Isn't this fixed by commit 5710a3e09f9?
commit 5710a3e09f9b85801e5ce70797a4a511e5fc9e2c
Author: Paolo Bonzini <[email protected]>
Date: Tue Apr 7 10:07:46 2020 -0400
async: use explicit memory barriers
When using C11 atomics, non-seqcst reads and writes do not participate
in the total order of seqcst operations. In util/async.c and
util/aio-posix.c,
in particular, the pattern that we use
write ctx->notify_me write bh->scheduled
read bh->scheduled read ctx->notify_me
if !bh->scheduled, sleep if ctx->notify_me, notify
needs to use seqcst operations for both the write and the read. In
general this is something that we do not want, because there can be
many sources that are polled in addition to bottom halves. The
alternative is to place a seqcst memory barrier between the write
and the read. This also comes with a disadvantage, in that the
memory barrier is implicit on strongly-ordered architectures and
it wastes a few dozen clock cycles.
Fortunately, ctx->notify_me is never written concurrently by two
threads, so we can assert that and relax the writes to ctx->notify_me.
The resulting solution works and performs well on both aarch64 and x86.
Note that the atomic_set/atomic_read combination is not an atomic
read-modify-write, and therefore it is even weaker than C11 ATOMIC_RELAXED;
on x86, ATOMIC_RELAXED compiles to a locked operation.
--
You received this bug notification because you are a member of Ubuntu
Bugs, which is subscribed to Ubuntu.
https://bugs.launchpad.net/bugs/1805256
Title:
qemu-img hangs on rcu_call_ready_event logic in Aarch64 when
converting images
To manage notifications about this bug go to:
https://bugs.launchpad.net/kunpeng920/+bug/1805256/+subscriptions
--
ubuntu-bugs mailing list
[email protected]
https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
