From 617caccebe451716df21c069b079d5936ed7b0f3 Mon Sep 17 00:00:00 2001 From: AnilKumar Ch Date: Wed, 23 May 2012 17:45:09 +0530 Subject: can: c_can: fix "BUG! echo_skb is occupied!" during transmit This patch fixes an issue with transmit routine, which causes "can_put_echo_skb: BUG! echo_skb is occupied!" message when using "cansequence -p" on D_CAN controller. In c_can driver, while transmitting packets tx_echo flag holds the no of can frames put for transmission into the hardware. As the comment above c_can_do_tx() indicates, if we find any packet which is not transmitted then we should stop looking for more. In the current implementation this is not taken care of causing the said message. Also, fix the condition used to find if the packet is transmitted or not. Current code skips the first tx message object and ends up checking one extra invalid object. While at it, fix the comment on top of c_can_do_tx() to use the terminology "packet" instead of "package" since it is more standard. Cc: stable@kernel.org # 2.6.39+ Signed-off-by: AnilKumar Ch Acked-by: Wolfgang Grandegger Signed-off-by: Marc Kleine-Budde diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 536bda0..9ac28df 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -686,7 +686,7 @@ static int c_can_get_berr_counter(const struct net_device *dev, * * We iterate from priv->tx_echo to priv->tx_next and check if the * packet has been transmitted, echo it back to the CAN framework. - * If we discover a not yet transmitted package, stop looking for more. + * If we discover a not yet transmitted packet, stop looking for more. */ static void c_can_do_tx(struct net_device *dev) { @@ -698,7 +698,7 @@ static void c_can_do_tx(struct net_device *dev) for (/* nix */; (priv->tx_next - priv->tx_echo) > 0; priv->tx_echo++) { msg_obj_no = get_tx_echo_msg_obj(priv); val = c_can_read_reg32(priv, &priv->regs->txrqst1); - if (!(val & (1 << msg_obj_no))) { + if (!(val & (1 << (msg_obj_no - 1)))) { can_get_echo_skb(dev, msg_obj_no - C_CAN_MSG_OBJ_TX_FIRST); stats->tx_bytes += priv->read_reg(priv, @@ -706,6 +706,8 @@ static void c_can_do_tx(struct net_device *dev) & IF_MCONT_DLC_MASK; stats->tx_packets++; c_can_inval_msg_object(dev, 0, msg_obj_no); + } else { + break; } } -- cgit v0.10.2 From 148c87c89e1a8863d3d965179f3ab1a06490569e Mon Sep 17 00:00:00 2001 From: AnilKumar Ch Date: Wed, 23 May 2012 17:45:10 +0530 Subject: can: c_can: fix an interrupt thrash issue with c_can driver This patch fixes an interrupt thrash issue with c_can driver. In c_can_isr() function interrupts are disabled and enabled only in c_can_poll() function. c_can_isr() & c_can_poll() both read the irqstatus flag. However, irqstatus is always read as 0 in c_can_poll() because all C_CAN interrupts are disabled in c_can_isr(). This causes all interrupts to be re-enabled in c_can_poll() which in turn causes another interrupt since the event is not really handled. This keeps happening causing a flood of interrupts. To fix this, read the irqstatus register in isr and use the same cached value in the poll function. Cc: stable@kernel.org # 2.6.39+ Signed-off-by: AnilKumar Ch Acked-by: Wolfgang Grandegger Signed-off-by: Marc Kleine-Budde diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index 9ac28df..fa01621 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -952,7 +952,7 @@ static int c_can_poll(struct napi_struct *napi, int quota) struct net_device *dev = napi->dev; struct c_can_priv *priv = netdev_priv(dev); - irqstatus = priv->read_reg(priv, &priv->regs->interrupt); + irqstatus = priv->irqstatus; if (!irqstatus) goto end; @@ -1030,12 +1030,11 @@ end: static irqreturn_t c_can_isr(int irq, void *dev_id) { - u16 irqstatus; struct net_device *dev = (struct net_device *)dev_id; struct c_can_priv *priv = netdev_priv(dev); - irqstatus = priv->read_reg(priv, &priv->regs->interrupt); - if (!irqstatus) + priv->irqstatus = priv->read_reg(priv, &priv->regs->interrupt); + if (!priv->irqstatus) return IRQ_NONE; /* disable all interrupts and schedule the NAPI */ diff --git a/drivers/net/can/c_can/c_can.h b/drivers/net/can/c_can/c_can.h index 9b7fbef..5f32d34 100644 --- a/drivers/net/can/c_can/c_can.h +++ b/drivers/net/can/c_can/c_can.h @@ -76,6 +76,7 @@ struct c_can_priv { unsigned int tx_next; unsigned int tx_echo; void *priv; /* for board-specific data */ + u16 irqstatus; }; struct net_device *alloc_c_can_dev(void); -- cgit v0.10.2 From f461f27a4436dbe691908fe08b867ef888848cc3 Mon Sep 17 00:00:00 2001 From: AnilKumar Ch Date: Wed, 23 May 2012 17:45:11 +0530 Subject: can: c_can: fix race condition in c_can_open() Fix the issue of C_CAN interrupts getting disabled forever when canconfig utility is used multiple times. According to NAPI usage we disable all the hardware interrupts in ISR and re-enable them in poll(). Current implementation calls napi_enable() after hardware interrupts are enabled. If we get any interrupts between these two steps then we do not process those interrupts because napi is not enabled. Mostly these interrupts come because of STATUS is not 0x7 or ERROR interrupts. If napi_enable() happens before HW interrupts enabled then c_can_poll() function will be called eventual re-enabling. This patch moves the napi_enable() call before interrupts enabled. Cc: stable@kernel.org # 2.6.39+ Signed-off-by: AnilKumar Ch Acked-by: Wolfgang Grandegger Signed-off-by: Marc Kleine-Budde diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c index fa01621..8dc84d6 100644 --- a/drivers/net/can/c_can/c_can.c +++ b/drivers/net/can/c_can/c_can.c @@ -1064,10 +1064,11 @@ static int c_can_open(struct net_device *dev) goto exit_irq_fail; } + napi_enable(&priv->napi); + /* start the c_can controller */ c_can_start(dev); - napi_enable(&priv->napi); netif_start_queue(dev); return 0; -- cgit v0.10.2 From dc605dbdb8dd152448ccb8d4c4d5bd9439965a20 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 30 May 2012 13:25:55 -0700 Subject: can: cc770: Fix likely misuse of | for & Using | with a constant is always true. Likely this should have be &. Signed-off-by: Joe Perches Signed-off-by: Marc Kleine-Budde diff --git a/drivers/net/can/cc770/cc770_platform.c b/drivers/net/can/cc770/cc770_platform.c index 53115ee..688371c 100644 --- a/drivers/net/can/cc770/cc770_platform.c +++ b/drivers/net/can/cc770/cc770_platform.c @@ -154,7 +154,7 @@ static int __devinit cc770_get_platform_data(struct platform_device *pdev, struct cc770_platform_data *pdata = pdev->dev.platform_data; priv->can.clock.freq = pdata->osc_freq; - if (priv->cpu_interface | CPUIF_DSC) + if (priv->cpu_interface & CPUIF_DSC) priv->can.clock.freq /= 2; priv->clkout = pdata->cor; priv->bus_config = pdata->bcr; -- cgit v0.10.2 From bec4596b4e6770c7037f21f6bd27567b152dc0d6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 4 Jun 2012 00:18:19 +0000 Subject: drop_monitor: dont sleep in atomic context drop_monitor calls several sleeping functions while in atomic context. BUG: sleeping function called from invalid context at mm/slub.c:943 in_atomic(): 1, irqs_disabled(): 0, pid: 2103, name: kworker/0:2 Pid: 2103, comm: kworker/0:2 Not tainted 3.5.0-rc1+ #55 Call Trace: [] __might_sleep+0xca/0xf0 [] kmem_cache_alloc_node+0x1b3/0x1c0 [] ? queue_delayed_work_on+0x11c/0x130 [] __alloc_skb+0x4b/0x230 [] ? reset_per_cpu_data+0x160/0x160 [drop_monitor] [] reset_per_cpu_data+0x2f/0x160 [drop_monitor] [] send_dm_alert+0x4b/0xb0 [drop_monitor] [] process_one_work+0x130/0x4c0 [] worker_thread+0x159/0x360 [] ? manage_workers.isra.27+0x240/0x240 [] kthread+0x93/0xa0 [] kernel_thread_helper+0x4/0x10 [] ? kthread_freezable_should_stop+0x80/0x80 [] ? gs_change+0xb/0xb Rework the logic to call the sleeping functions in right context. Use standard timer/workqueue api to let system chose any cpu to perform the allocation and netlink send. Also avoid a loop if reset_per_cpu_data() cannot allocate memory : use mod_timer() to wait 1/10 second before next try. Signed-off-by: Eric Dumazet Cc: Neil Horman Reviewed-by: Neil Horman Signed-off-by: David S. Miller diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index ea5fb9f..d23b668 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -36,9 +36,6 @@ #define TRACE_ON 1 #define TRACE_OFF 0 -static void send_dm_alert(struct work_struct *unused); - - /* * Globals, our netlink socket pointer * and the work handle that will send up @@ -48,11 +45,10 @@ static int trace_state = TRACE_OFF; static DEFINE_MUTEX(trace_state_mutex); struct per_cpu_dm_data { - struct work_struct dm_alert_work; - struct sk_buff __rcu *skb; - atomic_t dm_hit_count; - struct timer_list send_timer; - int cpu; + spinlock_t lock; + struct sk_buff *skb; + struct work_struct dm_alert_work; + struct timer_list send_timer; }; struct dm_hw_stat_delta { @@ -78,13 +74,13 @@ static int dm_delay = 1; static unsigned long dm_hw_check_delta = 2*HZ; static LIST_HEAD(hw_stats_list); -static void reset_per_cpu_data(struct per_cpu_dm_data *data) +static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data) { size_t al; struct net_dm_alert_msg *msg; struct nlattr *nla; struct sk_buff *skb; - struct sk_buff *oskb = rcu_dereference_protected(data->skb, 1); + unsigned long flags; al = sizeof(struct net_dm_alert_msg); al += dm_hit_limit * sizeof(struct net_dm_drop_point); @@ -99,65 +95,40 @@ static void reset_per_cpu_data(struct per_cpu_dm_data *data) sizeof(struct net_dm_alert_msg)); msg = nla_data(nla); memset(msg, 0, al); - } else - schedule_work_on(data->cpu, &data->dm_alert_work); - - /* - * Don't need to lock this, since we are guaranteed to only - * run this on a single cpu at a time. - * Note also that we only update data->skb if the old and new skb - * pointers don't match. This ensures that we don't continually call - * synchornize_rcu if we repeatedly fail to alloc a new netlink message. - */ - if (skb != oskb) { - rcu_assign_pointer(data->skb, skb); - - synchronize_rcu(); - - atomic_set(&data->dm_hit_count, dm_hit_limit); + } else { + mod_timer(&data->send_timer, jiffies + HZ / 10); } + spin_lock_irqsave(&data->lock, flags); + swap(data->skb, skb); + spin_unlock_irqrestore(&data->lock, flags); + + return skb; } -static void send_dm_alert(struct work_struct *unused) +static void send_dm_alert(struct work_struct *work) { struct sk_buff *skb; - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); + struct per_cpu_dm_data *data; - WARN_ON_ONCE(data->cpu != smp_processor_id()); + data = container_of(work, struct per_cpu_dm_data, dm_alert_work); - /* - * Grab the skb we're about to send - */ - skb = rcu_dereference_protected(data->skb, 1); - - /* - * Replace it with a new one - */ - reset_per_cpu_data(data); + skb = reset_per_cpu_data(data); - /* - * Ship it! - */ if (skb) genlmsg_multicast(skb, 0, NET_DM_GRP_ALERT, GFP_KERNEL); - - put_cpu_var(dm_cpu_data); } /* * This is the timer function to delay the sending of an alert * in the event that more drops will arrive during the - * hysteresis period. Note that it operates under the timer interrupt - * so we don't need to disable preemption here + * hysteresis period. */ -static void sched_send_work(unsigned long unused) +static void sched_send_work(unsigned long _data) { - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); - - schedule_work_on(smp_processor_id(), &data->dm_alert_work); + struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data; - put_cpu_var(dm_cpu_data); + schedule_work(&data->dm_alert_work); } static void trace_drop_common(struct sk_buff *skb, void *location) @@ -167,33 +138,28 @@ static void trace_drop_common(struct sk_buff *skb, void *location) struct nlattr *nla; int i; struct sk_buff *dskb; - struct per_cpu_dm_data *data = &get_cpu_var(dm_cpu_data); - + struct per_cpu_dm_data *data; + unsigned long flags; - rcu_read_lock(); - dskb = rcu_dereference(data->skb); + local_irq_save(flags); + data = &__get_cpu_var(dm_cpu_data); + spin_lock(&data->lock); + dskb = data->skb; if (!dskb) goto out; - if (!atomic_add_unless(&data->dm_hit_count, -1, 0)) { - /* - * we're already at zero, discard this hit - */ - goto out; - } - nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); for (i = 0; i < msg->entries; i++) { if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { msg->points[i].count++; - atomic_inc(&data->dm_hit_count); goto out; } } - + if (msg->entries == dm_hit_limit) + goto out; /* * We need to create a new entry */ @@ -205,13 +171,11 @@ static void trace_drop_common(struct sk_buff *skb, void *location) if (!timer_pending(&data->send_timer)) { data->send_timer.expires = jiffies + dm_delay * HZ; - add_timer_on(&data->send_timer, smp_processor_id()); + add_timer(&data->send_timer); } out: - rcu_read_unlock(); - put_cpu_var(dm_cpu_data); - return; + spin_unlock_irqrestore(&data->lock, flags); } static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location) @@ -418,11 +382,11 @@ static int __init init_net_drop_monitor(void) for_each_possible_cpu(cpu) { data = &per_cpu(dm_cpu_data, cpu); - data->cpu = cpu; INIT_WORK(&data->dm_alert_work, send_dm_alert); init_timer(&data->send_timer); - data->send_timer.data = cpu; + data->send_timer.data = (unsigned long)data; data->send_timer.function = sched_send_work; + spin_lock_init(&data->lock); reset_per_cpu_data(data); } -- cgit v0.10.2 From 9ec0db71af04f4560e27a3c2f5a0411ba3155198 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 4 Jun 2012 05:51:18 +0000 Subject: net: icplus: fix interrupt mask This patch fixes the interrupt mask for IC101 A/G devices and now enables the link/speed/duplex interrupts. This is done by setting the "INTR pin used" bit and cleaning all the other bits in the Register 17. Reported-by: Stuart Menefy Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller diff --git a/drivers/net/phy/icplus.c b/drivers/net/phy/icplus.c index 5ac46f5..47f8e89 100644 --- a/drivers/net/phy/icplus.c +++ b/drivers/net/phy/icplus.c @@ -41,6 +41,8 @@ MODULE_LICENSE("GPL"); #define IP1001_APS_ON 11 /* IP1001 APS Mode bit */ #define IP101A_G_APS_ON 2 /* IP101A/G APS Mode bit */ #define IP101A_G_IRQ_CONF_STATUS 0x11 /* Conf Info IRQ & Status Reg */ +#define IP101A_G_IRQ_PIN_USED (1<<15) /* INTR pin used */ +#define IP101A_G_IRQ_DEFAULT IP101A_G_IRQ_PIN_USED static int ip175c_config_init(struct phy_device *phydev) { @@ -136,6 +138,11 @@ static int ip1001_config_init(struct phy_device *phydev) if (c < 0) return c; + /* INTR pin used: speed/link/duplex will cause an interrupt */ + c = phy_write(phydev, IP101A_G_IRQ_CONF_STATUS, IP101A_G_IRQ_DEFAULT); + if (c < 0) + return c; + if (phydev->interface == PHY_INTERFACE_MODE_RGMII) { /* Additional delay (2ns) used to adjust RX clock phase * at RGMII interface */ -- cgit v0.10.2 From dc5cd894cace7bda4a743487a9f87d59a3f0a095 Mon Sep 17 00:00:00 2001 From: Haiyang Zhang Date: Mon, 4 Jun 2012 06:42:38 +0000 Subject: net/hyperv: Use wait_event on outstanding sends during device removal Change the busy-waiting/udelay to wait_event on outstanding sends. Signed-off-by: Haiyang Zhang Reviewed-by: K. Y. Srinivasan Signed-off-by: David S. Miller diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 4ffcd57..2857ab07 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -478,6 +478,7 @@ struct netvsc_device { u32 nvsp_version; atomic_t num_outstanding_sends; + wait_queue_head_t wait_drain; bool start_remove; bool destroy; /* diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 8b91947..0c56983 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -42,6 +42,7 @@ static struct netvsc_device *alloc_net_device(struct hv_device *device) if (!net_device) return NULL; + init_waitqueue_head(&net_device->wait_drain); net_device->start_remove = false; net_device->destroy = false; net_device->dev = device; @@ -387,12 +388,8 @@ int netvsc_device_remove(struct hv_device *device) spin_unlock_irqrestore(&device->channel->inbound_lock, flags); /* Wait for all send completions */ - while (atomic_read(&net_device->num_outstanding_sends)) { - dev_info(&device->device, - "waiting for %d requests to complete...\n", - atomic_read(&net_device->num_outstanding_sends)); - udelay(100); - } + wait_event(net_device->wait_drain, + atomic_read(&net_device->num_outstanding_sends) == 0); netvsc_disconnect_vsp(net_device); @@ -486,6 +483,9 @@ static void netvsc_send_completion(struct hv_device *device, num_outstanding_sends = atomic_dec_return(&net_device->num_outstanding_sends); + if (net_device->destroy && num_outstanding_sends == 0) + wake_up(&net_device->wait_drain); + if (netif_queue_stopped(ndev) && !net_device->start_remove && (hv_ringbuf_avail_percent(&device->channel->outbound) > RING_AVAIL_PERCENT_HIWATER || -- cgit v0.10.2 From 925e64c3c512e9f4452eaa7d52fd4c1518b8fb11 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Wed, 16 May 2012 15:27:20 +0200 Subject: mac80211: run scan after finish connection monitoring commit 133d40f9a22bdfd2617a446f1e3209537c5415ec Author: Stanislaw Gruszka Date: Wed Mar 28 16:01:19 2012 +0200 mac80211: do not scan and monitor connection in parallel add bug, which make possible to start a scan and never finish it, so make every new scanning request finish with -EBUSY error. This can happen on code paths where we finish connection monitoring and clear IEEE80211_STA_*_POLL flags, but do not check if scan was deferred. This patch fixes those code paths. Signed-off-by: Stanislaw Gruszka Signed-off-by: John W. Linville diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 04c3063..d94627c 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1220,6 +1220,22 @@ static void ieee80211_sta_wmm_params(struct ieee80211_local *local, sdata->vif.bss_conf.qos = true; } +static void __ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata) +{ + lockdep_assert_held(&sdata->local->mtx); + + sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | + IEEE80211_STA_BEACON_POLL); + ieee80211_run_deferred_scan(sdata->local); +} + +static void ieee80211_stop_poll(struct ieee80211_sub_if_data *sdata) +{ + mutex_lock(&sdata->local->mtx); + __ieee80211_stop_poll(sdata); + mutex_unlock(&sdata->local->mtx); +} + static u32 ieee80211_handle_bss_capability(struct ieee80211_sub_if_data *sdata, u16 capab, bool erp_valid, u8 erp) { @@ -1285,8 +1301,7 @@ static void ieee80211_set_associated(struct ieee80211_sub_if_data *sdata, sdata->u.mgd.flags |= IEEE80211_STA_RESET_SIGNAL_AVE; /* just to be sure */ - sdata->u.mgd.flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + ieee80211_stop_poll(sdata); ieee80211_led_assoc(local, 1); @@ -1456,8 +1471,7 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) return; } - ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + __ieee80211_stop_poll(sdata); mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); @@ -1477,7 +1491,6 @@ static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata) round_jiffies_up(jiffies + IEEE80211_CONNECTION_IDLE_TIME)); out: - ieee80211_run_deferred_scan(local); mutex_unlock(&local->mtx); } @@ -2408,7 +2421,11 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, net_dbg_ratelimited("%s: cancelling probereq poll due to a received beacon\n", sdata->name); #endif + mutex_lock(&local->mtx); ifmgd->flags &= ~IEEE80211_STA_BEACON_POLL; + ieee80211_run_deferred_scan(local); + mutex_unlock(&local->mtx); + mutex_lock(&local->iflist_mtx); ieee80211_recalc_ps(local, -1); mutex_unlock(&local->iflist_mtx); @@ -2595,8 +2612,7 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; u8 frame_buf[DEAUTH_DISASSOC_LEN]; - ifmgd->flags &= ~(IEEE80211_STA_CONNECTION_POLL | - IEEE80211_STA_BEACON_POLL); + ieee80211_stop_poll(sdata); ieee80211_set_disassoc(sdata, IEEE80211_STYPE_DEAUTH, reason, false, frame_buf); @@ -2874,8 +2890,7 @@ static void ieee80211_restart_sta_timer(struct ieee80211_sub_if_data *sdata) u32 flags; if (sdata->vif.type == NL80211_IFTYPE_STATION) { - sdata->u.mgd.flags &= ~(IEEE80211_STA_BEACON_POLL | - IEEE80211_STA_CONNECTION_POLL); + __ieee80211_stop_poll(sdata); /* let's probe the connection once */ flags = sdata->local->hw.flags; @@ -2944,7 +2959,10 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) if (test_and_clear_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running)) add_timer(&ifmgd->chswitch_timer); ieee80211_sta_reset_beacon_monitor(sdata); + + mutex_lock(&sdata->local->mtx); ieee80211_restart_sta_timer(sdata); + mutex_unlock(&sdata->local->mtx); } #endif -- cgit v0.10.2 From f0e3bd23418e1ec1aeac5fc36b74bf2f645b1244 Mon Sep 17 00:00:00 2001 From: Avinash Patil Date: Tue, 29 May 2012 15:39:04 -0700 Subject: mwifiex: invalidate bss config before setting channel for uAP Mark bss_config parameters as invalid before setting AP channel. This prevents from setting invalid parameters while setting AP channel to FW. Signed-off-by: Avinash Patil Signed-off-by: Kiran Divekar Signed-off-by: Bing Zhao Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/mwifiex/uap_cmd.c b/drivers/net/wireless/mwifiex/uap_cmd.c index 76dfbc4..e9482c9 100644 --- a/drivers/net/wireless/mwifiex/uap_cmd.c +++ b/drivers/net/wireless/mwifiex/uap_cmd.c @@ -416,6 +416,7 @@ int mwifiex_uap_set_channel(struct mwifiex_private *priv, int channel) if (!bss_cfg) return -ENOMEM; + mwifiex_set_sys_config_invalid_data(bss_cfg); bss_cfg->band_cfg = BAND_CONFIG_MANUAL; bss_cfg->channel = channel; -- cgit v0.10.2 From 7a1c99343c5305c47b5e078d1af2144f9026df40 Mon Sep 17 00:00:00 2001 From: Avinash Patil Date: Tue, 29 May 2012 15:39:05 -0700 Subject: mwifiex: support NL80211_HIDDEN_SSID_ZERO_LEN for uAP mwifiex uAP supports NL80211_HIDDEN_SSID_ZERO_LEN type of hidden SSID only. NL80211_HIDDEN_SSID_ZERO_CONTENTS is not supported. Signed-off-by: Avinash Patil Signed-off-by: Kiran Divekar Signed-off-by: Bing Zhao Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/mwifiex/cfg80211.c b/drivers/net/wireless/mwifiex/cfg80211.c index 8767144..015fec3 100644 --- a/drivers/net/wireless/mwifiex/cfg80211.c +++ b/drivers/net/wireless/mwifiex/cfg80211.c @@ -948,6 +948,19 @@ static int mwifiex_cfg80211_start_ap(struct wiphy *wiphy, bss_cfg->ssid.ssid_len = params->ssid_len; } + switch (params->hidden_ssid) { + case NL80211_HIDDEN_SSID_NOT_IN_USE: + bss_cfg->bcast_ssid_ctl = 1; + break; + case NL80211_HIDDEN_SSID_ZERO_LEN: + bss_cfg->bcast_ssid_ctl = 0; + break; + case NL80211_HIDDEN_SSID_ZERO_CONTENTS: + /* firmware doesn't support this type of hidden SSID */ + default: + return -EINVAL; + } + if (mwifiex_set_secure_params(priv, bss_cfg, params)) { kfree(bss_cfg); wiphy_err(wiphy, "Failed to parse secuirty parameters!\n"); diff --git a/drivers/net/wireless/mwifiex/fw.h b/drivers/net/wireless/mwifiex/fw.h index 9f674bb..561452a 100644 --- a/drivers/net/wireless/mwifiex/fw.h +++ b/drivers/net/wireless/mwifiex/fw.h @@ -122,6 +122,7 @@ enum MWIFIEX_802_11_PRIVACY_FILTER { #define TLV_TYPE_CHANNELBANDLIST (PROPRIETARY_TLV_BASE_ID + 42) #define TLV_TYPE_UAP_BEACON_PERIOD (PROPRIETARY_TLV_BASE_ID + 44) #define TLV_TYPE_UAP_DTIM_PERIOD (PROPRIETARY_TLV_BASE_ID + 45) +#define TLV_TYPE_UAP_BCAST_SSID (PROPRIETARY_TLV_BASE_ID + 48) #define TLV_TYPE_UAP_RTS_THRESHOLD (PROPRIETARY_TLV_BASE_ID + 51) #define TLV_TYPE_UAP_WPA_PASSPHRASE (PROPRIETARY_TLV_BASE_ID + 60) #define TLV_TYPE_UAP_ENCRY_PROTOCOL (PROPRIETARY_TLV_BASE_ID + 64) @@ -1209,6 +1210,11 @@ struct host_cmd_tlv_ssid { u8 ssid[0]; } __packed; +struct host_cmd_tlv_bcast_ssid { + struct host_cmd_tlv tlv; + u8 bcast_ctl; +} __packed; + struct host_cmd_tlv_beacon_period { struct host_cmd_tlv tlv; __le16 period; diff --git a/drivers/net/wireless/mwifiex/uap_cmd.c b/drivers/net/wireless/mwifiex/uap_cmd.c index e9482c9..8173ab6 100644 --- a/drivers/net/wireless/mwifiex/uap_cmd.c +++ b/drivers/net/wireless/mwifiex/uap_cmd.c @@ -132,6 +132,7 @@ mwifiex_uap_bss_param_prepare(u8 *tlv, void *cmd_buf, u16 *param_size) struct host_cmd_tlv_dtim_period *dtim_period; struct host_cmd_tlv_beacon_period *beacon_period; struct host_cmd_tlv_ssid *ssid; + struct host_cmd_tlv_bcast_ssid *bcast_ssid; struct host_cmd_tlv_channel_band *chan_band; struct host_cmd_tlv_frag_threshold *frag_threshold; struct host_cmd_tlv_rts_threshold *rts_threshold; @@ -153,6 +154,14 @@ mwifiex_uap_bss_param_prepare(u8 *tlv, void *cmd_buf, u16 *param_size) cmd_size += sizeof(struct host_cmd_tlv) + bss_cfg->ssid.ssid_len; tlv += sizeof(struct host_cmd_tlv) + bss_cfg->ssid.ssid_len; + + bcast_ssid = (struct host_cmd_tlv_bcast_ssid *)tlv; + bcast_ssid->tlv.type = cpu_to_le16(TLV_TYPE_UAP_BCAST_SSID); + bcast_ssid->tlv.len = + cpu_to_le16(sizeof(bcast_ssid->bcast_ctl)); + bcast_ssid->bcast_ctl = bss_cfg->bcast_ssid_ctl; + cmd_size += sizeof(struct host_cmd_tlv_bcast_ssid); + tlv += sizeof(struct host_cmd_tlv_bcast_ssid); } if (bss_cfg->channel && bss_cfg->channel <= MAX_CHANNEL_BAND_BG) { chan_band = (struct host_cmd_tlv_channel_band *)tlv; -- cgit v0.10.2 From 28f333666ea766fdfb25de3783ff56cd2d1c51f0 Mon Sep 17 00:00:00 2001 From: Amitkumar Karwar Date: Tue, 29 May 2012 15:39:06 -0700 Subject: cfg80211: use sme_state in ibss start/join path CFG80211_DEV_WARN_ON() at "net/wireless/ibss.c line 63" is unnecessarily triggered even after successful connection, when cfg80211_ibss_joined() is called by driver inside .join_ibss handler. This patch fixes the problem by changing 'sme_state' in ibss path and having WARN_ON() check for 'sme_state' similar to infra association. Signed-off-by: Amitkumar Karwar Signed-off-by: Bing Zhao Signed-off-by: John W. Linville diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c index d2a19b0..89baa33 100644 --- a/net/wireless/ibss.c +++ b/net/wireless/ibss.c @@ -42,6 +42,7 @@ void __cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid) cfg80211_hold_bss(bss_from_pub(bss)); wdev->current_bss = bss_from_pub(bss); + wdev->sme_state = CFG80211_SME_CONNECTED; cfg80211_upload_connect_keys(wdev); nl80211_send_ibss_bssid(wiphy_to_dev(wdev->wiphy), dev, bssid, @@ -60,7 +61,7 @@ void cfg80211_ibss_joined(struct net_device *dev, const u8 *bssid, gfp_t gfp) struct cfg80211_event *ev; unsigned long flags; - CFG80211_DEV_WARN_ON(!wdev->ssid_len); + CFG80211_DEV_WARN_ON(wdev->sme_state != CFG80211_SME_CONNECTING); ev = kzalloc(sizeof(*ev), gfp); if (!ev) @@ -115,9 +116,11 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev, #ifdef CONFIG_CFG80211_WEXT wdev->wext.ibss.channel = params->channel; #endif + wdev->sme_state = CFG80211_SME_CONNECTING; err = rdev->ops->join_ibss(&rdev->wiphy, dev, params); if (err) { wdev->connect_keys = NULL; + wdev->sme_state = CFG80211_SME_IDLE; return err; } @@ -169,6 +172,7 @@ static void __cfg80211_clear_ibss(struct net_device *dev, bool nowext) } wdev->current_bss = NULL; + wdev->sme_state = CFG80211_SME_IDLE; wdev->ssid_len = 0; #ifdef CONFIG_CFG80211_WEXT if (!nowext) -- cgit v0.10.2 From b8bacc187aa5b59af9b9fa19b3ce4df5ad1db112 Mon Sep 17 00:00:00 2001 From: Chun-Yeow Yeoh Date: Wed, 30 May 2012 09:30:41 +0800 Subject: mac80211: Fix Unreachable Mesh Station Problem when joining to another MBSS Mesh station that joins an MBSS is reachable using mesh portal with 6 address frame by mesh stations from another MBSS if these two different MBSSes are bridged. However, if the mesh station later moves into the same MBSS of those mesh stations, it is unreachable by mesh stations in the MBSS due to the mpp_paths table is not deleted. A quick fix is to perform mesh_path_lookup, if it is available for the target destination, mpp_path_lookup is not performed. When the mesh station moves back to its original MBSS, the mesh_paths will be deleted once expired. So, it will be reachable using mpp_path_lookup again. Signed-off-by: Chun-Yeow Yeoh Signed-off-by: John W. Linville diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 847215b..e453212 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1737,7 +1737,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, __le16 fc; struct ieee80211_hdr hdr; struct ieee80211s_hdr mesh_hdr __maybe_unused; - struct mesh_path __maybe_unused *mppath = NULL; + struct mesh_path __maybe_unused *mppath = NULL, *mpath = NULL; const u8 *encaps_data; int encaps_len, skip_header_bytes; int nh_pos, h_pos; @@ -1803,8 +1803,11 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, goto fail; } rcu_read_lock(); - if (!is_multicast_ether_addr(skb->data)) - mppath = mpp_path_lookup(skb->data, sdata); + if (!is_multicast_ether_addr(skb->data)) { + mpath = mesh_path_lookup(skb->data, sdata); + if (!mpath) + mppath = mpp_path_lookup(skb->data, sdata); + } /* * Use address extension if it is a packet from -- cgit v0.10.2 From a5fdde28b4f5fb756032e7ad2c6fcdcffde20958 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 30 May 2012 10:36:12 +0200 Subject: iwlwifi: fix TX power antenna access Since my commit iwlwifi: use valid TX/RX antenna from hw_params the config values are pure overrides, not the real values for all hardware. Therefore, the EEPROM TX power reading code checks the wrong values, it should check the hw_params values. Cc: stable@kernel.org [3.4] Reviewed-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/iwlwifi/iwl-eeprom.c b/drivers/net/wireless/iwlwifi/iwl-eeprom.c index 50c5891..b8e2b22 100644 --- a/drivers/net/wireless/iwlwifi/iwl-eeprom.c +++ b/drivers/net/wireless/iwlwifi/iwl-eeprom.c @@ -568,28 +568,28 @@ static int iwl_find_otp_image(struct iwl_trans *trans, * iwl_get_max_txpower_avg - get the highest tx power from all chains. * find the highest tx power from all chains for the channel */ -static s8 iwl_get_max_txpower_avg(const struct iwl_cfg *cfg, +static s8 iwl_get_max_txpower_avg(struct iwl_priv *priv, struct iwl_eeprom_enhanced_txpwr *enhanced_txpower, int element, s8 *max_txpower_in_half_dbm) { s8 max_txpower_avg = 0; /* (dBm) */ /* Take the highest tx power from any valid chains */ - if ((cfg->valid_tx_ant & ANT_A) && + if ((priv->hw_params.valid_tx_ant & ANT_A) && (enhanced_txpower[element].chain_a_max > max_txpower_avg)) max_txpower_avg = enhanced_txpower[element].chain_a_max; - if ((cfg->valid_tx_ant & ANT_B) && + if ((priv->hw_params.valid_tx_ant & ANT_B) && (enhanced_txpower[element].chain_b_max > max_txpower_avg)) max_txpower_avg = enhanced_txpower[element].chain_b_max; - if ((cfg->valid_tx_ant & ANT_C) && + if ((priv->hw_params.valid_tx_ant & ANT_C) && (enhanced_txpower[element].chain_c_max > max_txpower_avg)) max_txpower_avg = enhanced_txpower[element].chain_c_max; - if (((cfg->valid_tx_ant == ANT_AB) | - (cfg->valid_tx_ant == ANT_BC) | - (cfg->valid_tx_ant == ANT_AC)) && + if (((priv->hw_params.valid_tx_ant == ANT_AB) | + (priv->hw_params.valid_tx_ant == ANT_BC) | + (priv->hw_params.valid_tx_ant == ANT_AC)) && (enhanced_txpower[element].mimo2_max > max_txpower_avg)) max_txpower_avg = enhanced_txpower[element].mimo2_max; - if ((cfg->valid_tx_ant == ANT_ABC) && + if ((priv->hw_params.valid_tx_ant == ANT_ABC) && (enhanced_txpower[element].mimo3_max > max_txpower_avg)) max_txpower_avg = enhanced_txpower[element].mimo3_max; @@ -691,7 +691,7 @@ static void iwl_eeprom_enhanced_txpower(struct iwl_priv *priv) ((txp->delta_20_in_40 & 0xf0) >> 4), (txp->delta_20_in_40 & 0x0f)); - max_txp_avg = iwl_get_max_txpower_avg(priv->cfg, txp_array, idx, + max_txp_avg = iwl_get_max_txpower_avg(priv, txp_array, idx, &max_txp_avg_halfdbm); /* -- cgit v0.10.2 From bd34ab62a3297bd7685da11b0cbe05ae4cd8b02c Mon Sep 17 00:00:00 2001 From: Meenakshi Venkataraman Date: Wed, 30 May 2012 11:39:33 +0200 Subject: mac80211: fix error in station state transitions during reconfig As part of hardware reconfig mac80211 tries to restore the station state to its values before the hardware reconfig, but it only goes to the last-state - 1. Fix this off-by-one error. Cc: stable@kernel.org [3.4] Signed-off-by: Meenakshi Venkataraman Reviewed-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/net/mac80211/util.c b/net/mac80211/util.c index a44c680..8dd4712 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1271,7 +1271,7 @@ int ieee80211_reconfig(struct ieee80211_local *local) enum ieee80211_sta_state state; for (state = IEEE80211_STA_NOTEXIST; - state < sta->sta_state - 1; state++) + state < sta->sta_state; state++) WARN_ON(drv_sta_state(local, sta->sdata, sta, state, state + 1)); } -- cgit v0.10.2 From 1ae2fc25a1289a84ca726541e3356ba5bcb7f7fe Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 30 May 2012 14:59:36 +0200 Subject: mac80211_hwsim: advertise interface combinations Enforcing interface combinations broke uses of hwsim with multiple virtual interfaces. Advertise that all combinations are possible to fix this. Reported-by: Nirav Shah Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index fb787df..4c9336c 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1721,6 +1721,24 @@ static void hwsim_exit_netlink(void) "unregister family %i\n", ret); } +static const struct ieee80211_iface_limit hwsim_if_limits[] = { + { .max = 1, .types = BIT(NL80211_IFTYPE_ADHOC) }, + { .max = 2048, .types = BIT(NL80211_IFTYPE_STATION) | + BIT(NL80211_IFTYPE_P2P_CLIENT) | +#ifdef CONFIG_MAC80211_MESH + BIT(NL80211_IFTYPE_MESH_POINT) | +#endif + BIT(NL80211_IFTYPE_AP) | + BIT(NL80211_IFTYPE_P2P_GO) }, +}; + +static const struct ieee80211_iface_combination hwsim_if_comb = { + .limits = hwsim_if_limits, + .n_limits = ARRAY_SIZE(hwsim_if_limits), + .max_interfaces = 2048, + .num_different_channels = 1, +}; + static int __init init_mac80211_hwsim(void) { int i, err = 0; @@ -1782,6 +1800,9 @@ static int __init init_mac80211_hwsim(void) hw->wiphy->n_addresses = 2; hw->wiphy->addresses = data->addresses; + hw->wiphy->iface_combinations = &hwsim_if_comb; + hw->wiphy->n_iface_combinations = 1; + if (fake_hw_scan) { hw->wiphy->max_scan_ssids = 255; hw->wiphy->max_scan_ie_len = IEEE80211_MAX_DATA_LEN; -- cgit v0.10.2 From 71ecfa1893034eeb1c93e02e22ee2ad26d080858 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 31 May 2012 15:09:27 +0200 Subject: mac80211: clean up remain-on-channel on interface stop When any interface goes down, it could be the one that we were doing a remain-on-channel with. We therefore need to cancel the remain-on-channel and flush the related work structs so they don't run after the interface has been removed or even destroyed. It's also possible in this case that an off-channel SKB was never transmitted, so free it if this is the case. Note that this can also happen if the driver finishes the off-channel period without ever starting it. Cc: stable@kernel.org Reported-by: Nirav Shah Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index d4c19a7..8664111 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -637,6 +637,18 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, ieee80211_configure_filter(local); break; default: + mutex_lock(&local->mtx); + if (local->hw_roc_dev == sdata->dev && + local->hw_roc_channel) { + /* ignore return value since this is racy */ + drv_cancel_remain_on_channel(local); + ieee80211_queue_work(&local->hw, &local->hw_roc_done); + } + mutex_unlock(&local->mtx); + + flush_work(&local->hw_roc_start); + flush_work(&local->hw_roc_done); + flush_work(&sdata->work); /* * When we get here, the interface is marked down. diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c index f054e94..935aa4b 100644 --- a/net/mac80211/offchannel.c +++ b/net/mac80211/offchannel.c @@ -234,6 +234,22 @@ static void ieee80211_hw_roc_done(struct work_struct *work) return; } + /* was never transmitted */ + if (local->hw_roc_skb) { + u64 cookie; + + cookie = local->hw_roc_cookie ^ 2; + + cfg80211_mgmt_tx_status(local->hw_roc_dev, cookie, + local->hw_roc_skb->data, + local->hw_roc_skb->len, false, + GFP_KERNEL); + + kfree_skb(local->hw_roc_skb); + local->hw_roc_skb = NULL; + local->hw_roc_skb_for_status = NULL; + } + if (!local->hw_roc_for_tx) cfg80211_remain_on_channel_expired(local->hw_roc_dev, local->hw_roc_cookie, -- cgit v0.10.2 From d8c7aae64cd2db5eccc631c29fa978a24fb1feef Mon Sep 17 00:00:00 2001 From: Felix Fietkau Date: Wed, 30 May 2012 15:32:24 +0200 Subject: mac80211: add missing rcu_read_lock/unlock in agg-rx session timer Fixes a lockdep warning: =================================================== [ INFO: suspicious rcu_dereference_check() usage. ] --------------------------------------------------- net/mac80211/agg-rx.c:148 invoked rcu_dereference_check() without protection! other info that might help us debug this: rcu_scheduler_active = 1, debug_locks = 1 1 lock held by arecord/11226: #0: (&tid_agg_rx->session_timer){+.-...}, at: [] call_timer_fn+0x0/0x360 stack backtrace: Pid: 11226, comm: arecord Not tainted 3.1.0-kml #16 Call Trace: [] lockdep_rcu_dereference+0xa4/0xc0 [] sta_rx_agg_session_timer_expired+0xc9/0x110 [mac80211] [] ? ieee80211_process_addba_resp+0x220/0x220 [mac80211] [] call_timer_fn+0x8a/0x360 [] ? init_timer_deferrable_key+0x30/0x30 [] ? _raw_spin_unlock_irq+0x30/0x70 [] run_timer_softirq+0x139/0x310 [] ? put_lock_stats.isra.25+0xe/0x40 [] ? lock_release_holdtime.part.26+0xdc/0x160 [] ? ieee80211_process_addba_resp+0x220/0x220 [mac80211] [] __do_softirq+0xc8/0x3c0 [] ? tick_dev_program_event+0x48/0x110 [] ? tick_program_event+0x1f/0x30 [] ? putname+0x35/0x50 [] call_softirq+0x1c/0x30 [] do_softirq+0xa5/0xe0 [] irq_exit+0xae/0xe0 [] smp_apic_timer_interrupt+0x6b/0x98 [] apic_timer_interrupt+0x73/0x80 [] ? free_debug_processing+0x1a1/0x1d5 [] ? putname+0x35/0x50 [] __slab_free+0x31/0x2ca [] ? _raw_spin_unlock_irqrestore+0x4a/0x90 [] ? __debug_check_no_obj_freed+0x15f/0x210 [] ? lock_release_nested+0x84/0xc0 [] ? kmem_cache_free+0x105/0x250 [] ? putname+0x35/0x50 [] ? putname+0x35/0x50 [] kmem_cache_free+0x23f/0x250 [] putname+0x35/0x50 [] do_sys_open+0x16d/0x1d0 [] sys_open+0x20/0x30 [] system_call_fastpath+0x16/0x1b Reported-by: Johannes Berg Signed-off-by: Felix Fietkau Signed-off-by: John W. Linville diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 26ddb69..c649188 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -145,15 +145,20 @@ static void sta_rx_agg_session_timer_expired(unsigned long data) struct tid_ampdu_rx *tid_rx; unsigned long timeout; + rcu_read_lock(); tid_rx = rcu_dereference(sta->ampdu_mlme.tid_rx[*ptid]); - if (!tid_rx) + if (!tid_rx) { + rcu_read_unlock(); return; + } timeout = tid_rx->last_rx + TU_TO_JIFFIES(tid_rx->timeout); if (time_is_after_jiffies(timeout)) { mod_timer(&tid_rx->session_timer, timeout); + rcu_read_unlock(); return; } + rcu_read_unlock(); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "rx session timer expired on tid %d\n", (u16)*ptid); -- cgit v0.10.2 From 5204267d2fd5e98fc52b44fec01ad10352642b78 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 30 May 2012 13:25:54 -0700 Subject: mac80211: Fix likely misuse of | for & Using | with a constant is always true. Likely this should have be &. cc: Ben Greear Signed-off-by: Joe Perches Signed-off-by: John W. Linville diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 495831e..e9cecca 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -533,16 +533,16 @@ static void ieee80211_get_et_stats(struct wiphy *wiphy, sinfo.filled = 0; sta_set_sinfo(sta, &sinfo); - if (sinfo.filled | STATION_INFO_TX_BITRATE) + if (sinfo.filled & STATION_INFO_TX_BITRATE) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate); i++; - if (sinfo.filled | STATION_INFO_RX_BITRATE) + if (sinfo.filled & STATION_INFO_RX_BITRATE) data[i] = 100000 * cfg80211_calculate_bitrate(&sinfo.rxrate); i++; - if (sinfo.filled | STATION_INFO_SIGNAL_AVG) + if (sinfo.filled & STATION_INFO_SIGNAL_AVG) data[i] = (u8)sinfo.signal_avg; i++; } else { -- cgit v0.10.2 From f304a993190965f48baa49792d5ab2849ae26bf9 Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Wed, 30 May 2012 13:25:56 -0700 Subject: brcmfmac: Fix likely misuse of | for & Using | with a constant is always true. Likely this should have be &. Signed-off-by: Joe Perches Acked-by: Arend van Spriel Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c index e2480d1..8e7e692 100644 --- a/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c +++ b/drivers/net/wireless/brcm80211/brcmfmac/bcmsdh.c @@ -89,9 +89,9 @@ int brcmf_sdio_intr_register(struct brcmf_sdio_dev *sdiodev) data |= 1 << SDIO_FUNC_1 | 1 << SDIO_FUNC_2 | 1; brcmf_sdio_regwb(sdiodev, SDIO_CCCR_IENx, data, &ret); - /* redirect, configure ane enable io for interrupt signal */ + /* redirect, configure and enable io for interrupt signal */ data = SDIO_SEPINT_MASK | SDIO_SEPINT_OE; - if (sdiodev->irq_flags | IRQF_TRIGGER_HIGH) + if (sdiodev->irq_flags & IRQF_TRIGGER_HIGH) data |= SDIO_SEPINT_ACT_HI; brcmf_sdio_regwb(sdiodev, SDIO_CCCR_BRCM_SEPINT, data, &ret); -- cgit v0.10.2 From e5851dac2c95af7159716832300b9f50c62c648e Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Fri, 1 Jun 2012 11:29:40 +0200 Subject: rt2x00: use atomic variable for seqno Remove spinlock as atomic_t can be used instead. Note we use only 16 lower bits, upper bits are changed but we impilcilty cast to u16. This fix possible deadlock on IBSS mode reproted by lockdep: ================================= [ INFO: inconsistent lock state ] 3.4.0-wl+ #4 Not tainted --------------------------------- inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. kworker/u:2/30374 [HC0[0]:SC0[0]:HE1:SE1] takes: (&(&intf->seqlock)->rlock){+.?...}, at: [] rt2x00queue_create_tx_descriptor+0x380/0x490 [rt2x00lib] {IN-SOFTIRQ-W} state was registered at: [] __lock_acquire+0x47b/0x1050 [] lock_acquire+0x84/0xf0 [] _raw_spin_lock+0x33/0x40 [] rt2x00queue_create_tx_descriptor+0x380/0x490 [rt2x00lib] [] rt2x00queue_write_tx_frame+0x1a/0x300 [rt2x00lib] [] rt2x00mac_tx+0x7f/0x380 [rt2x00lib] [] __ieee80211_tx+0x1b3/0x300 [mac80211] [] ieee80211_tx+0x105/0x130 [mac80211] [] ieee80211_xmit+0xad/0x100 [mac80211] [] ieee80211_subif_start_xmit+0x2d9/0x930 [mac80211] [] dev_hard_start_xmit+0x307/0x660 [] sch_direct_xmit+0xa1/0x1e0 [] dev_queue_xmit+0x183/0x730 [] neigh_resolve_output+0xfa/0x1e0 [] ip_finish_output+0x24a/0x460 [] ip_output+0xb7/0x100 [] ip_local_out+0x20/0x60 [] igmpv3_sendpack+0x4f/0x60 [] igmp_ifc_timer_expire+0x29f/0x330 [] run_timer_softirq+0x15c/0x2f0 [] __do_softirq+0xae/0x1e0 irq event stamp: 18380437 hardirqs last enabled at (18380437): [] __slab_alloc.clone.3+0x67/0x5f0 hardirqs last disabled at (18380436): [] __slab_alloc.clone.3+0x33/0x5f0 softirqs last enabled at (18377616): [] __do_softirq+0x123/0x1e0 softirqs last disabled at (18377611): [] do_softirq+0x9d/0xe0 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(&(&intf->seqlock)->rlock); lock(&(&intf->seqlock)->rlock); *** DEADLOCK *** 4 locks held by kworker/u:2/30374: #0: (wiphy_name(local->hw.wiphy)){++++.+}, at: [] process_one_work+0x109/0x3f0 #1: ((&sdata->work)){+.+.+.}, at: [] process_one_work+0x109/0x3f0 #2: (&ifibss->mtx){+.+.+.}, at: [] ieee80211_ibss_work+0x1b/0x470 [mac80211] #3: (&intf->beacon_skb_mutex){+.+...}, at: [] rt2x00queue_update_beacon+0x24/0x50 [rt2x00lib] stack backtrace: Pid: 30374, comm: kworker/u:2 Not tainted 3.4.0-wl+ #4 Call Trace: [] print_usage_bug+0x1f6/0x220 [] mark_lock+0x2c2/0x300 [] ? check_usage_forwards+0xc0/0xc0 [] __lock_acquire+0x4bc/0x1050 [] ? __kmalloc_track_caller+0x1c0/0x1d0 [] ? copy_skb_header+0x26/0x90 [] lock_acquire+0x84/0xf0 [] ? rt2x00queue_create_tx_descriptor+0x380/0x490 [rt2x00lib] [] _raw_spin_lock+0x33/0x40 [] ? rt2x00queue_create_tx_descriptor+0x380/0x490 [rt2x00lib] [] rt2x00queue_create_tx_descriptor+0x380/0x490 [rt2x00lib] [] rt2x00queue_update_beacon_locked+0x5f/0xb0 [rt2x00lib] [] rt2x00queue_update_beacon+0x2d/0x50 [rt2x00lib] [] rt2x00mac_bss_info_changed+0x1ca/0x200 [rt2x00lib] [] ? rt2x00mac_remove_interface+0x70/0x70 [rt2x00lib] [] ieee80211_bss_info_change_notify+0xe0/0x1d0 [mac80211] [] __ieee80211_sta_join_ibss+0x3b8/0x610 [mac80211] [] ? mark_held_locks+0x64/0xc0 [] ? virt_efi_query_capsule_caps+0x12/0x50 [] ieee80211_sta_join_ibss+0xf9/0x140 [mac80211] [] ieee80211_ibss_work+0x416/0x470 [mac80211] [] ? trace_hardirqs_on+0xb/0x10 [] ? skb_dequeue+0x4b/0x70 [] ieee80211_iface_work+0x13f/0x230 [mac80211] [] ? process_one_work+0x109/0x3f0 [] process_one_work+0x185/0x3f0 [] ? process_one_work+0x109/0x3f0 [] ? ieee80211_teardown_sdata+0xa0/0xa0 [mac80211] [] worker_thread+0x116/0x270 [] ? manage_workers+0x1e0/0x1e0 [] kthread+0x84/0x90 [] ? __init_kthread_worker+0x60/0x60 [] kernel_thread_helper+0x6/0x10 Cc: stable@vger.kernel.org Signed-off-by: Stanislaw Gruszka Acked-by: Helmut Schaa Acked-by: Gertjan van Wingerde Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/rt2x00/rt2x00.h b/drivers/net/wireless/rt2x00/rt2x00.h index ca36ccc..8f75402 100644 --- a/drivers/net/wireless/rt2x00/rt2x00.h +++ b/drivers/net/wireless/rt2x00/rt2x00.h @@ -396,8 +396,7 @@ struct rt2x00_intf { * for hardware which doesn't support hardware * sequence counting. */ - spinlock_t seqlock; - u16 seqno; + atomic_t seqno; }; static inline struct rt2x00_intf* vif_to_intf(struct ieee80211_vif *vif) diff --git a/drivers/net/wireless/rt2x00/rt2x00mac.c b/drivers/net/wireless/rt2x00/rt2x00mac.c index b49773e..dd24b26 100644 --- a/drivers/net/wireless/rt2x00/rt2x00mac.c +++ b/drivers/net/wireless/rt2x00/rt2x00mac.c @@ -277,7 +277,6 @@ int rt2x00mac_add_interface(struct ieee80211_hw *hw, else rt2x00dev->intf_sta_count++; - spin_lock_init(&intf->seqlock); mutex_init(&intf->beacon_skb_mutex); intf->beacon = entry; diff --git a/drivers/net/wireless/rt2x00/rt2x00queue.c b/drivers/net/wireless/rt2x00/rt2x00queue.c index 4c662ec..2fd8301 100644 --- a/drivers/net/wireless/rt2x00/rt2x00queue.c +++ b/drivers/net/wireless/rt2x00/rt2x00queue.c @@ -207,6 +207,7 @@ static void rt2x00queue_create_tx_descriptor_seq(struct rt2x00_dev *rt2x00dev, struct ieee80211_tx_info *tx_info = IEEE80211_SKB_CB(skb); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; struct rt2x00_intf *intf = vif_to_intf(tx_info->control.vif); + u16 seqno; if (!(tx_info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)) return; @@ -238,15 +239,13 @@ static void rt2x00queue_create_tx_descriptor_seq(struct rt2x00_dev *rt2x00dev, * sequence counting per-frame, since those will override the * sequence counter given by mac80211. */ - spin_lock(&intf->seqlock); - if (test_bit(ENTRY_TXD_FIRST_FRAGMENT, &txdesc->flags)) - intf->seqno += 0x10; - hdr->seq_ctrl &= cpu_to_le16(IEEE80211_SCTL_FRAG); - hdr->seq_ctrl |= cpu_to_le16(intf->seqno); - - spin_unlock(&intf->seqlock); + seqno = atomic_add_return(0x10, &intf->seqno); + else + seqno = atomic_read(&intf->seqno); + hdr->seq_ctrl &= cpu_to_le16(IEEE80211_SCTL_FRAG); + hdr->seq_ctrl |= cpu_to_le16(seqno); } static void rt2x00queue_create_tx_descriptor_plcp(struct rt2x00_dev *rt2x00dev, -- cgit v0.10.2 From 69aaedd3cfd23b2c732e3cf1227370a35f5c89d4 Mon Sep 17 00:00:00 2001 From: Seth Forshee Date: Fri, 1 Jun 2012 09:13:17 -0500 Subject: bcma: add ext PA workaround for BCM4331 and BCM43431 MacBook Pro models with BCM4331 wireless have been found to have the ext PA lines disabled after resuming from S3 without external power attach. This causes them to be unable to transmit. Add a workaround to ensure that the ext PA lines are enabled on BCM4331. Also extend all handling of ext PA line muxing to BCM43431 as is done in the Broadcom SDK. BugLink: http://bugs.launchpad.net/bugs/925577 Cc: Arend van Spriel Cc: Hauke Mehrtens Cc: stable@vger.kernel.org Signed-off-by: Seth Forshee Signed-off-by: John W. Linville diff --git a/drivers/bcma/driver_chipcommon_pmu.c b/drivers/bcma/driver_chipcommon_pmu.c index a058842..61ce405 100644 --- a/drivers/bcma/driver_chipcommon_pmu.c +++ b/drivers/bcma/driver_chipcommon_pmu.c @@ -139,7 +139,9 @@ void bcma_pmu_workarounds(struct bcma_drv_cc *cc) bcma_chipco_chipctl_maskset(cc, 0, ~0, 0x7); break; case 0x4331: - /* BCM4331 workaround is SPROM-related, we put it in sprom.c */ + case 43431: + /* Ext PA lines must be enabled for tx on BCM4331 */ + bcma_chipco_bcm4331_ext_pa_lines_ctl(cc, true); break; case 43224: if (bus->chipinfo.rev == 0) { diff --git a/drivers/bcma/sprom.c b/drivers/bcma/sprom.c index c7f9335..f16f42d3 100644 --- a/drivers/bcma/sprom.c +++ b/drivers/bcma/sprom.c @@ -579,13 +579,13 @@ int bcma_sprom_get(struct bcma_bus *bus) if (!sprom) return -ENOMEM; - if (bus->chipinfo.id == 0x4331) + if (bus->chipinfo.id == 0x4331 || bus->chipinfo.id == 43431) bcma_chipco_bcm4331_ext_pa_lines_ctl(&bus->drv_cc, false); pr_debug("SPROM offset 0x%x\n", offset); bcma_sprom_read(bus, offset, sprom); - if (bus->chipinfo.id == 0x4331) + if (bus->chipinfo.id == 0x4331 || bus->chipinfo.id == 43431) bcma_chipco_bcm4331_ext_pa_lines_ctl(&bus->drv_cc, true); err = bcma_sprom_valid(sprom); -- cgit v0.10.2 From 794454ce72a298de6f4536ade597bdcc7dcde7c7 Mon Sep 17 00:00:00 2001 From: Arik Nemtsov Date: Sun, 3 Jun 2012 23:32:32 +0300 Subject: mac80211: fix non RCU-safe sta_list manipulation sta_info_cleanup locks the sta_list using rcu_read_lock however the delete operation isn't rcu safe. A race between sta_info_cleanup timer being called and a STA being removed can occur which leads to a panic while traversing sta_list. Fix this by switching to the RCU-safe versions. Cc: stable@vger.kernel.org Reported-by: Eyal Shapira Signed-off-by: Arik Nemtsov Signed-off-by: John W. Linville diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index f5b1638..de455f8 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -378,7 +378,7 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) /* make the station visible */ sta_info_hash_add(local, sta); - list_add(&sta->list, &local->sta_list); + list_add_rcu(&sta->list, &local->sta_list); set_sta_flag(sta, WLAN_STA_INSERTED); @@ -688,7 +688,7 @@ int __must_check __sta_info_destroy(struct sta_info *sta) if (ret) return ret; - list_del(&sta->list); + list_del_rcu(&sta->list); mutex_lock(&local->key_mtx); for (i = 0; i < NUM_DEFAULT_KEYS; i++) -- cgit v0.10.2 From fcb6ff5e2cb83e1de10631f6621f45ca3401bf61 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Mon, 4 Jun 2012 13:43:11 +0200 Subject: iwlwifi: disable WoWLAN if !CONFIG_PM_SLEEP If CONFIG_PM_SLEEP is disabled, then iwlwifi doesn't support suspend/resume handlers and thus mac80211 (correctly) refuses advertising WoWLAN. Disable WoWLAN in the driver in this case. Cc: stable@kernel.org Reported-by: Sebastian Kemper Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/iwlwifi/iwl-mac80211.c b/drivers/net/wireless/iwlwifi/iwl-mac80211.c index ab2f4d7..5d158ca 100644 --- a/drivers/net/wireless/iwlwifi/iwl-mac80211.c +++ b/drivers/net/wireless/iwlwifi/iwl-mac80211.c @@ -199,6 +199,7 @@ int iwlagn_mac_setup_register(struct iwl_priv *priv, WIPHY_FLAG_DISABLE_BEACON_HINTS | WIPHY_FLAG_IBSS_RSN; +#ifdef CONFIG_PM_SLEEP if (priv->fw->img[IWL_UCODE_WOWLAN].sec[0].len && priv->trans->ops->wowlan_suspend && device_can_wakeup(priv->trans->dev)) { @@ -217,6 +218,7 @@ int iwlagn_mac_setup_register(struct iwl_priv *priv, hw->wiphy->wowlan.pattern_max_len = IWLAGN_WOWLAN_MAX_PATTERN_LEN; } +#endif if (iwlwifi_mod_params.power_save) hw->wiphy->flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT; -- cgit v0.10.2 From ddcd0f41471a1e0394c8840a119ec3986a78462c Mon Sep 17 00:00:00 2001 From: Vinicius Costa Gomes Date: Thu, 31 May 2012 22:53:39 -0300 Subject: Bluetooth: Fix checking the wrong flag when accepting a socket Most probably a typo, the check should have been for BT_SK_DEFER_SETUP instead of BT_DEFER_SETUP (which right now only represents a socket option). Signed-off-by: Vinicius Costa Gomes Acked-by: Andrei Emeltchenko Signed-off-by: Gustavo Padovan diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 46e7f86..3e18af4 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -210,7 +210,7 @@ struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) } if (sk->sk_state == BT_CONNECTED || !newsock || - test_bit(BT_DEFER_SETUP, &bt_sk(parent)->flags)) { + test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) { bt_accept_unlink(sk); if (newsock) sock_graft(sk, newsock); -- cgit v0.10.2 From f69a23b795d6ee3673583146ed7efcbaaa5add18 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 5 Jun 2012 19:56:06 +0200 Subject: iwlwifi: fix double free/complete in firmware loading Linus reported that due to mac80211 failing to register the device (due to WoWLAN) his machine crashed etc. as we double-freed the vmalloc() firmware area. His patch to fix it was very similar to this one but I noticed that there's another bug in the area: we complete the completion before starting, so since we're running in a work struct context stop() could be called while in the middle of start() which will almost certainly lead to issues. Make a modification similar to his to avoid the double- free but also move the completion to another spot so it is only done after start() either finished or failed so that stop() can have a consistent state. Reported-by: Linus Torvalds Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/iwlwifi/iwl-drv.c b/drivers/net/wireless/iwlwifi/iwl-drv.c index d742900..fac67a5 100644 --- a/drivers/net/wireless/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/iwlwifi/iwl-drv.c @@ -861,13 +861,18 @@ static void iwl_ucode_callback(const struct firmware *ucode_raw, void *context) /* We have our copies now, allow OS release its copies */ release_firmware(ucode_raw); - complete(&drv->request_firmware_complete); drv->op_mode = iwl_dvm_ops.start(drv->trans, drv->cfg, &drv->fw); if (!drv->op_mode) - goto out_free_fw; + goto out_unbind; + /* + * Complete the firmware request last so that + * a driver unbind (stop) doesn't run while we + * are doing the start() above. + */ + complete(&drv->request_firmware_complete); return; try_again: -- cgit v0.10.2 From 0e1fa7ef25004b9c1a14147bce61c15c2f1c6744 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 5 Jun 2012 09:38:35 +0200 Subject: iwlwifi: unregister LEDs if mac80211 registration fails Otherwise the LEDs stick around and cause issues the next time around since they're still there but not really hooked up. Cc: stable@kernel.org Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/iwlwifi/iwl-mac80211.c b/drivers/net/wireless/iwlwifi/iwl-mac80211.c index 5d158ca..3ee23134 100644 --- a/drivers/net/wireless/iwlwifi/iwl-mac80211.c +++ b/drivers/net/wireless/iwlwifi/iwl-mac80211.c @@ -251,6 +251,7 @@ int iwlagn_mac_setup_register(struct iwl_priv *priv, ret = ieee80211_register_hw(priv->hw); if (ret) { IWL_ERR(priv, "Failed to register hw (error %d)\n", ret); + iwl_leds_exit(priv); return ret; } priv->mac80211_registered = 1; -- cgit v0.10.2 From 463454b5dbd8dbab6e2fc6c557329e5b811b9c32 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 5 Jun 2012 12:16:50 +0200 Subject: cfg80211: fix interface combinations check If a given interface combination doesn't contain a required interface type then we missed checking that and erroneously allowed it even though iface type wasn't there at all. Add a check that makes sure that all interface types are accounted for. Cc: stable@kernel.org Reported-by: Mohammed Shafi Shajakhan Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/net/wireless/util.c b/net/wireless/util.c index 55d9946..8f2d68f 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -935,6 +935,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, enum nl80211_iftype iftype) { struct wireless_dev *wdev_iter; + u32 used_iftypes = BIT(iftype); int num[NUM_NL80211_IFTYPES]; int total = 1; int i, j; @@ -961,6 +962,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, num[wdev_iter->iftype]++; total++; + used_iftypes |= BIT(wdev_iter->iftype); } mutex_unlock(&rdev->devlist_mtx); @@ -970,6 +972,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, for (i = 0; i < rdev->wiphy.n_iface_combinations; i++) { const struct ieee80211_iface_combination *c; struct ieee80211_iface_limit *limits; + u32 all_iftypes = 0; c = &rdev->wiphy.iface_combinations[i]; @@ -984,6 +987,7 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, if (rdev->wiphy.software_iftypes & BIT(iftype)) continue; for (j = 0; j < c->n_limits; j++) { + all_iftypes |= limits[j].types; if (!(limits[j].types & BIT(iftype))) continue; if (limits[j].max < num[iftype]) @@ -991,7 +995,20 @@ int cfg80211_can_change_interface(struct cfg80211_registered_device *rdev, limits[j].max -= num[iftype]; } } - /* yay, it fits */ + + /* + * Finally check that all iftypes that we're currently + * using are actually part of this combination. If they + * aren't then we can't use this combination and have + * to continue to the next. + */ + if ((all_iftypes & used_iftypes) != used_iftypes) + goto cont; + + /* + * This combination covered all interface types and + * supported the requested numbers, so we're good. + */ kfree(limits); return 0; cont: -- cgit v0.10.2 From 470a54207ccf7045a59df727573bd9d148988582 Mon Sep 17 00:00:00 2001 From: Bruce Allan Date: Sat, 26 May 2012 06:08:48 +0000 Subject: e1000e: test for valid check_reset_block function pointer commit 44abd5c12767a8c567dc4e45fd9aec3b13ca85e0 introduced NULL pointer dereferences when attempting to access the check_reset_block function pointer on 8257x and 80003es2lan non-copper devices. This fix should be applied back through 3.4. Signed-off-by: Bruce Allan Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index d863075..905e214 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -258,7 +258,8 @@ static int e1000_set_settings(struct net_device *netdev, * When SoL/IDER sessions are active, autoneg/speed/duplex * cannot be changed */ - if (hw->phy.ops.check_reset_block(hw)) { + if (hw->phy.ops.check_reset_block && + hw->phy.ops.check_reset_block(hw)) { e_err("Cannot change link characteristics when SoL/IDER is active.\n"); return -EINVAL; } @@ -1615,7 +1616,8 @@ static int e1000_loopback_test(struct e1000_adapter *adapter, u64 *data) * PHY loopback cannot be performed if SoL/IDER * sessions are active */ - if (hw->phy.ops.check_reset_block(hw)) { + if (hw->phy.ops.check_reset_block && + hw->phy.ops.check_reset_block(hw)) { e_err("Cannot do PHY loopback test when SoL/IDER is active.\n"); *data = 0; goto out; diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index 026e8b3..a134399 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -709,7 +709,7 @@ s32 e1000e_setup_link_generic(struct e1000_hw *hw) * In the case of the phy reset being blocked, we already have a link. * We do not need to set it up again. */ - if (hw->phy.ops.check_reset_block(hw)) + if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw)) return 0; /* diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index a4b0435..31d37a2 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -6237,7 +6237,7 @@ static int __devinit e1000_probe(struct pci_dev *pdev, adapter->hw.phy.ms_type = e1000_ms_hw_default; } - if (hw->phy.ops.check_reset_block(hw)) + if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw)) e_info("PHY reset is blocked due to SOL/IDER session.\n"); /* Set initial default active device features */ @@ -6404,7 +6404,7 @@ err_register: if (!(adapter->flags & FLAG_HAS_AMT)) e1000e_release_hw_control(adapter); err_eeprom: - if (!hw->phy.ops.check_reset_block(hw)) + if (hw->phy.ops.check_reset_block && !hw->phy.ops.check_reset_block(hw)) e1000_phy_hw_reset(&adapter->hw); err_hw_init: kfree(adapter->tx_ring); diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index 0334d01..b860d4f 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -2155,9 +2155,11 @@ s32 e1000e_phy_hw_reset_generic(struct e1000_hw *hw) s32 ret_val; u32 ctrl; - ret_val = phy->ops.check_reset_block(hw); - if (ret_val) - return 0; + if (phy->ops.check_reset_block) { + ret_val = phy->ops.check_reset_block(hw); + if (ret_val) + return 0; + } ret_val = phy->ops.acquire(hw); if (ret_val) -- cgit v0.10.2 From 146d4cc98d660cbdeae52ae35a4d038d0dab6da5 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 May 2012 05:59:26 +0000 Subject: ixgbe: fix_features rxvlan is independent of DCB and needs to be set DCB can be used independent of if RX VLAN stripping is enabled or disabled so remove erroneous check. Also enable or disable VLAN stripping when features are applied so hardware and feature flags are in sync. CC: Alexander Duyck Signed-off-by: John Fastabend Tested-by: Marcus Dennis Signed-off-by: Jeff Kirsher diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index bf20457..b8b2087 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3607,10 +3607,6 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) if (hw->mac.type == ixgbe_mac_82598EB) netif_set_gso_max_size(adapter->netdev, 32768); - - /* Enable VLAN tag insert/strip */ - adapter->netdev->features |= NETIF_F_HW_VLAN_RX; - hw->mac.ops.set_vfta(&adapter->hw, 0, 0, true); #ifdef IXGBE_FCOE @@ -6701,11 +6697,6 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev, { struct ixgbe_adapter *adapter = netdev_priv(netdev); -#ifdef CONFIG_DCB - if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) - features &= ~NETIF_F_HW_VLAN_RX; -#endif - /* return error if RXHASH is being enabled when RSS is not supported */ if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) features &= ~NETIF_F_RXHASH; @@ -6718,7 +6709,6 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev, if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) features &= ~NETIF_F_LRO; - return features; } @@ -6766,6 +6756,11 @@ static int ixgbe_set_features(struct net_device *netdev, need_reset = true; } + if (features & NETIF_F_HW_VLAN_RX) + ixgbe_vlan_strip_enable(adapter); + else + ixgbe_vlan_strip_disable(adapter); + if (changed & NETIF_F_RXALL) need_reset = true; -- cgit v0.10.2 From 43e95f11ac0b06fec2c58431b092a60934d730e2 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 15 May 2012 06:12:17 +0000 Subject: ixgbe: IXGBE_RXD_STAT_VP set even with Rx stripping enabled The hardware bit IXGBE_RXD_STAT_VP appears to be set even when Rx stripping is disabled. This results in passing frames up the stack which do not have the 802.1Q tag stripped but have the tci bits set as if it was. Working around this with a check for the feature flag bit. I would welcome any better ideas or a pointer to exactly which bits in the hardware register need to be cleared to get the IXGBE_RXD_STAT_VP bit to be set per data sheet. Signed-off-by: John Fastabend Acked-by: Alexander Duyck Tested-by: Marcus Dennis Signed-off-by: Jeff Kirsher diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index b8b2087..17ad6a3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1390,6 +1390,8 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { + struct net_device *dev = rx_ring->netdev; + ixgbe_update_rsc_stats(rx_ring, skb); ixgbe_rx_hash(rx_ring, rx_desc, skb); @@ -1401,14 +1403,15 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector, skb); #endif - if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { + if ((dev->features & NETIF_F_HW_VLAN_RX) && + ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan); __vlan_hwaccel_put_tag(skb, vid); } skb_record_rx_queue(skb, rx_ring->queue_index); - skb->protocol = eth_type_trans(skb, rx_ring->netdev); + skb->protocol = eth_type_trans(skb, dev); } static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, -- cgit v0.10.2 From ff3dd78cb8055bcb3a10e526044d8b54a773c612 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 4 Jun 2012 19:22:55 +0000 Subject: stmmac: fix driver's doc when run kernel-doc script Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 7096633..ea33eae 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -833,8 +833,9 @@ static u32 stmmac_get_synopsys_id(struct stmmac_priv *priv) /** * stmmac_selec_desc_mode - * @dev : device pointer - * Description: select the Enhanced/Alternate or Normal descriptors */ + * @priv : private structure + * Description: select the Enhanced/Alternate or Normal descriptors + */ static void stmmac_selec_desc_mode(struct stmmac_priv *priv) { if (priv->plat->enh_desc) { @@ -1861,6 +1862,8 @@ static int stmmac_hw_init(struct stmmac_priv *priv) /** * stmmac_dvr_probe * @device: device pointer + * @plat_dat: platform data pointer + * @addr: iobase memory address * Description: this is the main probe function used to * call the alloc_etherdev, allocate the priv structure. */ -- cgit v0.10.2 From 3d2377144ca66c98fa220bda5f945590cf5cfdc0 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 4 Jun 2012 19:22:56 +0000 Subject: stmmac: update driver's doc Fixed the driver's documentation that was obsolete and didn't report new platform fields (recently added). Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt index ab1e8d7..5cb9a19 100644 --- a/Documentation/networking/stmmac.txt +++ b/Documentation/networking/stmmac.txt @@ -10,8 +10,8 @@ Currently this network device driver is for all STM embedded MAC/GMAC (i.e. 7xxx/5xxx SoCs), SPEAr (arm), Loongson1B (mips) and XLINX XC2V3000 FF1152AMT0221 D1215994A VIRTEX FPGA board. -DWC Ether MAC 10/100/1000 Universal version 3.60a (and older) and DWC Ether MAC 10/100 -Universal version 4.0 have been used for developing this driver. +DWC Ether MAC 10/100/1000 Universal version 3.60a (and older) and DWC Ether +MAC 10/100 Universal version 4.0 have been used for developing this driver. This driver supports both the platform bus and PCI. @@ -54,27 +54,27 @@ net_device structure enabling the scatter/gather feature. When one or more packets are received, an interrupt happens. The interrupts are not queued so the driver has to scan all the descriptors in the ring during the receive process. -This is based on NAPI so the interrupt handler signals only if there is work to be -done, and it exits. +This is based on NAPI so the interrupt handler signals only if there is work +to be done, and it exits. Then the poll method will be scheduled at some future point. The incoming packets are stored, by the DMA, in a list of pre-allocated socket buffers in order to avoid the memcpy (Zero-copy). 4.3) Timer-Driver Interrupt -Instead of having the device that asynchronously notifies the frame receptions, the -driver configures a timer to generate an interrupt at regular intervals. -Based on the granularity of the timer, the frames that are received by the device -will experience different levels of latency. Some NICs have dedicated timer -device to perform this task. STMMAC can use either the RTC device or the TMU -channel 2 on STLinux platforms. +Instead of having the device that asynchronously notifies the frame receptions, +the driver configures a timer to generate an interrupt at regular intervals. +Based on the granularity of the timer, the frames that are received by the +device will experience different levels of latency. Some NICs have dedicated +timer device to perform this task. STMMAC can use either the RTC device or the +TMU channel 2 on STLinux platforms. The timers frequency can be passed to the driver as parameter; when change it, take care of both hardware capability and network stability/performance impact. -Several performance tests on STM platforms showed this optimisation allows to spare -the CPU while having the maximum throughput. +Several performance tests on STM platforms showed this optimisation allows to +spare the CPU while having the maximum throughput. 4.4) WOL -Wake up on Lan feature through Magic and Unicast frames are supported for the GMAC -core. +Wake up on Lan feature through Magic and Unicast frames are supported for the +GMAC core. 4.5) DMA descriptors Driver handles both normal and enhanced descriptors. The latter has been only @@ -106,7 +106,8 @@ Several driver's information can be passed through the platform These are included in the include/linux/stmmac.h header file and detailed below as well: - struct plat_stmmacenet_data { +struct plat_stmmacenet_data { + char *phy_bus_name; int bus_id; int phy_addr; int interface; @@ -124,19 +125,24 @@ and detailed below as well: void (*bus_setup)(void __iomem *ioaddr); int (*init)(struct platform_device *pdev); void (*exit)(struct platform_device *pdev); + void *custom_cfg; + void *custom_data; void *bsp_priv; }; Where: + o phy_bus_name: phy bus name to attach to the stmmac. o bus_id: bus identifier. o phy_addr: the physical address can be passed from the platform. If it is set to -1 the driver will automatically detect it at run-time by probing all the 32 addresses. o interface: PHY device's interface. o mdio_bus_data: specific platform fields for the MDIO bus. - o pbl: the Programmable Burst Length is maximum number of beats to + o dma_cfg: internal DMA parameters + o pbl: the Programmable Burst Length is maximum number of beats to be transferred in one DMA transaction. GMAC also enables the 4xPBL by default. + o fixed_burst/mixed_burst/burst_len o clk_csr: fixed CSR Clock range selection. o has_gmac: uses the GMAC core. o enh_desc: if sets the MAC will use the enhanced descriptor structure. @@ -160,8 +166,9 @@ Where: this is sometime necessary on some platforms (e.g. ST boxes) where the HW needs to have set some PIO lines or system cfg registers. - o custom_cfg: this is a custom configuration that can be passed while - initialising the resources. + o custom_cfg/custom_data: this is a custom configuration that can be passed + while initialising the resources. + o bsp_priv: another private poiter. For MDIO bus The we have: @@ -180,7 +187,6 @@ Where: o irqs: list of IRQs, one per PHY. o probed_phy_irq: if irqs is NULL, use this for probed PHY. - For DMA engine we have the following internal fields that should be tuned according to the HW capabilities. -- cgit v0.10.2 From ba27ec66ffeb78cbf9f85e168b32551a9aaf2a34 Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Mon, 4 Jun 2012 19:22:57 +0000 Subject: stmmac: fix driver Kconfig when built as module This patches fixes the driver when built as dynamic module. In fact, the platform part cannot be built and the probe fails (thanks to Bob Liu that reported this bug). v2: as D. Miller suggested, it is not necessary to make the pci and the platform code mutually exclusive. Having both could also help, at built time ,to verify that all the code is validated and compiles fine. v3: removed wrong Reviewed-by from the patch Reported-by: Bob Liu cc: Rayagond Kokatanur Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 0364283..0076f77 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -13,9 +13,8 @@ config STMMAC_ETH if STMMAC_ETH config STMMAC_PLATFORM - tristate "STMMAC platform bus support" + bool "STMMAC Platform bus support" depends on STMMAC_ETH - default y ---help--- This selects the platform specific bus support for the stmmac device driver. This is the driver used @@ -26,7 +25,7 @@ config STMMAC_PLATFORM If unsure, say N. config STMMAC_PCI - tristate "STMMAC support on PCI bus (EXPERIMENTAL)" + bool "STMMAC PCI bus support (EXPERIMENTAL)" depends on STMMAC_ETH && PCI && EXPERIMENTAL ---help--- This is to select the Synopsys DWMAC available on PCI devices, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 6b5d060..6d07ba2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -95,7 +95,8 @@ extern int stmmac_mdio_register(struct net_device *ndev); extern void stmmac_set_ethtool_ops(struct net_device *netdev); extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; - +extern struct pci_driver stmmac_pci_driver; +extern struct platform_driver stmmac_pltfr_driver; int stmmac_freeze(struct net_device *ndev); int stmmac_restore(struct net_device *ndev); int stmmac_resume(struct net_device *ndev); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index ea33eae..3638569 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -42,6 +42,7 @@ #include #include #include +#include #ifdef CONFIG_STMMAC_DEBUG_FS #include #include @@ -2093,6 +2094,30 @@ int stmmac_restore(struct net_device *ndev) } #endif /* CONFIG_PM */ +static int __init stmmac_init(void) +{ + int err = 0; + + err = platform_driver_register(&stmmac_pltfr_driver); + + if (!err) { + err = pci_register_driver(&stmmac_pci_driver); + if (err) + platform_driver_unregister(&stmmac_pltfr_driver); + } + + return err; +} + +static void __exit stmmac_exit(void) +{ + pci_unregister_driver(&stmmac_pci_driver); + platform_driver_unregister(&stmmac_pltfr_driver); +} + +module_init(stmmac_init); +module_exit(stmmac_exit); + #ifndef MODULE static int __init stmmac_cmdline_opt(char *str) { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 58fab53..cf826e6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -179,7 +179,7 @@ static DEFINE_PCI_DEVICE_TABLE(stmmac_id_table) = { MODULE_DEVICE_TABLE(pci, stmmac_id_table); -static struct pci_driver stmmac_driver = { +struct pci_driver stmmac_pci_driver = { .name = STMMAC_RESOURCE_NAME, .id_table = stmmac_id_table, .probe = stmmac_pci_probe, @@ -190,33 +190,6 @@ static struct pci_driver stmmac_driver = { #endif }; -/** - * stmmac_init_module - Entry point for the driver - * Description: This function is the entry point for the driver. - */ -static int __init stmmac_init_module(void) -{ - int ret; - - ret = pci_register_driver(&stmmac_driver); - if (ret < 0) - pr_err("%s: ERROR: driver registration failed\n", __func__); - - return ret; -} - -/** - * stmmac_cleanup_module - Cleanup routine for the driver - * Description: This function is the cleanup routine for the driver. - */ -static void __exit stmmac_cleanup_module(void) -{ - pci_unregister_driver(&stmmac_driver); -} - -module_init(stmmac_init_module); -module_exit(stmmac_cleanup_module); - MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet PCI driver"); MODULE_AUTHOR("Rayagond Kokatanur "); MODULE_AUTHOR("Giuseppe Cavallaro "); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 3dd8f08..680d2b8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -255,7 +255,7 @@ static const struct of_device_id stmmac_dt_ids[] = { }; MODULE_DEVICE_TABLE(of, stmmac_dt_ids); -static struct platform_driver stmmac_driver = { +struct platform_driver stmmac_pltfr_driver = { .probe = stmmac_pltfr_probe, .remove = stmmac_pltfr_remove, .driver = { @@ -266,8 +266,6 @@ static struct platform_driver stmmac_driver = { }, }; -module_platform_driver(stmmac_driver); - MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet PLATFORM driver"); MODULE_AUTHOR("Giuseppe Cavallaro "); MODULE_LICENSE("GPL"); -- cgit v0.10.2 From 9a43a02648e8414b2a757437820aa928208fc42f Mon Sep 17 00:00:00 2001 From: Andrew Lunn Date: Wed, 6 Jun 2012 06:40:43 +0000 Subject: mv643xx_eth: Fix compile error for architectures without clk. Commit 452503ebc (ARM: Orion: Eth: Add clk/clkdev support.) broke the building of the driver on architectures which don't have clk support. In particular PPC32 Pegasos which uses this driver. Add #ifdef around the clk API usage. Signed-off-by: Andrew Lunn Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 04d901d..f0f06b2 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -436,7 +436,9 @@ struct mv643xx_eth_private { /* * Hardware-specific parameters. */ +#if defined(CONFIG_HAVE_CLK) struct clk *clk; +#endif unsigned int t_clk; }; @@ -2895,17 +2897,17 @@ static int mv643xx_eth_probe(struct platform_device *pdev) mp->dev = dev; /* - * Get the clk rate, if there is one, otherwise use the default. + * Start with a default rate, and if there is a clock, allow + * it to override the default. */ + mp->t_clk = 133000000; +#if defined(CONFIG_HAVE_CLK) mp->clk = clk_get(&pdev->dev, (pdev->id ? "1" : "0")); if (!IS_ERR(mp->clk)) { clk_prepare_enable(mp->clk); mp->t_clk = clk_get_rate(mp->clk); - } else { - mp->t_clk = 133000000; - printk(KERN_WARNING "Unable to get clock"); } - +#endif set_params(mp, pd); netif_set_real_num_tx_queues(dev, mp->txq_count); netif_set_real_num_rx_queues(dev, mp->rxq_count); @@ -2995,10 +2997,13 @@ static int mv643xx_eth_remove(struct platform_device *pdev) phy_detach(mp->phy); cancel_work_sync(&mp->tx_timeout_task); +#if defined(CONFIG_HAVE_CLK) if (!IS_ERR(mp->clk)) { clk_disable_unprepare(mp->clk); clk_put(mp->clk); } +#endif + free_netdev(mp->dev); platform_set_drvdata(pdev, NULL); -- cgit v0.10.2 From dd03cff23d694cfb0fdae80cb618e7ced05ea696 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Bj=C3=B8rn=20Mork?= Date: Tue, 5 Jun 2012 21:18:10 +0000 Subject: net: sierra_net: device IDs for Aircard 320U++ MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Adding device IDs for Aircard 320U and two other devices found in the out-of-tree version of this driver. Cc: linux@sierrawireless.com Cc: Autif Khan Cc: Tom Cassidy Cc: stable@vger.kernel.org Signed-off-by: Bjørn Mork Acked-by: Greg Kroah-Hartman Signed-off-by: David S. Miller diff --git a/drivers/net/usb/sierra_net.c b/drivers/net/usb/sierra_net.c index 3faef56..d75d1f5 100644 --- a/drivers/net/usb/sierra_net.c +++ b/drivers/net/usb/sierra_net.c @@ -946,7 +946,7 @@ struct sk_buff *sierra_net_tx_fixup(struct usbnet *dev, struct sk_buff *skb, } static const u8 sierra_net_ifnum_list[] = { 7, 10, 11 }; -static const struct sierra_net_info_data sierra_net_info_data_68A3 = { +static const struct sierra_net_info_data sierra_net_info_data_direct_ip = { .rx_urb_size = 8 * 1024, .whitelist = { .infolen = ARRAY_SIZE(sierra_net_ifnum_list), @@ -954,7 +954,7 @@ static const struct sierra_net_info_data sierra_net_info_data_68A3 = { } }; -static const struct driver_info sierra_net_info_68A3 = { +static const struct driver_info sierra_net_info_direct_ip = { .description = "Sierra Wireless USB-to-WWAN Modem", .flags = FLAG_WWAN | FLAG_SEND_ZLP, .bind = sierra_net_bind, @@ -962,12 +962,18 @@ static const struct driver_info sierra_net_info_68A3 = { .status = sierra_net_status, .rx_fixup = sierra_net_rx_fixup, .tx_fixup = sierra_net_tx_fixup, - .data = (unsigned long)&sierra_net_info_data_68A3, + .data = (unsigned long)&sierra_net_info_data_direct_ip, }; static const struct usb_device_id products[] = { {USB_DEVICE(0x1199, 0x68A3), /* Sierra Wireless USB-to-WWAN modem */ - .driver_info = (unsigned long) &sierra_net_info_68A3}, + .driver_info = (unsigned long) &sierra_net_info_direct_ip}, + {USB_DEVICE(0x0F3D, 0x68A3), /* AT&T Direct IP modem */ + .driver_info = (unsigned long) &sierra_net_info_direct_ip}, + {USB_DEVICE(0x1199, 0x68AA), /* Sierra Wireless Direct IP LTE modem */ + .driver_info = (unsigned long) &sierra_net_info_direct_ip}, + {USB_DEVICE(0x0F3D, 0x68AA), /* AT&T Direct IP LTE modem */ + .driver_info = (unsigned long) &sierra_net_info_direct_ip}, {}, /* last item */ }; -- cgit v0.10.2 From 55432d2b543a4b6dfae54f5c432a566877a85d90 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Jun 2012 03:00:18 +0000 Subject: inetpeer: fix a race in inetpeer_gc_worker() commit 5faa5df1fa2024 (inetpeer: Invalidate the inetpeer tree along with the routing cache) added a race : Before freeing an inetpeer, we must respect a RCU grace period, and make sure no user will attempt to increase refcnt. inetpeer_invalidate_tree() waits for a RCU grace period before inserting inetpeer tree into gc_list and waking the worker. At that time, no concurrent lookup can find a inetpeer in this tree. Signed-off-by: Eric Dumazet Cc: Steffen Klassert Acked-by: Steffen Klassert Signed-off-by: David S. Miller diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index b94765e..2040bff 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -40,7 +40,10 @@ struct inet_peer { u32 pmtu_orig; u32 pmtu_learned; struct inetpeer_addr_base redirect_learned; - struct list_head gc_list; + union { + struct list_head gc_list; + struct rcu_head gc_rcu; + }; /* * Once inet_peer is queued for deletion (refcnt == -1), following fields * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index d4d61b6..dfba343 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -560,6 +560,17 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout) } EXPORT_SYMBOL(inet_peer_xrlim_allow); +static void inetpeer_inval_rcu(struct rcu_head *head) +{ + struct inet_peer *p = container_of(head, struct inet_peer, gc_rcu); + + spin_lock_bh(&gc_lock); + list_add_tail(&p->gc_list, &gc_list); + spin_unlock_bh(&gc_lock); + + schedule_delayed_work(&gc_work, gc_delay); +} + void inetpeer_invalidate_tree(int family) { struct inet_peer *old, *new, *prev; @@ -576,10 +587,7 @@ void inetpeer_invalidate_tree(int family) prev = cmpxchg(&base->root, old, new); if (prev == old) { base->total = 0; - spin_lock(&gc_lock); - list_add_tail(&prev->gc_list, &gc_list); - spin_unlock(&gc_lock); - schedule_delayed_work(&gc_work, gc_delay); + call_rcu(&prev->gc_rcu, inetpeer_inval_rcu); } out: -- cgit v0.10.2 From d1992b169d31f339dc5ea4e9f312567c8cf322a3 Mon Sep 17 00:00:00 2001 From: Hans Schillstrom Date: Thu, 17 May 2012 22:35:46 +0000 Subject: netfilter: xt_HMARK: fix endianness and provide consistent hashing This patch addresses two issues: a) Fix usage of u32 and __be32 that causes endianess warnings via sparse. b) Ensure consistent hashing in a cluster that is composed of big and little endian systems. Thus, we obtain the same hash mark in an heterogeneous cluster. Reported-by: Dan Carpenter Signed-off-by: Hans Schillstrom Signed-off-by: Pablo Neira Ayuso diff --git a/include/linux/netfilter/xt_HMARK.h b/include/linux/netfilter/xt_HMARK.h index abb1650..826fc58 100644 --- a/include/linux/netfilter/xt_HMARK.h +++ b/include/linux/netfilter/xt_HMARK.h @@ -27,7 +27,12 @@ union hmark_ports { __u16 src; __u16 dst; } p16; + struct { + __be16 src; + __be16 dst; + } b16; __u32 v32; + __be32 b32; }; struct xt_hmark_info { diff --git a/net/netfilter/xt_HMARK.c b/net/netfilter/xt_HMARK.c index 0a96a43..1686ca1 100644 --- a/net/netfilter/xt_HMARK.c +++ b/net/netfilter/xt_HMARK.c @@ -32,13 +32,13 @@ MODULE_ALIAS("ipt_HMARK"); MODULE_ALIAS("ip6t_HMARK"); struct hmark_tuple { - u32 src; - u32 dst; + __be32 src; + __be32 dst; union hmark_ports uports; - uint8_t proto; + u8 proto; }; -static inline u32 hmark_addr6_mask(const __u32 *addr32, const __u32 *mask) +static inline __be32 hmark_addr6_mask(const __be32 *addr32, const __be32 *mask) { return (addr32[0] & mask[0]) ^ (addr32[1] & mask[1]) ^ @@ -46,8 +46,8 @@ static inline u32 hmark_addr6_mask(const __u32 *addr32, const __u32 *mask) (addr32[3] & mask[3]); } -static inline u32 -hmark_addr_mask(int l3num, const __u32 *addr32, const __u32 *mask) +static inline __be32 +hmark_addr_mask(int l3num, const __be32 *addr32, const __be32 *mask) { switch (l3num) { case AF_INET: @@ -58,6 +58,22 @@ hmark_addr_mask(int l3num, const __u32 *addr32, const __u32 *mask) return 0; } +static inline void hmark_swap_ports(union hmark_ports *uports, + const struct xt_hmark_info *info) +{ + union hmark_ports hp; + u16 src, dst; + + hp.b32 = (uports->b32 & info->port_mask.b32) | info->port_set.b32; + src = ntohs(hp.b16.src); + dst = ntohs(hp.b16.dst); + + if (dst > src) + uports->v32 = (dst << 16) | src; + else + uports->v32 = (src << 16) | dst; +} + static int hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t, const struct xt_hmark_info *info) @@ -74,22 +90,19 @@ hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t, otuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; rtuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; - t->src = hmark_addr_mask(otuple->src.l3num, otuple->src.u3.all, - info->src_mask.all); - t->dst = hmark_addr_mask(otuple->src.l3num, rtuple->src.u3.all, - info->dst_mask.all); + t->src = hmark_addr_mask(otuple->src.l3num, otuple->src.u3.ip6, + info->src_mask.ip6); + t->dst = hmark_addr_mask(otuple->src.l3num, rtuple->src.u3.ip6, + info->dst_mask.ip6); if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) return 0; t->proto = nf_ct_protonum(ct); if (t->proto != IPPROTO_ICMP) { - t->uports.p16.src = otuple->src.u.all; - t->uports.p16.dst = rtuple->src.u.all; - t->uports.v32 = (t->uports.v32 & info->port_mask.v32) | - info->port_set.v32; - if (t->uports.p16.dst < t->uports.p16.src) - swap(t->uports.p16.dst, t->uports.p16.src); + t->uports.b16.src = otuple->src.u.all; + t->uports.b16.dst = rtuple->src.u.all; + hmark_swap_ports(&t->uports, info); } return 0; @@ -98,15 +111,19 @@ hmark_ct_set_htuple(const struct sk_buff *skb, struct hmark_tuple *t, #endif } +/* This hash function is endian independent, to ensure consistent hashing if + * the cluster is composed of big and little endian systems. */ static inline u32 hmark_hash(struct hmark_tuple *t, const struct xt_hmark_info *info) { u32 hash; + u32 src = ntohl(t->src); + u32 dst = ntohl(t->dst); - if (t->dst < t->src) - swap(t->src, t->dst); + if (dst < src) + swap(src, dst); - hash = jhash_3words(t->src, t->dst, t->uports.v32, info->hashrnd); + hash = jhash_3words(src, dst, t->uports.v32, info->hashrnd); hash = hash ^ (t->proto & info->proto_mask); return (((u64)hash * info->hmodulus) >> 32) + info->hoffset; @@ -126,11 +143,7 @@ hmark_set_tuple_ports(const struct sk_buff *skb, unsigned int nhoff, if (skb_copy_bits(skb, nhoff, &t->uports, sizeof(t->uports)) < 0) return; - t->uports.v32 = (t->uports.v32 & info->port_mask.v32) | - info->port_set.v32; - - if (t->uports.p16.dst < t->uports.p16.src) - swap(t->uports.p16.dst, t->uports.p16.src); + hmark_swap_ports(&t->uports, info); } #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES) @@ -178,8 +191,8 @@ hmark_pkt_set_htuple_ipv6(const struct sk_buff *skb, struct hmark_tuple *t, return -1; } noicmp: - t->src = hmark_addr6_mask(ip6->saddr.s6_addr32, info->src_mask.all); - t->dst = hmark_addr6_mask(ip6->daddr.s6_addr32, info->dst_mask.all); + t->src = hmark_addr6_mask(ip6->saddr.s6_addr32, info->src_mask.ip6); + t->dst = hmark_addr6_mask(ip6->daddr.s6_addr32, info->dst_mask.ip6); if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) return 0; @@ -255,11 +268,8 @@ hmark_pkt_set_htuple_ipv4(const struct sk_buff *skb, struct hmark_tuple *t, } } - t->src = (__force u32) ip->saddr; - t->dst = (__force u32) ip->daddr; - - t->src &= info->src_mask.ip; - t->dst &= info->dst_mask.ip; + t->src = ip->saddr & info->src_mask.ip; + t->dst = ip->daddr & info->dst_mask.ip; if (info->flags & XT_HMARK_FLAG(XT_HMARK_METHOD_L3)) return 0; -- cgit v0.10.2 From d109e9af61a6d2fdf33dc615ab8b724a8e75a8a4 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 4 Jun 2012 13:31:04 +0200 Subject: netfilter: nf_ct_h323: fix bug in rtcp natting The nat_rtp_rtcp hook takes two separate parameters port and rtp_port. port is expected to be the real h245 address (found inside the packet). rtp_port is the even number closest to port (RTP ports are even and RTCP ports are odd). However currently, both port and rtp_port are having same value (both are rounded to nearest even numbers). This works well in case of openlogicalchannel with media (RTP/even) port. But in case of openlogicalchannel for media control (RTCP/odd) port, h245 address in the packet is wrongly modified to have an even port. I am attaching a pcap demonstrating the problem, for any further analysis. This behavior was introduced around v2.6.19 while rewriting the helper. Signed-off-by: Jagdish Motwani Signed-off-by: Sanket Shah Signed-off-by: Pablo Neira Ayuso diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 46d69d7..31f50bc 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -270,9 +270,8 @@ static int expect_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, return 0; /* RTP port is even */ - port &= htons(~1); - rtp_port = port; - rtcp_port = htons(ntohs(port) + 1); + rtp_port = port & ~htons(1); + rtcp_port = port | htons(1); /* Create expect for RTP */ if ((rtp_exp = nf_ct_expect_alloc(ct)) == NULL) -- cgit v0.10.2 From a06998b88b1651c5f71c0e35f528bf2057188ead Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Jun 2012 00:07:20 +0000 Subject: net: l2tp_eth: fix kernel panic on rmmod l2tp_eth We must prevent module unloading if some devices are still attached to l2tp_eth driver. Signed-off-by: Eric Dumazet Reported-by: Denys Fedoryshchenko Tested-by: Denys Fedoryshchenko Cc: James Chapman Signed-off-by: David S. Miller diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c index 443591d..185f12f 100644 --- a/net/l2tp/l2tp_eth.c +++ b/net/l2tp/l2tp_eth.c @@ -162,6 +162,7 @@ static void l2tp_eth_delete(struct l2tp_session *session) if (dev) { unregister_netdev(dev); spriv->dev = NULL; + module_put(THIS_MODULE); } } } @@ -249,6 +250,7 @@ static int l2tp_eth_create(struct net *net, u32 tunnel_id, u32 session_id, u32 p if (rc < 0) goto out_del_dev; + __module_get(THIS_MODULE); /* Must be done after register_netdev() */ strlcpy(session->ifname, dev->name, IFNAMSIZ); -- cgit v0.10.2 From 4bd6683bd400c8b1d2ad544bb155d86a5d10f91c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Jun 2012 04:58:35 +0000 Subject: net: neighbour: fix neigh_dump_info() Denys found out "ip neigh" output was truncated to about 54 neighbours. Signed-off-by: Eric Dumazet Reported-by: Denys Fedoryshchenko Signed-off-by: David S. Miller diff --git a/net/core/neighbour.c b/net/core/neighbour.c index eb09f8b..d81d026 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2219,9 +2219,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - for (h = 0; h < (1 << nht->hash_shift); h++) { - if (h < s_h) - continue; + for (h = s_h; h < (1 << nht->hash_shift); h++) { if (h > s_h) s_idx = 0; for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; @@ -2260,9 +2258,7 @@ static int pneigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, read_lock_bh(&tbl->lock); - for (h = 0; h <= PNEIGH_HASHMASK; h++) { - if (h < s_h) - continue; + for (h = s_h; h <= PNEIGH_HASHMASK; h++) { if (h > s_h) s_idx = 0; for (n = tbl->phash_buckets[h], idx = 0; n; n = n->next) { @@ -2297,7 +2293,7 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) struct neigh_table *tbl; int t, family, s_t; int proxy = 0; - int err = 0; + int err; read_lock(&neigh_tbl_lock); family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; @@ -2311,7 +2307,7 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; - for (tbl = neigh_tables, t = 0; tbl && (err >= 0); + for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { if (t < s_t || (family && tbl->family != family)) continue; @@ -2322,6 +2318,8 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) err = pneigh_dump_table(tbl, skb, cb); else err = neigh_dump_table(tbl, skb, cb); + if (err < 0) + break; } read_unlock(&neigh_tbl_lock); -- cgit v0.10.2 From 8bd74516b1bd9308c17f67583134d93f777203ca Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Thu, 7 Jun 2012 06:51:04 +0000 Subject: ipv6: fib: Restore NTF_ROUTER exception in fib6_age() Commit 5339ab8b1dd82 (ipv6: fib: Convert fib6_age() to dst_neigh_lookup().) seems to have mistakenly inverted the exception for cached NTF_ROUTER routes. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 0c220a4..74c21b9 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1561,7 +1561,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) neigh_flags = neigh->flags; neigh_release(neigh); } - if (neigh_flags & NTF_ROUTER) { + if (!(neigh_flags & NTF_ROUTER)) { RT6_TRACE("purging route %p via non-router but gateway\n", rt); return -1; -- cgit v0.10.2 From 5ff0feac88ced864f44adb145142269196fa79d9 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 6 Jun 2012 10:01:30 +0000 Subject: sky2: fix checksum bit management on some chips The newer flavors of Yukon II use a different method for receive checksum offload. This is indicated in the driver by the SKY2_HW_NEW_LE flag. On these newer chips, the BMU_ENA_RX_CHKSUM should not be set. The driver would get incorrectly toggle the bit, enabling the old checksum logic on these chips and cause a BUG_ON() assertion. If receive checksum was toggled via ethtool. Reported-by: Kirill Smelkov Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index cace36f..28a5445 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -4381,10 +4381,12 @@ static int sky2_set_features(struct net_device *dev, netdev_features_t features) struct sky2_port *sky2 = netdev_priv(dev); netdev_features_t changed = dev->features ^ features; - if (changed & NETIF_F_RXCSUM) { - bool on = features & NETIF_F_RXCSUM; - sky2_write32(sky2->hw, Q_ADDR(rxqaddr[sky2->port], Q_CSR), - on ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM); + if ((changed & NETIF_F_RXCSUM) && + !(sky2->hw->flags & SKY2_HW_NEW_LE)) { + sky2_write32(sky2->hw, + Q_ADDR(rxqaddr[sky2->port], Q_CSR), + (features & NETIF_F_RXCSUM) + ? BMU_ENA_RX_CHKSUM : BMU_DIS_RX_CHKSUM); } if (changed & NETIF_F_RXHASH) -- cgit v0.10.2 From 278f015e9b67566991d4e831fe38e0ebbeef245e Mon Sep 17 00:00:00 2001 From: Dave Jones Date: Wed, 6 Jun 2012 08:45:59 +0000 Subject: appletalk: Remove out of date message in printk I accidentally triggered this printk, which amused me for a few moments. Given we're post 2.2, we could just -EACCES, but does anyone even care about Appletalk now ? I figure it's better to leave sleeping dogs lie, and just update the message. Signed-off-by: Dave Jones Signed-off-by: David S. Miller diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 0301b32..8685296 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1208,9 +1208,7 @@ static int atalk_connect(struct socket *sock, struct sockaddr *uaddr, if (addr->sat_addr.s_node == ATADDR_BCAST && !sock_flag(sk, SOCK_BROADCAST)) { #if 1 - printk(KERN_WARNING "%s is broken and did not set " - "SO_BROADCAST. It will break when 2.2 is " - "released.\n", + pr_warn("atalk_connect: %s is broken and did not set SO_BROADCAST.\n", current->comm); #else return -EACCES; -- cgit v0.10.2 From 2d8dbb04c63e5369988f008bc4df3359c01d8812 Mon Sep 17 00:00:00 2001 From: Vincent Bernat Date: Tue, 5 Jun 2012 03:41:42 +0000 Subject: snmp: fix OutOctets counter to include forwarded datagrams RFC 4293 defines ipIfStatsOutOctets (similar definition for ipSystemStatsOutOctets): The total number of octets in IP datagrams delivered to the lower layers for transmission. Octets from datagrams counted in ipIfStatsOutTransmits MUST be counted here. And ipIfStatsOutTransmits: The total number of IP datagrams that this entity supplied to the lower layers for transmission. This includes datagrams generated locally and those forwarded by this entity. Therefore, IPSTATS_MIB_OUTOCTETS must be incremented when incrementing IPSTATS_MIB_OUTFORWDATAGRAMS. IP_UPD_PO_STATS is not used since ipIfStatsOutRequests must not include forwarded datagrams: The total number of IP datagrams that local IP user-protocols (including ICMP) supplied to IP in requests for transmission. Note that this counter does not include any datagrams counted in ipIfStatsOutForwDatagrams. Signed-off-by: Vincent Bernat Signed-off-by: David S. Miller diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e5c44fc..ab09b12 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -44,6 +44,7 @@ static int ip_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index a9e519a..c94bbc6 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1574,6 +1574,7 @@ static inline int ipmr_forward_finish(struct sk_buff *skb) struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len); if (unlikely(opt->optlen)) ip_forward_options(skb); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 17b8c67..decc21d1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -526,6 +526,7 @@ int ip6_forward(struct sk_buff *skb) hdr->hop_limit--; IP6_INC_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS_BH(net, ip6_dst_idev(dst), IPSTATS_MIB_OUTOCTETS, skb->len); return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index b15dc08..461e47c 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1886,6 +1886,8 @@ static inline int ip6mr_forward2_finish(struct sk_buff *skb) { IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_OUTFORWDATAGRAMS); + IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_OUTOCTETS, skb->len); return dst_output(skb); } -- cgit v0.10.2 From 33d5e332b9c5ce0bf3bfd44ca2127d1773b3f2ad Mon Sep 17 00:00:00 2001 From: Giuseppe CAVALLARO Date: Thu, 7 Jun 2012 19:25:07 +0000 Subject: stmmac: fix driver built w/ w/o both pci and platf modules The commit ba27ec66ffeb78cbf fixes the Kconfig of the driver when built as module allowing to select/unselect the PCI and Platform modules that are not anymore mutually exclusive. This patch fixes and guarantees that the driver builds on all the platforms w/ w/o PCI and when select/unselect the two stmmac supports. In case of there are some problems on both the configuration and the pci/pltf registration the module_init will fail. v2: set the CONFIG_STMMAC_PLATFORM enabled by default. I've just noticed that this can actually help on some configurations that don't enable any STMMAC options by default (e.g. SPEAr). v3: change printk level when do not register the driver. Reported-by: Fengguang Wu Signed-off-by: Giuseppe Cavallaro Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 0076f77..9f44827 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -15,6 +15,7 @@ if STMMAC_ETH config STMMAC_PLATFORM bool "STMMAC Platform bus support" depends on STMMAC_ETH + default y ---help--- This selects the platform specific bus support for the stmmac device driver. This is the driver used diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 6d07ba2..94b21b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -26,6 +26,7 @@ #include #include #include +#include #include "common.h" #ifdef CONFIG_STMMAC_TIMER #include "stmmac_timer.h" @@ -95,8 +96,6 @@ extern int stmmac_mdio_register(struct net_device *ndev); extern void stmmac_set_ethtool_ops(struct net_device *netdev); extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; -extern struct pci_driver stmmac_pci_driver; -extern struct platform_driver stmmac_pltfr_driver; int stmmac_freeze(struct net_device *ndev); int stmmac_restore(struct net_device *ndev); int stmmac_resume(struct net_device *ndev); @@ -144,3 +143,60 @@ static inline int stmmac_clk_get(struct stmmac_priv *priv) return 0; } #endif /* CONFIG_HAVE_CLK */ + + +#ifdef CONFIG_STMMAC_PLATFORM +extern struct platform_driver stmmac_pltfr_driver; +static inline int stmmac_register_platform(void) +{ + int err; + + err = platform_driver_register(&stmmac_pltfr_driver); + if (err) + pr_err("stmmac: failed to register the platform driver\n"); + + return err; +} +static inline void stmmac_unregister_platform(void) +{ + platform_driver_register(&stmmac_pltfr_driver); +} +#else +static inline int stmmac_register_platform(void) +{ + pr_debug("stmmac: do not register the platf driver\n"); + + return -EINVAL; +} +static inline void stmmac_unregister_platform(void) +{ +} +#endif /* CONFIG_STMMAC_PLATFORM */ + +#ifdef CONFIG_STMMAC_PCI +extern struct pci_driver stmmac_pci_driver; +static inline int stmmac_register_pci(void) +{ + int err; + + err = pci_register_driver(&stmmac_pci_driver); + if (err) + pr_err("stmmac: failed to register the PCI driver\n"); + + return err; +} +static inline void stmmac_unregister_pci(void) +{ + pci_unregister_driver(&stmmac_pci_driver); +} +#else +static inline int stmmac_register_pci(void) +{ + pr_debug("stmmac: do not register the PCI driver\n"); + + return -EINVAL; +} +static inline void stmmac_unregister_pci(void) +{ +} +#endif /* CONFIG_STMMAC_PCI */ diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 3638569..51b3b68 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -42,7 +42,6 @@ #include #include #include -#include #ifdef CONFIG_STMMAC_DEBUG_FS #include #include @@ -2094,25 +2093,29 @@ int stmmac_restore(struct net_device *ndev) } #endif /* CONFIG_PM */ +/* Driver can be configured w/ and w/ both PCI and Platf drivers + * depending on the configuration selected. + */ static int __init stmmac_init(void) { - int err = 0; + int err_plt = 0; + int err_pci = 0; - err = platform_driver_register(&stmmac_pltfr_driver); + err_plt = stmmac_register_platform(); + err_pci = stmmac_register_pci(); - if (!err) { - err = pci_register_driver(&stmmac_pci_driver); - if (err) - platform_driver_unregister(&stmmac_pltfr_driver); + if ((err_pci) && (err_plt)) { + pr_err("stmmac: driver registration failed\n"); + return -EINVAL; } - return err; + return 0; } static void __exit stmmac_exit(void) { - pci_unregister_driver(&stmmac_pci_driver); - platform_driver_unregister(&stmmac_pltfr_driver); + stmmac_unregister_platform(); + stmmac_unregister_pci(); } module_init(stmmac_init); -- cgit v0.10.2 From 6a2b28ef036ab5c66fdc606fe97d9e5cb34ea409 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 8 Jun 2012 00:28:16 -0700 Subject: Revert "niu: Add support for byte queue limits." This reverts commit efa230f2c68abab817f13473077f8d0cc74f43f3. BQL doesn't work with how this driver currently only takes TX interrupts every 1/4 of the TX ring. That behavior needs to be fixed, but that's a larger non-trivial task and for now we have to revert BQL support as this makes the device currently completely unusable. Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 703c8cc..8c726b7 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3598,7 +3598,6 @@ static int release_tx_packet(struct niu *np, struct tx_ring_info *rp, int idx) static void niu_tx_work(struct niu *np, struct tx_ring_info *rp) { struct netdev_queue *txq; - unsigned int tx_bytes; u16 pkt_cnt, tmp; int cons, index; u64 cs; @@ -3621,18 +3620,12 @@ static void niu_tx_work(struct niu *np, struct tx_ring_info *rp) netif_printk(np, tx_done, KERN_DEBUG, np->dev, "%s() pkt_cnt[%u] cons[%d]\n", __func__, pkt_cnt, cons); - tx_bytes = 0; - tmp = pkt_cnt; - while (tmp--) { - tx_bytes += rp->tx_buffs[cons].skb->len; + while (pkt_cnt--) cons = release_tx_packet(np, rp, cons); - } rp->cons = cons; smp_mb(); - netdev_tx_completed_queue(txq, pkt_cnt, tx_bytes); - out: if (unlikely(netif_tx_queue_stopped(txq) && (niu_tx_avail(rp) > NIU_TX_WAKEUP_THRESH(rp)))) { @@ -4333,7 +4326,6 @@ static void niu_free_channels(struct niu *np) struct tx_ring_info *rp = &np->tx_rings[i]; niu_free_tx_ring_info(np, rp); - netdev_tx_reset_queue(netdev_get_tx_queue(np->dev, i)); } kfree(np->tx_rings); np->tx_rings = NULL; @@ -6739,8 +6731,6 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, prod = NEXT_TX(rp, prod); } - netdev_tx_sent_queue(txq, skb->len); - if (prod < rp->prod) rp->wrap_bit ^= TX_RING_KICK_WRAP; rp->prod = prod; -- cgit v0.10.2 From aac495a8002bbf20e879572c6cf0789ab2ffb32b Mon Sep 17 00:00:00 2001 From: Stanislav Yakovlev Date: Mon, 14 May 2012 19:06:19 -0400 Subject: net/wireless: ipw2100: Fix WARN_ON occurring in wiphy_register called by ipw2100_pci_init_one The problem was found by Larry Finger: http://marc.info/?l=linux-wireless&m=133702401700614&w=2 The problem is identical to the one for ipw2200 which is already fixed: http://marc.info/?l=linux-wireless&m=133457257407196&w=2 [ 17.766431] ------------[ cut here ]------------ [ 17.766467] WARNING: at net/wireless/core.c:562 wiphy_register+0x34c/0x3c0 [cfg80211]() [ 17.766471] Hardware name: Latitude D600 [ 17.766474] Modules linked in: ipw2100(+) libipw pcmcia cfg80211 ppdev parport_pc yenta_socket sr_mod pcmcia_rsrc parport iTCO_wdt cdrom sg rfkill pcmcia_ core lib80211 tg3 video button battery ac iTCO_vendor_support joydev shpchp pcspkr pciehp pci_hotplug autofs4 radeon ttm drm_kms_helper uhci_hcd ehci_hcd rtc _cmos thermal drm hwmon i2c_algo_bit i2c_core processor usbcore usb_common ata_generic ata_piix ahci libahci libata [ 17.766525] Pid: 474, comm: modprobe Not tainted 3.4.0-rc7-wl+ #6 [ 17.766528] Call Trace: [ 17.766541] [] ? printk+0x28/0x2a [ 17.766552] [] warn_slowpath_common+0x6d/0xa0 [ 17.766563] [] ? wiphy_register+0x34c/0x3c0 [cfg80211] [ 17.766573] [] ? wiphy_register+0x34c/0x3c0 [cfg80211] [ 17.766578] [] warn_slowpath_null+0x1d/0x20 [ 17.766588] [] wiphy_register+0x34c/0x3c0 [cfg80211] [ 17.766605] [] ipw2100_wdev_init+0x196/0x1c0 [ipw2100] [ 17.766616] [] ipw2100_pci_init_one+0x2b2/0x694 [ipw2100] [ 17.766632] [] local_pci_probe+0x42/0xb0 [ 17.766637] [] pci_device_probe+0x60/0x90 [ 17.766645] [] ? sysfs_create_link+0x12/0x20 [ 17.766654] [] really_probe+0x56/0x2e0 [ 17.766659] [] ? create_dir+0x5d/0xa0 [ 17.766667] [] ? pm_runtime_barrier+0x3b/0xa0 [ 17.766672] [] driver_probe_device+0x44/0xa0 [ 17.766677] [] ? pci_match_device+0x97/0xa0 [ 17.766681] [] __driver_attach+0x89/0x90 [ 17.766686] [] ? driver_probe_device+0xa0/0xa0 [ 17.766691] [] bus_for_each_dev+0x3a/0x70 [ 17.766695] [] driver_attach+0x1c/0x30 [ 17.766699] [] ? driver_probe_device+0xa0/0xa0 [ 17.766704] [] bus_add_driver+0x187/0x280 [ 17.766710] [] ? kset_find_obj+0x2d/0x60 [ 17.766715] [] ? pci_device_probe+0x90/0x90 [ 17.766719] [] ? pci_device_probe+0x90/0x90 [ 17.766724] [] driver_register+0x65/0x110 [ 17.766729] [] __pci_register_driver+0x3d/0xa0 [ 17.766738] [] ipw2100_init+0x5c/0x1000 [ipw2100] [ 17.766743] [] do_one_initcall+0x2f/0x170 [ 17.766749] [] ? 0xe09f6fff [ 17.766757] [] sys_init_module+0xa8/0x210 [ 17.766766] [] syscall_call+0x7/0xb [ 17.766769] ---[ end trace 559898c6bb0d1c75 ]--- [ 17.767093] ipw2100: probe of 0000:02:03.0 failed with error -5 This warning appears only if we apply Ben Hutchings' fix http://marc.info/?l=linux-wireless&m=132720204412667&w=2 for the bug reported by Cesare Leonardi http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=656813 with cfg80211 warning during device registration ("cfg80211: failed to add phy80211 symlink to netdev!"). We separate device bring up and registration with network stack to avoid the problem. Signed-off-by: Stanislav Yakovlev Tested-by: Larry Finger Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c index 9cfae0c..95aa8e1 100644 --- a/drivers/net/wireless/ipw2x00/ipw2100.c +++ b/drivers/net/wireless/ipw2x00/ipw2100.c @@ -1903,14 +1903,6 @@ static void ipw2100_down(struct ipw2100_priv *priv) netif_stop_queue(priv->net_dev); } -/* Called by register_netdev() */ -static int ipw2100_net_init(struct net_device *dev) -{ - struct ipw2100_priv *priv = libipw_priv(dev); - - return ipw2100_up(priv, 1); -} - static int ipw2100_wdev_init(struct net_device *dev) { struct ipw2100_priv *priv = libipw_priv(dev); @@ -6087,7 +6079,6 @@ static const struct net_device_ops ipw2100_netdev_ops = { .ndo_stop = ipw2100_close, .ndo_start_xmit = libipw_xmit, .ndo_change_mtu = libipw_change_mtu, - .ndo_init = ipw2100_net_init, .ndo_tx_timeout = ipw2100_tx_timeout, .ndo_set_mac_address = ipw2100_set_address, .ndo_validate_addr = eth_validate_addr, @@ -6329,6 +6320,10 @@ static int ipw2100_pci_init_one(struct pci_dev *pci_dev, printk(KERN_INFO DRV_NAME ": Detected Intel PRO/Wireless 2100 Network Connection\n"); + err = ipw2100_up(priv, 1); + if (err) + goto fail; + err = ipw2100_wdev_init(dev); if (err) goto fail; @@ -6338,12 +6333,7 @@ static int ipw2100_pci_init_one(struct pci_dev *pci_dev, * network device we would call ipw2100_up. This introduced a race * condition with newer hotplug configurations (network was coming * up and making calls before the device was initialized). - * - * If we called ipw2100_up before we registered the device, then the - * device name wasn't registered. So, we instead use the net_dev->init - * member to call a function that then just turns and calls ipw2100_up. - * net_dev->init is called after name allocation but before the - * notifier chain is called */ + */ err = register_netdev(dev); if (err) { printk(KERN_WARNING DRV_NAME -- cgit v0.10.2 From 0fde0a8cfd0ede7f310d6a681c8e5a7cb3e32406 Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Wed, 16 May 2012 11:06:21 +0200 Subject: rtl8187: ->brightness_set can not sleep Fix: BUG: sleeping function called from invalid context at kernel/workqueue.c:2547 in_atomic(): 1, irqs_disabled(): 0, pid: 629, name: wpa_supplicant 2 locks held by wpa_supplicant/629: #0: (rtnl_mutex){+.+.+.}, at: [] rtnl_lock+0x14/0x20 #1: (&trigger->leddev_list_lock){.+.?..}, at: [] led_trigger_event+0x21/0x80 Pid: 629, comm: wpa_supplicant Not tainted 3.3.0-0.rc3.git5.1.fc17.i686 Call Trace: [] __might_sleep+0x126/0x1d0 [] wait_on_work+0x2c/0x1d0 [] __cancel_work_timer+0x6a/0x120 [] cancel_delayed_work_sync+0x10/0x20 [] rtl8187_led_brightness_set+0x82/0xf0 [rtl8187] [] led_trigger_event+0x5c/0x80 [] ieee80211_led_radio+0x1d/0x40 [mac80211] [] ieee80211_stop_device+0x13/0x230 [mac80211] Removing _sync is ok, because if led_on work is currently running it will be finished before led_off work start to perform, since they are always queued on the same mac80211 local->workqueue. Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=795176 Signed-off-by: Stanislaw Gruszka Acked-by: Larry Finger Acked-by: Hin-Tak Leung Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/rtl818x/rtl8187/leds.c b/drivers/net/wireless/rtl818x/rtl8187/leds.c index 2e0de2f..c2d5b49 100644 --- a/drivers/net/wireless/rtl818x/rtl8187/leds.c +++ b/drivers/net/wireless/rtl818x/rtl8187/leds.c @@ -117,7 +117,7 @@ static void rtl8187_led_brightness_set(struct led_classdev *led_dev, radio_on = true; } else if (radio_on) { radio_on = false; - cancel_delayed_work_sync(&priv->led_on); + cancel_delayed_work(&priv->led_on); ieee80211_queue_delayed_work(hw, &priv->led_off, 0); } } else if (radio_on) { -- cgit v0.10.2 From 06cf5c4c5bea549235da1aace86b90d4ad0084f8 Mon Sep 17 00:00:00 2001 From: Qasim Javed Date: Tue, 5 Jun 2012 01:25:44 -0500 Subject: mac80211_hwsim: Set IEEE80211_STAT_ACK flag when userspace indicates that the frame has been acknowledged. The station fail average is not updated correctly since the IEEE80211_STAT_ACK flag is not set when using wmediumd with mac80211_hwsim. Set this flag when wmediumd indicates that the frame was successfully transmitted (eventually). Signed-off-by: Qasim Javed Signed-off-by: Javier Cardona Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 4c9336c..a0b7cfd 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -1555,6 +1555,7 @@ static int hwsim_tx_info_frame_received_nl(struct sk_buff *skb_2, hdr = (struct ieee80211_hdr *) skb->data; mac80211_hwsim_monitor_ack(data2->hw, hdr->addr2); } + txi->flags |= IEEE80211_TX_STAT_ACK; } ieee80211_tx_status_irqsafe(data2->hw, skb); return 0; -- cgit v0.10.2 From ce466579b1c92fce78bf5f74a3707f46e228d949 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Tue, 5 Jun 2012 15:42:55 +0200 Subject: wireless: add my new trees to MAINTAINERS Add my new trees to the MAINTAINERS file for the components that I maintain in the new trees. Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/MAINTAINERS b/MAINTAINERS index 55f0fda..03660de 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1800,6 +1800,9 @@ F: include/linux/cfag12864b.h CFG80211 and NL80211 M: Johannes Berg L: linux-wireless@vger.kernel.org +W: http://wireless.kernel.org/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained F: include/linux/nl80211.h F: include/net/cfg80211.h @@ -4340,7 +4343,8 @@ MAC80211 M: Johannes Berg L: linux-wireless@vger.kernel.org W: http://linuxwireless.org/ -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained F: Documentation/networking/mac80211-injection.txt F: include/net/mac80211.h @@ -4351,7 +4355,8 @@ M: Stefano Brivio M: Mattias Nissler L: linux-wireless@vger.kernel.org W: http://linuxwireless.org/en/developers/Documentation/mac80211/RateControl/PID -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained F: net/mac80211/rc80211_pid* @@ -5695,6 +5700,9 @@ F: include/linux/remoteproc.h RFKILL M: Johannes Berg L: linux-wireless@vger.kernel.org +W: http://wireless.kernel.org/ +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jberg/mac80211-next.git S: Maintained F: Documentation/rfkill.txt F: net/rfkill/ -- cgit v0.10.2 From d2c8b15d0cb486f4938ba7f2af349d9d1220cb10 Mon Sep 17 00:00:00 2001 From: Meenakshi Venkataraman Date: Tue, 5 Jun 2012 20:24:37 +0200 Subject: iwlwifi: use correct supported firmware for 6035 and 6000g2 My patch iwlwifi: use correct released ucode version did not correctly report supported firmware for the 6035 device. This patch fixes it. The minimum supported firmware version for 6035 is v6. Also correct the minimum supported firmware version for the 6000g2 series of devices. Cc: stable@kernel.org Signed-off-by: Meenakshi Venkataraman Reviewed-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index 19f7ee8..e5e8ada 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -35,17 +35,20 @@ #define IWL6000_UCODE_API_MAX 6 #define IWL6050_UCODE_API_MAX 5 #define IWL6000G2_UCODE_API_MAX 6 +#define IWL6035_UCODE_API_MAX 6 /* Oldest version we won't warn about */ #define IWL6000_UCODE_API_OK 4 #define IWL6000G2_UCODE_API_OK 5 #define IWL6050_UCODE_API_OK 5 #define IWL6000G2B_UCODE_API_OK 6 +#define IWL6035_UCODE_API_OK 6 /* Lowest firmware API version supported */ #define IWL6000_UCODE_API_MIN 4 #define IWL6050_UCODE_API_MIN 4 -#define IWL6000G2_UCODE_API_MIN 4 +#define IWL6000G2_UCODE_API_MIN 5 +#define IWL6035_UCODE_API_MIN 6 /* EEPROM versions */ #define EEPROM_6000_TX_POWER_VERSION (4) @@ -227,9 +230,25 @@ const struct iwl_cfg iwl6030_2bg_cfg = { IWL_DEVICE_6030, }; +#define IWL_DEVICE_6035 \ + .fw_name_pre = IWL6030_FW_PRE, \ + .ucode_api_max = IWL6035_UCODE_API_MAX, \ + .ucode_api_ok = IWL6035_UCODE_API_OK, \ + .ucode_api_min = IWL6035_UCODE_API_MIN, \ + .device_family = IWL_DEVICE_FAMILY_6030, \ + .max_inst_size = IWL60_RTC_INST_SIZE, \ + .max_data_size = IWL60_RTC_DATA_SIZE, \ + .eeprom_ver = EEPROM_6030_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6030_TX_POWER_VERSION, \ + .base_params = &iwl6000_g2_base_params, \ + .bt_params = &iwl6000_bt_params, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true + const struct iwl_cfg iwl6035_2agn_cfg = { .name = "Intel(R) Centrino(R) Advanced-N 6235 AGN", - IWL_DEVICE_6030, + IWL_DEVICE_6035, .ht_params = &iwl6000_ht_params, }; -- cgit v0.10.2 From e64add27e1b4874f589e550b4e0ca6715070373f Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Tue, 5 Jun 2012 20:39:32 +0200 Subject: b43: do not call ieee80211_unregister_hw if we are not registred this patch fixes kernel Oops on "rmmod b43" if firmware was not loaded: BUG: unable to handle kernel NULL pointer dereference at 0000000000000088 IP: [] drain_workqueue+0x25/0x142 PGD 153ac6067 PUD 153b82067 PMD 0 Oops: 0000 [#1] SMP Signed-off-by: Oleksij Rempel Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/b43/b43.h b/drivers/net/wireless/b43/b43.h index 67c13af..c06b6cb 100644 --- a/drivers/net/wireless/b43/b43.h +++ b/drivers/net/wireless/b43/b43.h @@ -877,6 +877,10 @@ struct b43_wl { * from the mac80211 subsystem. */ u16 mac80211_initially_registered_queues; + /* Set this if we call ieee80211_register_hw() and check if we call + * ieee80211_unregister_hw(). */ + bool hw_registred; + /* We can only have one operating interface (802.11 core) * at a time. General information about this interface follows. */ diff --git a/drivers/net/wireless/b43/main.c b/drivers/net/wireless/b43/main.c index 5a39b22..acd03a4 100644 --- a/drivers/net/wireless/b43/main.c +++ b/drivers/net/wireless/b43/main.c @@ -2437,6 +2437,7 @@ start_ieee80211: err = ieee80211_register_hw(wl->hw); if (err) goto err_one_core_detach; + wl->hw_registred = true; b43_leds_register(wl->current_dev); goto out; @@ -5299,6 +5300,7 @@ static struct b43_wl *b43_wireless_init(struct b43_bus_dev *dev) hw->queues = modparam_qos ? B43_QOS_QUEUE_NUM : 1; wl->mac80211_initially_registered_queues = hw->queues; + wl->hw_registred = false; hw->max_rates = 2; SET_IEEE80211_DEV(hw, dev->dev); if (is_valid_ether_addr(sprom->et1mac)) @@ -5370,12 +5372,15 @@ static void b43_bcma_remove(struct bcma_device *core) * as the ieee80211 unreg will destroy the workqueue. */ cancel_work_sync(&wldev->restart_work); - /* Restore the queues count before unregistering, because firmware detect - * might have modified it. Restoring is important, so the networking - * stack can properly free resources. */ - wl->hw->queues = wl->mac80211_initially_registered_queues; - b43_leds_stop(wldev); - ieee80211_unregister_hw(wl->hw); + B43_WARN_ON(!wl); + if (wl->current_dev == wldev && wl->hw_registred) { + /* Restore the queues count before unregistering, because firmware detect + * might have modified it. Restoring is important, so the networking + * stack can properly free resources. */ + wl->hw->queues = wl->mac80211_initially_registered_queues; + b43_leds_stop(wldev); + ieee80211_unregister_hw(wl->hw); + } b43_one_core_detach(wldev->dev); @@ -5446,7 +5451,7 @@ static void b43_ssb_remove(struct ssb_device *sdev) cancel_work_sync(&wldev->restart_work); B43_WARN_ON(!wl); - if (wl->current_dev == wldev) { + if (wl->current_dev == wldev && wl->hw_registred) { /* Restore the queues count before unregistering, because firmware detect * might have modified it. Restoring is important, so the networking * stack can properly free resources. */ -- cgit v0.10.2 From e7027075d0d8fe2d1bf7b0db24623328d2601d3c Mon Sep 17 00:00:00 2001 From: Hauke Mehrtens Date: Tue, 5 Jun 2012 20:58:20 +0200 Subject: bcma: fix null pointer in bcma_core_pci_irq_ctl pc could be null if hosttype != BCMA_HOSTTYPE_PCI. If we are on a device without a pci core this function is called with pc = null by b43 and brcmsmac. If the host type is PCI we have a pci core as well and pc can not be null. Signed-off-by: Hauke Mehrtens Signed-off-by: John W. Linville diff --git a/drivers/bcma/driver_pci.c b/drivers/bcma/driver_pci.c index 9a96f14..c32ebd5 100644 --- a/drivers/bcma/driver_pci.c +++ b/drivers/bcma/driver_pci.c @@ -232,17 +232,19 @@ void __devinit bcma_core_pci_init(struct bcma_drv_pci *pc) int bcma_core_pci_irq_ctl(struct bcma_drv_pci *pc, struct bcma_device *core, bool enable) { - struct pci_dev *pdev = pc->core->bus->host_pci; + struct pci_dev *pdev; u32 coremask, tmp; int err = 0; - if (core->bus->hosttype != BCMA_HOSTTYPE_PCI) { + if (!pc || core->bus->hosttype != BCMA_HOSTTYPE_PCI) { /* This bcma device is not on a PCI host-bus. So the IRQs are * not routed through the PCI core. * So we must not enable routing through the PCI core. */ goto out; } + pdev = pc->core->bus->host_pci; + err = pci_read_config_dword(pdev, BCMA_PCI_IRQMASK, &tmp); if (err) goto out; -- cgit v0.10.2 From d6ee27eb13beab94056e0de52d81220058ca2297 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 6 Jun 2012 09:13:36 +0200 Subject: iwlwifi: don't mess up the SCD when removing a key When we remove a key, we put a key index which was supposed to tell the fw that we are actually removing the key. But instead the fw took that index as a valid index and messed up the SRAM of the device. This memory corruption on the device mangled the data of the SCD. The impact on the user is that SCD queue 2 got stuck after having removed keys. The message is the log that was printed is: Queue 2 stuck for 10000ms This doesn't seem to fix the higher queues that get stuck from time to time. Cc: stable@vger.kernel.org [2.6.27+] Reviewed-by: Meenakshi Venkataraman Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c index aea07aa..eb6a8ea 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-sta.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-sta.c @@ -1267,7 +1267,7 @@ int iwl_remove_dynamic_key(struct iwl_priv *priv, key_flags |= STA_KEY_MULTICAST_MSK; sta_cmd.key.key_flags = key_flags; - sta_cmd.key.key_offset = WEP_INVALID_OFFSET; + sta_cmd.key.key_offset = keyconf->hw_key_idx; sta_cmd.sta.modify_mask = STA_MODIFY_KEY_MASK; sta_cmd.mode = STA_CONTROL_MODIFY_MSK; -- cgit v0.10.2 From d012d04e4d6312ea157b6cf19e9689af934f5aa7 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 6 Jun 2012 13:55:02 +0200 Subject: iwlwifi: disable the buggy chain extension feature in HW This feature has been reported to be buggy and enabled by default. We therefore need to disable it manually. Cc: stable@vger.kernel.org Signed-off-by: Emmanuel Grumbach Signed-off-by: Johannes Berg Signed-off-by: John W. Linville diff --git a/drivers/net/wireless/iwlwifi/iwl-prph.h b/drivers/net/wireless/iwlwifi/iwl-prph.h index 3b106929..dfd5466 100644 --- a/drivers/net/wireless/iwlwifi/iwl-prph.h +++ b/drivers/net/wireless/iwlwifi/iwl-prph.h @@ -224,6 +224,7 @@ #define SCD_TXFACT (SCD_BASE + 0x10) #define SCD_ACTIVE (SCD_BASE + 0x14) #define SCD_QUEUECHAIN_SEL (SCD_BASE + 0xe8) +#define SCD_CHAINEXT_EN (SCD_BASE + 0x244) #define SCD_AGGR_SEL (SCD_BASE + 0x248) #define SCD_INTERRUPT_MASK (SCD_BASE + 0x108) diff --git a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c index ec6fb39..79c6b91 100644 --- a/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c +++ b/drivers/net/wireless/iwlwifi/iwl-trans-pcie.c @@ -1058,6 +1058,11 @@ static void iwl_tx_start(struct iwl_trans *trans) iwl_write_prph(trans, SCD_DRAM_BASE_ADDR, trans_pcie->scd_bc_tbls.dma >> 10); + /* The chain extension of the SCD doesn't work well. This feature is + * enabled by default by the HW, so we need to disable it manually. + */ + iwl_write_prph(trans, SCD_CHAINEXT_EN, 0); + /* Enable DMA channel */ for (chan = 0; chan < FH_TCSR_CHNL_NUM ; chan++) iwl_write_direct32(trans, FH_TCSR_CHNL_TX_CONFIG_REG(chan), -- cgit v0.10.2 From 58d1eab7ef1d7ff8e448699dfd1a21b7f3303296 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Wed, 6 Jun 2012 23:02:55 +0200 Subject: NFC: Fix possible NULL ptr deref when getting the name of a socket llcp_sock_getname() might get called before the LLCP socket was created. This condition isn't checked, and llcp_sock_getname will simply deref a NULL ptr in that case. This exists starting with d646960 ("NFC: Initial LLCP support"). Signed-off-by: Sasha Levin Signed-off-by: John W. Linville diff --git a/net/nfc/llcp/sock.c b/net/nfc/llcp/sock.c index 3f339b1..17a707d 100644 --- a/net/nfc/llcp/sock.c +++ b/net/nfc/llcp/sock.c @@ -292,6 +292,9 @@ static int llcp_sock_getname(struct socket *sock, struct sockaddr *addr, pr_debug("%p\n", sk); + if (llcp_sock == NULL) + return -EBADFD; + addr->sa_family = AF_NFC; *len = sizeof(struct sockaddr_nfc_llcp); -- cgit v0.10.2 From 6aee4ca3d2217d3f76469e5ed576d62695f0912a Mon Sep 17 00:00:00 2001 From: Stanislaw Gruszka Date: Thu, 7 Jun 2012 14:47:21 +0200 Subject: mac80211: add back channel change flag commit 24398e39c8ee4a9d9123eed322b859ece4d16cac Author: Johannes Berg Date: Wed Mar 28 10:58:36 2012 +0200 mac80211: set HT channel before association removed IEEE80211_CONF_CHANGE_CHANNEL argument from ieee80211_hw_config, which is required by iwl4965 driver, otherwise that driver does not configure channel properly and is not able to associate. Signed-off-by: Stanislaw Gruszka Signed-off-by: John W. Linville diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index d94627c..91d84cc 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -3124,7 +3124,7 @@ static int ieee80211_prep_connection(struct ieee80211_sub_if_data *sdata, } local->oper_channel = cbss->channel; - ieee80211_hw_config(local, 0); + ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_CHANNEL); if (!have_sta) { u32 rates = 0, basic_rates = 0; -- cgit v0.10.2 From 4399a4df98a63e30fd16e9d0cecc46ea92269e8f Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 8 Jun 2012 06:25:00 +0000 Subject: l2tp: fix a race in l2tp_ip_sendmsg() Commit 081b1b1bb27f (l2tp: fix l2tp_ip_sendmsg() route handling) added a race, in case IP route cache is disabled. In this case, we should not do the dst_release(&rt->dst), since it'll free the dst immediately, instead of waiting a RCU grace period. Signed-off-by: Eric Dumazet Cc: James Chapman Cc: Denys Fedoryshchenko Signed-off-by: David S. Miller diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 70614e7..61d8b75 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -464,10 +464,12 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; - if (connected) + if (connected) { sk_setup_caps(sk, &rt->dst); - else - dst_release(&rt->dst); /* safe since we hold rcu_read_lock */ + } else { + skb_dst_set(skb, &rt->dst); + goto xmit; + } } /* We dont need to clone dst here, it is guaranteed to not disappear. @@ -475,6 +477,7 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m */ skb_dst_set_noref(skb, &rt->dst); +xmit: /* Queue the packet to IP for output */ rc = ip_queue_xmit(skb, &inet->cork.fl); rcu_read_unlock(); -- cgit v0.10.2 From cd8f76c0a0c6fce0b2cf23c9bd0123f91453f46d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 7 Jun 2012 22:59:59 +0000 Subject: be2net: fix a race in be_xmit() As soon as hardware is notified of a transmit, we no longer can assume skb can be dereferenced, as TX completion might have freed the packet. Signed-off-by: Eric Dumazet Cc: Sathya Perla Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 08efd30..fdb50ce 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -736,6 +736,8 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, copied = make_tx_wrbs(adapter, txq, skb, wrb_cnt, dummy_wrb); if (copied) { + int gso_segs = skb_shinfo(skb)->gso_segs; + /* record the sent skb in the sent_skb table */ BUG_ON(txo->sent_skb_list[start]); txo->sent_skb_list[start] = skb; @@ -753,8 +755,7 @@ static netdev_tx_t be_xmit(struct sk_buff *skb, be_txq_notify(adapter, txq->id, wrb_cnt); - be_tx_stats_update(txo, wrb_cnt, copied, - skb_shinfo(skb)->gso_segs, stopped); + be_tx_stats_update(txo, wrb_cnt, copied, gso_segs, stopped); } else { txq->head = start; dev_kfree_skb_any(skb); -- cgit v0.10.2 From c6c4b97c6b7003e8082dd43db224c1d1f7a24aa2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 8 Jun 2012 14:01:44 +0000 Subject: net/core: fix kernel-doc warnings Fix kernel-doc warnings in net/core: Warning(net/core/skbuff.c:3368): No description found for parameter 'delta_truesize' Warning(net/core/filter.c:628): No description found for parameter 'pfp' Warning(net/core/filter.c:628): Excess function parameter 'sk' description in 'sk_unattached_filter_create' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller diff --git a/net/core/filter.c b/net/core/filter.c index a3eddb5..d4ce2dc 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -616,9 +616,9 @@ static int __sk_prepare_filter(struct sk_filter *fp) /** * sk_unattached_filter_create - create an unattached filter * @fprog: the filter program - * @sk: the socket to use + * @pfp: the unattached filter that is created * - * Create a filter independent ofr any socket. We first run some + * Create a filter independent of any socket. We first run some * sanity checks on it to make sure it does not explode on us later. * If an error occurs or there is insufficient memory for the filter * a negative errno code is returned. On success the return is zero. diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 016694d..d78671e 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3361,7 +3361,7 @@ EXPORT_SYMBOL(kfree_skb_partial); * @to: prior buffer * @from: buffer to add * @fragstolen: pointer to boolean - * + * @delta_truesize: how much more was allocated than was requested */ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, bool *fragstolen, int *delta_truesize) -- cgit v0.10.2 From f41ef2e7dc4515777810016612316c38f84275e7 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Fri, 8 Jun 2012 14:07:19 +0000 Subject: netdev: fix drivers/net/phy/ kernel-doc warnings Fix kernel-doc warnings in drivers/net/phy: Warning(drivers/net/phy/mdio_bus.c:109): No description found for parameter 'mdio_bus_np' Warning(drivers/net/phy/mdio_bus.c:109): Excess function parameter 'mdio_np' description in 'of_mdio_find_bus' Signed-off-by: Randy Dunlap Signed-off-by: David S. Miller diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index 683ef1c..5061608 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -96,7 +96,7 @@ static int of_mdio_bus_match(struct device *dev, void *mdio_bus_np) } /** * of_mdio_find_bus - Given an mii_bus node, find the mii_bus. - * @mdio_np: Pointer to the mii_bus. + * @mdio_bus_np: Pointer to the mii_bus. * * Returns a pointer to the mii_bus, or NULL if none found. * -- cgit v0.10.2 From 8876d6b5f81f4e242a6660da22bbd92f17a8d058 Mon Sep 17 00:00:00 2001 From: Paul Pluzhnikov Date: Sat, 9 Jun 2012 07:53:03 -0700 Subject: net: Make linux/tcp.h C++ friendly (trivial) I originally sent this patch to , but Jiri Kosina did not feel that this is fully appropriate for the trivial tree. Using linux/tcp.h from C++ results in: cat t.cc #include int main() { } g++ -c t.cc In file included from t.cc:1: /usr/include/linux/tcp.h:72: error: '__u32 __fswab32(__u32)' cannot appear in a constant-expression /usr/include/linux/tcp.h:72: error: a function call cannot appear in a constant-expression ... Attached trivial patch fixes this problem. Tested: - the t.cc above compiles with g++ and - the following program generates the same output before/after the patch: #include #include int main () { #define P(a) printf("%s: %08x\n", #a, (int)a) P(TCP_FLAG_CWR); P(TCP_FLAG_ECE); P(TCP_FLAG_URG); P(TCP_FLAG_ACK); P(TCP_FLAG_PSH); P(TCP_FLAG_RST); P(TCP_FLAG_SYN); P(TCP_FLAG_FIN); P(TCP_RESERVED_BITS); P(TCP_DATA_OFFSET); #undef P return 0; } Signed-off-by: Paul Pluzhnikov Signed-off-by: David S. Miller diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 4c5b632..5f359db 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -69,16 +69,16 @@ union tcp_word_hdr { #define tcp_flag_word(tp) ( ((union tcp_word_hdr *)(tp))->words [3]) enum { - TCP_FLAG_CWR = __cpu_to_be32(0x00800000), - TCP_FLAG_ECE = __cpu_to_be32(0x00400000), - TCP_FLAG_URG = __cpu_to_be32(0x00200000), - TCP_FLAG_ACK = __cpu_to_be32(0x00100000), - TCP_FLAG_PSH = __cpu_to_be32(0x00080000), - TCP_FLAG_RST = __cpu_to_be32(0x00040000), - TCP_FLAG_SYN = __cpu_to_be32(0x00020000), - TCP_FLAG_FIN = __cpu_to_be32(0x00010000), - TCP_RESERVED_BITS = __cpu_to_be32(0x0F000000), - TCP_DATA_OFFSET = __cpu_to_be32(0xF0000000) + TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), + TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), + TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), + TCP_FLAG_ACK = __constant_cpu_to_be32(0x00100000), + TCP_FLAG_PSH = __constant_cpu_to_be32(0x00080000), + TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000), + TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000), + TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), + TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), + TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) }; /* -- cgit v0.10.2 From 7dbb491878a2c51d372a8890fa45a8ff80358af1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?fran=C3=A7ois=20romieu?= Date: Sat, 9 Jun 2012 10:53:16 +0000 Subject: r8169: avoid NAPI scheduling delay. While reworking the r8169 driver a few months ago to perform the smallest amount of work in the irq handler, I took care of avoiding any irq mask register operation in the slow work dedicated user context thread. The slow work thread scheduled an extra round of NAPI work which would ultimately set the irq mask register as required, thus keeping such irq mask operations in the NAPI handler. It would eventually race with the irq handler and delay NAPI execution for - assuming no further irq - a whole ksoftirqd period. Mildly a problem for rare link changes or corner case PCI events. The race was always lost after the last bh disabling lock had been removed from the work thread and people started wondering where those pesky "NOHZ: local_softirq_pending 08" messages came from. Actually the irq mask register _can_ be set up directly in the slow work thread. Signed-off-by: Francois Romieu Reported-by: Dave Jones Tested-by: Marc Dionne Cc: Thomas Gleixner Cc: Hayes Wang Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 9757ce3..7260aa7 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -5889,11 +5889,7 @@ static void rtl_slow_event_work(struct rtl8169_private *tp) if (status & LinkChg) __rtl8169_check_link_status(dev, tp, tp->mmio_addr, true); - napi_disable(&tp->napi); - rtl_irq_disable(tp); - - napi_enable(&tp->napi); - napi_schedule(&tp->napi); + rtl_irq_enable_all(tp); } static void rtl_task(struct work_struct *work) -- cgit v0.10.2 From 83a27052c3376793bc879e00e6e6805d6fb7aab9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Jun 2012 22:35:24 +0000 Subject: virtio-net: fix a race on 32bit arches commit 3fa2a1df909 (virtio-net: per cpu 64 bit stats (v2)) added a race on 32bit arches. We must use separate syncp for rx and tx path as they can be run at the same time on different cpus. Thus one sequence increment can be lost and readers spin forever. Signed-off-by: Eric Dumazet Cc: Stephen Hemminger Cc: Michael S. Tsirkin Cc: Jason Wang Acked-by: Rusty Russell Acked-by: Michael S. Tsirkin Signed-off-by: David S. Miller diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 5214b1e..f18149a 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -42,7 +42,8 @@ module_param(gso, bool, 0444); #define VIRTNET_DRIVER_VERSION "1.0.0" struct virtnet_stats { - struct u64_stats_sync syncp; + struct u64_stats_sync tx_syncp; + struct u64_stats_sync rx_syncp; u64 tx_bytes; u64 tx_packets; @@ -300,10 +301,10 @@ static void receive_buf(struct net_device *dev, void *buf, unsigned int len) hdr = skb_vnet_hdr(skb); - u64_stats_update_begin(&stats->syncp); + u64_stats_update_begin(&stats->rx_syncp); stats->rx_bytes += skb->len; stats->rx_packets++; - u64_stats_update_end(&stats->syncp); + u64_stats_update_end(&stats->rx_syncp); if (hdr->hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) { pr_debug("Needs csum!\n"); @@ -565,10 +566,10 @@ static unsigned int free_old_xmit_skbs(struct virtnet_info *vi) while ((skb = virtqueue_get_buf(vi->svq, &len)) != NULL) { pr_debug("Sent skb %p\n", skb); - u64_stats_update_begin(&stats->syncp); + u64_stats_update_begin(&stats->tx_syncp); stats->tx_bytes += skb->len; stats->tx_packets++; - u64_stats_update_end(&stats->syncp); + u64_stats_update_end(&stats->tx_syncp); tot_sgs += skb_vnet_hdr(skb)->num_sg; dev_kfree_skb_any(skb); @@ -703,12 +704,16 @@ static struct rtnl_link_stats64 *virtnet_stats(struct net_device *dev, u64 tpackets, tbytes, rpackets, rbytes; do { - start = u64_stats_fetch_begin(&stats->syncp); + start = u64_stats_fetch_begin(&stats->tx_syncp); tpackets = stats->tx_packets; tbytes = stats->tx_bytes; + } while (u64_stats_fetch_retry(&stats->tx_syncp, start)); + + do { + start = u64_stats_fetch_begin(&stats->rx_syncp); rpackets = stats->rx_packets; rbytes = stats->rx_bytes; - } while (u64_stats_fetch_retry(&stats->syncp, start)); + } while (u64_stats_fetch_retry(&stats->rx_syncp, start)); tot->rx_packets += rpackets; tot->tx_packets += tpackets; -- cgit v0.10.2 From c5d21c4b2a7765ab0600c8426374b50eb9f4a36f Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Sun, 10 Jun 2012 20:05:24 +0000 Subject: net: Reorder initialization in ip_route_output to fix gcc warning If I build with W=1, for every file that includes , I get the warning include/net/route.h: In function 'ip_route_output': include/net/route.h:135:3: warning: initialized field overwritten [-Woverride-init] include/net/route.h:135:3: warning: (near initialization for 'fl4') [-Woverride-init] (This is with "gcc (Debian 4.6.3-1) 4.6.3") A fix seems pretty trivial: move the initialization of .flowi4_tos earlier. As far as I can tell, this has no effect on code generation. Signed-off-by: Roland Dreier Signed-off-by: David S. Miller diff --git a/include/net/route.h b/include/net/route.h index ed2b78e..9870546 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -130,9 +130,9 @@ static inline struct rtable *ip_route_output(struct net *net, __be32 daddr, { struct flowi4 fl4 = { .flowi4_oif = oif, + .flowi4_tos = tos, .daddr = daddr, .saddr = saddr, - .flowi4_tos = tos, }; return ip_route_output_key(net, &fl4); } -- cgit v0.10.2 From 16b0dc29c1af9df341428f4c49ada4f626258082 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Jun 2012 21:11:57 +0000 Subject: dummy: fix rcu_sched self-detected stalls Trying to "modprobe dummy numdummies=30000" triggers : INFO: rcu_sched self-detected stall on CPU { 8} (t=60000 jiffies) After this splat, RTNL is locked and reboot is needed. We must call cond_resched() to avoid this, even holding RTNL. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index 442d91a..bab0158 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -187,8 +187,10 @@ static int __init dummy_init_module(void) rtnl_lock(); err = __rtnl_link_register(&dummy_link_ops); - for (i = 0; i < numdummies && !err; i++) + for (i = 0; i < numdummies && !err; i++) { err = dummy_init_one(); + cond_resched(); + } if (err < 0) __rtnl_link_unregister(&dummy_link_ops); rtnl_unlock(); -- cgit v0.10.2 From e30478598a8476d02e3b00caa89ce1a3b1dad54b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Jun 2012 23:24:00 +0000 Subject: lpc_eth: add missing ndo_change_mtu() lpc_eth does a copy of transmitted skbs to DMA area, without checking skb lengths, so can trigger buffer overflows : memcpy(pldat->tx_buff_v + txidx * ENET_MAXF_SIZE, skb->data, len); One way to get bigger skbs is to allow MTU changes above the 1500 limit. Calling eth_change_mtu() in ndo_change_mtu() makes sure this cannot happen. Signed-off-by: Eric Dumazet Cc: Roland Stigge Cc: Kevin Wells Acked-by: Roland Stigge Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 8d2666f..10febdc 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -1320,6 +1320,7 @@ static const struct net_device_ops lpc_netdev_ops = { .ndo_set_rx_mode = lpc_eth_set_multicast_list, .ndo_do_ioctl = lpc_eth_ioctl, .ndo_set_mac_address = lpc_set_mac_address, + .ndo_change_mtu = eth_change_mtu, }; static int lpc_eth_drv_probe(struct platform_device *pdev) -- cgit v0.10.2 From 3f16da51b0e533871d22a29682f3c3969d4f7e22 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Jun 2012 07:21:36 +0000 Subject: lpc_eth: fix tx completion __lpc_handle_xmit() has two bugs : 1) It can leak skbs in case TXSTATUS_ERROR is set 2) It can wake up txqueue while no slot was freed. Signed-off-by: Eric Dumazet Reported-by: Roland Stigge Tested-by: Roland Stigge Cc: Kevin Wells Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/nxp/lpc_eth.c b/drivers/net/ethernet/nxp/lpc_eth.c index 10febdc..083d671 100644 --- a/drivers/net/ethernet/nxp/lpc_eth.c +++ b/drivers/net/ethernet/nxp/lpc_eth.c @@ -946,16 +946,16 @@ static void __lpc_handle_xmit(struct net_device *ndev) /* Update stats */ ndev->stats.tx_packets++; ndev->stats.tx_bytes += skb->len; - - /* Free buffer */ - dev_kfree_skb_irq(skb); } + dev_kfree_skb_irq(skb); txcidx = readl(LPC_ENET_TXCONSUMEINDEX(pldat->net_base)); } - if (netif_queue_stopped(ndev)) - netif_wake_queue(ndev); + if (pldat->num_used_tx_buffs <= ENET_TX_DESC/2) { + if (netif_queue_stopped(ndev)) + netif_wake_queue(ndev); + } } static int __lpc_handle_recv(struct net_device *ndev, int budget) -- cgit v0.10.2 From 883ffd6e64114495f68652721065149a2bbd9de6 Mon Sep 17 00:00:00 2001 From: Stefan Roese Date: Thu, 7 Jun 2012 23:21:05 +0000 Subject: net: stmmac: Fix clock en-/disable calls clk_{un}prepare is mandatory for platforms using common clock framework. Since these drivers are used by SPEAr platform, which supports common clock framework, add clk_{un}prepare() support for them. Otherwise the clocks are not correctly en-/disabled and ethernet support doesn't work. Signed-off-by: Stefan Roese Cc: Viresh Kumar Cc: Giuseppe Cavallaro Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 94b21b4..dc20c56 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -109,7 +109,7 @@ struct stmmac_priv *stmmac_dvr_probe(struct device *device, static inline int stmmac_clk_enable(struct stmmac_priv *priv) { if (!IS_ERR(priv->stmmac_clk)) - return clk_enable(priv->stmmac_clk); + return clk_prepare_enable(priv->stmmac_clk); return 0; } @@ -119,7 +119,7 @@ static inline void stmmac_clk_disable(struct stmmac_priv *priv) if (IS_ERR(priv->stmmac_clk)) return; - clk_disable(priv->stmmac_clk); + clk_disable_unprepare(priv->stmmac_clk); } static inline int stmmac_clk_get(struct stmmac_priv *priv) { -- cgit v0.10.2 From b7abee6ef888117f92db370620ebf116a38e3f4d Mon Sep 17 00:00:00 2001 From: Matt Carlson Date: Thu, 7 Jun 2012 12:56:54 +0000 Subject: tg3: Apply short DMA frag workaround to 5906 5906 devices also need the short DMA fragment workaround. This patch makes the necessary change. Signed-off-by: Matt Carlson Tested-by: Christian Kujau Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index edeeb51..e47ff8b 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -14275,7 +14275,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) } } - if (tg3_flag(tp, 5755_PLUS)) + if (tg3_flag(tp, 5755_PLUS) || + GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) tg3_flag_set(tp, SHORT_DMA_BUG); if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) -- cgit v0.10.2 From e3d62d7e8e05a6a4b08f4672385ae58fc0f132c4 Mon Sep 17 00:00:00 2001 From: Chris Metcalf Date: Thu, 7 Jun 2012 10:45:02 +0000 Subject: tilegx network driver: initial support This change adds support for the tilegx network driver based on the GXIO IORPC support in the tilegx software stack, using the on-chip mPIPE packet processing engine. Signed-off-by: Chris Metcalf Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/tile/Kconfig b/drivers/net/ethernet/tile/Kconfig index 2d9218f..098b1c4 100644 --- a/drivers/net/ethernet/tile/Kconfig +++ b/drivers/net/ethernet/tile/Kconfig @@ -7,6 +7,8 @@ config TILE_NET depends on TILE default y select CRC32 + select TILE_GXIO_MPIPE if TILEGX + select HIGH_RES_TIMERS if TILEGX ---help--- This is a standard Linux network device driver for the on-chip Tilera Gigabit Ethernet and XAUI interfaces. diff --git a/drivers/net/ethernet/tile/Makefile b/drivers/net/ethernet/tile/Makefile index f634f14..0ef9eef 100644 --- a/drivers/net/ethernet/tile/Makefile +++ b/drivers/net/ethernet/tile/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_TILE_NET) += tile_net.o ifdef CONFIG_TILEGX -tile_net-objs := tilegx.o mpipe.o iorpc_mpipe.o dma_queue.o +tile_net-y := tilegx.o else -tile_net-objs := tilepro.o +tile_net-y := tilepro.o endif diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c new file mode 100644 index 0000000..83b4b38 --- /dev/null +++ b/drivers/net/ethernet/tile/tilegx.c @@ -0,0 +1,1898 @@ +/* + * Copyright 2012 Tilera Corporation. All Rights Reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation, version 2. + * + * 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, GOOD TITLE or + * NON INFRINGEMENT. See the GNU General Public License for + * more details. + */ + +#include +#include +#include +#include +#include /* printk() */ +#include /* kmalloc() */ +#include /* error codes */ +#include /* size_t */ +#include +#include +#include +#include /* struct device, and other headers */ +#include /* eth_type_trans */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* Default transmit lockup timeout period, in jiffies. */ +#define TILE_NET_TIMEOUT (5 * HZ) + +/* The maximum number of distinct channels (idesc.channel is 5 bits). */ +#define TILE_NET_CHANNELS 32 + +/* Maximum number of idescs to handle per "poll". */ +#define TILE_NET_BATCH 128 + +/* Maximum number of packets to handle per "poll". */ +#define TILE_NET_WEIGHT 64 + +/* Number of entries in each iqueue. */ +#define IQUEUE_ENTRIES 512 + +/* Number of entries in each equeue. */ +#define EQUEUE_ENTRIES 2048 + +/* Total header bytes per equeue slot. Must be big enough for 2 bytes + * of NET_IP_ALIGN alignment, plus 14 bytes (?) of L2 header, plus up to + * 60 bytes of actual TCP header. We round up to align to cache lines. + */ +#define HEADER_BYTES 128 + +/* Maximum completions per cpu per device (must be a power of two). + * ISSUE: What is the right number here? If this is too small, then + * egress might block waiting for free space in a completions array. + * ISSUE: At the least, allocate these only for initialized echannels. + */ +#define TILE_NET_MAX_COMPS 64 + +#define MAX_FRAGS (MAX_SKB_FRAGS + 1) + +/* Size of completions data to allocate. + * ISSUE: Probably more than needed since we don't use all the channels. + */ +#define COMPS_SIZE (TILE_NET_CHANNELS * sizeof(struct tile_net_comps)) + +/* Size of NotifRing data to allocate. */ +#define NOTIF_RING_SIZE (IQUEUE_ENTRIES * sizeof(gxio_mpipe_idesc_t)) + +/* Timeout to wake the per-device TX timer after we stop the queue. + * We don't want the timeout too short (adds overhead, and might end + * up causing stop/wake/stop/wake cycles) or too long (affects performance). + * For the 10 Gb NIC, 30 usec means roughly 30+ 1500-byte packets. + */ +#define TX_TIMER_DELAY_USEC 30 + +/* Timeout to wake the per-cpu egress timer to free completions. */ +#define EGRESS_TIMER_DELAY_USEC 1000 + +MODULE_AUTHOR("Tilera Corporation"); +MODULE_LICENSE("GPL"); + +/* A "packet fragment" (a chunk of memory). */ +struct frag { + void *buf; + size_t length; +}; + +/* A single completion. */ +struct tile_net_comp { + /* The "complete_count" when the completion will be complete. */ + s64 when; + /* The buffer to be freed when the completion is complete. */ + struct sk_buff *skb; +}; + +/* The completions for a given cpu and echannel. */ +struct tile_net_comps { + /* The completions. */ + struct tile_net_comp comp_queue[TILE_NET_MAX_COMPS]; + /* The number of completions used. */ + unsigned long comp_next; + /* The number of completions freed. */ + unsigned long comp_last; +}; + +/* The transmit wake timer for a given cpu and echannel. */ +struct tile_net_tx_wake { + struct hrtimer timer; + struct net_device *dev; +}; + +/* Info for a specific cpu. */ +struct tile_net_info { + /* The NAPI struct. */ + struct napi_struct napi; + /* Packet queue. */ + gxio_mpipe_iqueue_t iqueue; + /* Our cpu. */ + int my_cpu; + /* True if iqueue is valid. */ + bool has_iqueue; + /* NAPI flags. */ + bool napi_added; + bool napi_enabled; + /* Number of small sk_buffs which must still be provided. */ + unsigned int num_needed_small_buffers; + /* Number of large sk_buffs which must still be provided. */ + unsigned int num_needed_large_buffers; + /* A timer for handling egress completions. */ + struct hrtimer egress_timer; + /* True if "egress_timer" is scheduled. */ + bool egress_timer_scheduled; + /* Comps for each egress channel. */ + struct tile_net_comps *comps_for_echannel[TILE_NET_CHANNELS]; + /* Transmit wake timer for each egress channel. */ + struct tile_net_tx_wake tx_wake[TILE_NET_CHANNELS]; +}; + +/* Info for egress on a particular egress channel. */ +struct tile_net_egress { + /* The "equeue". */ + gxio_mpipe_equeue_t *equeue; + /* The headers for TSO. */ + unsigned char *headers; +}; + +/* Info for a specific device. */ +struct tile_net_priv { + /* Our network device. */ + struct net_device *dev; + /* The primary link. */ + gxio_mpipe_link_t link; + /* The primary channel, if open, else -1. */ + int channel; + /* The "loopify" egress link, if needed. */ + gxio_mpipe_link_t loopify_link; + /* The "loopify" egress channel, if open, else -1. */ + int loopify_channel; + /* The egress channel (channel or loopify_channel). */ + int echannel; + /* Total stats. */ + struct net_device_stats stats; +}; + +/* Egress info, indexed by "priv->echannel" (lazily created as needed). */ +static struct tile_net_egress egress_for_echannel[TILE_NET_CHANNELS]; + +/* Devices currently associated with each channel. + * NOTE: The array entry can become NULL after ifconfig down, but + * we do not free the underlying net_device structures, so it is + * safe to use a pointer after reading it from this array. + */ +static struct net_device *tile_net_devs_for_channel[TILE_NET_CHANNELS]; + +/* A mutex for "tile_net_devs_for_channel". */ +static DEFINE_MUTEX(tile_net_devs_for_channel_mutex); + +/* The per-cpu info. */ +static DEFINE_PER_CPU(struct tile_net_info, per_cpu_info); + +/* The "context" for all devices. */ +static gxio_mpipe_context_t context; + +/* Buffer sizes and mpipe enum codes for buffer stacks. + * See arch/tile/include/gxio/mpipe.h for the set of possible values. + */ +#define BUFFER_SIZE_SMALL_ENUM GXIO_MPIPE_BUFFER_SIZE_128 +#define BUFFER_SIZE_SMALL 128 +#define BUFFER_SIZE_LARGE_ENUM GXIO_MPIPE_BUFFER_SIZE_1664 +#define BUFFER_SIZE_LARGE 1664 + +/* The small/large "buffer stacks". */ +static int small_buffer_stack = -1; +static int large_buffer_stack = -1; + +/* Amount of memory allocated for each buffer stack. */ +static size_t buffer_stack_size; + +/* The actual memory allocated for the buffer stacks. */ +static void *small_buffer_stack_va; +static void *large_buffer_stack_va; + +/* The buckets. */ +static int first_bucket = -1; +static int num_buckets = 1; + +/* The ingress irq. */ +static int ingress_irq = -1; + +/* Text value of tile_net.cpus if passed as a module parameter. */ +static char *network_cpus_string; + +/* The actual cpus in "network_cpus". */ +static struct cpumask network_cpus_map; + +/* If "loopify=LINK" was specified, this is "LINK". */ +static char *loopify_link_name; + +/* If "tile_net.custom" was specified, this is non-NULL. */ +static char *custom_str; + +/* The "tile_net.cpus" argument specifies the cpus that are dedicated + * to handle ingress packets. + * + * The parameter should be in the form "tile_net.cpus=m-n[,x-y]", where + * m, n, x, y are integer numbers that represent the cpus that can be + * neither a dedicated cpu nor a dataplane cpu. + */ +static bool network_cpus_init(void) +{ + char buf[1024]; + int rc; + + if (network_cpus_string == NULL) + return false; + + rc = cpulist_parse_crop(network_cpus_string, &network_cpus_map); + if (rc != 0) { + pr_warn("tile_net.cpus=%s: malformed cpu list\n", + network_cpus_string); + return false; + } + + /* Remove dedicated cpus. */ + cpumask_and(&network_cpus_map, &network_cpus_map, cpu_possible_mask); + + if (cpumask_empty(&network_cpus_map)) { + pr_warn("Ignoring empty tile_net.cpus='%s'.\n", + network_cpus_string); + return false; + } + + cpulist_scnprintf(buf, sizeof(buf), &network_cpus_map); + pr_info("Linux network CPUs: %s\n", buf); + return true; +} + +module_param_named(cpus, network_cpus_string, charp, 0444); +MODULE_PARM_DESC(cpus, "cpulist of cores that handle network interrupts"); + +/* The "tile_net.loopify=LINK" argument causes the named device to + * actually use "loop0" for ingress, and "loop1" for egress. This + * allows an app to sit between the actual link and linux, passing + * (some) packets along to linux, and forwarding (some) packets sent + * out by linux. + */ +module_param_named(loopify, loopify_link_name, charp, 0444); +MODULE_PARM_DESC(loopify, "name the device to use loop0/1 for ingress/egress"); + +/* The "tile_net.custom" argument causes us to ignore the "conventional" + * classifier metadata, in particular, the "l2_offset". + */ +module_param_named(custom, custom_str, charp, 0444); +MODULE_PARM_DESC(custom, "indicates a (heavily) customized classifier"); + +/* Atomically update a statistics field. + * Note that on TILE-Gx, this operation is fire-and-forget on the + * issuing core (single-cycle dispatch) and takes only a few cycles + * longer than a regular store when the request reaches the home cache. + * No expensive bus management overhead is required. + */ +static void tile_net_stats_add(unsigned long value, unsigned long *field) +{ + BUILD_BUG_ON(sizeof(atomic_long_t) != sizeof(unsigned long)); + atomic_long_add(value, (atomic_long_t *)field); +} + +/* Allocate and push a buffer. */ +static bool tile_net_provide_buffer(bool small) +{ + int stack = small ? small_buffer_stack : large_buffer_stack; + const unsigned long buffer_alignment = 128; + struct sk_buff *skb; + int len; + + len = sizeof(struct sk_buff **) + buffer_alignment; + len += (small ? BUFFER_SIZE_SMALL : BUFFER_SIZE_LARGE); + skb = dev_alloc_skb(len); + if (skb == NULL) + return false; + + /* Make room for a back-pointer to 'skb' and guarantee alignment. */ + skb_reserve(skb, sizeof(struct sk_buff **)); + skb_reserve(skb, -(long)skb->data & (buffer_alignment - 1)); + + /* Save a back-pointer to 'skb'. */ + *(struct sk_buff **)(skb->data - sizeof(struct sk_buff **)) = skb; + + /* Make sure "skb" and the back-pointer have been flushed. */ + wmb(); + + gxio_mpipe_push_buffer(&context, stack, + (void *)va_to_tile_io_addr(skb->data)); + + return true; +} + +/* Convert a raw mpipe buffer to its matching skb pointer. */ +static struct sk_buff *mpipe_buf_to_skb(void *va) +{ + /* Acquire the associated "skb". */ + struct sk_buff **skb_ptr = va - sizeof(*skb_ptr); + struct sk_buff *skb = *skb_ptr; + + /* Paranoia. */ + if (skb->data != va) { + /* Panic here since there's a reasonable chance + * that corrupt buffers means generic memory + * corruption, with unpredictable system effects. + */ + panic("Corrupt linux buffer! va=%p, skb=%p, skb->data=%p", + va, skb, skb->data); + } + + return skb; +} + +static void tile_net_pop_all_buffers(int stack) +{ + for (;;) { + tile_io_addr_t addr = + (tile_io_addr_t)gxio_mpipe_pop_buffer(&context, stack); + if (addr == 0) + break; + dev_kfree_skb_irq(mpipe_buf_to_skb(tile_io_addr_to_va(addr))); + } +} + +/* Provide linux buffers to mPIPE. */ +static void tile_net_provide_needed_buffers(void) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + + while (info->num_needed_small_buffers != 0) { + if (!tile_net_provide_buffer(true)) + goto oops; + info->num_needed_small_buffers--; + } + + while (info->num_needed_large_buffers != 0) { + if (!tile_net_provide_buffer(false)) + goto oops; + info->num_needed_large_buffers--; + } + + return; + +oops: + /* Add a description to the page allocation failure dump. */ + pr_notice("Tile %d still needs some buffers\n", info->my_cpu); +} + +static inline bool filter_packet(struct net_device *dev, void *buf) +{ + /* Filter packets received before we're up. */ + if (dev == NULL || !(dev->flags & IFF_UP)) + return true; + + /* Filter out packets that aren't for us. */ + if (!(dev->flags & IFF_PROMISC) && + !is_multicast_ether_addr(buf) && + compare_ether_addr(dev->dev_addr, buf) != 0) + return true; + + return false; +} + +static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb, + gxio_mpipe_idesc_t *idesc, unsigned long len) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + + /* Encode the actual packet length. */ + skb_put(skb, len); + + skb->protocol = eth_type_trans(skb, dev); + + /* Acknowledge "good" hardware checksums. */ + if (idesc->cs && idesc->csum_seed_val == 0xFFFF) + skb->ip_summed = CHECKSUM_UNNECESSARY; + + netif_receive_skb(skb); + + /* Update stats. */ + tile_net_stats_add(1, &priv->stats.rx_packets); + tile_net_stats_add(len, &priv->stats.rx_bytes); + + /* Need a new buffer. */ + if (idesc->size == BUFFER_SIZE_SMALL_ENUM) + info->num_needed_small_buffers++; + else + info->num_needed_large_buffers++; +} + +/* Handle a packet. Return true if "processed", false if "filtered". */ +static bool tile_net_handle_packet(gxio_mpipe_idesc_t *idesc) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct net_device *dev = tile_net_devs_for_channel[idesc->channel]; + uint8_t l2_offset; + void *va; + void *buf; + unsigned long len; + bool filter; + + /* Drop packets for which no buffer was available. + * NOTE: This happens under heavy load. + */ + if (idesc->be) { + struct tile_net_priv *priv = netdev_priv(dev); + tile_net_stats_add(1, &priv->stats.rx_dropped); + gxio_mpipe_iqueue_consume(&info->iqueue, idesc); + if (net_ratelimit()) + pr_info("Dropping packet (insufficient buffers).\n"); + return false; + } + + /* Get the "l2_offset", if allowed. */ + l2_offset = custom_str ? 0 : gxio_mpipe_idesc_get_l2_offset(idesc); + + /* Get the raw buffer VA (includes "headroom"). */ + va = tile_io_addr_to_va((unsigned long)(long)idesc->va); + + /* Get the actual packet start/length. */ + buf = va + l2_offset; + len = idesc->l2_size - l2_offset; + + /* Point "va" at the raw buffer. */ + va -= NET_IP_ALIGN; + + filter = filter_packet(dev, buf); + if (filter) { + gxio_mpipe_iqueue_drop(&info->iqueue, idesc); + } else { + struct sk_buff *skb = mpipe_buf_to_skb(va); + + /* Skip headroom, and any custom header. */ + skb_reserve(skb, NET_IP_ALIGN + l2_offset); + + tile_net_receive_skb(dev, skb, idesc, len); + } + + gxio_mpipe_iqueue_consume(&info->iqueue, idesc); + return !filter; +} + +/* Handle some packets for the current CPU. + * + * This function handles up to TILE_NET_BATCH idescs per call. + * + * ISSUE: Since we do not provide new buffers until this function is + * complete, we must initially provide enough buffers for each network + * cpu to fill its iqueue and also its batched idescs. + * + * ISSUE: The "rotting packet" race condition occurs if a packet + * arrives after the queue appears to be empty, and before the + * hypervisor interrupt is re-enabled. + */ +static int tile_net_poll(struct napi_struct *napi, int budget) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + unsigned int work = 0; + gxio_mpipe_idesc_t *idesc; + int i, n; + + /* Process packets. */ + while ((n = gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc)) > 0) { + for (i = 0; i < n; i++) { + if (i == TILE_NET_BATCH) + goto done; + if (tile_net_handle_packet(idesc + i)) { + if (++work >= budget) + goto done; + } + } + } + + /* There are no packets left. */ + napi_complete(&info->napi); + + /* Re-enable hypervisor interrupts. */ + gxio_mpipe_enable_notif_ring_interrupt(&context, info->iqueue.ring); + + /* HACK: Avoid the "rotting packet" problem. */ + if (gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc) > 0) + napi_schedule(&info->napi); + + /* ISSUE: Handle completions? */ + +done: + tile_net_provide_needed_buffers(); + + return work; +} + +/* Handle an ingress interrupt on the current cpu. */ +static irqreturn_t tile_net_handle_ingress_irq(int irq, void *unused) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + napi_schedule(&info->napi); + return IRQ_HANDLED; +} + +/* Free some completions. This must be called with interrupts blocked. */ +static int tile_net_free_comps(gxio_mpipe_equeue_t *equeue, + struct tile_net_comps *comps, + int limit, bool force_update) +{ + int n = 0; + while (comps->comp_last < comps->comp_next) { + unsigned int cid = comps->comp_last % TILE_NET_MAX_COMPS; + struct tile_net_comp *comp = &comps->comp_queue[cid]; + if (!gxio_mpipe_equeue_is_complete(equeue, comp->when, + force_update || n == 0)) + break; + dev_kfree_skb_irq(comp->skb); + comps->comp_last++; + if (++n == limit) + break; + } + return n; +} + +/* Add a completion. This must be called with interrupts blocked. + * tile_net_equeue_try_reserve() will have ensured a free completion entry. + */ +static void add_comp(gxio_mpipe_equeue_t *equeue, + struct tile_net_comps *comps, + uint64_t when, struct sk_buff *skb) +{ + int cid = comps->comp_next % TILE_NET_MAX_COMPS; + comps->comp_queue[cid].when = when; + comps->comp_queue[cid].skb = skb; + comps->comp_next++; +} + +static void tile_net_schedule_tx_wake_timer(struct net_device *dev) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + + hrtimer_start(&info->tx_wake[priv->echannel].timer, + ktime_set(0, TX_TIMER_DELAY_USEC * 1000UL), + HRTIMER_MODE_REL_PINNED); +} + +static enum hrtimer_restart tile_net_handle_tx_wake_timer(struct hrtimer *t) +{ + struct tile_net_tx_wake *tx_wake = + container_of(t, struct tile_net_tx_wake, timer); + netif_wake_subqueue(tx_wake->dev, smp_processor_id()); + return HRTIMER_NORESTART; +} + +/* Make sure the egress timer is scheduled. */ +static void tile_net_schedule_egress_timer(void) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + + if (!info->egress_timer_scheduled) { + hrtimer_start(&info->egress_timer, + ktime_set(0, EGRESS_TIMER_DELAY_USEC * 1000UL), + HRTIMER_MODE_REL_PINNED); + info->egress_timer_scheduled = true; + } +} + +/* The "function" for "info->egress_timer". + * + * This timer will reschedule itself as long as there are any pending + * completions expected for this tile. + */ +static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + unsigned long irqflags; + bool pending = false; + int i; + + local_irq_save(irqflags); + + /* The timer is no longer scheduled. */ + info->egress_timer_scheduled = false; + + /* Free all possible comps for this tile. */ + for (i = 0; i < TILE_NET_CHANNELS; i++) { + struct tile_net_egress *egress = &egress_for_echannel[i]; + struct tile_net_comps *comps = info->comps_for_echannel[i]; + if (comps->comp_last >= comps->comp_next) + continue; + tile_net_free_comps(egress->equeue, comps, -1, true); + pending = pending || (comps->comp_last < comps->comp_next); + } + + /* Reschedule timer if needed. */ + if (pending) + tile_net_schedule_egress_timer(); + + local_irq_restore(irqflags); + + return HRTIMER_NORESTART; +} + +/* Helper function for "tile_net_update()". + * "dev" (i.e. arg) is the device being brought up or down, + * or NULL if all devices are now down. + */ +static void tile_net_update_cpu(void *arg) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct net_device *dev = arg; + + if (!info->has_iqueue) + return; + + if (dev != NULL) { + if (!info->napi_added) { + netif_napi_add(dev, &info->napi, + tile_net_poll, TILE_NET_WEIGHT); + info->napi_added = true; + } + if (!info->napi_enabled) { + napi_enable(&info->napi); + info->napi_enabled = true; + } + enable_percpu_irq(ingress_irq, 0); + } else { + disable_percpu_irq(ingress_irq); + if (info->napi_enabled) { + napi_disable(&info->napi); + info->napi_enabled = false; + } + /* FIXME: Drain the iqueue. */ + } +} + +/* Helper function for tile_net_open() and tile_net_stop(). + * Always called under tile_net_devs_for_channel_mutex. + */ +static int tile_net_update(struct net_device *dev) +{ + static gxio_mpipe_rules_t rules; /* too big to fit on the stack */ + bool saw_channel = false; + int channel; + int rc; + int cpu; + + gxio_mpipe_rules_init(&rules, &context); + + for (channel = 0; channel < TILE_NET_CHANNELS; channel++) { + if (tile_net_devs_for_channel[channel] == NULL) + continue; + if (!saw_channel) { + saw_channel = true; + gxio_mpipe_rules_begin(&rules, first_bucket, + num_buckets, NULL); + gxio_mpipe_rules_set_headroom(&rules, NET_IP_ALIGN); + } + gxio_mpipe_rules_add_channel(&rules, channel); + } + + /* NOTE: This can fail if there is no classifier. + * ISSUE: Can anything else cause it to fail? + */ + rc = gxio_mpipe_rules_commit(&rules); + if (rc != 0) { + netdev_warn(dev, "gxio_mpipe_rules_commit failed: %d\n", rc); + return -EIO; + } + + /* Update all cpus, sequentially (to protect "netif_napi_add()"). */ + for_each_online_cpu(cpu) + smp_call_function_single(cpu, tile_net_update_cpu, + (saw_channel ? dev : NULL), 1); + + /* HACK: Allow packets to flow in the simulator. */ + if (saw_channel) + sim_enable_mpipe_links(0, -1); + + return 0; +} + +/* Allocate and initialize mpipe buffer stacks, and register them in + * the mPIPE TLBs, for both small and large packet sizes. + * This routine supports tile_net_init_mpipe(), below. + */ +static int init_buffer_stacks(struct net_device *dev, int num_buffers) +{ + pte_t hash_pte = pte_set_home((pte_t) { 0 }, PAGE_HOME_HASH); + int rc; + + /* Compute stack bytes; we round up to 64KB and then use + * alloc_pages() so we get the required 64KB alignment as well. + */ + buffer_stack_size = + ALIGN(gxio_mpipe_calc_buffer_stack_bytes(num_buffers), + 64 * 1024); + + /* Allocate two buffer stack indices. */ + rc = gxio_mpipe_alloc_buffer_stacks(&context, 2, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_buffer_stacks failed: %d\n", + rc); + return rc; + } + small_buffer_stack = rc; + large_buffer_stack = rc + 1; + + /* Allocate the small memory stack. */ + small_buffer_stack_va = + alloc_pages_exact(buffer_stack_size, GFP_KERNEL); + if (small_buffer_stack_va == NULL) { + netdev_err(dev, + "Could not alloc %zd bytes for buffer stacks\n", + buffer_stack_size); + return -ENOMEM; + } + rc = gxio_mpipe_init_buffer_stack(&context, small_buffer_stack, + BUFFER_SIZE_SMALL_ENUM, + small_buffer_stack_va, + buffer_stack_size, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_init_buffer_stack: %d\n", rc); + return rc; + } + rc = gxio_mpipe_register_client_memory(&context, small_buffer_stack, + hash_pte, 0); + if (rc != 0) { + netdev_err(dev, + "gxio_mpipe_register_buffer_memory failed: %d\n", + rc); + return rc; + } + + /* Allocate the large buffer stack. */ + large_buffer_stack_va = + alloc_pages_exact(buffer_stack_size, GFP_KERNEL); + if (large_buffer_stack_va == NULL) { + netdev_err(dev, + "Could not alloc %zd bytes for buffer stacks\n", + buffer_stack_size); + return -ENOMEM; + } + rc = gxio_mpipe_init_buffer_stack(&context, large_buffer_stack, + BUFFER_SIZE_LARGE_ENUM, + large_buffer_stack_va, + buffer_stack_size, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_init_buffer_stack failed: %d\n", + rc); + return rc; + } + rc = gxio_mpipe_register_client_memory(&context, large_buffer_stack, + hash_pte, 0); + if (rc != 0) { + netdev_err(dev, + "gxio_mpipe_register_buffer_memory failed: %d\n", + rc); + return rc; + } + + return 0; +} + +/* Allocate per-cpu resources (memory for completions and idescs). + * This routine supports tile_net_init_mpipe(), below. + */ +static int alloc_percpu_mpipe_resources(struct net_device *dev, + int cpu, int ring) +{ + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + int order, i, rc; + struct page *page; + void *addr; + + /* Allocate the "comps". */ + order = get_order(COMPS_SIZE); + page = homecache_alloc_pages(GFP_KERNEL, order, cpu); + if (page == NULL) { + netdev_err(dev, "Failed to alloc %zd bytes comps memory\n", + COMPS_SIZE); + return -ENOMEM; + } + addr = pfn_to_kaddr(page_to_pfn(page)); + memset(addr, 0, COMPS_SIZE); + for (i = 0; i < TILE_NET_CHANNELS; i++) + info->comps_for_echannel[i] = + addr + i * sizeof(struct tile_net_comps); + + /* If this is a network cpu, create an iqueue. */ + if (cpu_isset(cpu, network_cpus_map)) { + order = get_order(NOTIF_RING_SIZE); + page = homecache_alloc_pages(GFP_KERNEL, order, cpu); + if (page == NULL) { + netdev_err(dev, + "Failed to alloc %zd bytes iqueue memory\n", + NOTIF_RING_SIZE); + return -ENOMEM; + } + addr = pfn_to_kaddr(page_to_pfn(page)); + rc = gxio_mpipe_iqueue_init(&info->iqueue, &context, ring++, + addr, NOTIF_RING_SIZE, 0); + if (rc < 0) { + netdev_err(dev, + "gxio_mpipe_iqueue_init failed: %d\n", rc); + return rc; + } + info->has_iqueue = true; + } + + return ring; +} + +/* Initialize NotifGroup and buckets. + * This routine supports tile_net_init_mpipe(), below. + */ +static int init_notif_group_and_buckets(struct net_device *dev, + int ring, int network_cpus_count) +{ + int group, rc; + + /* Allocate one NotifGroup. */ + rc = gxio_mpipe_alloc_notif_groups(&context, 1, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_notif_groups failed: %d\n", + rc); + return rc; + } + group = rc; + + /* Initialize global num_buckets value. */ + if (network_cpus_count > 4) + num_buckets = 256; + else if (network_cpus_count > 1) + num_buckets = 16; + + /* Allocate some buckets, and set global first_bucket value. */ + rc = gxio_mpipe_alloc_buckets(&context, num_buckets, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_buckets failed: %d\n", rc); + return rc; + } + first_bucket = rc; + + /* Init group and buckets. */ + rc = gxio_mpipe_init_notif_group_and_buckets( + &context, group, ring, network_cpus_count, + first_bucket, num_buckets, + GXIO_MPIPE_BUCKET_STICKY_FLOW_LOCALITY); + if (rc != 0) { + netdev_err( + dev, + "gxio_mpipe_init_notif_group_and_buckets failed: %d\n", + rc); + return rc; + } + + return 0; +} + +/* Create an irq and register it, then activate the irq and request + * interrupts on all cores. Note that "ingress_irq" being initialized + * is how we know not to call tile_net_init_mpipe() again. + * This routine supports tile_net_init_mpipe(), below. + */ +static int tile_net_setup_interrupts(struct net_device *dev) +{ + int cpu, rc; + + rc = create_irq(); + if (rc < 0) { + netdev_err(dev, "create_irq failed: %d\n", rc); + return rc; + } + ingress_irq = rc; + tile_irq_activate(ingress_irq, TILE_IRQ_PERCPU); + rc = request_irq(ingress_irq, tile_net_handle_ingress_irq, + 0, NULL, NULL); + if (rc != 0) { + netdev_err(dev, "request_irq failed: %d\n", rc); + destroy_irq(ingress_irq); + ingress_irq = -1; + return rc; + } + + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + if (info->has_iqueue) { + gxio_mpipe_request_notif_ring_interrupt( + &context, cpu_x(cpu), cpu_y(cpu), + 1, ingress_irq, info->iqueue.ring); + } + } + + return 0; +} + +/* Undo any state set up partially by a failed call to tile_net_init_mpipe. */ +static void tile_net_init_mpipe_fail(void) +{ + int cpu; + + /* Do cleanups that require the mpipe context first. */ + if (small_buffer_stack >= 0) + tile_net_pop_all_buffers(small_buffer_stack); + if (large_buffer_stack >= 0) + tile_net_pop_all_buffers(large_buffer_stack); + + /* Destroy mpipe context so the hardware no longer owns any memory. */ + gxio_mpipe_destroy(&context); + + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + free_pages((unsigned long)(info->comps_for_echannel[0]), + get_order(COMPS_SIZE)); + info->comps_for_echannel[0] = NULL; + free_pages((unsigned long)(info->iqueue.idescs), + get_order(NOTIF_RING_SIZE)); + info->iqueue.idescs = NULL; + } + + if (small_buffer_stack_va) + free_pages_exact(small_buffer_stack_va, buffer_stack_size); + if (large_buffer_stack_va) + free_pages_exact(large_buffer_stack_va, buffer_stack_size); + + small_buffer_stack_va = NULL; + large_buffer_stack_va = NULL; + large_buffer_stack = -1; + small_buffer_stack = -1; + first_bucket = -1; +} + +/* The first time any tilegx network device is opened, we initialize + * the global mpipe state. If this step fails, we fail to open the + * device, but if it succeeds, we never need to do it again, and since + * tile_net can't be unloaded, we never undo it. + * + * Note that some resources in this path (buffer stack indices, + * bindings from init_buffer_stack, etc.) are hypervisor resources + * that are freed implicitly by gxio_mpipe_destroy(). + */ +static int tile_net_init_mpipe(struct net_device *dev) +{ + int i, num_buffers, rc; + int cpu; + int first_ring, ring; + int network_cpus_count = cpus_weight(network_cpus_map); + + if (!hash_default) { + netdev_err(dev, "Networking requires hash_default!\n"); + return -EIO; + } + + rc = gxio_mpipe_init(&context, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_init failed: %d\n", rc); + return -EIO; + } + + /* Set up the buffer stacks. */ + num_buffers = + network_cpus_count * (IQUEUE_ENTRIES + TILE_NET_BATCH); + rc = init_buffer_stacks(dev, num_buffers); + if (rc != 0) + goto fail; + + /* Provide initial buffers. */ + rc = -ENOMEM; + for (i = 0; i < num_buffers; i++) { + if (!tile_net_provide_buffer(true)) { + netdev_err(dev, "Cannot allocate initial sk_bufs!\n"); + goto fail; + } + } + for (i = 0; i < num_buffers; i++) { + if (!tile_net_provide_buffer(false)) { + netdev_err(dev, "Cannot allocate initial sk_bufs!\n"); + goto fail; + } + } + + /* Allocate one NotifRing for each network cpu. */ + rc = gxio_mpipe_alloc_notif_rings(&context, network_cpus_count, 0, 0); + if (rc < 0) { + netdev_err(dev, "gxio_mpipe_alloc_notif_rings failed %d\n", + rc); + goto fail; + } + + /* Init NotifRings per-cpu. */ + first_ring = rc; + ring = first_ring; + for_each_online_cpu(cpu) { + rc = alloc_percpu_mpipe_resources(dev, cpu, ring); + if (rc < 0) + goto fail; + ring = rc; + } + + /* Initialize NotifGroup and buckets. */ + rc = init_notif_group_and_buckets(dev, first_ring, network_cpus_count); + if (rc != 0) + goto fail; + + /* Create and enable interrupts. */ + rc = tile_net_setup_interrupts(dev); + if (rc != 0) + goto fail; + + return 0; + +fail: + tile_net_init_mpipe_fail(); + return rc; +} + +/* Create persistent egress info for a given egress channel. + * Note that this may be shared between, say, "gbe0" and "xgbe0". + * ISSUE: Defer header allocation until TSO is actually needed? + */ +static int tile_net_init_egress(struct net_device *dev, int echannel) +{ + struct page *headers_page, *edescs_page, *equeue_page; + gxio_mpipe_edesc_t *edescs; + gxio_mpipe_equeue_t *equeue; + unsigned char *headers; + int headers_order, edescs_order, equeue_order; + size_t edescs_size; + int edma; + int rc = -ENOMEM; + + /* Only initialize once. */ + if (egress_for_echannel[echannel].equeue != NULL) + return 0; + + /* Allocate memory for the "headers". */ + headers_order = get_order(EQUEUE_ENTRIES * HEADER_BYTES); + headers_page = alloc_pages(GFP_KERNEL, headers_order); + if (headers_page == NULL) { + netdev_warn(dev, + "Could not alloc %zd bytes for TSO headers.\n", + PAGE_SIZE << headers_order); + goto fail; + } + headers = pfn_to_kaddr(page_to_pfn(headers_page)); + + /* Allocate memory for the "edescs". */ + edescs_size = EQUEUE_ENTRIES * sizeof(*edescs); + edescs_order = get_order(edescs_size); + edescs_page = alloc_pages(GFP_KERNEL, edescs_order); + if (edescs_page == NULL) { + netdev_warn(dev, + "Could not alloc %zd bytes for eDMA ring.\n", + edescs_size); + goto fail_headers; + } + edescs = pfn_to_kaddr(page_to_pfn(edescs_page)); + + /* Allocate memory for the "equeue". */ + equeue_order = get_order(sizeof(*equeue)); + equeue_page = alloc_pages(GFP_KERNEL, equeue_order); + if (equeue_page == NULL) { + netdev_warn(dev, + "Could not alloc %zd bytes for equeue info.\n", + PAGE_SIZE << equeue_order); + goto fail_edescs; + } + equeue = pfn_to_kaddr(page_to_pfn(equeue_page)); + + /* Allocate an edma ring. Note that in practice this can't + * fail, which is good, because we will leak an edma ring if so. + */ + rc = gxio_mpipe_alloc_edma_rings(&context, 1, 0, 0); + if (rc < 0) { + netdev_warn(dev, "gxio_mpipe_alloc_edma_rings failed: %d\n", + rc); + goto fail_equeue; + } + edma = rc; + + /* Initialize the equeue. */ + rc = gxio_mpipe_equeue_init(equeue, &context, edma, echannel, + edescs, edescs_size, 0); + if (rc != 0) { + netdev_err(dev, "gxio_mpipe_equeue_init failed: %d\n", rc); + goto fail_equeue; + } + + /* Done. */ + egress_for_echannel[echannel].equeue = equeue; + egress_for_echannel[echannel].headers = headers; + return 0; + +fail_equeue: + __free_pages(equeue_page, equeue_order); + +fail_edescs: + __free_pages(edescs_page, edescs_order); + +fail_headers: + __free_pages(headers_page, headers_order); + +fail: + return rc; +} + +/* Return channel number for a newly-opened link. */ +static int tile_net_link_open(struct net_device *dev, gxio_mpipe_link_t *link, + const char *link_name) +{ + int rc = gxio_mpipe_link_open(link, &context, link_name, 0); + if (rc < 0) { + netdev_err(dev, "Failed to open '%s'\n", link_name); + return rc; + } + rc = gxio_mpipe_link_channel(link); + if (rc < 0 || rc >= TILE_NET_CHANNELS) { + netdev_err(dev, "gxio_mpipe_link_channel bad value: %d\n", rc); + gxio_mpipe_link_close(link); + return -EINVAL; + } + return rc; +} + +/* Help the kernel activate the given network interface. */ +static int tile_net_open(struct net_device *dev) +{ + struct tile_net_priv *priv = netdev_priv(dev); + int cpu, rc; + + mutex_lock(&tile_net_devs_for_channel_mutex); + + /* Do one-time initialization the first time any device is opened. */ + if (ingress_irq < 0) { + rc = tile_net_init_mpipe(dev); + if (rc != 0) + goto fail; + } + + /* Determine if this is the "loopify" device. */ + if (unlikely((loopify_link_name != NULL) && + !strcmp(dev->name, loopify_link_name))) { + rc = tile_net_link_open(dev, &priv->link, "loop0"); + if (rc < 0) + goto fail; + priv->channel = rc; + rc = tile_net_link_open(dev, &priv->loopify_link, "loop1"); + if (rc < 0) + goto fail; + priv->loopify_channel = rc; + priv->echannel = rc; + } else { + rc = tile_net_link_open(dev, &priv->link, dev->name); + if (rc < 0) + goto fail; + priv->channel = rc; + priv->echannel = rc; + } + + /* Initialize egress info (if needed). Once ever, per echannel. */ + rc = tile_net_init_egress(dev, priv->echannel); + if (rc != 0) + goto fail; + + tile_net_devs_for_channel[priv->channel] = dev; + + rc = tile_net_update(dev); + if (rc != 0) + goto fail; + + mutex_unlock(&tile_net_devs_for_channel_mutex); + + /* Initialize the transmit wake timer for this device for each cpu. */ + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + struct tile_net_tx_wake *tx_wake = + &info->tx_wake[priv->echannel]; + + hrtimer_init(&tx_wake->timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); + tx_wake->timer.function = tile_net_handle_tx_wake_timer; + tx_wake->dev = dev; + } + + for_each_online_cpu(cpu) + netif_start_subqueue(dev, cpu); + netif_carrier_on(dev); + return 0; + +fail: + if (priv->loopify_channel >= 0) { + if (gxio_mpipe_link_close(&priv->loopify_link) != 0) + netdev_warn(dev, "Failed to close loopify link!\n"); + priv->loopify_channel = -1; + } + if (priv->channel >= 0) { + if (gxio_mpipe_link_close(&priv->link) != 0) + netdev_warn(dev, "Failed to close link!\n"); + priv->channel = -1; + } + priv->echannel = -1; + tile_net_devs_for_channel[priv->channel] = NULL; + mutex_unlock(&tile_net_devs_for_channel_mutex); + + /* Don't return raw gxio error codes to generic Linux. */ + return (rc > -512) ? rc : -EIO; +} + +/* Help the kernel deactivate the given network interface. */ +static int tile_net_stop(struct net_device *dev) +{ + struct tile_net_priv *priv = netdev_priv(dev); + int cpu; + + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + struct tile_net_tx_wake *tx_wake = + &info->tx_wake[priv->echannel]; + + hrtimer_cancel(&tx_wake->timer); + netif_stop_subqueue(dev, cpu); + } + + mutex_lock(&tile_net_devs_for_channel_mutex); + tile_net_devs_for_channel[priv->channel] = NULL; + (void)tile_net_update(dev); + if (priv->loopify_channel >= 0) { + if (gxio_mpipe_link_close(&priv->loopify_link) != 0) + netdev_warn(dev, "Failed to close loopify link!\n"); + priv->loopify_channel = -1; + } + if (priv->channel >= 0) { + if (gxio_mpipe_link_close(&priv->link) != 0) + netdev_warn(dev, "Failed to close link!\n"); + priv->channel = -1; + } + priv->echannel = -1; + mutex_unlock(&tile_net_devs_for_channel_mutex); + + return 0; +} + +/* Determine the VA for a fragment. */ +static inline void *tile_net_frag_buf(skb_frag_t *f) +{ + unsigned long pfn = page_to_pfn(skb_frag_page(f)); + return pfn_to_kaddr(pfn) + f->page_offset; +} + +/* Acquire a completion entry and an egress slot, or if we can't, + * stop the queue and schedule the tx_wake timer. + */ +static s64 tile_net_equeue_try_reserve(struct net_device *dev, + struct tile_net_comps *comps, + gxio_mpipe_equeue_t *equeue, + int num_edescs) +{ + /* Try to acquire a completion entry. */ + if (comps->comp_next - comps->comp_last < TILE_NET_MAX_COMPS - 1 || + tile_net_free_comps(equeue, comps, 32, false) != 0) { + + /* Try to acquire an egress slot. */ + s64 slot = gxio_mpipe_equeue_try_reserve(equeue, num_edescs); + if (slot >= 0) + return slot; + + /* Freeing some completions gives the equeue time to drain. */ + tile_net_free_comps(equeue, comps, TILE_NET_MAX_COMPS, false); + + slot = gxio_mpipe_equeue_try_reserve(equeue, num_edescs); + if (slot >= 0) + return slot; + } + + /* Still nothing; give up and stop the queue for a short while. */ + netif_stop_subqueue(dev, smp_processor_id()); + tile_net_schedule_tx_wake_timer(dev); + return -1; +} + +/* Determine how many edesc's are needed for TSO. + * + * Sometimes, if "sendfile()" requires copying, we will be called with + * "data" containing the header and payload, with "frags" being empty. + * Sometimes, for example when using NFS over TCP, a single segment can + * span 3 fragments. This requires special care. + */ +static int tso_count_edescs(struct sk_buff *skb) +{ + struct skb_shared_info *sh = skb_shinfo(skb); + unsigned int data_len = skb->data_len; + unsigned int p_len = sh->gso_size; + long f_id = -1; /* id of the current fragment */ + long f_size = -1; /* size of the current fragment */ + long f_used = -1; /* bytes used from the current fragment */ + long n; /* size of the current piece of payload */ + int num_edescs = 0; + int segment; + + for (segment = 0; segment < sh->gso_segs; segment++) { + + unsigned int p_used = 0; + + /* One edesc for header and for each piece of the payload. */ + for (num_edescs++; p_used < p_len; num_edescs++) { + + /* Advance as needed. */ + while (f_used >= f_size) { + f_id++; + f_size = sh->frags[f_id].size; + f_used = 0; + } + + /* Use bytes from the current fragment. */ + n = p_len - p_used; + if (n > f_size - f_used) + n = f_size - f_used; + f_used += n; + p_used += n; + } + + /* The last segment may be less than gso_size. */ + data_len -= p_len; + if (data_len < p_len) + p_len = data_len; + } + + return num_edescs; +} + +/* Prepare modified copies of the skbuff headers. + * FIXME: add support for IPv6. + */ +static void tso_headers_prepare(struct sk_buff *skb, unsigned char *headers, + s64 slot) +{ + struct skb_shared_info *sh = skb_shinfo(skb); + struct iphdr *ih; + struct tcphdr *th; + unsigned int data_len = skb->data_len; + unsigned char *data = skb->data; + unsigned int ih_off, th_off, sh_len, p_len; + unsigned int isum_seed, tsum_seed, id, seq; + long f_id = -1; /* id of the current fragment */ + long f_size = -1; /* size of the current fragment */ + long f_used = -1; /* bytes used from the current fragment */ + long n; /* size of the current piece of payload */ + int segment; + + /* Locate original headers and compute various lengths. */ + ih = ip_hdr(skb); + th = tcp_hdr(skb); + ih_off = skb_network_offset(skb); + th_off = skb_transport_offset(skb); + sh_len = th_off + tcp_hdrlen(skb); + p_len = sh->gso_size; + + /* Set up seed values for IP and TCP csum and initialize id and seq. */ + isum_seed = ((0xFFFF - ih->check) + + (0xFFFF - ih->tot_len) + + (0xFFFF - ih->id)); + tsum_seed = th->check + (0xFFFF ^ htons(skb->len)); + id = ntohs(ih->id); + seq = ntohl(th->seq); + + /* Prepare all the headers. */ + for (segment = 0; segment < sh->gso_segs; segment++) { + unsigned char *buf; + unsigned int p_used = 0; + + /* Copy to the header memory for this segment. */ + buf = headers + (slot % EQUEUE_ENTRIES) * HEADER_BYTES + + NET_IP_ALIGN; + memcpy(buf, data, sh_len); + + /* Update copied ip header. */ + ih = (struct iphdr *)(buf + ih_off); + ih->tot_len = htons(sh_len + p_len - ih_off); + ih->id = htons(id); + ih->check = csum_long(isum_seed + ih->tot_len + + ih->id) ^ 0xffff; + + /* Update copied tcp header. */ + th = (struct tcphdr *)(buf + th_off); + th->seq = htonl(seq); + th->check = csum_long(tsum_seed + htons(sh_len + p_len)); + if (segment != sh->gso_segs - 1) { + th->fin = 0; + th->psh = 0; + } + + /* Skip past the header. */ + slot++; + + /* Skip past the payload. */ + while (p_used < p_len) { + + /* Advance as needed. */ + while (f_used >= f_size) { + f_id++; + f_size = sh->frags[f_id].size; + f_used = 0; + } + + /* Use bytes from the current fragment. */ + n = p_len - p_used; + if (n > f_size - f_used) + n = f_size - f_used; + f_used += n; + p_used += n; + + slot++; + } + + id++; + seq += p_len; + + /* The last segment may be less than gso_size. */ + data_len -= p_len; + if (data_len < p_len) + p_len = data_len; + } + + /* Flush the headers so they are ready for hardware DMA. */ + wmb(); +} + +/* Pass all the data to mpipe for egress. */ +static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue, + struct sk_buff *skb, unsigned char *headers, s64 slot) +{ + struct tile_net_priv *priv = netdev_priv(dev); + struct skb_shared_info *sh = skb_shinfo(skb); + unsigned int data_len = skb->data_len; + unsigned int p_len = sh->gso_size; + gxio_mpipe_edesc_t edesc_head = { { 0 } }; + gxio_mpipe_edesc_t edesc_body = { { 0 } }; + long f_id = -1; /* id of the current fragment */ + long f_size = -1; /* size of the current fragment */ + long f_used = -1; /* bytes used from the current fragment */ + long n; /* size of the current piece of payload */ + unsigned long tx_packets = 0, tx_bytes = 0; + unsigned int csum_start, sh_len; + int segment; + + /* Prepare to egress the headers: set up header edesc. */ + csum_start = skb_checksum_start_offset(skb); + sh_len = skb_transport_offset(skb) + tcp_hdrlen(skb); + edesc_head.csum = 1; + edesc_head.csum_start = csum_start; + edesc_head.csum_dest = csum_start + skb->csum_offset; + edesc_head.xfer_size = sh_len; + + /* This is only used to specify the TLB. */ + edesc_head.stack_idx = large_buffer_stack; + edesc_body.stack_idx = large_buffer_stack; + + /* Egress all the edescs. */ + for (segment = 0; segment < sh->gso_segs; segment++) { + void *va; + unsigned char *buf; + unsigned int p_used = 0; + + /* Egress the header. */ + buf = headers + (slot % EQUEUE_ENTRIES) * HEADER_BYTES + + NET_IP_ALIGN; + edesc_head.va = va_to_tile_io_addr(buf); + gxio_mpipe_equeue_put_at(equeue, edesc_head, slot); + slot++; + + /* Egress the payload. */ + while (p_used < p_len) { + + /* Advance as needed. */ + while (f_used >= f_size) { + f_id++; + f_size = sh->frags[f_id].size; + f_used = 0; + } + + va = tile_net_frag_buf(&sh->frags[f_id]) + f_used; + + /* Use bytes from the current fragment. */ + n = p_len - p_used; + if (n > f_size - f_used) + n = f_size - f_used; + f_used += n; + p_used += n; + + /* Egress a piece of the payload. */ + edesc_body.va = va_to_tile_io_addr(va); + edesc_body.xfer_size = n; + edesc_body.bound = !(p_used < p_len); + gxio_mpipe_equeue_put_at(equeue, edesc_body, slot); + slot++; + } + + tx_packets++; + tx_bytes += sh_len + p_len; + + /* The last segment may be less than gso_size. */ + data_len -= p_len; + if (data_len < p_len) + p_len = data_len; + } + + /* Update stats. */ + tile_net_stats_add(tx_packets, &priv->stats.tx_packets); + tile_net_stats_add(tx_bytes, &priv->stats.tx_bytes); +} + +/* Do "TSO" handling for egress. + * + * Normally drivers set NETIF_F_TSO only to support hardware TSO; + * otherwise the stack uses scatter-gather to implement GSO in software. + * On our testing, enabling GSO support (via NETIF_F_SG) drops network + * performance down to around 7.5 Gbps on the 10G interfaces, although + * also dropping cpu utilization way down, to under 8%. But + * implementing "TSO" in the driver brings performance back up to line + * rate, while dropping cpu usage even further, to less than 4%. In + * practice, profiling of GSO shows that skb_segment() is what causes + * the performance overheads; we benefit in the driver from using + * preallocated memory to duplicate the TCP/IP headers. + */ +static int tile_net_tx_tso(struct sk_buff *skb, struct net_device *dev) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + int channel = priv->echannel; + struct tile_net_egress *egress = &egress_for_echannel[channel]; + struct tile_net_comps *comps = info->comps_for_echannel[channel]; + gxio_mpipe_equeue_t *equeue = egress->equeue; + unsigned long irqflags; + int num_edescs; + s64 slot; + + /* Determine how many mpipe edesc's are needed. */ + num_edescs = tso_count_edescs(skb); + + local_irq_save(irqflags); + + /* Try to acquire a completion entry and an egress slot. */ + slot = tile_net_equeue_try_reserve(dev, comps, equeue, num_edescs); + if (slot < 0) { + local_irq_restore(irqflags); + return NETDEV_TX_BUSY; + } + + /* Set up copies of header data properly. */ + tso_headers_prepare(skb, egress->headers, slot); + + /* Actually pass the data to the network hardware. */ + tso_egress(dev, equeue, skb, egress->headers, slot); + + /* Add a completion record. */ + add_comp(equeue, comps, slot + num_edescs - 1, skb); + + local_irq_restore(irqflags); + + /* Make sure the egress timer is scheduled. */ + tile_net_schedule_egress_timer(); + + return NETDEV_TX_OK; +} + +/* Analyze the body and frags for a transmit request. */ +static unsigned int tile_net_tx_frags(struct frag *frags, + struct sk_buff *skb, + void *b_data, unsigned int b_len) +{ + unsigned int i, n = 0; + + struct skb_shared_info *sh = skb_shinfo(skb); + + if (b_len != 0) { + frags[n].buf = b_data; + frags[n++].length = b_len; + } + + for (i = 0; i < sh->nr_frags; i++) { + skb_frag_t *f = &sh->frags[i]; + frags[n].buf = tile_net_frag_buf(f); + frags[n++].length = skb_frag_size(f); + } + + return n; +} + +/* Help the kernel transmit a packet. */ +static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct tile_net_priv *priv = netdev_priv(dev); + struct tile_net_egress *egress = &egress_for_echannel[priv->echannel]; + gxio_mpipe_equeue_t *equeue = egress->equeue; + struct tile_net_comps *comps = + info->comps_for_echannel[priv->echannel]; + unsigned int len = skb->len; + unsigned char *data = skb->data; + unsigned int num_edescs; + struct frag frags[MAX_FRAGS]; + gxio_mpipe_edesc_t edescs[MAX_FRAGS]; + unsigned long irqflags; + gxio_mpipe_edesc_t edesc = { { 0 } }; + unsigned int i; + s64 slot; + + if (skb_is_gso(skb)) + return tile_net_tx_tso(skb, dev); + + num_edescs = tile_net_tx_frags(frags, skb, data, skb_headlen(skb)); + + /* This is only used to specify the TLB. */ + edesc.stack_idx = large_buffer_stack; + + /* Prepare the edescs. */ + for (i = 0; i < num_edescs; i++) { + edesc.xfer_size = frags[i].length; + edesc.va = va_to_tile_io_addr(frags[i].buf); + edescs[i] = edesc; + } + + /* Mark the final edesc. */ + edescs[num_edescs - 1].bound = 1; + + /* Add checksum info to the initial edesc, if needed. */ + if (skb->ip_summed == CHECKSUM_PARTIAL) { + unsigned int csum_start = skb_checksum_start_offset(skb); + edescs[0].csum = 1; + edescs[0].csum_start = csum_start; + edescs[0].csum_dest = csum_start + skb->csum_offset; + } + + local_irq_save(irqflags); + + /* Try to acquire a completion entry and an egress slot. */ + slot = tile_net_equeue_try_reserve(dev, comps, equeue, num_edescs); + if (slot < 0) { + local_irq_restore(irqflags); + return NETDEV_TX_BUSY; + } + + for (i = 0; i < num_edescs; i++) + gxio_mpipe_equeue_put_at(equeue, edescs[i], slot++); + + /* Add a completion record. */ + add_comp(equeue, comps, slot - 1, skb); + + /* NOTE: Use ETH_ZLEN for short packets (e.g. 42 < 60). */ + tile_net_stats_add(1, &priv->stats.tx_packets); + tile_net_stats_add(max_t(unsigned int, len, ETH_ZLEN), + &priv->stats.tx_bytes); + + local_irq_restore(irqflags); + + /* Make sure the egress timer is scheduled. */ + tile_net_schedule_egress_timer(); + + return NETDEV_TX_OK; +} + +/* Return subqueue id on this core (one per core). */ +static u16 tile_net_select_queue(struct net_device *dev, struct sk_buff *skb) +{ + return smp_processor_id(); +} + +/* Deal with a transmit timeout. */ +static void tile_net_tx_timeout(struct net_device *dev) +{ + int cpu; + + for_each_online_cpu(cpu) + netif_wake_subqueue(dev, cpu); +} + +/* Ioctl commands. */ +static int tile_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + return -EOPNOTSUPP; +} + +/* Get system network statistics for device. */ +static struct net_device_stats *tile_net_get_stats(struct net_device *dev) +{ + struct tile_net_priv *priv = netdev_priv(dev); + return &priv->stats; +} + +/* Change the MTU. */ +static int tile_net_change_mtu(struct net_device *dev, int new_mtu) +{ + if ((new_mtu < 68) || (new_mtu > 1500)) + return -EINVAL; + dev->mtu = new_mtu; + return 0; +} + +/* Change the Ethernet address of the NIC. + * + * The hypervisor driver does not support changing MAC address. However, + * the hardware does not do anything with the MAC address, so the address + * which gets used on outgoing packets, and which is accepted on incoming + * packets, is completely up to us. + * + * Returns 0 on success, negative on failure. + */ +static int tile_net_set_mac_address(struct net_device *dev, void *p) +{ + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EINVAL; + memcpy(dev->dev_addr, addr->sa_data, dev->addr_len); + return 0; +} + +#ifdef CONFIG_NET_POLL_CONTROLLER +/* Polling 'interrupt' - used by things like netconsole to send skbs + * without having to re-enable interrupts. It's not called while + * the interrupt routine is executing. + */ +static void tile_net_netpoll(struct net_device *dev) +{ + disable_percpu_irq(ingress_irq); + tile_net_handle_ingress_irq(ingress_irq, NULL); + enable_percpu_irq(ingress_irq, 0); +} +#endif + +static const struct net_device_ops tile_net_ops = { + .ndo_open = tile_net_open, + .ndo_stop = tile_net_stop, + .ndo_start_xmit = tile_net_tx, + .ndo_select_queue = tile_net_select_queue, + .ndo_do_ioctl = tile_net_ioctl, + .ndo_get_stats = tile_net_get_stats, + .ndo_change_mtu = tile_net_change_mtu, + .ndo_tx_timeout = tile_net_tx_timeout, + .ndo_set_mac_address = tile_net_set_mac_address, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = tile_net_netpoll, +#endif +}; + +/* The setup function. + * + * This uses ether_setup() to assign various fields in dev, including + * setting IFF_BROADCAST and IFF_MULTICAST, then sets some extra fields. + */ +static void tile_net_setup(struct net_device *dev) +{ + ether_setup(dev); + dev->netdev_ops = &tile_net_ops; + dev->watchdog_timeo = TILE_NET_TIMEOUT; + dev->features |= NETIF_F_LLTX; + dev->features |= NETIF_F_HW_CSUM; + dev->features |= NETIF_F_SG; + dev->features |= NETIF_F_TSO; + dev->mtu = 1500; +} + +/* Allocate the device structure, register the device, and obtain the + * MAC address from the hypervisor. + */ +static void tile_net_dev_init(const char *name, const uint8_t *mac) +{ + int ret; + int i; + int nz_addr = 0; + struct net_device *dev; + struct tile_net_priv *priv; + + /* HACK: Ignore "loop" links. */ + if (strncmp(name, "loop", 4) == 0) + return; + + /* Allocate the device structure. Normally, "name" is a + * template, instantiated by register_netdev(), but not for us. + */ + dev = alloc_netdev_mqs(sizeof(*priv), name, tile_net_setup, + NR_CPUS, 1); + if (!dev) { + pr_err("alloc_netdev_mqs(%s) failed\n", name); + return; + } + + /* Initialize "priv". */ + priv = netdev_priv(dev); + memset(priv, 0, sizeof(*priv)); + priv->dev = dev; + priv->channel = -1; + priv->loopify_channel = -1; + priv->echannel = -1; + + /* Get the MAC address and set it in the device struct; this must + * be done before the device is opened. If the MAC is all zeroes, + * we use a random address, since we're probably on the simulator. + */ + for (i = 0; i < 6; i++) + nz_addr |= mac[i]; + + if (nz_addr) { + memcpy(dev->dev_addr, mac, 6); + dev->addr_len = 6; + } else { + random_ether_addr(dev->dev_addr); + } + + /* Register the network device. */ + ret = register_netdev(dev); + if (ret) { + netdev_err(dev, "register_netdev failed %d\n", ret); + free_netdev(dev); + return; + } +} + +/* Per-cpu module initialization. */ +static void tile_net_init_module_percpu(void *unused) +{ + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + int my_cpu = smp_processor_id(); + + info->has_iqueue = false; + + info->my_cpu = my_cpu; + + /* Initialize the egress timer. */ + hrtimer_init(&info->egress_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + info->egress_timer.function = tile_net_handle_egress_timer; +} + +/* Module initialization. */ +static int __init tile_net_init_module(void) +{ + int i; + char name[GXIO_MPIPE_LINK_NAME_LEN]; + uint8_t mac[6]; + + pr_info("Tilera Network Driver\n"); + + mutex_init(&tile_net_devs_for_channel_mutex); + + /* Initialize each CPU. */ + on_each_cpu(tile_net_init_module_percpu, NULL, 1); + + /* Find out what devices we have, and initialize them. */ + for (i = 0; gxio_mpipe_link_enumerate_mac(i, name, mac) >= 0; i++) + tile_net_dev_init(name, mac); + + if (!network_cpus_init()) + network_cpus_map = *cpu_online_mask; + + return 0; +} + +module_init(tile_net_init_module); -- cgit v0.10.2 From 8a93664df90db983cfede122f9b4ddb3a8284e52 Mon Sep 17 00:00:00 2001 From: Weiping Pan Date: Sun, 10 Jun 2012 23:00:20 +0000 Subject: bonding:record primary when modify it via sysfs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit If we modify primary via sysfs and it is not a valid slave, we should record it for future use, and this behavior is the same with bond_check_params(). Signed-off-by: Weiping Pan Acked-by: Nicolas de Pesloüan Signed-off-by: Jay Vosburgh Signed-off-by: David S. Miller diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index aef42f0..485bedb 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1082,8 +1082,12 @@ static ssize_t bonding_store_primary(struct device *d, } } - pr_info("%s: Unable to set %.*s as primary slave.\n", - bond->dev->name, (int)strlen(buf) - 1, buf); + strncpy(bond->params.primary, ifname, IFNAMSIZ); + bond->params.primary[IFNAMSIZ - 1] = 0; + + pr_info("%s: Recording %s as primary, " + "but it has not been enslaved to %s yet.\n", + bond->dev->name, ifname, bond->dev->name); out: write_unlock_bh(&bond->curr_slave_lock); read_unlock(&bond->lock); -- cgit v0.10.2 From 5ee31c6898ea5537fcea160999d60dc63bc0c305 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Jun 2012 06:03:51 +0000 Subject: bonding: Fix corrupted queue_mapping In the transmit path of the bonding driver, skb->cb is used to stash the skb->queue_mapping so that the bonding device can set its own queue mapping. This value becomes corrupted since the skb->cb is also used in __dev_xmit_skb. When transmitting through bonding driver, bond_select_queue is called from dev_queue_xmit. In bond_select_queue the original skb->queue_mapping is copied into skb->cb (via bond_queue_mapping) and skb->queue_mapping is overwritten with the bond driver queue. Subsequently in dev_queue_xmit, __dev_xmit_skb is called which writes the packet length into skb->cb, thereby overwriting the stashed queue mappping. In bond_dev_queue_xmit (called from hard_start_xmit), the queue mapping for the skb is set to the stashed value which is now the skb length and hence is an invalid queue for the slave device. If we want to save skb->queue_mapping into skb->cb[], best place is to add a field in struct qdisc_skb_cb, to make sure it wont conflict with other layers (eg : Qdiscc, Infiniband...) This patchs also makes sure (struct qdisc_skb_cb)->data is aligned on 8 bytes : netem qdisc for example assumes it can store an u64 in it, without misalignment penalty. Note : we only have 20 bytes left in (struct qdisc_skb_cb)->data[]. The largest user is CHOKe and it fills it. Based on a previous patch from Tom Herbert. Signed-off-by: Eric Dumazet Reported-by: Tom Herbert Cc: John Fastabend Cc: Roland Dreier Acked-by: Neil Horman Signed-off-by: David S. Miller diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2ee8cf9..b9c2ae6 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -76,6 +76,7 @@ #include #include #include +#include #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" @@ -381,8 +382,6 @@ struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr) return next; } -#define bond_queue_mapping(skb) (*(u16 *)((skb)->cb)) - /** * bond_dev_queue_xmit - Prepare skb for xmit. * @@ -395,7 +394,9 @@ int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, { skb->dev = slave_dev; - skb->queue_mapping = bond_queue_mapping(skb); + BUILD_BUG_ON(sizeof(skb->queue_mapping) != + sizeof(qdisc_skb_cb(skb)->bond_queue_mapping)); + skb->queue_mapping = qdisc_skb_cb(skb)->bond_queue_mapping; if (unlikely(netpoll_tx_running(slave_dev))) bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); @@ -4171,7 +4172,7 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb) /* * Save the original txq to restore before passing to the driver */ - bond_queue_mapping(skb) = skb->queue_mapping; + qdisc_skb_cb(skb)->bond_queue_mapping = skb->queue_mapping; if (unlikely(txq >= dev->real_num_tx_queues)) { do { diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 55ce96b..9d7d54a 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -220,13 +220,16 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; - unsigned char data[24]; + u16 bond_queue_mapping; + u16 _pad; + unsigned char data[20]; }; static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz) { struct qdisc_skb_cb *qcb; - BUILD_BUG_ON(sizeof(skb->cb) < sizeof(unsigned int) + sz); + + BUILD_BUG_ON(sizeof(skb->cb) < offsetof(struct qdisc_skb_cb, data) + sz); BUILD_BUG_ON(sizeof(qcb->data) < sz); } -- cgit v0.10.2 From 954fba0274058d27c7c07b5ea07c41b3b7477894 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Jun 2012 19:30:21 +0000 Subject: netpoll: fix netpoll_send_udp() bugs Bogdan Hamciuc diagnosed and fixed following bug in netpoll_send_udp() : "skb->len += len;" instead of "skb_put(skb, len);" Meaning that _if_ a network driver needs to call skb_realloc_headroom(), only packet headers would be copied, leaving garbage in the payload. However the skb_realloc_headroom() must be avoided as much as possible since it requires memory and netpoll tries hard to work even if memory is exhausted (using a pool of preallocated skbs) It appears netpoll_send_udp() reserved 16 bytes for the ethernet header, which happens to work for typicall drivers but not all. Right thing is to use LL_RESERVED_SPACE(dev) (And also add dev->needed_tailroom of tailroom) This patch combines both fixes. Many thanks to Bogdan for raising this issue. Reported-by: Bogdan Hamciuc Signed-off-by: Eric Dumazet Tested-by: Bogdan Hamciuc Cc: Herbert Xu Cc: Neil Horman Reviewed-by: Neil Horman Reviewed-by: Cong Wang Signed-off-by: David S. Miller diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 3d84fb9..f9f40b9 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -362,22 +362,23 @@ EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { - int total_len, eth_len, ip_len, udp_len; + int total_len, ip_len, udp_len; struct sk_buff *skb; struct udphdr *udph; struct iphdr *iph; struct ethhdr *eth; udp_len = len + sizeof(*udph); - ip_len = eth_len = udp_len + sizeof(*iph); - total_len = eth_len + ETH_HLEN + NET_IP_ALIGN; + ip_len = udp_len + sizeof(*iph); + total_len = ip_len + LL_RESERVED_SPACE(np->dev); - skb = find_skb(np, total_len, total_len - len); + skb = find_skb(np, total_len + np->dev->needed_tailroom, + total_len - len); if (!skb) return; skb_copy_to_linear_data(skb, msg, len); - skb->len += len; + skb_put(skb, len); skb_push(skb, sizeof(*udph)); skb_reset_transport_header(skb); -- cgit v0.10.2 From d6cb3e41386f20fb0777d0b59a2def82c65d37f7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Jun 2012 23:50:04 +0000 Subject: bnx2x: fix checksum validation bnx2x driver incorrectly sets ip_summed to CHECKSUM_UNNECESSARY on encapsulated segments. TCP stack happily accepts frames with bad checksums, if they are inside a GRE or IPIP encapsulation. Our understanding is that if no IP or L4 csum validation was done by the hardware, we should leave ip_summed as is (CHECKSUM_NONE), since hardware doesn't provide CHECKSUM_COMPLETE support in its cqe. Then, if IP/L4 checksumming was done by the hardware, set CHECKSUM_UNNECESSARY if no error was flagged. Patch based on findings and analysis from Robert Evans Signed-off-by: Eric Dumazet Cc: Eilon Greenstein Cc: Yaniv Rosner Cc: Merav Sicron Cc: Tom Herbert Cc: Robert Evans Cc: Willem de Bruijn Acked-by: Eilon Greenstein Signed-off-by: David S. Miller diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index e30e2a2..7de8241 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -747,21 +747,6 @@ struct bnx2x_fastpath { #define ETH_RX_ERROR_FALGS ETH_FAST_PATH_RX_CQE_PHY_DECODE_ERR_FLG -#define BNX2X_IP_CSUM_ERR(cqe) \ - (!((cqe)->fast_path_cqe.status_flags & \ - ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG) && \ - ((cqe)->fast_path_cqe.type_error_flags & \ - ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG)) - -#define BNX2X_L4_CSUM_ERR(cqe) \ - (!((cqe)->fast_path_cqe.status_flags & \ - ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG) && \ - ((cqe)->fast_path_cqe.type_error_flags & \ - ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG)) - -#define BNX2X_RX_CSUM_OK(cqe) \ - (!(BNX2X_L4_CSUM_ERR(cqe) || BNX2X_IP_CSUM_ERR(cqe))) - #define BNX2X_PRS_FLAG_OVERETH_IPV4(flags) \ (((le16_to_cpu(flags) & \ PARSING_FLAGS_OVER_ETHERNET_PROTOCOL) >> \ diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index ad0743b..cbc56f2 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -617,6 +617,25 @@ static int bnx2x_alloc_rx_data(struct bnx2x *bp, return 0; } +static void bnx2x_csum_validate(struct sk_buff *skb, union eth_rx_cqe *cqe, + struct bnx2x_fastpath *fp) +{ + /* Do nothing if no IP/L4 csum validation was done */ + + if (cqe->fast_path_cqe.status_flags & + (ETH_FAST_PATH_RX_CQE_IP_XSUM_NO_VALIDATION_FLG | + ETH_FAST_PATH_RX_CQE_L4_XSUM_NO_VALIDATION_FLG)) + return; + + /* If both IP/L4 validation were done, check if an error was found. */ + + if (cqe->fast_path_cqe.type_error_flags & + (ETH_FAST_PATH_RX_CQE_IP_BAD_XSUM_FLG | + ETH_FAST_PATH_RX_CQE_L4_BAD_XSUM_FLG)) + fp->eth_q_stats.hw_csum_err++; + else + skb->ip_summed = CHECKSUM_UNNECESSARY; +} int bnx2x_rx_int(struct bnx2x_fastpath *fp, int budget) { @@ -806,13 +825,9 @@ reuse_rx: skb_checksum_none_assert(skb); - if (bp->dev->features & NETIF_F_RXCSUM) { + if (bp->dev->features & NETIF_F_RXCSUM) + bnx2x_csum_validate(skb, cqe, fp); - if (likely(BNX2X_RX_CSUM_OK(cqe))) - skb->ip_summed = CHECKSUM_UNNECESSARY; - else - fp->eth_q_stats.hw_csum_err++; - } skb_record_rx_queue(skb, fp->rx_queue); -- cgit v0.10.2