Age | Commit message (Collapse) | Author | Files | Lines |
|
|
|
Currently the vfio msi interrupt is kept as IRQ thread, this is not good
for NFV scenerio because in NFV scenerio, we want to inject the interrupt
to the guest asap. A threaded IRQ introduces schedule latency.
However, this change is like a quick and dirty and may bring
potential deadlock, because the spinlock_irqsave() from eventfd_signal()
is preemptible in RT kernel, which should not be held on IRQ context. But
changing it to be raw_spinlock is bad because it will increase the latency
a lot if the eventfd is accessed by user space.
The deadlock should be ok since for vfio MSI handler is purely kernel story
and the lock is a per-eventfd lock and seems no one else is using it for the
vfio msi scenario.
Upstream status: discussion https://lkml.org/lkml/2015/10/26/764
Change-Id: Ie4405a5b568aa75ca8c3481eeeea228a486b9794
|
|
This is a backporting from upstream linux, please refer to
http://marc.info/?t=142904577100001&r=1&w=2 for more information, the
corresponding kernel commit is 0ff53d09642204c64842 (tick: sched: Force
tick interrupt and get rid of softirq magic).
The purpose of this patch is, if a tick_sched interrupt is missed, don't
try to raise softirq, instead, we can simply trigger the timer interrupt.
The reason is, softirq requires context switch and has much higher overhead
than interrupt.
Upstream status: backport 0ff53d09642204c64842
Change-Id: I70131fb85189d15972fcaa1a2a2fa190270787f9
Back-port-by: Yunhong Jiang <yunhong.jiang@linux.intel.com>
|
|
Change-Id: I3e91161abafc62554e793e4851df639c099421e7
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
|
|
Change-Id: Icd51e1625a57867b2f79cb2b2d1ab21b23bd80e0
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
|
|
|
|
Kernel config is important for RT linux. A specific config
file is provided for the opnfv project to build the
reference config options.
Currently this config file is assumed to be used for
both host and guest kernel. We may split them in future.
Change-Id: Ia9ebe0bc002518bb603af8901c6f31531d2f0cee
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
|
|
recently announced rt patch patch-4.1.10-rt10.patch. No further changes
needed.
Change-Id: I9a0cf084498133b10771e744b6da4b29dff706ba
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
|
|
These changes brings a vanilla kernel from kernel.org, and the patch
applied for rt is patch-4.1.7-rt8.patch. No further changes needed.
Change-Id: Id8dd03c2ddd971e4d1d69b905f3069737053b700
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
|
|
Import the rt linux 4.1.3-rt3 as OPNFV kvm base.
It's from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-rt-devel.git linux-4.1.y-rt and
the base is:
commit 0917f823c59692d751951bf5ea699a2d1e2f26a2
Author: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Sat Jul 25 12:13:34 2015 +0200
Prepare v4.1.3-rt3
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
We lose all the git history this way and it's not good. We
should apply another opnfv project repo in future.
Change-Id: I87543d81c9df70d99c5001fbdf646b202c19f423
Signed-off-by: Yunhong Jiang <yunhong.jiang@intel.com>
|