KVM: PPC: Book3S HV: Use new mutex to synchronize MMU setup

Currently the HV KVM code uses kvm->lock in conjunction with a flag,
kvm->arch.mmu_ready, to synchronize MMU setup and hold off vcpu
execution until the MMU-related data structures are ready.  However,
this means that kvm->lock is being taken inside vcpu->mutex, which
is contrary to Documentation/virtual/kvm/locking.txt and results in
lockdep warnings.

To fix this, we add a new mutex, kvm->arch.mmu_setup_lock, which nests
inside the vcpu mutexes, and is taken in the places where kvm->lock
was taken that are related to MMU setup.

Additionally we take the new mutex in the vcpu creation code at the
point where we are creating a new vcore, in order to provide mutual
exclusion with kvmppc_update_lpcr() and ensure that an update to
kvm->arch.lpcr doesn't get missed, which could otherwise lead to a
stale vcore->lpcr value.

Signed-off-by: Paul Mackerras <paulus@ozlabs.org>

1 files changed, 18 insertions, 18 deletions

diff --git a/arch/powerpc/kvm/book3s_64_mmu_hv.c b/arch/powerpc/kvm/book3s_64_mmu_hv.c
index ab3d484c5e2e..51971311e6c9 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_hv.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_hv.c
@@ -63,7 +63,7 @@ struct kvm_resize_hpt {
 	struct work_struct work;
 	u32 order;
 
-	/* These fields protected by kvm->lock */
+	/* These fields protected by kvm->arch.mmu_setup_lock */
 
 	/* Possible values and their usage:
 	 *  <0     an error occurred during allocation,
@@ -73,7 +73,7 @@ struct kvm_resize_hpt {
 	int error;
 
 	/* Private to the work thread, until error != -EBUSY,
-	 * then protected by kvm->lock.
+	 * then protected by kvm->arch.mmu_setup_lock.
 	 */
 	struct kvm_hpt_info hpt;
 };
@@ -139,7 +139,7 @@ long kvmppc_alloc_reset_hpt(struct kvm *kvm, int order)
 	long err = -EBUSY;
 	struct kvm_hpt_info info;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	if (kvm->arch.mmu_ready) {
 		kvm->arch.mmu_ready = 0;
 		/* order mmu_ready vs. vcpus_running */
@@ -183,7 +183,7 @@ out:
 		/* Ensure that each vcpu will flush its TLB on next entry. */
 		cpumask_setall(&kvm->arch.need_tlb_flush);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return err;
 }
 
@@ -1447,7 +1447,7 @@ static void resize_hpt_pivot(struct kvm_resize_hpt *resize)
 
 static void resize_hpt_release(struct kvm *kvm, struct kvm_resize_hpt *resize)
 {
-	if (WARN_ON(!mutex_is_locked(&kvm->lock)))
+	if (WARN_ON(!mutex_is_locked(&kvm->arch.mmu_setup_lock)))
 		return;
 
 	if (!resize)
@@ -1474,14 +1474,14 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 	if (WARN_ON(resize->error != -EBUSY))
 		return;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	/* Request is still current? */
 	if (kvm->arch.resize_hpt == resize) {
 		/* We may request large allocations here:
-		 * do not sleep with kvm->lock held for a while.
+		 * do not sleep with kvm->arch.mmu_setup_lock held for a while.
 		 */
-		mutex_unlock(&kvm->lock);
+		mutex_unlock(&kvm->arch.mmu_setup_lock);
 
 		resize_hpt_debug(resize, "resize_hpt_prepare_work(): order = %d\n",
 				 resize->order);
@@ -1494,9 +1494,9 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 		if (WARN_ON(err == -EBUSY))
 			err = -EINPROGRESS;
 
-		mutex_lock(&kvm->lock);
+		mutex_lock(&kvm->arch.mmu_setup_lock);
 		/* It is possible that kvm->arch.resize_hpt != resize
-		 * after we grab kvm->lock again.
+		 * after we grab kvm->arch.mmu_setup_lock again.
 		 */
 	}
 
@@ -1505,7 +1505,7 @@ static void resize_hpt_prepare_work(struct work_struct *work)
 	if (kvm->arch.resize_hpt != resize)
 		resize_hpt_release(kvm, resize);
 
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 }
 
 long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
@@ -1522,7 +1522,7 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 	if (shift && ((shift < 18) || (shift > 46)))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	resize = kvm->arch.resize_hpt;
 
@@ -1565,7 +1565,7 @@ long kvm_vm_ioctl_resize_hpt_prepare(struct kvm *kvm,
 	ret = 100; /* estimated time in ms */
 
 out:
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return ret;
 }
 
@@ -1588,7 +1588,7 @@ long kvm_vm_ioctl_resize_hpt_commit(struct kvm *kvm,
 	if (shift && ((shift < 18) || (shift > 46)))
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 
 	resize = kvm->arch.resize_hpt;
 
@@ -1625,7 +1625,7 @@ out:
 	smp_mb();
 out_no_hpt:
 	resize_hpt_release(kvm, resize);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 	return ret;
 }
 
@@ -1868,7 +1868,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 		return -EINVAL;
 
 	/* lock out vcpus from running while we're doing this */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->arch.mmu_setup_lock);
 	mmu_ready = kvm->arch.mmu_ready;
 	if (mmu_ready) {
 		kvm->arch.mmu_ready = 0;	/* temporarily */
@@ -1876,7 +1876,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 		smp_mb();
 		if (atomic_read(&kvm->arch.vcpus_running)) {
 			kvm->arch.mmu_ready = 1;
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->arch.mmu_setup_lock);
 			return -EBUSY;
 		}
 	}
@@ -1963,7 +1963,7 @@ static ssize_t kvm_htab_write(struct file *file, const char __user *buf,
 	/* Order HPTE updates vs. mmu_ready */
 	smp_wmb();
 	kvm->arch.mmu_ready = mmu_ready;
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->arch.mmu_setup_lock);
 
 	if (err)
 		return err;