Bug 7611

Most recent kernel where this bug did *NOT* occur: errrrr
Distribution: FC6
Hardware Environment: x86+64
Software Environment: FC6 based using stock 2.6.19-rc6
Problem Description: eth0: hw csum failure.

Steps to reproduce: just use the network

Sorry, I couldn't quite work out the mechanism to convert the stack output into
line numbers despite having the kernel source and compiled objects to hand 8/

the way I've gotten around this is to simply use
   ethtool -K eth0 rx off tx off
which only fixs the symptom not the problem. Though going by the trace it seems
to be on the rx side though thats no guarentte it doesn't exist in the tx path

Phil
=--=


eth0: hw csum failure.

Call Trace:
 [<ffffffff80268741>] show_trace+0x34/0x47
 [<ffffffff80268766>] dump_stack+0x12/0x17
 [<ffffffff8024aa75>] __skb_checksum_complete+0x4a/0x62
 [<ffffffff802268dd>] tcp_v4_rcv+0x17f/0x9b7
 [<ffffffff80233621>] ip_local_deliver+0x19b/0x25f
 [<ffffffff802345dd>] ip_rcv+0x499/0x4e0
 [<ffffffff8021ff8f>] netif_receive_skb+0x350/0x3db
 [<ffffffff8819cb95>] :sky2:sky2_poll+0x7f0/0xa86
 [<ffffffff8020bf8c>] net_rx_action+0xa4/0x1a7
 [<ffffffff80211924>] __do_softirq+0x55/0xc3
 [<ffffffff8025c24c>] call_softirq+0x1c/0x30
DWARF2 unwinder stuck at call_softirq+0x1c/0x30

Leftover inexact backtrace:

 <IRQ>  [<ffffffff802697ab>] do_softirq+0x2c/0x7d
 [<ffffffff8026992c>] do_IRQ+0x130/0x151
 [<ffffffff802546db>] mwait_idle+0x0/0x20
 [<ffffffff8025b641>] ret_from_intr+0x0/0xa
 <EOI>  [<ffffffff80267ead>] mwait_idle_with_hints+0x44/0x45
 [<ffffffff802546e7>] mwait_idle+0xc/0x20
 [<ffffffff80246ab7>] cpu_idle+0x8b/0xae
 [<ffffffff80895697>] start_kernel+0x22a/0x22f
 [<ffffffff8089515c>] _sinittext+0x15c/0x160

****

relevent routines and locations (based on 2.6.19-rc6)

--------------------------------------------------
__skb_checksum_complete     net/core/datagram.c +414
--------------------------------------------------
unsigned int __skb_checksum_complete(struct sk_buff *skb)
{
        unsigned int sum;

        sum = (u16)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum));
        if (likely(!sum)) {
                if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
                        netdev_rx_csum_fault(skb->dev);
                skb->ip_summed = CHECKSUM_UNNECESSARY;
        }
        return sum;
}
EXPORT_SYMBOL(__skb_checksum_complete);


--------------------------------------------------
tcp_v4_rcv    net/ipv4/tcp_ipv4.c +1053
--------------------------------------------------
int tcp_v4_rcv(struct sk_buff *skb)
{               
        struct tcphdr *th;
        struct sock *sk;
        int ret;

        if (skb->pkt_type != PACKET_HOST)
                goto discard_it;
                
        /* Count it even if it's bad */
        TCP_INC_STATS_BH(TCP_MIB_INSEGS);
                
        if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
                goto discard_it;

        th = skb->h.th;
                        
        if (th->doff < sizeof(struct tcphdr) / 4)
                goto bad_packet;
        if (!pskb_may_pull(skb, th->doff * 4))
                goto discard_it;
        
        /* An explanation is required here, I think.
         * Packet length and doff are validated by header prediction,
         * provided case of th->doff==0 is eliminated.
         * So, we defer the checks. */
        if ((skb->ip_summed != CHECKSUM_UNNECESSARY &&
             tcp_v4_checksum_init(skb)))
                goto bad_packet;
                
        th = skb->h.th;
        TCP_SKB_CB(skb)->seq = ntohl(th->seq);
        TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
                                    skb->len - th->doff * 4);
        TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
        TCP_SKB_CB(skb)->when    = 0;
        TCP_SKB_CB(skb)->flags   = skb->nh.iph->tos;
        TCP_SKB_CB(skb)->sacked  = 0;

        sk = __inet_lookup(&tcp_hashinfo, skb->nh.iph->saddr, th->source,
                           skb->nh.iph->daddr, th->dest,
                           inet_iif(skb));
         
        if (!sk)
                goto no_tcp_socket;
        
process:                
        if (sk->sk_state == TCP_TIME_WAIT)
                goto do_time_wait;
                
        if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
                goto discard_and_relse;
        nf_reset(skb);  
        
        if (sk_filter(sk, skb))
                goto discard_and_relse;
                
        skb->dev = NULL;  
        
        bh_lock_sock_nested(sk);
        ret = 0;
        if (!sock_owned_by_user(sk)) {   
#ifdef CONFIG_NET_DMA
                struct tcp_sock *tp = tcp_sk(sk);
                if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
                        tp->ucopy.dma_chan = get_softnet_dma();
                if (tp->ucopy.dma_chan)
                        ret = tcp_v4_do_rcv(sk, skb);  
                else
#endif
                {
                        if (!tcp_prequeue(sk, skb))
                        ret = tcp_v4_do_rcv(sk, skb);
                }
        } else
                sk_add_backlog(sk, skb);
        bh_unlock_sock(sk);

        sock_put(sk);
        
        return ret;
        
no_tcp_socket:
        if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
                goto discard_it;
 
        if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
bad_packet:
                TCP_INC_STATS_BH(TCP_MIB_INERRS);
        } else {
                tcp_v4_send_reset(skb);
        }
        
discard_it:
        /* Discard frame. */
        kfree_skb(skb);
        return 0;
         
discard_and_relse:
        sock_put(sk);
        goto discard_it;

do_time_wait:
        if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
                inet_twsk_put(inet_twsk(sk));
                goto discard_it;
        }
        
        if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
                TCP_INC_STATS_BH(TCP_MIB_INERRS);
                inet_twsk_put(inet_twsk(sk));
                goto discard_it;
        }
        switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
        case TCP_TW_SYN: {
                struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo,
                                                        skb->nh.iph->daddr,
                                                        th->dest,
                                                        inet_iif(skb));
                if (sk2) {
                        inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
                        inet_twsk_put(inet_twsk(sk));
                        sk = sk2;
                        goto process;
                }
                /* Fall through to ACK */
        }
        case TCP_TW_ACK:
                tcp_v4_timewait_ack(sk, skb);
                break;
        case TCP_TW_RST:
                goto no_tcp_socket;
        case TCP_TW_SUCCESS:;
        }
        goto discard_it;
}


--------------------------------------------------
ip_local_deliver    net/ipv4/ip_input.c +263
--------------------------------------------------
int ip_local_deliver(struct sk_buff *skb)
{
        /*
         *      Reassemble IP fragments.
         */
         
        if (skb->nh.iph->frag_off & htons(IP_MF|IP_OFFSET)) {
                skb = ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER);
                if (!skb)
                        return 0;
        }
          
        return NF_HOOK(PF_INET, NF_IP_LOCAL_IN, skb, skb->dev, NULL,
                       ip_local_deliver_finish);
}



--------------------------------------------------
ip_rcv    net/ipv4/ip_input.c +373
--------------------------------------------------
int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
struct net_device *orig_dev)
{
        struct iphdr *iph;
        u32 len;

        /* When the interface is in promisc. mode, drop all the crap
         * that it receives, do not try to analyse it.
         */
        if (skb->pkt_type == PACKET_OTHERHOST)
                goto drop;

        IP_INC_STATS_BH(IPSTATS_MIB_INRECEIVES);

        if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) {
                IP_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
                goto out;
        }

        if (!pskb_may_pull(skb, sizeof(struct iphdr)))
                goto inhdr_error;

        iph = skb->nh.iph;

        /*
         *      RFC1122: 3.1.2.2 MUST silently discard any IP frame that fails
the checksum.
         *
         *      Is the datagram acceptable?
         *
         *      1.      Length at least the size of an ip header
         *      2.      Version of 4
         *      3.      Checksums correctly. [Speed optimisation for later, skip
loopback checksums]
         *      4.      Doesn't have a bogus length
         */

        if (iph->ihl < 5 || iph->version != 4)
                goto inhdr_error;

        if (!pskb_may_pull(skb, iph->ihl*4))
                goto inhdr_error;

        iph = skb->nh.iph; 
 
        if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl)))
                goto inhdr_error;

        len = ntohs(iph->tot_len);
        if (skb->len < len || len < (iph->ihl*4))
                goto inhdr_error;

        /* Our transport medium may have padded the buffer out. Now we know it
         * is IP we can trim to the true length of the frame.
         * Note this now means skb->len holds ntohs(iph->tot_len).
         */
        if (pskb_trim_rcsum(skb, len)) {
                IP_INC_STATS_BH(IPSTATS_MIB_INDISCARDS);
                goto drop;
        } 
         
        /* Remove any debris in the socket control block */
        memset(IPCB(skb), 0, sizeof(struct inet_skb_parm));
         
        return NF_HOOK(PF_INET, NF_IP_PRE_ROUTING, skb, dev, NULL,
                       ip_rcv_finish);

inhdr_error:
        IP_INC_STATS_BH(IPSTATS_MIB_INHDRERRORS);
drop:
        kfree_skb(skb);
out:
        return NET_RX_DROP;
}


--------------------------------------------------
netif_receive_skb    net/core/dev.c +1765
--------------------------------------------------
int netif_receive_skb(struct sk_buff *skb)
{
        struct packet_type *ptype, *pt_prev;
        struct net_device *orig_dev;
        int ret = NET_RX_DROP;
        unsigned short type;

        /* if we've gotten here through NAPI, check netpoll */
        if (skb->dev->poll && netpoll_rx(skb))
                return NET_RX_DROP;

        if (!skb->tstamp.off_sec)
                net_timestamp(skb);

        if (!skb->input_dev)
                skb->input_dev = skb->dev;

        orig_dev = skb_bond(skb);

        if (!orig_dev)
                return NET_RX_DROP;

        __get_cpu_var(netdev_rx_stat).total++;

        skb->h.raw = skb->nh.raw = skb->data;
        skb->mac_len = skb->nh.raw - skb->mac.raw;

        pt_prev = NULL;

        rcu_read_lock();

#ifdef CONFIG_NET_CLS_ACT
        if (skb->tc_verd & TC_NCLS) {
                skb->tc_verd = CLR_TC_NCLS(skb->tc_verd);
                goto ncls;
        }
#endif

        list_for_each_entry_rcu(ptype, &ptype_all, list) {
                if (!ptype->dev || ptype->dev == skb->dev) {
                        if (pt_prev) 
                                ret = deliver_skb(skb, pt_prev, orig_dev);
                        pt_prev = ptype;
                }
        }

#ifdef CONFIG_NET_CLS_ACT
        if (pt_prev) {
                ret = deliver_skb(skb, pt_prev, orig_dev);
                pt_prev = NULL; /* noone else should process this after*/
        } else {
                skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd);
        }

        ret = ing_filter(skb);

        if (ret == TC_ACT_SHOT || (ret == TC_ACT_STOLEN)) {
                kfree_skb(skb);
                goto out;
        }

        skb->tc_verd = 0;
ncls:
#endif

        handle_diverter(skb);

        if (handle_bridge(&skb, &pt_prev, &ret, orig_dev))
                goto out;

        type = skb->protocol;
        list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) {
                if (ptype->type == type &&
                    (!ptype->dev || ptype->dev == skb->dev)) {
                        if (pt_prev) 
                                ret = deliver_skb(skb, pt_prev, orig_dev);
                        pt_prev = ptype;
                }
        }

        if (pt_prev) {
                ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
        } else {
                kfree_skb(skb);
                /* Jamal, now you will not able to escape explaining
                 * me how you were going to use this. :-)
                 */
                ret = NET_RX_DROP;
        }

out:
        rcu_read_unlock();
        return ret;
}


--------------------------------------------------
sky2_poll    drivers/net/sky2.c +2304
--------------------------------------------------
static int sky2_poll(struct net_device *dev0, int *budget)
{
        struct sky2_hw *hw = ((struct sky2_port *) netdev_priv(dev0))->hw;
        int work_limit = min(dev0->quota, *budget);
        int work_done = 0;
        u32 status = sky2_read32(hw, B0_Y2_SP_EISR);

        if (status & Y2_IS_HW_ERR)
                sky2_hw_intr(hw);

        if (status & Y2_IS_IRQ_PHY1)
                sky2_phy_intr(hw, 0);

        if (status & Y2_IS_IRQ_PHY2)
                sky2_phy_intr(hw, 1);

        if (status & Y2_IS_IRQ_MAC1)
                sky2_mac_intr(hw, 0);

        if (status & Y2_IS_IRQ_MAC2)
                sky2_mac_intr(hw, 1);

        if (status & Y2_IS_CHK_RX1)
                sky2_descriptor_error(hw, 0, "receive", Y2_IS_CHK_RX1);

        if (status & Y2_IS_CHK_RX2)
                sky2_descriptor_error(hw, 1, "receive", Y2_IS_CHK_RX2);

        if (status & Y2_IS_CHK_TXA1)
                sky2_descriptor_error(hw, 0, "transmit", Y2_IS_CHK_TXA1);

        if (status & Y2_IS_CHK_TXA2)
                sky2_descriptor_error(hw, 1, "transmit", Y2_IS_CHK_TXA2);

        work_done = sky2_status_intr(hw, work_limit);
        if (work_done < work_limit) {
                netif_rx_complete(dev0);

                sky2_read32(hw, B0_Y2_SP_LISR);
                return 0;
        } else {
                *budget -= work_done;
                dev0->quota -= work_done;
                return 1;
        }
}


--------------------------------------------------
net_rx_action    net/core/dev.c +1907
--------------------------------------------------

static void net_rx_action(struct softirq_action *h)
{
        struct softnet_data *queue = &__get_cpu_var(softnet_data);
        unsigned long start_time = jiffies;
        int budget = netdev_budget;
        void *have;

        local_irq_disable();

        while (!list_empty(&queue->poll_list)) {
                struct net_device *dev;

                if (budget <= 0 || jiffies - start_time > 1)
                        goto softnet_break;

                local_irq_enable();

                dev = list_entry(queue->poll_list.next,
                                 struct net_device, poll_list);
                have = netpoll_poll_lock(dev);

                if (dev->quota <= 0 || dev->poll(dev, &budget)) {
                        netpoll_poll_unlock(have);
                        local_irq_disable();
                        list_move_tail(&dev->poll_list, &queue->poll_list);
                        if (dev->quota < 0)
                                dev->quota += dev->weight;
                        else
                                dev->quota = dev->weight;
                } else {
                        netpoll_poll_unlock(have);
                        dev_put(dev);
                        local_irq_disable();
                }
        }
out:
#ifdef CONFIG_NET_DMA
        /*
         * There may not be any more sk_buffs coming right now, so push
         * any pending DMA copies to hardware
         */
        if (net_dma_client) {
                struct dma_chan *chan;
                rcu_read_lock();
                list_for_each_entry_rcu(chan, &net_dma_client->channels, client_
node)
                        dma_async_memcpy_issue_pending(chan);
                rcu_read_unlock();
        }
#endif
        local_irq_enable();
        return;

softnet_break:
        __get_cpu_var(netdev_rx_stat).time_squeeze++;
        __raise_softirq_irqoff(NET_RX_SOFTIRQ);
        goto out;
}