Björn Töpel 541d7fdd76 xsk: proper AF_XDP socket teardown ordering ... The AF_XDP socket struct can exist in three different, implicit states: setup, bound and released. Setup is prior the socket has been bound to a device. Bound is when the socket is active for receive and send. Released is when the process/userspace side of the socket is released, but the sock object is still lingering, e.g. when there is a reference to the socket in an XSKMAP after process termination. The Rx fast-path code uses the "dev" member of struct xdp_sock to check whether a socket is bound or relased, and the Tx code uses the struct xdp_umem "xsk_list" member in conjunction with "dev" to determine the state of a socket. However, the transition from bound to released did not tear the socket down in correct order. On the Rx side "dev" was cleared after synchronize_net() making the synchronization useless. On the Tx side, the internal queues were destroyed prior removing them from the "xsk_list". This commit corrects the cleanup order, and by doing so xdp_del_sk_umem() can be simplified and one synchronize_net() can be removed. Fixes: 965a990984 ("xsk: add support for bind for Rx") Fixes: ac98d8aab6 ("xsk: wire upp Tx zero-copy functions") Reported-by: Jesper Dangaard Brouer <brouer@redhat.com> Signed-off-by: Björn Töpel <bjorn.topel@intel.com> Acked-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>		2018-10-08 10:09:22 +02:00
..
Kconfig	net: initial AF_XDP skeleton	2018-05-03 15:55:23 -07:00
Makefile	xsk: remove newline at end of file	2018-05-18 16:07:02 +02:00
xdp_umem.c	xsk: proper AF_XDP socket teardown ordering	2018-10-08 10:09:22 +02:00
xdp_umem.h	xsk: fix bug when trying to use both copy and zero-copy on one queue id	2018-10-05 09:31:00 +02:00
xsk_queue.c	net: xsk: add a simple buffer reuse queue	2018-09-25 13:13:15 -07:00
xsk_queue.h	net: xsk: add a simple buffer reuse queue	2018-09-25 13:13:15 -07:00
xsk.c	xsk: proper AF_XDP socket teardown ordering	2018-10-08 10:09:22 +02:00