Add more kernel panic information
authorMichal Sojka <sojkam1@fel.cvut.cz>
Sun, 5 Dec 2010 09:56:32 +0000 (10:56 +0100)
committerMichal Sojka <sojkam1@fel.cvut.cz>
Sun, 5 Dec 2010 09:56:32 +0000 (10:56 +0100)
doc/notes.org

index b27d6e2..db1b96c 100644 (file)
@@ -189,6 +189,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q,
        spin_lock(root_lock);
 
 ** 2.6.36.1-00006-g2e11adb
+Unable to handle kernel paging request for data at address 0xfffffffe
 Faulting instruction address: 0xc0262358
 Oops: Kernel access of bad area, sig: 11 [#1]
 PREEMPT Shark
@@ -263,6 +264,201 @@ Call Trace:
 [c0401fc0] [c03ad91c] start_kernel+0x2c0/0x2d8
 [c0401ff0] [00003438] 0x3438
 
+** With "Spinlock and rw-lock debugging: basic checks" 
+BUG: spinlock bad magic on CPU#0, swapper/0
+ lock: c7985abc, .magic: c0000000, .owner: <none>/-1, .owner_cpu: -1069448776
+
+
+** With "Spinlock debugging: sleep-inside-spinlock checking"
+BUG: sleeping function called from invalid context at /home/wsh/projects/can-benchmark/kernel/2.6.36/mm/slab.c:3101
+in_atomic(): 1, irqs_disabled(): 0, pid: 379, name: cangw
+Call Trace:
+[c7abdb50] [c0009c04] show_stack+0xb0/0x1d4 (unreliable)
+[c7abdba0] [c02ffe54] dump_stack+0x2c/0x44
+[c7abdbb0] [c002157c] __might_sleep+0xfc/0x124
+[c7abdbc0] [c00c45bc] kmem_cache_alloc+0x15c/0x180
+[c7abdbf0] [c02d60d8] can_rx_register+0x78/0x210
+[c7abdc30] [c02d9ebc] cgw_create_job+0x1cc/0x220
+[c7abdc50] [c026c208] rtnetlink_rcv_msg+0x21c/0x28c
+[c7abdc70] [c02762a4] netlink_rcv_skb+0xb8/0x100
+[c7abdc90] [c026bfd0] rtnetlink_rcv+0x40/0x5c
+[c7abdcb0] [c0275e9c] netlink_unicast+0x320/0x368
+[c7abdd00] [c0276a0c] netlink_sendmsg+0x2e0/0x33c
+[c7abdd50] [c0244cc0] sock_sendmsg+0x9c/0xd4
+[c7abde20] [c0247194] sys_sendto+0xcc/0x108
+[c7abdf00] [c0248980] sys_socketcall+0x17c/0x218
+[c7abdf40] [c0012524] ret_from_syscall+0x0/0x38
+--- Exception: c01 at 0xff3413c
+    LR = 0x10001f9c
+BUG: spinlock bad magic on CPU#0, swapper/0
+ lock: c798aabc, .magic: c0000000, .owner: <none>/-1, .owner_cpu: -1069424200
+Call Trace:
+[c7ffbd00] [c0009c04] show_stack+0xb0/0x1d4 (unreliable)
+[c7ffbd50] [c02ffe54] dump_stack+0x2c/0x44
+[c7ffbd60] [c01afa50] spin_bug+0x84/0xd0
+[c7ffbd80] [c01afbfc] do_raw_spin_lock+0x3c/0x15c
+[c7ffbdb0] [c02ff70c] _raw_spin_lock+0x34/0x4c
+[c7ffbdd0] [c025bbdc] dev_queue_xmit+0xa4/0x428
+[c7ffbe00] [c02d630c] can_send+0x9c/0x1a0
+[c7ffbe20] [c02d991c] can_can_gw_rcv+0x108/0x164
+[c7ffbe50] [c02d53b4] can_rcv_filter+0xf8/0x2e8
+[c7ffbe70] [c02d566c] can_rcv+0xc8/0x140
+[c7ffbe90] [c025a0d0] __netif_receive_skb+0x2cc/0x338
+[c7ffbed0] [c025a314] netif_receive_skb+0x5c/0x98
+[c7ffbef0] [c0208374] mscan_rx_poll+0x1c0/0x454
+[c7ffbf50] [c025a644] net_rx_action+0x104/0x230
+[c7ffbfa0] [c00317a8] __do_softirq+0x118/0x22c
+[c7ffbff0] [c0011eec] call_do_softirq+0x14/0x24
+[c042fe60] [c0006d78] do_softirq+0x84/0xa8
+[c042fe80] [c00314cc] irq_exit+0x88/0xb4
+[c042fe90] [c0006efc] do_IRQ+0xe0/0x234
+[c042fec0] [c0012bbc] ret_from_except+0x0/0x14
+--- Exception: 501 at cpu_idle+0xfc/0x10c
+    LR = cpu_idle+0xfc/0x10c
+[c042ff80] [c000afb8] cpu_idle+0x68/0x10c (unreliable)
+[c042ffa0] [c0003ec0] rest_init+0x9c/0xbc
+[c042ffc0] [c03da91c] start_kernel+0x2c0/0x2d8
+[c042fff0] [00003438] 0x3438
+** First patch
+diff --git a/net/can/gw.c b/net/can/gw.c
+index 94ba3f1..7779ca6 100644
+--- a/net/can/gw.c
++++ b/net/can/gw.c
+@@ -822,11 +822,14 @@ static int cgw_create_job(struct sk_buff *skb,  struct nlmsghdr *nlh,
+        if (gwj->dst.dev->type != ARPHRD_CAN)
+                goto put_src_dst_out;
+                
+-       spin_lock(&cgw_list_lock);
+        err = cgw_register_filter(gwj);
+-       if (!err)
+-               hlist_add_head_rcu(&gwj->list, &cgw_list);
++       if (err)
++               goto put_src_dst_out;
++
++       spin_lock(&cgw_list_lock);
++
++       hlist_add_head_rcu(&gwj->list, &cgw_list);
+        spin_unlock(&cgw_list_lock);
+** GFP_ATOMIC patch
+diff --git a/net/can/af_can.c b/net/can/af_can.c
+index 702be5a..b046ff0 100644
+--- a/net/can/af_can.c
++++ b/net/can/af_can.c
+@@ -418,7 +418,7 @@ int can_rx_register(struct net_device *dev, canid_t can_id, canid_t mask,
+        if (dev && dev->type != ARPHRD_CAN)
+                return -ENODEV;
+-       r = kmem_cache_alloc(rcv_cache, GFP_KERNEL);
++       r = kmem_cache_alloc(rcv_cache, GFP_ATOMIC);
+        if (!r)
+                return -ENOMEM;
+
+        
+** Another panic
+BUG: spinlock bad magic on CPU#0, swapper/0
+ lock: c7986abc, .magic: c0000000, .owner: <none>/-1, .owner_cpu: -1069424200
+Call Trace:
+[c7ffbd00] [c0009c04] show_stack+0xb0/0x1d4 (unreliable)
+[c7ffbd50] [c02ffe54] dump_stack+0x2c/0x44
+[c7ffbd60] [c01afa50] spin_bug+0x84/0xd0
+[c7ffbd80] [c01afbfc] do_raw_spin_lock+0x3c/0x15c
+[c7ffbdb0] [c02ff70c] _raw_spin_lock+0x34/0x4c
+[c7ffbdd0] [c025bbdc] dev_queue_xmit+0xa4/0x428
+[c7ffbe00] [c02d630c] can_send+0x9c/0x1a0
+[c7ffbe20] [c02d991c] can_can_gw_rcv+0x108/0x164
+[c7ffbe50] [c02d53b4] can_rcv_filter+0xf8/0x2e8
+[c7ffbe70] [c02d566c] can_rcv+0xc8/0x140
+[c7ffbe90] [c025a0d0] __netif_receive_skb+0x2cc/0x338
+[c7ffbed0] [c025a314] netif_receive_skb+0x5c/0x98
+[c7ffbef0] [c0208374] mscan_rx_poll+0x1c0/0x454
+[c7ffbf50] [c025a644] net_rx_action+0x104/0x230
+[c7ffbfa0] [c00317a8] __do_softirq+0x118/0x22c
+[c7ffbff0] [c0011eec] call_do_softirq+0x14/0x24
+[c042fe60] [c0006d78] do_softirq+0x84/0xa8
+[c042fe80] [c00314cc] irq_exit+0x88/0xb4
+[c042fe90] [c0006efc] do_IRQ+0xe0/0x234
+[c042fec0] [c0012bbc] ret_from_except+0x0/0x14
+--- Exception: 501 at cpu_idle+0xfc/0x10c
+    LR = cpu_idle+0xfc/0x10c
+[c042ff80] [c000afb8] cpu_idle+0x68/0x10c (unreliable)
+[c042ffa0] [c0003ec0] rest_init+0x9c/0xbc
+[c042ffc0] [c03da91c] start_kernel+0x2c0/0x2d8
+[c042fff0] [00003438] 0x3438
+Unrecoverable FP Unavailable Exception 801 at c7986ca0
+Oops: Unrecoverable FP Unavailable Exception, sig: 6 [#1]
+PREEMPT Shark
+last sysfs file: /sys/devices/lpb.0/fc000000.flash/mtd/mtd2ro/dev
+Modules linked in:
+NIP: c7986ca0 LR: c025bc3c CTR: c7986ca0
+REGS: c7ffbd20 TRAP: 0801   Not tainted  (2.6.36.1-00006-g2e11adb-dirty)
+MSR: 00009032 <EE,ME,IR,DR>  CR: 22002024  XER: 2000005f
+TASK = c0411520[0] 'swapper' THREAD: c042e000
+GPR00: c7986ca0 c7ffbdd0 c0411520 c79b8240 c7986a60 00000010 c043b384 00004000 
+GPR08: c043b788 00000000 00003fff c7ffbdd0 42002024 
+NIP [c7986ca0] 0xc7986ca0
+LR [c025bc3c] dev_queue_xmit+0x104/0x428
+Call Trace:
+[c7ffbdd0] [c025bbdc] dev_queue_xmit+0xa4/0x428 (unreliable)
+[c7ffbe00] [c02d630c] can_send+0x9c/0x1a0
+[c7ffbe20] [c02d991c] can_can_gw_rcv+0x108/0x164
+[c7ffbe50] [c02d53b4] can_rcv_filter+0xf8/0x2e8
+[c7ffbe70] [c02d566c] can_rcv+0xc8/0x140
+[c7ffbe90] [c025a0d0] __netif_receive_skb+0x2cc/0x338
+[c7ffbed0] [c025a314] netif_receive_skb+0x5c/0x98
+[c7ffbef0] [c0208374] mscan_rx_poll+0x1c0/0x454
+[c7ffbf50] [c025a644] net_rx_action+0x104/0x230
+[c7ffbfa0] [c00317a8] __do_softirq+0x118/0x22c
+[c7ffbff0] [c0011eec] call_do_softirq+0x14/0x24
+[c042fe60] [c0006d78] do_softirq+0x84/0xa8
+[c042fe80] [c00314cc] irq_exit+0x88/0xb4
+[c042fe90] [c0006efc] do_IRQ+0xe0/0x234
+[c042fec0] [c0012bbc] ret_from_except+0x0/0x14
+--- Exception: 501 at cpu_idle+0xfc/0x10c
+    LR = cpu_idle+0xfc/0x10c
+[c042ff80] [c000afb8] cpu_idle+0x68/0x10c (unreliable)
+[c042ffa0] [c0003ec0] rest_init+0x9c/0xbc
+[c042ffc0] [c03da91c] start_kernel+0x2c0/0x2d8
+[c042fff0] [00003438] 0x3438
+Instruction dump:
+XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX 
+XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX XXXXXXXX 
+Kernel panic - not syncing: Fatal exception in interrupt
+Call Trace:
+[c7ffbc10] [c0009c04] show_stack+0xb0/0x1d4 (unreliable)
+[c7ffbc60] [c02ffe54] dump_stack+0x2c/0x44
+[c7ffbc70] [c02fff28] panic+0xbc/0x200
+[c7ffbcd0] [c000faf8] die+0x1a4/0x1cc
+[c7ffbcf0] [c000fc34] kernel_fp_unavailable_exception+0x4c/0x64
+[c7ffbd10] [c0012bbc] ret_from_except+0x0/0x14
+--- Exception: 801 at 0xc7986ca0
+    LR = dev_queue_xmit+0x104/0x428
+[c7ffbdd0] [c025bbdc] dev_queue_xmit+0xa4/0x428 (unreliable)
+[c7ffbe00] [c02d630c] can_send+0x9c/0x1a0
+[c7ffbe20] [c02d991c] can_can_gw_rcv+0x108/0x164
+[c7ffbe50] [c02d53b4] can_rcv_filter+0xf8/0x2e8
+[c7ffbe70] [c02d566c] can_rcv+0xc8/0x140
+[c7ffbe90] [c025a0d0] __netif_receive_skb+0x2cc/0x338
+[c7ffbed0] [c025a314] netif_receive_skb+0x5c/0x98
+[c7ffbef0] [c0208374] mscan_rx_poll+0x1c0/0x454
+[c7ffbf50] [c025a644] net_rx_action+0x104/0x230
+[c7ffbfa0] [c00317a8] __do_softirq+0x118/0x22c
+[c7ffbff0] [c0011eec] call_do_softirq+0x14/0x24
+[c042fe60] [c0006d78] do_softirq+0x84/0xa8
+[c042fe80] [c00314cc] irq_exit+0x88/0xb4
+[c042fe90] [c0006efc] do_IRQ+0xe0/0x234
+[c042fec0] [c0012bbc] ret_from_except+0x0/0x14
+--- Exception: 501 at cpu_idle+0xfc/0x10c
+    LR = cpu_idle+0xfc/0x10c
+[c042ff80] [c000afb8] cpu_idle+0x68/0x10c (unreliable)
+[c042ffa0] [c0003ec0] rest_init+0x9c/0xbc
+[c042ffc0] [c03da91c] start_kernel+0x2c0/0x2d8
+[c042fff0] [00003438] 0x3438
+
 * write returns ENOBUFS
 The reason is queuing discipline - the queue is full and
 pfifo_fast_enqueue returns failure. This failure is propagated down to