Eric Dumazet 0287587884 net: better IFF_XMIT_DST_RELEASE support ... Testing xmit_more support with netperf and connected UDP sockets, I found strange dst refcount false sharing. Current handling of IFF_XMIT_DST_RELEASE is not optimal. Dropping dst in validate_xmit_skb() is certainly too late in case packet was queued by cpu X but dequeued by cpu Y The logical point to take care of drop/force is in __dev_queue_xmit() before even taking qdisc lock. As Julian Anastasov pointed out, need for skb_dst() might come from some packet schedulers or classifiers. This patch adds new helper to cleanly express needs of various drivers or qdiscs/classifiers. Drivers that need skb_dst() in their ndo_start_xmit() should call following helper in their setup instead of the prior : dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; -> netif_keep_dst(dev); Instead of using a single bit, we use two bits, one being eventually rebuilt in bonding/team drivers. The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being rebuilt in bonding/team. Eventually, we could add something smarter later. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Julian Anastasov <ja@ssi.bg> Signed-off-by: David S. Miller <davem@davemloft.net>		2014-10-07 13:22:11 -04:00
..
addr.c
addr.h
atm_misc.c
atm_sysfs.c
br2684.c	net: set name_assign_type in alloc_netdev()	2014-07-15 16:12:48 -07:00
clip.c	net: better IFF_XMIT_DST_RELEASE support	2014-10-07 13:22:11 -04:00
common.c	atm: Convert pr_warning to pr_warn	2014-09-10 12:40:10 -07:00
common.h
ioctl.c
Kconfig
lec_arpc.h
lec.c	lec: Use rtnl lock/unlock when updating MTU	2014-08-21 16:31:23 -07:00
lec.h
Makefile
mpc.c	net: Pass a "more" indication down into netdev_start_xmit() code paths.	2014-09-01 17:39:55 -07:00
mpc.h
mpoa_caches.c
mpoa_caches.h
mpoa_proc.c
pppoatm.c	arch: Mass conversion of smp_mb__*()	2014-04-18 14:20:48 +02:00
proc.c
protocols.h
pvc.c
raw.c
resources.c
resources.h
signaling.c
signaling.h
svc.c	atm/svc: Fix blocking in wait loop	2014-08-13 20:04:46 -07:00