mirror of
https://github.com/torvalds/linux.git
synced 2024-11-01 17:51:43 +00:00
1ba42da479
In the very first implementation of HT, the driver was responsible for the queueing: stopping and waking the queues while the HW queues where being drained. In this implementation, we had to deal with the case where we were draining the AGG queue because we wanted to tear down the BA agreement. In the normal flow (when we don't drain any HW queue), when packets are reclaimed, we wake the SW queue in case the SW queue was stopped which can happen when the HW queues are too full. While draining a HW queue, we must make sure that we don't wake the SW queue, since the whole point of the draining is to empty totally the HW queue and not only get below a certain threshold. This is why there is condition in the reclaim function: if (NOT EMPTYING DELBA) wake the SW queue is applicable Since then, a lot has changed and mac80211 is now able to buffer packets that are being sent to a packet list that will be spliced after the driver has reported it has drained its HW queues. Hence, there is no need for the for aforementioned if, and we can safely wake up the queue even if we are draining HW queues. Removing this if, also allows us to remove the wake_queue in check_empty that was there in order to deal with a corner case created by the if. Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com> Signed-off-by: Wey-Yi Guy <wey-yi.w.guy@intel.com> |
||
---|---|---|
.. | ||
appletalk | ||
arcnet | ||
bonding | ||
caif | ||
can | ||
cris | ||
ethernet | ||
fddi | ||
hamradio | ||
hippi | ||
irda | ||
phy | ||
plip | ||
ppp | ||
slip | ||
tokenring | ||
usb | ||
vmxnet3 | ||
wan | ||
wimax | ||
wireless | ||
xen-netback | ||
dummy.c | ||
eql.c | ||
ifb.c | ||
Kconfig | ||
LICENSE.SRC | ||
loopback.c | ||
macvlan.c | ||
macvtap.c | ||
Makefile | ||
mdio.c | ||
mii.c | ||
netconsole.c | ||
rionet.c | ||
sb1000.c | ||
Space.c | ||
sungem_phy.c | ||
tun.c | ||
veth.c | ||
virtio_net.c | ||
xen-netfront.c |