Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging

* target/i386: new decoder bugfix
* target/i386: complete x86-v3 support for TCG

# -----BEGIN PGP SIGNATURE-----
#
# iQFHBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmNTlqQUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroOQNQf430MHbrtN9WKKiXv3684XxmcnoRqg
# PHmaGg2SKp7UB+hI2FMYgCZWOl5s3cGTHtwX8byFCttmE4kI7HJR7IouW6znm57j
# 7QVx2TJXIZgqSYcfYzfLu46yS6pNqJUA+mBv5In3Vqt4ZQT2szefVBg6BzmuF6lT
# HXbu/llc3iVfW4SNLJOABXzKNbPacmmpmLjoporfwOHwHjv4iikuXNUOZ84FFL11
# 2tkdcff282q00IRgHm1lSyiRiqh+kAxzSDanMjOZbphBiE9gNJjLGoV5F2X63e1O
# DQGg4wqBWP68O/r8Fj8tOUMCTW212DwWyv1+d/lQB+wwpJK+P4O14dCW
# =Fd+y
# -----END PGP SIGNATURE-----
# gpg: Signature made Sat 22 Oct 2022 03:07:16 EDT
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* tag 'for-upstream' of https://gitlab.com/bonzini/qemu:
  target/i386: implement FMA instructions
  target/i386: implement F16C instructions
  target/i386: introduce function to set rounding mode from FPCW or MXCSR bits
  target/i386: decode-new: avoid out-of-bounds access to xmm_regs[-1]

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

2 files changed, 23 insertions, 2 deletions

diff --git a/tests/tcg/i386/test-avx.c b/tests/tcg/i386/test-avx.c
index 953e290..c39c0e5 100644
--- a/tests/tcg/i386/test-avx.c
+++ b/tests/tcg/i386/test-avx.c
@@ -28,6 +28,7 @@ typedef struct {
 } TestDef;
 
 reg_state initI;
+reg_state initF16;
 reg_state initF32;
 reg_state initF64;
 
@@ -221,6 +222,7 @@ static void run_all(void)
 
 #define ARRAY_LEN(x) (sizeof(x) / sizeof(x[0]))
 
+uint16_t val_f16[] = { 0x4000, 0xbc00, 0x44cd, 0x3a66, 0x4200, 0x7a1a, 0x4780, 0x4826 };
 float val_f32[] = {2.0, -1.0, 4.8, 0.8, 3, -42.0, 5e6, 7.5, 8.3};
 double val_f64[] = {2.0, -1.0, 4.8, 0.8, 3, -42.0, 5e6, 7.5};
 v4di val_i64[] = {
@@ -241,6 +243,12 @@ v4di indexd = {0x00000002000000efull, 0xfffffff500000010ull,
 
 v4di gather_mem[0x20];
 
+void init_f16reg(v4di *r)
+{
+    memset(r, 0, sizeof(*r));
+    memcpy(r, val_f16, sizeof(val_f16));
+}
+
 void init_f32reg(v4di *r)
 {
     static int n;
@@ -315,6 +323,15 @@ int main(int argc, char *argv[])
     printf("Int:\n");
     dump_regs(&initI);
 
+    init_all(&initF16);
+    init_f16reg(&initF16.ymm[10]);
+    init_f16reg(&initF16.ymm[11]);
+    init_f16reg(&initF16.ymm[12]);
+    init_f16reg(&initF16.mem0[1]);
+    initF16.ff = 16;
+    printf("F16:\n");
+    dump_regs(&initF16);
+
     init_all(&initF32);
     init_f32reg(&initF32.ymm[10]);
     init_f32reg(&initF32.ymm[11]);
diff --git a/tests/tcg/i386/test-avx.py b/tests/tcg/i386/test-avx.py
index 0298232..d9ca00a 100755
--- a/tests/tcg/i386/test-avx.py
+++ b/tests/tcg/i386/test-avx.py
@@ -9,6 +9,7 @@ from fnmatch import fnmatch
 archs = [
     "SSE", "SSE2", "SSE3", "SSSE3", "SSE4_1", "SSE4_2",
     "AES", "AVX", "AVX2", "AES+AVX", "VAES+AVX",
+    "F16C", "FMA",
 ]
 
 ignore = set(["FISTTP",
@@ -19,6 +20,7 @@ imask = {
     'vBLENDPS': 0x0f,
     'CMP[PS][SD]': 0x07,
     'VCMP[PS][SD]': 0x1f,
+    'vCVTPS2PH': 0x7,
     'vDPPD': 0x33,
     'vDPPS': 0xff,
     'vEXTRACTPS': 0x03,
@@ -221,8 +223,10 @@ def ArgGenerator(arg, op):
 class InsnGenerator:
     def __init__(self, op, args):
         self.op = op
-        if op[-2:] in ["PS", "PD", "SS", "SD"]:
-            if op[-1] == 'S':
+        if op[-2:] in ["PH", "PS", "PD", "SS", "SD"]:
+            if op[-1] == 'H':
+                self.optype = 'F16'
+            elif op[-1] == 'S':
                 self.optype = 'F32'
             else:
                 self.optype = 'F64'