Hi KVM guys,
I've had a bit of challenges figuring out the exact functinality and
synchronization of vcpu->requests and friends. In lack of a better
method, I wrote some comments as a patch.
I think this code really deserves some explaining, as it is really hard
to understand otherwise. Unfortunately, I wasn't able to write down
concise and exact comments, but I hope someone else feels up to the
challenge.
Let me know if I just got this completely wrong and upside down.
Thanks,
Christoffer
---
include/linux/kvm_host.h | 4 ++++
virt/kvm/kvm_main.c | 29 +++++++++++++++++++++++++++--
2 files changed, 31 insertions(+), 2 deletions(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index cbe0d68..25deef8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -252,6 +252,10 @@ struct kvm_vcpu {
struct kvm_vcpu_arch arch;
};
+/*
+ * XXX: Could we explain what we're trying to achieve? Is this an
+ * optimization as to not send multiple IPIs?
+ */
static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
{
return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index e45c20c..ccc292d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -165,7 +165,18 @@ static void ack_flush(void *_completed)
{
}
-static bool make_all_cpus_request(struct kvm *kvm, unsigned int req)
+/**
+ * make_all_cpus_request - place request on vcpus
+ * @kvm: KVM Struct
+ * @req: Request to make on the VCPU
+ *
+ * This function places a request on a VCPU and ensures that the VCPU request
+ * is handled before returning from the function, if the VCPU is in guest
+ * mode (or exiting, or reading shadow page tables?).
+ *
+ * Returns true if at least of the vcpus were sent an IPI and responded to it,
+ */
+static bool make_all_vcpus_request(struct kvm *kvm, unsigned int req)
{
int i, cpu, me;
cpumask_var_t cpus;
@@ -179,9 +190,19 @@ static bool make_all_cpus_request(struct kvm *kvm,
unsigned int req)
kvm_make_request(req, vcpu);
cpu = vcpu->cpu;
+ /*
+ * Is the following really true? Can we have an example of the
+ * race that would otherwise happen? Doesn't the make_request
+ * pair against the IPI and interrupt disabling, not the mode?
+ */
/* Set ->requests bit before we read ->mode */
smp_mb();
+ /*
+ * Set the bit on the CPU mask for all CPUs which are somehow
+ * running a guest (IN_GUEST_MODE, EXITING_GUEST_MODE, and
+ * READING_SHADOW_PAGE_TABLES).
+ */
if (cpus != NULL && cpu != -1 && cpu != me &&
kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE)
cpumask_set_cpu(cpu, cpus);
@@ -201,9 +222,13 @@ void kvm_flush_remote_tlbs(struct kvm *kvm)
{
long dirty_count = kvm->tlbs_dirty;
- smp_mb();
+ smp_mb(); /* TODO: Someone should explain this! */
if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH))
++kvm->stat.remote_tlb_flush;
+ /*
+ * TODO: Someone should explain this, why is it a cmpxchg, what
+ * happens if the dirty is different from dirty_count?
+ */
cmpxchg(&kvm->tlbs_dirty, dirty_count, 0);
}
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
