diff --git a/sys/dev/drm2/drm_atomic.h b/sys/dev/drm2/drm_atomic.h
index 0f11f0b..b901341 100644
--- a/sys/dev/drm2/drm_atomic.h
+++ b/sys/dev/drm2/drm_atomic.h
@@ -32,110 +32,51 @@
 #include <sys/cdefs.h>
 __FBSDID("$FreeBSD$");
 
-/* Many of these implementations are rather fake, but good enough. */
+typedef uint32_t	atomic_t;
+typedef uint64_t	atomic64_t;
 
-typedef u_int32_t atomic_t;
-typedef u_int64_t atomic64_t;
+#define	BITS_TO_LONGS(x)		howmany(x, sizeof(long) * NBBY)
 
-#define atomic_set(p, v)	(*(p) = (v))
-#define atomic_read(p)		(*(p))
-#define atomic_inc(p)		atomic_add_int(p, 1)
-#define atomic_dec(p)		atomic_subtract_int(p, 1)
-#define atomic_add(n, p)	atomic_add_int(p, n)
-#define atomic_sub(n, p)	atomic_subtract_int(p, n)
+#define	atomic_set(p, v)		atomic_store_rel_int(p, v)
+#define	atomic_read(p)			atomic_load_acq_int(p)
 
-static __inline atomic_t
-test_and_set_bit(int b, volatile void *p)
-{
-	long bit, val;
+#define	atomic_add(v, p)		atomic_add_int(p, v)
+#define	atomic_sub(v, p)		atomic_subtract_int(p, v)
+#define	atomic_inc(p)			atomic_add(1, p)
+#define	atomic_dec(p)			atomic_sub(1, p)
 
-	bit = 1 << b;
-	do {
-		val = *(volatile long *)p;
-	} while (atomic_cmpset_long(p, val, val | bit) == 0);
+#define	atomic_add_return(v, p)		(atomic_fetchadd_int(p, v) + (v))
+#define	atomic_sub_return(v, p)		(atomic_fetchadd_int(p, -(v)) - (v))
+#define	atomic_inc_return(p)		atomic_add_return(1, p)
+#define	atomic_dec_return(p)		atomic_sub_return(1, p)
 
-	return ((val & bit) != 0);
-}
+#define	atomic_add_and_test(v, p)	(atomic_add_return(v, p) == 0)
+#define	atomic_sub_and_test(v, p)	(atomic_sub_return(v, p) == 0)
+#define	atomic_inc_and_test(p)		(atomic_inc_return(p) == 0)
+#define	atomic_dec_and_test(p)		(atomic_dec_return(p) == 0)
 
-static __inline void
-clear_bit(int b, volatile void *p)
-{
-	atomic_clear_int(((volatile int *)p) + (b >> 5), 1 << (b & 0x1f));
-}
+#define	atomic_xchg(p, v)		atomic_swap_int(p, v)
+#define	atomic64_xchg(p, v)		atomic_swap_64(p, v)
 
-static __inline void
-set_bit(int b, volatile void *p)
-{
-	atomic_set_int(((volatile int *)p) + (b >> 5), 1 << (b & 0x1f));
-}
-
-static __inline int
-test_bit(int b, volatile void *p)
-{
-	return ((volatile int *)p)[b >> 5] & (1 << (b & 0x1f));
-}
+#define	clear_bit(b, p) \
+    atomic_clear_int((volatile u_int *)(p) + (b) / 32, 1 << (b) % 32)
+#define	set_bit(b, p) \
+    atomic_set_int((volatile u_int *)(p) + (b) / 32, 1 << (b) % 32)
+#define	test_bit(b, p) \
+    (atomic_load_acq_int((volatile u_int *)(p) + (b) / 32) & (1 << (b) % 32))
+#define	test_and_set_bit(b, p) \
+    atomic_testandset_int((volatile u_int *)(p) + (b) / 32, b)
 
 static __inline int
 find_first_zero_bit(volatile void *p, int max)
 {
-	int b;
-	volatile int *ptr = (volatile int *)p;
+	volatile int *np = p;
+	int i, n;
 
-	for (b = 0; b < max; b += 32) {
-		if (ptr[b >> 5] != ~0) {
-			for (;;) {
-				if ((ptr[b >> 5] & (1 << (b & 0x1f))) == 0)
-					return b;
-				b++;
-			}
-		}
+	for (i = 0; i < max / (NBBY * sizeof(int)); i++) {
+		n = ~np[i];
+		if (n != 0)
+			return (i * NBBY * sizeof(int) + ffs(n) - 1);
 	}
-	return max;
-}
-
-static __inline int
-atomic_xchg(volatile int *p, int new)
-{
-	int old;
-
-	do {
-		old = *p;
-	} while(!atomic_cmpset_int(p, old, new));
-
-	return (old);
-}
-
-static __inline uint64_t
-atomic64_xchg(volatile uint64_t *p, uint64_t new)
-{
-	uint64_t old;
-
-	do {
-		old = *p;
-	} while(!atomic_cmpset_64(p, old, new));
-
-	return (old);
-}
-
-static __inline int
-atomic_add_return(int i, atomic_t *p)
-{
-
-	return i + atomic_fetchadd_int(p, i);
+	return (max);
 }
-
-static __inline int
-atomic_sub_return(int i, atomic_t *p)
-{
-
-	return atomic_fetchadd_int(p, -i) - i;
-}
-
-#define	atomic_inc_return(v)		atomic_add_return(1, (v))
-#define	atomic_dec_return(v)		atomic_sub_return(1, (v))
-
-#define	atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define	atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define	atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
-#define	BITS_TO_LONGS(x) (howmany((x), NBBY * sizeof(long)))
diff --git a/sys/dev/drm2/drm_gem.c b/sys/dev/drm2/drm_gem.c
index 2ddea98..b780e50 100644
--- a/sys/dev/drm2/drm_gem.c
+++ b/sys/dev/drm2/drm_gem.c
@@ -121,7 +121,7 @@ drm_gem_private_object_init(struct drm_device *dev, struct drm_gem_object *obj,
 	obj->vm_obj = NULL;
 
 	obj->refcount = 1;
-	atomic_set(&obj->handle_count, 0);
+	atomic_store_rel_int(&obj->handle_count, 0);
 	obj->size = size;
 
 	return (0);
diff --git a/sys/dev/drm2/drm_irq.c b/sys/dev/drm2/drm_irq.c
index 0324e8c..130c20f 100644
--- a/sys/dev/drm2/drm_irq.c
+++ b/sys/dev/drm2/drm_irq.c
@@ -786,7 +786,7 @@ int drm_vblank_get(struct drm_device *dev, int crtc)
 
 	mtx_lock(&dev->vbl_lock);
 	/* Going from 0->1 means we have to enable interrupts again */
-	if (atomic_fetchadd_int(&dev->vblank_refcount[crtc], 1) == 0) {
+	if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1) {
 		mtx_lock(&dev->vblank_time_lock);
 		if (!dev->vblank_enabled[crtc]) {
 			/* Enable vblank irqs under vblank_time_lock protection.
@@ -831,7 +831,7 @@ void drm_vblank_put(struct drm_device *dev, int crtc)
 	    ("Too many drm_vblank_put for crtc %d", crtc));
 
 	/* Last user schedules interrupt disable */
-	if (atomic_fetchadd_int(&dev->vblank_refcount[crtc], -1) == 1 &&
+	if (atomic_dec_and_test(&dev->vblank_refcount[crtc]) &&
 	    (drm_vblank_offdelay > 0))
 		callout_reset(&dev->vblank_disable_callout,
 		    (drm_vblank_offdelay * DRM_HZ) / 1000,
diff --git a/sys/dev/drm2/ttm/ttm_bo.c b/sys/dev/drm2/ttm/ttm_bo.c
index 3b13540..f598748 100644
--- a/sys/dev/drm2/ttm/ttm_bo.c
+++ b/sys/dev/drm2/ttm/ttm_bo.c
@@ -1723,7 +1723,8 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 		if (driver->sync_obj_signaled(bo->sync_obj)) {
 			void *tmp_obj = bo->sync_obj;
 			bo->sync_obj = NULL;
-			clear_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
+			atomic_clear_long(&bo->priv_flags,
+					  1UL << TTM_BO_PRIV_FLAG_MOVING);
 			mtx_unlock(&bdev->fence_lock);
 			driver->sync_obj_unref(&tmp_obj);
 			mtx_lock(&bdev->fence_lock);
@@ -1746,8 +1747,8 @@ int ttm_bo_wait(struct ttm_buffer_object *bo,
 		if (likely(bo->sync_obj == sync_obj)) {
 			void *tmp_obj = bo->sync_obj;
 			bo->sync_obj = NULL;
-			clear_bit(TTM_BO_PRIV_FLAG_MOVING,
-				  &bo->priv_flags);
+			atomic_clear_long(&bo->priv_flags,
+					  1UL << TTM_BO_PRIV_FLAG_MOVING);
 			mtx_unlock(&bdev->fence_lock);
 			driver->sync_obj_unref(&sync_obj);
 			driver->sync_obj_unref(&tmp_obj);
diff --git a/sys/dev/drm2/ttm/ttm_bo_util.c b/sys/dev/drm2/ttm/ttm_bo_util.c
index bca0ad3..98d4a5f 100644
--- a/sys/dev/drm2/ttm/ttm_bo_util.c
+++ b/sys/dev/drm2/ttm/ttm_bo_util.c
@@ -638,7 +638,8 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 		 * operation has completed.
 		 */
 
-		set_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags);
+		atomic_set_long(&bo->priv_flags,
+				1UL << TTM_BO_PRIV_FLAG_MOVING);
 		mtx_unlock(&bdev->fence_lock);
 		if (tmp_obj)
 			driver->sync_obj_unref(&tmp_obj);
diff --git a/sys/dev/drm2/ttm/ttm_bo_vm.c b/sys/dev/drm2/ttm/ttm_bo_vm.c
index 6b4e86e..fdff8cb 100644
--- a/sys/dev/drm2/ttm/ttm_bo_vm.c
+++ b/sys/dev/drm2/ttm/ttm_bo_vm.c
@@ -152,7 +152,8 @@ reserve:
 	 */
 
 	mtx_lock(&bdev->fence_lock);
-	if (test_bit(TTM_BO_PRIV_FLAG_MOVING, &bo->priv_flags)) {
+	if ((atomic_load_acq_long(&bo->priv_flags) &
+	    (1UL << TTM_BO_PRIV_FLAG_MOVING)) != 0) {
 		/*
 		 * Here, the behavior differs between Linux and FreeBSD.
 		 *