KVM: VMX: switch blocked_vcpu_on_cpu_lock to raw spinlock

blocked_vcpu_on_cpu_lock is taken from hard interrupt context
(pi_wakeup_handler), therefore it cannot sleep.

Switch it to a raw spinlock.

Fixes:

[41297.066254] BUG: scheduling while atomic: CPU 0/KVM/635218/0x00010001
[41297.066323] Preemption disabled at:
[41297.066324] [<ffffffff902ee47f>] irq_enter_rcu+0xf/0x60
[41297.066339] Call Trace:
[41297.066342]  <IRQ>
[41297.066346]  dump_stack_lvl+0x34/0x44
[41297.066353]  ? irq_enter_rcu+0xf/0x60
[41297.066356]  __schedule_bug.cold+0x7d/0x8b
[41297.066361]  __schedule+0x439/0x5b0
[41297.066365]  ? task_blocks_on_rt_mutex.constprop.0.isra.0+0x1b0/0x440
[41297.066369]  schedule_rtlock+0x1e/0x40
[41297.066371]  rtlock_slowlock_locked+0xf1/0x260
[41297.066374]  rt_spin_lock+0x3b/0x60
[41297.066378]  pi_wakeup_handler+0x31/0x90 [kvm_intel]
[41297.066388]  sysvec_kvm_posted_intr_wakeup_ipi+0x9d/0xd0
[41297.066392]  </IRQ>
[41297.066392]  asm_sysvec_kvm_posted_intr_wakeup_ipi+0x12/0x20
...

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Cc: stable@vger.kernel.org
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 1c94783b5a54c5520466bb8b3753c89cfa1d5850..21ea58d25771f6e35646edd7cf3549c6cb204646 100644 (file)
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -15,7 +15,7 @@
  * can find which vCPU should be waken up.
  */
 static DEFINE_PER_CPU(struct list_head, blocked_vcpu_on_cpu);
-static DEFINE_PER_CPU(spinlock_t, blocked_vcpu_on_cpu_lock);
+static DEFINE_PER_CPU(raw_spinlock_t, blocked_vcpu_on_cpu_lock);
 
 static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
 {
@@ -121,9 +121,9 @@ static void __pi_post_block(struct kvm_vcpu *vcpu)
                           new.control) != old.control);
 
        if (!WARN_ON_ONCE(vcpu->pre_pcpu == -1)) {
-               spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+               raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
                list_del(&vcpu->blocked_vcpu_list);
-               spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+               raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
                vcpu->pre_pcpu = -1;
        }
 }
@@ -154,11 +154,11 @@ int pi_pre_block(struct kvm_vcpu *vcpu)
        local_irq_disable();
        if (!WARN_ON_ONCE(vcpu->pre_pcpu != -1)) {
                vcpu->pre_pcpu = vcpu->cpu;
-               spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+               raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
                list_add_tail(&vcpu->blocked_vcpu_list,
                              &per_cpu(blocked_vcpu_on_cpu,
                                       vcpu->pre_pcpu));
-               spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
+               raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, vcpu->pre_pcpu));
        }
 
        do {
@@ -215,7 +215,7 @@ void pi_wakeup_handler(void)
        struct kvm_vcpu *vcpu;
        int cpu = smp_processor_id();
 
-       spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+       raw_spin_lock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
        list_for_each_entry(vcpu, &per_cpu(blocked_vcpu_on_cpu, cpu),
                        blocked_vcpu_list) {
                struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -223,13 +223,13 @@ void pi_wakeup_handler(void)
                if (pi_test_on(pi_desc) == 1)
                        kvm_vcpu_kick(vcpu);
        }
-       spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+       raw_spin_unlock(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
 }
 
 void __init pi_init_cpu(int cpu)
 {
        INIT_LIST_HEAD(&per_cpu(blocked_vcpu_on_cpu, cpu));
-       spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
+       raw_spin_lock_init(&per_cpu(blocked_vcpu_on_cpu_lock, cpu));
 }
 
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)