Sign Up
Log In
Log In
or
Sign Up
Places
All Projects
Status Monitor
Collapse sidebar
openSUSE:Step:FrontRunner
xen.23271
5fc4ee23-evtchn-FIFO-queue-locking.patch
Overview
Repositories
Revisions
Requests
Users
Attributes
Meta
File 5fc4ee23-evtchn-FIFO-queue-locking.patch of Package xen.23271
# Commit 71ac522909e9302350a88bc378be99affa87067c # Date 2020-11-30 14:05:39 +0100 # Author Juergen Gross <jgross@suse.com> # Committer Jan Beulich <jbeulich@suse.com> xen/events: rework fifo queue locking Two cpus entering evtchn_fifo_set_pending() for the same event channel can race in case the first one gets interrupted after setting EVTCHN_FIFO_PENDING and when the other one manages to set EVTCHN_FIFO_LINKED before the first one is testing that bit. This can lead to evtchn_check_pollers() being called before the event is put properly into the queue, resulting eventually in the guest not seeing the event pending and thus blocking forever afterwards. Note that commit 5f2df45ead7c1195 ("xen/evtchn: rework per event channel lock") made the race just more obvious, while the fifo event channel implementation had this race forever since the introduction and use of per-channel locks, when an unmask operation was running in parallel with an event channel send operation. Using a spinlock for the per event channel lock had turned out problematic due to some paths needing to take the lock are called with interrupts off, so the lock would need to disable interrupts, which in turn broke some use cases related to vm events. For avoiding this race the queue locking in evtchn_fifo_set_pending() needs to be reworked to cover the test of EVTCHN_FIFO_PENDING, EVTCHN_FIFO_MASKED and EVTCHN_FIFO_LINKED, too. Additionally when an event channel needs to change queues both queues need to be locked initially, in order to avoid having a window with no lock held at all. Reported-by: Jan Beulich <jbeulich@suse.com> Fixes: 5f2df45ead7c1195 ("xen/evtchn: rework per event channel lock") Fixes: de6acb78bf0e137c ("evtchn: use a per-event channel lock for sending events") Signed-off-by: Juergen Gross <jgross@suse.com> Reviewed-by: Jan Beulich <jbeulich@suse.com> --- a/xen/common/event_fifo.c +++ b/xen/common/event_fifo.c @@ -66,38 +66,6 @@ static void evtchn_fifo_init(struct doma d->domain_id, evtchn->port); } -static struct evtchn_fifo_queue *lock_old_queue(const struct domain *d, - struct evtchn *evtchn, - unsigned long *flags) -{ - struct vcpu *v; - struct evtchn_fifo_queue *q, *old_q; - unsigned int try; - union evtchn_fifo_lastq lastq; - - for ( try = 0; try < 3; try++ ) - { - lastq.raw = read_atomic(&evtchn->fifo_lastq); - v = d->vcpu[lastq.last_vcpu_id]; - old_q = &v->evtchn_fifo->queue[lastq.last_priority]; - - spin_lock_irqsave(&old_q->lock, *flags); - - v = d->vcpu[lastq.last_vcpu_id]; - q = &v->evtchn_fifo->queue[lastq.last_priority]; - - if ( old_q == q ) - return old_q; - - spin_unlock_irqrestore(&old_q->lock, *flags); - } - - gprintk(XENLOG_WARNING, - "dom%d port %d lost event (too many queue changes)\n", - d->domain_id, evtchn->port); - return NULL; -} - static int try_set_link(event_word_t *word, event_word_t *w, uint32_t link) { event_word_t new, old; @@ -169,6 +137,9 @@ static void evtchn_fifo_set_pending(stru event_word_t *word; unsigned long flags; bool_t was_pending; + struct evtchn_fifo_queue *q, *old_q; + unsigned int try; + bool linked = true; port = evtchn->port; word = evtchn_fifo_word_from_port(d, port); @@ -183,17 +154,67 @@ static void evtchn_fifo_set_pending(stru return; } + /* + * Lock all queues related to the event channel (in case of a queue change + * this might be two). + * It is mandatory to do that before setting and testing the PENDING bit + * and to hold the current queue lock until the event has been put into the + * list of pending events in order to avoid waking up a guest without the + * event being visibly pending in the guest. + */ + for ( try = 0; try < 3; try++ ) + { + union evtchn_fifo_lastq lastq; + const struct vcpu *old_v; + + lastq.raw = read_atomic(&evtchn->fifo_lastq); + old_v = d->vcpu[lastq.last_vcpu_id]; + + q = &v->evtchn_fifo->queue[evtchn->priority]; + old_q = &old_v->evtchn_fifo->queue[lastq.last_priority]; + + if ( q == old_q ) + spin_lock_irqsave(&q->lock, flags); + else if ( q < old_q ) + { + spin_lock_irqsave(&q->lock, flags); + spin_lock(&old_q->lock); + } + else + { + spin_lock_irqsave(&old_q->lock, flags); + spin_lock(&q->lock); + } + + lastq.raw = read_atomic(&evtchn->fifo_lastq); + old_v = d->vcpu[lastq.last_vcpu_id]; + if ( q == &v->evtchn_fifo->queue[evtchn->priority] && + old_q == &old_v->evtchn_fifo->queue[lastq.last_priority] ) + break; + + if ( q != old_q ) + spin_unlock(&old_q->lock); + spin_unlock_irqrestore(&q->lock, flags); + } + was_pending = guest_test_and_set_bit(d, EVTCHN_FIFO_PENDING, word); + /* If we didn't get the lock bail out. */ + if ( try == 3 ) + { + gprintk(XENLOG_WARNING, + "%pd port %u lost event (too many queue changes)\n", + d, evtchn->port); + goto done; + } + /* * Link the event if it unmasked and not already linked. */ if ( !guest_test_bit(d, EVTCHN_FIFO_MASKED, word) && !guest_test_bit(d, EVTCHN_FIFO_LINKED, word) ) { - struct evtchn_fifo_queue *q, *old_q; event_word_t *tail_word; - bool_t linked = 0; /* * Control block not mapped. The guest must not unmask an @@ -204,25 +225,11 @@ static void evtchn_fifo_set_pending(stru { printk(XENLOG_G_WARNING "%pv has no FIFO event channel control block\n", v); - goto done; + goto unlock; } - /* - * No locking around getting the queue. This may race with - * changing the priority but we are allowed to signal the - * event once on the old priority. - */ - q = &v->evtchn_fifo->queue[evtchn->priority]; - - old_q = lock_old_queue(d, evtchn, &flags); - if ( !old_q ) - goto done; - if ( guest_test_and_set_bit(d, EVTCHN_FIFO_LINKED, word) ) - { - spin_unlock_irqrestore(&old_q->lock, flags); - goto done; - } + goto unlock; /* * If this event was a tail, the old queue is now empty and @@ -241,8 +248,8 @@ static void evtchn_fifo_set_pending(stru lastq.last_priority = q->priority; write_atomic(&evtchn->fifo_lastq, lastq.raw); - spin_unlock_irqrestore(&old_q->lock, flags); - spin_lock_irqsave(&q->lock, flags); + spin_unlock(&old_q->lock); + old_q = q; } /* @@ -255,6 +262,7 @@ static void evtchn_fifo_set_pending(stru * If the queue is empty (i.e., we haven't linked to the new * event), head must be updated. */ + linked = false; if ( q->tail ) { tail_word = evtchn_fifo_word_from_port(d, q->tail); @@ -263,15 +271,19 @@ static void evtchn_fifo_set_pending(stru if ( !linked ) write_atomic(q->head, port); q->tail = port; + } - spin_unlock_irqrestore(&q->lock, flags); + unlock: + if ( q != old_q ) + spin_unlock(&old_q->lock); + spin_unlock_irqrestore(&q->lock, flags); - if ( !linked - && !guest_test_and_set_bit(d, q->priority, - &v->evtchn_fifo->control_block->ready) ) - vcpu_mark_events_pending(v); - } done: + if ( !linked && + !guest_test_and_set_bit(d, q->priority, + &v->evtchn_fifo->control_block->ready) ) + vcpu_mark_events_pending(v); + if ( !was_pending ) evtchn_check_pollers(d, port); }
Locations
Projects
Search
Status Monitor
Help
OpenBuildService.org
Documentation
API Documentation
Code of Conduct
Contact
Support
@OBShq
Terms
openSUSE Build Service is sponsored by
The Open Build Service is an
openSUSE project
.
Sign Up
Log In
Places
Places
All Projects
Status Monitor
