forked from luck/tmp_suning_uos_patched
2efaf5ff7f
The recovery thread, when failing, tears down the respective interface. To do so, it needs to obtain the rtnl lock first, as the interface configuration is changed. If another process tries to modify an interface setting at the same time, that process can obtain the rtnl lock first, but the respective callback in the qeth driver will block until recovery has completed - which cannot happen since the calling process already obtained it. In one particular case, the bonding driver acquired the rtnl lock to modify the card's MAC address, while the recovery failed at the same time due to the card being removed. Hence qeth_l2_set_mac_address (implicitly holding the rtnl lock) was waiting on qeth_l2_recover, which deadlocked when waiting on the rtnl lock. This patch uses rtnl_trylock instead of rtnl_lock in the recovery thread. If the lock cannot be obtained, the interface will be left up, but the card state remains in CARD_STATE_RECOVER, which will prevent any further activities on the card. Signed-off-by: Stefan Raspl <raspl@linux.vnet.ibm.com> Signed-off-by: Frank Blaschka <frank.blaschka@de.ibm.com> Reviewed-by: Ursula Braun <ursula.braun@de.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net> |
||
|---|---|---|
| .. | ||
| claw.c | ||
| claw.h | ||
| ctcm_dbug.c | ||
| ctcm_dbug.h | ||
| ctcm_fsms.c | ||
| ctcm_fsms.h | ||
| ctcm_main.c | ||
| ctcm_main.h | ||
| ctcm_mpc.c | ||
| ctcm_mpc.h | ||
| ctcm_sysfs.c | ||
| fsm.c | ||
| fsm.h | ||
| Kconfig | ||
| lcs.c | ||
| lcs.h | ||
| Makefile | ||
| netiucv.c | ||
| qeth_core_main.c | ||
| qeth_core_mpc.c | ||
| qeth_core_mpc.h | ||
| qeth_core_sys.c | ||
| qeth_core.h | ||
| qeth_l2_main.c | ||
| qeth_l3_main.c | ||
| qeth_l3_sys.c | ||
| qeth_l3.h | ||
| smsgiucv_app.c | ||
| smsgiucv.c | ||
| smsgiucv.h | ||