From: Paolo Bonzini <pbonzini@redhat.com>
To: qemu-devel@nongnu.org
Cc: gleb@kernel.org, thomas knych <thomaswk@google.com>,
mtosatti@redhat.com, qemu-stable@nongnu.org
Subject: [Qemu-devel] [PULL 7/9] KVM: Retry KVM_CREATE_VM on EINTR
Date: Mon, 20 Jan 2014 15:44:09 +0100 [thread overview]
Message-ID: <1390229051-28635-8-git-send-email-pbonzini@redhat.com> (raw)
In-Reply-To: <1390229051-28635-1-git-send-email-pbonzini@redhat.com>
From: thomas knych <thomaswk@google.com>
Upstreaming this change from Android (https://android-review.googlesource.com/54211).
On heavily loaded machines with many VM instances we see KVM_CREATE_VM
failing with EINTR on this path:
kvm_dev_ioctl_create_vm -> kvm_create_vm -> kvm_init_mmu_notifier -> mmu_notifier_register -> do_mmu_notifier_register -> mm_take_all_locks
which checks if any signals have been raised while it was attaining locks
and returns EINTR. Retrying the system call greatly improves reliability.
Cc: qemu-stable@nongnu.org
Signed-off-by: thomas knych <thomaswk@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
kvm-all.c | 12 +++++++++---
1 file changed, 9 insertions(+), 3 deletions(-)
diff --git a/kvm-all.c b/kvm-all.c
index 3937754..6df2ee1 100644
--- a/kvm-all.c
+++ b/kvm-all.c
@@ -1442,16 +1442,22 @@ int kvm_init(void)
nc++;
}
- s->vmfd = kvm_ioctl(s, KVM_CREATE_VM, 0);
- if (s->vmfd < 0) {
+ do {
+ ret = kvm_ioctl(s, KVM_CREATE_VM, 0);
+ } while (ret == -EINTR);
+
+ if (ret < 0) {
+ fprintf(stderr, "ioctl(KVM_CREATE_VM) failed: %d %s\n", -s->vmfd,
+ strerror(-ret));
+
#ifdef TARGET_S390X
fprintf(stderr, "Please add the 'switch_amode' kernel parameter to "
"your host kernel command line\n");
#endif
- ret = s->vmfd;
goto err;
}
+ s->vmfd = ret;
missing_cap = kvm_check_extension_list(s, kvm_required_capabilites);
if (!missing_cap) {
missing_cap =
--
1.8.3.1
next prev parent reply other threads:[~2014-01-20 14:44 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-20 14:44 [Qemu-devel] [PULL 0/8] KVM uq/master changes for 2014-01-20 Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 1/9] target-i386: Intel MPX Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 2/9] target-i386: do not special case TSC writeback Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 3/9] target-i386: clear guest TSC on reset Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 4/9] roms: Flush icache when writing roms to guest memory Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 5/9] kvm: x86: Separately write feature control MSR on reset Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 6/9] mempath prefault: fix off-by-one error Paolo Bonzini
2014-01-20 14:44 ` Paolo Bonzini [this message]
2014-01-27 13:44 ` [Qemu-devel] [PULL 7/9] KVM: Retry KVM_CREATE_VM on EINTR Alexander Graf
2014-01-27 13:53 ` Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 8/9] KVM: fix addr type for KVM_IOEVENTFD Paolo Bonzini
2014-01-20 14:44 ` [Qemu-devel] [PULL 9/9] kvm: always update the MPX model specific register Paolo Bonzini
2014-01-22 4:48 ` Liu, Jinsong
2014-01-20 14:47 ` [Qemu-devel] [PULL 0/8] KVM uq/master changes for 2014-01-20 Paolo Bonzini
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1390229051-28635-8-git-send-email-pbonzini@redhat.com \
--to=pbonzini@redhat.com \
--cc=gleb@kernel.org \
--cc=mtosatti@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qemu-stable@nongnu.org \
--cc=thomaswk@google.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).