From 305d552accae6afb859c493ebc7d98ca3371dae2 Mon Sep 17 00:00:00 2001 From: Brian Haley Date: Tue, 4 Nov 2008 17:51:14 -0800 Subject: [PATCH 01/11] bonding: send IPv6 neighbor advertisement on failover This patch adds better IPv6 failover support for bonding devices, especially when in active-backup mode and there are only IPv6 addresses configured, as reported by Alex Sidorenko. - Creates a new file, net/drivers/bonding/bond_ipv6.c, for the IPv6-specific routines. Both regular bonds and VLANs over bonds are supported. - Adds a new tunable, num_unsol_na, to limit the number of unsolicited IPv6 Neighbor Advertisements that are sent on a failover event. Default is 1. - Creates two new IPv6 neighbor discovery functions: ndisc_build_skb() ndisc_send_skb() These were required to support VLANs since we have to be able to add the VLAN id to the skb since ndisc_send_na() and friends shouldn't be asked to do this. These two routines are basically __ndisc_send() split into two pieces, in a slightly different order. - Updates Documentation/networking/bonding.txt and bumps the rev of bond support to 3.4.0. On failover, this new code will generate one packet: - An unsolicited IPv6 Neighbor Advertisement, which helps the switch learn that the address has moved to the new slave. Testing has shown that sending just the NA results in pretty good behavior when in active-back mode, I saw no lost ping packets for example. Signed-off-by: Brian Haley Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- Documentation/networking/bonding.txt | 10 ++ drivers/net/Kconfig | 1 + drivers/net/bonding/Makefile | 3 + drivers/net/bonding/bond_ipv6.c | 218 +++++++++++++++++++++++++++ drivers/net/bonding/bond_main.c | 33 +++- drivers/net/bonding/bond_sysfs.c | 42 ++++++ drivers/net/bonding/bonding.h | 34 ++++- include/net/ndisc.h | 14 ++ net/ipv6/ndisc.c | 92 +++++++---- 9 files changed, 416 insertions(+), 31 deletions(-) create mode 100644 drivers/net/bonding/bond_ipv6.c diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index d733a428eff6..3f4d0fae7081 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -551,6 +551,16 @@ num_grat_arp affects only the active-backup mode. This option was added for bonding version 3.3.0. +num_unsol_na + + Specifies the number of unsolicited IPv6 Neighbor Advertisements + to be issued after a failover event. One unsolicited NA is issued + immediately after the failover. + + The valid range is 0 - 255; the default value is 1. This option + affects only the active-backup mode. This option was added for + bonding version 3.4.0. + primary A string (eth0, eth2, etc) specifying which slave is the diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 0f3e6b2d2808..f1d0a1371695 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -61,6 +61,7 @@ config DUMMY config BONDING tristate "Bonding driver support" depends on INET + depends on IPV6 || IPV6=n ---help--- Say 'Y' or 'M' if you wish to be able to 'bond' multiple Ethernet Channels together. This is called 'Etherchannel' by Cisco, diff --git a/drivers/net/bonding/Makefile b/drivers/net/bonding/Makefile index 5cdae2bc055a..6f9c6faef24c 100644 --- a/drivers/net/bonding/Makefile +++ b/drivers/net/bonding/Makefile @@ -6,3 +6,6 @@ obj-$(CONFIG_BONDING) += bonding.o bonding-objs := bond_main.o bond_3ad.o bond_alb.o bond_sysfs.o +ipv6-$(subst m,y,$(CONFIG_IPV6)) += bond_ipv6.o +bonding-objs += $(ipv6-y) + diff --git a/drivers/net/bonding/bond_ipv6.c b/drivers/net/bonding/bond_ipv6.c new file mode 100644 index 000000000000..7c78b7bf671c --- /dev/null +++ b/drivers/net/bonding/bond_ipv6.c @@ -0,0 +1,218 @@ +/* + * Copyright(c) 2008 Hewlett-Packard Development Company, L.P. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, write to the Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + * The full GNU General Public License is included in this distribution in the + * file called LICENSE. + * + */ + +//#define BONDING_DEBUG 1 + +#include +#include +#include +#include +#include +#include "bonding.h" + +/* + * Assign bond->master_ipv6 to the next IPv6 address in the list, or + * zero it out if there are none. + */ +static void bond_glean_dev_ipv6(struct net_device *dev, struct in6_addr *addr) +{ + struct inet6_dev *idev; + struct inet6_ifaddr *ifa; + + if (!dev) + return; + + idev = in6_dev_get(dev); + if (!idev) + return; + + read_lock_bh(&idev->lock); + ifa = idev->addr_list; + if (ifa) + ipv6_addr_copy(addr, &ifa->addr); + else + ipv6_addr_set(addr, 0, 0, 0, 0); + + read_unlock_bh(&idev->lock); + + in6_dev_put(idev); +} + +static void bond_na_send(struct net_device *slave_dev, + struct in6_addr *daddr, + int router, + unsigned short vlan_id) +{ + struct in6_addr mcaddr; + struct icmp6hdr icmp6h = { + .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT, + }; + struct sk_buff *skb; + + icmp6h.icmp6_router = router; + icmp6h.icmp6_solicited = 0; + icmp6h.icmp6_override = 1; + + addrconf_addr_solict_mult(daddr, &mcaddr); + + dprintk("ipv6 na on slave %s: dest %pI6, src %pI6\n", + slave->name, &mcaddr, daddr); + + skb = ndisc_build_skb(slave_dev, &mcaddr, daddr, &icmp6h, daddr, + ND_OPT_TARGET_LL_ADDR); + + if (!skb) { + printk(KERN_ERR DRV_NAME ": NA packet allocation failed\n"); + return; + } + + if (vlan_id) { + skb = vlan_put_tag(skb, vlan_id); + if (!skb) { + printk(KERN_ERR DRV_NAME ": failed to insert VLAN tag\n"); + return; + } + } + + ndisc_send_skb(skb, slave_dev, NULL, &mcaddr, daddr, &icmp6h); +} + +/* + * Kick out an unsolicited Neighbor Advertisement for an IPv6 address on + * the bonding master. This will help the switch learn our address + * if in active-backup mode. + * + * Caller must hold curr_slave_lock for read or better + */ +void bond_send_unsolicited_na(struct bonding *bond) +{ + struct slave *slave = bond->curr_active_slave; + struct vlan_entry *vlan; + struct inet6_dev *idev; + int is_router; + + dprintk("bond_send_unsol_na: bond %s slave %s\n", bond->dev->name, + slave ? slave->dev->name : "NULL"); + + if (!slave || !bond->send_unsol_na || + test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) + return; + + bond->send_unsol_na--; + + idev = in6_dev_get(bond->dev); + if (!idev) + return; + + is_router = !!idev->cnf.forwarding; + + in6_dev_put(idev); + + if (!ipv6_addr_any(&bond->master_ipv6)) + bond_na_send(slave->dev, &bond->master_ipv6, is_router, 0); + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + if (!ipv6_addr_any(&vlan->vlan_ipv6)) { + bond_na_send(slave->dev, &vlan->vlan_ipv6, is_router, + vlan->vlan_id); + } + } +} + +/* + * bond_inet6addr_event: handle inet6addr notifier chain events. + * + * We keep track of device IPv6 addresses primarily to use as source + * addresses in NS probes. + * + * We track one IPv6 for the main device (if it has one). + */ +static int bond_inet6addr_event(struct notifier_block *this, + unsigned long event, + void *ptr) +{ + struct inet6_ifaddr *ifa = ptr; + struct net_device *vlan_dev, *event_dev = ifa->idev->dev; + struct bonding *bond; + struct vlan_entry *vlan; + + if (dev_net(event_dev) != &init_net) + return NOTIFY_DONE; + + list_for_each_entry(bond, &bond_dev_list, bond_list) { + if (bond->dev == event_dev) { + switch (event) { + case NETDEV_UP: + if (ipv6_addr_any(&bond->master_ipv6)) + ipv6_addr_copy(&bond->master_ipv6, + &ifa->addr); + return NOTIFY_OK; + case NETDEV_DOWN: + if (ipv6_addr_equal(&bond->master_ipv6, + &ifa->addr)) + bond_glean_dev_ipv6(bond->dev, + &bond->master_ipv6); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } + } + + list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { + vlan_dev = vlan_group_get_device(bond->vlgrp, + vlan->vlan_id); + if (vlan_dev == event_dev) { + switch (event) { + case NETDEV_UP: + if (ipv6_addr_any(&vlan->vlan_ipv6)) + ipv6_addr_copy(&vlan->vlan_ipv6, + &ifa->addr); + return NOTIFY_OK; + case NETDEV_DOWN: + if (ipv6_addr_equal(&vlan->vlan_ipv6, + &ifa->addr)) + bond_glean_dev_ipv6(vlan_dev, + &vlan->vlan_ipv6); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } + } + } + } + return NOTIFY_DONE; +} + +static struct notifier_block bond_inet6addr_notifier = { + .notifier_call = bond_inet6addr_event, +}; + +void bond_register_ipv6_notifier(void) +{ + register_inet6addr_notifier(&bond_inet6addr_notifier); +} + +void bond_unregister_ipv6_notifier(void) +{ + unregister_inet6addr_notifier(&bond_inet6addr_notifier); +} + diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 39575d764974..798d98ce2d97 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -89,6 +89,7 @@ static int max_bonds = BOND_DEFAULT_MAX_BONDS; static int num_grat_arp = 1; +static int num_unsol_na = 1; static int miimon = BOND_LINK_MON_INTERV; static int updelay = 0; static int downdelay = 0; @@ -107,6 +108,8 @@ module_param(max_bonds, int, 0); MODULE_PARM_DESC(max_bonds, "Max number of bonded devices"); module_param(num_grat_arp, int, 0644); MODULE_PARM_DESC(num_grat_arp, "Number of gratuitous ARP packets to send on failover event"); +module_param(num_unsol_na, int, 0644); +MODULE_PARM_DESC(num_unsol_na, "Number of unsolicited IPv6 Neighbor Advertisements packets to send on failover event"); module_param(miimon, int, 0); MODULE_PARM_DESC(miimon, "Link check interval in milliseconds"); module_param(updelay, int, 0); @@ -242,14 +245,13 @@ static int bond_add_vlan(struct bonding *bond, unsigned short vlan_id) dprintk("bond: %s, vlan id %d\n", (bond ? bond->dev->name: "None"), vlan_id); - vlan = kmalloc(sizeof(struct vlan_entry), GFP_KERNEL); + vlan = kzalloc(sizeof(struct vlan_entry), GFP_KERNEL); if (!vlan) { return -ENOMEM; } INIT_LIST_HEAD(&vlan->vlan_list); vlan->vlan_id = vlan_id; - vlan->vlan_ip = 0; write_lock_bh(&bond->lock); @@ -1208,6 +1210,9 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) bond->send_grat_arp = bond->params.num_grat_arp; bond_send_gratuitous_arp(bond); + bond->send_unsol_na = bond->params.num_unsol_na; + bond_send_unsolicited_na(bond); + write_unlock_bh(&bond->curr_slave_lock); read_unlock(&bond->lock); @@ -2463,6 +2468,12 @@ void bond_mii_monitor(struct work_struct *work) read_unlock(&bond->curr_slave_lock); } + if (bond->send_unsol_na) { + read_lock(&bond->curr_slave_lock); + bond_send_unsolicited_na(bond); + read_unlock(&bond->curr_slave_lock); + } + if (bond_miimon_inspect(bond)) { read_unlock(&bond->lock); rtnl_lock(); @@ -3158,6 +3169,12 @@ void bond_activebackup_arp_mon(struct work_struct *work) read_unlock(&bond->curr_slave_lock); } + if (bond->send_unsol_na) { + read_lock(&bond->curr_slave_lock); + bond_send_unsolicited_na(bond); + read_unlock(&bond->curr_slave_lock); + } + if (bond_ab_arp_inspect(bond, delta_in_ticks)) { read_unlock(&bond->lock); rtnl_lock(); @@ -3827,6 +3844,7 @@ static int bond_close(struct net_device *bond_dev) write_lock_bh(&bond->lock); bond->send_grat_arp = 0; + bond->send_unsol_na = 0; /* signal timers not to re-arm */ bond->kill_timers = 1; @@ -4542,6 +4560,7 @@ static int bond_init(struct net_device *bond_dev, struct bond_params *params) bond->primary_slave = NULL; bond->dev = bond_dev; bond->send_grat_arp = 0; + bond->send_unsol_na = 0; bond->setup_by_slave = 0; INIT_LIST_HEAD(&bond->vlan_list); @@ -4791,6 +4810,13 @@ static int bond_check_params(struct bond_params *params) num_grat_arp = 1; } + if (num_unsol_na < 0 || num_unsol_na > 255) { + printk(KERN_WARNING DRV_NAME + ": Warning: num_unsol_na (%d) not in range 0-255 so it " + "was reset to 1 \n", num_unsol_na); + num_unsol_na = 1; + } + /* reset values for 802.3ad */ if (bond_mode == BOND_MODE_8023AD) { if (!miimon) { @@ -4992,6 +5018,7 @@ static int bond_check_params(struct bond_params *params) params->xmit_policy = xmit_hashtype; params->miimon = miimon; params->num_grat_arp = num_grat_arp; + params->num_unsol_na = num_unsol_na; params->arp_interval = arp_interval; params->arp_validate = arp_validate_value; params->updelay = updelay; @@ -5144,6 +5171,7 @@ static int __init bonding_init(void) register_netdevice_notifier(&bond_netdev_notifier); register_inetaddr_notifier(&bond_inetaddr_notifier); + bond_register_ipv6_notifier(); goto out; err: @@ -5166,6 +5194,7 @@ static void __exit bonding_exit(void) { unregister_netdevice_notifier(&bond_netdev_notifier); unregister_inetaddr_notifier(&bond_inetaddr_notifier); + bond_unregister_ipv6_notifier(); bond_destroy_sysfs(); diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index e400d7dfdfc8..8788e3e33852 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -983,6 +983,47 @@ out: return ret; } static DEVICE_ATTR(num_grat_arp, S_IRUGO | S_IWUSR, bonding_show_n_grat_arp, bonding_store_n_grat_arp); + +/* + * Show and set the number of unsolicted NA's to send after a failover event. + */ +static ssize_t bonding_show_n_unsol_na(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%d\n", bond->params.num_unsol_na); +} + +static ssize_t bonding_store_n_unsol_na(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int new_value, ret = count; + struct bonding *bond = to_bond(d); + + if (sscanf(buf, "%d", &new_value) != 1) { + printk(KERN_ERR DRV_NAME + ": %s: no num_unsol_na value specified.\n", + bond->dev->name); + ret = -EINVAL; + goto out; + } + if (new_value < 0 || new_value > 255) { + printk(KERN_ERR DRV_NAME + ": %s: Invalid num_unsol_na value %d not in range 0-255; rejected.\n", + bond->dev->name, new_value); + ret = -EINVAL; + goto out; + } else { + bond->params.num_unsol_na = new_value; + } +out: + return ret; +} +static DEVICE_ATTR(num_unsol_na, S_IRUGO | S_IWUSR, bonding_show_n_unsol_na, bonding_store_n_unsol_na); + /* * Show and set the MII monitor interval. There are two tricky bits * here. First, if MII monitoring is activated, then we must disable @@ -1420,6 +1461,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_lacp_rate.attr, &dev_attr_xmit_hash_policy.attr, &dev_attr_num_grat_arp.attr, + &dev_attr_num_unsol_na.attr, &dev_attr_miimon.attr, &dev_attr_primary.attr, &dev_attr_use_carrier.attr, diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index ffb668dd6d3b..0491c7c2645b 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -19,16 +19,19 @@ #include #include #include +#include #include "bond_3ad.h" #include "bond_alb.h" -#define DRV_VERSION "3.3.0" -#define DRV_RELDATE "June 10, 2008" +#define DRV_VERSION "3.4.0" +#define DRV_RELDATE "October 7, 2008" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" #define BOND_MAX_ARP_TARGETS 16 +extern struct list_head bond_dev_list; + #ifdef BONDING_DEBUG #define dprintk(fmt, args...) \ printk(KERN_DEBUG \ @@ -126,6 +129,7 @@ struct bond_params { int xmit_policy; int miimon; int num_grat_arp; + int num_unsol_na; int arp_interval; int arp_validate; int use_carrier; @@ -148,6 +152,9 @@ struct vlan_entry { struct list_head vlan_list; __be32 vlan_ip; unsigned short vlan_id; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + struct in6_addr vlan_ipv6; +#endif }; struct slave { @@ -195,6 +202,7 @@ struct bonding { rwlock_t curr_slave_lock; s8 kill_timers; s8 send_grat_arp; + s8 send_unsol_na; s8 setup_by_slave; struct net_device_stats stats; #ifdef CONFIG_PROC_FS @@ -218,6 +226,9 @@ struct bonding { struct delayed_work arp_work; struct delayed_work alb_work; struct delayed_work ad_work; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + struct in6_addr master_ipv6; +#endif }; /** @@ -341,5 +352,24 @@ extern struct bond_parm_tbl xmit_hashtype_tbl[]; extern struct bond_parm_tbl arp_validate_tbl[]; extern struct bond_parm_tbl fail_over_mac_tbl[]; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +void bond_send_unsolicited_na(struct bonding *bond); +void bond_register_ipv6_notifier(void); +void bond_unregister_ipv6_notifier(void); +#else +static inline void bond_send_unsolicited_na(struct bonding *bond) +{ + return; +} +static inline void bond_register_ipv6_notifier(void) +{ + return; +} +static inline void bond_unregister_ipv6_notifier(void) +{ + return; +} +#endif + #endif /* _LINUX_BONDING_H */ diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 11dd0137c6a5..ce532f2222ce 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -108,6 +108,20 @@ extern void ndisc_send_redirect(struct sk_buff *skb, extern int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir); +extern struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo); + +extern void ndisc_send_skb(struct sk_buff *skb, + struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h); + /* diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 2a6752dae09d..fbf451c0d77a 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -437,38 +437,20 @@ static void pndisc_destructor(struct pneigh_entry *n) ipv6_dev_mc_dec(dev, &maddr); } -/* - * Send a Neighbour Advertisement - */ -static void __ndisc_send(struct net_device *dev, - struct neighbour *neigh, - const struct in6_addr *daddr, - const struct in6_addr *saddr, - struct icmp6hdr *icmp6h, const struct in6_addr *target, - int llinfo) +struct sk_buff *ndisc_build_skb(struct net_device *dev, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, + const struct in6_addr *target, + int llinfo) { - struct flowi fl; - struct dst_entry *dst; struct net *net = dev_net(dev); struct sock *sk = net->ipv6.ndisc_sk; struct sk_buff *skb; struct icmp6hdr *hdr; - struct inet6_dev *idev; int len; int err; - u8 *opt, type; - - type = icmp6h->icmp6_type; - - icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); - - dst = icmp6_dst_alloc(dev, neigh, daddr); - if (!dst) - return; - - err = xfrm_lookup(&dst, &fl, NULL, 0); - if (err < 0) - return; + u8 *opt; if (!dev->addr_len) llinfo = 0; @@ -485,8 +467,7 @@ static void __ndisc_send(struct net_device *dev, ND_PRINTK0(KERN_ERR "ICMPv6 ND: %s() failed to allocate an skb.\n", __func__); - dst_release(dst); - return; + return NULL; } skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -513,6 +494,42 @@ static void __ndisc_send(struct net_device *dev, csum_partial((__u8 *) hdr, len, 0)); + return skb; +} + +EXPORT_SYMBOL(ndisc_build_skb); + +void ndisc_send_skb(struct sk_buff *skb, + struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h) +{ + struct flowi fl; + struct dst_entry *dst; + struct net *net = dev_net(dev); + struct sock *sk = net->ipv6.ndisc_sk; + struct inet6_dev *idev; + int err; + u8 type; + + type = icmp6h->icmp6_type; + + icmpv6_flow_init(sk, &fl, type, saddr, daddr, dev->ifindex); + + dst = icmp6_dst_alloc(dev, neigh, daddr); + if (!dst) { + kfree_skb(skb); + return; + } + + err = xfrm_lookup(&dst, &fl, NULL, 0); + if (err < 0) { + kfree_skb(skb); + return; + } + skb->dst = dst; idev = in6_dev_get(dst->dev); @@ -529,6 +546,27 @@ static void __ndisc_send(struct net_device *dev, in6_dev_put(idev); } +EXPORT_SYMBOL(ndisc_send_skb); + +/* + * Send a Neighbour Discover packet + */ +static void __ndisc_send(struct net_device *dev, + struct neighbour *neigh, + const struct in6_addr *daddr, + const struct in6_addr *saddr, + struct icmp6hdr *icmp6h, const struct in6_addr *target, + int llinfo) +{ + struct sk_buff *skb; + + skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo); + if (!skb) + return; + + ndisc_send_skb(skb, dev, neigh, daddr, saddr, icmp6h); +} + static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, From 6146b1a4da98377e4abddc91ba5856bef8f23f1e Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Tue, 4 Nov 2008 17:51:15 -0800 Subject: [PATCH 02/11] bonding: Fix ALB mode to balance traffic on VLANs The current ALB function that processes incoming ARPs does not handle traffic for VLANs configured above bonding. This causes traffic on those VLANs to all be assigned the same slave. This patch corrects that misbehavior by locating the bonding interface nested below the VLAN interface. Bug reported by Sven Anders , who also tested an earlier version of this patch and confirmed that it resolved the problem. Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- drivers/net/bonding/bond_alb.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 87437c788476..e170fa2fa1a1 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -346,14 +346,18 @@ static void rlb_update_entry_from_arp(struct bonding *bond, struct arp_pkt *arp) static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct packet_type *ptype, struct net_device *orig_dev) { - struct bonding *bond = bond_dev->priv; + struct bonding *bond; struct arp_pkt *arp = (struct arp_pkt *)skb->data; int res = NET_RX_DROP; if (dev_net(bond_dev) != &init_net) goto out; - if (!(bond_dev->flags & IFF_MASTER)) + while (bond_dev->priv_flags & IFF_802_1Q_VLAN) + bond_dev = vlan_dev_real_dev(bond_dev); + + if (!(bond_dev->priv_flags & IFF_BONDING) || + !(bond_dev->flags & IFF_MASTER)) goto out; if (!arp) { @@ -368,6 +372,9 @@ static int rlb_arp_recv(struct sk_buff *skb, struct net_device *bond_dev, struct if (arp->op_code == htons(ARPOP_REPLY)) { /* update rx hash table for this ARP */ + printk("rar: update orig %s bond_dev %s\n", orig_dev->name, + bond_dev->name); + bond = bond_dev->priv; rlb_update_entry_from_arp(bond, arp); dprintk("Server received an ARP Reply from client\n"); } @@ -818,7 +825,7 @@ static int rlb_initialize(struct bonding *bond) /*initialize packet type*/ pk_type->type = __constant_htons(ETH_P_ARP); - pk_type->dev = bond->dev; + pk_type->dev = NULL; pk_type->func = rlb_arp_recv; /* register to receive ARPs */ From fd989c83325cb34795bc4d4aa6b13c06f90eac99 Mon Sep 17 00:00:00 2001 From: Jay Vosburgh Date: Tue, 4 Nov 2008 17:51:16 -0800 Subject: [PATCH 03/11] bonding: alternate agg selection policies for 802.3ad This patch implements alternative aggregator selection policies for 802.3ad. The existing policy, now termed "stable," selects the active aggregator by greatest bandwidth, and only reselects a new aggregator if the active aggregator is entirely disabled (no more ports or all ports down). This patch adds two new policies: bandwidth and count, selecting the active aggregator by total bandwidth (like the stable policy) or by the number of ports in the aggregator, respectively. These two policies also differ from the stable policy in that they will reselect the active aggregator when availability-related changes occur in the bond (e.g., link state change). This permits "gang failover" within 802.3ad, allowing redundant aggregators along parallel paths to always maintain the "best" aggregator as the active aggregator (rather than having to wait for the active to entirely fail). This patch also updates the driver version to 3.5.0. Signed-off-by: Jay Vosburgh Signed-off-by: Jeff Garzik --- Documentation/networking/bonding.txt | 42 ++++ drivers/net/bonding/bond_3ad.c | 322 +++++++++++++++++---------- drivers/net/bonding/bond_3ad.h | 10 +- drivers/net/bonding/bond_main.c | 30 +++ drivers/net/bonding/bond_sysfs.c | 49 ++++ drivers/net/bonding/bonding.h | 5 +- 6 files changed, 331 insertions(+), 127 deletions(-) diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 3f4d0fae7081..5ede7473b425 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -194,6 +194,48 @@ or, for backwards compatibility, the option value. E.g., The parameters are as follows: +ad_select + + Specifies the 802.3ad aggregation selection logic to use. The + possible values and their effects are: + + stable or 0 + + The active aggregator is chosen by largest aggregate + bandwidth. + + Reselection of the active aggregator occurs only when all + slaves of the active aggregator are down or the active + aggregator has no slaves. + + This is the default value. + + bandwidth or 1 + + The active aggregator is chosen by largest aggregate + bandwidth. Reselection occurs if: + + - A slave is added to or removed from the bond + + - Any slave's link state changes + + - Any slave's 802.3ad association state changes + + - The bond's adminstrative state changes to up + + count or 2 + + The active aggregator is chosen by the largest number of + ports (slaves). Reselection occurs as described under the + "bandwidth" setting, above. + + The bandwidth and count selection policies permit failover of + 802.3ad aggregations when partial failure of the active aggregator + occurs. This keeps the aggregator with the highest availability + (either in bandwidth or in number of ports) active at all times. + + This option was added in bonding version 3.4.0. + arp_interval Specifies the ARP link monitoring frequency in milliseconds. diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 6106660a4a44..ba1372f2f144 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -236,6 +237,17 @@ static inline struct aggregator *__get_next_agg(struct aggregator *aggregator) return &(SLAVE_AD_INFO(slave->next).aggregator); } +/* + * __agg_has_partner + * + * Return nonzero if aggregator has a partner (denoted by a non-zero ether + * address for the partner). Return 0 if not. + */ +static inline int __agg_has_partner(struct aggregator *agg) +{ + return !is_zero_ether_addr(agg->partner_system.mac_addr_value); +} + /** * __disable_port - disable the port's slave * @port: the port we're looking at @@ -274,14 +286,14 @@ static inline int __port_is_enabled(struct port *port) * __get_agg_selection_mode - get the aggregator selection mode * @port: the port we're looking at * - * Get the aggregator selection mode. Can be %BANDWIDTH or %COUNT. + * Get the aggregator selection mode. Can be %STABLE, %BANDWIDTH or %COUNT. */ static inline u32 __get_agg_selection_mode(struct port *port) { struct bonding *bond = __get_bond_by_port(port); if (bond == NULL) { - return AD_BANDWIDTH; + return BOND_AD_STABLE; } return BOND_AD_INFO(bond).agg_select_mode; @@ -1414,9 +1426,82 @@ static void ad_port_selection_logic(struct port *port) // else set ready=FALSE in all aggregator's ports __set_agg_ports_ready(port->aggregator, __agg_ports_are_ready(port->aggregator)); - if (!__check_agg_selection_timer(port) && (aggregator = __get_first_agg(port))) { - ad_agg_selection_logic(aggregator); + aggregator = __get_first_agg(port); + ad_agg_selection_logic(aggregator); +} + +/* + * Decide if "agg" is a better choice for the new active aggregator that + * the current best, according to the ad_select policy. + */ +static struct aggregator *ad_agg_selection_test(struct aggregator *best, + struct aggregator *curr) +{ + /* + * 0. If no best, select current. + * + * 1. If the current agg is not individual, and the best is + * individual, select current. + * + * 2. If current agg is individual and the best is not, keep best. + * + * 3. Therefore, current and best are both individual or both not + * individual, so: + * + * 3a. If current agg partner replied, and best agg partner did not, + * select current. + * + * 3b. If current agg partner did not reply and best agg partner + * did reply, keep best. + * + * 4. Therefore, current and best both have partner replies or + * both do not, so perform selection policy: + * + * BOND_AD_COUNT: Select by count of ports. If count is equal, + * select by bandwidth. + * + * BOND_AD_STABLE, BOND_AD_BANDWIDTH: Select by bandwidth. + */ + if (!best) + return curr; + + if (!curr->is_individual && best->is_individual) + return curr; + + if (curr->is_individual && !best->is_individual) + return best; + + if (__agg_has_partner(curr) && !__agg_has_partner(best)) + return curr; + + if (!__agg_has_partner(curr) && __agg_has_partner(best)) + return best; + + switch (__get_agg_selection_mode(curr->lag_ports)) { + case BOND_AD_COUNT: + if (curr->num_of_ports > best->num_of_ports) + return curr; + + if (curr->num_of_ports < best->num_of_ports) + return best; + + /*FALLTHROUGH*/ + case BOND_AD_STABLE: + case BOND_AD_BANDWIDTH: + if (__get_agg_bandwidth(curr) > __get_agg_bandwidth(best)) + return curr; + + break; + + default: + printk(KERN_WARNING DRV_NAME + ": %s: Impossible agg select mode %d\n", + curr->slave->dev->master->name, + __get_agg_selection_mode(curr->lag_ports)); + break; } + + return best; } /** @@ -1424,156 +1509,138 @@ static void ad_port_selection_logic(struct port *port) * @aggregator: the aggregator we're looking at * * It is assumed that only one aggregator may be selected for a team. - * The logic of this function is to select (at first time) the aggregator with - * the most ports attached to it, and to reselect the active aggregator only if - * the previous aggregator has no more ports related to it. + * + * The logic of this function is to select the aggregator according to + * the ad_select policy: + * + * BOND_AD_STABLE: select the aggregator with the most ports attached to + * it, and to reselect the active aggregator only if the previous + * aggregator has no more ports related to it. + * + * BOND_AD_BANDWIDTH: select the aggregator with the highest total + * bandwidth, and reselect whenever a link state change takes place or the + * set of slaves in the bond changes. + * + * BOND_AD_COUNT: select the aggregator with largest number of ports + * (slaves), and reselect whenever a link state change takes place or the + * set of slaves in the bond changes. * * FIXME: this function MUST be called with the first agg in the bond, or * __get_active_agg() won't work correctly. This function should be better * called with the bond itself, and retrieve the first agg from it. */ -static void ad_agg_selection_logic(struct aggregator *aggregator) +static void ad_agg_selection_logic(struct aggregator *agg) { - struct aggregator *best_aggregator = NULL, *active_aggregator = NULL; - struct aggregator *last_active_aggregator = NULL, *origin_aggregator; + struct aggregator *best, *active, *origin; struct port *port; - u16 num_of_aggs=0; - origin_aggregator = aggregator; + origin = agg; - //get current active aggregator - last_active_aggregator = __get_active_agg(aggregator); + active = __get_active_agg(agg); + best = active; - // search for the aggregator with the most ports attached to it. do { - // count how many candidate lag's we have - if (aggregator->lag_ports) { - num_of_aggs++; - } - if (aggregator->is_active && !aggregator->is_individual && // if current aggregator is the active aggregator - MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr))) { // and partner answers to 802.3ad PDUs - if (aggregator->num_of_ports) { // if any ports attached to the current aggregator - best_aggregator=NULL; // disregard the best aggregator that was chosen by now - break; // stop the selection of other aggregator if there are any ports attached to this active aggregator - } else { // no ports attached to this active aggregator - aggregator->is_active = 0; // mark this aggregator as not active anymore - } - } - if (aggregator->num_of_ports) { // if any ports attached - if (best_aggregator) { // if there is a candidte aggregator - //The reasons for choosing new best aggregator: - // 1. if current agg is NOT individual and the best agg chosen so far is individual OR - // current and best aggs are both individual or both not individual, AND - // 2a. current agg partner reply but best agg partner do not reply OR - // 2b. current agg partner reply OR current agg partner do not reply AND best agg partner also do not reply AND - // current has more ports/bandwidth, or same amount of ports but current has faster ports, THEN - // current agg become best agg so far + agg->is_active = 0; - //if current agg is NOT individual and the best agg chosen so far is individual change best_aggregator - if (!aggregator->is_individual && best_aggregator->is_individual) { - best_aggregator=aggregator; - } - // current and best aggs are both individual or both not individual - else if ((aggregator->is_individual && best_aggregator->is_individual) || - (!aggregator->is_individual && !best_aggregator->is_individual)) { - // current and best aggs are both individual or both not individual AND - // current agg partner reply but best agg partner do not reply - if ((MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr)) && - !MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) { - best_aggregator=aggregator; - } - // current agg partner reply OR current agg partner do not reply AND best agg partner also do not reply - else if (! (!MAC_ADDRESS_COMPARE(&(aggregator->partner_system), &(null_mac_addr)) && - MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) { - if ((__get_agg_selection_mode(aggregator->lag_ports) == AD_BANDWIDTH)&& - (__get_agg_bandwidth(aggregator) > __get_agg_bandwidth(best_aggregator))) { - best_aggregator=aggregator; - } else if (__get_agg_selection_mode(aggregator->lag_ports) == AD_COUNT) { - if (((aggregator->num_of_ports > best_aggregator->num_of_ports) && - (aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS))|| - ((aggregator->num_of_ports == best_aggregator->num_of_ports) && - ((u16)(aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS) > - (u16)(best_aggregator->actor_oper_aggregator_key & AD_SPEED_KEY_BITS)))) { - best_aggregator=aggregator; - } - } - } - } - } else { - best_aggregator=aggregator; - } - } - aggregator->is_active = 0; // mark all aggregators as not active anymore - } while ((aggregator = __get_next_agg(aggregator))); + if (agg->num_of_ports) + best = ad_agg_selection_test(best, agg); - // if we have new aggregator selected, don't replace the old aggregator if it has an answering partner, - // or if both old aggregator and new aggregator don't have answering partner - if (best_aggregator) { - if (last_active_aggregator && last_active_aggregator->lag_ports && last_active_aggregator->lag_ports->is_enabled && - (MAC_ADDRESS_COMPARE(&(last_active_aggregator->partner_system), &(null_mac_addr)) || // partner answers OR - (!MAC_ADDRESS_COMPARE(&(last_active_aggregator->partner_system), &(null_mac_addr)) && // both old and new - !MAC_ADDRESS_COMPARE(&(best_aggregator->partner_system), &(null_mac_addr)))) // partner do not answer - ) { - // if new aggregator has link, and old aggregator does not, replace old aggregator.(do nothing) - // -> don't replace otherwise. - if (!(!last_active_aggregator->actor_oper_aggregator_key && best_aggregator->actor_oper_aggregator_key)) { - best_aggregator=NULL; - last_active_aggregator->is_active = 1; // don't replace good old aggregator + } while ((agg = __get_next_agg(agg))); + if (best && + __get_agg_selection_mode(best->lag_ports) == BOND_AD_STABLE) { + /* + * For the STABLE policy, don't replace the old active + * aggregator if it's still active (it has an answering + * partner) or if both the best and active don't have an + * answering partner. + */ + if (active && active->lag_ports && + active->lag_ports->is_enabled && + (__agg_has_partner(active) || + (!__agg_has_partner(active) && !__agg_has_partner(best)))) { + if (!(!active->actor_oper_aggregator_key && + best->actor_oper_aggregator_key)) { + best = NULL; + active->is_active = 1; } } } - // if there is new best aggregator, activate it - if (best_aggregator) { - for (aggregator = __get_first_agg(best_aggregator->lag_ports); - aggregator; - aggregator = __get_next_agg(aggregator)) { + if (best && (best == active)) { + best = NULL; + active->is_active = 1; + } - dprintk("Agg=%d; Ports=%d; a key=%d; p key=%d; Indiv=%d; Active=%d\n", - aggregator->aggregator_identifier, aggregator->num_of_ports, - aggregator->actor_oper_aggregator_key, aggregator->partner_oper_aggregator_key, - aggregator->is_individual, aggregator->is_active); + // if there is new best aggregator, activate it + if (best) { + dprintk("best Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + best->aggregator_identifier, best->num_of_ports, + best->actor_oper_aggregator_key, + best->partner_oper_aggregator_key, + best->is_individual, best->is_active); + dprintk("best ports %p slave %p %s\n", + best->lag_ports, best->slave, + best->slave ? best->slave->dev->name : "NULL"); + + for (agg = __get_first_agg(best->lag_ports); agg; + agg = __get_next_agg(agg)) { + + dprintk("Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + agg->aggregator_identifier, agg->num_of_ports, + agg->actor_oper_aggregator_key, + agg->partner_oper_aggregator_key, + agg->is_individual, agg->is_active); } // check if any partner replys - if (best_aggregator->is_individual) { - printk(KERN_WARNING DRV_NAME ": %s: Warning: No 802.3ad response from " - "the link partner for any adapters in the bond\n", - best_aggregator->slave->dev->master->name); + if (best->is_individual) { + printk(KERN_WARNING DRV_NAME ": %s: Warning: No 802.3ad" + " response from the link partner for any" + " adapters in the bond\n", + best->slave->dev->master->name); } - // check if there are more than one aggregator - if (num_of_aggs > 1) { - dprintk("Warning: More than one Link Aggregation Group was " - "found in the bond. Only one group will function in the bond\n"); - } - - best_aggregator->is_active = 1; - dprintk("LAG %d choosed as the active LAG\n", best_aggregator->aggregator_identifier); - dprintk("Agg=%d; Ports=%d; a key=%d; p key=%d; Indiv=%d; Active=%d\n", - best_aggregator->aggregator_identifier, best_aggregator->num_of_ports, - best_aggregator->actor_oper_aggregator_key, best_aggregator->partner_oper_aggregator_key, - best_aggregator->is_individual, best_aggregator->is_active); + best->is_active = 1; + dprintk("LAG %d chosen as the active LAG\n", + best->aggregator_identifier); + dprintk("Agg=%d; P=%d; a k=%d; p k=%d; Ind=%d; Act=%d\n", + best->aggregator_identifier, best->num_of_ports, + best->actor_oper_aggregator_key, + best->partner_oper_aggregator_key, + best->is_individual, best->is_active); // disable the ports that were related to the former active_aggregator - if (last_active_aggregator) { - for (port=last_active_aggregator->lag_ports; port; port=port->next_port_in_aggregator) { + if (active) { + for (port = active->lag_ports; port; + port = port->next_port_in_aggregator) { __disable_port(port); } } } - // if the selected aggregator is of join individuals(partner_system is NULL), enable their ports - active_aggregator = __get_active_agg(origin_aggregator); + /* + * if the selected aggregator is of join individuals + * (partner_system is NULL), enable their ports + */ + active = __get_active_agg(origin); - if (active_aggregator) { - if (!MAC_ADDRESS_COMPARE(&(active_aggregator->partner_system), &(null_mac_addr))) { - for (port=active_aggregator->lag_ports; port; port=port->next_port_in_aggregator) { + if (active) { + if (!__agg_has_partner(active)) { + for (port = active->lag_ports; port; + port = port->next_port_in_aggregator) { __enable_port(port); } } } + + if (origin->slave) { + struct bonding *bond; + + bond = bond_get_bond_by_slave(origin->slave); + if (bond) + bond_3ad_set_carrier(bond); + } } /** @@ -1830,6 +1897,19 @@ static void ad_initialize_lacpdu(struct lacpdu *lacpdu) // Check aggregators status in team every T seconds #define AD_AGGREGATOR_SELECTION_TIMER 8 +/* + * bond_3ad_initiate_agg_selection(struct bonding *bond) + * + * Set the aggregation selection timer, to initiate an agg selection in + * the very near future. Called during first initialization, and during + * any down to up transitions of the bond. + */ +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout) +{ + BOND_AD_INFO(bond).agg_select_timer = timeout; + BOND_AD_INFO(bond).agg_select_mode = bond->params.ad_select; +} + static u16 aggregator_identifier; /** @@ -1854,9 +1934,9 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fas // initialize how many times this module is called in one second(should be about every 100ms) ad_ticks_per_sec = tick_resolution; - // initialize the aggregator selection timer(to activate an aggregation selection after initialize) - BOND_AD_INFO(bond).agg_select_timer = (AD_AGGREGATOR_SELECTION_TIMER * ad_ticks_per_sec); - BOND_AD_INFO(bond).agg_select_mode = AD_BANDWIDTH; + bond_3ad_initiate_agg_selection(bond, + AD_AGGREGATOR_SELECTION_TIMER * + ad_ticks_per_sec); } } diff --git a/drivers/net/bonding/bond_3ad.h b/drivers/net/bonding/bond_3ad.h index b5ee45f6d55a..a803fe05f63e 100644 --- a/drivers/net/bonding/bond_3ad.h +++ b/drivers/net/bonding/bond_3ad.h @@ -42,10 +42,11 @@ typedef struct mac_addr { u8 mac_addr_value[ETH_ALEN]; } mac_addr_t; -typedef enum { - AD_BANDWIDTH = 0, - AD_COUNT -} agg_selection_t; +enum { + BOND_AD_STABLE = 0, + BOND_AD_BANDWIDTH = 1, + BOND_AD_COUNT = 2, +}; // rx machine states(43.4.11 in the 802.3ad standard) typedef enum { @@ -277,6 +278,7 @@ void bond_3ad_initialize(struct bonding *bond, u16 tick_resolution, int lacp_fas int bond_3ad_bind_slave(struct slave *slave); void bond_3ad_unbind_slave(struct slave *slave); void bond_3ad_state_machine_handler(struct work_struct *); +void bond_3ad_initiate_agg_selection(struct bonding *bond, int timeout); void bond_3ad_adapter_speed_changed(struct slave *slave); void bond_3ad_adapter_duplex_changed(struct slave *slave); void bond_3ad_handle_link_change(struct slave *slave, char link); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 798d98ce2d97..02de3e031237 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -97,6 +97,7 @@ static int use_carrier = 1; static char *mode = NULL; static char *primary = NULL; static char *lacp_rate = NULL; +static char *ad_select = NULL; static char *xmit_hash_policy = NULL; static int arp_interval = BOND_LINK_ARP_INTERV; static char *arp_ip_target[BOND_MAX_ARP_TARGETS] = { NULL, }; @@ -130,6 +131,8 @@ MODULE_PARM_DESC(primary, "Primary network device to use"); module_param(lacp_rate, charp, 0); MODULE_PARM_DESC(lacp_rate, "LACPDU tx rate to request from 802.3ad partner " "(slow/fast)"); +module_param(ad_select, charp, 0); +MODULE_PARM_DESC(ad_select, "803.ad aggregation selection logic: stable (0, default), bandwidth (1), count (2)"); module_param(xmit_hash_policy, charp, 0); MODULE_PARM_DESC(xmit_hash_policy, "XOR hashing method: 0 for layer 2 (default)" ", 1 for layer 3+4"); @@ -200,6 +203,13 @@ struct bond_parm_tbl fail_over_mac_tbl[] = { { NULL, -1}, }; +struct bond_parm_tbl ad_select_tbl[] = { +{ "stable", BOND_AD_STABLE}, +{ "bandwidth", BOND_AD_BANDWIDTH}, +{ "count", BOND_AD_COUNT}, +{ NULL, -1}, +}; + /*-------------------------- Forward declarations ---------------------------*/ static void bond_send_gratuitous_arp(struct bonding *bond); @@ -3318,6 +3328,8 @@ static void bond_info_show_master(struct seq_file *seq) seq_puts(seq, "\n802.3ad info\n"); seq_printf(seq, "LACP rate: %s\n", (bond->params.lacp_fast) ? "fast" : "slow"); + seq_printf(seq, "Aggregator selection policy (ad_select): %s\n", + ad_select_tbl[bond->params.ad_select].modename); if (bond_3ad_get_active_agg_info(bond, &ad_info)) { seq_printf(seq, "bond %s has no active aggregator\n", @@ -3824,6 +3836,7 @@ static int bond_open(struct net_device *bond_dev) queue_delayed_work(bond->wq, &bond->ad_work, 0); /* register to receive LACPDUs */ bond_register_lacpdu(bond); + bond_3ad_initiate_agg_selection(bond, 1); } return 0; @@ -4763,6 +4776,23 @@ static int bond_check_params(struct bond_params *params) } } + if (ad_select) { + params->ad_select = bond_parse_parm(ad_select, ad_select_tbl); + if (params->ad_select == -1) { + printk(KERN_ERR DRV_NAME + ": Error: Invalid ad_select \"%s\"\n", + ad_select == NULL ? "NULL" : ad_select); + return -EINVAL; + } + + if (bond_mode != BOND_MODE_8023AD) { + printk(KERN_WARNING DRV_NAME + ": ad_select param only affects 802.3ad mode\n"); + } + } else { + params->ad_select = BOND_AD_STABLE; + } + if (max_bonds < 0 || max_bonds > INT_MAX) { printk(KERN_WARNING DRV_NAME ": Warning: max_bonds (%d) not in range %d-%d, so it " diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 8788e3e33852..aaf2927b5c38 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -48,6 +48,7 @@ extern struct list_head bond_dev_list; extern struct bond_params bonding_defaults; extern struct bond_parm_tbl bond_mode_tbl[]; extern struct bond_parm_tbl bond_lacp_tbl[]; +extern struct bond_parm_tbl ad_select_tbl[]; extern struct bond_parm_tbl xmit_hashtype_tbl[]; extern struct bond_parm_tbl arp_validate_tbl[]; extern struct bond_parm_tbl fail_over_mac_tbl[]; @@ -944,6 +945,53 @@ out: } static DEVICE_ATTR(lacp_rate, S_IRUGO | S_IWUSR, bonding_show_lacp, bonding_store_lacp); +static ssize_t bonding_show_ad_select(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct bonding *bond = to_bond(d); + + return sprintf(buf, "%s %d\n", + ad_select_tbl[bond->params.ad_select].modename, + bond->params.ad_select); +} + + +static ssize_t bonding_store_ad_select(struct device *d, + struct device_attribute *attr, + const char *buf, size_t count) +{ + int new_value, ret = count; + struct bonding *bond = to_bond(d); + + if (bond->dev->flags & IFF_UP) { + printk(KERN_ERR DRV_NAME + ": %s: Unable to update ad_select because interface " + "is up.\n", bond->dev->name); + ret = -EPERM; + goto out; + } + + new_value = bond_parse_parm(buf, ad_select_tbl); + + if (new_value != -1) { + bond->params.ad_select = new_value; + printk(KERN_INFO DRV_NAME + ": %s: Setting ad_select to %s (%d).\n", + bond->dev->name, ad_select_tbl[new_value].modename, + new_value); + } else { + printk(KERN_ERR DRV_NAME + ": %s: Ignoring invalid ad_select value %.*s.\n", + bond->dev->name, (int)strlen(buf) - 1, buf); + ret = -EINVAL; + } +out: + return ret; +} + +static DEVICE_ATTR(ad_select, S_IRUGO | S_IWUSR, bonding_show_ad_select, bonding_store_ad_select); + /* * Show and set the number of grat ARP to send after a failover event. */ @@ -1459,6 +1507,7 @@ static struct attribute *per_bond_attrs[] = { &dev_attr_downdelay.attr, &dev_attr_updelay.attr, &dev_attr_lacp_rate.attr, + &dev_attr_ad_select.attr, &dev_attr_xmit_hash_policy.attr, &dev_attr_num_grat_arp.attr, &dev_attr_num_unsol_na.attr, diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 0491c7c2645b..b5eb8e65b309 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -23,8 +23,8 @@ #include "bond_3ad.h" #include "bond_alb.h" -#define DRV_VERSION "3.4.0" -#define DRV_RELDATE "October 7, 2008" +#define DRV_VERSION "3.5.0" +#define DRV_RELDATE "November 4, 2008" #define DRV_NAME "bonding" #define DRV_DESCRIPTION "Ethernet Channel Bonding Driver" @@ -137,6 +137,7 @@ struct bond_params { int updelay; int downdelay; int lacp_fast; + int ad_select; char primary[IFNAMSIZ]; __be32 arp_targets[BOND_MAX_ARP_TARGETS]; }; From 2883f552f2c6c6ccb2021643652c6d930f205f6f Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 4 Nov 2008 20:32:45 +0000 Subject: [PATCH 04/11] sfc: Correct address of gPXE boot configuration in EEPROM Due to a hardware bug, the originally assigned range cannot reliably be used for boot configuration and must not be modifiable through ethtool. Signed-off-by: Ben Hutchings Signed-off-by: Jeff Garzik --- drivers/net/sfc/ethtool.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index fa98af58223e..cd0d0873d978 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -174,8 +174,8 @@ static struct efx_ethtool_stat efx_ethtool_stats[] = { /* EEPROM range with gPXE configuration */ #define EFX_ETHTOOL_EEPROM_MAGIC 0xEFAB -#define EFX_ETHTOOL_EEPROM_MIN 0x100U -#define EFX_ETHTOOL_EEPROM_MAX 0x400U +#define EFX_ETHTOOL_EEPROM_MIN 0x800U +#define EFX_ETHTOOL_EEPROM_MAX 0x1800U /************************************************************************** * From 0a95f56323ce93dac354c1b2d54bf959a985cf7d Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 4 Nov 2008 20:33:11 +0000 Subject: [PATCH 05/11] sfc: Clean up non-volatile memory partitioning Move flash and EEPROM partition boundary constants into spi.h and rename them to be consistent. Add a comment on the partitioning. Signed-off-by: Ben Hutchings Signed-off-by: Jeff Garzik --- drivers/net/sfc/ethtool.c | 11 ++++------- drivers/net/sfc/falcon.c | 6 +++--- drivers/net/sfc/falcon_hwdefs.h | 1 - drivers/net/sfc/spi.h | 17 +++++++++++++++++ 4 files changed, 24 insertions(+), 11 deletions(-) diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index cd0d0873d978..df0579e386f7 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -172,10 +172,7 @@ static struct efx_ethtool_stat efx_ethtool_stats[] = { /* Number of ethtool statistics */ #define EFX_ETHTOOL_NUM_STATS ARRAY_SIZE(efx_ethtool_stats) -/* EEPROM range with gPXE configuration */ #define EFX_ETHTOOL_EEPROM_MAGIC 0xEFAB -#define EFX_ETHTOOL_EEPROM_MIN 0x800U -#define EFX_ETHTOOL_EEPROM_MAX 0x1800U /************************************************************************** * @@ -545,8 +542,8 @@ static int efx_ethtool_get_eeprom_len(struct net_device *net_dev) if (!spi) return 0; - return min(spi->size, EFX_ETHTOOL_EEPROM_MAX) - - min(spi->size, EFX_ETHTOOL_EEPROM_MIN); + return min(spi->size, EFX_EEPROM_BOOTCONFIG_END) - + min(spi->size, EFX_EEPROM_BOOTCONFIG_START); } static int efx_ethtool_get_eeprom(struct net_device *net_dev, @@ -557,7 +554,7 @@ static int efx_ethtool_get_eeprom(struct net_device *net_dev, size_t len; int rc; - rc = falcon_spi_read(spi, eeprom->offset + EFX_ETHTOOL_EEPROM_MIN, + rc = falcon_spi_read(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, eeprom->len, &len, buf); eeprom->magic = EFX_ETHTOOL_EEPROM_MAGIC; eeprom->len = len; @@ -575,7 +572,7 @@ static int efx_ethtool_set_eeprom(struct net_device *net_dev, if (eeprom->magic != EFX_ETHTOOL_EEPROM_MAGIC) return -EINVAL; - rc = falcon_spi_write(spi, eeprom->offset + EFX_ETHTOOL_EEPROM_MIN, + rc = falcon_spi_write(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, eeprom->len, &len, buf); eeprom->len = len; return rc; diff --git a/drivers/net/sfc/falcon.c b/drivers/net/sfc/falcon.c index 31ed1f49de00..3f74ceff6a2e 100644 --- a/drivers/net/sfc/falcon.c +++ b/drivers/net/sfc/falcon.c @@ -2253,13 +2253,13 @@ int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out) __le16 *word, *limit; u32 csum; - region = kmalloc(NVCONFIG_END, GFP_KERNEL); + region = kmalloc(FALCON_NVCONFIG_END, GFP_KERNEL); if (!region) return -ENOMEM; nvconfig = region + NVCONFIG_OFFSET; spi = efx->spi_flash ? efx->spi_flash : efx->spi_eeprom; - rc = falcon_spi_read(spi, 0, NVCONFIG_END, NULL, region); + rc = falcon_spi_read(spi, 0, FALCON_NVCONFIG_END, NULL, region); if (rc) { EFX_ERR(efx, "Failed to read %s\n", efx->spi_flash ? "flash" : "EEPROM"); @@ -2283,7 +2283,7 @@ int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out) limit = (__le16 *) (nvconfig + 1); } else { word = region; - limit = region + NVCONFIG_END; + limit = region + FALCON_NVCONFIG_END; } for (csum = 0; word < limit; ++word) csum += le16_to_cpu(*word); diff --git a/drivers/net/sfc/falcon_hwdefs.h b/drivers/net/sfc/falcon_hwdefs.h index 5d584b0dbb51..040e70ed4ec7 100644 --- a/drivers/net/sfc/falcon_hwdefs.h +++ b/drivers/net/sfc/falcon_hwdefs.h @@ -1150,7 +1150,6 @@ struct falcon_nvconfig_board_v3 { (((type) >> EFX_LOW_BIT(field)) & EFX_MASK32(EFX_WIDTH(field))) #define NVCONFIG_OFFSET 0x300 -#define NVCONFIG_END 0x400 #define NVCONFIG_BOARD_MAGIC_NUM 0xFA1C struct falcon_nvconfig { diff --git a/drivers/net/sfc/spi.h b/drivers/net/sfc/spi.h index feef61942377..b73f86cf5fa2 100644 --- a/drivers/net/sfc/spi.h +++ b/drivers/net/sfc/spi.h @@ -63,4 +63,21 @@ int falcon_spi_read(const struct efx_spi_device *spi, loff_t start, int falcon_spi_write(const struct efx_spi_device *spi, loff_t start, size_t len, size_t *retlen, const u8 *buffer); +/* + * SFC4000 flash is partitioned into: + * 0-0x400 chip and board config (see falcon_hwdefs.h) + * 0x400-0x8000 unused (or may contain VPD if EEPROM not present) + * 0x8000-end boot code (mapped to PCI expansion ROM) + * SFC4000 small EEPROM (size < 0x400) is used for VPD only. + * SFC4000 large EEPROM (size >= 0x400) is partitioned into: + * 0-0x400 chip and board config + * configurable VPD + * 0x800-0x1800 boot config + * Aside from the chip and board config, all of these are optional and may + * be absent or truncated depending on the devices used. + */ +#define FALCON_NVCONFIG_END 0x400U +#define EFX_EEPROM_BOOTCONFIG_START 0x800U +#define EFX_EEPROM_BOOTCONFIG_END 0x1800U + #endif /* EFX_SPI_H */ From f41507245ef8b079685aba8da5b5b2b5e87e70bc Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 4 Nov 2008 20:34:28 +0000 Subject: [PATCH 06/11] sfc: Expose flash region storing boot code as MTD The boot code that appears as a PCI expansion ROM on the SFC4000 is stored in flash. Expose this as a standard MTD device to allow for in-place upgrades. Signed-off-by: Ben Hutchings Signed-off-by: Jeff Garzik --- drivers/net/sfc/Kconfig | 8 ++ drivers/net/sfc/Makefile | 1 + drivers/net/sfc/efx.c | 7 + drivers/net/sfc/efx.h | 10 ++ drivers/net/sfc/ethtool.c | 4 + drivers/net/sfc/falcon.c | 17 ++- drivers/net/sfc/mtd.c | 268 +++++++++++++++++++++++++++++++++++ drivers/net/sfc/net_driver.h | 2 + drivers/net/sfc/spi.h | 17 ++- 9 files changed, 327 insertions(+), 7 deletions(-) create mode 100644 drivers/net/sfc/mtd.c diff --git a/drivers/net/sfc/Kconfig b/drivers/net/sfc/Kconfig index 3be13b592b4d..3e25fb38f739 100644 --- a/drivers/net/sfc/Kconfig +++ b/drivers/net/sfc/Kconfig @@ -12,3 +12,11 @@ config SFC To compile this driver as a module, choose M here. The module will be called sfc. +config SFC_MTD + bool "Solarflare Solarstorm SFC4000 flash MTD support" + depends on SFC && MTD + default y + help + This exposes the on-board flash memory as an MTD device (e.g. + /dev/mtd1). This makes it possible to upload new boot code + to the NIC. diff --git a/drivers/net/sfc/Makefile b/drivers/net/sfc/Makefile index c8f5704c8fb1..e507daa4f0e8 100644 --- a/drivers/net/sfc/Makefile +++ b/drivers/net/sfc/Makefile @@ -1,5 +1,6 @@ sfc-y += efx.o falcon.o tx.o rx.o falcon_xmac.o \ selftest.o ethtool.o xfp_phy.o \ mdio_10g.o tenxpress.o boards.o sfe4001.o +sfc-$(CONFIG_SFC_MTD) += mtd.o obj-$(CONFIG_SFC) += sfc.o diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index 5b05789f0b79..f9139377989f 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -1459,6 +1459,7 @@ static int efx_netdev_event(struct notifier_block *this, struct efx_nic *efx = netdev_priv(net_dev); strcpy(efx->name, net_dev->name); + efx_mtd_rename(efx); } return NOTIFY_DONE; @@ -1550,6 +1551,7 @@ void efx_reset_down(struct efx_nic *efx, struct ethtool_cmd *ecmd) efx_stop_all(efx); mutex_lock(&efx->mac_lock); + mutex_lock(&efx->spi_lock); rc = falcon_xmac_get_settings(efx, ecmd); if (rc) @@ -1582,6 +1584,7 @@ int efx_reset_up(struct efx_nic *efx, struct ethtool_cmd *ecmd, bool ok) EFX_ERR(efx, "could not restore PHY settings\n"); } + mutex_unlock(&efx->spi_lock); mutex_unlock(&efx->mac_lock); if (ok) { @@ -1777,6 +1780,7 @@ static int efx_init_struct(struct efx_nic *efx, struct efx_nic_type *type, memset(efx, 0, sizeof(*efx)); spin_lock_init(&efx->biu_lock); spin_lock_init(&efx->phy_lock); + mutex_init(&efx->spi_lock); INIT_WORK(&efx->reset_work, efx_reset_work); INIT_DELAYED_WORK(&efx->monitor_work, efx_monitor); efx->pci_dev = pci_dev; @@ -1911,6 +1915,8 @@ static void efx_pci_remove(struct pci_dev *pci_dev) if (!efx) return; + efx_mtd_remove(efx); + /* Mark the NIC as fini, then stop the interface */ rtnl_lock(); efx->state = STATE_FINI; @@ -2077,6 +2083,7 @@ static int __devinit efx_pci_probe(struct pci_dev *pci_dev, EFX_LOG(efx, "initialisation successful\n"); + efx_mtd_probe(efx); /* allowed to fail */ return 0; fail5: diff --git a/drivers/net/sfc/efx.h b/drivers/net/sfc/efx.h index d02937b70eee..dd0d45b9e71f 100644 --- a/drivers/net/sfc/efx.h +++ b/drivers/net/sfc/efx.h @@ -58,6 +58,16 @@ extern int efx_port_dummy_op_int(struct efx_nic *efx); extern void efx_port_dummy_op_void(struct efx_nic *efx); extern void efx_port_dummy_op_blink(struct efx_nic *efx, bool blink); +/* MTD */ +#ifdef CONFIG_SFC_MTD +extern int efx_mtd_probe(struct efx_nic *efx); +extern void efx_mtd_rename(struct efx_nic *efx); +extern void efx_mtd_remove(struct efx_nic *efx); +#else +static inline int efx_mtd_probe(struct efx_nic *efx) { return 0; } +static inline void efx_mtd_rename(struct efx_nic *efx) {} +static inline void efx_mtd_remove(struct efx_nic *efx) {} +#endif extern unsigned int efx_monitor_interval; diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index df0579e386f7..abd8fcd6e62d 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -554,8 +554,10 @@ static int efx_ethtool_get_eeprom(struct net_device *net_dev, size_t len; int rc; + mutex_lock(&efx->spi_lock); rc = falcon_spi_read(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, eeprom->len, &len, buf); + mutex_unlock(&efx->spi_lock); eeprom->magic = EFX_ETHTOOL_EEPROM_MAGIC; eeprom->len = len; return rc; @@ -572,8 +574,10 @@ static int efx_ethtool_set_eeprom(struct net_device *net_dev, if (eeprom->magic != EFX_ETHTOOL_EEPROM_MAGIC) return -EINVAL; + mutex_lock(&efx->spi_lock); rc = falcon_spi_write(spi, eeprom->offset + EFX_EEPROM_BOOTCONFIG_START, eeprom->len, &len, buf); + mutex_unlock(&efx->spi_lock); eeprom->len = len; return rc; } diff --git a/drivers/net/sfc/falcon.c b/drivers/net/sfc/falcon.c index 3f74ceff6a2e..71e0bed60616 100644 --- a/drivers/net/sfc/falcon.c +++ b/drivers/net/sfc/falcon.c @@ -1628,9 +1628,9 @@ static int falcon_spi_wait(struct efx_nic *efx) } } -static int falcon_spi_cmd(const struct efx_spi_device *spi, - unsigned int command, int address, - const void *in, void *out, unsigned int len) +int falcon_spi_cmd(const struct efx_spi_device *spi, + unsigned int command, int address, + const void *in, void *out, unsigned int len) { struct efx_nic *efx = spi->efx; bool addressed = (address >= 0); @@ -1641,6 +1641,7 @@ static int falcon_spi_cmd(const struct efx_spi_device *spi, /* Input validation */ if (len > FALCON_SPI_MAX_LEN) return -EINVAL; + BUG_ON(!mutex_is_locked(&efx->spi_lock)); /* Check SPI not currently being accessed */ rc = falcon_spi_wait(efx); @@ -1699,8 +1700,7 @@ efx_spi_munge_command(const struct efx_spi_device *spi, return command | (((address >> 8) & spi->munge_address) << 3); } - -static int falcon_spi_fast_wait(const struct efx_spi_device *spi) +int falcon_spi_fast_wait(const struct efx_spi_device *spi) { u8 status; int i, rc; @@ -2259,7 +2259,9 @@ int falcon_read_nvram(struct efx_nic *efx, struct falcon_nvconfig *nvconfig_out) nvconfig = region + NVCONFIG_OFFSET; spi = efx->spi_flash ? efx->spi_flash : efx->spi_eeprom; + mutex_lock(&efx->spi_lock); rc = falcon_spi_read(spi, 0, FALCON_NVCONFIG_END, NULL, region); + mutex_unlock(&efx->spi_lock); if (rc) { EFX_ERR(efx, "Failed to read %s\n", efx->spi_flash ? "flash" : "EEPROM"); @@ -2555,6 +2557,11 @@ static int falcon_spi_device_init(struct efx_nic *efx, SPI_DEV_TYPE_FIELD(device_type, SPI_DEV_TYPE_ADDR_LEN); spi_device->munge_address = (spi_device->size == 1 << 9 && spi_device->addr_len == 1); + spi_device->erase_command = + SPI_DEV_TYPE_FIELD(device_type, SPI_DEV_TYPE_ERASE_CMD); + spi_device->erase_size = + 1 << SPI_DEV_TYPE_FIELD(device_type, + SPI_DEV_TYPE_ERASE_SIZE); spi_device->block_size = 1 << SPI_DEV_TYPE_FIELD(device_type, SPI_DEV_TYPE_BLOCK_SIZE); diff --git a/drivers/net/sfc/mtd.c b/drivers/net/sfc/mtd.c new file mode 100644 index 000000000000..a1e6c2875fc0 --- /dev/null +++ b/drivers/net/sfc/mtd.c @@ -0,0 +1,268 @@ +/**************************************************************************** + * Driver for Solarflare Solarstorm network controllers and boards + * Copyright 2005-2006 Fen Systems Ltd. + * Copyright 2006-2008 Solarflare Communications Inc. + * + * 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, incorporated herein by reference. + */ + +#include +#include +#include + +#define EFX_DRIVER_NAME "sfc_mtd" +#include "net_driver.h" +#include "spi.h" + +#define EFX_SPI_VERIFY_BUF_LEN 16 + +struct efx_mtd { + const struct efx_spi_device *spi; + struct mtd_info mtd; + char name[IFNAMSIZ + 20]; +}; + +/* SPI utilities */ + +static int efx_spi_slow_wait(struct efx_mtd *efx_mtd, bool uninterruptible) +{ + const struct efx_spi_device *spi = efx_mtd->spi; + struct efx_nic *efx = spi->efx; + u8 status; + int rc, i; + + /* Wait up to 4s for flash/EEPROM to finish a slow operation. */ + for (i = 0; i < 40; i++) { + __set_current_state(uninterruptible ? + TASK_UNINTERRUPTIBLE : TASK_INTERRUPTIBLE); + schedule_timeout(HZ / 10); + rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL, + &status, sizeof(status)); + if (rc) + return rc; + if (!(status & SPI_STATUS_NRDY)) + return 0; + if (signal_pending(current)) + return -EINTR; + } + EFX_ERR(efx, "timed out waiting for %s\n", efx_mtd->name); + return -ETIMEDOUT; +} + +static int efx_spi_unlock(const struct efx_spi_device *spi) +{ + const u8 unlock_mask = (SPI_STATUS_BP2 | SPI_STATUS_BP1 | + SPI_STATUS_BP0); + u8 status; + int rc; + + rc = falcon_spi_cmd(spi, SPI_RDSR, -1, NULL, &status, sizeof(status)); + if (rc) + return rc; + + if (!(status & unlock_mask)) + return 0; /* already unlocked */ + + rc = falcon_spi_cmd(spi, SPI_WREN, -1, NULL, NULL, 0); + if (rc) + return rc; + rc = falcon_spi_cmd(spi, SPI_SST_EWSR, -1, NULL, NULL, 0); + if (rc) + return rc; + + status &= ~unlock_mask; + rc = falcon_spi_cmd(spi, SPI_WRSR, -1, &status, NULL, sizeof(status)); + if (rc) + return rc; + rc = falcon_spi_fast_wait(spi); + if (rc) + return rc; + + return 0; +} + +static int efx_spi_erase(struct efx_mtd *efx_mtd, loff_t start, size_t len) +{ + const struct efx_spi_device *spi = efx_mtd->spi; + unsigned pos, block_len; + u8 empty[EFX_SPI_VERIFY_BUF_LEN]; + u8 buffer[EFX_SPI_VERIFY_BUF_LEN]; + int rc; + + if (len != spi->erase_size) + return -EINVAL; + + if (spi->erase_command == 0) + return -EOPNOTSUPP; + + rc = efx_spi_unlock(spi); + if (rc) + return rc; + rc = falcon_spi_cmd(spi, SPI_WREN, -1, NULL, NULL, 0); + if (rc) + return rc; + rc = falcon_spi_cmd(spi, spi->erase_command, start, NULL, NULL, 0); + if (rc) + return rc; + rc = efx_spi_slow_wait(efx_mtd, false); + + /* Verify the entire region has been wiped */ + memset(empty, 0xff, sizeof(empty)); + for (pos = 0; pos < len; pos += block_len) { + block_len = min(len - pos, sizeof(buffer)); + rc = falcon_spi_read(spi, start + pos, block_len, NULL, buffer); + if (rc) + return rc; + if (memcmp(empty, buffer, block_len)) + return -EIO; + + /* Avoid locking up the system */ + cond_resched(); + if (signal_pending(current)) + return -EINTR; + } + + return rc; +} + +/* MTD interface */ + +static int efx_mtd_read(struct mtd_info *mtd, loff_t start, size_t len, + size_t *retlen, u8 *buffer) +{ + struct efx_mtd *efx_mtd = mtd->priv; + const struct efx_spi_device *spi = efx_mtd->spi; + struct efx_nic *efx = spi->efx; + int rc; + + rc = mutex_lock_interruptible(&efx->spi_lock); + if (rc) + return rc; + rc = falcon_spi_read(spi, FALCON_FLASH_BOOTCODE_START + start, + len, retlen, buffer); + mutex_unlock(&efx->spi_lock); + return rc; +} + +static int efx_mtd_erase(struct mtd_info *mtd, struct erase_info *erase) +{ + struct efx_mtd *efx_mtd = mtd->priv; + struct efx_nic *efx = efx_mtd->spi->efx; + int rc; + + rc = mutex_lock_interruptible(&efx->spi_lock); + if (rc) + return rc; + rc = efx_spi_erase(efx_mtd, FALCON_FLASH_BOOTCODE_START + erase->addr, + erase->len); + mutex_unlock(&efx->spi_lock); + + if (rc == 0) { + erase->state = MTD_ERASE_DONE; + } else { + erase->state = MTD_ERASE_FAILED; + erase->fail_addr = 0xffffffff; + } + mtd_erase_callback(erase); + return rc; +} + +static int efx_mtd_write(struct mtd_info *mtd, loff_t start, + size_t len, size_t *retlen, const u8 *buffer) +{ + struct efx_mtd *efx_mtd = mtd->priv; + const struct efx_spi_device *spi = efx_mtd->spi; + struct efx_nic *efx = spi->efx; + int rc; + + rc = mutex_lock_interruptible(&efx->spi_lock); + if (rc) + return rc; + rc = falcon_spi_write(spi, FALCON_FLASH_BOOTCODE_START + start, + len, retlen, buffer); + mutex_unlock(&efx->spi_lock); + return rc; +} + +static void efx_mtd_sync(struct mtd_info *mtd) +{ + struct efx_mtd *efx_mtd = mtd->priv; + struct efx_nic *efx = efx_mtd->spi->efx; + int rc; + + mutex_lock(&efx->spi_lock); + rc = efx_spi_slow_wait(efx_mtd, true); + mutex_unlock(&efx->spi_lock); + + if (rc) + EFX_ERR(efx, "%s sync failed (%d)\n", efx_mtd->name, rc); + return; +} + +void efx_mtd_remove(struct efx_nic *efx) +{ + if (efx->spi_flash && efx->spi_flash->mtd) { + struct efx_mtd *efx_mtd = efx->spi_flash->mtd; + int rc; + + for (;;) { + rc = del_mtd_device(&efx_mtd->mtd); + if (rc != -EBUSY) + break; + ssleep(1); + } + WARN_ON(rc); + kfree(efx_mtd); + } +} + +void efx_mtd_rename(struct efx_nic *efx) +{ + if (efx->spi_flash && efx->spi_flash->mtd) { + struct efx_mtd *efx_mtd = efx->spi_flash->mtd; + snprintf(efx_mtd->name, sizeof(efx_mtd->name), + "%s sfc_flash_bootrom", efx->name); + } +} + +int efx_mtd_probe(struct efx_nic *efx) +{ + struct efx_spi_device *spi = efx->spi_flash; + struct efx_mtd *efx_mtd; + + if (!spi || spi->size <= FALCON_FLASH_BOOTCODE_START) + return -ENODEV; + + efx_mtd = kzalloc(sizeof(*efx_mtd), GFP_KERNEL); + if (!efx_mtd) + return -ENOMEM; + + efx_mtd->spi = spi; + spi->mtd = efx_mtd; + + efx_mtd->mtd.type = MTD_NORFLASH; + efx_mtd->mtd.flags = MTD_CAP_NORFLASH; + efx_mtd->mtd.size = spi->size - FALCON_FLASH_BOOTCODE_START; + efx_mtd->mtd.erasesize = spi->erase_size; + efx_mtd->mtd.writesize = 1; + efx_mtd_rename(efx); + + efx_mtd->mtd.owner = THIS_MODULE; + efx_mtd->mtd.priv = efx_mtd; + efx_mtd->mtd.name = efx_mtd->name; + efx_mtd->mtd.erase = efx_mtd_erase; + efx_mtd->mtd.read = efx_mtd_read; + efx_mtd->mtd.write = efx_mtd_write; + efx_mtd->mtd.sync = efx_mtd_sync; + + if (add_mtd_device(&efx_mtd->mtd)) { + kfree(efx_mtd); + spi->mtd = NULL; + /* add_mtd_device() returns 1 if the MTD table is full */ + return -ENOMEM; + } + + return 0; +} diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h index cdb11fad6050..c953eb19df42 100644 --- a/drivers/net/sfc/net_driver.h +++ b/drivers/net/sfc/net_driver.h @@ -655,6 +655,7 @@ union efx_multicast_hash { * This field will be %NULL if no flash device is present. * @spi_eeprom: SPI EEPROM device * This field will be %NULL if no EEPROM device is present. + * @spi_lock: SPI bus lock * @n_rx_nodesc_drop_cnt: RX no descriptor drop count * @nic_data: Hardware dependant state * @mac_lock: MAC access lock. Protects @port_enabled, @phy_mode, @@ -731,6 +732,7 @@ struct efx_nic { struct efx_spi_device *spi_flash; struct efx_spi_device *spi_eeprom; + struct mutex spi_lock; unsigned n_rx_nodesc_drop_cnt; diff --git a/drivers/net/sfc/spi.h b/drivers/net/sfc/spi.h index b73f86cf5fa2..c4aca132348a 100644 --- a/drivers/net/sfc/spi.h +++ b/drivers/net/sfc/spi.h @@ -25,6 +25,7 @@ #define SPI_WRDI 0x04 /* Reset write enable latch */ #define SPI_RDSR 0x05 /* Read status register */ #define SPI_WREN 0x06 /* Set write enable latch */ +#define SPI_SST_EWSR 0x50 /* SST: Enable write to status register */ #define SPI_STATUS_WPEN 0x80 /* Write-protect pin enabled */ #define SPI_STATUS_BP2 0x10 /* Block protection bit 2 */ @@ -36,6 +37,7 @@ /** * struct efx_spi_device - an Efx SPI (Serial Peripheral Interface) device * @efx: The Efx controller that owns this device + * @mtd: MTD state * @device_id: Controller's id for the device * @size: Size (in bytes) * @addr_len: Number of address bytes in read/write commands @@ -44,20 +46,30 @@ * use bit 3 of the command byte as address bit A8, rather * than having a two-byte address. If this flag is set, then * commands should be munged in this way. + * @erase_command: Erase command (or 0 if sector erase not needed). + * @erase_size: Erase sector size (in bytes) + * Erase commands affect sectors with this size and alignment. + * This must be a power of two. * @block_size: Write block size (in bytes). * Write commands are limited to blocks with this size and alignment. - * @read: Read function for the device - * @write: Write function for the device */ struct efx_spi_device { struct efx_nic *efx; +#ifdef CONFIG_SFC_MTD + void *mtd; +#endif int device_id; unsigned int size; unsigned int addr_len; unsigned int munge_address:1; + u8 erase_command; + unsigned int erase_size; unsigned int block_size; }; +int falcon_spi_cmd(const struct efx_spi_device *spi, unsigned int command, + int address, const void* in, void *out, unsigned int len); +int falcon_spi_fast_wait(const struct efx_spi_device *spi); int falcon_spi_read(const struct efx_spi_device *spi, loff_t start, size_t len, size_t *retlen, u8 *buffer); int falcon_spi_write(const struct efx_spi_device *spi, loff_t start, @@ -77,6 +89,7 @@ int falcon_spi_write(const struct efx_spi_device *spi, loff_t start, * be absent or truncated depending on the devices used. */ #define FALCON_NVCONFIG_END 0x400U +#define FALCON_FLASH_BOOTCODE_START 0x8000U #define EFX_EEPROM_BOOTCONFIG_START 0x800U #define EFX_EEPROM_BOOTCONFIG_END 0x1800U From 3e133c44d24a094118caee182200462d46c55b56 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 4 Nov 2008 20:34:56 +0000 Subject: [PATCH 07/11] sfc: Use lm87 and lm90 drivers for board temperature/power monitoring Add board monitoring to periodic work whenever link is down. For SFE4001, report when a fault has caused the PHY to turn off. For SFE4002, switch XFP PHY into low-power state in case of a fault. Signed-off-by: Ben Hutchings Signed-off-by: Jeff Garzik --- drivers/net/sfc/boards.c | 136 ++++++++++++++++++++++++++++++++++ drivers/net/sfc/mdio_10g.c | 35 +++++++++ drivers/net/sfc/mdio_10g.h | 7 ++ drivers/net/sfc/net_driver.h | 6 ++ drivers/net/sfc/sfe4001.c | 116 +++++++++++++---------------- drivers/net/sfc/tenxpress.c | 18 ++++- drivers/net/sfc/workarounds.h | 2 + drivers/net/sfc/xfp_phy.c | 9 +++ 8 files changed, 265 insertions(+), 64 deletions(-) diff --git a/drivers/net/sfc/boards.c b/drivers/net/sfc/boards.c index 99e602373269..edf026280bec 100644 --- a/drivers/net/sfc/boards.c +++ b/drivers/net/sfc/boards.c @@ -11,6 +11,7 @@ #include "phy.h" #include "boards.h" #include "efx.h" +#include "workarounds.h" /* Macros for unpacking the board revision */ /* The revision info is in host byte order. */ @@ -51,10 +52,129 @@ static void board_blink(struct efx_nic *efx, bool blink) } } +/***************************************************************************** + * Support for LM87 sensor chip used on several boards + */ +#define LM87_REG_ALARMS1 0x41 +#define LM87_REG_ALARMS2 0x42 +#define LM87_IN_LIMITS(nr, _min, _max) \ + 0x2B + (nr) * 2, _max, 0x2C + (nr) * 2, _min +#define LM87_AIN_LIMITS(nr, _min, _max) \ + 0x3B + (nr), _max, 0x1A + (nr), _min +#define LM87_TEMP_INT_LIMITS(_min, _max) \ + 0x39, _max, 0x3A, _min +#define LM87_TEMP_EXT1_LIMITS(_min, _max) \ + 0x37, _max, 0x38, _min + +#define LM87_ALARM_TEMP_INT 0x10 +#define LM87_ALARM_TEMP_EXT1 0x20 + +#if defined(CONFIG_SENSORS_LM87) || defined(CONFIG_SENSORS_LM87_MODULE) + +static int efx_init_lm87(struct efx_nic *efx, struct i2c_board_info *info, + const u8 *reg_values) +{ + struct i2c_client *client = i2c_new_device(&efx->i2c_adap, info); + int rc; + + if (!client) + return -EIO; + + while (*reg_values) { + u8 reg = *reg_values++; + u8 value = *reg_values++; + rc = i2c_smbus_write_byte_data(client, reg, value); + if (rc) + goto err; + } + + efx->board_info.hwmon_client = client; + return 0; + +err: + i2c_unregister_device(client); + return rc; +} + +static void efx_fini_lm87(struct efx_nic *efx) +{ + i2c_unregister_device(efx->board_info.hwmon_client); +} + +static int efx_check_lm87(struct efx_nic *efx, unsigned mask) +{ + struct i2c_client *client = efx->board_info.hwmon_client; + s32 alarms1, alarms2; + + /* If link is up then do not monitor temperature */ + if (EFX_WORKAROUND_7884(efx) && efx->link_up) + return 0; + + alarms1 = i2c_smbus_read_byte_data(client, LM87_REG_ALARMS1); + alarms2 = i2c_smbus_read_byte_data(client, LM87_REG_ALARMS2); + if (alarms1 < 0) + return alarms1; + if (alarms2 < 0) + return alarms2; + alarms1 &= mask; + alarms2 &= mask >> 8; + if (alarms1 || alarms2) { + EFX_ERR(efx, + "LM87 detected a hardware failure (status %02x:%02x)" + "%s%s\n", + alarms1, alarms2, + (alarms1 & LM87_ALARM_TEMP_INT) ? " INTERNAL" : "", + (alarms1 & LM87_ALARM_TEMP_EXT1) ? " EXTERNAL" : ""); + return -ERANGE; + } + + return 0; +} + +#else /* !CONFIG_SENSORS_LM87 */ + +static inline int +efx_init_lm87(struct efx_nic *efx, struct i2c_board_info *info, + const u8 *reg_values) +{ + return 0; +} +static inline void efx_fini_lm87(struct efx_nic *efx) +{ +} +static inline int efx_check_lm87(struct efx_nic *efx, unsigned mask) +{ + return 0; +} + +#endif /* CONFIG_SENSORS_LM87 */ + /***************************************************************************** * Support for the SFE4002 * */ +static u8 sfe4002_lm87_channel = 0x03; /* use AIN not FAN inputs */ + +static const u8 sfe4002_lm87_regs[] = { + LM87_IN_LIMITS(0, 0x83, 0x91), /* 2.5V: 1.8V +/- 5% */ + LM87_IN_LIMITS(1, 0x51, 0x5a), /* Vccp1: 1.2V +/- 5% */ + LM87_IN_LIMITS(2, 0xb6, 0xca), /* 3.3V: 3.3V +/- 5% */ + LM87_IN_LIMITS(3, 0xb0, 0xc9), /* 5V: 4.6-5.2V */ + LM87_IN_LIMITS(4, 0xb0, 0xe0), /* 12V: 11-14V */ + LM87_IN_LIMITS(5, 0x44, 0x4b), /* Vccp2: 1.0V +/- 5% */ + LM87_AIN_LIMITS(0, 0xa0, 0xb2), /* AIN1: 1.66V +/- 5% */ + LM87_AIN_LIMITS(1, 0x91, 0xa1), /* AIN2: 1.5V +/- 5% */ + LM87_TEMP_INT_LIMITS(10, 60), /* board */ + LM87_TEMP_EXT1_LIMITS(10, 70), /* Falcon */ + 0 +}; + +static struct i2c_board_info sfe4002_hwmon_info = { + I2C_BOARD_INFO("lm87", 0x2e), + .platform_data = &sfe4002_lm87_channel, + .irq = -1, +}; + /****************************************************************************/ /* LED allocations. Note that on rev A0 boards the schematic and the reality * differ: red and green are swapped. Below is the fixed (A1) layout (there @@ -84,11 +204,27 @@ static void sfe4002_fault_led(struct efx_nic *efx, bool state) QUAKE_LED_OFF); } +static int sfe4002_check_hw(struct efx_nic *efx) +{ + /* A0 board rev. 4002s report a temperature fault the whole time + * (bad sensor) so we mask it out. */ + unsigned alarm_mask = + (efx->board_info.major == 0 && efx->board_info.minor == 0) ? + ~LM87_ALARM_TEMP_EXT1 : ~0; + + return efx_check_lm87(efx, alarm_mask); +} + static int sfe4002_init(struct efx_nic *efx) { + int rc = efx_init_lm87(efx, &sfe4002_hwmon_info, sfe4002_lm87_regs); + if (rc) + return rc; + efx->board_info.monitor = sfe4002_check_hw; efx->board_info.init_leds = sfe4002_init_leds; efx->board_info.set_fault_led = sfe4002_fault_led; efx->board_info.blink = board_blink; + efx->board_info.fini = efx_fini_lm87; return 0; } diff --git a/drivers/net/sfc/mdio_10g.c b/drivers/net/sfc/mdio_10g.c index 003e48dcb2f3..19e25210b687 100644 --- a/drivers/net/sfc/mdio_10g.c +++ b/drivers/net/sfc/mdio_10g.c @@ -260,6 +260,41 @@ void mdio_clause45_phy_reconfigure(struct efx_nic *efx) MDIO_MMDREG_CTRL1, ctrl2); } +static void mdio_clause45_set_mmd_lpower(struct efx_nic *efx, + int lpower, int mmd) +{ + int phy = efx->mii.phy_id; + int stat = mdio_clause45_read(efx, phy, mmd, MDIO_MMDREG_STAT1); + int ctrl1, ctrl2; + + EFX_TRACE(efx, "Setting low power mode for MMD %d to %d\n", + mmd, lpower); + + if (stat & (1 << MDIO_MMDREG_STAT1_LPABLE_LBN)) { + ctrl1 = ctrl2 = mdio_clause45_read(efx, phy, + mmd, MDIO_MMDREG_CTRL1); + if (lpower) + ctrl2 |= (1 << MDIO_MMDREG_CTRL1_LPOWER_LBN); + else + ctrl2 &= ~(1 << MDIO_MMDREG_CTRL1_LPOWER_LBN); + if (ctrl1 != ctrl2) + mdio_clause45_write(efx, phy, mmd, + MDIO_MMDREG_CTRL1, ctrl2); + } +} + +void mdio_clause45_set_mmds_lpower(struct efx_nic *efx, + int low_power, unsigned int mmd_mask) +{ + int mmd = 0; + while (mmd_mask) { + if (mmd_mask & 1) + mdio_clause45_set_mmd_lpower(efx, low_power, mmd); + mmd_mask = (mmd_mask >> 1); + mmd++; + } +} + /** * mdio_clause45_get_settings - Read (some of) the PHY settings over MDIO. * @efx: Efx NIC diff --git a/drivers/net/sfc/mdio_10g.h b/drivers/net/sfc/mdio_10g.h index 19c42eaf7fb4..db9f358349c6 100644 --- a/drivers/net/sfc/mdio_10g.h +++ b/drivers/net/sfc/mdio_10g.h @@ -54,6 +54,9 @@ /* Loopback bit for WIS, PCS, PHYSX and DTEXS */ #define MDIO_MMDREG_CTRL1_LBACK_LBN (14) #define MDIO_MMDREG_CTRL1_LBACK_WIDTH (1) +/* Low power */ +#define MDIO_MMDREG_CTRL1_LPOWER_LBN (11) +#define MDIO_MMDREG_CTRL1_LPOWER_WIDTH (1) /* Bits in MMDREG_STAT1 */ #define MDIO_MMDREG_STAT1_FAULT_LBN (7) @@ -240,6 +243,10 @@ extern void mdio_clause45_transmit_disable(struct efx_nic *efx); /* Generic part of reconfigure: set/clear loopback bits */ extern void mdio_clause45_phy_reconfigure(struct efx_nic *efx); +/* Set the power state of the specified MMDs */ +extern void mdio_clause45_set_mmds_lpower(struct efx_nic *efx, + int low_power, unsigned int mmd_mask); + /* Read (some of) the PHY settings over MDIO */ extern void mdio_clause45_get_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd); diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h index c953eb19df42..e596c9a6a4c4 100644 --- a/drivers/net/sfc/net_driver.h +++ b/drivers/net/sfc/net_driver.h @@ -414,6 +414,7 @@ struct efx_blinker { * @init_leds: Sets up board LEDs * @set_fault_led: Turns the fault LED on or off * @blink: Starts/stops blinking + * @monitor: Board-specific health check function * @fini: Cleanup function * @blinker: used to blink LEDs in software * @hwmon_client: I2C client for hardware monitor @@ -428,6 +429,7 @@ struct efx_board { * have a separate init callback that happens later than * board init. */ int (*init_leds)(struct efx_nic *efx); + int (*monitor) (struct efx_nic *nic); void (*set_fault_led) (struct efx_nic *efx, bool state); void (*blink) (struct efx_nic *efx, bool start); void (*fini) (struct efx_nic *nic); @@ -525,11 +527,15 @@ struct efx_phy_operations { * @enum efx_phy_mode - PHY operating mode flags * @PHY_MODE_NORMAL: on and should pass traffic * @PHY_MODE_TX_DISABLED: on with TX disabled + * @PHY_MODE_LOW_POWER: set to low power through MDIO + * @PHY_MODE_OFF: switched off through external control * @PHY_MODE_SPECIAL: on but will not pass traffic */ enum efx_phy_mode { PHY_MODE_NORMAL = 0, PHY_MODE_TX_DISABLED = 1, + PHY_MODE_LOW_POWER = 2, + PHY_MODE_OFF = 4, PHY_MODE_SPECIAL = 8, }; diff --git a/drivers/net/sfc/sfe4001.c b/drivers/net/sfc/sfe4001.c index fe4e3fd22330..aa576c559ec8 100644 --- a/drivers/net/sfc/sfe4001.c +++ b/drivers/net/sfc/sfe4001.c @@ -21,6 +21,7 @@ #include "falcon_hwdefs.h" #include "falcon_io.h" #include "mac.h" +#include "workarounds.h" /************************************************************************** * @@ -65,48 +66,9 @@ #define P1_SPARE_LBN 4 #define P1_SPARE_WIDTH 4 - -/************************************************************************** - * - * Temperature Sensor - * - **************************************************************************/ -#define MAX6647 0x4e - -#define RLTS 0x00 -#define RLTE 0x01 -#define RSL 0x02 -#define RCL 0x03 -#define RCRA 0x04 -#define RLHN 0x05 -#define RLLI 0x06 -#define RRHI 0x07 -#define RRLS 0x08 -#define WCRW 0x0a -#define WLHO 0x0b -#define WRHA 0x0c -#define WRLN 0x0e -#define OSHT 0x0f -#define REET 0x10 -#define RIET 0x11 -#define RWOE 0x19 -#define RWOI 0x20 -#define HYS 0x21 -#define QUEUE 0x22 -#define MFID 0xfe -#define REVID 0xff - -/* Status bits */ -#define MAX6647_BUSY (1 << 7) /* ADC is converting */ -#define MAX6647_LHIGH (1 << 6) /* Local high temp. alarm */ -#define MAX6647_LLOW (1 << 5) /* Local low temp. alarm */ -#define MAX6647_RHIGH (1 << 4) /* Remote high temp. alarm */ -#define MAX6647_RLOW (1 << 3) /* Remote low temp. alarm */ -#define MAX6647_FAULT (1 << 2) /* DXN/DXP short/open circuit */ -#define MAX6647_EOT (1 << 1) /* Remote junction overtemp. */ -#define MAX6647_IOT (1 << 0) /* Local junction overtemp. */ - -static const u8 xgphy_max_temperature = 90; +/* Temperature Sensor */ +#define MAX664X_REG_RSL 0x02 +#define MAX664X_REG_WLHO 0x0B static void sfe4001_poweroff(struct efx_nic *efx) { @@ -119,7 +81,7 @@ static void sfe4001_poweroff(struct efx_nic *efx) i2c_smbus_write_byte_data(ioexp_client, P0_CONFIG, 0xff); /* Clear any over-temperature alert */ - i2c_smbus_read_byte_data(hwmon_client, RSL); + i2c_smbus_read_byte_data(hwmon_client, MAX664X_REG_RSL); } static int sfe4001_poweron(struct efx_nic *efx) @@ -131,7 +93,7 @@ static int sfe4001_poweron(struct efx_nic *efx) u8 out; /* Clear any previous over-temperature alert */ - rc = i2c_smbus_read_byte_data(hwmon_client, RSL); + rc = i2c_smbus_read_byte_data(hwmon_client, MAX664X_REG_RSL); if (rc < 0) return rc; @@ -209,6 +171,34 @@ fail_on: return rc; } +static int sfe4001_check_hw(struct efx_nic *efx) +{ + s32 status; + + /* If XAUI link is up then do not monitor */ + if (EFX_WORKAROUND_7884(efx) && falcon_xaui_link_ok(efx)) + return 0; + + /* Check the powered status of the PHY. Lack of power implies that + * the MAX6647 has shut down power to it, probably due to a temp. + * alarm. Reading the power status rather than the MAX6647 status + * directly because the later is read-to-clear and would thus + * start to power up the PHY again when polled, causing us to blip + * the power undesirably. + * We know we can read from the IO expander because we did + * it during power-on. Assume failure now is bad news. */ + status = i2c_smbus_read_byte_data(efx->board_info.ioexp_client, P1_IN); + if (status >= 0 && + (status & ((1 << P1_AFE_PWD_LBN) | (1 << P1_DSP_PWD25_LBN))) != 0) + return 0; + + /* Use board power control, not PHY power control */ + sfe4001_poweroff(efx); + efx->phy_mode = PHY_MODE_OFF; + + return (status < 0) ? -EIO : -ERANGE; +} + /* On SFE4001 rev A2 and later, we can control the FLASH_CFG_1 pin * using the 3V3X output of the IO-expander. Allow the user to set * this when the device is stopped, and keep it stopped then. @@ -261,35 +251,34 @@ static void sfe4001_fini(struct efx_nic *efx) i2c_unregister_device(efx->board_info.hwmon_client); } +static struct i2c_board_info sfe4001_hwmon_info = { + I2C_BOARD_INFO("max6647", 0x4e), + .irq = -1, +}; + /* This board uses an I2C expander to provider power to the PHY, which needs to * be turned on before the PHY can be used. * Context: Process context, rtnl lock held */ int sfe4001_init(struct efx_nic *efx) { - struct i2c_client *hwmon_client; int rc; - hwmon_client = i2c_new_dummy(&efx->i2c_adap, MAX6647); - if (!hwmon_client) +#if defined(CONFIG_SENSORS_LM90) || defined(CONFIG_SENSORS_LM90_MODULE) + efx->board_info.hwmon_client = + i2c_new_device(&efx->i2c_adap, &sfe4001_hwmon_info); +#else + efx->board_info.hwmon_client = + i2c_new_dummy(&efx->i2c_adap, sfe4001_hwmon_info.addr); +#endif + if (!efx->board_info.hwmon_client) return -EIO; - efx->board_info.hwmon_client = hwmon_client; - /* Set DSP over-temperature alert threshold */ - EFX_INFO(efx, "DSP cut-out at %dC\n", xgphy_max_temperature); - rc = i2c_smbus_write_byte_data(hwmon_client, WLHO, - xgphy_max_temperature); + /* Raise board/PHY high limit from 85 to 90 degrees Celsius */ + rc = i2c_smbus_write_byte_data(efx->board_info.hwmon_client, + MAX664X_REG_WLHO, 90); if (rc) - goto fail_ioexp; - - /* Read it back and verify */ - rc = i2c_smbus_read_byte_data(hwmon_client, RLHN); - if (rc < 0) - goto fail_ioexp; - if (rc != xgphy_max_temperature) { - rc = -EFAULT; - goto fail_ioexp; - } + goto fail_hwmon; efx->board_info.ioexp_client = i2c_new_dummy(&efx->i2c_adap, PCA9539); if (!efx->board_info.ioexp_client) { @@ -301,6 +290,7 @@ int sfe4001_init(struct efx_nic *efx) * blink code. */ efx->board_info.blink = tenxpress_phy_blink; + efx->board_info.monitor = sfe4001_check_hw; efx->board_info.fini = sfe4001_fini; rc = sfe4001_poweron(efx); @@ -319,6 +309,6 @@ fail_on: fail_ioexp: i2c_unregister_device(efx->board_info.ioexp_client); fail_hwmon: - i2c_unregister_device(hwmon_client); + i2c_unregister_device(efx->board_info.hwmon_client); return rc; } diff --git a/drivers/net/sfc/tenxpress.c b/drivers/net/sfc/tenxpress.c index d507c93d666e..8d41c29b9d7b 100644 --- a/drivers/net/sfc/tenxpress.c +++ b/drivers/net/sfc/tenxpress.c @@ -376,6 +376,7 @@ static int tenxpress_phy_check_hw(struct efx_nic *efx) { struct tenxpress_phy_data *phy_data = efx->phy_data; bool link_ok; + int rc = 0; link_ok = tenxpress_link_ok(efx, true); @@ -391,7 +392,22 @@ static int tenxpress_phy_check_hw(struct efx_nic *efx) atomic_set(&phy_data->bad_crc_count, 0); } - return 0; + rc = efx->board_info.monitor(efx); + if (rc) { + EFX_ERR(efx, "Board sensor %s; shutting down PHY\n", + (rc == -ERANGE) ? "reported fault" : "failed"); + if (efx->phy_mode & PHY_MODE_OFF) { + /* Assume that board has shut PHY off */ + phy_data->phy_mode = PHY_MODE_OFF; + } else { + efx->phy_mode |= PHY_MODE_LOW_POWER; + mdio_clause45_set_mmds_lpower(efx, true, + efx->phy_op->mmds); + phy_data->phy_mode |= PHY_MODE_LOW_POWER; + } + } + + return rc; } static void tenxpress_phy_fini(struct efx_nic *efx) diff --git a/drivers/net/sfc/workarounds.h b/drivers/net/sfc/workarounds.h index fa7b49d69288..ec50b90f4285 100644 --- a/drivers/net/sfc/workarounds.h +++ b/drivers/net/sfc/workarounds.h @@ -22,6 +22,8 @@ #define EFX_WORKAROUND_5147 EFX_WORKAROUND_ALWAYS /* RX PCIe double split performance issue */ #define EFX_WORKAROUND_7575 EFX_WORKAROUND_ALWAYS +/* Bit-bashed I2C reads cause performance drop */ +#define EFX_WORKAROUND_7884 EFX_WORKAROUND_ALWAYS /* TX pkt parser problem with <= 16 byte TXes */ #define EFX_WORKAROUND_9141 EFX_WORKAROUND_ALWAYS /* Low rate CRC errors require XAUI reset */ diff --git a/drivers/net/sfc/xfp_phy.c b/drivers/net/sfc/xfp_phy.c index 276151df3a70..91f024662101 100644 --- a/drivers/net/sfc/xfp_phy.c +++ b/drivers/net/sfc/xfp_phy.c @@ -128,6 +128,15 @@ static int xfp_phy_check_hw(struct efx_nic *efx) if (link_up != efx->link_up) falcon_xmac_sim_phy_event(efx); + rc = efx->board_info.monitor(efx); + if (rc) { + struct xfp_phy_data *phy_data = efx->phy_data; + EFX_ERR(efx, "XFP sensor alert; putting PHY into low power\n"); + efx->phy_mode |= PHY_MODE_LOW_POWER; + mdio_clause45_set_mmds_lpower(efx, 1, XFP_REQUIRED_DEVS); + phy_data->phy_mode |= PHY_MODE_LOW_POWER; + } + return rc; } From 739bb23d722313e37322f485eb65f700b060d817 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Tue, 4 Nov 2008 20:35:36 +0000 Subject: [PATCH 08/11] sfc: Do not reset when hardware monitor detects a fault The TX watchdog should trigger a reset, but a temperature/power alarm should not as this is unlikely to solve the problem. Signed-off-by: Ben Hutchings Signed-off-by: Jeff Garzik --- drivers/net/sfc/efx.c | 25 ++++--------------------- drivers/net/sfc/enum.h | 4 ++-- 2 files changed, 6 insertions(+), 23 deletions(-) diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c index f9139377989f..ac7bdbf3fd4a 100644 --- a/drivers/net/sfc/efx.c +++ b/drivers/net/sfc/efx.c @@ -77,11 +77,6 @@ static int napi_weight = 64; */ unsigned int efx_monitor_interval = 1 * HZ; -/* This controls whether or not the hardware monitor will trigger a - * reset when it detects an error condition. - */ -static unsigned int monitor_reset = true; - /* This controls whether or not the driver will initialise devices * with invalid MAC addresses stored in the EEPROM or flash. If true, * such devices will be initialised with a random locally-generated @@ -1176,17 +1171,6 @@ static void efx_monitor(struct work_struct *data) rc = falcon_check_xmac(efx); mutex_unlock(&efx->mac_lock); - if (rc) { - if (monitor_reset) { - EFX_ERR(efx, "hardware monitor detected a fault: " - "triggering reset\n"); - efx_schedule_reset(efx, RESET_TYPE_MONITOR); - } else { - EFX_ERR(efx, "hardware monitor detected a fault, " - "skipping reset\n"); - } - } - queue_delayed_work(efx->workqueue, &efx->monitor_work, efx_monitor_interval); } @@ -1358,12 +1342,11 @@ static void efx_watchdog(struct net_device *net_dev) { struct efx_nic *efx = netdev_priv(net_dev); - EFX_ERR(efx, "TX stuck with stop_count=%d port_enabled=%d: %s\n", - atomic_read(&efx->netif_stop_count), efx->port_enabled, - monitor_reset ? "resetting channels" : "skipping reset"); + EFX_ERR(efx, "TX stuck with stop_count=%d port_enabled=%d:" + " resetting channels\n", + atomic_read(&efx->netif_stop_count), efx->port_enabled); - if (monitor_reset) - efx_schedule_reset(efx, RESET_TYPE_MONITOR); + efx_schedule_reset(efx, RESET_TYPE_TX_WATCHDOG); } diff --git a/drivers/net/sfc/enum.h b/drivers/net/sfc/enum.h index cec15dbb88e4..41e758e8fdb1 100644 --- a/drivers/net/sfc/enum.h +++ b/drivers/net/sfc/enum.h @@ -72,7 +72,7 @@ extern const char *efx_loopback_mode_names[]; * @RESET_TYPE_ALL: reset everything but PCI core blocks * @RESET_TYPE_WORLD: reset everything, save & restore PCI config * @RESET_TYPE_DISABLE: disable NIC - * @RESET_TYPE_MONITOR: reset due to hardware monitor + * @RESET_TYPE_TX_WATCHDOG: reset due to TX watchdog * @RESET_TYPE_INT_ERROR: reset due to internal error * @RESET_TYPE_RX_RECOVERY: reset to recover from RX datapath errors * @RESET_TYPE_RX_DESC_FETCH: pcie error during rx descriptor fetch @@ -86,7 +86,7 @@ enum reset_type { RESET_TYPE_WORLD = 2, RESET_TYPE_DISABLE = 3, RESET_TYPE_MAX_METHOD, - RESET_TYPE_MONITOR, + RESET_TYPE_TX_WATCHDOG, RESET_TYPE_INT_ERROR, RESET_TYPE_RX_RECOVERY, RESET_TYPE_RX_DESC_FETCH, From c5916cf8dbd3ac5ec675d9347aeaa796b546b50e Mon Sep 17 00:00:00 2001 From: Hannes Hering Date: Wed, 5 Nov 2008 13:18:21 +0100 Subject: [PATCH 09/11] ehea: Fix some whitespace issues This patch removes some trailing whitespaces and spaces before tabs. Signed-off-by: Hannes Hering Signed-off-by: Jeff Garzik --- drivers/net/ehea/ehea.h | 2 +- drivers/net/ehea/ehea_qmr.c | 10 +++++----- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/drivers/net/ehea/ehea.h b/drivers/net/ehea/ehea.h index 002d918fb4c7..9930d5f8b9e1 100644 --- a/drivers/net/ehea/ehea.h +++ b/drivers/net/ehea/ehea.h @@ -40,7 +40,7 @@ #include #define DRV_NAME "ehea" -#define DRV_VERSION "EHEA_0095" +#define DRV_VERSION "EHEA_0096" /* eHEA capability flags */ #define DLPAR_PORT_ADD_REM 1 diff --git a/drivers/net/ehea/ehea_qmr.c b/drivers/net/ehea/ehea_qmr.c index 9d006878f045..3c0ec82f36fb 100644 --- a/drivers/net/ehea/ehea_qmr.c +++ b/drivers/net/ehea/ehea_qmr.c @@ -653,7 +653,7 @@ static int ehea_update_busmap(unsigned long pfn, unsigned long nr_pages, int add int top = ehea_calc_index(i, EHEA_TOP_INDEX_SHIFT); int dir = ehea_calc_index(i, EHEA_DIR_INDEX_SHIFT); int idx = i & EHEA_INDEX_MASK; - + if (add) { int ret = ehea_init_bmap(ehea_bmap, top, dir); if (ret) @@ -780,7 +780,7 @@ void ehea_destroy_busmap(void) kfree(ehea_bmap); ehea_bmap = NULL; -out_destroy: +out_destroy: mutex_unlock(&ehea_busmap_mutex); } @@ -858,10 +858,10 @@ static u64 ehea_reg_mr_sections(int top, int dir, u64 *pt, for (idx = 0; idx < EHEA_MAP_ENTRIES; idx++) { if (!ehea_bmap->top[top]->dir[dir]->ent[idx]) continue; - + hret = ehea_reg_mr_section(top, dir, idx, pt, adapter, mr); if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED)) - return hret; + return hret; } return hret; } @@ -879,7 +879,7 @@ static u64 ehea_reg_mr_dir_sections(int top, u64 *pt, hret = ehea_reg_mr_sections(top, dir, pt, adapter, mr); if ((hret != H_SUCCESS) && (hret != H_PAGE_REGISTERED)) - return hret; + return hret; } return hret; } From fd9abb3d97c2ab883e4732ec1214fe64190236e7 Mon Sep 17 00:00:00 2001 From: Steve Glendinning Date: Wed, 5 Nov 2008 00:35:37 +0000 Subject: [PATCH 10/11] SMSC LAN911x and LAN921x vendor driver Attached is a driver for SMSC's LAN911x and LAN921x families of embedded ethernet controllers. There is an existing smc911x driver in the tree; this is intended to replace it. Dustin McIntire (the author of the smc911x driver) has expressed his support for switching to this driver. This driver contains workarounds for all known hardware issues, and has been tested on all flavours of the chip on multiple architectures. This driver now uses phylib, so this patch also adds support for the device's internal phy Signed-off-by: Steve Glendinning Signed-off-by: Bahadir Balban Signed-off-by: Dustin Mcintire Signed-off-by: Bill Gatliff Signed-off-by: Jeff Garzik --- MAINTAINERS | 6 + drivers/net/Kconfig | 14 + drivers/net/Makefile | 1 + drivers/net/phy/smsc.c | 28 + drivers/net/smsc911x.c | 2091 ++++++++++++++++++++++++++++++++++++++ drivers/net/smsc911x.h | 394 +++++++ include/linux/smsc911x.h | 42 + 7 files changed, 2576 insertions(+) create mode 100644 drivers/net/smsc911x.c create mode 100644 drivers/net/smsc911x.h create mode 100644 include/linux/smsc911x.h diff --git a/MAINTAINERS b/MAINTAINERS index 129117fe6490..5d951f3db018 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3853,6 +3853,12 @@ M: mhoffman@lightlink.com L: lm-sensors@lm-sensors.org S: Maintained +SMSC911x ETHERNET DRIVER +P: Steve Glendinning +M: steve.glendinning@smsc.com +L: netdev@vger.kernel.org +S: Supported + SMX UIO Interface P: Ben Nizette M: bn@niasdigital.com diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index f1d0a1371695..74a18a7f8f40 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -979,6 +979,20 @@ config SMC911X called smc911x. If you want to compile it as a module, say M here and read +config SMSC911X + tristate "SMSC LAN911x/LAN921x families embedded ethernet support" + depends on ARM || SUPERH + select CRC32 + select MII + select PHYLIB + ---help--- + Say Y here if you want support for SMSC LAN911x and LAN921x families + of ethernet controllers. + + To compile this driver as a module, choose M here and read + . The module + will be called smsc911x. + config NET_VENDOR_RACAL bool "Racal-Interlan (Micom) NI cards" depends on ISA diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 657c47b1a6b6..e06829aa75b0 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -219,6 +219,7 @@ obj-$(CONFIG_S2IO) += s2io.o obj-$(CONFIG_MYRI10GE) += myri10ge/ obj-$(CONFIG_SMC91X) += smc91x.o obj-$(CONFIG_SMC911X) += smc911x.o +obj-$(CONFIG_SMSC911X) += smsc911x.o obj-$(CONFIG_BFIN_MAC) += bfin_mac.o obj-$(CONFIG_DM9000) += dm9000.o obj-$(CONFIG_PASEMI_MAC) += pasemi_mac_driver.o diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index 73baa7a3bb0e..c05d38d46350 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -126,6 +126,27 @@ static struct phy_driver lan8700_driver = { .driver = { .owner = THIS_MODULE, } }; +static struct phy_driver lan911x_int_driver = { + .phy_id = 0x0007c0d0, /* OUI=0x00800f, Model#=0x0d */ + .phy_id_mask = 0xfffffff0, + .name = "SMSC LAN911x Internal PHY", + + .features = (PHY_BASIC_FEATURES | SUPPORTED_Pause + | SUPPORTED_Asym_Pause), + .flags = PHY_HAS_INTERRUPT | PHY_HAS_MAGICANEG, + + /* basic functions */ + .config_aneg = genphy_config_aneg, + .read_status = genphy_read_status, + .config_init = smsc_phy_config_init, + + /* IRQ related */ + .ack_interrupt = smsc_phy_ack_interrupt, + .config_intr = smsc_phy_config_intr, + + .driver = { .owner = THIS_MODULE, } +}; + static int __init smsc_init(void) { int ret; @@ -142,8 +163,14 @@ static int __init smsc_init(void) if (ret) goto err3; + ret = phy_driver_register (&lan911x_int_driver); + if (ret) + goto err4; + return 0; +err4: + phy_driver_unregister (&lan8700_driver); err3: phy_driver_unregister (&lan8187_driver); err2: @@ -154,6 +181,7 @@ err1: static void __exit smsc_exit(void) { + phy_driver_unregister (&lan911x_int_driver); phy_driver_unregister (&lan8700_driver); phy_driver_unregister (&lan8187_driver); phy_driver_unregister (&lan83c185_driver); diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c new file mode 100644 index 000000000000..fe517880fc97 --- /dev/null +++ b/drivers/net/smsc911x.c @@ -0,0 +1,2091 @@ +/*************************************************************************** + * + * Copyright (C) 2004-2008 SMSC + * Copyright (C) 2005-2008 ARM + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + *************************************************************************** + * Rewritten, heavily based on smsc911x simple driver by SMSC. + * Partly uses io macros from smc91x.c by Nicolas Pitre + * + * Supported devices: + * LAN9115, LAN9116, LAN9117, LAN9118 + * LAN9215, LAN9216, LAN9217, LAN9218 + * LAN9210, LAN9211 + * LAN9220, LAN9221 + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "smsc911x.h" + +#define SMSC_CHIPNAME "smsc911x" +#define SMSC_MDIONAME "smsc911x-mdio" +#define SMSC_DRV_VERSION "2008-10-21" + +MODULE_LICENSE("GPL"); +MODULE_VERSION(SMSC_DRV_VERSION); + +#if USE_DEBUG > 0 +static int debug = 16; +#else +static int debug = 3; +#endif + +module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); + +struct smsc911x_data { + void __iomem *ioaddr; + + unsigned int idrev; + + /* used to decide which workarounds apply */ + unsigned int generation; + + /* device configuration (copied from platform_data during probe) */ + unsigned int irq_polarity; + unsigned int irq_type; + phy_interface_t phy_interface; + + /* This needs to be acquired before calling any of below: + * smsc911x_mac_read(), smsc911x_mac_write() + */ + spinlock_t mac_lock; + +#if (!SMSC_CAN_USE_32BIT) + /* spinlock to ensure 16-bit accesses are serialised */ + spinlock_t dev_lock; +#endif + + struct phy_device *phy_dev; + struct mii_bus *mii_bus; + int phy_irq[PHY_MAX_ADDR]; + unsigned int using_extphy; + int last_duplex; + int last_carrier; + + u32 msg_enable; + unsigned int gpio_setting; + unsigned int gpio_orig_setting; + struct net_device *dev; + struct napi_struct napi; + + unsigned int software_irq_signal; + +#ifdef USE_PHY_WORK_AROUND +#define MIN_PACKET_SIZE (64) + char loopback_tx_pkt[MIN_PACKET_SIZE]; + char loopback_rx_pkt[MIN_PACKET_SIZE]; + unsigned int resetcount; +#endif + + /* Members for Multicast filter workaround */ + unsigned int multicast_update_pending; + unsigned int set_bits_mask; + unsigned int clear_bits_mask; + unsigned int hashhi; + unsigned int hashlo; +}; + +#if SMSC_CAN_USE_32BIT + +static inline u32 smsc911x_reg_read(struct smsc911x_data *pdata, u32 reg) +{ + return readl(pdata->ioaddr + reg); +} + +static inline void smsc911x_reg_write(struct smsc911x_data *pdata, u32 reg, + u32 val) +{ + writel(val, pdata->ioaddr + reg); +} + +/* Writes a packet to the TX_DATA_FIFO */ +static inline void +smsc911x_tx_writefifo(struct smsc911x_data *pdata, unsigned int *buf, + unsigned int wordcount) +{ + writesl(pdata->ioaddr + TX_DATA_FIFO, buf, wordcount); +} + +/* Reads a packet out of the RX_DATA_FIFO */ +static inline void +smsc911x_rx_readfifo(struct smsc911x_data *pdata, unsigned int *buf, + unsigned int wordcount) +{ + readsl(pdata->ioaddr + RX_DATA_FIFO, buf, wordcount); +} + +#else /* SMSC_CAN_USE_32BIT */ + +/* These 16-bit access functions are significantly slower, due to the locking + * necessary. If your bus hardware can be configured to do this for you + * (in response to a single 32-bit operation from software), you should use + * the 32-bit access functions instead. */ + +static inline u32 smsc911x_reg_read(struct smsc911x_data *pdata, u32 reg) +{ + unsigned long flags; + u32 data; + + /* these two 16-bit reads must be performed consecutively, so must + * not be interrupted by our own ISR (which would start another + * read operation) */ + spin_lock_irqsave(&pdata->dev_lock, flags); + data = ((readw(pdata->ioaddr + reg) & 0xFFFF) | + ((readw(pdata->ioaddr + reg + 2) & 0xFFFF) << 16)); + spin_unlock_irqrestore(&pdata->dev_lock, flags); + + return data; +} + +static inline void smsc911x_reg_write(struct smsc911x_data *pdata, u32 reg, + u32 val) +{ + unsigned long flags; + + /* these two 16-bit writes must be performed consecutively, so must + * not be interrupted by our own ISR (which would start another + * read operation) */ + spin_lock_irqsave(&pdata->dev_lock, flags); + writew(val & 0xFFFF, pdata->ioaddr + reg); + writew((val >> 16) & 0xFFFF, pdata->ioaddr + reg + 2); + spin_unlock_irqrestore(&pdata->dev_lock, flags); +} + +/* Writes a packet to the TX_DATA_FIFO */ +static inline void +smsc911x_tx_writefifo(struct smsc911x_data *pdata, unsigned int *buf, + unsigned int wordcount) +{ + while (wordcount--) + smsc911x_reg_write(pdata, TX_DATA_FIFO, *buf++); +} + +/* Reads a packet out of the RX_DATA_FIFO */ +static inline void +smsc911x_rx_readfifo(struct smsc911x_data *pdata, unsigned int *buf, + unsigned int wordcount) +{ + while (wordcount--) + *buf++ = smsc911x_reg_read(pdata, RX_DATA_FIFO); +} + +#endif /* SMSC_CAN_USE_32BIT */ + +/* waits for MAC not busy, with timeout. Only called by smsc911x_mac_read + * and smsc911x_mac_write, so assumes mac_lock is held */ +static int smsc911x_mac_complete(struct smsc911x_data *pdata) +{ + int i; + u32 val; + + SMSC_ASSERT_MAC_LOCK(pdata); + + for (i = 0; i < 40; i++) { + val = smsc911x_reg_read(pdata, MAC_CSR_CMD); + if (!(val & MAC_CSR_CMD_CSR_BUSY_)) + return 0; + } + SMSC_WARNING(HW, "Timed out waiting for MAC not BUSY. " + "MAC_CSR_CMD: 0x%08X", val); + return -EIO; +} + +/* Fetches a MAC register value. Assumes mac_lock is acquired */ +static u32 smsc911x_mac_read(struct smsc911x_data *pdata, unsigned int offset) +{ + unsigned int temp; + + SMSC_ASSERT_MAC_LOCK(pdata); + + temp = smsc911x_reg_read(pdata, MAC_CSR_CMD); + if (unlikely(temp & MAC_CSR_CMD_CSR_BUSY_)) { + SMSC_WARNING(HW, "MAC busy at entry"); + return 0xFFFFFFFF; + } + + /* Send the MAC cmd */ + smsc911x_reg_write(pdata, MAC_CSR_CMD, ((offset & 0xFF) | + MAC_CSR_CMD_CSR_BUSY_ | MAC_CSR_CMD_R_NOT_W_)); + + /* Workaround for hardware read-after-write restriction */ + temp = smsc911x_reg_read(pdata, BYTE_TEST); + + /* Wait for the read to complete */ + if (likely(smsc911x_mac_complete(pdata) == 0)) + return smsc911x_reg_read(pdata, MAC_CSR_DATA); + + SMSC_WARNING(HW, "MAC busy after read"); + return 0xFFFFFFFF; +} + +/* Set a mac register, mac_lock must be acquired before calling */ +static void smsc911x_mac_write(struct smsc911x_data *pdata, + unsigned int offset, u32 val) +{ + unsigned int temp; + + SMSC_ASSERT_MAC_LOCK(pdata); + + temp = smsc911x_reg_read(pdata, MAC_CSR_CMD); + if (unlikely(temp & MAC_CSR_CMD_CSR_BUSY_)) { + SMSC_WARNING(HW, + "smsc911x_mac_write failed, MAC busy at entry"); + return; + } + + /* Send data to write */ + smsc911x_reg_write(pdata, MAC_CSR_DATA, val); + + /* Write the actual data */ + smsc911x_reg_write(pdata, MAC_CSR_CMD, ((offset & 0xFF) | + MAC_CSR_CMD_CSR_BUSY_)); + + /* Workaround for hardware read-after-write restriction */ + temp = smsc911x_reg_read(pdata, BYTE_TEST); + + /* Wait for the write to complete */ + if (likely(smsc911x_mac_complete(pdata) == 0)) + return; + + SMSC_WARNING(HW, + "smsc911x_mac_write failed, MAC busy after write"); +} + +/* Get a phy register */ +static int smsc911x_mii_read(struct mii_bus *bus, int phyaddr, int regidx) +{ + struct smsc911x_data *pdata = (struct smsc911x_data *)bus->priv; + unsigned long flags; + unsigned int addr; + int i, reg; + + spin_lock_irqsave(&pdata->mac_lock, flags); + + /* Confirm MII not busy */ + if (unlikely(smsc911x_mac_read(pdata, MII_ACC) & MII_ACC_MII_BUSY_)) { + SMSC_WARNING(HW, + "MII is busy in smsc911x_mii_read???"); + reg = -EIO; + goto out; + } + + /* Set the address, index & direction (read from PHY) */ + addr = ((phyaddr & 0x1F) << 11) | ((regidx & 0x1F) << 6); + smsc911x_mac_write(pdata, MII_ACC, addr); + + /* Wait for read to complete w/ timeout */ + for (i = 0; i < 100; i++) + if (!(smsc911x_mac_read(pdata, MII_ACC) & MII_ACC_MII_BUSY_)) { + reg = smsc911x_mac_read(pdata, MII_DATA); + goto out; + } + + SMSC_WARNING(HW, "Timed out waiting for MII write to finish"); + reg = -EIO; + +out: + spin_unlock_irqrestore(&pdata->mac_lock, flags); + return reg; +} + +/* Set a phy register */ +static int smsc911x_mii_write(struct mii_bus *bus, int phyaddr, int regidx, + u16 val) +{ + struct smsc911x_data *pdata = (struct smsc911x_data *)bus->priv; + unsigned long flags; + unsigned int addr; + int i, reg; + + spin_lock_irqsave(&pdata->mac_lock, flags); + + /* Confirm MII not busy */ + if (unlikely(smsc911x_mac_read(pdata, MII_ACC) & MII_ACC_MII_BUSY_)) { + SMSC_WARNING(HW, + "MII is busy in smsc911x_mii_write???"); + reg = -EIO; + goto out; + } + + /* Put the data to write in the MAC */ + smsc911x_mac_write(pdata, MII_DATA, val); + + /* Set the address, index & direction (write to PHY) */ + addr = ((phyaddr & 0x1F) << 11) | ((regidx & 0x1F) << 6) | + MII_ACC_MII_WRITE_; + smsc911x_mac_write(pdata, MII_ACC, addr); + + /* Wait for write to complete w/ timeout */ + for (i = 0; i < 100; i++) + if (!(smsc911x_mac_read(pdata, MII_ACC) & MII_ACC_MII_BUSY_)) { + reg = 0; + goto out; + } + + SMSC_WARNING(HW, "Timed out waiting for MII write to finish"); + reg = -EIO; + +out: + spin_unlock_irqrestore(&pdata->mac_lock, flags); + return reg; +} + +/* Autodetects and initialises external phy for SMSC9115 and SMSC9117 flavors. + * If something goes wrong, returns -ENODEV to revert back to internal phy. + * Performed at initialisation only, so interrupts are enabled */ +static int smsc911x_phy_initialise_external(struct smsc911x_data *pdata) +{ + unsigned int hwcfg = smsc911x_reg_read(pdata, HW_CFG); + + /* External phy is requested, supported, and detected */ + if (hwcfg & HW_CFG_EXT_PHY_DET_) { + + /* Switch to external phy. Assuming tx and rx are stopped + * because smsc911x_phy_initialise is called before + * smsc911x_rx_initialise and tx_initialise. */ + + /* Disable phy clocks to the MAC */ + hwcfg &= (~HW_CFG_PHY_CLK_SEL_); + hwcfg |= HW_CFG_PHY_CLK_SEL_CLK_DIS_; + smsc911x_reg_write(pdata, HW_CFG, hwcfg); + udelay(10); /* Enough time for clocks to stop */ + + /* Switch to external phy */ + hwcfg |= HW_CFG_EXT_PHY_EN_; + smsc911x_reg_write(pdata, HW_CFG, hwcfg); + + /* Enable phy clocks to the MAC */ + hwcfg &= (~HW_CFG_PHY_CLK_SEL_); + hwcfg |= HW_CFG_PHY_CLK_SEL_EXT_PHY_; + smsc911x_reg_write(pdata, HW_CFG, hwcfg); + udelay(10); /* Enough time for clocks to restart */ + + hwcfg |= HW_CFG_SMI_SEL_; + smsc911x_reg_write(pdata, HW_CFG, hwcfg); + + SMSC_TRACE(HW, "Successfully switched to external PHY"); + pdata->using_extphy = 1; + } else { + SMSC_WARNING(HW, "No external PHY detected, " + "Using internal PHY instead."); + /* Use internal phy */ + return -ENODEV; + } + return 0; +} + +/* Fetches a tx status out of the status fifo */ +static unsigned int smsc911x_tx_get_txstatus(struct smsc911x_data *pdata) +{ + unsigned int result = + smsc911x_reg_read(pdata, TX_FIFO_INF) & TX_FIFO_INF_TSUSED_; + + if (result != 0) + result = smsc911x_reg_read(pdata, TX_STATUS_FIFO); + + return result; +} + +/* Fetches the next rx status */ +static unsigned int smsc911x_rx_get_rxstatus(struct smsc911x_data *pdata) +{ + unsigned int result = + smsc911x_reg_read(pdata, RX_FIFO_INF) & RX_FIFO_INF_RXSUSED_; + + if (result != 0) + result = smsc911x_reg_read(pdata, RX_STATUS_FIFO); + + return result; +} + +#ifdef USE_PHY_WORK_AROUND +static int smsc911x_phy_check_loopbackpkt(struct smsc911x_data *pdata) +{ + unsigned int tries; + u32 wrsz; + u32 rdsz; + ulong bufp; + + for (tries = 0; tries < 10; tries++) { + unsigned int txcmd_a; + unsigned int txcmd_b; + unsigned int status; + unsigned int pktlength; + unsigned int i; + + /* Zero-out rx packet memory */ + memset(pdata->loopback_rx_pkt, 0, MIN_PACKET_SIZE); + + /* Write tx packet to 118 */ + txcmd_a = (u32)((ulong)pdata->loopback_tx_pkt & 0x03) << 16; + txcmd_a |= TX_CMD_A_FIRST_SEG_ | TX_CMD_A_LAST_SEG_; + txcmd_a |= MIN_PACKET_SIZE; + + txcmd_b = MIN_PACKET_SIZE << 16 | MIN_PACKET_SIZE; + + smsc911x_reg_write(pdata, TX_DATA_FIFO, txcmd_a); + smsc911x_reg_write(pdata, TX_DATA_FIFO, txcmd_b); + + bufp = (ulong)pdata->loopback_tx_pkt & (~0x3); + wrsz = MIN_PACKET_SIZE + 3; + wrsz += (u32)((ulong)pdata->loopback_tx_pkt & 0x3); + wrsz >>= 2; + + smsc911x_tx_writefifo(pdata, (unsigned int *)bufp, wrsz); + + /* Wait till transmit is done */ + i = 60; + do { + udelay(5); + status = smsc911x_tx_get_txstatus(pdata); + } while ((i--) && (!status)); + + if (!status) { + SMSC_WARNING(HW, "Failed to transmit " + "during loopback test"); + continue; + } + if (status & TX_STS_ES_) { + SMSC_WARNING(HW, "Transmit encountered " + "errors during loopback test"); + continue; + } + + /* Wait till receive is done */ + i = 60; + do { + udelay(5); + status = smsc911x_rx_get_rxstatus(pdata); + } while ((i--) && (!status)); + + if (!status) { + SMSC_WARNING(HW, + "Failed to receive during loopback test"); + continue; + } + if (status & RX_STS_ES_) { + SMSC_WARNING(HW, "Receive encountered " + "errors during loopback test"); + continue; + } + + pktlength = ((status & 0x3FFF0000UL) >> 16); + bufp = (ulong)pdata->loopback_rx_pkt; + rdsz = pktlength + 3; + rdsz += (u32)((ulong)pdata->loopback_rx_pkt & 0x3); + rdsz >>= 2; + + smsc911x_rx_readfifo(pdata, (unsigned int *)bufp, rdsz); + + if (pktlength != (MIN_PACKET_SIZE + 4)) { + SMSC_WARNING(HW, "Unexpected packet size " + "during loop back test, size=%d, will retry", + pktlength); + } else { + unsigned int j; + int mismatch = 0; + for (j = 0; j < MIN_PACKET_SIZE; j++) { + if (pdata->loopback_tx_pkt[j] + != pdata->loopback_rx_pkt[j]) { + mismatch = 1; + break; + } + } + if (!mismatch) { + SMSC_TRACE(HW, "Successfully verified " + "loopback packet"); + return 0; + } else { + SMSC_WARNING(HW, "Data mismatch " + "during loop back test, will retry"); + } + } + } + + return -EIO; +} + +static int smsc911x_phy_reset(struct smsc911x_data *pdata) +{ + struct phy_device *phy_dev = pdata->phy_dev; + unsigned int temp; + unsigned int i = 100000; + + BUG_ON(!phy_dev); + BUG_ON(!phy_dev->bus); + + SMSC_TRACE(HW, "Performing PHY BCR Reset"); + smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, BMCR_RESET); + do { + msleep(1); + temp = smsc911x_mii_read(phy_dev->bus, phy_dev->addr, + MII_BMCR); + } while ((i--) && (temp & BMCR_RESET)); + + if (temp & BMCR_RESET) { + SMSC_WARNING(HW, "PHY reset failed to complete."); + return -EIO; + } + /* Extra delay required because the phy may not be completed with + * its reset when BMCR_RESET is cleared. Specs say 256 uS is + * enough delay but using 1ms here to be safe */ + msleep(1); + + return 0; +} + +static int smsc911x_phy_loopbacktest(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + struct phy_device *phy_dev = pdata->phy_dev; + int result = -EIO; + unsigned int i, val; + unsigned long flags; + + /* Initialise tx packet using broadcast destination address */ + memset(pdata->loopback_tx_pkt, 0xff, ETH_ALEN); + + /* Use incrementing source address */ + for (i = 6; i < 12; i++) + pdata->loopback_tx_pkt[i] = (char)i; + + /* Set length type field */ + pdata->loopback_tx_pkt[12] = 0x00; + pdata->loopback_tx_pkt[13] = 0x00; + + for (i = 14; i < MIN_PACKET_SIZE; i++) + pdata->loopback_tx_pkt[i] = (char)i; + + val = smsc911x_reg_read(pdata, HW_CFG); + val &= HW_CFG_TX_FIF_SZ_; + val |= HW_CFG_SF_; + smsc911x_reg_write(pdata, HW_CFG, val); + + smsc911x_reg_write(pdata, TX_CFG, TX_CFG_TX_ON_); + smsc911x_reg_write(pdata, RX_CFG, + (u32)((ulong)pdata->loopback_rx_pkt & 0x03) << 8); + + for (i = 0; i < 10; i++) { + /* Set PHY to 10/FD, no ANEG, and loopback mode */ + smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, + BMCR_LOOPBACK | BMCR_FULLDPLX); + + /* Enable MAC tx/rx, FD */ + spin_lock_irqsave(&pdata->mac_lock, flags); + smsc911x_mac_write(pdata, MAC_CR, MAC_CR_FDPX_ + | MAC_CR_TXEN_ | MAC_CR_RXEN_); + spin_unlock_irqrestore(&pdata->mac_lock, flags); + + if (smsc911x_phy_check_loopbackpkt(pdata) == 0) { + result = 0; + break; + } + pdata->resetcount++; + + /* Disable MAC rx */ + spin_lock_irqsave(&pdata->mac_lock, flags); + smsc911x_mac_write(pdata, MAC_CR, 0); + spin_unlock_irqrestore(&pdata->mac_lock, flags); + + smsc911x_phy_reset(pdata); + } + + /* Disable MAC */ + spin_lock_irqsave(&pdata->mac_lock, flags); + smsc911x_mac_write(pdata, MAC_CR, 0); + spin_unlock_irqrestore(&pdata->mac_lock, flags); + + /* Cancel PHY loopback mode */ + smsc911x_mii_write(phy_dev->bus, phy_dev->addr, MII_BMCR, 0); + + smsc911x_reg_write(pdata, TX_CFG, 0); + smsc911x_reg_write(pdata, RX_CFG, 0); + + return result; +} +#endif /* USE_PHY_WORK_AROUND */ + +static u8 smsc95xx_resolve_flowctrl_fulldplx(u16 lcladv, u16 rmtadv) +{ + u8 cap = 0; + + if (lcladv & ADVERTISE_PAUSE_CAP) { + if (lcladv & ADVERTISE_PAUSE_ASYM) { + if (rmtadv & LPA_PAUSE_CAP) + cap = FLOW_CTRL_TX | FLOW_CTRL_RX; + else if (rmtadv & LPA_PAUSE_ASYM) + cap = FLOW_CTRL_RX; + } else { + if (rmtadv & LPA_PAUSE_CAP) + cap = FLOW_CTRL_TX | FLOW_CTRL_RX; + } + } else if (lcladv & ADVERTISE_PAUSE_ASYM) { + if ((rmtadv & LPA_PAUSE_CAP) && (rmtadv & LPA_PAUSE_ASYM)) + cap = FLOW_CTRL_TX; + } + + return cap; +} + +static void smsc911x_phy_update_flowcontrol(struct smsc911x_data *pdata) +{ + struct phy_device *phy_dev = pdata->phy_dev; + u32 afc = smsc911x_reg_read(pdata, AFC_CFG); + u32 flow; + unsigned long flags; + + if (phy_dev->duplex == DUPLEX_FULL) { + u16 lcladv = phy_read(phy_dev, MII_ADVERTISE); + u16 rmtadv = phy_read(phy_dev, MII_LPA); + u8 cap = smsc95xx_resolve_flowctrl_fulldplx(lcladv, rmtadv); + + if (cap & FLOW_CTRL_RX) + flow = 0xFFFF0002; + else + flow = 0; + + if (cap & FLOW_CTRL_TX) + afc |= 0xF; + else + afc &= ~0xF; + + SMSC_TRACE(HW, "rx pause %s, tx pause %s", + (cap & FLOW_CTRL_RX ? "enabled" : "disabled"), + (cap & FLOW_CTRL_TX ? "enabled" : "disabled")); + } else { + SMSC_TRACE(HW, "half duplex"); + flow = 0; + afc |= 0xF; + } + + spin_lock_irqsave(&pdata->mac_lock, flags); + smsc911x_mac_write(pdata, FLOW, flow); + spin_unlock_irqrestore(&pdata->mac_lock, flags); + + smsc911x_reg_write(pdata, AFC_CFG, afc); +} + +/* Update link mode if anything has changed. Called periodically when the + * PHY is in polling mode, even if nothing has changed. */ +static void smsc911x_phy_adjust_link(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + struct phy_device *phy_dev = pdata->phy_dev; + unsigned long flags; + int carrier; + + if (phy_dev->duplex != pdata->last_duplex) { + unsigned int mac_cr; + SMSC_TRACE(HW, "duplex state has changed"); + + spin_lock_irqsave(&pdata->mac_lock, flags); + mac_cr = smsc911x_mac_read(pdata, MAC_CR); + if (phy_dev->duplex) { + SMSC_TRACE(HW, + "configuring for full duplex mode"); + mac_cr |= MAC_CR_FDPX_; + } else { + SMSC_TRACE(HW, + "configuring for half duplex mode"); + mac_cr &= ~MAC_CR_FDPX_; + } + smsc911x_mac_write(pdata, MAC_CR, mac_cr); + spin_unlock_irqrestore(&pdata->mac_lock, flags); + + smsc911x_phy_update_flowcontrol(pdata); + pdata->last_duplex = phy_dev->duplex; + } + + carrier = netif_carrier_ok(dev); + if (carrier != pdata->last_carrier) { + SMSC_TRACE(HW, "carrier state has changed"); + if (carrier) { + SMSC_TRACE(HW, "configuring for carrier OK"); + if ((pdata->gpio_orig_setting & GPIO_CFG_LED1_EN_) && + (!pdata->using_extphy)) { + /* Restore orginal GPIO configuration */ + pdata->gpio_setting = pdata->gpio_orig_setting; + smsc911x_reg_write(pdata, GPIO_CFG, + pdata->gpio_setting); + } + } else { + SMSC_TRACE(HW, "configuring for no carrier"); + /* Check global setting that LED1 + * usage is 10/100 indicator */ + pdata->gpio_setting = smsc911x_reg_read(pdata, + GPIO_CFG); + if ((pdata->gpio_setting & GPIO_CFG_LED1_EN_) + && (!pdata->using_extphy)) { + /* Force 10/100 LED off, after saving + * orginal GPIO configuration */ + pdata->gpio_orig_setting = pdata->gpio_setting; + + pdata->gpio_setting &= ~GPIO_CFG_LED1_EN_; + pdata->gpio_setting |= (GPIO_CFG_GPIOBUF0_ + | GPIO_CFG_GPIODIR0_ + | GPIO_CFG_GPIOD0_); + smsc911x_reg_write(pdata, GPIO_CFG, + pdata->gpio_setting); + } + } + pdata->last_carrier = carrier; + } +} + +static int smsc911x_mii_probe(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + struct phy_device *phydev = NULL; + int phy_addr; + + /* find the first phy */ + for (phy_addr = 0; phy_addr < PHY_MAX_ADDR; phy_addr++) { + if (pdata->mii_bus->phy_map[phy_addr]) { + phydev = pdata->mii_bus->phy_map[phy_addr]; + SMSC_TRACE(PROBE, "PHY %d: addr %d, phy_id 0x%08X", + phy_addr, phydev->addr, phydev->phy_id); + break; + } + } + + if (!phydev) { + pr_err("%s: no PHY found\n", dev->name); + return -ENODEV; + } + + phydev = phy_connect(dev, phydev->dev.bus_id, + &smsc911x_phy_adjust_link, 0, pdata->phy_interface); + + if (IS_ERR(phydev)) { + pr_err("%s: Could not attach to PHY\n", dev->name); + return PTR_ERR(phydev); + } + + pr_info("%s: attached PHY driver [%s] (mii_bus:phy_addr=%s, irq=%d)\n", + dev->name, phydev->drv->name, phydev->dev.bus_id, phydev->irq); + + /* mask with MAC supported features */ + phydev->supported &= (PHY_BASIC_FEATURES | SUPPORTED_Pause | + SUPPORTED_Asym_Pause); + phydev->advertising = phydev->supported; + + pdata->phy_dev = phydev; + pdata->last_duplex = -1; + pdata->last_carrier = -1; + +#ifdef USE_PHY_WORK_AROUND + if (smsc911x_phy_loopbacktest(dev) < 0) { + SMSC_WARNING(HW, "Failed Loop Back Test"); + return -ENODEV; + } + SMSC_TRACE(HW, "Passed Loop Back Test"); +#endif /* USE_PHY_WORK_AROUND */ + + SMSC_TRACE(HW, "phy initialised succesfully"); + return 0; +} + +static int __devinit smsc911x_mii_init(struct platform_device *pdev, + struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + int err = -ENXIO, i; + + pdata->mii_bus = mdiobus_alloc(); + if (!pdata->mii_bus) { + err = -ENOMEM; + goto err_out_1; + } + + pdata->mii_bus->name = SMSC_MDIONAME; + snprintf(pdata->mii_bus->id, MII_BUS_ID_SIZE, "%x", pdev->id); + pdata->mii_bus->priv = pdata; + pdata->mii_bus->read = smsc911x_mii_read; + pdata->mii_bus->write = smsc911x_mii_write; + pdata->mii_bus->irq = pdata->phy_irq; + for (i = 0; i < PHY_MAX_ADDR; ++i) + pdata->mii_bus->irq[i] = PHY_POLL; + + pdata->mii_bus->parent = &pdev->dev; + dev_set_drvdata(&pdev->dev, &pdata->mii_bus); + + pdata->using_extphy = 0; + + switch (pdata->idrev & 0xFFFF0000) { + case 0x01170000: + case 0x01150000: + case 0x117A0000: + case 0x115A0000: + /* External PHY supported, try to autodetect */ + if (smsc911x_phy_initialise_external(pdata) < 0) { + SMSC_TRACE(HW, "No external PHY detected, " + "using internal PHY"); + } + break; + default: + SMSC_TRACE(HW, "External PHY is not supported, " + "using internal PHY"); + break; + } + + if (!pdata->using_extphy) { + /* Mask all PHYs except ID 1 (internal) */ + pdata->mii_bus->phy_mask = ~(1 << 1); + } + + if (mdiobus_register(pdata->mii_bus)) { + SMSC_WARNING(PROBE, "Error registering mii bus"); + goto err_out_free_bus_2; + } + + if (smsc911x_mii_probe(dev) < 0) { + SMSC_WARNING(PROBE, "Error registering mii bus"); + goto err_out_unregister_bus_3; + } + + return 0; + +err_out_unregister_bus_3: + mdiobus_unregister(pdata->mii_bus); +err_out_free_bus_2: + mdiobus_free(pdata->mii_bus); +err_out_1: + return err; +} + +/* Gets the number of tx statuses in the fifo */ +static unsigned int smsc911x_tx_get_txstatcount(struct smsc911x_data *pdata) +{ + return (smsc911x_reg_read(pdata, TX_FIFO_INF) + & TX_FIFO_INF_TSUSED_) >> 16; +} + +/* Reads tx statuses and increments counters where necessary */ +static void smsc911x_tx_update_txcounters(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + unsigned int tx_stat; + + while ((tx_stat = smsc911x_tx_get_txstatus(pdata)) != 0) { + if (unlikely(tx_stat & 0x80000000)) { + /* In this driver the packet tag is used as the packet + * length. Since a packet length can never reach the + * size of 0x8000, this bit is reserved. It is worth + * noting that the "reserved bit" in the warning above + * does not reference a hardware defined reserved bit + * but rather a driver defined one. + */ + SMSC_WARNING(HW, + "Packet tag reserved bit is high"); + } else { + if (unlikely(tx_stat & 0x00008000)) { + dev->stats.tx_errors++; + } else { + dev->stats.tx_packets++; + dev->stats.tx_bytes += (tx_stat >> 16); + } + if (unlikely(tx_stat & 0x00000100)) { + dev->stats.collisions += 16; + dev->stats.tx_aborted_errors += 1; + } else { + dev->stats.collisions += + ((tx_stat >> 3) & 0xF); + } + if (unlikely(tx_stat & 0x00000800)) + dev->stats.tx_carrier_errors += 1; + if (unlikely(tx_stat & 0x00000200)) { + dev->stats.collisions++; + dev->stats.tx_aborted_errors++; + } + } + } +} + +/* Increments the Rx error counters */ +static void +smsc911x_rx_counterrors(struct net_device *dev, unsigned int rxstat) +{ + int crc_err = 0; + + if (unlikely(rxstat & 0x00008000)) { + dev->stats.rx_errors++; + if (unlikely(rxstat & 0x00000002)) { + dev->stats.rx_crc_errors++; + crc_err = 1; + } + } + if (likely(!crc_err)) { + if (unlikely((rxstat & 0x00001020) == 0x00001020)) { + /* Frame type indicates length, + * and length error is set */ + dev->stats.rx_length_errors++; + } + if (rxstat & RX_STS_MCAST_) + dev->stats.multicast++; + } +} + +/* Quickly dumps bad packets */ +static void +smsc911x_rx_fastforward(struct smsc911x_data *pdata, unsigned int pktbytes) +{ + unsigned int pktwords = (pktbytes + NET_IP_ALIGN + 3) >> 2; + + if (likely(pktwords >= 4)) { + unsigned int timeout = 500; + unsigned int val; + smsc911x_reg_write(pdata, RX_DP_CTRL, RX_DP_CTRL_RX_FFWD_); + do { + udelay(1); + val = smsc911x_reg_read(pdata, RX_DP_CTRL); + } while (timeout-- && (val & RX_DP_CTRL_RX_FFWD_)); + + if (unlikely(timeout == 0)) + SMSC_WARNING(HW, "Timed out waiting for " + "RX FFWD to finish, RX_DP_CTRL: 0x%08X", val); + } else { + unsigned int temp; + while (pktwords--) + temp = smsc911x_reg_read(pdata, RX_DATA_FIFO); + } +} + +/* NAPI poll function */ +static int smsc911x_poll(struct napi_struct *napi, int budget) +{ + struct smsc911x_data *pdata = + container_of(napi, struct smsc911x_data, napi); + struct net_device *dev = pdata->dev; + int npackets = 0; + + while (likely(netif_running(dev)) && (npackets < budget)) { + unsigned int pktlength; + unsigned int pktwords; + struct sk_buff *skb; + unsigned int rxstat = smsc911x_rx_get_rxstatus(pdata); + + if (!rxstat) { + unsigned int temp; + /* We processed all packets available. Tell NAPI it can + * stop polling then re-enable rx interrupts */ + smsc911x_reg_write(pdata, INT_STS, INT_STS_RSFL_); + netif_rx_complete(dev, napi); + temp = smsc911x_reg_read(pdata, INT_EN); + temp |= INT_EN_RSFL_EN_; + smsc911x_reg_write(pdata, INT_EN, temp); + break; + } + + /* Count packet for NAPI scheduling, even if it has an error. + * Error packets still require cycles to discard */ + npackets++; + + pktlength = ((rxstat & 0x3FFF0000) >> 16); + pktwords = (pktlength + NET_IP_ALIGN + 3) >> 2; + smsc911x_rx_counterrors(dev, rxstat); + + if (unlikely(rxstat & RX_STS_ES_)) { + SMSC_WARNING(RX_ERR, + "Discarding packet with error bit set"); + /* Packet has an error, discard it and continue with + * the next */ + smsc911x_rx_fastforward(pdata, pktwords); + dev->stats.rx_dropped++; + continue; + } + + skb = netdev_alloc_skb(dev, pktlength + NET_IP_ALIGN); + if (unlikely(!skb)) { + SMSC_WARNING(RX_ERR, + "Unable to allocate skb for rx packet"); + /* Drop the packet and stop this polling iteration */ + smsc911x_rx_fastforward(pdata, pktwords); + dev->stats.rx_dropped++; + break; + } + + skb->data = skb->head; + skb_reset_tail_pointer(skb); + + /* Align IP on 16B boundary */ + skb_reserve(skb, NET_IP_ALIGN); + skb_put(skb, pktlength - 4); + smsc911x_rx_readfifo(pdata, (unsigned int *)skb->head, + pktwords); + skb->protocol = eth_type_trans(skb, dev); + skb->ip_summed = CHECKSUM_NONE; + netif_receive_skb(skb); + + /* Update counters */ + dev->stats.rx_packets++; + dev->stats.rx_bytes += (pktlength - 4); + dev->last_rx = jiffies; + } + + /* Return total received packets */ + return npackets; +} + +/* Returns hash bit number for given MAC address + * Example: + * 01 00 5E 00 00 01 -> returns bit number 31 */ +static unsigned int smsc911x_hash(char addr[ETH_ALEN]) +{ + return (ether_crc(ETH_ALEN, addr) >> 26) & 0x3f; +} + +static void smsc911x_rx_multicast_update(struct smsc911x_data *pdata) +{ + /* Performs the multicast & mac_cr update. This is called when + * safe on the current hardware, and with the mac_lock held */ + unsigned int mac_cr; + + SMSC_ASSERT_MAC_LOCK(pdata); + + mac_cr = smsc911x_mac_read(pdata, MAC_CR); + mac_cr |= pdata->set_bits_mask; + mac_cr &= ~(pdata->clear_bits_mask); + smsc911x_mac_write(pdata, MAC_CR, mac_cr); + smsc911x_mac_write(pdata, HASHH, pdata->hashhi); + smsc911x_mac_write(pdata, HASHL, pdata->hashlo); + SMSC_TRACE(HW, "maccr 0x%08X, HASHH 0x%08X, HASHL 0x%08X", + mac_cr, pdata->hashhi, pdata->hashlo); +} + +static void smsc911x_rx_multicast_update_workaround(struct smsc911x_data *pdata) +{ + unsigned int mac_cr; + + /* This function is only called for older LAN911x devices + * (revA or revB), where MAC_CR, HASHH and HASHL should not + * be modified during Rx - newer devices immediately update the + * registers. + * + * This is called from interrupt context */ + + spin_lock(&pdata->mac_lock); + + /* Check Rx has stopped */ + if (smsc911x_mac_read(pdata, MAC_CR) & MAC_CR_RXEN_) + SMSC_WARNING(DRV, "Rx not stopped"); + + /* Perform the update - safe to do now Rx has stopped */ + smsc911x_rx_multicast_update(pdata); + + /* Re-enable Rx */ + mac_cr = smsc911x_mac_read(pdata, MAC_CR); + mac_cr |= MAC_CR_RXEN_; + smsc911x_mac_write(pdata, MAC_CR, mac_cr); + + pdata->multicast_update_pending = 0; + + spin_unlock(&pdata->mac_lock); +} + +static int smsc911x_soft_reset(struct smsc911x_data *pdata) +{ + unsigned int timeout; + unsigned int temp; + + /* Reset the LAN911x */ + smsc911x_reg_write(pdata, HW_CFG, HW_CFG_SRST_); + timeout = 10; + do { + udelay(10); + temp = smsc911x_reg_read(pdata, HW_CFG); + } while ((--timeout) && (temp & HW_CFG_SRST_)); + + if (unlikely(temp & HW_CFG_SRST_)) { + SMSC_WARNING(DRV, "Failed to complete reset"); + return -EIO; + } + return 0; +} + +/* Sets the device MAC address to dev_addr, called with mac_lock held */ +static void +smsc911x_set_mac_address(struct smsc911x_data *pdata, u8 dev_addr[6]) +{ + u32 mac_high16 = (dev_addr[5] << 8) | dev_addr[4]; + u32 mac_low32 = (dev_addr[3] << 24) | (dev_addr[2] << 16) | + (dev_addr[1] << 8) | dev_addr[0]; + + SMSC_ASSERT_MAC_LOCK(pdata); + + smsc911x_mac_write(pdata, ADDRH, mac_high16); + smsc911x_mac_write(pdata, ADDRL, mac_low32); +} + +static int smsc911x_open(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + unsigned int timeout; + unsigned int temp; + unsigned int intcfg; + + /* if the phy is not yet registered, retry later*/ + if (!pdata->phy_dev) { + SMSC_WARNING(HW, "phy_dev is NULL"); + return -EAGAIN; + } + + if (!is_valid_ether_addr(dev->dev_addr)) { + SMSC_WARNING(HW, "dev_addr is not a valid MAC address"); + return -EADDRNOTAVAIL; + } + + /* Reset the LAN911x */ + if (smsc911x_soft_reset(pdata)) { + SMSC_WARNING(HW, "soft reset failed"); + return -EIO; + } + + smsc911x_reg_write(pdata, HW_CFG, 0x00050000); + smsc911x_reg_write(pdata, AFC_CFG, 0x006E3740); + + /* Make sure EEPROM has finished loading before setting GPIO_CFG */ + timeout = 50; + while ((timeout--) && + (smsc911x_reg_read(pdata, E2P_CMD) & E2P_CMD_EPC_BUSY_)) { + udelay(10); + } + + if (unlikely(timeout == 0)) + SMSC_WARNING(IFUP, + "Timed out waiting for EEPROM busy bit to clear"); + + smsc911x_reg_write(pdata, GPIO_CFG, 0x70070000); + + /* The soft reset above cleared the device's MAC address, + * restore it from local copy (set in probe) */ + spin_lock_irq(&pdata->mac_lock); + smsc911x_set_mac_address(pdata, dev->dev_addr); + spin_unlock_irq(&pdata->mac_lock); + + /* Initialise irqs, but leave all sources disabled */ + smsc911x_reg_write(pdata, INT_EN, 0); + smsc911x_reg_write(pdata, INT_STS, 0xFFFFFFFF); + + /* Set interrupt deassertion to 100uS */ + intcfg = ((10 << 24) | INT_CFG_IRQ_EN_); + + if (pdata->irq_polarity) { + SMSC_TRACE(IFUP, "irq polarity: active high"); + intcfg |= INT_CFG_IRQ_POL_; + } else { + SMSC_TRACE(IFUP, "irq polarity: active low"); + } + + if (pdata->irq_type) { + SMSC_TRACE(IFUP, "irq type: push-pull"); + intcfg |= INT_CFG_IRQ_TYPE_; + } else { + SMSC_TRACE(IFUP, "irq type: open drain"); + } + + smsc911x_reg_write(pdata, INT_CFG, intcfg); + + SMSC_TRACE(IFUP, "Testing irq handler using IRQ %d", dev->irq); + pdata->software_irq_signal = 0; + smp_wmb(); + + temp = smsc911x_reg_read(pdata, INT_EN); + temp |= INT_EN_SW_INT_EN_; + smsc911x_reg_write(pdata, INT_EN, temp); + + timeout = 1000; + while (timeout--) { + if (pdata->software_irq_signal) + break; + msleep(1); + } + + if (!pdata->software_irq_signal) { + dev_warn(&dev->dev, "ISR failed signaling test (IRQ %d)\n", + dev->irq); + return -ENODEV; + } + SMSC_TRACE(IFUP, "IRQ handler passed test using IRQ %d", dev->irq); + + dev_info(&dev->dev, "SMSC911x/921x identified at %#08lx, IRQ: %d\n", + (unsigned long)pdata->ioaddr, dev->irq); + + /* Bring the PHY up */ + phy_start(pdata->phy_dev); + + temp = smsc911x_reg_read(pdata, HW_CFG); + /* Preserve TX FIFO size and external PHY configuration */ + temp &= (HW_CFG_TX_FIF_SZ_|0x00000FFF); + temp |= HW_CFG_SF_; + smsc911x_reg_write(pdata, HW_CFG, temp); + + temp = smsc911x_reg_read(pdata, FIFO_INT); + temp |= FIFO_INT_TX_AVAIL_LEVEL_; + temp &= ~(FIFO_INT_RX_STS_LEVEL_); + smsc911x_reg_write(pdata, FIFO_INT, temp); + + /* set RX Data offset to 2 bytes for alignment */ + smsc911x_reg_write(pdata, RX_CFG, (2 << 8)); + + /* enable NAPI polling before enabling RX interrupts */ + napi_enable(&pdata->napi); + + temp = smsc911x_reg_read(pdata, INT_EN); + temp |= (INT_EN_TDFA_EN_ | INT_EN_RSFL_EN_); + smsc911x_reg_write(pdata, INT_EN, temp); + + spin_lock_irq(&pdata->mac_lock); + temp = smsc911x_mac_read(pdata, MAC_CR); + temp |= (MAC_CR_TXEN_ | MAC_CR_RXEN_ | MAC_CR_HBDIS_); + smsc911x_mac_write(pdata, MAC_CR, temp); + spin_unlock_irq(&pdata->mac_lock); + + smsc911x_reg_write(pdata, TX_CFG, TX_CFG_TX_ON_); + + netif_start_queue(dev); + return 0; +} + +/* Entry point for stopping the interface */ +static int smsc911x_stop(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + unsigned int temp; + + BUG_ON(!pdata->phy_dev); + + /* Disable all device interrupts */ + temp = smsc911x_reg_read(pdata, INT_CFG); + temp &= ~INT_CFG_IRQ_EN_; + smsc911x_reg_write(pdata, INT_CFG, temp); + + /* Stop Tx and Rx polling */ + netif_stop_queue(dev); + napi_disable(&pdata->napi); + + /* At this point all Rx and Tx activity is stopped */ + dev->stats.rx_dropped += smsc911x_reg_read(pdata, RX_DROP); + smsc911x_tx_update_txcounters(dev); + + /* Bring the PHY down */ + phy_stop(pdata->phy_dev); + + SMSC_TRACE(IFDOWN, "Interface stopped"); + return 0; +} + +/* Entry point for transmitting a packet */ +static int smsc911x_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + unsigned int freespace; + unsigned int tx_cmd_a; + unsigned int tx_cmd_b; + unsigned int temp; + u32 wrsz; + ulong bufp; + + freespace = smsc911x_reg_read(pdata, TX_FIFO_INF) & TX_FIFO_INF_TDFREE_; + + if (unlikely(freespace < TX_FIFO_LOW_THRESHOLD)) + SMSC_WARNING(TX_ERR, + "Tx data fifo low, space available: %d", freespace); + + /* Word alignment adjustment */ + tx_cmd_a = (u32)((ulong)skb->data & 0x03) << 16; + tx_cmd_a |= TX_CMD_A_FIRST_SEG_ | TX_CMD_A_LAST_SEG_; + tx_cmd_a |= (unsigned int)skb->len; + + tx_cmd_b = ((unsigned int)skb->len) << 16; + tx_cmd_b |= (unsigned int)skb->len; + + smsc911x_reg_write(pdata, TX_DATA_FIFO, tx_cmd_a); + smsc911x_reg_write(pdata, TX_DATA_FIFO, tx_cmd_b); + + bufp = (ulong)skb->data & (~0x3); + wrsz = (u32)skb->len + 3; + wrsz += (u32)((ulong)skb->data & 0x3); + wrsz >>= 2; + + smsc911x_tx_writefifo(pdata, (unsigned int *)bufp, wrsz); + freespace -= (skb->len + 32); + dev_kfree_skb(skb); + dev->trans_start = jiffies; + + if (unlikely(smsc911x_tx_get_txstatcount(pdata) >= 30)) + smsc911x_tx_update_txcounters(dev); + + if (freespace < TX_FIFO_LOW_THRESHOLD) { + netif_stop_queue(dev); + temp = smsc911x_reg_read(pdata, FIFO_INT); + temp &= 0x00FFFFFF; + temp |= 0x32000000; + smsc911x_reg_write(pdata, FIFO_INT, temp); + } + + return NETDEV_TX_OK; +} + +/* Entry point for getting status counters */ +static struct net_device_stats *smsc911x_get_stats(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + smsc911x_tx_update_txcounters(dev); + dev->stats.rx_dropped += smsc911x_reg_read(pdata, RX_DROP); + return &dev->stats; +} + +/* Entry point for setting addressing modes */ +static void smsc911x_set_multicast_list(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + unsigned long flags; + + if (dev->flags & IFF_PROMISC) { + /* Enabling promiscuous mode */ + pdata->set_bits_mask = MAC_CR_PRMS_; + pdata->clear_bits_mask = (MAC_CR_MCPAS_ | MAC_CR_HPFILT_); + pdata->hashhi = 0; + pdata->hashlo = 0; + } else if (dev->flags & IFF_ALLMULTI) { + /* Enabling all multicast mode */ + pdata->set_bits_mask = MAC_CR_MCPAS_; + pdata->clear_bits_mask = (MAC_CR_PRMS_ | MAC_CR_HPFILT_); + pdata->hashhi = 0; + pdata->hashlo = 0; + } else if (dev->mc_count > 0) { + /* Enabling specific multicast addresses */ + unsigned int hash_high = 0; + unsigned int hash_low = 0; + unsigned int count = 0; + struct dev_mc_list *mc_list = dev->mc_list; + + pdata->set_bits_mask = MAC_CR_HPFILT_; + pdata->clear_bits_mask = (MAC_CR_PRMS_ | MAC_CR_MCPAS_); + + while (mc_list) { + count++; + if ((mc_list->dmi_addrlen) == ETH_ALEN) { + unsigned int bitnum = + smsc911x_hash(mc_list->dmi_addr); + unsigned int mask = 0x01 << (bitnum & 0x1F); + if (bitnum & 0x20) + hash_high |= mask; + else + hash_low |= mask; + } else { + SMSC_WARNING(DRV, "dmi_addrlen != 6"); + } + mc_list = mc_list->next; + } + if (count != (unsigned int)dev->mc_count) + SMSC_WARNING(DRV, "mc_count != dev->mc_count"); + + pdata->hashhi = hash_high; + pdata->hashlo = hash_low; + } else { + /* Enabling local MAC address only */ + pdata->set_bits_mask = 0; + pdata->clear_bits_mask = + (MAC_CR_PRMS_ | MAC_CR_MCPAS_ | MAC_CR_HPFILT_); + pdata->hashhi = 0; + pdata->hashlo = 0; + } + + spin_lock_irqsave(&pdata->mac_lock, flags); + + if (pdata->generation <= 1) { + /* Older hardware revision - cannot change these flags while + * receiving data */ + if (!pdata->multicast_update_pending) { + unsigned int temp; + SMSC_TRACE(HW, "scheduling mcast update"); + pdata->multicast_update_pending = 1; + + /* Request the hardware to stop, then perform the + * update when we get an RX_STOP interrupt */ + smsc911x_reg_write(pdata, INT_STS, INT_STS_RXSTOP_INT_); + temp = smsc911x_reg_read(pdata, INT_EN); + temp |= INT_EN_RXSTOP_INT_EN_; + smsc911x_reg_write(pdata, INT_EN, temp); + + temp = smsc911x_mac_read(pdata, MAC_CR); + temp &= ~(MAC_CR_RXEN_); + smsc911x_mac_write(pdata, MAC_CR, temp); + } else { + /* There is another update pending, this should now + * use the newer values */ + } + } else { + /* Newer hardware revision - can write immediately */ + smsc911x_rx_multicast_update(pdata); + } + + spin_unlock_irqrestore(&pdata->mac_lock, flags); +} + +static irqreturn_t smsc911x_irqhandler(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + struct smsc911x_data *pdata = netdev_priv(dev); + u32 intsts = smsc911x_reg_read(pdata, INT_STS); + u32 inten = smsc911x_reg_read(pdata, INT_EN); + int serviced = IRQ_NONE; + u32 temp; + + if (unlikely(intsts & inten & INT_STS_SW_INT_)) { + temp = smsc911x_reg_read(pdata, INT_EN); + temp &= (~INT_EN_SW_INT_EN_); + smsc911x_reg_write(pdata, INT_EN, temp); + smsc911x_reg_write(pdata, INT_STS, INT_STS_SW_INT_); + pdata->software_irq_signal = 1; + smp_wmb(); + serviced = IRQ_HANDLED; + } + + if (unlikely(intsts & inten & INT_STS_RXSTOP_INT_)) { + /* Called when there is a multicast update scheduled and + * it is now safe to complete the update */ + SMSC_TRACE(INTR, "RX Stop interrupt"); + temp = smsc911x_reg_read(pdata, INT_EN); + temp &= (~INT_EN_RXSTOP_INT_EN_); + smsc911x_reg_write(pdata, INT_EN, temp); + smsc911x_reg_write(pdata, INT_STS, INT_STS_RXSTOP_INT_); + smsc911x_rx_multicast_update_workaround(pdata); + serviced = IRQ_HANDLED; + } + + if (intsts & inten & INT_STS_TDFA_) { + temp = smsc911x_reg_read(pdata, FIFO_INT); + temp |= FIFO_INT_TX_AVAIL_LEVEL_; + smsc911x_reg_write(pdata, FIFO_INT, temp); + smsc911x_reg_write(pdata, INT_STS, INT_STS_TDFA_); + netif_wake_queue(dev); + serviced = IRQ_HANDLED; + } + + if (unlikely(intsts & inten & INT_STS_RXE_)) { + SMSC_TRACE(INTR, "RX Error interrupt"); + smsc911x_reg_write(pdata, INT_STS, INT_STS_RXE_); + serviced = IRQ_HANDLED; + } + + if (likely(intsts & inten & INT_STS_RSFL_)) { + if (likely(netif_rx_schedule_prep(dev, &pdata->napi))) { + /* Disable Rx interrupts */ + temp = smsc911x_reg_read(pdata, INT_EN); + temp &= (~INT_EN_RSFL_EN_); + smsc911x_reg_write(pdata, INT_EN, temp); + /* Schedule a NAPI poll */ + __netif_rx_schedule(dev, &pdata->napi); + } else { + SMSC_WARNING(RX_ERR, + "netif_rx_schedule_prep failed"); + } + serviced = IRQ_HANDLED; + } + + return serviced; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +void smsc911x_poll_controller(struct net_device *dev) +{ + disable_irq(dev->irq); + smsc911x_irqhandler(0, dev); + enable_irq(dev->irq); +} +#endif /* CONFIG_NET_POLL_CONTROLLER */ + +/* Standard ioctls for mii-tool */ +static int smsc911x_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + + if (!netif_running(dev) || !pdata->phy_dev) + return -EINVAL; + + return phy_mii_ioctl(pdata->phy_dev, if_mii(ifr), cmd); +} + +static int +smsc911x_ethtool_getsettings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + + cmd->maxtxpkt = 1; + cmd->maxrxpkt = 1; + return phy_ethtool_gset(pdata->phy_dev, cmd); +} + +static int +smsc911x_ethtool_setsettings(struct net_device *dev, struct ethtool_cmd *cmd) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + + return phy_ethtool_sset(pdata->phy_dev, cmd); +} + +static void smsc911x_ethtool_getdrvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) +{ + strlcpy(info->driver, SMSC_CHIPNAME, sizeof(info->driver)); + strlcpy(info->version, SMSC_DRV_VERSION, sizeof(info->version)); + strlcpy(info->bus_info, dev->dev.parent->bus_id, + sizeof(info->bus_info)); +} + +static int smsc911x_ethtool_nwayreset(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + + return phy_start_aneg(pdata->phy_dev); +} + +static u32 smsc911x_ethtool_getmsglevel(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + return pdata->msg_enable; +} + +static void smsc911x_ethtool_setmsglevel(struct net_device *dev, u32 level) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + pdata->msg_enable = level; +} + +static int smsc911x_ethtool_getregslen(struct net_device *dev) +{ + return (((E2P_DATA - ID_REV) / 4 + 1) + (WUCSR - MAC_CR) + 1 + 32) * + sizeof(u32); +} + +static void +smsc911x_ethtool_getregs(struct net_device *dev, struct ethtool_regs *regs, + void *buf) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + struct phy_device *phy_dev = pdata->phy_dev; + unsigned long flags; + unsigned int i; + unsigned int j = 0; + u32 *data = buf; + + regs->version = pdata->idrev; + for (i = ID_REV; i <= E2P_DATA; i += (sizeof(u32))) + data[j++] = smsc911x_reg_read(pdata, i); + + for (i = MAC_CR; i <= WUCSR; i++) { + spin_lock_irqsave(&pdata->mac_lock, flags); + data[j++] = smsc911x_mac_read(pdata, i); + spin_unlock_irqrestore(&pdata->mac_lock, flags); + } + + for (i = 0; i <= 31; i++) + data[j++] = smsc911x_mii_read(phy_dev->bus, phy_dev->addr, i); +} + +static void smsc911x_eeprom_enable_access(struct smsc911x_data *pdata) +{ + unsigned int temp = smsc911x_reg_read(pdata, GPIO_CFG); + temp &= ~GPIO_CFG_EEPR_EN_; + smsc911x_reg_write(pdata, GPIO_CFG, temp); + msleep(1); +} + +static int smsc911x_eeprom_send_cmd(struct smsc911x_data *pdata, u32 op) +{ + int timeout = 100; + u32 e2cmd; + + SMSC_TRACE(DRV, "op 0x%08x", op); + if (smsc911x_reg_read(pdata, E2P_CMD) & E2P_CMD_EPC_BUSY_) { + SMSC_WARNING(DRV, "Busy at start"); + return -EBUSY; + } + + e2cmd = op | E2P_CMD_EPC_BUSY_; + smsc911x_reg_write(pdata, E2P_CMD, e2cmd); + + do { + msleep(1); + e2cmd = smsc911x_reg_read(pdata, E2P_CMD); + } while ((e2cmd & E2P_CMD_EPC_BUSY_) && (timeout--)); + + if (!timeout) { + SMSC_TRACE(DRV, "TIMED OUT"); + return -EAGAIN; + } + + if (e2cmd & E2P_CMD_EPC_TIMEOUT_) { + SMSC_TRACE(DRV, "Error occured during eeprom operation"); + return -EINVAL; + } + + return 0; +} + +static int smsc911x_eeprom_read_location(struct smsc911x_data *pdata, + u8 address, u8 *data) +{ + u32 op = E2P_CMD_EPC_CMD_READ_ | address; + int ret; + + SMSC_TRACE(DRV, "address 0x%x", address); + ret = smsc911x_eeprom_send_cmd(pdata, op); + + if (!ret) + data[address] = smsc911x_reg_read(pdata, E2P_DATA); + + return ret; +} + +static int smsc911x_eeprom_write_location(struct smsc911x_data *pdata, + u8 address, u8 data) +{ + u32 op = E2P_CMD_EPC_CMD_ERASE_ | address; + int ret; + + SMSC_TRACE(DRV, "address 0x%x, data 0x%x", address, data); + ret = smsc911x_eeprom_send_cmd(pdata, op); + + if (!ret) { + op = E2P_CMD_EPC_CMD_WRITE_ | address; + smsc911x_reg_write(pdata, E2P_DATA, (u32)data); + ret = smsc911x_eeprom_send_cmd(pdata, op); + } + + return ret; +} + +static int smsc911x_ethtool_get_eeprom_len(struct net_device *dev) +{ + return SMSC911X_EEPROM_SIZE; +} + +static int smsc911x_ethtool_get_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + u8 eeprom_data[SMSC911X_EEPROM_SIZE]; + int len; + int i; + + smsc911x_eeprom_enable_access(pdata); + + len = min(eeprom->len, SMSC911X_EEPROM_SIZE); + for (i = 0; i < len; i++) { + int ret = smsc911x_eeprom_read_location(pdata, i, eeprom_data); + if (ret < 0) { + eeprom->len = 0; + return ret; + } + } + + memcpy(data, &eeprom_data[eeprom->offset], len); + eeprom->len = len; + return 0; +} + +static int smsc911x_ethtool_set_eeprom(struct net_device *dev, + struct ethtool_eeprom *eeprom, u8 *data) +{ + int ret; + struct smsc911x_data *pdata = netdev_priv(dev); + + smsc911x_eeprom_enable_access(pdata); + smsc911x_eeprom_send_cmd(pdata, E2P_CMD_EPC_CMD_EWEN_); + ret = smsc911x_eeprom_write_location(pdata, eeprom->offset, *data); + smsc911x_eeprom_send_cmd(pdata, E2P_CMD_EPC_CMD_EWDS_); + + /* Single byte write, according to man page */ + eeprom->len = 1; + + return ret; +} + +static struct ethtool_ops smsc911x_ethtool_ops = { + .get_settings = smsc911x_ethtool_getsettings, + .set_settings = smsc911x_ethtool_setsettings, + .get_link = ethtool_op_get_link, + .get_drvinfo = smsc911x_ethtool_getdrvinfo, + .nway_reset = smsc911x_ethtool_nwayreset, + .get_msglevel = smsc911x_ethtool_getmsglevel, + .set_msglevel = smsc911x_ethtool_setmsglevel, + .get_regs_len = smsc911x_ethtool_getregslen, + .get_regs = smsc911x_ethtool_getregs, + .get_eeprom_len = smsc911x_ethtool_get_eeprom_len, + .get_eeprom = smsc911x_ethtool_get_eeprom, + .set_eeprom = smsc911x_ethtool_set_eeprom, +}; + +/* Initializing private device structures, only called from probe */ +static int __devinit smsc911x_init(struct net_device *dev) +{ + struct smsc911x_data *pdata = netdev_priv(dev); + unsigned int byte_test; + + SMSC_TRACE(PROBE, "Driver Parameters:"); + SMSC_TRACE(PROBE, "LAN base: 0x%08lX", + (unsigned long)pdata->ioaddr); + SMSC_TRACE(PROBE, "IRQ: %d", dev->irq); + SMSC_TRACE(PROBE, "PHY will be autodetected."); + +#if (!SMSC_CAN_USE_32BIT) + spin_lock_init(&pdata->dev_lock); +#endif + + if (pdata->ioaddr == 0) { + SMSC_WARNING(PROBE, "pdata->ioaddr: 0x00000000"); + return -ENODEV; + } + + /* Check byte ordering */ + byte_test = smsc911x_reg_read(pdata, BYTE_TEST); + SMSC_TRACE(PROBE, "BYTE_TEST: 0x%08X", byte_test); + if (byte_test == 0x43218765) { + SMSC_TRACE(PROBE, "BYTE_TEST looks swapped, " + "applying WORD_SWAP"); + smsc911x_reg_write(pdata, WORD_SWAP, 0xffffffff); + + /* 1 dummy read of BYTE_TEST is needed after a write to + * WORD_SWAP before its contents are valid */ + byte_test = smsc911x_reg_read(pdata, BYTE_TEST); + + byte_test = smsc911x_reg_read(pdata, BYTE_TEST); + } + + if (byte_test != 0x87654321) { + SMSC_WARNING(DRV, "BYTE_TEST: 0x%08X", byte_test); + if (((byte_test >> 16) & 0xFFFF) == (byte_test & 0xFFFF)) { + SMSC_WARNING(PROBE, + "top 16 bits equal to bottom 16 bits"); + SMSC_TRACE(PROBE, "This may mean the chip is set " + "for 32 bit while the bus is reading 16 bit"); + } + return -ENODEV; + } + + /* Default generation to zero (all workarounds apply) */ + pdata->generation = 0; + + pdata->idrev = smsc911x_reg_read(pdata, ID_REV); + switch (pdata->idrev & 0xFFFF0000) { + case 0x01180000: + case 0x01170000: + case 0x01160000: + case 0x01150000: + /* LAN911[5678] family */ + pdata->generation = pdata->idrev & 0x0000FFFF; + break; + + case 0x118A0000: + case 0x117A0000: + case 0x116A0000: + case 0x115A0000: + /* LAN921[5678] family */ + pdata->generation = 3; + break; + + case 0x92100000: + case 0x92110000: + case 0x92200000: + case 0x92210000: + /* LAN9210/LAN9211/LAN9220/LAN9221 */ + pdata->generation = 4; + break; + + default: + SMSC_WARNING(PROBE, "LAN911x not identified, idrev: 0x%08X", + pdata->idrev); + return -ENODEV; + } + + SMSC_TRACE(PROBE, "LAN911x identified, idrev: 0x%08X, generation: %d", + pdata->idrev, pdata->generation); + + if (pdata->generation == 0) + SMSC_WARNING(PROBE, + "This driver is not intended for this chip revision"); + + /* Reset the LAN911x */ + if (smsc911x_soft_reset(pdata)) + return -ENODEV; + + /* Disable all interrupt sources until we bring the device up */ + smsc911x_reg_write(pdata, INT_EN, 0); + + ether_setup(dev); + dev->open = smsc911x_open; + dev->stop = smsc911x_stop; + dev->hard_start_xmit = smsc911x_hard_start_xmit; + dev->get_stats = smsc911x_get_stats; + dev->set_multicast_list = smsc911x_set_multicast_list; + dev->flags |= IFF_MULTICAST; + dev->do_ioctl = smsc911x_do_ioctl; + netif_napi_add(dev, &pdata->napi, smsc911x_poll, SMSC_NAPI_WEIGHT); + dev->ethtool_ops = &smsc911x_ethtool_ops; + +#ifdef CONFIG_NET_POLL_CONTROLLER + dev->poll_controller = smsc911x_poll_controller; +#endif /* CONFIG_NET_POLL_CONTROLLER */ + + return 0; +} + +static int __devexit smsc911x_drv_remove(struct platform_device *pdev) +{ + struct net_device *dev; + struct smsc911x_data *pdata; + struct resource *res; + + dev = platform_get_drvdata(pdev); + BUG_ON(!dev); + pdata = netdev_priv(dev); + BUG_ON(!pdata); + BUG_ON(!pdata->ioaddr); + BUG_ON(!pdata->phy_dev); + + SMSC_TRACE(IFDOWN, "Stopping driver."); + + phy_disconnect(pdata->phy_dev); + pdata->phy_dev = NULL; + mdiobus_unregister(pdata->mii_bus); + mdiobus_free(pdata->mii_bus); + + platform_set_drvdata(pdev, NULL); + unregister_netdev(dev); + free_irq(dev->irq, dev); + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "smsc911x-memory"); + if (!res) + platform_get_resource(pdev, IORESOURCE_MEM, 0); + + release_mem_region(res->start, res->end - res->start); + + iounmap(pdata->ioaddr); + + free_netdev(dev); + + return 0; +} + +static int __devinit smsc911x_drv_probe(struct platform_device *pdev) +{ + struct net_device *dev; + struct smsc911x_data *pdata; + struct resource *res; + unsigned int intcfg = 0; + int res_size; + int retval; + DECLARE_MAC_BUF(mac); + + pr_info("%s: Driver version %s.\n", SMSC_CHIPNAME, SMSC_DRV_VERSION); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "smsc911x-memory"); + if (!res) + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!res) { + pr_warning("%s: Could not allocate resource.\n", + SMSC_CHIPNAME); + retval = -ENODEV; + goto out_0; + } + res_size = res->end - res->start; + + if (!request_mem_region(res->start, res_size, SMSC_CHIPNAME)) { + retval = -EBUSY; + goto out_0; + } + + dev = alloc_etherdev(sizeof(struct smsc911x_data)); + if (!dev) { + pr_warning("%s: Could not allocate device.\n", SMSC_CHIPNAME); + retval = -ENOMEM; + goto out_release_io_1; + } + + SET_NETDEV_DEV(dev, &pdev->dev); + + pdata = netdev_priv(dev); + + dev->irq = platform_get_irq(pdev, 0); + pdata->ioaddr = ioremap_nocache(res->start, res_size); + + /* copy config parameters across if present, otherwise pdata + * defaults to zeros */ + if (pdev->dev.platform_data) { + struct smsc911x_platform_config *config = + pdev->dev.platform_data; + pdata->irq_polarity = config->irq_polarity; + pdata->irq_type = config->irq_type; + pdata->phy_interface = config->phy_interface; + } + + pdata->dev = dev; + pdata->msg_enable = ((1 << debug) - 1); + + if (pdata->ioaddr == NULL) { + SMSC_WARNING(PROBE, + "Error smsc911x base address invalid"); + retval = -ENOMEM; + goto out_free_netdev_2; + } + + retval = smsc911x_init(dev); + if (retval < 0) + goto out_unmap_io_3; + + /* configure irq polarity and type before connecting isr */ + if (pdata->irq_polarity == SMSC911X_IRQ_POLARITY_ACTIVE_HIGH) + intcfg |= INT_CFG_IRQ_POL_; + + if (pdata->irq_type == SMSC911X_IRQ_TYPE_PUSH_PULL) + intcfg |= INT_CFG_IRQ_TYPE_; + + smsc911x_reg_write(pdata, INT_CFG, intcfg); + + /* Ensure interrupts are globally disabled before connecting ISR */ + smsc911x_reg_write(pdata, INT_EN, 0); + smsc911x_reg_write(pdata, INT_STS, 0xFFFFFFFF); + + retval = request_irq(dev->irq, smsc911x_irqhandler, IRQF_DISABLED, + SMSC_CHIPNAME, dev); + if (retval) { + SMSC_WARNING(PROBE, + "Unable to claim requested irq: %d", dev->irq); + goto out_unmap_io_3; + } + + platform_set_drvdata(pdev, dev); + + retval = register_netdev(dev); + if (retval) { + SMSC_WARNING(PROBE, + "Error %i registering device", retval); + goto out_unset_drvdata_4; + } else { + SMSC_TRACE(PROBE, "Network interface: \"%s\"", dev->name); + } + + spin_lock_init(&pdata->mac_lock); + + retval = smsc911x_mii_init(pdev, dev); + if (retval) { + SMSC_WARNING(PROBE, + "Error %i initialising mii", retval); + goto out_unregister_netdev_5; + } + + spin_lock_irq(&pdata->mac_lock); + + /* Check if mac address has been specified when bringing interface up */ + if (is_valid_ether_addr(dev->dev_addr)) { + smsc911x_set_mac_address(pdata, dev->dev_addr); + SMSC_TRACE(PROBE, "MAC Address is specified by configuration"); + } else { + /* Try reading mac address from device. if EEPROM is present + * it will already have been set */ + u32 mac_high16 = smsc911x_mac_read(pdata, ADDRH); + u32 mac_low32 = smsc911x_mac_read(pdata, ADDRL); + dev->dev_addr[0] = (u8)(mac_low32); + dev->dev_addr[1] = (u8)(mac_low32 >> 8); + dev->dev_addr[2] = (u8)(mac_low32 >> 16); + dev->dev_addr[3] = (u8)(mac_low32 >> 24); + dev->dev_addr[4] = (u8)(mac_high16); + dev->dev_addr[5] = (u8)(mac_high16 >> 8); + + if (is_valid_ether_addr(dev->dev_addr)) { + /* eeprom values are valid so use them */ + SMSC_TRACE(PROBE, + "Mac Address is read from LAN911x EEPROM"); + } else { + /* eeprom values are invalid, generate random MAC */ + random_ether_addr(dev->dev_addr); + smsc911x_set_mac_address(pdata, dev->dev_addr); + SMSC_TRACE(PROBE, + "MAC Address is set to random_ether_addr"); + } + } + + spin_unlock_irq(&pdata->mac_lock); + + dev_info(&dev->dev, "MAC Address: %s\n", + print_mac(mac, dev->dev_addr)); + + return 0; + +out_unregister_netdev_5: + unregister_netdev(dev); +out_unset_drvdata_4: + platform_set_drvdata(pdev, NULL); + free_irq(dev->irq, dev); +out_unmap_io_3: + iounmap(pdata->ioaddr); +out_free_netdev_2: + free_netdev(dev); +out_release_io_1: + release_mem_region(res->start, res->end - res->start); +out_0: + return retval; +} + +static struct platform_driver smsc911x_driver = { + .probe = smsc911x_drv_probe, + .remove = smsc911x_drv_remove, + .driver = { + .name = SMSC_CHIPNAME, + }, +}; + +/* Entry point for loading the module */ +static int __init smsc911x_init_module(void) +{ + return platform_driver_register(&smsc911x_driver); +} + +/* entry point for unloading the module */ +static void __exit smsc911x_cleanup_module(void) +{ + platform_driver_unregister(&smsc911x_driver); +} + +module_init(smsc911x_init_module); +module_exit(smsc911x_cleanup_module); diff --git a/drivers/net/smsc911x.h b/drivers/net/smsc911x.h new file mode 100644 index 000000000000..feb36de274ca --- /dev/null +++ b/drivers/net/smsc911x.h @@ -0,0 +1,394 @@ +/*************************************************************************** + * + * Copyright (C) 2004-2008 SMSC + * Copyright (C) 2005-2008 ARM + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + ***************************************************************************/ +#ifndef __SMSC911X_H__ +#define __SMSC911X_H__ + +#define SMSC_CAN_USE_32BIT 1 +#define TX_FIFO_LOW_THRESHOLD ((u32)1600) +#define SMSC911X_EEPROM_SIZE ((u32)7) +#define USE_DEBUG 0 + +/* This is the maximum number of packets to be received every + * NAPI poll */ +#define SMSC_NAPI_WEIGHT 16 + +/* implements a PHY loopback test at initialisation time, to ensure a packet + * can be succesfully looped back */ +#define USE_PHY_WORK_AROUND + +#define DPRINTK(nlevel, klevel, fmt, args...) \ + ((void)((NETIF_MSG_##nlevel & pdata->msg_enable) && \ + printk(KERN_##klevel "%s: %s: " fmt "\n", \ + pdata->dev->name, __func__, ## args))) + +#if USE_DEBUG >= 1 +#define SMSC_WARNING(nlevel, fmt, args...) \ + DPRINTK(nlevel, WARNING, fmt, ## args) +#else +#define SMSC_WARNING(nlevel, fmt, args...) \ + ({ do {} while (0); 0; }) +#endif + +#if USE_DEBUG >= 2 +#define SMSC_TRACE(nlevel, fmt, args...) \ + DPRINTK(nlevel, INFO, fmt, ## args) +#else +#define SMSC_TRACE(nlevel, fmt, args...) \ + ({ do {} while (0); 0; }) +#endif + +#ifdef CONFIG_DEBUG_SPINLOCK +#define SMSC_ASSERT_MAC_LOCK(pdata) \ + WARN_ON(!spin_is_locked(&pdata->mac_lock)) +#else +#define SMSC_ASSERT_MAC_LOCK(pdata) do {} while (0) +#endif /* CONFIG_DEBUG_SPINLOCK */ + +#define FLOW_CTRL_TX (1) +#define FLOW_CTRL_RX (2) + +/* SMSC911x registers and bitfields */ +#define RX_DATA_FIFO 0x00 + +#define TX_DATA_FIFO 0x20 +#define TX_CMD_A_ON_COMP_ 0x80000000 +#define TX_CMD_A_BUF_END_ALGN_ 0x03000000 +#define TX_CMD_A_4_BYTE_ALGN_ 0x00000000 +#define TX_CMD_A_16_BYTE_ALGN_ 0x01000000 +#define TX_CMD_A_32_BYTE_ALGN_ 0x02000000 +#define TX_CMD_A_DATA_OFFSET_ 0x001F0000 +#define TX_CMD_A_FIRST_SEG_ 0x00002000 +#define TX_CMD_A_LAST_SEG_ 0x00001000 +#define TX_CMD_A_BUF_SIZE_ 0x000007FF +#define TX_CMD_B_PKT_TAG_ 0xFFFF0000 +#define TX_CMD_B_ADD_CRC_DISABLE_ 0x00002000 +#define TX_CMD_B_DISABLE_PADDING_ 0x00001000 +#define TX_CMD_B_PKT_BYTE_LENGTH_ 0x000007FF + +#define RX_STATUS_FIFO 0x40 +#define RX_STS_ES_ 0x00008000 +#define RX_STS_MCAST_ 0x00000400 + +#define RX_STATUS_FIFO_PEEK 0x44 + +#define TX_STATUS_FIFO 0x48 +#define TX_STS_ES_ 0x00008000 + +#define TX_STATUS_FIFO_PEEK 0x4C + +#define ID_REV 0x50 +#define ID_REV_CHIP_ID_ 0xFFFF0000 +#define ID_REV_REV_ID_ 0x0000FFFF + +#define INT_CFG 0x54 +#define INT_CFG_INT_DEAS_ 0xFF000000 +#define INT_CFG_INT_DEAS_CLR_ 0x00004000 +#define INT_CFG_INT_DEAS_STS_ 0x00002000 +#define INT_CFG_IRQ_INT_ 0x00001000 +#define INT_CFG_IRQ_EN_ 0x00000100 +#define INT_CFG_IRQ_POL_ 0x00000010 +#define INT_CFG_IRQ_TYPE_ 0x00000001 + +#define INT_STS 0x58 +#define INT_STS_SW_INT_ 0x80000000 +#define INT_STS_TXSTOP_INT_ 0x02000000 +#define INT_STS_RXSTOP_INT_ 0x01000000 +#define INT_STS_RXDFH_INT_ 0x00800000 +#define INT_STS_RXDF_INT_ 0x00400000 +#define INT_STS_TX_IOC_ 0x00200000 +#define INT_STS_RXD_INT_ 0x00100000 +#define INT_STS_GPT_INT_ 0x00080000 +#define INT_STS_PHY_INT_ 0x00040000 +#define INT_STS_PME_INT_ 0x00020000 +#define INT_STS_TXSO_ 0x00010000 +#define INT_STS_RWT_ 0x00008000 +#define INT_STS_RXE_ 0x00004000 +#define INT_STS_TXE_ 0x00002000 +#define INT_STS_TDFU_ 0x00000800 +#define INT_STS_TDFO_ 0x00000400 +#define INT_STS_TDFA_ 0x00000200 +#define INT_STS_TSFF_ 0x00000100 +#define INT_STS_TSFL_ 0x00000080 +#define INT_STS_RXDF_ 0x00000040 +#define INT_STS_RDFL_ 0x00000020 +#define INT_STS_RSFF_ 0x00000010 +#define INT_STS_RSFL_ 0x00000008 +#define INT_STS_GPIO2_INT_ 0x00000004 +#define INT_STS_GPIO1_INT_ 0x00000002 +#define INT_STS_GPIO0_INT_ 0x00000001 + +#define INT_EN 0x5C +#define INT_EN_SW_INT_EN_ 0x80000000 +#define INT_EN_TXSTOP_INT_EN_ 0x02000000 +#define INT_EN_RXSTOP_INT_EN_ 0x01000000 +#define INT_EN_RXDFH_INT_EN_ 0x00800000 +#define INT_EN_TIOC_INT_EN_ 0x00200000 +#define INT_EN_RXD_INT_EN_ 0x00100000 +#define INT_EN_GPT_INT_EN_ 0x00080000 +#define INT_EN_PHY_INT_EN_ 0x00040000 +#define INT_EN_PME_INT_EN_ 0x00020000 +#define INT_EN_TXSO_EN_ 0x00010000 +#define INT_EN_RWT_EN_ 0x00008000 +#define INT_EN_RXE_EN_ 0x00004000 +#define INT_EN_TXE_EN_ 0x00002000 +#define INT_EN_TDFU_EN_ 0x00000800 +#define INT_EN_TDFO_EN_ 0x00000400 +#define INT_EN_TDFA_EN_ 0x00000200 +#define INT_EN_TSFF_EN_ 0x00000100 +#define INT_EN_TSFL_EN_ 0x00000080 +#define INT_EN_RXDF_EN_ 0x00000040 +#define INT_EN_RDFL_EN_ 0x00000020 +#define INT_EN_RSFF_EN_ 0x00000010 +#define INT_EN_RSFL_EN_ 0x00000008 +#define INT_EN_GPIO2_INT_ 0x00000004 +#define INT_EN_GPIO1_INT_ 0x00000002 +#define INT_EN_GPIO0_INT_ 0x00000001 + +#define BYTE_TEST 0x64 + +#define FIFO_INT 0x68 +#define FIFO_INT_TX_AVAIL_LEVEL_ 0xFF000000 +#define FIFO_INT_TX_STS_LEVEL_ 0x00FF0000 +#define FIFO_INT_RX_AVAIL_LEVEL_ 0x0000FF00 +#define FIFO_INT_RX_STS_LEVEL_ 0x000000FF + +#define RX_CFG 0x6C +#define RX_CFG_RX_END_ALGN_ 0xC0000000 +#define RX_CFG_RX_END_ALGN4_ 0x00000000 +#define RX_CFG_RX_END_ALGN16_ 0x40000000 +#define RX_CFG_RX_END_ALGN32_ 0x80000000 +#define RX_CFG_RX_DMA_CNT_ 0x0FFF0000 +#define RX_CFG_RX_DUMP_ 0x00008000 +#define RX_CFG_RXDOFF_ 0x00001F00 + +#define TX_CFG 0x70 +#define TX_CFG_TXS_DUMP_ 0x00008000 +#define TX_CFG_TXD_DUMP_ 0x00004000 +#define TX_CFG_TXSAO_ 0x00000004 +#define TX_CFG_TX_ON_ 0x00000002 +#define TX_CFG_STOP_TX_ 0x00000001 + +#define HW_CFG 0x74 +#define HW_CFG_TTM_ 0x00200000 +#define HW_CFG_SF_ 0x00100000 +#define HW_CFG_TX_FIF_SZ_ 0x000F0000 +#define HW_CFG_TR_ 0x00003000 +#define HW_CFG_SRST_ 0x00000001 + +/* only available on 115/117 */ +#define HW_CFG_PHY_CLK_SEL_ 0x00000060 +#define HW_CFG_PHY_CLK_SEL_INT_PHY_ 0x00000000 +#define HW_CFG_PHY_CLK_SEL_EXT_PHY_ 0x00000020 +#define HW_CFG_PHY_CLK_SEL_CLK_DIS_ 0x00000040 +#define HW_CFG_SMI_SEL_ 0x00000010 +#define HW_CFG_EXT_PHY_DET_ 0x00000008 +#define HW_CFG_EXT_PHY_EN_ 0x00000004 +#define HW_CFG_SRST_TO_ 0x00000002 + +/* only available on 116/118 */ +#define HW_CFG_32_16_BIT_MODE_ 0x00000004 + +#define RX_DP_CTRL 0x78 +#define RX_DP_CTRL_RX_FFWD_ 0x80000000 + +#define RX_FIFO_INF 0x7C +#define RX_FIFO_INF_RXSUSED_ 0x00FF0000 +#define RX_FIFO_INF_RXDUSED_ 0x0000FFFF + +#define TX_FIFO_INF 0x80 +#define TX_FIFO_INF_TSUSED_ 0x00FF0000 +#define TX_FIFO_INF_TDFREE_ 0x0000FFFF + +#define PMT_CTRL 0x84 +#define PMT_CTRL_PM_MODE_ 0x00003000 +#define PMT_CTRL_PM_MODE_D0_ 0x00000000 +#define PMT_CTRL_PM_MODE_D1_ 0x00001000 +#define PMT_CTRL_PM_MODE_D2_ 0x00002000 +#define PMT_CTRL_PM_MODE_D3_ 0x00003000 +#define PMT_CTRL_PHY_RST_ 0x00000400 +#define PMT_CTRL_WOL_EN_ 0x00000200 +#define PMT_CTRL_ED_EN_ 0x00000100 +#define PMT_CTRL_PME_TYPE_ 0x00000040 +#define PMT_CTRL_WUPS_ 0x00000030 +#define PMT_CTRL_WUPS_NOWAKE_ 0x00000000 +#define PMT_CTRL_WUPS_ED_ 0x00000010 +#define PMT_CTRL_WUPS_WOL_ 0x00000020 +#define PMT_CTRL_WUPS_MULTI_ 0x00000030 +#define PMT_CTRL_PME_IND_ 0x00000008 +#define PMT_CTRL_PME_POL_ 0x00000004 +#define PMT_CTRL_PME_EN_ 0x00000002 +#define PMT_CTRL_READY_ 0x00000001 + +#define GPIO_CFG 0x88 +#define GPIO_CFG_LED3_EN_ 0x40000000 +#define GPIO_CFG_LED2_EN_ 0x20000000 +#define GPIO_CFG_LED1_EN_ 0x10000000 +#define GPIO_CFG_GPIO2_INT_POL_ 0x04000000 +#define GPIO_CFG_GPIO1_INT_POL_ 0x02000000 +#define GPIO_CFG_GPIO0_INT_POL_ 0x01000000 +#define GPIO_CFG_EEPR_EN_ 0x00700000 +#define GPIO_CFG_GPIOBUF2_ 0x00040000 +#define GPIO_CFG_GPIOBUF1_ 0x00020000 +#define GPIO_CFG_GPIOBUF0_ 0x00010000 +#define GPIO_CFG_GPIODIR2_ 0x00000400 +#define GPIO_CFG_GPIODIR1_ 0x00000200 +#define GPIO_CFG_GPIODIR0_ 0x00000100 +#define GPIO_CFG_GPIOD4_ 0x00000020 +#define GPIO_CFG_GPIOD3_ 0x00000010 +#define GPIO_CFG_GPIOD2_ 0x00000004 +#define GPIO_CFG_GPIOD1_ 0x00000002 +#define GPIO_CFG_GPIOD0_ 0x00000001 + +#define GPT_CFG 0x8C +#define GPT_CFG_TIMER_EN_ 0x20000000 +#define GPT_CFG_GPT_LOAD_ 0x0000FFFF + +#define GPT_CNT 0x90 +#define GPT_CNT_GPT_CNT_ 0x0000FFFF + +#define WORD_SWAP 0x98 + +#define FREE_RUN 0x9C + +#define RX_DROP 0xA0 + +#define MAC_CSR_CMD 0xA4 +#define MAC_CSR_CMD_CSR_BUSY_ 0x80000000 +#define MAC_CSR_CMD_R_NOT_W_ 0x40000000 +#define MAC_CSR_CMD_CSR_ADDR_ 0x000000FF + +#define MAC_CSR_DATA 0xA8 + +#define AFC_CFG 0xAC +#define AFC_CFG_AFC_HI_ 0x00FF0000 +#define AFC_CFG_AFC_LO_ 0x0000FF00 +#define AFC_CFG_BACK_DUR_ 0x000000F0 +#define AFC_CFG_FCMULT_ 0x00000008 +#define AFC_CFG_FCBRD_ 0x00000004 +#define AFC_CFG_FCADD_ 0x00000002 +#define AFC_CFG_FCANY_ 0x00000001 + +#define E2P_CMD 0xB0 +#define E2P_CMD_EPC_BUSY_ 0x80000000 +#define E2P_CMD_EPC_CMD_ 0x70000000 +#define E2P_CMD_EPC_CMD_READ_ 0x00000000 +#define E2P_CMD_EPC_CMD_EWDS_ 0x10000000 +#define E2P_CMD_EPC_CMD_EWEN_ 0x20000000 +#define E2P_CMD_EPC_CMD_WRITE_ 0x30000000 +#define E2P_CMD_EPC_CMD_WRAL_ 0x40000000 +#define E2P_CMD_EPC_CMD_ERASE_ 0x50000000 +#define E2P_CMD_EPC_CMD_ERAL_ 0x60000000 +#define E2P_CMD_EPC_CMD_RELOAD_ 0x70000000 +#define E2P_CMD_EPC_TIMEOUT_ 0x00000200 +#define E2P_CMD_MAC_ADDR_LOADED_ 0x00000100 +#define E2P_CMD_EPC_ADDR_ 0x000000FF + +#define E2P_DATA 0xB4 +#define E2P_DATA_EEPROM_DATA_ 0x000000FF +#define LAN_REGISTER_EXTENT 0x00000100 + +/* + * MAC Control and Status Register (Indirect Address) + * Offset (through the MAC_CSR CMD and DATA port) + */ +#define MAC_CR 0x01 +#define MAC_CR_RXALL_ 0x80000000 +#define MAC_CR_HBDIS_ 0x10000000 +#define MAC_CR_RCVOWN_ 0x00800000 +#define MAC_CR_LOOPBK_ 0x00200000 +#define MAC_CR_FDPX_ 0x00100000 +#define MAC_CR_MCPAS_ 0x00080000 +#define MAC_CR_PRMS_ 0x00040000 +#define MAC_CR_INVFILT_ 0x00020000 +#define MAC_CR_PASSBAD_ 0x00010000 +#define MAC_CR_HFILT_ 0x00008000 +#define MAC_CR_HPFILT_ 0x00002000 +#define MAC_CR_LCOLL_ 0x00001000 +#define MAC_CR_BCAST_ 0x00000800 +#define MAC_CR_DISRTY_ 0x00000400 +#define MAC_CR_PADSTR_ 0x00000100 +#define MAC_CR_BOLMT_MASK_ 0x000000C0 +#define MAC_CR_DFCHK_ 0x00000020 +#define MAC_CR_TXEN_ 0x00000008 +#define MAC_CR_RXEN_ 0x00000004 + +#define ADDRH 0x02 + +#define ADDRL 0x03 + +#define HASHH 0x04 + +#define HASHL 0x05 + +#define MII_ACC 0x06 +#define MII_ACC_PHY_ADDR_ 0x0000F800 +#define MII_ACC_MIIRINDA_ 0x000007C0 +#define MII_ACC_MII_WRITE_ 0x00000002 +#define MII_ACC_MII_BUSY_ 0x00000001 + +#define MII_DATA 0x07 + +#define FLOW 0x08 +#define FLOW_FCPT_ 0xFFFF0000 +#define FLOW_FCPASS_ 0x00000004 +#define FLOW_FCEN_ 0x00000002 +#define FLOW_FCBSY_ 0x00000001 + +#define VLAN1 0x09 + +#define VLAN2 0x0A + +#define WUFF 0x0B + +#define WUCSR 0x0C +#define WUCSR_GUE_ 0x00000200 +#define WUCSR_WUFR_ 0x00000040 +#define WUCSR_MPR_ 0x00000020 +#define WUCSR_WAKE_EN_ 0x00000004 +#define WUCSR_MPEN_ 0x00000002 + +/* + * Phy definitions (vendor-specific) + */ +#define LAN9118_PHY_ID 0x00C0001C + +#define MII_INTSTS 0x1D + +#define MII_INTMSK 0x1E +#define PHY_INTMSK_AN_RCV_ (1 << 1) +#define PHY_INTMSK_PDFAULT_ (1 << 2) +#define PHY_INTMSK_AN_ACK_ (1 << 3) +#define PHY_INTMSK_LNKDOWN_ (1 << 4) +#define PHY_INTMSK_RFAULT_ (1 << 5) +#define PHY_INTMSK_AN_COMP_ (1 << 6) +#define PHY_INTMSK_ENERGYON_ (1 << 7) +#define PHY_INTMSK_DEFAULT_ (PHY_INTMSK_ENERGYON_ | \ + PHY_INTMSK_AN_COMP_ | \ + PHY_INTMSK_RFAULT_ | \ + PHY_INTMSK_LNKDOWN_) + +#define ADVERTISE_PAUSE_ALL (ADVERTISE_PAUSE_CAP | \ + ADVERTISE_PAUSE_ASYM) + +#define LPA_PAUSE_ALL (LPA_PAUSE_CAP | \ + LPA_PAUSE_ASYM) + +#endif /* __SMSC911X_H__ */ diff --git a/include/linux/smsc911x.h b/include/linux/smsc911x.h new file mode 100644 index 000000000000..47c4ffd10dbb --- /dev/null +++ b/include/linux/smsc911x.h @@ -0,0 +1,42 @@ +/*************************************************************************** + * + * Copyright (C) 2004-2008 SMSC + * Copyright (C) 2005-2008 ARM + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version 2 + * of the License, or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + * + ***************************************************************************/ +#ifndef __LINUX_SMSC911X_H__ +#define __LINUX_SMSC911X_H__ + +#include + +/* platform_device configuration data, should be assigned to + * the platform_device's dev.platform_data */ +struct smsc911x_platform_config { + unsigned int irq_polarity; + unsigned int irq_type; + phy_interface_t phy_interface; +}; + +/* Constants for platform_device irq polarity configuration */ +#define SMSC911X_IRQ_POLARITY_ACTIVE_LOW 0 +#define SMSC911X_IRQ_POLARITY_ACTIVE_HIGH 1 + +/* Constants for platform_device irq type configuration */ +#define SMSC911X_IRQ_TYPE_OPEN_DRAIN 0 +#define SMSC911X_IRQ_TYPE_PUSH_PULL 1 + +#endif /* __LINUX_SMSC911X_H__ */ From a8272061fe533f6d0261b38c58c93bd0855baebe Mon Sep 17 00:00:00 2001 From: Komuro Date: Mon, 3 Nov 2008 10:56:04 +0900 Subject: [PATCH 11/11] fmvj18x_cs: write interrupt ack bit for lan and modem to work simultaneously. Write interrupt ack bit in fjn_interrupt for lan and modem to work simultaneously. Signed-off-by: Komuro Signed-off-by: Jeff Garzik --- drivers/net/pcmcia/fmvj18x_cs.c | 73 ++++++++++++++++++++++++--------- 1 file changed, 54 insertions(+), 19 deletions(-) diff --git a/drivers/net/pcmcia/fmvj18x_cs.c b/drivers/net/pcmcia/fmvj18x_cs.c index e4f8fe3c5dae..69dcfbbabe82 100644 --- a/drivers/net/pcmcia/fmvj18x_cs.c +++ b/drivers/net/pcmcia/fmvj18x_cs.c @@ -125,6 +125,7 @@ typedef struct local_info_t { u_short tx_queue_len; cardtype_t cardtype; u_short sent; + u_char __iomem *base; } local_info_t; #define MC_FILTERBREAK 64 @@ -242,6 +243,7 @@ static int fmvj18x_probe(struct pcmcia_device *link) lp = netdev_priv(dev); link->priv = dev; lp->p_dev = link; + lp->base = NULL; /* The io structure describes IO port mapping */ link->io.NumPorts1 = 32; @@ -442,8 +444,10 @@ static int fmvj18x_config(struct pcmcia_device *link) dev->irq = link->irq.AssignedIRQ; dev->base_addr = link->io.BasePort1; - if (link->io.BasePort2 != 0) - fmvj18x_setup_mfc(link); + if (link->io.BasePort2 != 0) { + ret = fmvj18x_setup_mfc(link); + if (ret != 0) goto failed; + } ioaddr = dev->base_addr; @@ -610,10 +614,10 @@ static int fmvj18x_setup_mfc(struct pcmcia_device *link) { win_req_t req; memreq_t mem; - u_char __iomem *base; - int i, j; + int i; struct net_device *dev = link->priv; unsigned int ioaddr; + local_info_t *lp = netdev_priv(dev); /* Allocate a small memory window */ req.Attributes = WIN_DATA_WIDTH_8|WIN_MEMORY_TYPE_AM|WIN_ENABLE; @@ -625,25 +629,32 @@ static int fmvj18x_setup_mfc(struct pcmcia_device *link) return -1; } - base = ioremap(req.Base, req.Size); + lp->base = ioremap(req.Base, req.Size); + if (lp->base == NULL) { + printk(KERN_NOTICE "fmvj18x_cs: ioremap failed\n"); + return -1; + } + mem.Page = 0; mem.CardOffset = 0; - pcmcia_map_mem_page(link->win, &mem); - + i = pcmcia_map_mem_page(link->win, &mem); + if (i != 0) { + iounmap(lp->base); + lp->base = NULL; + cs_error(link, MapMemPage, i); + return -1; + } + ioaddr = dev->base_addr; - writeb(0x47, base+0x800); /* Config Option Register of LAN */ - writeb(0x0, base+0x802); /* Config and Status Register */ + writeb(0x47, lp->base+0x800); /* Config Option Register of LAN */ + writeb(0x0, lp->base+0x802); /* Config and Status Register */ - writeb(ioaddr & 0xff, base+0x80a); /* I/O Base(Low) of LAN */ - writeb((ioaddr >> 8) & 0xff, base+0x80c); /* I/O Base(High) of LAN */ + writeb(ioaddr & 0xff, lp->base+0x80a); /* I/O Base(Low) of LAN */ + writeb((ioaddr >> 8) & 0xff, lp->base+0x80c); /* I/O Base(High) of LAN */ - writeb(0x45, base+0x820); /* Config Option Register of Modem */ - writeb(0x8, base+0x822); /* Config and Status Register */ + writeb(0x45, lp->base+0x820); /* Config Option Register of Modem */ + writeb(0x8, lp->base+0x822); /* Config and Status Register */ - iounmap(base); - j = pcmcia_release_window(link->win); - if (j != 0) - cs_error(link, ReleaseWindow, j); return 0; } @@ -651,8 +662,25 @@ static int fmvj18x_setup_mfc(struct pcmcia_device *link) static void fmvj18x_release(struct pcmcia_device *link) { - DEBUG(0, "fmvj18x_release(0x%p)\n", link); - pcmcia_disable_device(link); + + struct net_device *dev = link->priv; + local_info_t *lp = netdev_priv(dev); + u_char __iomem *tmp; + int j; + + DEBUG(0, "fmvj18x_release(0x%p)\n", link); + + if (lp->base != NULL) { + tmp = lp->base; + lp->base = NULL; /* set NULL before iounmap */ + iounmap(tmp); + j = pcmcia_release_window(link->win); + if (j != 0) + cs_error(link, ReleaseWindow, j); + } + + pcmcia_disable_device(link); + } static int fmvj18x_suspend(struct pcmcia_device *link) @@ -783,6 +811,13 @@ static irqreturn_t fjn_interrupt(int dummy, void *dev_id) outb(D_TX_INTR, ioaddr + TX_INTR); outb(D_RX_INTR, ioaddr + RX_INTR); + + if (lp->base != NULL) { + /* Ack interrupt for multifunction card */ + writeb(0x01, lp->base+0x802); + writeb(0x09, lp->base+0x822); + } + return IRQ_HANDLED; } /* fjn_interrupt */