diff --git a/include/os/freebsd/spl/sys/atomic.h b/include/os/freebsd/spl/sys/atomic.h
index e283c6c0e..4227e5f7d 100644
--- a/include/os/freebsd/spl/sys/atomic.h
+++ b/include/os/freebsd/spl/sys/atomic.h
@@ -32,79 +32,30 @@
 #include <sys/types.h>
 #include <machine/atomic.h>
 
-#define	casptr(_a, _b, _c)	\
-	atomic_cmpset_ptr((volatile uintptr_t *)(_a), \
-	    (uintptr_t)(_b), \
-	    (uintptr_t)(_c))
-#define	cas32	atomic_cmpset_32
-#define	atomic_sub_64 atomic_subtract_64
+#define	atomic_sub_64	atomic_subtract_64
 
-#if defined(__i386__) || defined(KLD_MODULE)
+#if defined(__i386__) && (defined(_KERNEL) || defined(KLD_MODULE))
 #define	I386_HAVE_ATOMIC64
 #endif
 
+#if defined(__i386__) || defined(__amd64__) || defined(__arm__)
+/* No spurious failures from fcmpset. */
+#define	STRONG_FCMPSET
+#endif
+
 #if !defined(__LP64__) && !defined(__mips_n32) && \
-	!defined(ARM_HAVE_ATOMIC64) && !defined(I386_HAVE_ATOMIC64)
+	!defined(ARM_HAVE_ATOMIC64) && !defined(I386_HAVE_ATOMIC64) && \
+	!defined(HAS_EMULATED_ATOMIC64)
 extern void atomic_add_64(volatile uint64_t *target, int64_t delta);
 extern void atomic_dec_64(volatile uint64_t *target);
-#endif
-#ifndef __sparc64__
-#if defined(__LP64__) || defined(__mips_n32) ||	\
-    defined(ARM_HAVE_ATOMIC64) || defined(I386_HAVE_ATOMIC64)
-
-#define	membar_producer() wmb()
-
-static __inline uint64_t
-atomic_cas_64(volatile uint64_t *target, uint64_t cmp, uint64_t newval)
-{
-
-#ifdef __i386__
-	atomic_fcmpset_64(target, &cmp, newval);
-#else
-	atomic_fcmpset_long(target, &cmp, newval);
-#endif
-	return (cmp);
-}
-
-static __inline uint32_t
-atomic_cas_32(volatile uint32_t *target, uint32_t cmp, uint32_t newval)
-{
-
-	atomic_fcmpset_int(target, &cmp, newval);
-	return (cmp);
-}
-
-static __inline uint64_t
-atomic_add_64_nv(volatile uint64_t *target, int64_t delta)
-{
-	uint64_t prev;
-
-	prev = atomic_fetchadd_long(target, delta);
-
-	return (prev + delta);
-}
-
-#else
-extern uint32_t atomic_cas_32(volatile uint32_t *target, uint32_t cmp,
-    uint32_t newval);
+extern uint64_t atomic_swap_64(volatile uint64_t *a, uint64_t value);
+extern uint64_t atomic_load_64(volatile uint64_t *a);
+extern uint64_t atomic_add_64_nv(volatile uint64_t *target, int64_t delta);
 extern uint64_t atomic_cas_64(volatile uint64_t *target, uint64_t cmp,
     uint64_t newval);
-extern uint64_t atomic_add_64_nv(volatile uint64_t *target, int64_t delta);
-extern void membar_producer(void);
 #endif
-#endif
-extern uint8_t atomic_or_8_nv(volatile uint8_t *target, uint8_t value);
 
-#if defined(__sparc64__) || defined(__powerpc__) || defined(__arm__) || \
-    defined(__mips__) || defined(__aarch64__) || defined(__riscv)
-extern void atomic_or_8(volatile uint8_t *target, uint8_t value);
-#else
-static __inline void
-atomic_or_8(volatile uint8_t *target, uint8_t value)
-{
-	atomic_set_8(target, value);
-}
-#endif
+#define	membar_producer	atomic_thread_fence_rel
 
 static __inline uint32_t
 atomic_add_32_nv(volatile uint32_t *target, int32_t delta)
@@ -112,33 +63,12 @@ atomic_add_32_nv(volatile uint32_t *target, int32_t delta)
 	return (atomic_fetchadd_32(target, delta) + delta);
 }
 
-static __inline uint32_t
-atomic_add_int_nv(volatile uint32_t *target, int delta)
+static __inline uint_t
+atomic_add_int_nv(volatile uint_t *target, int delta)
 {
 	return (atomic_add_32_nv(target, delta));
 }
 
-static __inline void
-atomic_dec_32(volatile uint32_t *target)
-{
-	atomic_subtract_32(target, 1);
-}
-
-static __inline uint32_t
-atomic_dec_32_nv(volatile uint32_t *target)
-{
-	return (atomic_fetchadd_32(target, -1) - 1);
-}
-
-#if defined(__LP64__) || defined(__mips_n32) || \
-    defined(ARM_HAVE_ATOMIC64) || defined(I386_HAVE_ATOMIC64)
-static __inline void
-atomic_dec_64(volatile uint64_t *target)
-{
-	atomic_subtract_64(target, 1);
-}
-#endif
-
 static __inline void
 atomic_inc_32(volatile uint32_t *target)
 {
@@ -151,6 +81,70 @@ atomic_inc_32_nv(volatile uint32_t *target)
 	return (atomic_add_32_nv(target, 1));
 }
 
+static __inline void
+atomic_dec_32(volatile uint32_t *target)
+{
+	atomic_subtract_32(target, 1);
+}
+
+static __inline uint32_t
+atomic_dec_32_nv(volatile uint32_t *target)
+{
+	return (atomic_add_32_nv(target, -1));
+}
+
+#ifndef __sparc64__
+static inline uint32_t
+atomic_cas_32(volatile uint32_t *target, uint32_t cmp, uint32_t newval)
+{
+#ifdef STRONG_FCMPSET
+	(void) atomic_fcmpset_32(target, &cmp, newval);
+#else
+	uint32_t expected = cmp;
+
+	do {
+		if (atomic_fcmpset_32(target, &cmp, newval))
+			break;
+	} while (cmp == expected);
+#endif
+	return (cmp);
+}
+#endif
+
+#if defined(__LP64__) || defined(__mips_n32) || \
+	defined(ARM_HAVE_ATOMIC64) || defined(I386_HAVE_ATOMIC64) || \
+	defined(HAS_EMULATED_ATOMIC64)
+static __inline void
+atomic_dec_64(volatile uint64_t *target)
+{
+	atomic_subtract_64(target, 1);
+}
+
+static inline uint64_t
+atomic_add_64_nv(volatile uint64_t *target, int64_t delta)
+{
+	return (atomic_fetchadd_64(target, delta) + delta);
+}
+
+#ifndef __sparc64__
+static inline uint64_t
+atomic_cas_64(volatile uint64_t *target, uint64_t cmp, uint64_t newval)
+{
+#ifdef STRONG_FCMPSET
+	(void) atomic_fcmpset_64(target, &cmp, newval);
+#else
+	uint64_t expected = cmp;
+
+	do {
+		if (atomic_fcmpset_64(target, &cmp, newval))
+			break;
+	} while (cmp == expected);
+#endif
+	return (cmp);
+}
+#endif
+#endif
+
 static __inline void
 atomic_inc_64(volatile uint64_t *target)
 {
diff --git a/module/os/freebsd/spl/spl_atomic.c b/module/os/freebsd/spl/spl_atomic.c
index e82fed847..80040fc6a 100644
--- a/module/os/freebsd/spl/spl_atomic.c
+++ b/module/os/freebsd/spl/spl_atomic.c
@@ -32,6 +32,10 @@ __FBSDID("$FreeBSD$");
 #include <sys/mutex.h>
 #include <sys/atomic.h>
 
+#if !defined(__LP64__) && !defined(__mips_n32) && \
+	!defined(ARM_HAVE_ATOMIC64) && !defined(I386_HAVE_ATOMIC64) && \
+	!defined(HAS_EMULATED_ATOMIC64)
+
 #ifdef _KERNEL
 #include <sys/kernel.h>
 
@@ -52,8 +56,6 @@ atomic_init(void)
 }
 #endif
 
-#if !defined(__LP64__) && !defined(__mips_n32) && \
-	!defined(ARM_HAVE_ATOMIC64) && !defined(I386_HAVE_ATOMIC64)
 void
 atomic_add_64(volatile uint64_t *target, int64_t delta)
 {
@@ -71,7 +73,29 @@ atomic_dec_64(volatile uint64_t *target)
 	*target -= 1;
 	mtx_unlock(&atomic_mtx);
 }
-#endif
+
+uint64_t
+atomic_swap_64(volatile uint64_t *a, uint64_t value)
+{
+	uint64_t ret;
+
+	mtx_lock(&atomic_mtx);
+	ret = *a;
+	*a = value;
+	mtx_unlock(&atomic_mtx);
+	return (ret);
+}
+
+uint64_t
+atomic_load_64(volatile uint64_t *a)
+{
+	uint64_t ret;
+
+	mtx_lock(&atomic_mtx);
+	ret = *a;
+	mtx_unlock(&atomic_mtx);
+	return (ret);
+}
 
 uint64_t
 atomic_add_64_nv(volatile uint64_t *target, int64_t delta)
@@ -84,27 +108,6 @@ atomic_add_64_nv(volatile uint64_t *target, int64_t delta)
 	return (newval);
 }
 
-#if defined(__powerpc__) || defined(__arm__) || defined(__mips__)
-void
-atomic_or_8(volatile uint8_t *target, uint8_t value)
-{
-	mtx_lock(&atomic_mtx);
-	*target |= value;
-	mtx_unlock(&atomic_mtx);
-}
-#endif
-
-uint8_t
-atomic_or_8_nv(volatile uint8_t *target, uint8_t value)
-{
-	uint8_t newval;
-
-	mtx_lock(&atomic_mtx);
-	newval = (*target |= value);
-	mtx_unlock(&atomic_mtx);
-	return (newval);
-}
-
 uint64_t
 atomic_cas_64(volatile uint64_t *target, uint64_t cmp, uint64_t newval)
 {
@@ -117,22 +120,4 @@ atomic_cas_64(volatile uint64_t *target, uint64_t cmp, uint64_t newval)
 	mtx_unlock(&atomic_mtx);
 	return (oldval);
 }
-
-uint32_t
-atomic_cas_32(volatile uint32_t *target, uint32_t cmp, uint32_t newval)
-{
-	uint32_t oldval;
-
-	mtx_lock(&atomic_mtx);
-	oldval = *target;
-	if (oldval == cmp)
-		*target = newval;
-	mtx_unlock(&atomic_mtx);
-	return (oldval);
-}
-
-void
-membar_producer(void)
-{
-	/* nothing */
-}
+#endif