KVM: VMX: Clean up PI pre/post-block WARNs

Move the WARN sanity checks out of the PI descriptor update loop so as
not to spam the kernel log if the condition is violated and the update
takes multiple attempts due to another writer.  This also eliminates a
few extra uops from the retry path.

Technically not checking every attempt could mean KVM will now fail to
WARN in a scenario that would have failed before, but any such failure
would be inherently racy as some other agent (CPU or device) would have
to concurrent modify the PI descriptor.

Add a helper to handle the actual write and more importantly to document
why the write may need to be retried.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20211208015236.1616697-4-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 4db2b14ee7c6d10168b56c14486f9fa90be16afd..88c53c521094a5d96066b6cb91d4db1627baf02e 100644 (file)
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -34,6 +34,20 @@ static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
        return &(to_vmx(vcpu)->pi_desc);
 }
 
+static int pi_try_set_control(struct pi_desc *pi_desc, u64 old, u64 new)
+{
+       /*
+        * PID.ON can be set at any time by a different vCPU or by hardware,
+        * e.g. a device.  PID.control must be written atomically, and the
+        * update must be retried with a fresh snapshot an ON change causes
+        * the cmpxchg to fail.
+        */
+       if (cmpxchg64(&pi_desc->control, old, new) != old)
+               return -EBUSY;
+
+       return 0;
+}
+
 void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 {
        struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -74,8 +88,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
 
                new.ndst = dest;
                new.sn = 0;
-       } while (cmpxchg64(&pi_desc->control, old.control,
-                          new.control) != old.control);
+       } while (pi_try_set_control(pi_desc, old.control, new.control));
 
 after_clear_sn:
 
@@ -128,17 +141,17 @@ static void __pi_post_block(struct kvm_vcpu *vcpu)
        if (!x2apic_mode)
                dest = (dest << 8) & 0xFF00;
 
+       WARN(pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR,
+            "Wakeup handler not enabled while the vCPU was blocking");
+
        do {
                old.control = new.control = READ_ONCE(pi_desc->control);
-               WARN(old.nv != POSTED_INTR_WAKEUP_VECTOR,
-                    "Wakeup handler not enabled while the VCPU is blocked\n");
 
                new.ndst = dest;
 
                /* set 'NV' to 'notification vector' */
                new.nv = POSTED_INTR_VECTOR;
-       } while (cmpxchg64(&pi_desc->control, old.control,
-                          new.control) != old.control);
+       } while (pi_try_set_control(pi_desc, old.control, new.control));
 
        vcpu->pre_pcpu = -1;
 }
@@ -173,17 +186,15 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
                      &per_cpu(blocked_vcpu_on_cpu, vcpu->cpu));
        spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->cpu));
 
+       WARN(pi_desc->sn == 1,
+            "Posted Interrupt Suppress Notification set before blocking");
+
        do {
                old.control = new.control = READ_ONCE(pi_desc->control);
 
-               WARN((pi_desc->sn == 1),
-                    "Warning: SN field of posted-interrupts "
-                    "is set before blocking\n");
-
                /* set 'NV' to 'wakeup vector' */
                new.nv = POSTED_INTR_WAKEUP_VECTOR;
-       } while (cmpxchg64(&pi_desc->control, old.control,
-                          new.control) != old.control);
+       } while (pi_try_set_control(pi_desc, old.control, new.control));
 
        /* We should not block the vCPU if an interrupt is posted for it.  */
        if (pi_test_on(pi_desc))