linux_dsm_epyc7002/kernel/rcu
Paolo Bonzini 1123a60416 srcu: Allow use of Classic SRCU from both process and interrupt context
Linu Cherian reported a WARN in cleanup_srcu_struct() when shutting
down a guest running iperf on a VFIO assigned device.  This happens
because irqfd_wakeup() calls srcu_read_lock(&kvm->irq_srcu) in interrupt
context, while a worker thread does the same inside kvm_set_irq().  If the
interrupt happens while the worker thread is executing __srcu_read_lock(),
updates to the Classic SRCU ->lock_count[] field or the Tree SRCU
->srcu_lock_count[] field can be lost.

The docs say you are not supposed to call srcu_read_lock() and
srcu_read_unlock() from irq context, but KVM interrupt injection happens
from (host) interrupt context and it would be nice if SRCU supported the
use case.  KVM is using SRCU here not really for the "sleepable" part,
but rather due to its IPI-free fast detection of grace periods.  It is
therefore not desirable to switch back to RCU, which would effectively
revert commit 719d93cd5f ("kvm/irqchip: Speed up KVM_SET_GSI_ROUTING",
2014-01-16).

However, the docs are overly conservative.  You can have an SRCU instance
only has users in irq context, and you can mix process and irq context
as long as process context users disable interrupts.  In addition,
__srcu_read_unlock() actually uses this_cpu_dec() on both Tree SRCU and
Classic SRCU.  For those two implementations, only srcu_read_lock()
is unsafe.

When Classic SRCU's __srcu_read_unlock() was changed to use this_cpu_dec(),
in commit 5a41344a3d ("srcu: Simplify __srcu_read_unlock() via
this_cpu_dec()", 2012-11-29), __srcu_read_lock() did two increments.
Therefore it kept __this_cpu_inc(), with preempt_disable/enable in
the caller.  Tree SRCU however only does one increment, so on most
architectures it is more efficient for __srcu_read_lock() to use
this_cpu_inc(), and any performance differences appear to be down in
the noise.

Cc: stable@vger.kernel.org
Fixes: 719d93cd5f ("kvm/irqchip: Speed up KVM_SET_GSI_ROUTING")
Reported-by: Linu Cherian <linuc.decode@gmail.com>
Suggested-by: Linu Cherian <linuc.decode@gmail.com>
Cc: kvm@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
2017-06-08 08:25:19 -07:00
..
Makefile rcu: Separately compile large rcu_segcblist functions 2017-05-02 07:21:02 -07:00
rcu_segcblist.c rcu: Separately compile large rcu_segcblist functions 2017-05-02 07:21:02 -07:00
rcu_segcblist.h rcu: Open-code the rcu_cblist_n_lazy_cbs() function 2017-05-02 09:22:48 -07:00
rcu.h srcu: Merge ->srcu_state into ->srcu_gp_seq 2017-04-18 11:38:22 -07:00
rcuperf.c sched/headers: Prepare for new header dependencies before moving code to <uapi/linux/sched/types.h> 2017-03-02 08:42:27 +01:00
rcutorture.c srcu: Make rcutorture writer stalls print SRCU GP state 2017-04-26 11:23:28 -07:00
srcu.c srcu: Allow use of Classic SRCU from both process and interrupt context 2017-06-08 08:25:19 -07:00
srcutiny.c srcu: Allow use of Tiny/Tree SRCU from both process and interrupt context 2017-06-08 08:24:26 -07:00
srcutree.c srcu: Allow use of Tiny/Tree SRCU from both process and interrupt context 2017-06-08 08:24:26 -07:00
sync.c locking, rcu, cgroup: Avoid synchronize_sched() in __cgroup_procs_write() 2016-08-18 15:36:59 +02:00
tiny_plugin.h srcu: Allow SRCU to access rcu_scheduler_active 2017-04-18 11:38:18 -07:00
tiny.c rcu: Semicolon inside RCU_TRACE() for Tiny RCU 2017-04-18 11:38:17 -07:00
tree_exp.h srcu: Improve rcu_seq grace-period-counter abstraction 2017-04-18 11:38:21 -07:00
tree_plugin.h rcu: Open-code the rcu_cblist_n_lazy_cbs() function 2017-05-02 09:22:48 -07:00
tree_trace.c rcu: Open-code the rcu_cblist_n_lazy_cbs() function 2017-05-02 09:22:48 -07:00
tree.c Merge branch 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 2017-05-10 10:30:46 -07:00
tree.h srcu: Debloat the <linux/rcu_segcblist.h> header 2017-05-02 06:29:22 -07:00
update.c rcu: Make non-preemptive schedule be Tasks RCU quiescent state 2017-04-21 05:59:27 -07:00