I am trying to call sock_sendmsg() from a kernel thread
and it seems to work fine on a UP system but on SMP system
it hangs up and the thread can't even accept a SIGKILL.
It it stuck after the following calls happen:
sock_sendmsg()
sock->ops->sendmsg()
tcp_do_sendmsg()
then tcp_do_sendmsg() calls:
skb = sock_wmalloc(sk, tmp, 0, GFP_KERNEL);
but that call never returns. It doesn't get to
the code where the comment says: "If we didn't get
any memory, we need to sleep."
I've mucked with sock->sk->allocation flavors but to no avail.
BTW, this is 2.2.16-22 (stock red hat 6.2 kernel)
Is this fixed in later kernels, or is there some semaphore/spinlock
needed to call sock_sendmsg()/recvmsg() from kernel threads?
Is there a race with skbuff allocation/deallocation from the
NET_BH network bottom half handler or NIC interrupt handler
that I can prevent from happening somehow?
-Captain
_________________________________________________________________
Get your FREE download of MSN Explorer at http://explorer.msn.com/intl.asp
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Sun Oct 07 2001 - 21:00:24 EST