KVM: PPC: Book3S HV: Drop locks before reading guest memory

Running with CONFIG_DEBUG_ATOMIC_SLEEP reveals that HV KVM tries to
read guest memory, in order to emulate guest instructions, while
preempt is disabled and a vcore lock is held.  This occurs in
kvmppc_handle_exit_hv(), called from post_guest_process(), when
emulating guest doorbell instructions on POWER9 systems, and also
when checking whether we have hit a hypervisor breakpoint.
Reading guest memory can cause a page fault and thus cause the
task to sleep, so we need to avoid reading guest memory while
holding a spinlock or when preempt is disabled.

To fix this, we move the preempt_enable() in kvmppc_run_core() to
before the loop that calls post_guest_process() for each vcore that
has just run, and we drop and re-take the vcore lock around the calls
to kvmppc_emulate_debug_inst() and kvmppc_emulate_doorbell_instr().

Dropping the lock is safe with respect to the iteration over the
runnable vcpus in post_guest_process(); for_each_runnable_thread
is actually safe to use locklessly.  It is possible for a vcpu
to become runnable and add itself to the runnable_threads array
(code near the beginning of kvmppc_run_vcpu()) and then get included
in the iteration in post_guest_process despite the fact that it
has not just run.  This is benign because vcpu->arch.trap and
vcpu->arch.ceded will be zero.

Cc: stable@vger.kernel.org # v4.13+
Fixes: 579006944e0d ("KVM: PPC: Book3S HV: Virtualize doorbell facility on POWER9")
Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index e5f81fc108e094c100b3d73fc2c702603e692e47..aa6130b56b5ee300bf121c09c5ca026dcdb37aac 100644 (file)
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1008,8 +1008,6 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu)
        struct kvm *kvm = vcpu->kvm;
        struct kvm_vcpu *tvcpu;
 
-       if (!cpu_has_feature(CPU_FTR_ARCH_300))
-               return EMULATE_FAIL;
        if (kvmppc_get_last_inst(vcpu, INST_GENERIC, &inst) != EMULATE_DONE)
                return RESUME_GUEST;
        if (get_op(inst) != 31)
@@ -1059,6 +1057,7 @@ static int kvmppc_emulate_doorbell_instr(struct kvm_vcpu *vcpu)
        return RESUME_GUEST;
 }
 
+/* Called with vcpu->arch.vcore->lock held */
 static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                 struct task_struct *tsk)
 {
@@ -1179,7 +1178,10 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
                                swab32(vcpu->arch.emul_inst) :
                                vcpu->arch.emul_inst;
                if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP) {
+                       /* Need vcore unlocked to call kvmppc_get_last_inst */
+                       spin_unlock(&vcpu->arch.vcore->lock);
                        r = kvmppc_emulate_debug_inst(run, vcpu);
+                       spin_lock(&vcpu->arch.vcore->lock);
                } else {
                        kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
                        r = RESUME_GUEST;
@@ -1194,8 +1196,13 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
         */
        case BOOK3S_INTERRUPT_H_FAC_UNAVAIL:
                r = EMULATE_FAIL;
-               if ((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG)
+               if (((vcpu->arch.hfscr >> 56) == FSCR_MSGP_LG) &&
+                   cpu_has_feature(CPU_FTR_ARCH_300)) {
+                       /* Need vcore unlocked to call kvmppc_get_last_inst */
+                       spin_unlock(&vcpu->arch.vcore->lock);
                        r = kvmppc_emulate_doorbell_instr(vcpu);
+                       spin_lock(&vcpu->arch.vcore->lock);
+               }
                if (r == EMULATE_FAIL) {
                        kvmppc_core_queue_program(vcpu, SRR1_PROGILL);
                        r = RESUME_GUEST;
@@ -2946,13 +2953,14 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc)
        /* make sure updates to secondary vcpu structs are visible now */
        smp_mb();
 
+       preempt_enable();
+
        for (sub = 0; sub < core_info.n_subcores; ++sub) {
                pvc = core_info.vc[sub];
                post_guest_process(pvc, pvc == vc);
        }
 
        spin_lock(&vc->lock);
-       preempt_enable();
 
  out:
        vc->vcore_state = VCORE_INACTIVE;