qemu/atomic128: Add x86_64 atomic128-ldst.h

With CPUINFO_ATOMIC_VMOVDQA, we can perform proper atomic
load/store without cmpxchg16b.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 68 insertions, 0 deletions

diff --git a/host/include/x86_64/host/atomic128-ldst.h b/host/include/x86_64/host/atomic128-ldst.h
new file mode 100644
index 0000000..adc9332
--- /dev/null
+++ b/host/include/x86_64/host/atomic128-ldst.h
@@ -0,0 +1,68 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0-or-later
+ * Load/store for 128-bit atomic operations, x86_64 version.
+ *
+ * Copyright (C) 2023 Linaro, Ltd.
+ *
+ * See docs/devel/atomics.rst for discussion about the guarantees each
+ * atomic primitive is meant to provide.
+ */
+
+#ifndef AARCH64_ATOMIC128_LDST_H
+#define AARCH64_ATOMIC128_LDST_H
+
+#ifdef CONFIG_INT128_TYPE
+#include "host/cpuinfo.h"
+#include "tcg/debug-assert.h"
+
+/*
+ * Through clang 16, with -mcx16, __atomic_load_n is incorrectly
+ * expanded to a read-write operation: lock cmpxchg16b.
+ */
+
+#define HAVE_ATOMIC128_RO  likely(cpuinfo & CPUINFO_ATOMIC_VMOVDQA)
+#define HAVE_ATOMIC128_RW  1
+
+static inline Int128 atomic16_read_ro(const Int128 *ptr)
+{
+    Int128Alias r;
+
+    tcg_debug_assert(HAVE_ATOMIC128_RO);
+    asm("vmovdqa %1, %0" : "=x" (r.i) : "m" (*ptr));
+
+    return r.s;
+}
+
+static inline Int128 atomic16_read_rw(Int128 *ptr)
+{
+    __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16);
+    Int128Alias r;
+
+    if (HAVE_ATOMIC128_RO) {
+        asm("vmovdqa %1, %0" : "=x" (r.i) : "m" (*ptr_align));
+    } else {
+        r.i = __sync_val_compare_and_swap_16(ptr_align, 0, 0);
+    }
+    return r.s;
+}
+
+static inline void atomic16_set(Int128 *ptr, Int128 val)
+{
+    __int128_t *ptr_align = __builtin_assume_aligned(ptr, 16);
+    Int128Alias new = { .s = val };
+
+    if (HAVE_ATOMIC128_RO) {
+        asm("vmovdqa %1, %0" : "=m"(*ptr_align) : "x" (new.i));
+    } else {
+        __int128_t old;
+        do {
+            old = *ptr_align;
+        } while (!__sync_bool_compare_and_swap_16(ptr_align, old, new.i));
+    }
+}
+#else
+/* Provide QEMU_ERROR stubs. */
+#include "host/include/generic/host/atomic128-ldst.h"
+#endif
+
+#endif /* AARCH64_ATOMIC128_LDST_H */