + hw_dbg("NVM Read Error while updating checksum.\n"); goto out; } checksum += nvm_data; @@ -597,7 +597,7 @@ s32 igb_update_nvm_checksum(struct e1000_hw *hw) checksum = (u16) NVM_SUM - checksum; ret_val = hw->nvm.ops.write_nvm(hw, NVM_CHECKSUM_REG, 1, &checksum); if (ret_val) - hw_dbg(hw, "NVM Write Error while updating checksum.\n"); + hw_dbg("NVM Write Error while updating checksum.\n"); out: return ret_val; diff --git a/drivers/net/igb/e1000_phy.c b/drivers/net/igb/e1000_phy.c index 08a86b1..17fddb9 100644 --- a/drivers/net/igb/e1000_phy.c +++ b/drivers/net/igb/e1000_phy.c @@ -61,7 +61,7 @@ static const u16 e1000_igp_2_cable_length_table[] = sizeof(e1000_igp_2_cable_length_table[0])) /** - * e1000_check_reset_block - Check if PHY reset is blocked + * igb_check_reset_block - Check if PHY reset is blocked * @hw: pointer to the HW structure * * Read the PHY management control register and check whether a PHY reset @@ -79,7 +79,7 @@ s32 igb_check_reset_block(struct e1000_hw *hw) } /** - * e1000_get_phy_id - Retrieve the PHY ID and revision + * igb_get_phy_id - Retrieve the PHY ID and revision * @hw: pointer to the HW structure * * Reads the PHY registers and stores the PHY ID and possibly the PHY @@ -109,7 +109,7 @@ out: } /** - * e1000_phy_reset_dsp - Reset PHY DSP + * igb_phy_reset_dsp - Reset PHY DSP * @hw: pointer to the HW structure * * Reset the digital signal processor. @@ -129,7 +129,7 @@ out: } /** - * e1000_read_phy_reg_mdic - Read MDI control register + * igb_read_phy_reg_mdic - Read MDI control register * @hw: pointer to the HW structure * @offset: register offset to be read * @data: pointer to the read data @@ -144,7 +144,7 @@ static s32 igb_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) s32 ret_val = 0; if (offset > MAX_PHY_REG_ADDRESS) { - hw_dbg(hw, "PHY Address %d is out of range\n", offset); + hw_dbg("PHY Address %d is out of range\n", offset); ret_val = -E1000_ERR_PARAM; goto out; } @@ -172,12 +172,12 @@ static s32 igb_read_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 *data) break; } if (!(mdic & E1000_MDIC_READY)) { - hw_dbg(hw, "MDI Read did not complete\n"); + hw_dbg("MDI Read did not complete\n"); ret_val = -E1000_ERR_PHY; goto out; } if (mdic & E1000_MDIC_ERROR) { - hw_dbg(hw, "MDI Error\n"); + hw_dbg("MDI Error\n"); ret_val = -E1000_ERR_PHY; goto out; } @@ -188,7 +188,7 @@ out: } /** - * e1000_write_phy_reg_mdic - Write MDI control register + * igb_write_phy_reg_mdic - Write MDI control register * @hw: pointer to the HW structure * @offset: register offset to write to * @data: data to write to register at offset @@ -202,7 +202,7 @@ static s32 igb_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) s32 ret_val = 0; if (offset > MAX_PHY_REG_ADDRESS) { - hw_dbg(hw, "PHY Address %d is out of range\n", offset); + hw_dbg("PHY Address %d is out of range\n", offset); ret_val = -E1000_ERR_PARAM; goto out; } @@ -231,12 +231,12 @@ static s32 igb_write_phy_reg_mdic(struct e1000_hw *hw, u32 offset, u16 data) break; } if (!(mdic & E1000_MDIC_READY)) { - hw_dbg(hw, "MDI Write did not complete\n"); + hw_dbg("MDI Write did not complete\n"); ret_val = -E1000_ERR_PHY; goto out; } if (mdic & E1000_MDIC_ERROR) { - hw_dbg(hw, "MDI Error\n"); + hw_dbg("MDI Error\n"); ret_val = -E1000_ERR_PHY; goto out; } @@ -246,7 +246,7 @@ out: } /** - * e1000_read_phy_reg_igp - Read igp PHY register + * igb_read_phy_reg_igp - Read igp PHY register * @hw: pointer to the HW structure * @offset: register offset to be read * @data: pointer to the read data @@ -284,7 +284,7 @@ out: } /** - * e1000_write_phy_reg_igp - Write igp PHY register + * igb_write_phy_reg_igp - Write igp PHY register * @hw: pointer to the HW structure * @offset: register offset to write to * @data: data to write at register offset @@ -321,7 +321,7 @@ out: } /** - * e1000_copper_link_setup_m88 - Setup m88 PHY's for copper link + * igb_copper_link_setup_m88 - Setup m88 PHY's for copper link * @hw: pointer to the HW structure * * Sets up MDI/MDI-X and polarity for m88 PHY's. If necessary, transmit clock @@ -423,7 +423,7 @@ s32 igb_copper_link_setup_m88(struct e1000_hw *hw) /* Commit the changes. */ ret_val = igb_phy_sw_reset(hw); if (ret_val) { - hw_dbg(hw, "Error committing the PHY changes\n"); + hw_dbg("Error committing the PHY changes\n"); goto out; } @@ -432,7 +432,7 @@ out: } /** - * e1000_copper_link_setup_igp - Setup igp PHY's for copper link + * igb_copper_link_setup_igp - Setup igp PHY's for copper link * @hw: pointer to the HW structure * * Sets up LPLU, MDI/MDI-X, polarity, Smartspeed and Master/Slave config for @@ -451,7 +451,7 @@ s32 igb_copper_link_setup_igp(struct e1000_hw *hw) ret_val = hw->phy.ops.reset_phy(hw); if (ret_val) { - hw_dbg(hw, "Error resetting the PHY.\n"); + hw_dbg("Error resetting the PHY.\n"); goto out; } @@ -467,7 +467,7 @@ s32 igb_copper_link_setup_igp(struct e1000_hw *hw) if (hw->phy.ops.set_d3_lplu_state) ret_val = hw->phy.ops.set_d3_lplu_state(hw, false); if (ret_val) { - hw_dbg(hw, "Error Disabling LPLU D3\n"); + hw_dbg("Error Disabling LPLU D3\n"); goto out; } } @@ -475,7 +475,7 @@ s32 igb_copper_link_setup_igp(struct e1000_hw *hw) /* disable lplu d0 during driver init */ ret_val = hw->phy.ops.set_d0_lplu_state(hw, false); if (ret_val) { - hw_dbg(hw, "Error Disabling LPLU D0\n"); + hw_dbg("Error Disabling LPLU D0\n"); goto out; } /* Configure mdi-mdix settings */ @@ -570,7 +570,7 @@ out: } /** - * e1000_copper_link_autoneg - Setup/Enable autoneg for copper link + * igb_copper_link_autoneg - Setup/Enable autoneg for copper link * @hw: pointer to the HW structure * * Performs initial bounds checking on autoneg advertisement parameter, then @@ -597,13 +597,13 @@ s32 igb_copper_link_autoneg(struct e1000_hw *hw) if (phy->autoneg_advertised == 0) phy->autoneg_advertised = phy->autoneg_mask; - hw_dbg(hw, "Reconfiguring auto-neg advertisement params\n"); + hw_dbg("Reconfiguring auto-neg advertisement params\n"); ret_val = igb_phy_setup_autoneg(hw); if (ret_val) { - hw_dbg(hw, "Error Setting up Auto-Negotiation\n"); + hw_dbg("Error Setting up Auto-Negotiation\n"); goto out; } - hw_dbg(hw, "Restarting Auto-Neg\n"); + hw_dbg("Restarting Auto-Neg\n"); /* * Restart auto-negotiation by setting the Auto Neg Enable bit and @@ -625,8 +625,8 @@ s32 igb_copper_link_autoneg(struct e1000_hw *hw) if (phy->autoneg_wait_to_complete) { ret_val = igb_wait_autoneg(hw); if (ret_val) { - hw_dbg(hw, "Error while waiting for " - "autoneg to complete\n"); + hw_dbg("Error while waiting for " + "autoneg to complete\n"); goto out; } } @@ -638,7 +638,7 @@ out: } /** - * e1000_phy_setup_autoneg - Configure PHY for auto-negotiation + * igb_phy_setup_autoneg - Configure PHY for auto-negotiation * @hw: pointer to the HW structure * * Reads the MII auto-neg advertisement register and/or the 1000T control @@ -689,39 +689,39 @@ static s32 igb_phy_setup_autoneg(struct e1000_hw *hw) NWAY_AR_10T_HD_CAPS); mii_1000t_ctrl_reg &= ~(CR_1000T_HD_CAPS | CR_1000T_FD_CAPS); - hw_dbg(hw, "autoneg_advertised %x\n", phy->autoneg_advertised); + hw_dbg("autoneg_advertised %x\n", phy->autoneg_advertised); /* Do we want to advertise 10 Mb Half Duplex? */ if (phy->autoneg_advertised & ADVERTISE_10_HALF) { - hw_dbg(hw, "Advertise 10mb Half duplex\n"); + hw_dbg("Advertise 10mb Half duplex\n"); mii_autoneg_adv_reg |= NWAY_AR_10T_HD_CAPS; } /* Do we want to advertise 10 Mb Full Duplex? */ if (phy->autoneg_advertised & ADVERTISE_10_FULL) { - hw_dbg(hw, "Advertise 10mb Full duplex\n"); + hw_dbg("Advertise 10mb Full duplex\n"); mii_autoneg_adv_reg |= NWAY_AR_10T_FD_CAPS; } /* Do we want to advertise 100 Mb Half Duplex? */ if (phy->autoneg_advertised & ADVERTISE_100_HALF) { - hw_dbg(hw, "Advertise 100mb Half duplex\n"); + hw_dbg("Advertise 100mb Half duplex\n"); mii_autoneg_adv_reg |= NWAY_AR_100TX_HD_CAPS; } /* Do we want to advertise 100 Mb Full Duplex? */ if (phy->autoneg_advertised & ADVERTISE_100_FULL) { - hw_dbg(hw, "Advertise 100mb Full duplex\n"); + hw_dbg("Advertise 100mb Full duplex\n"); mii_autoneg_adv_reg |= NWAY_AR_100TX_FD_CAPS; } /* We do not allow the Phy to advertise 1000 Mb Half Duplex */ if (phy->autoneg_advertised & ADVERTISE_1000_HALF) - hw_dbg(hw, "Advertise 1000mb Half duplex request denied!\n"); + hw_dbg("Advertise 1000mb Half duplex request denied!\n"); /* Do we want to advertise 1000 Mb Full Duplex? */ if (phy->autoneg_advertised & ADVERTISE_1000_FULL) { - hw_dbg(hw, "Advertise 1000mb Full duplex\n"); + hw_dbg("Advertise 1000mb Full duplex\n"); mii_1000t_ctrl_reg |= CR_1000T_FD_CAPS; } @@ -780,7 +780,7 @@ static s32 igb_phy_setup_autoneg(struct e1000_hw *hw) mii_autoneg_adv_reg |= (NWAY_AR_ASM_DIR | NWAY_AR_PAUSE); break; default: - hw_dbg(hw, "Flow control param set incorrectly\n"); + hw_dbg("Flow control param set incorrectly\n"); ret_val = -E1000_ERR_CONFIG; goto out; } @@ -790,7 +790,7 @@ static s32 igb_phy_setup_autoneg(struct e1000_hw *hw) if (ret_val) goto out; - hw_dbg(hw, "Auto-Neg Advertising %x\n", mii_autoneg_adv_reg); + hw_dbg("Auto-Neg Advertising %x\n", mii_autoneg_adv_reg); if (phy->autoneg_mask & ADVERTISE_1000_FULL) { ret_val = hw->phy.ops.write_phy_reg(hw, @@ -805,7 +805,7 @@ out: } /** - * e1000_phy_force_speed_duplex_igp - Force speed/duplex for igp PHY + * igb_phy_force_speed_duplex_igp - Force speed/duplex for igp PHY * @hw: pointer to the HW structure * * Calls the PHY setup function to force speed and duplex. Clears the @@ -846,13 +846,12 @@ s32 igb_phy_force_speed_duplex_igp(struct e1000_hw *hw) if (ret_val) goto out; - hw_dbg(hw, "IGP PSCR: %X\n", phy_data); + hw_dbg("IGP PSCR: %X\n", phy_data); udelay(1); if (phy->autoneg_wait_to_complete) { - hw_dbg(hw, - "Waiting for forced speed/duplex link on IGP phy.\n"); + hw_dbg("Waiting for forced speed/duplex link on IGP phy.\n"); ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, @@ -862,7 +861,7 @@ s32 igb_phy_force_speed_duplex_igp(struct e1000_hw *hw) goto out; if (!link) - hw_dbg(hw, "Link taking longer than expected.\n"); + hw_dbg("Link taking longer than expected.\n"); /* Try once more */ ret_val = igb_phy_has_link(hw, @@ -878,7 +877,7 @@ out: } /** - * e1000_phy_force_speed_duplex_m88 - Force speed/duplex for m88 PHY + * igb_phy_force_speed_duplex_m88 - Force speed/duplex for m88 PHY * @hw: pointer to the HW structure * * Calls the PHY setup function to force speed and duplex. Clears the @@ -909,7 +908,7 @@ s32 igb_phy_force_speed_duplex_m88(struct e1000_hw *hw) if (ret_val) goto out; - hw_dbg(hw, "M88E1000 PSCR: %X\n", phy_data); + hw_dbg("M88E1000 PSCR: %X\n", phy_data); ret_val = hw->phy.ops.read_phy_reg(hw, PHY_CONTROL, &phy_data); if (ret_val) @@ -927,8 +926,7 @@ s32 igb_phy_force_speed_duplex_m88(struct e1000_hw *hw) udelay(1); if (phy->autoneg_wait_to_complete) { - hw_dbg(hw, - "Waiting for forced speed/duplex link on M88 phy.\n"); + hw_dbg("Waiting for forced speed/duplex link on M88 phy.\n"); ret_val = igb_phy_has_link(hw, PHY_FORCE_LIMIT, @@ -993,7 +991,7 @@ out: } /** - * e1000_phy_force_speed_duplex_setup - Configure forced PHY speed/duplex + * igb_phy_force_speed_duplex_setup - Configure forced PHY speed/duplex * @hw: pointer to the HW structure * @phy_ctrl: pointer to current value of PHY_CONTROL * @@ -1028,11 +1026,11 @@ static void igb_phy_force_speed_duplex_setup(struct e1000_hw *hw, if (mac->forced_speed_duplex & E1000_ALL_HALF_DUPLEX) { ctrl &= ~E1000_CTRL_FD; *phy_ctrl &= ~MII_CR_FULL_DUPLEX; - hw_dbg(hw, "Half Duplex\n"); + hw_dbg("Half Duplex\n"); } else { ctrl |= E1000_CTRL_FD; *phy_ctrl |= MII_CR_FULL_DUPLEX; - hw_dbg(hw, "Full Duplex\n"); + hw_dbg("Full Duplex\n"); } /* Forcing 10mb or 100mb? */ @@ -1040,12 +1038,12 @@ static void igb_phy_force_speed_duplex_setup(struct e1000_hw *hw, ctrl |= E1000_CTRL_SPD_100; *phy_ctrl |= MII_CR_SPEED_100; *phy_ctrl &= ~(MII_CR_SPEED_1000 | MII_CR_SPEED_10); - hw_dbg(hw, "Forcing 100mb\n"); + hw_dbg("Forcing 100mb\n"); } else { ctrl &= ~(E1000_CTRL_SPD_1000 | E1000_CTRL_SPD_100); *phy_ctrl |= MII_CR_SPEED_10; *phy_ctrl &= ~(MII_CR_SPEED_1000 | MII_CR_SPEED_100); - hw_dbg(hw, "Forcing 10mb\n"); + hw_dbg("Forcing 10mb\n"); } igb_config_collision_dist(hw); @@ -1054,7 +1052,7 @@ static void igb_phy_force_speed_duplex_setup(struct e1000_hw *hw, } /** - * e1000_set_d3_lplu_state - Sets low power link up state for D3 + * igb_set_d3_lplu_state - Sets low power link up state for D3 * @hw: pointer to the HW structure * @active: boolean used to enable/disable lplu * @@ -1146,7 +1144,7 @@ out: } /** - * e1000_check_downshift - Checks whether a downshift in speed occured + * igb_check_downshift - Checks whether a downshift in speed occured * @hw: pointer to the HW structure * * Success returns 0, Failure returns 1 @@ -1188,7 +1186,7 @@ out: } /** - * e1000_check_polarity_m88 - Checks the polarity. + * igb_check_polarity_m88 - Checks the polarity. * @hw: pointer to the HW structure * * Success returns 0, Failure returns -E1000_ERR_PHY (-2) @@ -1212,7 +1210,7 @@ static s32 igb_check_polarity_m88(struct e1000_hw *hw) } /** - * e1000_check_polarity_igp - Checks the polarity. + * igb_check_polarity_igp - Checks the polarity. * @hw: pointer to the HW structure * * Success returns 0, Failure returns -E1000_ERR_PHY (-2) @@ -1260,7 +1258,7 @@ out: } /** - * e1000_wait_autoneg - Wait for auto-neg compeletion + * igb_wait_autoneg - Wait for auto-neg compeletion * @hw: pointer to the HW structure * * Waits for auto-negotiation to complete or for the auto-negotiation time @@ -1292,7 +1290,7 @@ static s32 igb_wait_autoneg(struct e1000_hw *hw) } /** - * e1000_phy_has_link - Polls PHY for link + * igb_phy_has_link - Polls PHY for link * @hw: pointer to the HW structure * @iterations: number of times to poll for link * @usec_interval: delay between polling attempts @@ -1332,7 +1330,7 @@ s32 igb_phy_has_link(struct e1000_hw *hw, u32 iterations, } /** - * e1000_get_cable_length_m88 - Determine cable length for m88 PHY + * igb_get_cable_length_m88 - Determine cable length for m88 PHY * @hw: pointer to the HW structure * * Reads the PHY specific status register to retrieve the cable length @@ -1369,7 +1367,7 @@ out: } /** - * e1000_get_cable_length_igp_2 - Determine cable length for igp2 PHY + * igb_get_cable_length_igp_2 - Determine cable length for igp2 PHY * @hw: pointer to the HW structure * * The automatic gain control (agc) normalizes the amplitude of the @@ -1442,7 +1440,7 @@ out: } /** - * e1000_get_phy_info_m88 - Retrieve PHY information + * igb_get_phy_info_m88 - Retrieve PHY information * @hw: pointer to the HW structure * * Valid for only copper links. Read the PHY status register (sticky read) @@ -1459,7 +1457,7 @@ s32 igb_get_phy_info_m88(struct e1000_hw *hw) bool link; if (hw->phy.media_type != e1000_media_type_copper) { - hw_dbg(hw, "Phy info is only valid for copper media\n"); + hw_dbg("Phy info is only valid for copper media\n"); ret_val = -E1000_ERR_CONFIG; goto out; } @@ -1469,7 +1467,7 @@ s32 igb_get_phy_info_m88(struct e1000_hw *hw) goto out; if (!link) { - hw_dbg(hw, "Phy info is only valid if link is up\n"); + hw_dbg("Phy info is only valid if link is up\n"); ret_val = -E1000_ERR_CONFIG; goto out; } @@ -1523,7 +1521,7 @@ out: } /** - * e1000_get_phy_info_igp - Retrieve igp PHY information + * igb_get_phy_info_igp - Retrieve igp PHY information * @hw: pointer to the HW structure * * Read PHY status to determine if link is up. If link is up, then @@ -1543,7 +1541,7 @@ s32 igb_get_phy_info_igp(struct e1000_hw *hw) goto out; if (!link) { - hw_dbg(hw, "Phy info is only valid if link is up\n"); + hw_dbg("Phy info is only valid if link is up\n"); ret_val = -E1000_ERR_CONFIG; goto out; } @@ -1590,7 +1588,7 @@ out: } /** - * e1000_phy_sw_reset - PHY software reset + * igb_phy_sw_reset - PHY software reset * @hw: pointer to the HW structure * * Does a software reset of the PHY by reading the PHY control register and @@ -1617,7 +1615,7 @@ out: } /** - * e1000_phy_hw_reset - PHY hardware reset + * igb_phy_hw_reset - PHY hardware reset * @hw: pointer to the HW structure * * Verify the reset block is not blocking us from resetting. Acquire @@ -1663,7 +1661,7 @@ out: /* Internal function pointers */ /** - * e1000_get_phy_cfg_done - Generic PHY configuration done + * igb_get_phy_cfg_done - Generic PHY configuration done * @hw: pointer to the HW structure * * Return success if silicon family did not implement a family specific @@ -1678,7 +1676,7 @@ static s32 igb_get_phy_cfg_done(struct e1000_hw *hw) } /** - * e1000_release_phy - Generic release PHY + * igb_release_phy - Generic release PHY * @hw: pointer to the HW structure * * Return if silicon family does not require a semaphore when accessing the @@ -1691,7 +1689,7 @@ static void igb_release_phy(struct e1000_hw *hw) } /** - * e1000_acquire_phy - Generic acquire PHY + * igb_acquire_phy - Generic acquire PHY * @hw: pointer to the HW structure * * Return success if silicon family does not require a semaphore when @@ -1706,7 +1704,7 @@ static s32 igb_acquire_phy(struct e1000_hw *hw) } /** - * e1000_phy_force_speed_duplex - Generic force PHY speed/duplex + * igb_phy_force_speed_duplex - Generic force PHY speed/duplex * @hw: pointer to the HW structure * * When the silicon family has not implemented a forced speed/duplex @@ -1721,14 +1719,14 @@ s32 igb_phy_force_speed_duplex(struct e1000_hw *hw) } /** - * e1000_phy_init_script_igp3 - Inits the IGP3 PHY + * igb_phy_init_script_igp3 - Inits the IGP3 PHY * @hw: pointer to the HW structure * * Initializes a Intel Gigabit PHY3 when an EEPROM is not present. **/ s32 igb_phy_init_script_igp3(struct e1000_hw *hw) { - hw_dbg(hw, "Running IGP 3 PHY init script\n"); + hw_dbg("Running IGP 3 PHY init script\n"); /* PHY init IGP 3 */ /* Enable rise/fall, 10-mode work in class-A */ diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h index 0eecb8b..2c48eec 100644 --- a/drivers/net/igb/igb.h +++ b/drivers/net/igb/igb.h @@ -150,6 +150,7 @@ struct igb_ring { u16 itr_register; u16 cpu; + int queue_index; unsigned int total_bytes; unsigned int total_packets; @@ -265,6 +266,7 @@ struct igb_adapter { int msg_enable; struct msix_entry *msix_entries; u32 eims_enable_mask; + u32 eims_other; /* to not mess up cache alignment, always add to the bottom */ unsigned long state; diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index 171d1fc..7bc6fae 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -71,8 +71,8 @@ static int igb_setup_all_tx_resources(struct igb_adapter *); static int igb_setup_all_rx_resources(struct igb_adapter *); static void igb_free_all_tx_resources(struct igb_adapter *); static void igb_free_all_rx_resources(struct igb_adapter *); -static void igb_free_tx_resources(struct igb_adapter *, struct igb_ring *); -static void igb_free_rx_resources(struct igb_adapter *, struct igb_ring *); +static void igb_free_tx_resources(struct igb_ring *); +static void igb_free_rx_resources(struct igb_ring *); void igb_update_stats(struct igb_adapter *); static int igb_probe(struct pci_dev *, const struct pci_device_id *); static void __devexit igb_remove(struct pci_dev *pdev); @@ -84,8 +84,8 @@ static void igb_configure_rx(struct igb_adapter *); static void igb_setup_rctl(struct igb_adapter *); static void igb_clean_all_tx_rings(struct igb_adapter *); static void igb_clean_all_rx_rings(struct igb_adapter *); -static void igb_clean_tx_ring(struct igb_adapter *, struct igb_ring *); -static void igb_clean_rx_ring(struct igb_adapter *, struct igb_ring *); +static void igb_clean_tx_ring(struct igb_ring *); +static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_multi(struct net_device *); static void igb_update_phy_info(unsigned long); static void igb_watchdog(unsigned long); @@ -102,12 +102,10 @@ static irqreturn_t igb_msix_other(int irq, void *); static irqreturn_t igb_msix_rx(int irq, void *); static irqreturn_t igb_msix_tx(int irq, void *); static int igb_clean_rx_ring_msix(struct napi_struct *, int); -static bool igb_clean_tx_irq(struct igb_adapter *, struct igb_ring *); +static bool igb_clean_tx_irq(struct igb_ring *); static int igb_clean(struct napi_struct *, int); -static bool igb_clean_rx_irq_adv(struct igb_adapter *, - struct igb_ring *, int *, int); -static void igb_alloc_rx_buffers_adv(struct igb_adapter *, - struct igb_ring *, int); +static bool igb_clean_rx_irq_adv(struct igb_ring *, int *, int); +static void igb_alloc_rx_buffers_adv(struct igb_ring *, int); static int igb_ioctl(struct net_device *, struct ifreq *, int cmd); static void igb_tx_timeout(struct net_device *); static void igb_reset_task(struct work_struct *); @@ -229,12 +227,11 @@ static int igb_alloc_queues(struct igb_adapter *adapter) for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = &(adapter->rx_ring[i]); ring->adapter = adapter; + ring->queue_index = i; ring->itr_register = E1000_ITR; - if (!ring->napi.poll) - netif_napi_add(adapter->netdev, &ring->napi, igb_clean, - adapter->napi.weight / - adapter->num_rx_queues); + /* set a default napi handler for each rx_ring */ + netif_napi_add(adapter->netdev, &ring->napi, igb_clean, 64); } return 0; } @@ -302,9 +299,6 @@ static void igb_configure_msix(struct igb_adapter *adapter) array_wr32(E1000_MSIXBM(0), vector++, E1000_EIMS_OTHER); - /* disable IAM for ICR interrupt bits */ - wr32(E1000_IAM, 0); - tmp = rd32(E1000_CTRL_EXT); /* enable MSI-X PBA support*/ tmp |= E1000_CTRL_EXT_PBA_CLR; @@ -315,6 +309,7 @@ static void igb_configure_msix(struct igb_adapter *adapter) wr32(E1000_CTRL_EXT, tmp); adapter->eims_enable_mask |= E1000_EIMS_OTHER; + adapter->eims_other = E1000_EIMS_OTHER; wrfl(); } @@ -357,6 +352,9 @@ static int igb_request_msix(struct igb_adapter *adapter) goto out; ring->itr_register = E1000_EITR(0) + (vector << 2); ring->itr_val = adapter->itr; + /* overwrite the poll routine for MSIX, we've already done + * netif_napi_add */ + ring->napi.poll = &igb_clean_rx_ring_msix; vector++; } @@ -365,9 +363,6 @@ static int igb_request_msix(struct igb_adapter *adapter) if (err) goto out; - adapter->napi.poll = igb_clean_rx_ring_msix; - for (i = 0; i < adapter->num_rx_queues; i++) - adapter->rx_ring[i].napi.poll = adapter->napi.poll; igb_configure_msix(adapter); return 0; out: @@ -436,12 +431,8 @@ static int igb_request_irq(struct igb_adapter *adapter) if (adapter->msix_entries) { err = igb_request_msix(adapter); - if (!err) { - /* enable IAM, auto-mask, - * DO NOT USE EIAM or IAM in legacy mode */ - wr32(E1000_IAM, IMS_ENABLE_MASK); + if (!err) goto request_done; - } /* fall back to MSI */ igb_reset_interrupt_capability(adapter); if (!pci_enable_msi(adapter->pdev)) @@ -450,7 +441,11 @@ static int igb_request_irq(struct igb_adapter *adapter) igb_free_all_rx_resources(adapter); adapter->num_rx_queues = 1; igb_alloc_queues(adapter); + } else { + wr32(E1000_MSIXBM(0), (E1000_EICR_RX_QUEUE0 | + E1000_EIMS_OTHER)); } + if (adapter->msi_enabled) { err = request_irq(adapter->pdev->irq, &igb_intr_msi, 0, netdev->name, netdev); @@ -502,9 +497,12 @@ static void igb_irq_disable(struct igb_adapter *adapter) struct e1000_hw *hw = &adapter->hw; if (adapter->msix_entries) { + wr32(E1000_EIAM, 0); wr32(E1000_EIMC, ~0); wr32(E1000_EIAC, 0); } + + wr32(E1000_IAM, 0); wr32(E1000_IMC, ~0); wrfl(); synchronize_irq(adapter->pdev->irq); @@ -519,13 +517,14 @@ static void igb_irq_enable(struct igb_adapter *adapter) struct e1000_hw *hw = &adapter->hw; if (adapter->msix_entries) { - wr32(E1000_EIMS, - adapter->eims_enable_mask); - wr32(E1000_EIAC, - adapter->eims_enable_mask); + wr32(E1000_EIAC, adapter->eims_enable_mask); + wr32(E1000_EIAM, adapter->eims_enable_mask); + wr32(E1000_EIMS, adapter->eims_enable_mask); wr32(E1000_IMS, E1000_IMS_LSC); - } else - wr32(E1000_IMS, IMS_ENABLE_MASK); + } else { + wr32(E1000_IMS, IMS_ENABLE_MASK); + wr32(E1000_IAM, IMS_ENABLE_MASK); + } } static void igb_update_mng_vlan(struct igb_adapter *adapter) @@ -632,12 +631,15 @@ static void igb_configure(struct igb_adapter *adapter) igb_configure_tx(adapter); igb_setup_rctl(adapter); igb_configure_rx(adapter); + + igb_rx_fifo_flush_82575(&adapter->hw); + /* call IGB_DESC_UNUSED which always leaves * at least 1 descriptor unused to make sure * next_to_use != next_to_clean */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = &adapter->rx_ring[i]; - igb_alloc_rx_buffers_adv(adapter, ring, IGB_DESC_UNUSED(ring)); + igb_alloc_rx_buffers_adv(ring, IGB_DESC_UNUSED(ring)); } @@ -660,13 +662,10 @@ int igb_up(struct igb_adapter *adapter) clear_bit(__IGB_DOWN, &adapter->state); - napi_enable(&adapter->napi); - - if (adapter->msix_entries) { - for (i = 0; i < adapter->num_rx_queues; i++) - napi_enable(&adapter->rx_ring[i].napi); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_enable(&adapter->rx_ring[i].napi); + if (adapter->msix_entries) igb_configure_msix(adapter); - } /* Clear any pending interrupts. */ rd32(E1000_ICR); @@ -703,11 +702,9 @@ void igb_down(struct igb_adapter *adapter) wrfl(); msleep(10); - napi_disable(&adapter->napi); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_disable(&adapter->rx_ring[i].napi); - if (adapter->msix_entries) - for (i = 0; i < adapter->num_rx_queues; i++) - napi_disable(&adapter->rx_ring[i].napi); igb_irq_disable(adapter); del_timer_sync(&adapter->watchdog_timer); @@ -854,7 +851,6 @@ static int __devinit igb_probe(struct pci_dev *pdev, struct e1000_hw *hw; const struct e1000_info *ei = igb_info_tbl[ent->driver_data]; unsigned long mmio_start, mmio_len; - static int cards_found; int i, err, pci_using_dac; u16 eeprom_data = 0; u16 eeprom_apme_mask = IGB_EEPROM_APME; @@ -933,7 +929,6 @@ static int __devinit igb_probe(struct pci_dev *pdev, igb_set_ethtool_ops(netdev); netdev->tx_timeout = &igb_tx_timeout; netdev->watchdog_timeo = 5 * HZ; - netif_napi_add(netdev, &adapter->napi, igb_clean, 64); netdev->vlan_rx_register = igb_vlan_rx_register; netdev->vlan_rx_add_vid = igb_vlan_rx_add_vid; netdev->vlan_rx_kill_vid = igb_vlan_rx_kill_vid; @@ -947,8 +942,6 @@ static int __devinit igb_probe(struct pci_dev *pdev, netdev->mem_start = mmio_start; netdev->mem_end = mmio_start + mmio_len; - adapter->bd_number = cards_found; - /* PCI config space info */ hw->vendor_id = pdev->vendor; hw->device_id = pdev->device; @@ -1133,7 +1126,6 @@ static int __devinit igb_probe(struct pci_dev *pdev, adapter->msi_enabled ? "MSI" : "legacy", adapter->num_rx_queues, adapter->num_tx_queues); - cards_found++; return 0; err_register: @@ -1301,15 +1293,14 @@ static int igb_open(struct net_device *netdev) /* From here on the code is the same as igb_up() */ clear_bit(__IGB_DOWN, &adapter->state); - napi_enable(&adapter->napi); - if (adapter->msix_entries) - for (i = 0; i < adapter->num_rx_queues; i++) - napi_enable(&adapter->rx_ring[i].napi); - - igb_irq_enable(adapter); + for (i = 0; i < adapter->num_rx_queues; i++) + napi_enable(&adapter->rx_ring[i].napi); /* Clear any pending interrupts. */ rd32(E1000_ICR); + + igb_irq_enable(adapter); + /* Fire a link status change interrupt to start the watchdog. */ wr32(E1000_ICS, E1000_ICS_LSC); @@ -1423,8 +1414,7 @@ static int igb_setup_all_tx_resources(struct igb_adapter *adapter) dev_err(&adapter->pdev->dev, "Allocation for Tx Queue %u failed\n", i); for (i--; i >= 0; i--) - igb_free_tx_resources(adapter, - &adapter->tx_ring[i]); + igb_free_tx_resources(&adapter->tx_ring[i]); break; } } @@ -1538,8 +1528,6 @@ int igb_setup_rx_resources(struct igb_adapter *adapter, rx_ring->pending_skb = NULL; rx_ring->adapter = adapter; - /* FIXME: do we want to setup ring->napi->poll here? */ - rx_ring->napi.poll = adapter->napi.poll; return 0; @@ -1567,8 +1555,7 @@ static int igb_setup_all_rx_resources(struct igb_adapter *adapter) dev_err(&adapter->pdev->dev, "Allocation for Rx Queue %u failed\n", i); for (i--; i >= 0; i--) - igb_free_rx_resources(adapter, - &adapter->rx_ring[i]); + igb_free_rx_resources(&adapter->rx_ring[i]); break; } } @@ -1796,12 +1783,11 @@ static void igb_configure_rx(struct igb_adapter *adapter) * * Free all transmit software resources **/ -static void igb_free_tx_resources(struct igb_adapter *adapter, - struct igb_ring *tx_ring) +static void igb_free_tx_resources(struct igb_ring *tx_ring) { - struct pci_dev *pdev = adapter->pdev; + struct pci_dev *pdev = tx_ring->adapter->pdev; - igb_clean_tx_ring(adapter, tx_ring); + igb_clean_tx_ring(tx_ring); vfree(tx_ring->buffer_info); tx_ring->buffer_info = NULL; @@ -1822,7 +1808,7 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) int i; for (i = 0; i < adapter->num_tx_queues; i++) - igb_free_tx_resources(adapter, &adapter->tx_ring[i]); + igb_free_tx_resources(&adapter->tx_ring[i]); } static void igb_unmap_and_free_tx_resource(struct igb_adapter *adapter, @@ -1848,9 +1834,9 @@ static void igb_unmap_and_free_tx_resource(struct igb_adapter *adapter, * @adapter: board private structure * @tx_ring: ring to be cleaned **/ -static void igb_clean_tx_ring(struct igb_adapter *adapter, - struct igb_ring *tx_ring) +static void igb_clean_tx_ring(struct igb_ring *tx_ring) { + struct igb_adapter *adapter = tx_ring->adapter; struct igb_buffer *buffer_info; unsigned long size; unsigned int i; @@ -1887,7 +1873,7 @@ static void igb_clean_all_tx_rings(struct igb_adapter *adapter) int i; for (i = 0; i < adapter->num_tx_queues; i++) - igb_clean_tx_ring(adapter, &adapter->tx_ring[i]); + igb_clean_tx_ring(&adapter->tx_ring[i]); } /** @@ -1897,12 +1883,11 @@ static void igb_clean_all_tx_rings(struct igb_adapter *adapter) * * Free all receive software resources **/ -static void igb_free_rx_resources(struct igb_adapter *adapter, - struct igb_ring *rx_ring) +static void igb_free_rx_resources(struct igb_ring *rx_ring) { - struct pci_dev *pdev = adapter->pdev; + struct pci_dev *pdev = rx_ring->adapter->pdev; - igb_clean_rx_ring(adapter, rx_ring); + igb_clean_rx_ring(rx_ring); vfree(rx_ring->buffer_info); rx_ring->buffer_info = NULL; @@ -1923,7 +1908,7 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) int i; for (i = 0; i < adapter->num_rx_queues; i++) - igb_free_rx_resources(adapter, &adapter->rx_ring[i]); + igb_free_rx_resources(&adapter->rx_ring[i]); } /** @@ -1931,9 +1916,9 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) * @adapter: board private structure * @rx_ring: ring to free buffers from **/ -static void igb_clean_rx_ring(struct igb_adapter *adapter, - struct igb_ring *rx_ring) +static void igb_clean_rx_ring(struct igb_ring *rx_ring) { + struct igb_adapter *adapter = rx_ring->adapter; struct igb_buffer *buffer_info; struct pci_dev *pdev = adapter->pdev; unsigned long size; @@ -1997,7 +1982,7 @@ static void igb_clean_all_rx_rings(struct igb_adapter *adapter) int i; for (i = 0; i < adapter->num_rx_queues; i++) - igb_clean_rx_ring(adapter, &adapter->rx_ring[i]); + igb_clean_rx_ring(&adapter->rx_ring[i]); } /** @@ -3041,26 +3026,19 @@ static irqreturn_t igb_msix_other(int irq, void *data) struct net_device *netdev = data; struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 eicr; - /* disable interrupts from the "other" bit, avoid re-entry */ - wr32(E1000_EIMC, E1000_EIMS_OTHER); - - eicr = rd32(E1000_EICR); + u32 icr = rd32(E1000_ICR); - if (eicr & E1000_EIMS_OTHER) { - u32 icr = rd32(E1000_ICR); - /* reading ICR causes bit 31 of EICR to be cleared */ - if (!(icr & E1000_ICR_LSC)) - goto no_link_interrupt; - hw->mac.get_link_status = 1; - /* guard against interrupt when we're going down */ - if (!test_bit(__IGB_DOWN, &adapter->state)) - mod_timer(&adapter->watchdog_timer, jiffies + 1); - } + /* reading ICR causes bit 31 of EICR to be cleared */ + if (!(icr & E1000_ICR_LSC)) + goto no_link_interrupt; + hw->mac.get_link_status = 1; + /* guard against interrupt when we're going down */ + if (!test_bit(__IGB_DOWN, &adapter->state)) + mod_timer(&adapter->watchdog_timer, jiffies + 1); no_link_interrupt: wr32(E1000_IMS, E1000_IMS_LSC); - wr32(E1000_EIMS, E1000_EIMS_OTHER); + wr32(E1000_EIMS, adapter->eims_other); return IRQ_HANDLED; } @@ -3076,7 +3054,7 @@ static irqreturn_t igb_msix_tx(int irq, void *data) tx_ring->total_bytes = 0; tx_ring->total_packets = 0; - if (!igb_clean_tx_irq(adapter, tx_ring)) + if (!igb_clean_tx_irq(tx_ring)) /* Ring was not completely cleaned, so fire another interrupt */ wr32(E1000_EICS, tx_ring->eims_value); @@ -3091,21 +3069,19 @@ static irqreturn_t igb_msix_rx(int irq, void *data) struct igb_adapter *adapter = rx_ring->adapter; struct e1000_hw *hw = &adapter->hw; - if (!rx_ring->itr_val) - wr32(E1000_EIMC, rx_ring->eims_value); + /* Write the ITR value calculated at the end of the + * previous interrupt. + */ - if (netif_rx_schedule_prep(adapter->netdev, &rx_ring->napi)) { - rx_ring->total_bytes = 0; - rx_ring->total_packets = 0; - rx_ring->no_itr_adjust = 0; - __netif_rx_schedule(adapter->netdev, &rx_ring->napi); - } else { - if (!rx_ring->no_itr_adjust) { - igb_lower_rx_eitr(adapter, rx_ring); - rx_ring->no_itr_adjust = 1; - } + if (adapter->set_itr) { + wr32(rx_ring->itr_register, + 1000000000 / (rx_ring->itr_val * 256)); + adapter->set_itr = 0; } + if (netif_rx_schedule_prep(adapter->netdev, &rx_ring->napi)) + __netif_rx_schedule(adapter->netdev, &rx_ring->napi); + return IRQ_HANDLED; } @@ -3119,7 +3095,6 @@ static irqreturn_t igb_intr_msi(int irq, void *data) { struct net_device *netdev = data; struct igb_adapter *adapter = netdev_priv(netdev); - struct napi_struct *napi = &adapter->napi; struct e1000_hw *hw = &adapter->hw; /* read ICR disables interrupts using IAM */ u32 icr = rd32(E1000_ICR); @@ -3128,25 +3103,17 @@ static irqreturn_t igb_intr_msi(int irq, void *data) * previous interrupt. */ if (adapter->set_itr) { - wr32(E1000_ITR, - 1000000000 / (adapter->itr * 256)); + wr32(E1000_ITR, 1000000000 / (adapter->itr * 256)); adapter->set_itr = 0; } - /* read ICR disables interrupts using IAM */ if (icr & (E1000_ICR_RXSEQ | E1000_ICR_LSC)) { hw->mac.get_link_status = 1; if (!test_bit(__IGB_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, jiffies + 1); } - if (netif_rx_schedule_prep(netdev, napi)) { - adapter->tx_ring->total_bytes = 0; - adapter->tx_ring->total_packets = 0; - adapter->rx_ring->total_bytes = 0; - adapter->rx_ring->total_packets = 0; - __netif_rx_schedule(netdev, napi); - } + netif_rx_schedule(netdev, &adapter->rx_ring[0].napi); return IRQ_HANDLED; } @@ -3160,7 +3127,6 @@ static irqreturn_t igb_intr(int irq, void *data) { struct net_device *netdev = data; struct igb_adapter *adapter = netdev_priv(netdev); - struct napi_struct *napi = &adapter->napi; struct e1000_hw *hw = &adapter->hw; /* Interrupt Auto-Mask...upon reading ICR, interrupts are masked. No * need for the IMC write */ @@ -3173,8 +3139,7 @@ static irqreturn_t igb_intr(int irq, void *data) * previous interrupt. */ if (adapter->set_itr) { - wr32(E1000_ITR, - 1000000000 / (adapter->itr * 256)); + wr32(E1000_ITR, 1000000000 / (adapter->itr * 256)); adapter->set_itr = 0; } @@ -3192,13 +3157,7 @@ static irqreturn_t igb_intr(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } - if (netif_rx_schedule_prep(netdev, napi)) { - adapter->tx_ring->total_bytes = 0; - adapter->rx_ring->total_bytes = 0; - adapter->tx_ring->total_packets = 0; - adapter->rx_ring->total_packets = 0; - __netif_rx_schedule(netdev, napi); - } + netif_rx_schedule(netdev, &adapter->rx_ring[0].napi); return IRQ_HANDLED; } @@ -3227,14 +3186,13 @@ static int igb_clean(struct napi_struct *napi, int budget) * the lock means tx_ring[i] is currently being cleaned anyway. */ for (i = 0; i < adapter->num_tx_queues; i++) { if (spin_trylock(&adapter->tx_ring[i].tx_clean_lock)) { - tx_clean_complete &= igb_clean_tx_irq(adapter, - &adapter->tx_ring[i]); + tx_clean_complete &= igb_clean_tx_irq(&adapter->tx_ring[i]); spin_unlock(&adapter->tx_ring[i].tx_clean_lock); } } for (i = 0; i < adapter->num_rx_queues; i++) - igb_clean_rx_irq_adv(adapter, &adapter->rx_ring[i], &work_done, + igb_clean_rx_irq_adv(&adapter->rx_ring[i], &work_done, adapter->rx_ring[i].napi.weight); /* If no Tx and not enough Rx work done, exit the polling mode */ @@ -3264,7 +3222,7 @@ static int igb_clean_rx_ring_msix(struct napi_struct *napi, int budget) if (!netif_carrier_ok(netdev)) goto quit_polling; - igb_clean_rx_irq_adv(adapter, rx_ring, &work_done, budget); + igb_clean_rx_irq_adv(rx_ring, &work_done, budget); /* If not enough Rx work done, exit the polling mode */ @@ -3282,6 +3240,10 @@ quit_polling: else if (mean_size > IGB_DYN_ITR_LENGTH_HIGH) igb_lower_rx_eitr(adapter, rx_ring); } + + if (!test_bit(__IGB_DOWN, &adapter->state)) + wr32(E1000_EIMS, rx_ring->eims_value); + return 0; } @@ -3299,11 +3261,11 @@ static inline u32 get_head(struct igb_ring *tx_ring) * @adapter: board private structure * returns true if ring is completely cleaned **/ -static bool igb_clean_tx_irq(struct igb_adapter *adapter, - struct igb_ring *tx_ring) +static bool igb_clean_tx_irq(struct igb_ring *tx_ring) { - struct net_device *netdev = adapter->netdev; + struct igb_adapter *adapter = tx_ring->adapter; struct e1000_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; struct e1000_tx_desc *tx_desc; struct igb_buffer *buffer_info; struct sk_buff *skb; @@ -3458,10 +3420,10 @@ static inline void igb_rx_checksum_adv(struct igb_adapter *adapter, adapter->hw_csum_good++; } -static bool igb_clean_rx_irq_adv(struct igb_adapter *adapter, - struct igb_ring *rx_ring, - int *work_done, int budget) +static bool igb_clean_rx_irq_adv(struct igb_ring *rx_ring, + int *work_done, int budget) { + struct igb_adapter *adapter = rx_ring->adapter; struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; union e1000_adv_rx_desc *rx_desc , *next_rxd; @@ -3584,8 +3546,7 @@ next_desc: /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { - igb_alloc_rx_buffers_adv(adapter, rx_ring, - cleaned_count); + igb_alloc_rx_buffers_adv(rx_ring, cleaned_count); cleaned_count = 0; } @@ -3600,7 +3561,7 @@ out: cleaned_count = IGB_DESC_UNUSED(rx_ring); if (cleaned_count) - igb_alloc_rx_buffers_adv(adapter, rx_ring, cleaned_count); + igb_alloc_rx_buffers_adv(rx_ring, cleaned_count); rx_ring->total_packets += total_packets; rx_ring->total_bytes += total_bytes; @@ -3616,10 +3577,10 @@ out: * igb_alloc_rx_buffers_adv - Replace used receive buffers; packet split * @adapter: address of board private structure **/ -static void igb_alloc_rx_buffers_adv(struct igb_adapter *adapter, - struct igb_ring *rx_ring, +static void igb_alloc_rx_buffers_adv(struct igb_ring *rx_ring, int cleaned_count) { + struct igb_adapter *adapter = rx_ring->adapter; struct net_device *netdev = adapter->netdev; struct pci_dev *pdev = adapter->pdev; union e1000_adv_rx_desc *rx_desc; @@ -4062,10 +4023,10 @@ static void igb_netpoll(struct net_device *netdev) igb_irq_disable(adapter); for (i = 0; i < adapter->num_tx_queues; i++) - igb_clean_tx_irq(adapter, &adapter->tx_ring[i]); + igb_clean_tx_irq(&adapter->tx_ring[i]); for (i = 0; i < adapter->num_rx_queues; i++) - igb_clean_rx_irq_adv(adapter, &adapter->rx_ring[i], + igb_clean_rx_irq_adv(&adapter->rx_ring[i], &work_done, adapter->rx_ring[i].napi.weight); diff --git a/drivers/net/ipg.c b/drivers/net/ipg.c index 2c03f4e..7373daf 100644 --- a/drivers/net/ipg.c +++ b/drivers/net/ipg.c @@ -42,7 +42,6 @@ #define ipg_r16(reg) ioread16(ioaddr + (reg)) #define ipg_r8(reg) ioread8(ioaddr + (reg)) -#define JUMBO_FRAME_4k_ONLY enum { netdev_io_size = 128 }; @@ -55,6 +54,14 @@ MODULE_DESCRIPTION("IC Plus IP1000 Gigabit Ethernet Adapter Linux Driver"); MODULE_LICENSE("GPL"); /* + * Defaults + */ +#define IPG_MAX_RXFRAME_SIZE 0x0600 +#define IPG_RXFRAG_SIZE 0x0600 +#define IPG_RXSUPPORT_SIZE 0x0600 +#define IPG_IS_JUMBO false + +/* * Variable record -- index by leading revision/length * Revision/Length(=N*4), Address1, Data1, Address2, Data2,...,AddressN,DataN */ @@ -631,6 +638,7 @@ static void ipg_nic_set_multicast_list(struct net_device *dev) static int ipg_io_config(struct net_device *dev) { + struct ipg_nic_private *sp = netdev_priv(dev); void __iomem *ioaddr = ipg_ioaddr(dev); u32 origmacctrl; u32 restoremacctrl; @@ -670,7 +678,7 @@ static int ipg_io_config(struct net_device *dev) /* Set RECEIVEMODE register. */ ipg_nic_set_multicast_list(dev); - ipg_w16(IPG_MAX_RXFRAME_SIZE, MAX_FRAME_SIZE); + ipg_w16(sp->max_rxframe_size, MAX_FRAME_SIZE); ipg_w8(IPG_RXDMAPOLLPERIOD_VALUE, RX_DMA_POLL_PERIOD); ipg_w8(IPG_RXDMAURGENTTHRESH_VALUE, RX_DMA_URGENT_THRESH); @@ -730,7 +738,7 @@ static int ipg_get_rxbuff(struct net_device *dev, int entry) IPG_DEBUG_MSG("_get_rxbuff\n"); - skb = netdev_alloc_skb(dev, IPG_RXSUPPORT_SIZE + NET_IP_ALIGN); + skb = netdev_alloc_skb(dev, sp->rxsupport_size + NET_IP_ALIGN); if (!skb) { sp->rx_buff[entry] = NULL; return -ENOMEM; @@ -751,7 +759,7 @@ static int ipg_get_rxbuff(struct net_device *dev, int entry) sp->rx_buf_sz, PCI_DMA_FROMDEVICE)); /* Set the RFD fragment length. */ - rxfragsize = IPG_RXFRAG_SIZE; + rxfragsize = sp->rxfrag_size; rxfd->frag_info |= cpu_to_le64((rxfragsize << 48) & IPG_RFI_FRAGLEN); return 0; @@ -1076,8 +1084,6 @@ static int ipg_nic_rxrestore(struct net_device *dev) return 0; } -#ifdef JUMBO_FRAME - /* use jumboindex and jumbosize to control jumbo frame status * initial status is jumboindex=-1 and jumbosize=0 * 1. jumboindex = -1 and jumbosize=0 : previous jumbo frame has been done. @@ -1097,7 +1103,7 @@ enum { FRAME_WITH_START_WITH_END = 11 }; -inline void ipg_nic_rx_free_skb(struct net_device *dev) +static void ipg_nic_rx_free_skb(struct net_device *dev) { struct ipg_nic_private *sp = netdev_priv(dev); unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; @@ -1113,7 +1119,7 @@ inline void ipg_nic_rx_free_skb(struct net_device *dev) } } -inline int ipg_nic_rx_check_frame_type(struct net_device *dev) +static int ipg_nic_rx_check_frame_type(struct net_device *dev) { struct ipg_nic_private *sp = netdev_priv(dev); struct ipg_rx *rxfd = sp->rxd + (sp->rx_current % IPG_RFDLIST_LENGTH); @@ -1126,7 +1132,7 @@ inline int ipg_nic_rx_check_frame_type(struct net_device *dev) return type; } -inline int ipg_nic_rx_check_error(struct net_device *dev) +static int ipg_nic_rx_check_error(struct net_device *dev) { struct ipg_nic_private *sp = netdev_priv(dev); unsigned int entry = sp->rx_current % IPG_RFDLIST_LENGTH; @@ -1209,8 +1215,8 @@ static void ipg_nic_rx_with_start_and_end(struct net_device *dev, /* accept this frame and send to upper layer */ framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; - if (framelen > IPG_RXFRAG_SIZE) - framelen = IPG_RXFRAG_SIZE; + if (framelen > sp->rxfrag_size) + framelen = sp->rxfrag_size; skb_put(skb, framelen); skb->protocol = eth_type_trans(skb, dev); @@ -1243,10 +1249,10 @@ static void ipg_nic_rx_with_start(struct net_device *dev, pci_unmap_single(pdev, le64_to_cpu(rxfd->frag_info & ~IPG_RFI_FRAGLEN), sp->rx_buf_sz, PCI_DMA_FROMDEVICE); - skb_put(skb, IPG_RXFRAG_SIZE); + skb_put(skb, sp->rxfrag_size); jumbo->found_start = 1; - jumbo->current_size = IPG_RXFRAG_SIZE; + jumbo->current_size = sp->rxfrag_size; jumbo->skb = skb; sp->rx_buff[entry] = NULL; @@ -1272,11 +1278,7 @@ static void ipg_nic_rx_with_end(struct net_device *dev, framelen = le64_to_cpu(rxfd->rfs) & IPG_RFS_RXFRAMELEN; endframelen = framelen - jumbo->current_size; - /* - if (framelen > IPG_RXFRAG_SIZE) - framelen=IPG_RXFRAG_SIZE; - */ - if (framelen > IPG_RXSUPPORT_SIZE) + if (framelen > sp->rxsupport_size) dev_kfree_skb_irq(jumbo->skb); else { memcpy(skb_put(jumbo->skb, endframelen), @@ -1316,11 +1318,11 @@ static void ipg_nic_rx_no_start_no_end(struct net_device *dev, if (skb) { if (jumbo->found_start) { - jumbo->current_size += IPG_RXFRAG_SIZE; - if (jumbo->current_size <= IPG_RXSUPPORT_SIZE) { + jumbo->current_size += sp->rxfrag_size; + if (jumbo->current_size <= sp->rxsupport_size) { memcpy(skb_put(jumbo->skb, - IPG_RXFRAG_SIZE), - skb->data, IPG_RXFRAG_SIZE); + sp->rxfrag_size), + skb->data, sp->rxfrag_size); } } dev->last_rx = jiffies; @@ -1334,7 +1336,7 @@ static void ipg_nic_rx_no_start_no_end(struct net_device *dev, } } -static int ipg_nic_rx(struct net_device *dev) +static int ipg_nic_rx_jumbo(struct net_device *dev) { struct ipg_nic_private *sp = netdev_priv(dev); unsigned int curr = sp->rx_current; @@ -1382,7 +1384,6 @@ static int ipg_nic_rx(struct net_device *dev) return 0; } -#else static int ipg_nic_rx(struct net_device *dev) { /* Transfer received Ethernet frames to higher network layers. */ @@ -1413,11 +1414,11 @@ static int ipg_nic_rx(struct net_device *dev) /* Check for jumbo frame arrival with too small * RXFRAG_SIZE. */ - if (framelen > IPG_RXFRAG_SIZE) { + if (framelen > sp->rxfrag_size) { IPG_DEBUG_MSG ("RFS FrameLen > allocated fragment size.\n"); - framelen = IPG_RXFRAG_SIZE; + framelen = sp->rxfrag_size; } if ((IPG_DROP_ON_RX_ETH_ERRORS && (le64_to_cpu(rxfd->rfs) & @@ -1556,7 +1557,6 @@ static int ipg_nic_rx(struct net_device *dev) return 0; } -#endif static void ipg_reset_after_host_error(struct work_struct *work) { @@ -1592,9 +1592,9 @@ static irqreturn_t ipg_interrupt_handler(int irq, void *dev_inst) IPG_DEBUG_MSG("_interrupt_handler\n"); -#ifdef JUMBO_FRAME - ipg_nic_rxrestore(dev); -#endif + if (sp->is_jumbo) + ipg_nic_rxrestore(dev); + spin_lock(&sp->lock); /* Get interrupt source information, and acknowledge @@ -1650,7 +1650,10 @@ static irqreturn_t ipg_interrupt_handler(int irq, void *dev_inst) sp->RFDListCheckedCount++; #endif - ipg_nic_rx(dev); + if (sp->is_jumbo) + ipg_nic_rx_jumbo(dev); + else + ipg_nic_rx(dev); } /* If TxDMAComplete interrupt, free used TFDs. */ @@ -1749,7 +1752,7 @@ static int ipg_nic_open(struct net_device *dev) IPG_DEBUG_MSG("_nic_open\n"); - sp->rx_buf_sz = IPG_RXSUPPORT_SIZE; + sp->rx_buf_sz = sp->rxsupport_size; /* Check for interrupt line conflicts, and request interrupt * line for IPG. @@ -1804,13 +1807,10 @@ static int ipg_nic_open(struct net_device *dev) if (ipg_config_autoneg(dev) < 0) printk(KERN_INFO "%s: Auto-negotiation error.\n", dev->name); -#ifdef JUMBO_FRAME /* initialize JUMBO Frame control variable */ sp->jumbo.found_start = 0; sp->jumbo.current_size = 0; sp->jumbo.skb = NULL; - dev->mtu = IPG_TXFRAG_SIZE; -#endif /* Enable transmit and receive operation of the IPG. */ ipg_w32((ipg_r32(MAC_CTRL) | IPG_MC_RX_ENABLE | IPG_MC_TX_ENABLE) & @@ -2119,6 +2119,9 @@ static int ipg_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int ipg_nic_change_mtu(struct net_device *dev, int new_mtu) { + struct ipg_nic_private *sp = netdev_priv(dev); + int err; + /* Function to accomodate changes to Maximum Transfer Unit * (or MTU) of IPG NIC. Cannot use default function since * the default will not allow for MTU > 1500 bytes. @@ -2126,16 +2129,33 @@ static int ipg_nic_change_mtu(struct net_device *dev, int new_mtu) IPG_DEBUG_MSG("_nic_change_mtu\n"); - /* Check that the new MTU value is between 68 (14 byte header, 46 - * byte payload, 4 byte FCS) and IPG_MAX_RXFRAME_SIZE, which - * corresponds to the MAXFRAMESIZE register in the IPG. + /* + * Check that the new MTU value is between 68 (14 byte header, 46 byte + * payload, 4 byte FCS) and 10 KB, which is the largest supported MTU. */ - if ((new_mtu < 68) || (new_mtu > IPG_MAX_RXFRAME_SIZE)) + if (new_mtu < 68 || new_mtu > 10240) return -EINVAL; + err = ipg_nic_stop(dev); + if (err) + return err; + dev->mtu = new_mtu; - return 0; + sp->max_rxframe_size = new_mtu; + + sp->rxfrag_size = new_mtu; + if (sp->rxfrag_size > 4088) + sp->rxfrag_size = 4088; + + sp->rxsupport_size = sp->max_rxframe_size; + + if (new_mtu > 0x0600) + sp->is_jumbo = true; + else + sp->is_jumbo = false; + + return ipg_nic_open(dev); } static int ipg_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) @@ -2240,6 +2260,11 @@ static int __devinit ipg_probe(struct pci_dev *pdev, spin_lock_init(&sp->lock); mutex_init(&sp->mii_mutex); + sp->is_jumbo = IPG_IS_JUMBO; + sp->rxfrag_size = IPG_RXFRAG_SIZE; + sp->rxsupport_size = IPG_RXSUPPORT_SIZE; + sp->max_rxframe_size = IPG_MAX_RXFRAME_SIZE; + /* Declare IPG NIC functions for Ethernet device methods. */ dev->open = &ipg_nic_open; diff --git a/drivers/net/ipg.h b/drivers/net/ipg.h index cda5388..e0e718a 100644 --- a/drivers/net/ipg.h +++ b/drivers/net/ipg.h @@ -536,83 +536,6 @@ enum ipg_regs { */ #define IPG_FRAMESBETWEENTXDMACOMPLETES 0x1 -#ifdef JUMBO_FRAME - -# ifdef JUMBO_FRAME_SIZE_2K -# define JUMBO_FRAME_SIZE 2048 -# define __IPG_RXFRAG_SIZE 2048 -# else -# ifdef JUMBO_FRAME_SIZE_3K -# define JUMBO_FRAME_SIZE 3072 -# define __IPG_RXFRAG_SIZE 3072 -# else -# ifdef JUMBO_FRAME_SIZE_4K -# define JUMBO_FRAME_SIZE 4096 -# define __IPG_RXFRAG_SIZE 4088 -# else -# ifdef JUMBO_FRAME_SIZE_5K -# define JUMBO_FRAME_SIZE 5120 -# define __IPG_RXFRAG_SIZE 4088 -# else -# ifdef JUMBO_FRAME_SIZE_6K -# define JUMBO_FRAME_SIZE 6144 -# define __IPG_RXFRAG_SIZE 4088 -# else -# ifdef JUMBO_FRAME_SIZE_7K -# define JUMBO_FRAME_SIZE 7168 -# define __IPG_RXFRAG_SIZE 4088 -# else -# ifdef JUMBO_FRAME_SIZE_8K -# define JUMBO_FRAME_SIZE 8192 -# define __IPG_RXFRAG_SIZE 4088 -# else -# ifdef JUMBO_FRAME_SIZE_9K -# define JUMBO_FRAME_SIZE 9216 -# define __IPG_RXFRAG_SIZE 4088 -# else -# ifdef JUMBO_FRAME_SIZE_10K -# define JUMBO_FRAME_SIZE 10240 -# define __IPG_RXFRAG_SIZE 4088 -# else -# define JUMBO_FRAME_SIZE 4096 -# endif -# endif -# endif -# endif -# endif -# endif -# endif -# endif -# endif -#endif - -/* Size of allocated received buffers. Nominally 0x0600. - * Define larger if expecting jumbo frames. - */ -#ifdef JUMBO_FRAME -/* IPG_TXFRAG_SIZE must <= 0x2b00, or TX will crash */ -#define IPG_TXFRAG_SIZE JUMBO_FRAME_SIZE -#endif - -/* Size of allocated received buffers. Nominally 0x0600. - * Define larger if expecting jumbo frames. - */ -#ifdef JUMBO_FRAME -/* 4088 = 4096 - 8 */ -#define IPG_RXFRAG_SIZE __IPG_RXFRAG_SIZE -#define IPG_RXSUPPORT_SIZE IPG_MAX_RXFRAME_SIZE -#else -#define IPG_RXFRAG_SIZE 0x0600 -#define IPG_RXSUPPORT_SIZE IPG_RXFRAG_SIZE -#endif - -/* IPG_MAX_RXFRAME_SIZE <= IPG_RXFRAG_SIZE */ -#ifdef JUMBO_FRAME -#define IPG_MAX_RXFRAME_SIZE JUMBO_FRAME_SIZE -#else -#define IPG_MAX_RXFRAME_SIZE 0x0600 -#endif - #define IPG_RFDLIST_LENGTH 0x100 /* Maximum number of RFDs to process per interrupt. @@ -786,9 +709,11 @@ struct ipg_nic_private { unsigned int tx_dirty; unsigned int rx_current; unsigned int rx_dirty; -#ifdef JUMBO_FRAME + bool is_jumbo; struct ipg_jumbo jumbo; -#endif + unsigned long rxfrag_size; + unsigned long rxsupport_size; + unsigned long max_rxframe_size; unsigned int rx_buf_sz; struct pci_dev *pdev; struct net_device *dev; diff --git a/drivers/net/ne.c b/drivers/net/ne.c index 874d291..1412697 100644 --- a/drivers/net/ne.c +++ b/drivers/net/ne.c @@ -217,7 +217,7 @@ static int __init do_ne_probe(struct net_device *dev) #ifndef MODULE struct net_device * __init ne_probe(int unit) { - struct net_device *dev = alloc_ei_netdev(); + struct net_device *dev = alloc_eip_netdev(); int err; if (!dev) @@ -490,7 +490,7 @@ static int __init ne_probe1(struct net_device *dev, unsigned long ioaddr) /* Snarf the interrupt now. There's no point in waiting since we cannot share and the board will usually be enabled. */ - ret = request_irq(dev->irq, ei_interrupt, 0, name, dev); + ret = request_irq(dev->irq, eip_interrupt, 0, name, dev); if (ret) { printk (" unable to get IRQ %d (errno=%d).\n", dev->irq, ret); goto err_out; @@ -534,7 +534,7 @@ static int __init ne_probe1(struct net_device *dev, unsigned long ioaddr) dev->open = &ne_open; dev->stop = &ne_close; #ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ei_poll; + dev->poll_controller = eip_poll; #endif NS8390_init(dev, 0); @@ -554,7 +554,7 @@ err_out: static int ne_open(struct net_device *dev) { - ei_open(dev); + eip_open(dev); return 0; } @@ -562,7 +562,7 @@ static int ne_close(struct net_device *dev) { if (ei_debug > 1) printk(KERN_DEBUG "%s: Shutting down ethercard.\n", dev->name); - ei_close(dev); + eip_close(dev); return 0; } @@ -814,7 +814,7 @@ static int __init ne_drv_probe(struct platform_device *pdev) if (!res || irq < 0) return -ENODEV; - dev = alloc_ei_netdev(); + dev = alloc_eip_netdev(); if (!dev) return -ENOMEM; dev->irq = irq; @@ -912,7 +912,7 @@ int __init init_module(void) int plat_found = !ne_init(); for (this_dev = 0; this_dev < MAX_NE_CARDS; this_dev++) { - struct net_device *dev = alloc_ei_netdev(); + struct net_device *dev = alloc_eip_netdev(); if (!dev) break; dev->irq = irq[this_dev]; diff --git a/drivers/net/ne2.c b/drivers/net/ne2.c index f4cd8c7..8f72563 100644 --- a/drivers/net/ne2.c +++ b/drivers/net/ne2.c @@ -280,7 +280,7 @@ static int __init do_ne2_probe(struct net_device *dev) #ifndef MODULE struct net_device * __init ne2_probe(int unit) { - struct net_device *dev = alloc_ei_netdev(); + struct net_device *dev = alloc_eip_netdev(); int err; if (!dev) @@ -457,7 +457,7 @@ static int __init ne2_probe1(struct net_device *dev, int slot) /* Snarf the interrupt now. There's no point in waiting since we cannot share and the board will usually be enabled. */ - retval = request_irq(dev->irq, ei_interrupt, 0, DRV_NAME, dev); + retval = request_irq(dev->irq, eip_interrupt, 0, DRV_NAME, dev); if (retval) { printk (" unable to get IRQ %d (irqval=%d).\n", dev->irq, retval); @@ -497,9 +497,9 @@ static int __init ne2_probe1(struct net_device *dev, int slot) dev->open = &ne_open; dev->stop = &ne_close; #ifdef CONFIG_NET_POLL_CONTROLLER - dev->poll_controller = ei_poll; + dev->poll_controller = eip_poll; #endif - NS8390_init(dev, 0); + NS8390p_init(dev, 0); retval = register_netdev(dev); if (retval) @@ -515,7 +515,7 @@ out: static int ne_open(struct net_device *dev) { - ei_open(dev); + eip_open(dev); return 0; } @@ -523,7 +523,7 @@ static int ne_close(struct net_device *dev) { if (ei_debug > 1) printk("%s: Shutting down ethercard.\n", dev->name); - ei_close(dev); + eip_close(dev); return 0; } @@ -748,7 +748,7 @@ retry: if (time_after(jiffies, dma_start + 2*HZ/100)) { /* 20ms */ printk("%s: timeout waiting for Tx RDC.\n", dev->name); ne_reset_8390(dev); - NS8390_init(dev,1); + NS8390p_init(dev, 1); break; } @@ -781,7 +781,7 @@ int __init init_module(void) int this_dev, found = 0; for (this_dev = 0; this_dev < MAX_NE_CARDS; this_dev++) { - dev = alloc_ei_netdev(); + dev = alloc_eip_netdev(); if (!dev) break; dev->irq = irq[this_dev]; diff --git a/drivers/net/niu.c b/drivers/net/niu.c index 918f802..de2a8a3 100644 --- a/drivers/net/niu.c +++ b/drivers/net/niu.c @@ -6385,6 +6385,162 @@ static int niu_get_eeprom(struct net_device *dev, return 0; } +static int niu_ethflow_to_class(int flow_type, u64 *class) +{ + switch (flow_type) { + case TCP_V4_FLOW: + *class = CLASS_CODE_TCP_IPV4; + break; + case UDP_V4_FLOW: + *class = CLASS_CODE_UDP_IPV4; + break; + case AH_ESP_V4_FLOW: + *class = CLASS_CODE_AH_ESP_IPV4; + break; + case SCTP_V4_FLOW: + *class = CLASS_CODE_SCTP_IPV4; + break; + case TCP_V6_FLOW: + *class = CLASS_CODE_TCP_IPV6; + break; + case UDP_V6_FLOW: + *class = CLASS_CODE_UDP_IPV6; + break; + case AH_ESP_V6_FLOW: + *class = CLASS_CODE_AH_ESP_IPV6; + break; + case SCTP_V6_FLOW: + *class = CLASS_CODE_SCTP_IPV6; + break; + default: + return -1; + } + + return 1; +} + +static u64 niu_flowkey_to_ethflow(u64 flow_key) +{ + u64 ethflow = 0; + + if (flow_key & FLOW_KEY_PORT) + ethflow |= RXH_DEV_PORT; + if (flow_key & FLOW_KEY_L2DA) + ethflow |= RXH_L2DA; + if (flow_key & FLOW_KEY_VLAN) + ethflow |= RXH_VLAN; + if (flow_key & FLOW_KEY_IPSA) + ethflow |= RXH_IP_SRC; + if (flow_key & FLOW_KEY_IPDA) + ethflow |= RXH_IP_DST; + if (flow_key & FLOW_KEY_PROTO) + ethflow |= RXH_L3_PROTO; + if (flow_key & (FLOW_KEY_L4_BYTE12 << FLOW_KEY_L4_0_SHIFT)) + ethflow |= RXH_L4_B_0_1; + if (flow_key & (FLOW_KEY_L4_BYTE12 << FLOW_KEY_L4_1_SHIFT)) + ethflow |= RXH_L4_B_2_3; + + return ethflow; + +} + +static int niu_ethflow_to_flowkey(u64 ethflow, u64 *flow_key) +{ + u64 key = 0; + + if (ethflow & RXH_DEV_PORT) + key |= FLOW_KEY_PORT; + if (ethflow & RXH_L2DA) + key |= FLOW_KEY_L2DA; + if (ethflow & RXH_VLAN) + key |= FLOW_KEY_VLAN; + if (ethflow & RXH_IP_SRC) + key |= FLOW_KEY_IPSA; + if (ethflow & RXH_IP_DST) + key |= FLOW_KEY_IPDA; + if (ethflow & RXH_L3_PROTO) + key |= FLOW_KEY_PROTO; + if (ethflow & RXH_L4_B_0_1) + key |= (FLOW_KEY_L4_BYTE12 << FLOW_KEY_L4_0_SHIFT); + if (ethflow & RXH_L4_B_2_3) + key |= (FLOW_KEY_L4_BYTE12 << FLOW_KEY_L4_1_SHIFT); + + *flow_key = key; + + return 1; + +} + +static int niu_get_hash_opts(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct niu *np = netdev_priv(dev); + u64 class; + + cmd->data = 0; + + if (!niu_ethflow_to_class(cmd->flow_type, &class)) + return -EINVAL; + + if (np->parent->tcam_key[class - CLASS_CODE_USER_PROG1] & + TCAM_KEY_DISC) + cmd->data = RXH_DISCARD; + else + + cmd->data = niu_flowkey_to_ethflow(np->parent->flow_key[class - + CLASS_CODE_USER_PROG1]); + return 0; +} + +static int niu_set_hash_opts(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct niu *np = netdev_priv(dev); + u64 class; + u64 flow_key = 0; + unsigned long flags; + + if (!niu_ethflow_to_class(cmd->flow_type, &class)) + return -EINVAL; + + if (class < CLASS_CODE_USER_PROG1 || + class > CLASS_CODE_SCTP_IPV6) + return -EINVAL; + + if (cmd->data & RXH_DISCARD) { + niu_lock_parent(np, flags); + flow_key = np->parent->tcam_key[class - + CLASS_CODE_USER_PROG1]; + flow_key |= TCAM_KEY_DISC; + nw64(TCAM_KEY(class - CLASS_CODE_USER_PROG1), flow_key); + np->parent->tcam_key[class - CLASS_CODE_USER_PROG1] = flow_key; + niu_unlock_parent(np, flags); + return 0; + } else { + /* Discard was set before, but is not set now */ + if (np->parent->tcam_key[class - CLASS_CODE_USER_PROG1] & + TCAM_KEY_DISC) { + niu_lock_parent(np, flags); + flow_key = np->parent->tcam_key[class - + CLASS_CODE_USER_PROG1]; + flow_key &= ~TCAM_KEY_DISC; + nw64(TCAM_KEY(class - CLASS_CODE_USER_PROG1), + flow_key); + np->parent->tcam_key[class - CLASS_CODE_USER_PROG1] = + flow_key; + niu_unlock_parent(np, flags); + } + } + + if (!niu_ethflow_to_flowkey(cmd->data, &flow_key)) + return -EINVAL; + + niu_lock_parent(np, flags); + nw64(FLOW_KEY(class - CLASS_CODE_USER_PROG1), flow_key); + np->parent->flow_key[class - CLASS_CODE_USER_PROG1] = flow_key; + niu_unlock_parent(np, flags); + + return 0; +} + static const struct { const char string[ETH_GSTRING_LEN]; } niu_xmac_stat_keys[] = { @@ -6615,6 +6771,8 @@ static const struct ethtool_ops niu_ethtool_ops = { .get_stats_count = niu_get_stats_count, .get_ethtool_stats = niu_get_ethtool_stats, .phys_id = niu_phys_id, + .get_rxhash = niu_get_hash_opts, + .set_rxhash = niu_set_hash_opts, }; static int niu_ldg_assign_ldn(struct niu *np, struct niu_parent *parent, diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c index 6572425..cfe8829 100644 --- a/drivers/net/r8169.c +++ b/drivers/net/r8169.c @@ -28,13 +28,7 @@ #include <asm/io.h> #include <asm/irq.h> -#ifdef CONFIG_R8169_NAPI -#define NAPI_SUFFIX "-NAPI" -#else -#define NAPI_SUFFIX "" -#endif - -#define RTL8169_VERSION "2.2LK" NAPI_SUFFIX +#define RTL8169_VERSION "2.3LK-NAPI" #define MODULENAME "r8169" #define PFX MODULENAME ": " @@ -57,16 +51,6 @@ #define TX_BUFFS_AVAIL(tp) \ (tp->dirty_tx + NUM_TX_DESC - tp->cur_tx - 1) -#ifdef CONFIG_R8169_NAPI -#define rtl8169_rx_skb netif_receive_skb -#define rtl8169_rx_hwaccel_skb vlan_hwaccel_receive_skb -#define rtl8169_rx_quota(count, quota) min(count, quota) -#else -#define rtl8169_rx_skb netif_rx -#define rtl8169_rx_hwaccel_skb vlan_hwaccel_rx -#define rtl8169_rx_quota(count, quota) count -#endif - /* Maximum events (Rx packets, etc.) to handle at each interrupt. */ static const int max_interrupt_work = 20; @@ -394,9 +378,7 @@ struct rtl8169_private { void __iomem *mmio_addr; /* memory map physical address */ struct pci_dev *pci_dev; /* Index of PCI device */ struct net_device *dev; -#ifdef CONFIG_R8169_NAPI struct napi_struct napi; -#endif spinlock_t lock; /* spin lock flag */ u32 msg_enable; int chipset; @@ -458,10 +440,7 @@ static int rtl8169_rx_interrupt(struct net_device *, struct rtl8169_private *, static int rtl8169_change_mtu(struct net_device *dev, int new_mtu); static void rtl8169_down(struct net_device *dev); static void rtl8169_rx_clear(struct rtl8169_private *tp); - -#ifdef CONFIG_R8169_NAPI static int rtl8169_poll(struct napi_struct *napi, int budget); -#endif static const unsigned int rtl8169_rx_config = (RX_FIFO_THRESH << RxCfgFIFOShift) | (RX_DMA_BURST << RxCfgDMAShift); @@ -843,10 +822,11 @@ static int rtl8169_rx_vlan_skb(struct rtl8169_private *tp, struct RxDesc *desc, struct sk_buff *skb) { u32 opts2 = le32_to_cpu(desc->opts2); + struct vlan_group *vlgrp = tp->vlgrp; int ret; - if (tp->vlgrp && (opts2 & RxVlanTag)) { - rtl8169_rx_hwaccel_skb(skb, tp->vlgrp, swab16(opts2 & 0xffff)); + if (vlgrp && (opts2 & RxVlanTag)) { + vlan_hwaccel_receive_skb(skb, vlgrp, swab16(opts2 & 0xffff)); ret = 0; } else ret = -1; @@ -1764,9 +1744,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->change_mtu = rtl8169_change_mtu; dev->set_mac_address = rtl_set_mac_address; -#ifdef CONFIG_R8169_NAPI netif_napi_add(dev, &tp->napi, rtl8169_poll, R8169_NAPI_WEIGHT); -#endif #ifdef CONFIG_R8169_VLAN dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX; @@ -1887,9 +1865,7 @@ static int rtl8169_open(struct net_device *dev) if (retval < 0) goto err_release_ring_2; -#ifdef CONFIG_R8169_NAPI napi_enable(&tp->napi); -#endif rtl_hw_start(dev); @@ -2197,9 +2173,7 @@ static int rtl8169_change_mtu(struct net_device *dev, int new_mtu) if (ret < 0) goto out; -#ifdef CONFIG_R8169_NAPI napi_enable(&tp->napi); -#endif rtl_hw_start(dev); @@ -2391,17 +2365,13 @@ static void rtl8169_wait_for_quiescence(struct net_device *dev) synchronize_irq(dev->irq); /* Wait for any pending NAPI task to complete */ -#ifdef CONFIG_R8169_NAPI napi_disable(&tp->napi); -#endif rtl8169_irq_mask_and_ack(ioaddr); -#ifdef CONFIG_R8169_NAPI tp->intr_mask = 0xffff; RTL_W16(IntrMask, tp->intr_event); napi_enable(&tp->napi); -#endif } static void rtl8169_reinit_task(struct work_struct *work) @@ -2767,7 +2737,7 @@ static int rtl8169_rx_interrupt(struct net_device *dev, cur_rx = tp->cur_rx; rx_left = NUM_RX_DESC + tp->dirty_rx - cur_rx; - rx_left = rtl8169_rx_quota(rx_left, budget); + rx_left = min(rx_left, budget); for (; rx_left > 0; rx_left--, cur_rx++) { unsigned int entry = cur_rx % NUM_RX_DESC; @@ -2829,7 +2799,7 @@ static int rtl8169_rx_interrupt(struct net_device *dev, skb->protocol = eth_type_trans(skb, dev); if (rtl8169_rx_vlan_skb(tp, desc, skb) < 0) - rtl8169_rx_skb(skb); + netif_receive_skb(skb); dev->last_rx = jiffies; dev->stats.rx_bytes += pkt_size; @@ -2869,87 +2839,61 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) { struct net_device *dev = dev_instance; struct rtl8169_private *tp = netdev_priv(dev); - int boguscnt = max_interrupt_work; void __iomem *ioaddr = tp->mmio_addr; - int status; int handled = 0; + int status; - do { - status = RTL_R16(IntrStatus); + status = RTL_R16(IntrStatus); - /* hotplug/major error/no more work/shared irq */ - if ((status == 0xFFFF) || !status) - break; + /* hotplug/major error/no more work/shared irq */ + if ((status == 0xffff) || !status) + goto out; - handled = 1; + handled = 1; - if (unlikely(!netif_running(dev))) { - rtl8169_asic_down(ioaddr); - goto out; - } + if (unlikely(!netif_running(dev))) { + rtl8169_asic_down(ioaddr); + goto out; + } - status &= tp->intr_mask; - RTL_W16(IntrStatus, - (status & RxFIFOOver) ? (status | RxOverflow) : status); + status &= tp->intr_mask; + RTL_W16(IntrStatus, + (status & RxFIFOOver) ? (status | RxOverflow) : status); - if (!(status & tp->intr_event)) - break; + if (!(status & tp->intr_event)) + goto out; - /* Work around for rx fifo overflow */ - if (unlikely(status & RxFIFOOver) && - (tp->mac_version == RTL_GIGA_MAC_VER_11)) { - netif_stop_queue(dev); - rtl8169_tx_timeout(dev); - break; - } + /* Work around for rx fifo overflow */ + if (unlikely(status & RxFIFOOver) && + (tp->mac_version == RTL_GIGA_MAC_VER_11)) { + netif_stop_queue(dev); + rtl8169_tx_timeout(dev); + goto out; + } - if (unlikely(status & SYSErr)) { - rtl8169_pcierr_interrupt(dev); - break; - } + if (unlikely(status & SYSErr)) { + rtl8169_pcierr_interrupt(dev); + goto out; + } - if (status & LinkChg) - rtl8169_check_link_status(dev, tp, ioaddr); + if (status & LinkChg) + rtl8169_check_link_status(dev, tp, ioaddr); -#ifdef CONFIG_R8169_NAPI - if (status & tp->napi_event) { - RTL_W16(IntrMask, tp->intr_event & ~tp->napi_event); - tp->intr_mask = ~tp->napi_event; + if (status & tp->napi_event) { + RTL_W16(IntrMask, tp->intr_event & ~tp->napi_event); + tp->intr_mask = ~tp->napi_event; if (likely(netif_rx_schedule_prep(dev, &tp->napi))) __netif_rx_schedule(dev, &tp->napi); - else if (netif_msg_intr(tp)) { - printk(KERN_INFO "%s: interrupt %04x in poll\n", - dev->name, status); - } + else if (netif_msg_intr(tp)) { + printk(KERN_INFO "%s: interrupt %04x in poll\n", + dev->name, status); } - break; -#else - /* Rx interrupt */ - if (status & (RxOK | RxOverflow | RxFIFOOver)) - rtl8169_rx_interrupt(dev, tp, ioaddr, ~(u32)0); - - /* Tx interrupt */ - if (status & (TxOK | TxErr)) - rtl8169_tx_interrupt(dev, tp, ioaddr); -#endif - - boguscnt--; - } while (boguscnt > 0); - - if (boguscnt <= 0) { - if (netif_msg_intr(tp) && net_ratelimit() ) { - printk(KERN_WARNING - "%s: Too much work at interrupt!\n", dev->name); - } - /* Clear all interrupt sources. */ - RTL_W16(IntrStatus, 0xffff); } out: return IRQ_RETVAL(handled); } -#ifdef CONFIG_R8169_NAPI static int rtl8169_poll(struct napi_struct *napi, int budget) { struct rtl8169_private *tp = container_of(napi, struct rtl8169_private, napi); @@ -2975,7 +2919,6 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) return work_done; } -#endif static void rtl8169_down(struct net_device *dev) { @@ -2987,9 +2930,7 @@ static void rtl8169_down(struct net_device *dev) netif_stop_queue(dev); -#ifdef CONFIG_R8169_NAPI napi_disable(&tp->napi); -#endif core_down: spin_lock_irq(&tp->lock); @@ -3098,8 +3039,10 @@ static void rtl_set_rx_mode(struct net_device *dev) (tp->mac_version == RTL_GIGA_MAC_VER_15) || (tp->mac_version == RTL_GIGA_MAC_VER_16) || (tp->mac_version == RTL_GIGA_MAC_VER_17)) { - mc_filter[0] = 0xffffffff; - mc_filter[1] = 0xffffffff; + u32 data = mc_filter[0]; + + mc_filter[0] = swab32(mc_filter[1]); + mc_filter[1] = swab32(data); } RTL_W32(MAR0 + 0, mc_filter[0]); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 7ab94c8..aa4ee44 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -63,6 +63,7 @@ #include <linux/if_tun.h> #include <linux/crc32.h> #include <linux/nsproxy.h> +#include <linux/virtio_net.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -283,6 +284,7 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, struct tun_pi pi = { 0, __constant_htons(ETH_P_IP) }; struct sk_buff *skb; size_t len = count, align = 0; + struct virtio_net_hdr gso = { 0 }; if (!(tun->flags & TUN_NO_PI)) { if ((len -= sizeof(pi)) > count) @@ -292,6 +294,17 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, return -EFAULT; } + if (tun->flags & TUN_VNET_HDR) { + if ((len -= sizeof(gso)) > count) + return -EINVAL; + + if (memcpy_fromiovec((void *)&gso, iv, sizeof(gso))) + return -EFAULT; + + if (gso.hdr_len > len) + return -EINVAL; + } + if ((tun->flags & TUN_TYPE_MASK) == TUN_TAP_DEV) { align = NET_IP_ALIGN; if (unlikely(len < ETH_HLEN)) @@ -311,6 +324,16 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, return -EFAULT; } + if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { + if (!skb_partial_csum_set(skb, gso.csum_start, + gso.csum_offset)) { + tun->dev->stats.rx_frame_errors++; + kfree_skb(skb); + return -EINVAL; + } + } else if (tun->flags & TUN_NOCHECKSUM) + skb->ip_summed = CHECKSUM_UNNECESSARY; + switch (tun->flags & TUN_TYPE_MASK) { case TUN_TUN_DEV: if (tun->flags & TUN_NO_PI) { @@ -337,8 +360,35 @@ static __inline__ ssize_t tun_get_user(struct tun_struct *tun, struct iovec *iv, break; }; - if (tun->flags & TUN_NOCHECKSUM) - skb->ip_summed = CHECKSUM_UNNECESSARY; + if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { + pr_debug("GSO!\n"); + switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { + case VIRTIO_NET_HDR_GSO_TCPV4: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + break; + case VIRTIO_NET_HDR_GSO_TCPV6: + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; + break; + default: + tun->dev->stats.rx_frame_errors++; + kfree_skb(skb); + return -EINVAL; + } + + if (gso.gso_type & VIRTIO_NET_HDR_GSO_ECN) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + + skb_shinfo(skb)->gso_size = gso.gso_size; + if (skb_shinfo(skb)->gso_size == 0) { + tun->dev->stats.rx_frame_errors++; + kfree_skb(skb); + return -EINVAL; + } + + /* Header must be checked, and gso_segs computed. */ + skb_shinfo(skb)->gso_type |= SKB_GSO_DODGY; + skb_shinfo(skb)->gso_segs = 0; + } netif_rx_ni(skb); tun->dev->last_rx = jiffies; @@ -384,6 +434,39 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun, total += sizeof(pi); } + if (tun->flags & TUN_VNET_HDR) { + struct virtio_net_hdr gso = { 0 }; /* no info leak */ + if ((len -= sizeof(gso)) < 0) + return -EINVAL; + + if (skb_is_gso(skb)) { + struct skb_shared_info *sinfo = skb_shinfo(skb); + + /* This is a hint as to how much should be linear. */ + gso.hdr_len = skb_headlen(skb); + gso.gso_size = sinfo->gso_size; + if (sinfo->gso_type & SKB_GSO_TCPV4) + gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; + else if (sinfo->gso_type & SKB_GSO_TCPV6) + gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; + else + BUG(); + if (sinfo->gso_type & SKB_GSO_TCP_ECN) + gso.gso_type |= VIRTIO_NET_HDR_GSO_ECN; + } else + gso.gso_type = VIRTIO_NET_HDR_GSO_NONE; + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + gso.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; + gso.csum_start = skb->csum_start - skb_headroom(skb); + gso.csum_offset = skb->csum_offset; + } /* else everything is zero */ + + if (unlikely(memcpy_toiovec(iv, (void *)&gso, sizeof(gso)))) + return -EFAULT; + total += sizeof(gso); + } + len = min_t(int, skb->len, len); skb_copy_datagram_iovec(skb, 0, iv, len); @@ -598,6 +681,11 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) else tun->flags &= ~TUN_ONE_QUEUE; + if (ifr->ifr_flags & IFF_VNET_HDR) + tun->flags |= TUN_VNET_HDR; + else + tun->flags &= ~TUN_VNET_HDR; + file->private_data = tun; tun->attached = 1; get_net(dev_net(tun->dev)); @@ -611,6 +699,46 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) return err; } +/* This is like a cut-down ethtool ops, except done via tun fd so no + * privs required. */ +static int set_offload(struct net_device *dev, unsigned long arg) +{ + unsigned int old_features, features; + + old_features = dev->features; + /* Unset features, set them as we chew on the arg. */ + features = (old_features & ~(NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST + |NETIF_F_TSO_ECN|NETIF_F_TSO|NETIF_F_TSO6)); + + if (arg & TUN_F_CSUM) { + features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; + arg &= ~TUN_F_CSUM; + + if (arg & (TUN_F_TSO4|TUN_F_TSO6)) { + if (arg & TUN_F_TSO_ECN) { + features |= NETIF_F_TSO_ECN; + arg &= ~TUN_F_TSO_ECN; + } + if (arg & TUN_F_TSO4) + features |= NETIF_F_TSO; + if (arg & TUN_F_TSO6) + features |= NETIF_F_TSO6; + arg &= ~(TUN_F_TSO4|TUN_F_TSO6); + } + } + + /* This gives the user a way to test for new features in future by + * trying to set them. */ + if (arg) + return -EINVAL; + + dev->features = features; + if (old_features != dev->features) + netdev_features_change(dev); + + return 0; +} + static int tun_chr_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg) { @@ -640,6 +768,15 @@ static int tun_chr_ioctl(struct inode *inode, struct file *file, return 0; } + if (cmd == TUNGETFEATURES) { + /* Currently this just means: "what IFF flags are valid?". + * This is needed because we never checked for invalid flags on + * TUNSETIFF. */ + return put_user(IFF_TUN | IFF_TAP | IFF_NO_PI | IFF_ONE_QUEUE | + IFF_VNET_HDR, + (unsigned int __user*)argp); + } + if (!tun) return -EBADFD; @@ -707,6 +844,15 @@ static int tun_chr_ioctl(struct inode *inode, struct file *file, break; #endif + case TUNSETOFFLOAD: + { + int ret; + rtnl_lock(); + ret = set_offload(tun->dev, arg); + rtnl_unlock(); + return ret; + } + case SIOCGIFFLAGS: ifr.ifr_flags = tun->if_flags; if (copy_to_user( argp, &ifr, sizeof ifr)) diff --git a/drivers/net/wan/c101.c b/drivers/net/wan/c101.c index c2cc42f..c8e5631 100644 --- a/drivers/net/wan/c101.c +++ b/drivers/net/wan/c101.c @@ -133,9 +133,9 @@ static void sca_msci_intr(port_t *port) sca_out(stat & (ST1_UDRN | ST1_CDCD), MSCI0_OFFSET + ST1, port); if (stat & ST1_UDRN) { - struct net_device_stats *stats = hdlc_stats(port_to_dev(port)); - stats->tx_errors++; /* TX Underrun error detected */ - stats->tx_fifo_errors++; + /* TX Underrun error detected */ + port_to_dev(port)->stats.tx_errors++; + port_to_dev(port)->stats.tx_fifo_errors++; } stat = sca_in(MSCI1_OFFSET + ST1, port); /* read MSCI1 ST1 status */ diff --git a/drivers/net/wan/dscc4.c b/drivers/net/wan/dscc4.c index c6f26e2..50ef5b4 100644 --- a/drivers/net/wan/dscc4.c +++ b/drivers/net/wan/dscc4.c @@ -642,7 +642,6 @@ static inline void dscc4_rx_skb(struct dscc4_dev_priv *dpriv, struct net_device *dev) { struct RxFD *rx_fd = dpriv->rx_fd + dpriv->rx_current%RX_RING_SIZE; - struct net_device_stats *stats = hdlc_stats(dev); struct pci_dev *pdev = dpriv->pci_priv->pdev; struct sk_buff *skb; int pkt_len; @@ -656,8 +655,8 @@ static inline void dscc4_rx_skb(struct dscc4_dev_priv *dpriv, pci_unmap_single(pdev, le32_to_cpu(rx_fd->data), RX_MAX(HDLC_MAX_MRU), PCI_DMA_FROMDEVICE); if ((skb->data[--pkt_len] & FrameOk) == FrameOk) { - stats->rx_packets++; - stats->rx_bytes += pkt_len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += pkt_len; skb_put(skb, pkt_len); if (netif_running(dev)) skb->protocol = hdlc_type_trans(skb, dev); @@ -665,13 +664,13 @@ static inline void dscc4_rx_skb(struct dscc4_dev_priv *dpriv, netif_rx(skb); } else { if (skb->data[pkt_len] & FrameRdo) - stats->rx_fifo_errors++; + dev->stats.rx_fifo_errors++; else if (!(skb->data[pkt_len] | ~FrameCrc)) - stats->rx_crc_errors++; + dev->stats.rx_crc_errors++; else if (!(skb->data[pkt_len] | ~(FrameVfr | FrameRab))) - stats->rx_length_errors++; + dev->stats.rx_length_errors++; else - stats->rx_errors++; + dev->stats.rx_errors++; dev_kfree_skb_irq(skb); } refill: @@ -1569,7 +1568,6 @@ try: if (state & SccEvt) { if (state & Alls) { - struct net_device_stats *stats = hdlc_stats(dev); struct sk_buff *skb; struct TxFD *tx_fd; @@ -1586,8 +1584,8 @@ try: pci_unmap_single(ppriv->pdev, le32_to_cpu(tx_fd->data), skb->len, PCI_DMA_TODEVICE); if (tx_fd->state & FrameEnd) { - stats->tx_packets++; - stats->tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; } dev_kfree_skb_irq(skb); dpriv->tx_skbuff[cur] = NULL; @@ -1698,7 +1696,7 @@ try: } if (state & Err) { printk(KERN_INFO "%s: Tx ERR\n", dev->name); - hdlc_stats(dev)->tx_errors++; + dev->stats.tx_errors++; state &= ~Err; } } @@ -1834,7 +1832,7 @@ try: if (!(rx_fd->state2 & DataComplete)) break; if (rx_fd->state2 & FrameAborted) { - hdlc_stats(dev)->rx_over_errors++; + dev->stats.rx_over_errors++; rx_fd->state1 |= Hold; rx_fd->state2 = 0x00000000; rx_fd->end = cpu_to_le32(0xbabeface); diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c index 547368e..754f008 100644 --- a/drivers/net/wan/farsync.c +++ b/drivers/net/wan/farsync.c @@ -845,7 +845,6 @@ fst_tx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, int len, int txpos) { struct net_device *dev = port_to_dev(port); - struct net_device_stats *stats = hdlc_stats(dev); /* * Everything is now set, just tell the card to go @@ -853,8 +852,8 @@ fst_tx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, dbg(DBG_TX, "fst_tx_dma_complete\n"); FST_WRB(card, txDescrRing[port->index][txpos].bits, DMA_OWN | TX_STP | TX_ENP); - stats->tx_packets++; - stats->tx_bytes += len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += len; dev->trans_start = jiffies; } @@ -876,7 +875,6 @@ fst_rx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, int len, struct sk_buff *skb, int rxp) { struct net_device *dev = port_to_dev(port); - struct net_device_stats *stats = hdlc_stats(dev); int pi; int rx_status; @@ -888,8 +886,8 @@ fst_rx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN); /* Update stats */ - stats->rx_packets++; - stats->rx_bytes += len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += len; /* Push upstream */ dbg(DBG_RX, "Pushing the frame up the stack\n"); @@ -900,7 +898,7 @@ fst_rx_dma_complete(struct fst_card_info *card, struct fst_port_info *port, rx_status = netif_rx(skb); fst_process_rx_status(rx_status, port_to_dev(port)->name); if (rx_status == NET_RX_DROP) - stats->rx_dropped++; + dev->stats.rx_dropped++; dev->last_rx = jiffies; } @@ -1163,29 +1161,28 @@ fst_log_rx_error(struct fst_card_info *card, struct fst_port_info *port, unsigned char dmabits, int rxp, unsigned short len) { struct net_device *dev = port_to_dev(port); - struct net_device_stats *stats = hdlc_stats(dev); - /* + /* * Increment the appropriate error counter */ - stats->rx_errors++; + dev->stats.rx_errors++; if (dmabits & RX_OFLO) { - stats->rx_fifo_errors++; + dev->stats.rx_fifo_errors++; dbg(DBG_ASS, "Rx fifo error on card %d port %d buffer %d\n", card->card_no, port->index, rxp); } if (dmabits & RX_CRC) { - stats->rx_crc_errors++; + dev->stats.rx_crc_errors++; dbg(DBG_ASS, "Rx crc error on card %d port %d\n", card->card_no, port->index); } if (dmabits & RX_FRAM) { - stats->rx_frame_errors++; + dev->stats.rx_frame_errors++; dbg(DBG_ASS, "Rx frame error on card %d port %d\n", card->card_no, port->index); } if (dmabits == (RX_STP | RX_ENP)) { - stats->rx_length_errors++; + dev->stats.rx_length_errors++; dbg(DBG_ASS, "Rx length error (%d) on card %d port %d\n", len, card->card_no, port->index); } @@ -1242,7 +1239,6 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) unsigned short len; struct sk_buff *skb; struct net_device *dev = port_to_dev(port); - struct net_device_stats *stats = hdlc_stats(dev); /* Check we have a buffer to process */ pi = port->index; @@ -1291,7 +1287,7 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) if ((skb = dev_alloc_skb(len)) == NULL) { dbg(DBG_RX, "intr_rx: can't allocate buffer\n"); - stats->rx_dropped++; + dev->stats.rx_dropped++; /* Return descriptor to card */ FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN); @@ -1316,8 +1312,8 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) FST_WRB(card, rxDescrRing[pi][rxp].bits, DMA_OWN); /* Update stats */ - stats->rx_packets++; - stats->rx_bytes += len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += len; /* Push upstream */ dbg(DBG_RX, "Pushing frame up the stack\n"); @@ -1327,9 +1323,8 @@ fst_intr_rx(struct fst_card_info *card, struct fst_port_info *port) skb->protocol = hdlc_type_trans(skb, dev); rx_status = netif_rx(skb); fst_process_rx_status(rx_status, port_to_dev(port)->name); - if (rx_status == NET_RX_DROP) { - stats->rx_dropped++; - } + if (rx_status == NET_RX_DROP) + dev->stats.rx_dropped++; dev->last_rx = jiffies; } else { card->dma_skb_rx = skb; @@ -1361,7 +1356,6 @@ do_bottom_half_tx(struct fst_card_info *card) struct sk_buff *skb; unsigned long flags; struct net_device *dev; - struct net_device_stats *stats; /* * Find a free buffer for the transmit @@ -1373,12 +1367,10 @@ do_bottom_half_tx(struct fst_card_info *card) if (!port->run) continue; - dev = port_to_dev(port); - stats = hdlc_stats(dev); - while (! - (FST_RDB(card, txDescrRing[pi][port->txpos].bits) & - DMA_OWN) - && !(card->dmatx_in_progress)) { + dev = port_to_dev(port); + while (!(FST_RDB(card, txDescrRing[pi][port->txpos].bits) & + DMA_OWN) + && !(card->dmatx_in_progress)) { /* * There doesn't seem to be a txdone event per-se * We seem to have to deduce it, by checking the DMA_OWN @@ -1422,8 +1414,8 @@ do_bottom_half_tx(struct fst_card_info *card) txDescrRing[pi][port->txpos]. bits, DMA_OWN | TX_STP | TX_ENP); - stats->tx_packets++; - stats->tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; dev->trans_start = jiffies; } else { /* Or do it through dma */ @@ -1628,8 +1620,8 @@ fst_intr(int dummy, void *dev_id) * always load up the entire packet for DMA. */ dbg(DBG_TX, "Tx underflow port %d\n", port->index); - hdlc_stats(port_to_dev(port))->tx_errors++; - hdlc_stats(port_to_dev(port))->tx_fifo_errors++; + port_to_dev(port)->stats.tx_errors++; + port_to_dev(port)->stats.tx_fifo_errors++; dbg(DBG_ASS, "Tx underflow on card %d port %d\n", card->card_no, port->index); break; @@ -2292,12 +2284,11 @@ fst_tx_timeout(struct net_device *dev) { struct fst_port_info *port; struct fst_card_info *card; - struct net_device_stats *stats = hdlc_stats(dev); port = dev_to_port(dev); card = port->card; - stats->tx_errors++; - stats->tx_aborted_errors++; + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; dbg(DBG_ASS, "Tx timeout card %d port %d\n", card->card_no, port->index); fst_issue_cmd(port, ABORTTX); @@ -2312,7 +2303,6 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct fst_card_info *card; struct fst_port_info *port; - struct net_device_stats *stats = hdlc_stats(dev); unsigned long flags; int txq_length; @@ -2323,8 +2313,8 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) /* Drop packet with error if we don't have carrier */ if (!netif_carrier_ok(dev)) { dev_kfree_skb(skb); - stats->tx_errors++; - stats->tx_carrier_errors++; + dev->stats.tx_errors++; + dev->stats.tx_carrier_errors++; dbg(DBG_ASS, "Tried to transmit but no carrier on card %d port %d\n", card->card_no, port->index); @@ -2336,7 +2326,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) dbg(DBG_ASS, "Packet too large %d vs %d\n", skb->len, LEN_TX_BUFFER); dev_kfree_skb(skb); - stats->tx_errors++; + dev->stats.tx_errors++; return 0; } @@ -2368,7 +2358,7 @@ fst_start_xmit(struct sk_buff *skb, struct net_device *dev) * This shouldn't have happened but such is life */ dev_kfree_skb(skb); - stats->tx_errors++; + dev->stats.tx_errors++; dbg(DBG_ASS, "Tx queue overflow card %d port %d\n", card->card_no, port->index); return 0; diff --git a/drivers/net/wan/hd6457x.c b/drivers/net/wan/hd6457x.c index 8d0a1f2..591fb45 100644 --- a/drivers/net/wan/hd6457x.c +++ b/drivers/net/wan/hd6457x.c @@ -271,9 +271,9 @@ static inline void sca_msci_intr(port_t *port) sca_out(stat & (ST1_UDRN | ST1_CDCD), msci + ST1, card); if (stat & ST1_UDRN) { - struct net_device_stats *stats = hdlc_stats(port_to_dev(port)); - stats->tx_errors++; /* TX Underrun error detected */ - stats->tx_fifo_errors++; + /* TX Underrun error detected */ + port_to_dev(port)->stats.tx_errors++; + port_to_dev(port)->stats.tx_fifo_errors++; } if (stat & ST1_CDCD) @@ -286,7 +286,6 @@ static inline void sca_msci_intr(port_t *port) static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, u16 rxin) { struct net_device *dev = port_to_dev(port); - struct net_device_stats *stats = hdlc_stats(dev); struct sk_buff *skb; u16 len; u32 buff; @@ -298,7 +297,7 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, u1 len = readw(&desc->len); skb = dev_alloc_skb(len); if (!skb) { - stats->rx_dropped++; + dev->stats.rx_dropped++; return; } @@ -327,8 +326,8 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, u1 printk(KERN_DEBUG "%s RX(%i):", dev->name, skb->len); debug_frame(skb); #endif - stats->rx_packets++; - stats->rx_bytes += skb->len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; dev->last_rx = jiffies; skb->protocol = hdlc_type_trans(skb, dev); netif_rx(skb); @@ -339,17 +338,18 @@ static inline void sca_rx(card_t *card, port_t *port, pkt_desc __iomem *desc, u1 /* Receive DMA interrupt service */ static inline void sca_rx_intr(port_t *port) { + struct net_device *dev = port_to_dev(port); u16 dmac = get_dmac_rx(port); card_t *card = port_to_card(port); u8 stat = sca_in(DSR_RX(phy_node(port)), card); /* read DMA Status */ - struct net_device_stats *stats = hdlc_stats(port_to_dev(port)); /* Reset DSR status bits */ sca_out((stat & (DSR_EOT | DSR_EOM | DSR_BOF | DSR_COF)) | DSR_DWE, DSR_RX(phy_node(port)), card); if (stat & DSR_BOF) - stats->rx_over_errors++; /* Dropped one or more frames */ + /* Dropped one or more frames */ + dev->stats.rx_over_errors++; while (1) { u32 desc_off = desc_offset(port, port->rxin, 0); @@ -364,12 +364,14 @@ static inline void sca_rx_intr(port_t *port) if (!(stat & ST_RX_EOM)) port->rxpart = 1; /* partial frame received */ else if ((stat & ST_ERROR_MASK) || port->rxpart) { - stats->rx_errors++; - if (stat & ST_RX_OVERRUN) stats->rx_fifo_errors++; + dev->stats.rx_errors++; + if (stat & ST_RX_OVERRUN) + dev->stats.rx_fifo_errors++; else if ((stat & (ST_RX_SHORT | ST_RX_ABORT | ST_RX_RESBIT)) || port->rxpart) - stats->rx_frame_errors++; - else if (stat & ST_RX_CRC) stats->rx_crc_errors++; + dev->stats.rx_frame_errors++; + else if (stat & ST_RX_CRC) + dev->stats.rx_crc_errors++; if (stat & ST_RX_EOM) port->rxpart = 0; /* received last fragment */ } else @@ -390,7 +392,6 @@ static inline void sca_rx_intr(port_t *port) static inline void sca_tx_intr(port_t *port) { struct net_device *dev = port_to_dev(port); - struct net_device_stats *stats = hdlc_stats(dev); u16 dmac = get_dmac_tx(port); card_t* card = port_to_card(port); u8 stat; @@ -412,8 +413,8 @@ static inline void sca_tx_intr(port_t *port) break; /* Transmitter is/will_be sending this frame */ desc = desc_address(port, port->txlast, 1); - stats->tx_packets++; - stats->tx_bytes += readw(&desc->len); + dev->stats.tx_packets++; + dev->stats.tx_bytes += readw(&desc->len); writeb(0, &desc->stat); /* Free descriptor */ port->txlast = next_desc(port, port->txlast, 1); } diff --git a/drivers/net/wan/hdlc.c b/drivers/net/wan/hdlc.c index 7f98489..e3a5364 100644 --- a/drivers/net/wan/hdlc.c +++ b/drivers/net/wan/hdlc.c @@ -57,7 +57,7 @@ static int hdlc_change_mtu(struct net_device *dev, int new_mtu) static struct net_device_stats *hdlc_get_stats(struct net_device *dev) { - return hdlc_stats(dev); + return &dev->stats; } diff --git a/drivers/net/wan/hdlc_cisco.c b/drivers/net/wan/hdlc_cisco.c index 762d21c..849819c 100644 --- a/drivers/net/wan/hdlc_cisco.c +++ b/drivers/net/wan/hdlc_cisco.c @@ -252,8 +252,8 @@ static int cisco_rx(struct sk_buff *skb) dev_kfree_skb_any(skb); return NET_RX_DROP; - rx_error: - dev_to_hdlc(dev)->stats.rx_errors++; /* Mark error */ +rx_error: + dev->stats.rx_errors++; /* Mark error */ dev_kfree_skb_any(skb); return NET_RX_DROP; } diff --git a/drivers/net/wan/hdlc_fr.c b/drivers/net/wan/hdlc_fr.c index 520bb0b..109bab3 100644 --- a/drivers/net/wan/hdlc_fr.c +++ b/drivers/net/wan/hdlc_fr.c @@ -135,11 +135,6 @@ typedef struct pvc_device_struct { }state; }pvc_device; -struct pvc_desc { - struct net_device_stats stats; - pvc_device *pvc; -}; - struct frad_state { fr_proto settings; pvc_device *first_pvc; @@ -179,15 +174,6 @@ static inline struct frad_state* state(hdlc_device *hdlc) return(struct frad_state *)(hdlc->state); } -static inline struct pvc_desc* pvcdev_to_desc(struct net_device *dev) -{ - return dev->priv; -} - -static inline struct net_device_stats* pvc_get_stats(struct net_device *dev) -{ - return &pvcdev_to_desc(dev)->stats; -} static inline pvc_device* find_pvc(hdlc_device *hdlc, u16 dlci) { @@ -357,7 +343,7 @@ static int fr_hard_header(struct sk_buff **skb_p, u16 dlci) static int pvc_open(struct net_device *dev) { - pvc_device *pvc = pvcdev_to_desc(dev)->pvc; + pvc_device *pvc = dev->priv; if ((pvc->frad->flags & IFF_UP) == 0) return -EIO; /* Frad must be UP in order to activate PVC */ @@ -377,7 +363,7 @@ static int pvc_open(struct net_device *dev) static int pvc_close(struct net_device *dev) { - pvc_device *pvc = pvcdev_to_desc(dev)->pvc; + pvc_device *pvc = dev->priv; if (--pvc->open_count == 0) { hdlc_device *hdlc = dev_to_hdlc(pvc->frad); @@ -396,7 +382,7 @@ static int pvc_close(struct net_device *dev) static int pvc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { - pvc_device *pvc = pvcdev_to_desc(dev)->pvc; + pvc_device *pvc = dev->priv; fr_proto_pvc_info info; if (ifr->ifr_settings.type == IF_GET_PROTO) { @@ -424,8 +410,7 @@ static int pvc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) static int pvc_xmit(struct sk_buff *skb, struct net_device *dev) { - pvc_device *pvc = pvcdev_to_desc(dev)->pvc; - struct net_device_stats *stats = pvc_get_stats(dev); + pvc_device *pvc = dev->priv; if (pvc->state.active) { if (dev->type == ARPHRD_ETHER) { @@ -435,7 +420,7 @@ static int pvc_xmit(struct sk_buff *skb, struct net_device *dev) if (skb_tailroom(skb) < pad) if (pskb_expand_head(skb, 0, pad, GFP_ATOMIC)) { - stats->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return 0; } @@ -445,17 +430,17 @@ static int pvc_xmit(struct sk_buff *skb, struct net_device *dev) skb->protocol = __constant_htons(ETH_P_802_3); } if (!fr_hard_header(&skb, pvc->dlci)) { - stats->tx_bytes += skb->len; - stats->tx_packets++; + dev->stats.tx_bytes += skb->len; + dev->stats.tx_packets++; if (pvc->state.fecn) /* TX Congestion counter */ - stats->tx_compressed++; + dev->stats.tx_compressed++; skb->dev = pvc->frad; dev_queue_xmit(skb); return 0; } } - stats->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return 0; } @@ -955,7 +940,7 @@ static int fr_rx(struct sk_buff *skb) if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { - dev_to_hdlc(frad)->stats.rx_dropped++; + frad->stats.rx_dropped++; return NET_RX_DROP; } @@ -1003,11 +988,10 @@ static int fr_rx(struct sk_buff *skb) } if (dev) { - struct net_device_stats *stats = pvc_get_stats(dev); - stats->rx_packets++; /* PVC traffic */ - stats->rx_bytes += skb->len; + dev->stats.rx_packets++; /* PVC traffic */ + dev->stats.rx_bytes += skb->len; if (pvc->state.becn) - stats->rx_compressed++; + dev->stats.rx_compressed++; netif_rx(skb); return NET_RX_SUCCESS; } else { @@ -1016,7 +1000,7 @@ static int fr_rx(struct sk_buff *skb) } rx_error: - dev_to_hdlc(frad)->stats.rx_errors++; /* Mark error */ + frad->stats.rx_errors++; /* Mark error */ dev_kfree_skb_any(skb); return NET_RX_DROP; } @@ -1087,7 +1071,7 @@ static void pvc_setup(struct net_device *dev) static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) { hdlc_device *hdlc = dev_to_hdlc(frad); - pvc_device *pvc = NULL; + pvc_device *pvc; struct net_device *dev; int result, used; @@ -1103,10 +1087,9 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) used = pvc_is_used(pvc); if (type == ARPHRD_ETHER) - dev = alloc_netdev(sizeof(struct pvc_desc), "pvceth%d", - ether_setup); + dev = alloc_netdev(0, "pvceth%d", ether_setup); else - dev = alloc_netdev(sizeof(struct pvc_desc), "pvc%d", pvc_setup); + dev = alloc_netdev(0, "pvc%d", pvc_setup); if (!dev) { printk(KERN_WARNING "%s: Memory squeeze on fr_pvc()\n", @@ -1122,14 +1105,13 @@ static int fr_add_pvc(struct net_device *frad, unsigned int dlci, int type) dlci_to_q922(dev->broadcast, dlci); } dev->hard_start_xmit = pvc_xmit; - dev->get_stats = pvc_get_stats; dev->open = pvc_open; dev->stop = pvc_close; dev->do_ioctl = pvc_ioctl; dev->change_mtu = pvc_change_mtu; dev->mtu = HDLC_MAX_MTU; dev->tx_queue_len = 0; - pvcdev_to_desc(dev)->pvc = pvc; + dev->priv = pvc; result = dev_alloc_name(dev, dev->name); if (result < 0) { diff --git a/drivers/net/wan/hdlc_raw_eth.c b/drivers/net/wan/hdlc_raw_eth.c index d20c685..26dee60 100644 --- a/drivers/net/wan/hdlc_raw_eth.c +++ b/drivers/net/wan/hdlc_raw_eth.c @@ -33,7 +33,7 @@ static int eth_tx(struct sk_buff *skb, struct net_device *dev) int len = skb->len; if (skb_tailroom(skb) < pad) if (pskb_expand_head(skb, 0, pad, GFP_ATOMIC)) { - hdlc_stats(dev)->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return 0; } diff --git a/drivers/net/wan/hdlc_x25.c b/drivers/net/wan/hdlc_x25.c index c15cc11..e808720 100644 --- a/drivers/net/wan/hdlc_x25.c +++ b/drivers/net/wan/hdlc_x25.c @@ -164,17 +164,15 @@ static void x25_close(struct net_device *dev) static int x25_rx(struct sk_buff *skb) { - struct hdlc_device *hdlc = dev_to_hdlc(skb->dev); - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { - hdlc->stats.rx_dropped++; + skb->dev->stats.rx_dropped++; return NET_RX_DROP; } if (lapb_data_received(skb->dev, skb) == LAPB_OK) return NET_RX_SUCCESS; - hdlc->stats.rx_errors++; + skb->dev->stats.rx_errors++; dev_kfree_skb_any(skb); return NET_RX_DROP; } diff --git a/drivers/net/wan/pc300_drv.c b/drivers/net/wan/pc300_drv.c index 57914fb..3341705 100644 --- a/drivers/net/wan/pc300_drv.c +++ b/drivers/net/wan/pc300_drv.c @@ -285,7 +285,6 @@ static void rx_dma_buf_init(pc300_t *, int); static void tx_dma_buf_check(pc300_t *, int); static void rx_dma_buf_check(pc300_t *, int); static irqreturn_t cpc_intr(int, void *); -static struct net_device_stats *cpc_get_stats(struct net_device *); static int clock_rate_calc(uclong, uclong, int *); static uclong detect_ram(pc300_t *); static void plx_init(pc300_t *); @@ -1775,13 +1774,12 @@ static void cpc_tx_timeout(struct net_device *dev) pc300dev_t *d = (pc300dev_t *) dev->priv; pc300ch_t *chan = (pc300ch_t *) d->chan; pc300_t *card = (pc300_t *) chan->card; - struct net_device_stats *stats = hdlc_stats(dev); int ch = chan->channel; unsigned long flags; ucchar ilar; - stats->tx_errors++; - stats->tx_aborted_errors++; + dev->stats.tx_errors++; + dev->stats.tx_aborted_errors++; CPC_LOCK(card, flags); if ((ilar = cpc_readb(card->hw.scabase + ILAR)) != 0) { printk("%s: ILAR=0x%x\n", dev->name, ilar); @@ -1803,7 +1801,6 @@ static int cpc_queue_xmit(struct sk_buff *skb, struct net_device *dev) pc300dev_t *d = (pc300dev_t *) dev->priv; pc300ch_t *chan = (pc300ch_t *) d->chan; pc300_t *card = (pc300_t *) chan->card; - struct net_device_stats *stats = hdlc_stats(dev); int ch = chan->channel; unsigned long flags; #ifdef PC300_DEBUG_TX @@ -1817,13 +1814,13 @@ static int cpc_queue_xmit(struct sk_buff *skb, struct net_device *dev) } else if (!netif_carrier_ok(dev)) { /* DCD must be OFF: drop packet */ dev_kfree_skb(skb); - stats->tx_errors++; - stats->tx_carrier_errors++; + dev->stats.tx_errors++; + dev->stats.tx_carrier_errors++; return 0; } else if (cpc_readb(card->hw.scabase + M_REG(ST3, ch)) & ST3_DCD) { printk("%s: DCD is OFF. Going administrative down.\n", dev->name); - stats->tx_errors++; - stats->tx_carrier_errors++; + dev->stats.tx_errors++; + dev->stats.tx_carrier_errors++; dev_kfree_skb(skb); netif_carrier_off(dev); CPC_LOCK(card, flags); @@ -1843,8 +1840,8 @@ static int cpc_queue_xmit(struct sk_buff *skb, struct net_device *dev) // printk("%s: write error. Dropping TX packet.\n", dev->name); netif_stop_queue(dev); dev_kfree_skb(skb); - stats->tx_errors++; - stats->tx_dropped++; + dev->stats.tx_errors++; + dev->stats.tx_dropped++; return 0; } #ifdef PC300_DEBUG_TX @@ -1886,7 +1883,6 @@ static void cpc_net_rx(struct net_device *dev) pc300dev_t *d = (pc300dev_t *) dev->priv; pc300ch_t *chan = (pc300ch_t *) d->chan; pc300_t *card = (pc300_t *) chan->card; - struct net_device_stats *stats = hdlc_stats(dev); int ch = chan->channel; #ifdef PC300_DEBUG_RX int i; @@ -1922,24 +1918,24 @@ static void cpc_net_rx(struct net_device *dev) #endif if ((skb == NULL) && (rxb > 0)) { /* rxb > dev->mtu */ - stats->rx_errors++; - stats->rx_length_errors++; + dev->stats.rx_errors++; + dev->stats.rx_length_errors++; continue; } if (rxb < 0) { /* Invalid frame */ rxb = -rxb; if (rxb & DST_OVR) { - stats->rx_errors++; - stats->rx_fifo_errors++; + dev->stats.rx_errors++; + dev->stats.rx_fifo_errors++; } if (rxb & DST_CRC) { - stats->rx_errors++; - stats->rx_crc_errors++; + dev->stats.rx_errors++; + dev->stats.rx_crc_errors++; } if (rxb & (DST_RBIT | DST_SHRT | DST_ABT)) { - stats->rx_errors++; - stats->rx_frame_errors++; + dev->stats.rx_errors++; + dev->stats.rx_frame_errors++; } } if (skb) { @@ -1948,7 +1944,7 @@ static void cpc_net_rx(struct net_device *dev) continue; } - stats->rx_bytes += rxb; + dev->stats.rx_bytes += rxb; #ifdef PC300_DEBUG_RX printk("%s R:", dev->name); @@ -1959,7 +1955,7 @@ static void cpc_net_rx(struct net_device *dev) if (d->trace_on) { cpc_trace(dev, skb, 'R'); } - stats->rx_packets++; + dev->stats.rx_packets++; skb->protocol = hdlc_type_trans(skb, dev); netif_rx(skb); } @@ -1974,16 +1970,15 @@ static void sca_tx_intr(pc300dev_t *dev) pc300_t *card = (pc300_t *)chan->card; int ch = chan->channel; volatile pcsca_bd_t __iomem * ptdescr; - struct net_device_stats *stats = hdlc_stats(dev->dev); /* Clean up descriptors from previous transmission */ ptdescr = (card->hw.rambase + TX_BD_ADDR(ch,chan->tx_first_bd)); - while ((cpc_readl(card->hw.scabase + DTX_REG(CDAL,ch)) != - TX_BD_ADDR(ch,chan->tx_first_bd)) && - (cpc_readb(&ptdescr->status) & DST_OSB)) { - stats->tx_packets++; - stats->tx_bytes += cpc_readw(&ptdescr->len); + while ((cpc_readl(card->hw.scabase + DTX_REG(CDAL,ch)) != + TX_BD_ADDR(ch,chan->tx_first_bd)) && + (cpc_readb(&ptdescr->status) & DST_OSB)) { + dev->dev->stats.tx_packets++; + dev->dev->stats.tx_bytes += cpc_readw(&ptdescr->len); cpc_writeb(&ptdescr->status, DST_OSB); cpc_writew(&ptdescr->len, 0); chan->nfree_tx_bd++; @@ -2048,8 +2043,8 @@ static void sca_intr(pc300_t * card) } cpc_net_rx(dev); /* Discard invalid frames */ - hdlc_stats(dev)->rx_errors++; - hdlc_stats(dev)->rx_over_errors++; + dev->stats.rx_errors++; + dev->stats.rx_over_errors++; chan->rx_first_bd = 0; chan->rx_last_bd = N_DMA_RX_BUF - 1; rx_dma_start(card, ch); @@ -2115,8 +2110,8 @@ static void sca_intr(pc300_t * card) card->hw.cpld_reg2) & ~ (CPLD_REG2_FALC_LED1 << (2 * ch))); } - hdlc_stats(dev)->tx_errors++; - hdlc_stats(dev)->tx_fifo_errors++; + dev->stats.tx_errors++; + dev->stats.tx_fifo_errors++; sca_tx_intr(d); } } @@ -2604,7 +2599,7 @@ static int cpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) case SIOCGPC300UTILSTATS: { if (!arg) { /* clear statistics */ - memset(hdlc_stats(dev), 0, sizeof(struct net_device_stats)); + memset(&dev->stats, 0, sizeof(dev->stats)); if (card->hw.type == PC300_TE) { memset(&chan->falc, 0, sizeof(falc_t)); } @@ -2615,8 +2610,8 @@ static int cpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) pc300stats.hw_type = card->hw.type; pc300stats.line_on = card->chan[ch].d.line_on; pc300stats.line_off = card->chan[ch].d.line_off; - memcpy(&pc300stats.gen_stats, hdlc_stats(dev), - sizeof(struct net_device_stats)); + memcpy(&pc300stats.gen_stats, &dev->stats, + sizeof(dev->stats)); if (card->hw.type == PC300_TE) memcpy(&pc300stats.te_stats,&chan->falc,sizeof(falc_t)); if (copy_to_user(arg, &pc300stats, sizeof(pc300stats_t))) @@ -2823,11 +2818,6 @@ static int cpc_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) } } -static struct net_device_stats *cpc_get_stats(struct net_device *dev) -{ - return hdlc_stats(dev); -} - static int clock_rate_calc(uclong rate, uclong clock, int *br_io) { int br, tc; @@ -3394,7 +3384,6 @@ static void cpc_init_card(pc300_t * card) dev->stop = cpc_close; dev->tx_timeout = cpc_tx_timeout; dev->watchdog_timeo = PC300_TX_TIMEOUT; - dev->get_stats = cpc_get_stats; dev->set_multicast_list = NULL; dev->set_mac_address = NULL; dev->change_mtu = cpc_change_mtu; diff --git a/drivers/net/wan/pc300_tty.c b/drivers/net/wan/pc300_tty.c index e03eef2..eae94ab 100644 --- a/drivers/net/wan/pc300_tty.c +++ b/drivers/net/wan/pc300_tty.c @@ -458,7 +458,7 @@ static int cpc_tty_write(struct tty_struct *tty, const unsigned char *buf, int c CPC_TTY_DBG("%s: cpc_tty_write data len=%i\n",cpc_tty->name,count); pc300chan = (pc300ch_t *)((pc300dev_t*)cpc_tty->pc300dev)->chan; - stats = hdlc_stats(((pc300dev_t*)cpc_tty->pc300dev)->dev); + stats = &cpc_tty->pc300dev->dev->stats; card = (pc300_t *) pc300chan->card; ch = pc300chan->channel; @@ -743,7 +743,7 @@ void cpc_tty_receive(pc300dev_t *pc300dev) pc300_t *card = (pc300_t *)pc300chan->card; int ch = pc300chan->channel; volatile pcsca_bd_t __iomem * ptdescr; - struct net_device_stats *stats = hdlc_stats(pc300dev->dev); + struct net_device_stats *stats = &pc300dev->dev->stats; int rx_len, rx_aux; volatile unsigned char status; unsigned short first_bd = pc300chan->rx_first_bd; @@ -917,7 +917,7 @@ static int cpc_tty_send_to_card(pc300dev_t *dev,void* buf, int len) pc300ch_t *chan = (pc300ch_t *)dev->chan; pc300_t *card = (pc300_t *)chan->card; int ch = chan->channel; - struct net_device_stats *stats = hdlc_stats(dev->dev); + struct net_device_stats *stats = &dev->dev->stats; unsigned long flags; volatile pcsca_bd_t __iomem *ptdescr; int i, nchar; diff --git a/drivers/net/wan/wanxl.c b/drivers/net/wan/wanxl.c index d4aab8a..a8a5ca0 100644 --- a/drivers/net/wan/wanxl.c +++ b/drivers/net/wan/wanxl.c @@ -161,7 +161,6 @@ static inline void wanxl_cable_intr(port_t *port) static inline void wanxl_tx_intr(port_t *port) { struct net_device *dev = port->dev; - struct net_device_stats *stats = hdlc_stats(dev); while (1) { desc_t *desc = &get_status(port)->tx_descs[port->tx_in]; struct sk_buff *skb = port->tx_skbs[port->tx_in]; @@ -173,13 +172,13 @@ static inline void wanxl_tx_intr(port_t *port) return; case PACKET_UNDERRUN: - stats->tx_errors++; - stats->tx_fifo_errors++; + dev->stats.tx_errors++; + dev->stats.tx_fifo_errors++; break; default: - stats->tx_packets++; - stats->tx_bytes += skb->len; + dev->stats.tx_packets++; + dev->stats.tx_bytes += skb->len; } desc->stat = PACKET_EMPTY; /* Free descriptor */ pci_unmap_single(port->card->pdev, desc->address, skb->len, @@ -205,10 +204,9 @@ static inline void wanxl_rx_intr(card_t *card) port_t *port = &card->ports[desc->stat & PACKET_PORT_MASK]; struct net_device *dev = port->dev; - struct net_device_stats *stats = hdlc_stats(dev); if (!skb) - stats->rx_dropped++; + dev->stats.rx_dropped++; else { pci_unmap_single(card->pdev, desc->address, BUFFER_LENGTH, @@ -220,8 +218,8 @@ static inline void wanxl_rx_intr(card_t *card) skb->len); debug_frame(skb); #endif - stats->rx_packets++; - stats->rx_bytes += skb->len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += skb->len; dev->last_rx = jiffies; skb->protocol = hdlc_type_trans(skb, dev); netif_rx(skb); @@ -468,13 +466,13 @@ static int wanxl_close(struct net_device *dev) static struct net_device_stats *wanxl_get_stats(struct net_device *dev) { - struct net_device_stats *stats = hdlc_stats(dev); port_t *port = dev_to_port(dev); - stats->rx_over_errors = get_status(port)->rx_overruns; - stats->rx_frame_errors = get_status(port)->rx_frame_errors; - stats->rx_errors = stats->rx_over_errors + stats->rx_frame_errors; - return stats; + dev->stats.rx_over_errors = get_status(port)->rx_overruns; + dev->stats.rx_frame_errors = get_status(port)->rx_frame_errors; + dev->stats.rx_errors = dev->stats.rx_over_errors + + dev->stats.rx_frame_errors; + return &dev->stats; } diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c8d2163..8bb5e87 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -272,6 +272,12 @@ enum ethtool_flags { ETH_FLAG_LRO = (1 << 15), /* LRO is enabled */ }; +struct ethtool_rxnfc { + __u32 cmd; + __u32 flow_type; + __u64 data; +}; + #ifdef __KERNEL__ struct net_device; @@ -396,6 +402,8 @@ struct ethtool_ops { /* the following hooks are obsolete */ int (*self_test_count)(struct net_device *);/* use get_sset_count */ int (*get_stats_count)(struct net_device *);/* use get_sset_count */ + int (*get_rxhash)(struct net_device *, struct ethtool_rxnfc *); + int (*set_rxhash)(struct net_device *, struct ethtool_rxnfc *); }; #endif /* __KERNEL__ */ @@ -442,6 +450,9 @@ struct ethtool_ops { #define ETHTOOL_GPFLAGS 0x00000027 /* Get driver-private flags bitmap */ #define ETHTOOL_SPFLAGS 0x00000028 /* Set driver-private flags bitmap */ +#define ETHTOOL_GRXFH 0x00000029 /* Get RX flow hash configuration */ +#define ETHTOOL_SRXFH 0x0000002a /* Set RX flow hash configuration */ + /* compatibility with older code */ #define SPARC_ETH_GSET ETHTOOL_GSET #define SPARC_ETH_SSET ETHTOOL_SSET @@ -528,4 +539,26 @@ struct ethtool_ops { #define WAKE_MAGIC (1 << 5) #define WAKE_MAGICSECURE (1 << 6) /* only meaningful if WAKE_MAGIC */ +/* L3-L4 network traffic flow types */ +#define TCP_V4_FLOW 0x01 +#define UDP_V4_FLOW 0x02 +#define SCTP_V4_FLOW 0x03 +#define AH_ESP_V4_FLOW 0x04 +#define TCP_V6_FLOW 0x05 +#define UDP_V6_FLOW 0x06 +#define SCTP_V6_FLOW 0x07 +#define AH_ESP_V6_FLOW 0x08 + +/* L3-L4 network traffic flow hash options */ +#define RXH_DEV_PORT (1 << 0) +#define RXH_L2DA (1 << 1) +#define RXH_VLAN (1 << 2) +#define RXH_L3_PROTO (1 << 3) +#define RXH_IP_SRC (1 << 4) +#define RXH_IP_DST (1 << 5) +#define RXH_L4_B_0_1 (1 << 6) /* src port in case of TCP/UDP/SCTP */ +#define RXH_L4_B_2_3 (1 << 7) /* dst port in case of TCP/UDP/SCTP */ +#define RXH_DISCARD (1 << 31) + + #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/hdlc.h b/include/linux/hdlc.h index 6115545..c597696 100644 --- a/include/linux/hdlc.h +++ b/include/linux/hdlc.h @@ -45,7 +45,6 @@ struct hdlc_proto { /* Pointed to by dev->priv */ typedef struct hdlc_device { - struct net_device_stats stats; /* used by HDLC layer to take control over HDLC device from hw driver*/ int (*attach)(struct net_device *dev, unsigned short encoding, unsigned short parity); @@ -109,12 +108,6 @@ int attach_hdlc_protocol(struct net_device *dev, struct hdlc_proto *proto, /* May be used by hardware driver to gain control over HDLC device */ void detach_hdlc_protocol(struct net_device *dev); -static __inline__ struct net_device_stats *hdlc_stats(struct net_device *dev) -{ - return &dev_to_hdlc(dev)->stats; -} - - static __inline__ __be16 hdlc_type_trans(struct sk_buff *skb, struct net_device *dev) { diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index 18f31b6..563fae5 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -31,6 +31,7 @@ #define TUN_NO_PI 0x0040 #define TUN_ONE_QUEUE 0x0080 #define TUN_PERSIST 0x0100 +#define TUN_VNET_HDR 0x0200 /* Ioctl defines */ #define TUNSETNOCSUM _IOW('T', 200, int) @@ -40,12 +41,21 @@ #define TUNSETOWNER _IOW('T', 204, int) #define TUNSETLINK _IOW('T', 205, int) #define TUNSETGROUP _IOW('T', 206, int) +#define TUNGETFEATURES _IOR('T', 207, unsigned int) +#define TUNSETOFFLOAD _IOW('T', 208, unsigned int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 #define IFF_TAP 0x0002 #define IFF_NO_PI 0x1000 #define IFF_ONE_QUEUE 0x2000 +#define IFF_VNET_HDR 0x4000 + +/* Features for GSO (TUNSETOFFLOAD). */ +#define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */ +#define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */ +#define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */ +#define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */ struct tun_pi { unsigned short flags; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 15ace02..5190452 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -402,6 +402,7 @@ enum vlan_ioctl_cmds { enum vlan_flags { VLAN_FLAG_REORDER_HDR = 0x1, + VLAN_FLAG_GVRP = 0x2, }; enum vlan_name_types { diff --git a/include/linux/igmp.h b/include/linux/igmp.h index f5a1a0d..7bb3c09 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -228,7 +228,6 @@ extern int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, extern int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen); extern int ip_mc_sf_allow(struct sock *sk, __be32 local, __be32 rmt, int dif); -extern void ip_mr_init(void); extern void ip_mc_init_dev(struct in_device *); extern void ip_mc_destroy_dev(struct in_device *); extern void ip_mc_up(struct in_device *); diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index cde056e..391ad08 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -163,6 +163,8 @@ struct ipv6_devconf { #ifdef CONFIG_IPV6_MROUTE __s32 mc_forwarding; #endif + __s32 disable_ipv6; + __s32 accept_dad; void *sysctl; }; @@ -194,6 +196,8 @@ enum { DEVCONF_OPTIMISTIC_DAD, DEVCONF_ACCEPT_SOURCE_ROUTE, DEVCONF_MC_FORWARDING, + DEVCONF_DISABLE_IPV6, + DEVCONF_ACCEPT_DAD, DEVCONF_MAX }; diff --git a/include/linux/mroute.h b/include/linux/mroute.h index de4decf..07112ee 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -144,11 +144,37 @@ static inline int ip_mroute_opt(int opt) } #endif +#ifdef CONFIG_IP_MROUTE extern int ip_mroute_setsockopt(struct sock *, int, char __user *, int); extern int ip_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); -extern void ip_mr_init(void); +extern int ip_mr_init(void); +#else +static inline +int ip_mroute_setsockopt(struct sock *sock, + int optname, char __user *optval, int optlen) +{ + return -ENOPROTOOPT; +} + +static inline +int ip_mroute_getsockopt(struct sock *sock, + int optname, char __user *optval, int __user *optlen) +{ + return -ENOPROTOOPT; +} +static inline +int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) +{ + return -ENOIOCTLCMD; +} + +static inline int ip_mr_init(void) +{ + return 0; +} +#endif struct vif_device { diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index e798959..5cf5047 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -131,11 +131,44 @@ static inline int ip6_mroute_opt(int opt) struct sock; +#ifdef CONFIG_IPV6_MROUTE extern int ip6_mroute_setsockopt(struct sock *, int, char __user *, int); extern int ip6_mroute_getsockopt(struct sock *, int, char __user *, int __user *); extern int ip6_mr_input(struct sk_buff *skb); extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); -extern void ip6_mr_init(void); +extern int ip6_mr_init(void); +extern void ip6_mr_cleanup(void); +#else +static inline +int ip6_mroute_setsockopt(struct sock *sock, + int optname, char __user *optval, int optlen) +{ + return -ENOPROTOOPT; +} + +static inline +int ip6_mroute_getsockopt(struct sock *sock, + int optname, char __user *optval, int __user *optlen) +{ + return -ENOPROTOOPT; +} + +static inline +int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) +{ + return -ENOIOCTLCMD; +} + +static inline int ip6_mr_init(void) +{ + return 0; +} + +static inline void ip6_mr_cleanup(void) +{ + return; +} +#endif struct mif_device { diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 56dadb5..e009c6f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -740,6 +740,8 @@ struct net_device struct net_bridge_port *br_port; /* macvlan */ struct macvlan_port *macvlan_port; + /* GARP */ + struct garp_port *garp_port; /* class/net/name entry */ struct device dev; diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index a5c6ccc..c2bb5ca 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -62,7 +62,7 @@ struct fib_rules_ops /* Called after modifications to the rules set, must flush * the route cache if one exists. */ - void (*flush_cache)(void); + void (*flush_cache)(struct fib_rules_ops *ops); int nlgroup; const struct nla_policy *policy; diff --git a/include/net/garp.h b/include/net/garp.h new file mode 100644 index 0000000..825f172 --- /dev/null +++ b/include/net/garp.h @@ -0,0 +1,128 @@ +#ifndef _NET_GARP_H +#define _NET_GARP_H + +#include <net/stp.h> + +#define GARP_PROTOCOL_ID 0x1 +#define GARP_END_MARK 0x0 + +struct garp_pdu_hdr { + __be16 protocol; +}; + +struct garp_msg_hdr { + u8 attrtype; +}; + +enum garp_attr_event { + GARP_LEAVE_ALL, + GARP_JOIN_EMPTY, + GARP_JOIN_IN, + GARP_LEAVE_EMPTY, + GARP_LEAVE_IN, + GARP_EMPTY, +}; + +struct garp_attr_hdr { + u8 len; + u8 event; + u8 data[]; +}; + +struct garp_skb_cb { + u8 cur_type; +}; + +static inline struct garp_skb_cb *garp_cb(struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct garp_skb_cb) > + FIELD_SIZEOF(struct sk_buff, cb)); + return (struct garp_skb_cb *)skb->cb; +} + +enum garp_applicant_state { + GARP_APPLICANT_INVALID, + GARP_APPLICANT_VA, + GARP_APPLICANT_AA, + GARP_APPLICANT_QA, + GARP_APPLICANT_LA, + GARP_APPLICANT_VP, + GARP_APPLICANT_AP, + GARP_APPLICANT_QP, + GARP_APPLICANT_VO, + GARP_APPLICANT_AO, + GARP_APPLICANT_QO, + __GARP_APPLICANT_MAX +}; +#define GARP_APPLICANT_MAX (__GARP_APPLICANT_MAX - 1) + +enum garp_event { + GARP_EVENT_REQ_JOIN, + GARP_EVENT_REQ_LEAVE, + GARP_EVENT_R_JOIN_IN, + GARP_EVENT_R_JOIN_EMPTY, + GARP_EVENT_R_EMPTY, + GARP_EVENT_R_LEAVE_IN, + GARP_EVENT_R_LEAVE_EMPTY, + GARP_EVENT_TRANSMIT_PDU, + __GARP_EVENT_MAX +}; +#define GARP_EVENT_MAX (__GARP_EVENT_MAX - 1) + +enum garp_action { + GARP_ACTION_NONE, + GARP_ACTION_S_JOIN_IN, + GARP_ACTION_S_LEAVE_EMPTY, +}; + +struct garp_attr { + struct rb_node node; + enum garp_applicant_state state; + u8 type; + u8 dlen; + unsigned char data[]; +}; + +enum garp_applications { + GARP_APPLICATION_GVRP, + __GARP_APPLICATION_MAX +}; +#define GARP_APPLICATION_MAX (__GARP_APPLICATION_MAX - 1) + +struct garp_application { + enum garp_applications type; + unsigned int maxattr; + struct stp_proto proto; +}; + +struct garp_applicant { + struct garp_application *app; + struct net_device *dev; + struct timer_list join_timer; + + spinlock_t lock; + struct sk_buff_head queue; + struct sk_buff *pdu; + struct rb_root gid; +}; + +struct garp_port { + struct garp_applicant *applicants[GARP_APPLICATION_MAX + 1]; +}; + +extern int garp_register_application(struct garp_application *app); +extern void garp_unregister_application(struct garp_application *app); + +extern int garp_init_applicant(struct net_device *dev, + struct garp_application *app); +extern void garp_uninit_applicant(struct net_device *dev, + struct garp_application *app); + +extern int garp_request_join(const struct net_device *dev, + const struct garp_application *app, + const void *data, u8 len, u8 type); +extern void garp_request_leave(const struct net_device *dev, + const struct garp_application *app, + const void *data, u8 len, u8 type); + +#endif /* _NET_GARP_H */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 6ef90b5..a6ed838 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -18,6 +18,7 @@ struct netns_ipv4 { struct ctl_table_header *forw_hdr; struct ctl_table_header *frags_hdr; struct ctl_table_header *ipv4_hdr; + struct ctl_table_header *route_hdr; #endif struct ipv4_devconf *devconf_all; struct ipv4_devconf *devconf_dflt; @@ -45,5 +46,8 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; + + struct timer_list rt_secret_timer; + atomic_t rt_genid; }; #endif diff --git a/include/net/route.h b/include/net/route.h index fc836ff..3140cc5 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -111,7 +111,7 @@ struct in_device; extern int ip_rt_init(void); extern void ip_rt_redirect(__be32 old_gw, __be32 dst, __be32 new_gw, __be32 src, struct net_device *dev); -extern void rt_cache_flush(int how); +extern void rt_cache_flush(struct net *net, int how); extern int __ip_route_output_key(struct net *, struct rtable **, const struct flowi *flp); extern int ip_route_output_key(struct net *, struct rtable **, struct flowi *flp); extern int ip_route_output_flow(struct net *, struct rtable **rp, struct flowi *flp, struct sock *sk, int flags); diff --git a/include/net/stp.h b/include/net/stp.h new file mode 100644 index 0000000..ad447f1 --- /dev/null +++ b/include/net/stp.h @@ -0,0 +1,14 @@ +#ifndef _NET_STP_H +#define _NET_STP_H + +struct stp_proto { + unsigned char group_address[ETH_ALEN]; + void (*rcv)(const struct stp_proto *, struct sk_buff *, + struct net_device *); + void *data; +}; + +extern int stp_proto_register(const struct stp_proto *proto); +extern void stp_proto_unregister(const struct stp_proto *proto); + +#endif /* _NET_STP_H */ diff --git a/include/net/udp.h b/include/net/udp.h index 7a86848..3e55159 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -158,17 +158,17 @@ DECLARE_SNMP_STAT(struct udp_mib, udplite_stats_in6); /* * SNMP statistics for UDP and UDP-Lite */ -#define UDP_INC_STATS_USER(field, is_udplite) do { \ +#define UDP_INC_STATS_USER(net, field, is_udplite) do { (void)net; \ if (is_udplite) SNMP_INC_STATS_USER(udplite_statistics, field); \ else SNMP_INC_STATS_USER(udp_statistics, field); } while(0) -#define UDP_INC_STATS_BH(field, is_udplite) do { \ +#define UDP_INC_STATS_BH(net, field, is_udplite) do { (void)net; \ if (is_udplite) SNMP_INC_STATS_BH(udplite_statistics, field); \ else SNMP_INC_STATS_BH(udp_statistics, field); } while(0) -#define UDP6_INC_STATS_BH(field, is_udplite) do { \ +#define UDP6_INC_STATS_BH(net, field, is_udplite) do { (void)net; \ if (is_udplite) SNMP_INC_STATS_BH(udplite_stats_in6, field); \ else SNMP_INC_STATS_BH(udp_stats_in6, field); } while(0) -#define UDP6_INC_STATS_USER(field, is_udplite) do { \ +#define UDP6_INC_STATS_USER(net, field, is_udplite) do { (void)net; \ if (is_udplite) SNMP_INC_STATS_USER(udplite_stats_in6, field); \ else SNMP_INC_STATS_USER(udp_stats_in6, field); } while(0) @@ -176,12 +176,12 @@ DECLARE_SNMP_STAT(struct udp_mib, udplite_stats_in6); #define UDPX_INC_STATS_BH(sk, field) \ do { \ if ((sk)->sk_family == AF_INET) \ - UDP_INC_STATS_BH(field, 0); \ + UDP_INC_STATS_BH(sock_net(sk), field, 0); \ else \ - UDP6_INC_STATS_BH(field, 0); \ + UDP6_INC_STATS_BH(sock_net(sk), field, 0); \ } while (0); #else -#define UDPX_INC_STATS_BH(sk, field) UDP_INC_STATS_BH(field, 0) +#define UDPX_INC_STATS_BH(sk, field) UDP_INC_STATS_BH(sock_net(sk), field, 0) #endif /* /proc */ diff --git a/net/802/Kconfig b/net/802/Kconfig new file mode 100644 index 0000000..be33d27 --- /dev/null +++ b/net/802/Kconfig @@ -0,0 +1,7 @@ +config STP + tristate + select LLC + +config GARP + tristate + select STP diff --git a/net/802/Makefile b/net/802/Makefile index 68569ff..7893d67 100644 --- a/net/802/Makefile +++ b/net/802/Makefile @@ -10,3 +10,5 @@ obj-$(CONFIG_FDDI) += fddi.o obj-$(CONFIG_HIPPI) += hippi.o obj-$(CONFIG_IPX) += p8022.o psnap.o p8023.o obj-$(CONFIG_ATALK) += p8022.o psnap.o +obj-$(CONFIG_STP) += stp.o +obj-$(CONFIG_GARP) += garp.o diff --git a/net/802/garp.c b/net/802/garp.c new file mode 100644 index 0000000..3b78f7b --- /dev/null +++ b/net/802/garp.c @@ -0,0 +1,633 @@ +/* + * IEEE 802.1D Generic Attribute Registration Protocol (GARP) + * + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ +#include <linux/kernel.h> +#include <linux/timer.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/llc.h> +#include <net/llc.h> +#include <net/llc_pdu.h> +#include <net/garp.h> +#include <asm/unaligned.h> + +static unsigned int garp_join_time __read_mostly = 200; +module_param(garp_join_time, uint, 0644); +MODULE_PARM_DESC(garp_join_time, "Join time in ms (default 200ms)"); +MODULE_LICENSE("GPL"); + +static const struct garp_state_trans { + u8 state; + u8 action; +} garp_applicant_state_table[GARP_APPLICANT_MAX + 1][GARP_EVENT_MAX + 1] = { + [GARP_APPLICANT_VA] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, + .action = GARP_ACTION_S_JOIN_IN }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AA }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, + }, + [GARP_APPLICANT_AA] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, + .action = GARP_ACTION_S_JOIN_IN }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, + }, + [GARP_APPLICANT_QA] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QA }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_LA }, + }, + [GARP_APPLICANT_LA] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_VO, + .action = GARP_ACTION_S_LEAVE_EMPTY }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_LA }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_LA }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_LA }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VA }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, + }, + [GARP_APPLICANT_VP] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_AA, + .action = GARP_ACTION_S_JOIN_IN }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AP }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_VO }, + }, + [GARP_APPLICANT_AP] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_QA, + .action = GARP_ACTION_S_JOIN_IN }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_AO }, + }, + [GARP_APPLICANT_QP] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QP }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_QO }, + }, + [GARP_APPLICANT_VO] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_AO }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_VP }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, + }, + [GARP_APPLICANT_AO] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_AP }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, + }, + [GARP_APPLICANT_QO] = { + [GARP_EVENT_TRANSMIT_PDU] = { .state = GARP_APPLICANT_INVALID }, + [GARP_EVENT_R_JOIN_IN] = { .state = GARP_APPLICANT_QO }, + [GARP_EVENT_R_JOIN_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_LEAVE_IN] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_R_LEAVE_EMPTY] = { .state = GARP_APPLICANT_VO }, + [GARP_EVENT_REQ_JOIN] = { .state = GARP_APPLICANT_QP }, + [GARP_EVENT_REQ_LEAVE] = { .state = GARP_APPLICANT_INVALID }, + }, +}; + +static int garp_attr_cmp(const struct garp_attr *attr, + const void *data, u8 len, u8 type) +{ + if (attr->type != type) + return attr->type - type; + if (attr->dlen != len) + return attr->dlen - len; + return memcmp(attr->data, data, len); +} + +static struct garp_attr *garp_attr_lookup(const struct garp_applicant *app, + const void *data, u8 len, u8 type) +{ + struct rb_node *parent = app->gid.rb_node; + struct garp_attr *attr; + int d; + + while (parent) { + attr = rb_entry(parent, struct garp_attr, node); + d = garp_attr_cmp(attr, data, len, type); + if (d < 0) + parent = parent->rb_left; + else if (d > 0) + parent = parent->rb_right; + else + return attr; + } + return NULL; +} + +static void garp_attr_insert(struct garp_applicant *app, struct garp_attr *new) +{ + struct rb_node *parent = NULL, **p = &app->gid.rb_node; + struct garp_attr *attr; + int d; + + while (*p) { + parent = *p; + attr = rb_entry(parent, struct garp_attr, node); + d = garp_attr_cmp(attr, new->data, new->dlen, new->type); + if (d < 0) + p = &parent->rb_left; + else if (d > 0) + p = &parent->rb_right; + } + rb_link_node(&new->node, parent, p); + rb_insert_color(&new->node, &app->gid); +} + +static struct garp_attr *garp_attr_create(struct garp_applicant *app, + const void *data, u8 len, u8 type) +{ + struct garp_attr *attr; + + attr = kmalloc(sizeof(*attr) + len, GFP_ATOMIC); + if (!attr) + return attr; + attr->state = GARP_APPLICANT_VO; + attr->type = type; + attr->dlen = len; + memcpy(attr->data, data, len); + garp_attr_insert(app, attr); + return attr; +} + +static void garp_attr_destroy(struct garp_applicant *app, struct garp_attr *attr) +{ + rb_erase(&attr->node, &app->gid); + kfree(attr); +} + +static int garp_pdu_init(struct garp_applicant *app) +{ + struct sk_buff *skb; + struct garp_pdu_hdr *gp; + +#define LLC_RESERVE sizeof(struct llc_pdu_un) + skb = alloc_skb(app->dev->mtu + LL_RESERVED_SPACE(app->dev), + GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + skb->dev = app->dev; + skb->protocol = htons(ETH_P_802_2); + skb_reserve(skb, LL_RESERVED_SPACE(app->dev) + LLC_RESERVE); + + gp = (struct garp_pdu_hdr *)__skb_put(skb, sizeof(*gp)); + put_unaligned(htons(GARP_PROTOCOL_ID), &gp->protocol); + + app->pdu = skb; + return 0; +} + +static int garp_pdu_append_end_mark(struct garp_applicant *app) +{ + if (skb_tailroom(app->pdu) < sizeof(u8)) + return -1; + *(u8 *)__skb_put(app->pdu, sizeof(u8)) = GARP_END_MARK; + return 0; +} + +static void garp_pdu_queue(struct garp_applicant *app) +{ + if (!app->pdu) + return; + + garp_pdu_append_end_mark(app); + garp_pdu_append_end_mark(app); + + llc_pdu_header_init(app->pdu, LLC_PDU_TYPE_U, LLC_SAP_BSPAN, + LLC_SAP_BSPAN, LLC_PDU_CMD); + llc_pdu_init_as_ui_cmd(app->pdu); + llc_mac_hdr_init(app->pdu, app->dev->dev_addr, + app->app->proto.group_address); + + skb_queue_tail(&app->queue, app->pdu); + app->pdu = NULL; +} + +static void garp_queue_xmit(struct garp_applicant *app) +{ + struct sk_buff *skb; + + while ((skb = skb_dequeue(&app->queue))) + dev_queue_xmit(skb); +} + +static int garp_pdu_append_msg(struct garp_applicant *app, u8 attrtype) +{ + struct garp_msg_hdr *gm; + + if (skb_tailroom(app->pdu) < sizeof(*gm)) + return -1; + gm = (struct garp_msg_hdr *)__skb_put(app->pdu, sizeof(*gm)); + gm->attrtype = attrtype; + garp_cb(app->pdu)->cur_type = attrtype; + return 0; +} + +static int garp_pdu_append_attr(struct garp_applicant *app, + const struct garp_attr *attr, + enum garp_attr_event event) +{ + struct garp_attr_hdr *ga; + unsigned int len; + int err; +again: + if (!app->pdu) { + err = garp_pdu_init(app); + if (err < 0) + return err; + } + + if (garp_cb(app->pdu)->cur_type != attr->type) { + if (garp_cb(app->pdu)->cur_type && + garp_pdu_append_end_mark(app) < 0) + goto queue; + if (garp_pdu_append_msg(app, attr->type) < 0) + goto queue; + } + + len = sizeof(*ga) + attr->dlen; + if (skb_tailroom(app->pdu) < len) + goto queue; + ga = (struct garp_attr_hdr *)__skb_put(app->pdu, len); + ga->len = len; + ga->event = event; + memcpy(ga->data, attr->data, attr->dlen); + return 0; + +queue: + garp_pdu_queue(app); + goto again; +} + +static void garp_attr_event(struct garp_applicant *app, + struct garp_attr *attr, enum garp_event event) +{ + enum garp_applicant_state state; + + state = garp_applicant_state_table[attr->state][event].state; + if (state == GARP_APPLICANT_INVALID) + return; + + switch (garp_applicant_state_table[attr->state][event].action) { + case GARP_ACTION_NONE: + break; + case GARP_ACTION_S_JOIN_IN: + garp_pdu_append_attr(app, attr, GARP_JOIN_IN); + break; + case GARP_ACTION_S_LEAVE_EMPTY: + garp_pdu_append_attr(app, attr, GARP_LEAVE_EMPTY); + /* As a pure applicant, sending a leave message implies that + * the attribute was unregistered and can be destroyed. */ + garp_attr_destroy(app, attr); + return; + default: + WARN_ON(1); + } + + attr->state = state; +} + +int garp_request_join(const struct net_device *dev, + const struct garp_application *appl, + const void *data, u8 len, u8 type) +{ + struct garp_port *port = dev->garp_port; + struct garp_applicant *app = port->applicants[appl->type]; + struct garp_attr *attr; + + spin_lock_bh(&app->lock); + attr = garp_attr_create(app, data, len, type); + if (!attr) { + spin_unlock_bh(&app->lock); + return -ENOMEM; + } + garp_attr_event(app, attr, GARP_EVENT_REQ_JOIN); + spin_unlock_bh(&app->lock); + return 0; +} +EXPORT_SYMBOL_GPL(garp_request_join); + +void garp_request_leave(const struct net_device *dev, + const struct garp_application *appl, + const void *data, u8 len, u8 type) +{ + struct garp_port *port = dev->garp_port; + struct garp_applicant *app = port->applicants[appl->type]; + struct garp_attr *attr; + + spin_lock_bh(&app->lock); + attr = garp_attr_lookup(app, data, len, type); + if (!attr) { + spin_unlock_bh(&app->lock); + return; + } + garp_attr_event(app, attr, GARP_EVENT_REQ_LEAVE); + spin_unlock_bh(&app->lock); +} +EXPORT_SYMBOL_GPL(garp_request_leave); + +static void garp_gid_event(struct garp_applicant *app, enum garp_event event) +{ + struct rb_node *node, *next; + struct garp_attr *attr; + + for (node = rb_first(&app->gid); + next = node ? rb_next(node) : NULL, node != NULL; + node = next) { + attr = rb_entry(node, struct garp_attr, node); + garp_attr_event(app, attr, event); + } +} + +static void garp_join_timer_arm(struct garp_applicant *app) +{ + unsigned long delay; + + delay = (u64)msecs_to_jiffies(garp_join_time) * net_random() >> 32; + mod_timer(&app->join_timer, jiffies + delay); +} + +static void garp_join_timer(unsigned long data) +{ + struct garp_applicant *app = (struct garp_applicant *)data; + + spin_lock(&app->lock); + garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_pdu_queue(app); + spin_unlock(&app->lock); + + garp_queue_xmit(app); + garp_join_timer_arm(app); +} + +static int garp_pdu_parse_end_mark(struct sk_buff *skb) +{ + if (!pskb_may_pull(skb, sizeof(u8))) + return -1; + if (*skb->data == GARP_END_MARK) { + skb_pull(skb, sizeof(u8)); + return -1; + } + return 0; +} + +static int garp_pdu_parse_attr(struct garp_applicant *app, struct sk_buff *skb, + u8 attrtype) +{ + const struct garp_attr_hdr *ga; + struct garp_attr *attr; + enum garp_event event; + unsigned int dlen; + + if (!pskb_may_pull(skb, sizeof(*ga))) + return -1; + ga = (struct garp_attr_hdr *)skb->data; + if (ga->len < sizeof(*ga)) + return -1; + + if (!pskb_may_pull(skb, ga->len)) + return -1; + skb_pull(skb, ga->len); + dlen = sizeof(*ga) - ga->len; + + if (attrtype > app->app->maxattr) + return 0; + + switch (ga->event) { + case GARP_LEAVE_ALL: + if (dlen != 0) + return -1; + garp_gid_event(app, GARP_EVENT_R_LEAVE_EMPTY); + return 0; + case GARP_JOIN_EMPTY: + event = GARP_EVENT_R_JOIN_EMPTY; + break; + case GARP_JOIN_IN: + event = GARP_EVENT_R_JOIN_IN; + break; + case GARP_LEAVE_EMPTY: + event = GARP_EVENT_R_LEAVE_EMPTY; + break; + case GARP_EMPTY: + event = GARP_EVENT_R_EMPTY; + break; + default: + return 0; + } + + if (dlen == 0) + return -1; + attr = garp_attr_lookup(app, ga->data, dlen, attrtype); + if (attr == NULL) + return 0; + garp_attr_event(app, attr, event); + return 0; +} + +static int garp_pdu_parse_msg(struct garp_applicant *app, struct sk_buff *skb) +{ + const struct garp_msg_hdr *gm; + + if (!pskb_may_pull(skb, sizeof(*gm))) + return -1; + gm = (struct garp_msg_hdr *)skb->data; + if (gm->attrtype == 0) + return -1; + skb_pull(skb, sizeof(*gm)); + + while (skb->len > 0) { + if (garp_pdu_parse_attr(app, skb, gm->attrtype) < 0) + return -1; + if (garp_pdu_parse_end_mark(skb) < 0) + break; + } + return 0; +} + +static void garp_pdu_rcv(const struct stp_proto *proto, struct sk_buff *skb, + struct net_device *dev) +{ + struct garp_application *appl = proto->data; + struct garp_port *port; + struct garp_applicant *app; + const struct garp_pdu_hdr *gp; + + port = rcu_dereference(dev->garp_port); + if (!port) + goto err; + app = rcu_dereference(port->applicants[appl->type]); + if (!app) + goto err; + + if (!pskb_may_pull(skb, sizeof(*gp))) + goto err; + gp = (struct garp_pdu_hdr *)skb->data; + if (get_unaligned(&gp->protocol) != htons(GARP_PROTOCOL_ID)) + goto err; + skb_pull(skb, sizeof(*gp)); + + spin_lock(&app->lock); + while (skb->len > 0) { + if (garp_pdu_parse_msg(app, skb) < 0) + break; + if (garp_pdu_parse_end_mark(skb) < 0) + break; + } + spin_unlock(&app->lock); +err: + kfree_skb(skb); +} + +static int garp_init_port(struct net_device *dev) +{ + struct garp_port *port; + + port = kzalloc(sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + rcu_assign_pointer(dev->garp_port, port); + return 0; +} + +static void garp_release_port(struct net_device *dev) +{ + struct garp_port *port = dev->garp_port; + unsigned int i; + + for (i = 0; i <= GARP_APPLICATION_MAX; i++) { + if (port->applicants[i]) + return; + } + rcu_assign_pointer(dev->garp_port, NULL); + synchronize_rcu(); + kfree(port); +} + +int garp_init_applicant(struct net_device *dev, struct garp_application *appl) +{ + struct garp_applicant *app; + int err; + + ASSERT_RTNL(); + + if (!dev->garp_port) { + err = garp_init_port(dev); + if (err < 0) + goto err1; + } + + err = -ENOMEM; + app = kzalloc(sizeof(*app), GFP_KERNEL); + if (!app) + goto err2; + + err = dev_mc_add(dev, appl->proto.group_address, ETH_ALEN, 0); + if (err < 0) + goto err3; + + app->dev = dev; + app->app = appl; + app->gid = RB_ROOT; + spin_lock_init(&app->lock); + skb_queue_head_init(&app->queue); + rcu_assign_pointer(dev->garp_port->applicants[appl->type], app); + setup_timer(&app->join_timer, garp_join_timer, (unsigned long)app); + garp_join_timer_arm(app); + return 0; + +err3: + kfree(app); +err2: + garp_release_port(dev); +err1: + return err; +} +EXPORT_SYMBOL_GPL(garp_init_applicant); + +void garp_uninit_applicant(struct net_device *dev, struct garp_application *appl) +{ + struct garp_port *port = dev->garp_port; + struct garp_applicant *app = port->applicants[appl->type]; + + ASSERT_RTNL(); + + rcu_assign_pointer(port->applicants[appl->type], NULL); + synchronize_rcu(); + + /* Delete timer and generate a final TRANSMIT_PDU event to flush out + * all pending messages before the applicant is gone. */ + del_timer_sync(&app->join_timer); + garp_gid_event(app, GARP_EVENT_TRANSMIT_PDU); + garp_pdu_queue(app); + garp_queue_xmit(app); + + dev_mc_delete(dev, appl->proto.group_address, ETH_ALEN, 0); + kfree(app); + garp_release_port(dev); +} +EXPORT_SYMBOL_GPL(garp_uninit_applicant); + +int garp_register_application(struct garp_application *appl) +{ + appl->proto.rcv = garp_pdu_rcv; + appl->proto.data = appl; + return stp_proto_register(&appl->proto); +} +EXPORT_SYMBOL_GPL(garp_register_application); + +void garp_unregister_application(struct garp_application *appl) +{ + stp_proto_unregister(&appl->proto); +} +EXPORT_SYMBOL_GPL(garp_unregister_application); diff --git a/net/802/stp.c b/net/802/stp.c new file mode 100644 index 0000000..0b7a244 --- /dev/null +++ b/net/802/stp.c @@ -0,0 +1,102 @@ +/* + * STP SAP demux + * + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ +#include <linux/mutex.h> +#include <linux/skbuff.h> +#include <linux/etherdevice.h> +#include <linux/llc.h> +#include <net/llc.h> +#include <net/llc_pdu.h> +#include <net/stp.h> + +/* 01:80:c2:00:00:20 - 01:80:c2:00:00:2F */ +#define GARP_ADDR_MIN 0x20 +#define GARP_ADDR_MAX 0x2F +#define GARP_ADDR_RANGE (GARP_ADDR_MAX - GARP_ADDR_MIN) + +static const struct stp_proto *garp_protos[GARP_ADDR_RANGE + 1] __read_mostly; +static const struct stp_proto *stp_proto __read_mostly; + +static struct llc_sap *sap __read_mostly; +static unsigned int sap_registered; +static DEFINE_MUTEX(stp_proto_mutex); + +/* Called under rcu_read_lock from LLC */ +static int stp_pdu_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + const struct ethhdr *eh = eth_hdr(skb); + const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); + const struct stp_proto *proto; + + if (pdu->ssap != LLC_SAP_BSPAN || + pdu->dsap != LLC_SAP_BSPAN || + pdu->ctrl_1 != LLC_PDU_TYPE_U) + goto err; + + if (eh->h_dest[5] >= GARP_ADDR_MIN && eh->h_dest[5] <= GARP_ADDR_MAX) { + proto = rcu_dereference(garp_protos[eh->h_dest[5] - + GARP_ADDR_MIN]); + if (proto && + compare_ether_addr(eh->h_dest, proto->group_address)) + goto err; + } else + proto = rcu_dereference(stp_proto); + + if (!proto) + goto err; + + proto->rcv(proto, skb, dev); + return 0; + +err: + kfree_skb(skb); + return 0; +} + +int stp_proto_register(const struct stp_proto *proto) +{ + int err = 0; + + mutex_lock(&stp_proto_mutex); + if (sap_registered++ == 0) { + sap = llc_sap_open(LLC_SAP_BSPAN, stp_pdu_rcv); + if (!sap) { + err = -ENOMEM; + goto out; + } + } + if (is_zero_ether_addr(proto->group_address)) + rcu_assign_pointer(stp_proto, proto); + else + rcu_assign_pointer(garp_protos[proto->group_address[5] - + GARP_ADDR_MIN], proto); +out: + mutex_unlock(&stp_proto_mutex); + return err; +} +EXPORT_SYMBOL_GPL(stp_proto_register); + +void stp_proto_unregister(const struct stp_proto *proto) +{ + mutex_lock(&stp_proto_mutex); + if (is_zero_ether_addr(proto->group_address)) + rcu_assign_pointer(stp_proto, NULL); + else + rcu_assign_pointer(garp_protos[proto->group_address[5] - + GARP_ADDR_MIN], NULL); + synchronize_rcu(); + + if (--sap_registered == 0) + llc_sap_put(sap); + mutex_unlock(&stp_proto_mutex); +} +EXPORT_SYMBOL_GPL(stp_proto_unregister); + +MODULE_LICENSE("GPL"); diff --git a/net/8021q/Kconfig b/net/8021q/Kconfig index c4a382e..fa073a5 100644 --- a/net/8021q/Kconfig +++ b/net/8021q/Kconfig @@ -17,3 +17,13 @@ config VLAN_8021Q will be called 8021q. If unsure, say N. + +config VLAN_8021Q_GVRP + bool "GVRP (GARP VLAN Registration Protocol) support" + depends on VLAN_8021Q + select GARP + help + Select this to enable GVRP end-system support. GVRP is used for + automatic propagation of registered VLANs to switches. + + If unsure, say N. diff --git a/net/8021q/Makefile b/net/8021q/Makefile index 10ca7f4..3006e9e 100644 --- a/net/8021q/Makefile +++ b/net/8021q/Makefile @@ -4,9 +4,6 @@ obj-$(CONFIG_VLAN_8021Q) += 8021q.o -8021q-objs := vlan.o vlan_dev.o vlan_netlink.o - -ifeq ($(CONFIG_PROC_FS),y) -8021q-objs += vlanproc.o -endif - +8021q-y := vlan.o vlan_dev.o vlan_netlink.o +8021q-$(CONFIG_VLAN_8021Q_GVRP) += vlan_gvrp.o +8021q-$(CONFIG_PROC_FS) += vlanproc.o diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index ab2225d..b529110 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -165,8 +165,12 @@ void unregister_vlan_dev(struct net_device *dev) synchronize_net(); + unregister_netdevice(dev); + /* If the group is now empty, kill off the group. */ if (grp->nr_vlans == 0) { + vlan_gvrp_uninit_applicant(real_dev); + if (real_dev->features & NETIF_F_HW_VLAN_RX) real_dev->vlan_rx_register(real_dev, NULL); @@ -178,8 +182,6 @@ void unregister_vlan_dev(struct net_device *dev) /* Get rid of the vlan's reference to real_dev */ dev_put(real_dev); - - unregister_netdevice(dev); } static void vlan_transfer_operstate(const struct net_device *dev, @@ -249,15 +251,18 @@ int register_vlan_dev(struct net_device *dev) ngrp = grp = vlan_group_alloc(real_dev); if (!grp) return -ENOBUFS; + err = vlan_gvrp_init_applicant(real_dev); + if (err < 0) + goto out_free_group; } err = vlan_group_prealloc_vid(grp, vlan_id); if (err < 0) - goto out_free_group; + goto out_uninit_applicant; err = register_netdevice(dev); if (err < 0) - goto out_free_group; + goto out_uninit_applicant; /* Account for reference in struct vlan_dev_info */ dev_hold(real_dev); @@ -278,6 +283,9 @@ int register_vlan_dev(struct net_device *dev) return 0; +out_uninit_applicant: + if (ngrp) + vlan_gvrp_uninit_applicant(real_dev); out_free_group: if (ngrp) vlan_group_free(ngrp); @@ -591,9 +599,9 @@ static int vlan_ioctl_handler(struct net *net, void __user *arg) err = -EPERM; if (!capable(CAP_NET_ADMIN)) break; - err = vlan_dev_set_vlan_flag(dev, - args.u.flag, - args.vlan_qos); + err = vlan_dev_change_flags(dev, + args.vlan_qos ? args.u.flag : 0, + args.u.flag); break; case SET_VLAN_NAME_TYPE_CMD: @@ -713,14 +721,20 @@ static int __init vlan_proto_init(void) if (err < 0) goto err2; - err = vlan_netlink_init(); + err = vlan_gvrp_init(); if (err < 0) goto err3; + err = vlan_netlink_init(); + if (err < 0) + goto err4; + dev_add_pack(&vlan_packet_type); vlan_ioctl_set(vlan_ioctl_handler); return 0; +err4: + vlan_gvrp_uninit(); err3: unregister_netdevice_notifier(&vlan_notifier_block); err2: @@ -745,8 +759,9 @@ static void __exit vlan_cleanup_module(void) BUG_ON(!hlist_empty(&vlan_group_hash[i])); unregister_pernet_gen_device(vlan_net_id, &vlan_net_ops); - synchronize_net(); + + vlan_gvrp_uninit(); } module_init(vlan_proto_init); diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 5229a72..097b2e0 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -28,8 +28,7 @@ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, short vlan_prio); int vlan_dev_set_egress_priority(const struct net_device *dev, u32 skb_prio, short vlan_prio); -int vlan_dev_set_vlan_flag(const struct net_device *dev, - u32 flag, short flag_val); +int vlan_dev_change_flags(const struct net_device *dev, u32 flag, u32 mask); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); void vlan_dev_get_vid(const struct net_device *dev, unsigned short *result); @@ -38,6 +37,22 @@ void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev); void unregister_vlan_dev(struct net_device *dev); +#ifdef CONFIG_VLAN_8021Q_GVRP +extern int vlan_gvrp_request_join(const struct net_device *dev); +extern void vlan_gvrp_request_leave(const struct net_device *dev); +extern int vlan_gvrp_init_applicant(struct net_device *dev); +extern void vlan_gvrp_uninit_applicant(struct net_device *dev); +extern int vlan_gvrp_init(void); +extern void vlan_gvrp_uninit(void); +#else +static inline int vlan_gvrp_request_join(const struct net_device *dev) { return 0; } +static inline void vlan_gvrp_request_leave(const struct net_device *dev) {} +static inline int vlan_gvrp_init_applicant(struct net_device *dev) { return 0; } +static inline void vlan_gvrp_uninit_applicant(struct net_device *dev) {} +static inline int vlan_gvrp_init(void) { return 0; } +static inline void vlan_gvrp_uninit(void) {} +#endif + int vlan_netlink_init(void); void vlan_netlink_fini(void); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 5d055c2..a0617bf 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -507,18 +507,23 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, } /* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */ -int vlan_dev_set_vlan_flag(const struct net_device *dev, - u32 flag, short flag_val) +int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) { - /* verify flag is supported */ - if (flag == VLAN_FLAG_REORDER_HDR) { - if (flag_val) - vlan_dev_info(dev)->flags |= VLAN_FLAG_REORDER_HDR; + struct vlan_dev_info *vlan = vlan_dev_info(dev); + u32 old_flags = vlan->flags; + + if (mask & ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) + return -EINVAL; + + vlan->flags = (old_flags & ~mask) | (flags & mask); + + if (netif_running(dev) && (vlan->flags ^ old_flags) & VLAN_FLAG_GVRP) { + if (vlan->flags & VLAN_FLAG_GVRP) + vlan_gvrp_request_join(dev); else - vlan_dev_info(dev)->flags &= ~VLAN_FLAG_REORDER_HDR; - return 0; + vlan_gvrp_request_leave(dev); } - return -EINVAL; + return 0; } void vlan_dev_get_realdev_name(const struct net_device *dev, char *result) @@ -552,12 +557,19 @@ static int vlan_dev_open(struct net_device *dev) if (dev->flags & IFF_PROMISC) dev_set_promiscuity(real_dev, 1); + if (vlan->flags & VLAN_FLAG_GVRP) + vlan_gvrp_request_join(dev); + return 0; } static int vlan_dev_stop(struct net_device *dev) { - struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + struct vlan_dev_info *vlan = vlan_dev_info(dev); + struct net_device *real_dev = vlan->real_dev; + + if (vlan->flags & VLAN_FLAG_GVRP) + vlan_gvrp_request_leave(dev); dev_mc_unsync(real_dev, dev); dev_unicast_unsync(real_dev, dev); diff --git a/net/8021q/vlan_gvrp.c b/net/8021q/vlan_gvrp.c new file mode 100644 index 0000000..db97816 --- /dev/null +++ b/net/8021q/vlan_gvrp.c @@ -0,0 +1,66 @@ +/* + * IEEE 802.1Q GARP VLAN Registration Protocol (GVRP) + * + * Copyright (c) 2008 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ +#include <linux/types.h> +#include <linux/if_vlan.h> +#include <net/garp.h> +#include "vlan.h" + +#define GARP_GVRP_ADDRESS { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x21 } + +enum gvrp_attributes { + GVRP_ATTR_INVALID, + GVRP_ATTR_VID, + __GVRP_ATTR_MAX +}; +#define GVRP_ATTR_MAX (__GVRP_ATTR_MAX - 1) + +static struct garp_application vlan_gvrp_app __read_mostly = { + .proto.group_address = GARP_GVRP_ADDRESS, + .maxattr = GVRP_ATTR_MAX, + .type = GARP_APPLICATION_GVRP, +}; + +int vlan_gvrp_request_join(const struct net_device *dev) +{ + const struct vlan_dev_info *vlan = vlan_dev_info(dev); + __be16 vid = htons(vlan->vlan_id); + + return garp_request_join(vlan->real_dev, &vlan_gvrp_app, + &vid, sizeof(vid), GVRP_ATTR_VID); +} + +void vlan_gvrp_request_leave(const struct net_device *dev) +{ + const struct vlan_dev_info *vlan = vlan_dev_info(dev); + __be16 vid = htons(vlan->vlan_id); + + garp_request_leave(vlan->real_dev, &vlan_gvrp_app, + &vid, sizeof(vid), GVRP_ATTR_VID); +} + +int vlan_gvrp_init_applicant(struct net_device *dev) +{ + return garp_init_applicant(dev, &vlan_gvrp_app); +} + +void vlan_gvrp_uninit_applicant(struct net_device *dev) +{ + garp_uninit_applicant(dev, &vlan_gvrp_app); +} + +int __init vlan_gvrp_init(void) +{ + return garp_register_application(&vlan_gvrp_app); +} + +void vlan_gvrp_uninit(void) +{ + garp_unregister_application(&vlan_gvrp_app); +} diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c93e69e..e9c91dc 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -59,7 +59,8 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) } if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); - if ((flags->flags & flags->mask) & ~VLAN_FLAG_REORDER_HDR) + if ((flags->flags & flags->mask) & + ~(VLAN_FLAG_REORDER_HDR | VLAN_FLAG_GVRP)) return -EINVAL; } @@ -75,7 +76,6 @@ static int vlan_validate(struct nlattr *tb[], struct nlattr *data[]) static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct vlan_dev_info *vlan = vlan_dev_info(dev); struct ifla_vlan_flags *flags; struct ifla_vlan_qos_mapping *m; struct nlattr *attr; @@ -83,8 +83,7 @@ static int vlan_changelink(struct net_device *dev, if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); - vlan->flags = (vlan->flags & ~flags->mask) | - (flags->flags & flags->mask); + vlan_dev_change_flags(dev, flags->flags, flags->mask); } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { diff --git a/net/Kconfig b/net/Kconfig index acbf7c60..b986687 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -181,6 +181,7 @@ source "net/dccp/Kconfig" source "net/sctp/Kconfig" source "net/tipc/Kconfig" source "net/atm/Kconfig" +source "net/802/Kconfig" source "net/bridge/Kconfig" source "net/8021q/Kconfig" source "net/decnet/Kconfig" diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index 12265af..e143ca6 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -5,6 +5,7 @@ config BRIDGE tristate "802.1d Ethernet Bridging" select LLC + select STP ---help--- If you say Y here, then your Linux box will be able to act as an Ethernet bridge, which means that the different Ethernet segments it diff --git a/net/bridge/br.c b/net/bridge/br.c index cede010..573acdf 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -18,21 +18,24 @@ #include <linux/init.h> #include <linux/llc.h> #include <net/llc.h> +#include <net/stp.h> #include "br_private.h" int (*br_should_route_hook)(struct sk_buff *skb); -static struct llc_sap *br_stp_sap; +static const struct stp_proto br_stp_proto = { + .rcv = br_stp_rcv, +}; static int __init br_init(void) { int err; - br_stp_sap = llc_sap_open(LLC_SAP_BSPAN, br_stp_rcv); - if (!br_stp_sap) { + err = stp_proto_register(&br_stp_proto); + if (err < 0) { printk(KERN_ERR "bridge: can't register sap for STP\n"); - return -EADDRINUSE; + return err; } err = br_fdb_init(); @@ -65,13 +68,13 @@ err_out2: err_out1: br_fdb_fini(); err_out: - llc_sap_put(br_stp_sap); + stp_proto_unregister(&br_stp_proto); return err; } static void __exit br_deinit(void) { - rcu_assign_pointer(br_stp_sap->rcv_func, NULL); + stp_proto_unregister(&br_stp_proto); br_netlink_fini(); unregister_netdevice_notifier(&br_device_notifier); @@ -82,7 +85,6 @@ static void __exit br_deinit(void) synchronize_net(); br_netfilter_fini(); - llc_sap_put(br_stp_sap); br_fdb_get_hook = NULL; br_fdb_put_hook = NULL; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 8593c9f..815ed38 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -226,8 +226,9 @@ extern void br_stp_set_path_cost(struct net_bridge_port *p, extern ssize_t br_show_bridge_id(char *buf, const struct bridge_id *id); /* br_stp_bpdu.c */ -extern int br_stp_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev); +struct stp_proto; +extern void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, + struct net_device *dev); /* br_stp_timer.c */ extern void br_stp_timer_init(struct net_bridge *br); diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c index 9dc2de6..9964761 100644 --- a/net/bridge/br_stp_bpdu.c +++ b/net/bridge/br_stp_bpdu.c @@ -18,6 +18,7 @@ #include <net/net_namespace.h> #include <net/llc.h> #include <net/llc_pdu.h> +#include <net/stp.h> #include <asm/unaligned.h> #include "br_private.h" @@ -131,10 +132,9 @@ void br_send_tcn_bpdu(struct net_bridge_port *p) * * NO locks, but rcu_read_lock (preempt_disabled) */ -int br_stp_rcv(struct sk_buff *skb, struct net_device *dev, - struct packet_type *pt, struct net_device *orig_dev) +void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb, + struct net_device *dev) { - const struct llc_pdu_un *pdu = llc_pdu_un_hdr(skb); const unsigned char *dest = eth_hdr(skb)->h_dest; struct net_bridge_port *p = rcu_dereference(dev->br_port); struct net_bridge *br; @@ -146,11 +146,6 @@ int br_stp_rcv(struct sk_buff *skb, struct net_device *dev, if (!p) goto err; - if (pdu->ssap != LLC_SAP_BSPAN - || pdu->dsap != LLC_SAP_BSPAN - || pdu->ctrl_1 != LLC_PDU_TYPE_U) - goto err; - if (!pskb_may_pull(skb, 4)) goto err; @@ -224,5 +219,4 @@ int br_stp_rcv(struct sk_buff *skb, struct net_device *dev, spin_unlock(&br->lock); err: kfree_skb(skb); - return 0; } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 0133b5e..14ada53 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -209,6 +209,36 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) return 0; } +static int ethtool_set_rxhash(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_rxnfc cmd; + + if (!dev->ethtool_ops->set_rxhash) + return -EOPNOTSUPP; + + if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + return -EFAULT; + + return dev->ethtool_ops->set_rxhash(dev, &cmd); +} + +static int ethtool_get_rxhash(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_rxnfc info; + + if (!dev->ethtool_ops->get_rxhash) + return -EOPNOTSUPP; + + if (copy_from_user(&info, useraddr, sizeof(info))) + return -EFAULT; + + dev->ethtool_ops->get_rxhash(dev, &info); + + if (copy_to_user(useraddr, &info, sizeof(info))) + return -EFAULT; + return 0; +} + static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) { struct ethtool_regs regs; @@ -826,6 +856,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GGSO: case ETHTOOL_GFLAGS: case ETHTOOL_GPFLAGS: + case ETHTOOL_GRXFH: break; default: if (!capable(CAP_NET_ADMIN)) @@ -977,6 +1008,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) rc = ethtool_set_value(dev, useraddr, dev->ethtool_ops->set_priv_flags); break; + case ETHTOOL_GRXFH: + rc = ethtool_get_rxhash(dev, useraddr); + break; + case ETHTOOL_SRXFH: + rc = ethtool_set_rxhash(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index e3e9ab0..1c2943a 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -69,7 +69,7 @@ static void rules_ops_put(struct fib_rules_ops *ops) static void flush_route_cache(struct fib_rules_ops *ops) { if (ops->flush_cache) - ops->flush_cache(); + ops->flush_cache(ops); } int fib_rules_register(struct fib_rules_ops *ops) diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index 5b7539b..14fbca5 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -229,7 +229,7 @@ static u32 dn_fib_rule_default_pref(struct fib_rules_ops *ops) return 0; } -static void dn_fib_rule_flush_cache(void) +static void dn_fib_rule_flush_cache(struct fib_rules_ops *ops) { dn_rt_cache_flush(-1); } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 42bd24b..dc41133 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1479,14 +1479,15 @@ static int __init inet_init(void) * Initialise the multicast router */ #if defined(CONFIG_IP_MROUTE) - ip_mr_init(); + if (ip_mr_init()) + printk(KERN_CRIT "inet_init: Cannot init ipv4 mroute\n"); #endif /* * Initialise per-cpu ipv4 mibs */ if (init_ipv4_mibs()) - printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ; + printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ipv4_proc_init(); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 20c515a..29df75a 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1197,7 +1197,7 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, vo switch (event) { case NETDEV_CHANGEADDR: neigh_changeaddr(&arp_tbl, dev); - rt_cache_flush(0); + rt_cache_flush(dev_net(dev), 0); break; default: break; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 9de2514..2e667e2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1348,7 +1348,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, dev_disable_lro(idev->dev); } rtnl_unlock(); - rt_cache_flush(0); + rt_cache_flush(net, 0); } } @@ -1362,9 +1362,10 @@ int ipv4_doint_and_flush(ctl_table *ctl, int write, int *valp = ctl->data; int val = *valp; int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); + struct net *net = ctl->extra2; if (write && *valp != val) - rt_cache_flush(0); + rt_cache_flush(net, 0); return ret; } @@ -1375,9 +1376,10 @@ int ipv4_doint_and_flush_strategy(ctl_table *table, int __user *name, int nlen, { int ret = devinet_conf_sysctl(table, name, nlen, oldval, oldlenp, newval, newlen); + struct net *net = table->extra2; if (ret == 1) - rt_cache_flush(0); + rt_cache_flush(net, 0); return ret; } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 5ad01d6..65c1503 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -144,7 +144,7 @@ static void fib_flush(struct net *net) } if (flushed) - rt_cache_flush(-1); + rt_cache_flush(net, -1); } /* @@ -897,21 +897,22 @@ static void fib_disable_ip(struct net_device *dev, int force) { if (fib_sync_down_dev(dev, force)) fib_flush(dev_net(dev)); - rt_cache_flush(0); + rt_cache_flush(dev_net(dev), 0); arp_ifdown(dev); } static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { struct in_ifaddr *ifa = (struct in_ifaddr*)ptr; + struct net_device *dev = ifa->ifa_dev->dev; switch (event) { case NETDEV_UP: fib_add_ifaddr(ifa); #ifdef CONFIG_IP_ROUTE_MULTIPATH - fib_sync_up(ifa->ifa_dev->dev); + fib_sync_up(dev); #endif - rt_cache_flush(-1); + rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: fib_del_ifaddr(ifa); @@ -919,9 +920,9 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, /* Last address was deleted from this interface. Disable IP. */ - fib_disable_ip(ifa->ifa_dev->dev, 1); + fib_disable_ip(dev, 1); } else { - rt_cache_flush(-1); + rt_cache_flush(dev_net(dev), -1); } break; } @@ -949,14 +950,14 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo #ifdef CONFIG_IP_ROUTE_MULTIPATH fib_sync_up(dev); #endif - rt_cache_flush(-1); + rt_cache_flush(dev_net(dev), -1); break; case NETDEV_DOWN: fib_disable_ip(dev, 0); break; case NETDEV_CHANGEMTU: case NETDEV_CHANGE: - rt_cache_flush(0); + rt_cache_flush(dev_net(dev), 0); break; } return NOTIFY_DONE; diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index eeec4bf..c8cac6c 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -472,7 +472,7 @@ static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg) fib_release_info(fi_drop); if (state & FA_S_ACCESSED) - rt_cache_flush(-1); + rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); rtmsg_fib(RTM_NEWROUTE, key, fa, cfg->fc_dst_len, tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); return 0; @@ -532,7 +532,7 @@ static int fn_hash_insert(struct fib_table *tb, struct fib_config *cfg) if (new_f) fz->fz_nent++; - rt_cache_flush(-1); + rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, tb->tb_id, &cfg->fc_nlinfo, 0); @@ -614,7 +614,7 @@ static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg) write_unlock_bh(&fib_hash_lock); if (fa->fa_state & FA_S_ACCESSED) - rt_cache_flush(-1); + rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); fn_free_alias(fa, f); if (kill_fn) { fn_free_node(f); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 1fb5687..6080d71 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -258,9 +258,9 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(4); /* flow */ } -static void fib4_rule_flush_cache(void) +static void fib4_rule_flush_cache(struct fib_rules_ops *ops) { - rt_cache_flush(-1); + rt_cache_flush(ops->fro_net, -1); } static struct fib_rules_ops fib4_rules_ops_template = { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 394db9c..d16ae46 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1271,7 +1271,7 @@ static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg) fib_release_info(fi_drop); if (state & FA_S_ACCESSED) - rt_cache_flush(-1); + rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); @@ -1316,7 +1316,7 @@ static int fn_trie_insert(struct fib_table *tb, struct fib_config *cfg) list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : fa_head)); - rt_cache_flush(-1); + rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, 0); succeeded: @@ -1664,7 +1664,7 @@ static int fn_trie_delete(struct fib_table *tb, struct fib_config *cfg) trie_leaf_remove(t, l); if (fa->fa_state & FA_S_ACCESSED) - rt_cache_flush(-1); + rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); fib_release_info(fa->fa_info); alias_free_mem_rcu(fa); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 300ab0c..438fab9 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1878,16 +1878,36 @@ static struct net_protocol pim_protocol = { * Setup for IP multicast routing */ -void __init ip_mr_init(void) +int __init ip_mr_init(void) { + int err; + mrt_cachep = kmem_cache_create("ip_mrt_cache", sizeof(struct mfc_cache), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); + if (!mrt_cachep) + return -ENOMEM; + setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); - register_netdevice_notifier(&ip_mr_notifier); + err = register_netdevice_notifier(&ip_mr_notifier); + if (err) + goto reg_notif_fail; #ifdef CONFIG_PROC_FS - proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops); - proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops); + err = -ENOMEM; + if (!proc_net_fops_create(&init_net, "ip_mr_vif", 0, &ipmr_vif_fops)) + goto proc_vif_fail; + if (!proc_net_fops_create(&init_net, "ip_mr_cache", 0, &ipmr_mfc_fops)) + goto proc_cache_fail; #endif + return 0; +reg_notif_fail: + kmem_cache_destroy(mrt_cachep); +#ifdef CONFIG_PROC_FS +proc_vif_fail: + unregister_netdevice_notifier(&ip_mr_notifier); +proc_cache_fail: + proc_net_remove(&init_net, "ip_mr_vif"); +#endif + return err; } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index fe3a022..113cd25 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -132,7 +132,6 @@ static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ; static void rt_worker_func(struct work_struct *work); static DECLARE_DELAYED_WORK(expires_work, rt_worker_func); -static struct timer_list rt_secret_timer; /* * Interface to generic destination cache. @@ -251,20 +250,25 @@ static inline void rt_hash_lock_init(void) static struct rt_hash_bucket *rt_hash_table __read_mostly; static unsigned rt_hash_mask __read_mostly; static unsigned int rt_hash_log __read_mostly; -static atomic_t rt_genid __read_mostly; static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) \ (__raw_get_cpu_var(rt_cache_stat).field++) -static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx) +static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx, + int genid) { return jhash_3words((__force u32)(__be32)(daddr), (__force u32)(__be32)(saddr), - idx, atomic_read(&rt_genid)) + idx, genid) & rt_hash_mask; } +static inline int rt_genid(struct net *net) +{ + return atomic_read(&net->ipv4.rt_genid); +} + #ifdef CONFIG_PROC_FS struct rt_cache_iter_state { struct seq_net_private p; @@ -334,7 +338,7 @@ static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) struct rt_cache_iter_state *st = seq->private; if (*pos) return rt_cache_get_idx(seq, *pos - 1); - st->genid = atomic_read(&rt_genid); + st->genid = rt_genid(seq_file_net(seq)); return SEQ_START_TOKEN; } @@ -681,6 +685,11 @@ static inline int compare_netns(struct rtable *rt1, struct rtable *rt2) return dev_net(rt1->u.dst.dev) == dev_net(rt2->u.dst.dev); } +static inline int rt_is_expired(struct rtable *rth) +{ + return rth->rt_genid != rt_genid(dev_net(rth->u.dst.dev)); +} + /* * Perform a full scan of hash table and free all entries. * Can be called by a softirq or a process. @@ -690,6 +699,7 @@ static void rt_do_flush(int process_context) { unsigned int i; struct rtable *rth, *next; + struct rtable * tail; for (i = 0; i <= rt_hash_mask; i++) { if (process_context && need_resched()) @@ -699,11 +709,39 @@ static void rt_do_flush(int process_context) continue; spin_lock_bh(rt_hash_lock_addr(i)); +#ifdef CONFIG_NET_NS + { + struct rtable ** prev, * p; + + rth = rt_hash_table[i].chain; + + /* defer releasing the head of the list after spin_unlock */ + for (tail = rth; tail; tail = tail->u.dst.rt_next) + if (!rt_is_expired(tail)) + break; + if (rth != tail) + rt_hash_table[i].chain = tail; + + /* call rt_free on entries after the tail requiring flush */ + prev = &rt_hash_table[i].chain; + for (p = *prev; p; p = next) { + next = p->u.dst.rt_next; + if (!rt_is_expired(p)) { + prev = &p->u.dst.rt_next; + } else { + *prev = next; + rt_free(p); + } + } + } +#else rth = rt_hash_table[i].chain; rt_hash_table[i].chain = NULL; + tail = NULL; +#endif spin_unlock_bh(rt_hash_lock_addr(i)); - for (; rth; rth = next) { + for (; rth != tail; rth = next) { next = rth->u.dst.rt_next; rt_free(rth); } @@ -736,7 +774,7 @@ static void rt_check_expire(void) continue; spin_lock_bh(rt_hash_lock_addr(i)); while ((rth = *rthp) != NULL) { - if (rth->rt_genid != atomic_read(&rt_genid)) { + if (rt_is_expired(rth)) { *rthp = rth->u.dst.rt_next; rt_free(rth); continue; @@ -779,21 +817,21 @@ static void rt_worker_func(struct work_struct *work) * many times (2^24) without giving recent rt_genid. * Jenkins hash is strong enough that litle changes of rt_genid are OK. */ -static void rt_cache_invalidate(void) +static void rt_cache_invalidate(struct net *net) { unsigned char shuffle; get_random_bytes(&shuffle, sizeof(shuffle)); - atomic_add(shuffle + 1U, &rt_genid); + atomic_add(shuffle + 1U, &net->ipv4.rt_genid); } /* * delay < 0 : invalidate cache (fast : entries will be deleted later) * delay >= 0 : invalidate & flush cache (can be long) */ -void rt_cache_flush(int delay) +void rt_cache_flush(struct net *net, int delay) { - rt_cache_invalidate(); + rt_cache_invalidate(net); if (delay >= 0) rt_do_flush(!in_softirq()); } @@ -801,10 +839,11 @@ void rt_cache_flush(int delay) /* * We change rt_genid and let gc do the cleanup */ -static void rt_secret_rebuild(unsigned long dummy) +static void rt_secret_rebuild(unsigned long __net) { - rt_cache_invalidate(); - mod_timer(&rt_secret_timer, jiffies + ip_rt_secret_interval); + struct net *net = (struct net *)__net; + rt_cache_invalidate(net); + mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval); } /* @@ -880,7 +919,7 @@ static int rt_garbage_collect(struct dst_ops *ops) rthp = &rt_hash_table[k].chain; spin_lock_bh(rt_hash_lock_addr(k)); while ((rth = *rthp) != NULL) { - if (rth->rt_genid == atomic_read(&rt_genid) && + if (!rt_is_expired(rth) && !rt_may_expire(rth, tmo, expire)) { tmo >>= 1; rthp = &rth->u.dst.rt_next; @@ -962,7 +1001,7 @@ restart: spin_lock_bh(rt_hash_lock_addr(hash)); while ((rth = *rthp) != NULL) { - if (rth->rt_genid != atomic_read(&rt_genid)) { + if (rt_is_expired(rth)) { *rthp = rth->u.dst.rt_next; rt_free(rth); continue; @@ -1138,7 +1177,7 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_lock_bh(rt_hash_lock_addr(hash)); ip_rt_put(rt); while ((aux = *rthp) != NULL) { - if (aux == rt || (aux->rt_genid != atomic_read(&rt_genid))) { + if (aux == rt || rt_is_expired(aux)) { *rthp = aux->u.dst.rt_next; rt_free(aux); continue; @@ -1180,7 +1219,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, for (i = 0; i < 2; i++) { for (k = 0; k < 2; k++) { - unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]); + unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], + rt_genid(net)); rthp=&rt_hash_table[hash].chain; @@ -1192,7 +1232,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rth->fl.fl4_src != skeys[i] || rth->fl.oif != ikeys[k] || rth->fl.iif != 0 || - rth->rt_genid != atomic_read(&rt_genid) || + rt_is_expired(rth) || !net_eq(dev_net(rth->u.dst.dev), net)) { rthp = &rth->u.dst.rt_next; continue; @@ -1231,7 +1271,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rt->u.dst.neighbour = NULL; rt->u.dst.hh = NULL; rt->u.dst.xfrm = NULL; - rt->rt_genid = atomic_read(&rt_genid); + rt->rt_genid = rt_genid(net); rt->rt_flags |= RTCF_REDIRECTED; /* Gateway is different ... */ @@ -1295,7 +1335,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) } else if ((rt->rt_flags & RTCF_REDIRECTED) || rt->u.dst.expires) { unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src, - rt->fl.oif); + rt->fl.oif, + rt_genid(dev_net(dst->dev))); #if RT_CACHE_DEBUG >= 1 printk(KERN_DEBUG "ipv4_negative_advice: redirect to " NIPQUAD_FMT "/%02x dropped\n", @@ -1444,7 +1485,8 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, for (k = 0; k < 2; k++) { for (i = 0; i < 2; i++) { - unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]); + unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], + rt_genid(net)); rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -1459,7 +1501,7 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, rth->fl.iif != 0 || dst_metric_locked(&rth->u.dst, RTAX_MTU) || !net_eq(dev_net(rth->u.dst.dev), net) || - rth->rt_genid != atomic_read(&rt_genid)) + !rt_is_expired(rth)) continue; if (new_mtu < 68 || new_mtu >= old_mtu) { @@ -1694,7 +1736,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.oif = 0; rth->rt_gateway = daddr; rth->rt_spec_dst= spec_dst; - rth->rt_genid = atomic_read(&rt_genid); + rth->rt_genid = rt_genid(dev_net(dev)); rth->rt_flags = RTCF_MULTICAST; rth->rt_type = RTN_MULTICAST; if (our) { @@ -1709,7 +1751,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, RT_CACHE_STAT_INC(in_slow_mc); in_dev_put(in_dev); - hash = rt_hash(daddr, saddr, dev->ifindex); + hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); return rt_intern_hash(hash, rth, &skb->rtable); e_nobufs: @@ -1835,7 +1877,7 @@ static int __mkroute_input(struct sk_buff *skb, rth->u.dst.input = ip_forward; rth->u.dst.output = ip_output; - rth->rt_genid = atomic_read(&rt_genid); + rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev)); rt_set_nexthop(rth, res, itag); @@ -1870,7 +1912,8 @@ static int ip_mkroute_input(struct sk_buff *skb, return err; /* put it into the cache */ - hash = rt_hash(daddr, saddr, fl->iif); + hash = rt_hash(daddr, saddr, fl->iif, + rt_genid(dev_net(rth->u.dst.dev))); return rt_intern_hash(hash, rth, &skb->rtable); } @@ -1996,7 +2039,7 @@ local_input: goto e_nobufs; rth->u.dst.output= ip_rt_bug; - rth->rt_genid = atomic_read(&rt_genid); + rth->rt_genid = rt_genid(net); atomic_set(&rth->u.dst.__refcnt, 1); rth->u.dst.flags= DST_HOST; @@ -2026,7 +2069,7 @@ local_input: rth->rt_flags &= ~RTCF_LOCAL; } rth->rt_type = res.type; - hash = rt_hash(daddr, saddr, fl.iif); + hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); err = rt_intern_hash(hash, rth, &skb->rtable); goto done; @@ -2077,7 +2120,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, net = dev_net(dev); tos &= IPTOS_RT_MASK; - hash = rt_hash(daddr, saddr, iif); + hash = rt_hash(daddr, saddr, iif, rt_genid(net)); rcu_read_lock(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -2089,7 +2132,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, (rth->fl.fl4_tos ^ tos)) == 0 && rth->fl.mark == skb->mark && net_eq(dev_net(rth->u.dst.dev), net) && - rth->rt_genid == atomic_read(&rt_genid)) { + !rt_is_expired(rth)) { dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(in_hit); rcu_read_unlock(); @@ -2217,7 +2260,7 @@ static int __mkroute_output(struct rtable **result, rth->rt_spec_dst= fl->fl4_src; rth->u.dst.output=ip_output; - rth->rt_genid = atomic_read(&rt_genid); + rth->rt_genid = rt_genid(dev_net(dev_out)); RT_CACHE_STAT_INC(out_slow_tot); @@ -2266,7 +2309,8 @@ static int ip_mkroute_output(struct rtable **rp, int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags); unsigned hash; if (err == 0) { - hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif); + hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif, + rt_genid(dev_net(dev_out))); err = rt_intern_hash(hash, rth, rp); } @@ -2478,7 +2522,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, unsigned hash; struct rtable *rth; - hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif); + hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net)); rcu_read_lock_bh(); for (rth = rcu_dereference(rt_hash_table[hash].chain); rth; @@ -2491,7 +2535,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, !((rth->fl.fl4_tos ^ flp->fl4_tos) & (IPTOS_RT_MASK | RTO_ONLINK)) && net_eq(dev_net(rth->u.dst.dev), net) && - rth->rt_genid == atomic_read(&rt_genid)) { + !rt_is_expired(rth)) { dst_use(&rth->u.dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); @@ -2522,7 +2566,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { }; -static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp) +static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi *flp) { struct rtable *ort = *rp; struct rtable *rt = (struct rtable *) @@ -2546,7 +2590,7 @@ static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp) rt->idev = ort->idev; if (rt->idev) in_dev_hold(rt->idev); - rt->rt_genid = atomic_read(&rt_genid); + rt->rt_genid = rt_genid(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_dst = ort->rt_dst; @@ -2582,7 +2626,7 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp, err = __xfrm_lookup((struct dst_entry **)rp, flp, sk, flags ? XFRM_LOOKUP_WAIT : 0); if (err == -EREMOTE) - err = ipv4_dst_blackhole(rp, flp); + err = ipv4_dst_blackhole(net, rp, flp); return err; } @@ -2801,7 +2845,7 @@ int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb) rt = rcu_dereference(rt->u.dst.rt_next), idx++) { if (!net_eq(dev_net(rt->u.dst.dev), net) || idx < s_idx) continue; - if (rt->rt_genid != atomic_read(&rt_genid)) + if (rt_is_expired(rt)) continue; skb->dst = dst_clone(&rt->u.dst); if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid, @@ -2825,19 +2869,27 @@ done: void ip_rt_multicast_event(struct in_device *in_dev) { - rt_cache_flush(0); + rt_cache_flush(dev_net(in_dev->dev), 0); } #ifdef CONFIG_SYSCTL -static int flush_delay; - static int ipv4_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { if (write) { + int flush_delay; + struct net *net; + static DEFINE_MUTEX(flush_mutex); + + mutex_lock(&flush_mutex); + ctl->data = &flush_delay; proc_dointvec(ctl, write, filp, buffer, lenp, ppos); - rt_cache_flush(flush_delay); + ctl->data = NULL; + mutex_unlock(&flush_mutex); + + net = (struct net *)ctl->extra1; + rt_cache_flush(net, flush_delay); return 0; } @@ -2853,25 +2905,18 @@ static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, size_t newlen) { int delay; + struct net *net; if (newlen != sizeof(int)) return -EINVAL; if (get_user(delay, (int __user *)newval)) return -EFAULT; - rt_cache_flush(delay); + net = (struct net *)table->extra1; + rt_cache_flush(net, delay); return 0; } ctl_table ipv4_route_table[] = { { - .ctl_name = NET_IPV4_ROUTE_FLUSH, - .procname = "flush", - .data = &flush_delay, - .maxlen = sizeof(int), - .mode = 0200, - .proc_handler = &ipv4_sysctl_rtcache_flush, - .strategy = &ipv4_sysctl_rtcache_flush_strategy, - }, - { .ctl_name = NET_IPV4_ROUTE_GC_THRESH, .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, @@ -3009,8 +3054,97 @@ ctl_table ipv4_route_table[] = { }, { .ctl_name = 0 } }; + +static __net_initdata struct ctl_path ipv4_route_path[] = { + { .procname = "net", .ctl_name = CTL_NET, }, + { .procname = "ipv4", .ctl_name = NET_IPV4, }, + { .procname = "route", .ctl_name = NET_IPV4_ROUTE, }, + { }, +}; + + +static struct ctl_table ipv4_route_flush_table[] = { + { + .ctl_name = NET_IPV4_ROUTE_FLUSH, + .procname = "flush", + .maxlen = sizeof(int), + .mode = 0200, + .proc_handler = &ipv4_sysctl_rtcache_flush, + .strategy = &ipv4_sysctl_rtcache_flush_strategy, + }, + { .ctl_name = 0 }, +}; + +static __net_init int sysctl_route_net_init(struct net *net) +{ + struct ctl_table *tbl; + + tbl = ipv4_route_flush_table; + if (net != &init_net) { + tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); + if (tbl == NULL) + goto err_dup; + } + tbl[0].extra1 = net; + + net->ipv4.route_hdr = + register_net_sysctl_table(net, ipv4_route_path, tbl); + if (net->ipv4.route_hdr == NULL) + goto err_reg; + return 0; + +err_reg: + if (tbl != ipv4_route_flush_table) + kfree(tbl); +err_dup: + return -ENOMEM; +} + +static __net_exit void sysctl_route_net_exit(struct net *net) +{ + struct ctl_table *tbl; + + tbl = net->ipv4.route_hdr->ctl_table_arg; + unregister_net_sysctl_table(net->ipv4.route_hdr); + BUG_ON(tbl == ipv4_route_flush_table); + kfree(tbl); +} + +static __net_initdata struct pernet_operations sysctl_route_ops = { + .init = sysctl_route_net_init, + .exit = sysctl_route_net_exit, +}; #endif + +static __net_init int rt_secret_timer_init(struct net *net) +{ + atomic_set(&net->ipv4.rt_genid, + (int) ((num_physpages ^ (num_physpages>>8)) ^ + (jiffies ^ (jiffies >> 7)))); + + net->ipv4.rt_secret_timer.function = rt_secret_rebuild; + net->ipv4.rt_secret_timer.data = (unsigned long)net; + init_timer_deferrable(&net->ipv4.rt_secret_timer); + + net->ipv4.rt_secret_timer.expires = + jiffies + net_random() % ip_rt_secret_interval + + ip_rt_secret_interval; + add_timer(&net->ipv4.rt_secret_timer); + return 0; +} + +static __net_exit void rt_secret_timer_exit(struct net *net) +{ + del_timer_sync(&net->ipv4.rt_secret_timer); +} + +static __net_initdata struct pernet_operations rt_secret_timer_ops = { + .init = rt_secret_timer_init, + .exit = rt_secret_timer_exit, +}; + + #ifdef CONFIG_NET_CLS_ROUTE struct ip_rt_acct *ip_rt_acct __read_mostly; #endif /* CONFIG_NET_CLS_ROUTE */ @@ -3029,9 +3163,6 @@ int __init ip_rt_init(void) { int rc = 0; - atomic_set(&rt_genid, (int) ((num_physpages ^ (num_physpages>>8)) ^ - (jiffies ^ (jiffies >> 7)))); - #ifdef CONFIG_NET_CLS_ROUTE ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct)); if (!ip_rt_acct) @@ -3063,19 +3194,14 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); - rt_secret_timer.function = rt_secret_rebuild; - rt_secret_timer.data = 0; - init_timer_deferrable(&rt_secret_timer); - /* All the timers, started at system startup tend to synchronize. Perturb it a bit. */ schedule_delayed_work(&expires_work, net_random() % ip_rt_gc_interval + ip_rt_gc_interval); - rt_secret_timer.expires = jiffies + net_random() % ip_rt_secret_interval + - ip_rt_secret_interval; - add_timer(&rt_secret_timer); + if (register_pernet_subsys(&rt_secret_timer_ops)) + printk(KERN_ERR "Unable to setup rt_secret_timer\n"); if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); @@ -3085,6 +3211,9 @@ int __init ip_rt_init(void) #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL); +#ifdef CONFIG_SYSCTL + register_pernet_subsys(&sysctl_route_ops); +#endif return rc; } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 9016070..14ef202 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -793,7 +793,8 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_ratelimit, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec_ms_jiffies, + .strategy = &sysctl_ms_jiffies }, { .ctl_name = NET_IPV4_ICMP_RATEMASK, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index de30e70..d6ea970 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -947,17 +947,21 @@ static void tcp_update_reordering(struct sock *sk, const int metric, { struct tcp_sock *tp = tcp_sk(sk); if (metric > tp->reordering) { + int mib_idx; + tp->reordering = min(TCP_MAX_REORDERING, metric); /* This exciting event is worth to be remembered. 8) */ if (ts) - NET_INC_STATS_BH(LINUX_MIB_TCPTSREORDER); + mib_idx = LINUX_MIB_TCPTSREORDER; else if (tcp_is_reno(tp)) - NET_INC_STATS_BH(LINUX_MIB_TCPRENOREORDER); + mib_idx = LINUX_MIB_TCPRENOREORDER; else if (tcp_is_fack(tp)) - NET_INC_STATS_BH(LINUX_MIB_TCPFACKREORDER); + mib_idx = LINUX_MIB_TCPFACKREORDER; else - NET_INC_STATS_BH(LINUX_MIB_TCPSACKREORDER); + mib_idx = LINUX_MIB_TCPSACKREORDER; + + NET_INC_STATS_BH(mib_idx); #if FASTRETRANS_DEBUG > 1 printk(KERN_DEBUG "Disorder%d %d %u f%u s%u rr%d\n", tp->rx_opt.sack_ok, inet_csk(sk)->icsk_ca_state, @@ -1456,18 +1460,22 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, if (!tcp_is_sackblock_valid(tp, dup_sack, sp[used_sacks].start_seq, sp[used_sacks].end_seq)) { + int mib_idx; + if (dup_sack) { if (!tp->undo_marker) - NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDNOUNDO); + mib_idx = LINUX_MIB_TCPDSACKIGNOREDNOUNDO; else - NET_INC_STATS_BH(LINUX_MIB_TCPDSACKIGNOREDOLD); + mib_idx = LINUX_MIB_TCPDSACKIGNOREDOLD; } else { /* Don't count olds caused by ACK reordering */ if ((TCP_SKB_CB(ack_skb)->ack_seq != tp->snd_una) && !after(sp[used_sacks].end_seq, tp->snd_una)) continue; - NET_INC_STATS_BH(LINUX_MIB_TCPSACKDISCARD); + mib_idx = LINUX_MIB_TCPSACKDISCARD; } + + NET_INC_STATS_BH(mib_idx); if (i == 0) first_sack_index = -1; continue; @@ -2380,15 +2388,19 @@ static int tcp_try_undo_recovery(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); if (tcp_may_undo(tp)) { + int mib_idx; + /* Happy end! We did not retransmit anything * or our original transmission succeeded. */ DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans"); tcp_undo_cwr(sk, 1); if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) - NET_INC_STATS_BH(LINUX_MIB_TCPLOSSUNDO); + mib_idx = LINUX_MIB_TCPLOSSUNDO; else - NET_INC_STATS_BH(LINUX_MIB_TCPFULLUNDO); + mib_idx = LINUX_MIB_TCPFULLUNDO; + + NET_INC_STATS_BH(mib_idx); tp->undo_marker = 0; } if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) { @@ -2560,7 +2572,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); - int fast_rexmit = 0; + int fast_rexmit = 0, mib_idx; if (WARN_ON(!tp->packets_out && tp->sacked_out)) tp->sacked_out = 0; @@ -2683,9 +2695,11 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) /* Otherwise enter Recovery state */ if (tcp_is_reno(tp)) - NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERY); + mib_idx = LINUX_MIB_TCPRENORECOVERY; else - NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERY); + mib_idx = LINUX_MIB_TCPSACKRECOVERY; + + NET_INC_STATS_BH(mib_idx); tp->high_seq = tp->snd_nxt; tp->prior_ssthresh = 0; @@ -3700,10 +3714,14 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq, static void tcp_dsack_set(struct tcp_sock *tp, u32 seq, u32 end_seq) { if (tcp_is_sack(tp) && sysctl_tcp_dsack) { + int mib_idx; + if (before(seq, tp->rcv_nxt)) - NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOLDSENT); + mib_idx = LINUX_MIB_TCPDSACKOLDSENT; else - NET_INC_STATS_BH(LINUX_MIB_TCPDSACKOFOSENT); + mib_idx = LINUX_MIB_TCPDSACKOFOSENT; + + NET_INC_STATS_BH(mib_idx); tp->rx_opt.dsack = 1; tp->duplicate_sack[0].start_seq = seq; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 8f83ab4..edef2af 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1985,14 +1985,17 @@ void tcp_xmit_retransmit_queue(struct sock *sk) if (sacked & TCPCB_LOST) { if (!(sacked & (TCPCB_SACKED_ACKED|TCPCB_SACKED_RETRANS))) { + int mib_idx; + if (tcp_retransmit_skb(sk, skb)) { tp->retransmit_skb_hint = NULL; return; } if (icsk->icsk_ca_state != TCP_CA_Loss) - NET_INC_STATS_BH(LINUX_MIB_TCPFASTRETRANS); + mib_idx = LINUX_MIB_TCPFASTRETRANS; else - NET_INC_STATS_BH(LINUX_MIB_TCPSLOWSTARTRETRANS); + mib_idx = LINUX_MIB_TCPSLOWSTARTRETRANS; + NET_INC_STATS_BH(mib_idx); if (skb == tcp_write_queue_head(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 3e358cb..6a480d1 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -326,24 +326,27 @@ static void tcp_retransmit_timer(struct sock *sk) goto out; if (icsk->icsk_retransmits == 0) { + int mib_idx; + if (icsk->icsk_ca_state == TCP_CA_Disorder || icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) { if (icsk->icsk_ca_state == TCP_CA_Recovery) - NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERYFAIL); + mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL; else - NET_INC_STATS_BH(LINUX_MIB_TCPSACKFAILURES); + mib_idx = LINUX_MIB_TCPSACKFAILURES; } else { if (icsk->icsk_ca_state == TCP_CA_Recovery) - NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERYFAIL); + mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL; else - NET_INC_STATS_BH(LINUX_MIB_TCPRENOFAILURES); + mib_idx = LINUX_MIB_TCPRENOFAILURES; } } else if (icsk->icsk_ca_state == TCP_CA_Loss) { - NET_INC_STATS_BH(LINUX_MIB_TCPLOSSFAILURES); + mib_idx = LINUX_MIB_TCPLOSSFAILURES; } else { - NET_INC_STATS_BH(LINUX_MIB_TCPTIMEOUTS); + mib_idx = LINUX_MIB_TCPTIMEOUTS; } + NET_INC_STATS_BH(mib_idx); } if (tcp_use_frto(sk)) { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 3bbf6fb..7187121 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -526,7 +526,8 @@ out: up->len = 0; up->pending = 0; if (!err) - UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } @@ -725,7 +726,8 @@ out: * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); } return err; @@ -888,7 +890,8 @@ try_again: goto out_free; if (!peeked) - UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); sock_recv_timestamp(msg, sk, skb); @@ -917,7 +920,7 @@ out: csum_copy_err: lock_sock(sk); if (!skb_kill_datagram(sk, skb, flags)) - UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); release_sock(sk); if (noblock) @@ -988,7 +991,8 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) ret = (*up->encap_rcv)(sk, skb); if (ret <= 0) { - UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, + UDP_INC_STATS_BH(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); return -ret; } @@ -1041,7 +1045,8 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) { - UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite); + UDP_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); atomic_inc(&sk->sk_drops); } goto drop; @@ -1050,7 +1055,7 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) return 0; drop: - UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; } @@ -1158,7 +1163,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], struct rtable *rt = (struct rtable*)skb->dst; __be32 saddr = ip_hdr(skb)->saddr; __be32 daddr = ip_hdr(skb)->daddr; - struct net *net; + struct net *net = dev_net(skb->dev); /* * Validate the packet. @@ -1180,7 +1185,6 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (udp4_csum_init(skb, uh, proto)) goto csum_error; - net = dev_net(skb->dev); if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) return __udp4_lib_mcast_deliver(net, skb, uh, saddr, daddr, udptable); @@ -1214,7 +1218,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (udp_lib_checksum_complete(skb)) goto csum_error; - UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + UDP_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); /* @@ -1248,7 +1252,7 @@ csum_error: ntohs(uh->dest), ulen); drop: - UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); + UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); kfree_skb(skb); return 0; } @@ -1455,7 +1459,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) spin_lock_bh(&rcvq->lock); while ((skb = skb_peek(rcvq)) != NULL && udp_lib_checksum_complete(skb)) { - UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite); + UDP_INC_STATS_BH(sock_net(sk), + UDP_MIB_INERRORS, is_lite); __skb_unlink(skb, rcvq); kfree_skb(skb); } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 84127d8..2ec73e6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -119,6 +119,7 @@ static void ipv6_regen_rndid(unsigned long data); static int desync_factor = MAX_DESYNC_FACTOR * HZ; #endif +static int ipv6_generate_eui64(u8 *eui, struct net_device *dev); static int ipv6_count_addresses(struct inet6_dev *idev); /* @@ -183,6 +184,8 @@ struct ipv6_devconf ipv6_devconf __read_mostly = { #endif .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ + .disable_ipv6 = 0, + .accept_dad = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -215,6 +218,8 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { #endif .proxy_ndp = 0, .accept_source_route = 0, /* we do not accept RH0 by default. */ + .disable_ipv6 = 0, + .accept_dad = 1, }; /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ @@ -378,6 +383,9 @@ static struct inet6_dev * ipv6_add_dev(struct net_device *dev) */ in6_dev_hold(ndev); + if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) + ndev->cnf.accept_dad = -1; + #if defined(CONFIG_IPV6_SIT) || defined(CONFIG_IPV6_SIT_MODULE) if (dev->type == ARPHRD_SIT && (dev->priv_flags & IFF_ISATAP)) { printk(KERN_INFO @@ -578,6 +586,13 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, struct rt6_info *rt; int hash; int err = 0; + int addr_type = ipv6_addr_type(addr); + + if (addr_type == IPV6_ADDR_ANY || + addr_type & IPV6_ADDR_MULTICAST || + (!(idev->dev->flags & IFF_LOOPBACK) && + addr_type & IPV6_ADDR_LOOPBACK)) + return ERR_PTR(-EADDRNOTAVAIL); rcu_read_lock_bh(); if (idev->dead) { @@ -1412,6 +1427,20 @@ static void addrconf_dad_stop(struct inet6_ifaddr *ifp) void addrconf_dad_failure(struct inet6_ifaddr *ifp) { + struct inet6_dev *idev = ifp->idev; + if (idev->cnf.accept_dad > 1 && !idev->cnf.disable_ipv6) { + struct in6_addr addr; + + addr.s6_addr32[0] = htonl(0xfe800000); + addr.s6_addr32[1] = 0; + + if (!ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) && + ipv6_addr_equal(&ifp->addr, &addr)) { + /* DAD failed for link-local based on MAC address */ + idev->cnf.disable_ipv6 = 1; + } + } + if (net_ratelimit()) printk(KERN_INFO "%s: duplicate address detected!\n", ifp->idev->dev->name); addrconf_dad_stop(ifp); @@ -2744,6 +2773,7 @@ static void addrconf_dad_start(struct inet6_ifaddr *ifp, u32 flags) spin_lock_bh(&ifp->lock); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || + idev->cnf.accept_dad < 1 || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { ifp->flags &= ~(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC); @@ -2791,6 +2821,11 @@ static void addrconf_dad_timer(unsigned long data) read_unlock_bh(&idev->lock); goto out; } + if (idev->cnf.accept_dad > 1 && idev->cnf.disable_ipv6) { + read_unlock_bh(&idev->lock); + addrconf_dad_failure(ifp); + return; + } spin_lock_bh(&ifp->lock); if (ifp->probes == 0) { /* @@ -3650,6 +3685,8 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #ifdef CONFIG_IPV6_MROUTE array[DEVCONF_MC_FORWARDING] = cnf->mc_forwarding; #endif + array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; + array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; } static inline size_t inet6_if_nlmsg_size(void) @@ -4209,6 +4246,22 @@ static struct addrconf_sysctl_table }, #endif { + .ctl_name = CTL_UNNUMBERED, + .procname = "disable_ipv6", + .data = &ipv6_devconf.disable_ipv6, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "accept_dad", + .data = &ipv6_devconf.accept_dad, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec, + }, + { .ctl_name = 0, /* sentinel */ } }, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3ce8d2f..3d828bc 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -59,9 +59,7 @@ #include <asm/uaccess.h> #include <asm/system.h> -#ifdef CONFIG_IPV6_MROUTE #include <linux/mroute6.h> -#endif MODULE_AUTHOR("Cast of dozens"); MODULE_DESCRIPTION("IPv6 protocol stack for Linux"); @@ -952,9 +950,9 @@ static int __init inet6_init(void) err = icmpv6_init(); if (err) goto icmp_fail; -#ifdef CONFIG_IPV6_MROUTE - ip6_mr_init(); -#endif + err = ip6_mr_init(); + if (err) + goto ipmr_fail; err = ndisc_init(); if (err) goto ndisc_fail; @@ -1057,6 +1055,8 @@ netfilter_fail: igmp_fail: ndisc_cleanup(); ndisc_fail: + ip6_mr_cleanup(); +ipmr_fail: icmpv6_cleanup(); icmp_fail: unregister_pernet_subsys(&inet6_net_ops); @@ -1111,6 +1111,7 @@ static void __exit inet6_exit(void) ipv6_netfilter_fini(); igmp6_cleanup(); ndisc_cleanup(); + ip6_mr_cleanup(); icmpv6_cleanup(); rawv6_exit(); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 399d41f..abedf95 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -954,7 +954,8 @@ ctl_table ipv6_icmp_table_template[] = { .data = &init_net.ipv6.sysctl.icmpv6_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = &proc_dointvec_ms_jiffies, + .strategy = &sysctl_ms_jiffies }, { .ctl_name = 0 }, }; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 34e5a96..ea81c61 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -71,7 +71,8 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt IP6_INC_STATS_BH(idev, IPSTATS_MIB_INRECEIVES); - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) { + if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL || + !idev || unlikely(idev->cnf.disable_ipv6)) { IP6_INC_STATS_BH(idev, IPSTATS_MIB_INDISCARDS); rcu_read_unlock(); goto out; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index fd7cd1b..0981c1e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -173,6 +173,13 @@ static inline int ip6_skb_dst_mtu(struct sk_buff *skb) int ip6_output(struct sk_buff *skb) { + struct inet6_dev *idev = ip6_dst_idev(skb->dst); + if (unlikely(idev->cnf.disable_ipv6)) { + IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS); + kfree_skb(skb); + return 0; + } + if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb->dst)) return ip6_fragment(skb, ip6_output2); @@ -498,7 +505,8 @@ int ip6_forward(struct sk_buff *skb) int addrtype = ipv6_addr_type(&hdr->saddr); /* This check is security critical. */ - if (addrtype & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK)) + if (addrtype == IPV6_ADDR_ANY || + addrtype & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LOOPBACK)) goto error; if (addrtype & IPV6_ADDR_LINKLOCAL) { icmpv6_send(skb, ICMPV6_DEST_UNREACH, diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 90e7630..cfac26d 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -948,23 +948,51 @@ static struct notifier_block ip6_mr_notifier = { * Setup for IP multicast routing */ -void __init ip6_mr_init(void) +int __init ip6_mr_init(void) { + int err; + mrt_cachep = kmem_cache_create("ip6_mrt_cache", sizeof(struct mfc6_cache), 0, SLAB_HWCACHE_ALIGN, NULL); if (!mrt_cachep) - panic("cannot allocate ip6_mrt_cache"); + return -ENOMEM; setup_timer(&ipmr_expire_timer, ipmr_expire_process, 0); - register_netdevice_notifier(&ip6_mr_notifier); + err = register_netdevice_notifier(&ip6_mr_notifier); + if (err) + goto reg_notif_fail; +#ifdef CONFIG_PROC_FS + err = -ENOMEM; + if (!proc_net_fops_create(&init_net, "ip6_mr_vif", 0, &ip6mr_vif_fops)) + goto proc_vif_fail; + if (!proc_net_fops_create(&init_net, "ip6_mr_cache", + 0, &ip6mr_mfc_fops)) + goto proc_cache_fail; +#endif + return 0; +reg_notif_fail: + kmem_cache_destroy(mrt_cachep); #ifdef CONFIG_PROC_FS - proc_net_fops_create(&init_net, "ip6_mr_vif", 0, &ip6mr_vif_fops); - proc_net_fops_create(&init_net, "ip6_mr_cache", 0, &ip6mr_mfc_fops); +proc_vif_fail: + unregister_netdevice_notifier(&ip6_mr_notifier); +proc_cache_fail: + proc_net_remove(&init_net, "ip6_mr_vif"); #endif + return err; } +void ip6_mr_cleanup(void) +{ +#ifdef CONFIG_PROC_FS + proc_net_remove(&init_net, "ip6_mr_cache"); + proc_net_remove(&init_net, "ip6_mr_vif"); +#endif + unregister_netdevice_notifier(&ip6_mr_notifier); + del_timer(&ipmr_expire_timer); + kmem_cache_destroy(mrt_cachep); +} static int ip6mr_mfc_add(struct mf6cctl *mfc, int mrtsock) { diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 751e98f..5d6c166 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -228,7 +228,7 @@ static __inline__ int rt6_check_expired(const struct rt6_info *rt) static inline int rt6_need_strict(struct in6_addr *daddr) { return (ipv6_addr_type(daddr) & - (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); + (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK)); } /* @@ -237,15 +237,20 @@ static inline int rt6_need_strict(struct in6_addr *daddr) static inline struct rt6_info *rt6_device_match(struct net *net, struct rt6_info *rt, + struct in6_addr *saddr, int oif, int flags) { struct rt6_info *local = NULL; struct rt6_info *sprt; - if (oif) { - for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) { - struct net_device *dev = sprt->rt6i_dev; + if (!oif && ipv6_addr_any(saddr)) + goto out; + + for (sprt = rt; sprt; sprt = sprt->u.dst.rt6_next) { + struct net_device *dev = sprt->rt6i_dev; + + if (oif) { if (dev->ifindex == oif) return sprt; if (dev->flags & IFF_LOOPBACK) { @@ -259,14 +264,21 @@ static inline struct rt6_info *rt6_device_match(struct net *net, } local = sprt; } + } else { + if (ipv6_chk_addr(net, saddr, dev, + flags & RT6_LOOKUP_F_IFACE)) + return sprt; } + } + if (oif) { if (local) return local; if (flags & RT6_LOOKUP_F_IFACE) return net->ipv6.ip6_null_entry; } +out: return rt; } @@ -539,7 +551,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); restart: rt = fn->leaf; - rt = rt6_device_match(net, rt, fl->oif, flags); + rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags); BACKTRACK(net, &fl->fl6_src); out: dst_use(&rt->u.dst, jiffies); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f91e1df..d1477b3 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -166,7 +166,8 @@ try_again: goto out_free; if (!peeked) - UDP6_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite); + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); sock_recv_timestamp(msg, sk, skb); @@ -213,7 +214,7 @@ out: csum_copy_err: lock_sock(sk); if (!skb_kill_datagram(sk, skb, flags)) - UDP6_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); + UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); release_sock(sk); if (flags & MSG_DONTWAIT) @@ -298,7 +299,8 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { /* Note that an ENOMEM error is charged twice */ if (rc == -ENOMEM) { - UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite); + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, is_udplite); atomic_inc(&sk->sk_drops); } goto drop; @@ -306,7 +308,7 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) return 0; drop: - UDP6_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); + UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; } @@ -438,7 +440,7 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], struct net_device *dev = skb->dev; struct in6_addr *saddr, *daddr; u32 ulen = 0; - struct net *net; + struct net *net = dev_net(skb->dev); if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto short_packet; @@ -473,7 +475,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (udp6_csum_init(skb, uh, proto)) goto discard; - net = dev_net(skb->dev); /* * Multicast receive code */ @@ -496,7 +497,8 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (udp_lib_checksum_complete(skb)) goto discard; - UDP6_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + UDP6_INC_STATS_BH(net, UDP_MIB_NOPORTS, + proto == IPPROTO_UDPLITE); icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev); @@ -521,7 +523,7 @@ short_packet: ulen, skb->len); discard: - UDP6_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); + UDP6_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); kfree_skb(skb); return 0; } @@ -591,7 +593,8 @@ out: up->len = 0; up->pending = 0; if (!err) - UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } @@ -873,7 +876,8 @@ out: * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); } return err; diff --git a/net/rxrpc/ar-input.c b/net/rxrpc/ar-input.c index f8a699e..f98c802 100644 --- a/net/rxrpc/ar-input.c +++ b/net/rxrpc/ar-input.c @@ -21,6 +21,7 @@ #include <net/af_rxrpc.h> #include <net/ip.h> #include <net/udp.h> +#include <net/net_namespace.h> #include "ar-internal.h" unsigned long rxrpc_ack_timeout = 1; @@ -708,12 +709,12 @@ void rxrpc_data_ready(struct sock *sk, int count) if (skb_checksum_complete(skb)) { rxrpc_free_skb(skb); rxrpc_put_local(local); - UDP_INC_STATS_BH(UDP_MIB_INERRORS, 0); + UDP_INC_STATS_BH(&init_net, UDP_MIB_INERRORS, 0); _leave(" [CSUM failed]"); return; } - UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, 0); + UDP_INC_STATS_BH(&init_net, UDP_MIB_INDATAGRAMS, 0); /* the socket buffer we have is owned by UDP, with UDP's data all over * it, but we really want our own */ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 43460a1..df5572c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4223,6 +4223,8 @@ static int sctp_getsockopt_peer_addrs_num_old(struct sock *sk, int len, if (copy_from_user(&id, optval, sizeof(sctp_assoc_t))) return -EFAULT; + printk(KERN_WARNING "SCTP: Use of SCTP_GET_PEER_ADDRS_NUM_OLD " + "socket option deprecated\n"); /* For UDP-style sockets, id specifies the association to query. */ asoc = sctp_id2assoc(sk, id); if (!asoc) @@ -4262,6 +4264,9 @@ static int sctp_getsockopt_peer_addrs_old(struct sock *sk, int len, if (getaddrs.addr_num <= 0) return -EINVAL; + printk(KERN_WARNING "SCTP: Use of SCTP_GET_PEER_ADDRS_OLD " + "socket option deprecated\n"); + /* For UDP-style sockets, id specifies the association to query. */ asoc = sctp_id2assoc(sk, getaddrs.assoc_id); if (!asoc) @@ -4355,6 +4360,9 @@ static int sctp_getsockopt_local_addrs_num_old(struct sock *sk, int len, if (copy_from_user(&id, optval, sizeof(sctp_assoc_t))) return -EFAULT; + printk(KERN_WARNING "SCTP: Use of SCTP_GET_LOCAL_ADDRS_NUM_OLD " + "socket option deprecated\n"); + /* * For UDP-style sockets, id specifies the association to query. * If the id field is set to the value '0' then the locally bound @@ -4515,6 +4523,10 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, if (getaddrs.addr_num <= 0 || getaddrs.addr_num >= (INT_MAX / sizeof(union sctp_addr))) return -EINVAL; + + printk(KERN_WARNING "SCTP: Use of SCTP_GET_LOCAL_ADDRS_OLD " + "socket option deprecated\n"); + /* * For UDP-style sockets, id specifies the association to query. * If the id field is set to the value '0' then the locally bound |