[PATCH v2 14/30] tcg/i386: Add have_atomic16

[Richard Henderson <richard.henderson@linaro.org>]

Notice when Intel or AMD have guaranteed that vmovdqa is atomic.
The new variable will also be used in generated code.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 include/qemu/cpuid.h      | 18 ++++++++++++++++++
 tcg/i386/tcg-target.h     |  1 +
 tcg/i386/tcg-target.c.inc | 27 +++++++++++++++++++++++++++
 3 files changed, 46 insertions(+)

diff --git a/include/qemu/cpuid.h b/include/qemu/cpuid.h
index 1451e8ef2f..35325f1995 100644
--- a/include/qemu/cpuid.h
+++ b/include/qemu/cpuid.h
@@ -71,6 +71,24 @@
 #define bit_LZCNT       (1 << 5)
 #endif
 
+/*
+ * Signatures for different CPU implementations as returned from Leaf 0.
+ */
+
+#ifndef signature_INTEL_ecx
+/* "Genu" "ineI" "ntel" */
+#define signature_INTEL_ebx     0x756e6547
+#define signature_INTEL_edx     0x49656e69
+#define signature_INTEL_ecx     0x6c65746e
+#endif
+
+#ifndef signature_AMD_ecx
+/* "Auth" "enti" "cAMD" */
+#define signature_AMD_ebx       0x68747541
+#define signature_AMD_edx       0x69746e65
+#define signature_AMD_ecx       0x444d4163
+#endif
+
 static inline unsigned xgetbv_low(unsigned c)
 {
     unsigned a, d;
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index d4f2a6f8c2..0421776cb8 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -120,6 +120,7 @@ extern bool have_avx512dq;
 extern bool have_avx512vbmi2;
 extern bool have_avx512vl;
 extern bool have_movbe;
+extern bool have_atomic16;
 
 /* optional instructions */
 #define TCG_TARGET_HAS_div2_i32         1
diff --git a/tcg/i386/tcg-target.c.inc b/tcg/i386/tcg-target.c.inc
index 29dba3fa1c..977650263b 100644
--- a/tcg/i386/tcg-target.c.inc
+++ b/tcg/i386/tcg-target.c.inc
@@ -185,6 +185,7 @@ bool have_avx512dq;
 bool have_avx512vbmi2;
 bool have_avx512vl;
 bool have_movbe;
+bool have_atomic16;
 
 #ifdef CONFIG_CPUID_H
 static bool have_bmi2;
@@ -4173,6 +4174,32 @@ static void tcg_target_init(TCGContext *s)
                     have_avx512dq = (b7 & bit_AVX512DQ) != 0;
                     have_avx512vbmi2 = (c7 & bit_AVX512VBMI2) != 0;
                 }
+
+                /*
+                 * The Intel SDM has added:
+                 *   Processors that enumerate support for Intel® AVX
+                 *   (by setting the feature flag CPUID.01H:ECX.AVX[bit 28])
+                 *   guarantee that the 16-byte memory operations performed
+                 *   by the following instructions will always be carried
+                 *   out atomically:
+                 *   - MOVAPD, MOVAPS, and MOVDQA.
+                 *   - VMOVAPD, VMOVAPS, and VMOVDQA when encoded with VEX.128.
+                 *   - VMOVAPD, VMOVAPS, VMOVDQA32, and VMOVDQA64 when encoded
+                 *     with EVEX.128 and k0 (masking disabled).
+                 * Note that these instructions require the linear addresses
+                 * of their memory operands to be 16-byte aligned.
+                 *
+                 * AMD has provided an even stronger guarantee that processors
+                 * with AVX provide 16-byte atomicity for all cachable,
+                 * naturally aligned single loads and stores, e.g. MOVDQU.
+                 *
+                 * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104688
+                 */
+                if (have_avx1) {
+                    __cpuid(0, a, b, c, d);
+                    have_atomic16 = (c == signature_INTEL_ecx ||
+                                     c == signature_AMD_ecx);
+                }
             }
         }
     }
-- 
2.34.1