mmu_notifier_invalidate_range_start() may be invoked via
mmu_notifier_invalidate_range_start_nonblock(), e.g. from oom_reaper(),
where sleeping is explicitly forbidden.

KVM's mmu_notifier invalidate_range_start currently takes
mn_invalidate_lock using spin_lock(). On PREEMPT_RT, spin_lock() maps
to rt_mutex and may sleep, triggering:

  BUG: sleeping function called from invalid context

This violates the MMU notifier contract regardless of PREEMPT_RT; RT
kernels merely make the issue deterministic.

Fix by converting mn_invalidate_lock to a raw spinlock so that
invalidate_range_start() remains non-sleeping while preserving the
existing serialization between invalidate_range_start() and
invalidate_range_end().

Signed-off-by: shaikh.kamal <shaikhkamal2012@gmail.com>
---
 include/linux/kvm_host.h |  2 +-
 virt/kvm/kvm_main.c      | 18 +++++++++---------
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d93f75b05ae2..77a6d4833eda 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -797,7 +797,7 @@ struct kvm {
 	atomic_t nr_memslots_dirty_logging;
 
 	/* Used to wait for completion of MMU notifiers.  */
-	spinlock_t mn_invalidate_lock;
+	raw_spinlock_t mn_invalidate_lock;
 	unsigned long mn_active_invalidate_count;
 	struct rcuwait mn_memslots_update_rcuwait;
 
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 5fcd401a5897..7a9c33f01a37 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -747,9 +747,9 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 *
 	 * Pairs with the decrement in range_end().
 	 */
-	spin_lock(&kvm->mn_invalidate_lock);
+	raw_spin_lock(&kvm->mn_invalidate_lock);
 	kvm->mn_active_invalidate_count++;
-	spin_unlock(&kvm->mn_invalidate_lock);
+	raw_spin_unlock(&kvm->mn_invalidate_lock);
 
 	/*
 	 * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e.
@@ -817,11 +817,11 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	kvm_handle_hva_range(kvm, &hva_range);
 
 	/* Pairs with the increment in range_start(). */
-	spin_lock(&kvm->mn_invalidate_lock);
+	raw_spin_lock(&kvm->mn_invalidate_lock);
 	if (!WARN_ON_ONCE(!kvm->mn_active_invalidate_count))
 		--kvm->mn_active_invalidate_count;
 	wake = !kvm->mn_active_invalidate_count;
-	spin_unlock(&kvm->mn_invalidate_lock);
+	raw_spin_unlock(&kvm->mn_invalidate_lock);
 
 	/*
 	 * There can only be one waiter, since the wait happens under
@@ -1129,7 +1129,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
 	mutex_init(&kvm->slots_arch_lock);
-	spin_lock_init(&kvm->mn_invalidate_lock);
+	raw_spin_lock_init(&kvm->mn_invalidate_lock);
 	rcuwait_init(&kvm->mn_memslots_update_rcuwait);
 	xa_init(&kvm->vcpu_array);
 #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
@@ -1635,17 +1635,17 @@ static void kvm_swap_active_memslots(struct kvm *kvm, int as_id)
 	 * progress, otherwise the locking in invalidate_range_start and
 	 * invalidate_range_end will be unbalanced.
 	 */
-	spin_lock(&kvm->mn_invalidate_lock);
+	raw_spin_lock(&kvm->mn_invalidate_lock);
 	prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait);
 	while (kvm->mn_active_invalidate_count) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
-		spin_unlock(&kvm->mn_invalidate_lock);
+		raw_spin_unlock(&kvm->mn_invalidate_lock);
 		schedule();
-		spin_lock(&kvm->mn_invalidate_lock);
+		raw_spin_lock(&kvm->mn_invalidate_lock);
 	}
 	finish_rcuwait(&kvm->mn_memslots_update_rcuwait);
 	rcu_assign_pointer(kvm->memslots[as_id], slots);
-	spin_unlock(&kvm->mn_invalidate_lock);
+	raw_spin_unlock(&kvm->mn_invalidate_lock);
 
 	/*
 	 * Acquired in kvm_set_memslot. Must be released before synchronize
-- 
2.43.0