Merge tag 'pull-target-arm-20250211' of https://git.linaro.org/people/pmaydell/qemu-arm into staging

target-arm queue:
 * target/alpha: Don't corrupt error_code with unknown softfloat flags
 * target/arm: Implement FEAT_AFP and FEAT_RPRES

# -----BEGIN PGP SIGNATURE-----
#
# iQJNBAABCAA3FiEE4aXFk81BneKOgxXPPCUl7RQ2DN4FAmereaQZHHBldGVyLm1h
# eWRlbGxAbGluYXJvLm9yZwAKCRA8JSXtFDYM3gyLEACglOM4E0j1hRl/JZlWD384
# nZL01Hayp9xwSNn28hkXaajCxkErTWLuCZax1g1fBvt/Yqn+E3oFan8gIybMEVgK
# 9ei6/m45fuICSQQhifvYTtYhAMd5uclr0anjRp9gN7FH6aaNPan/ZQYcKYxFq6cp
# RDTF5qiHIgTeXAlU+WiioxravL3A/D+jcQMYLEI5L+Vt5nYNM589PSNFWNLQ6W9e
# Gtmvp0uzrRSZgWxR3nOvhsn1NS/xXK90Zil+GPBo4jf82QVumqKYMsAcireOlxfk
# zTlHXH3PuonGj/ZPLxmiVKYhLb1RglQ9kIs/FHVel18QTz4dJ3DaJp8QXCNHbrKz
# 3aUwSiIh5Y/s3Q/X2Qy3jUHQ5tSjayhIhGFbn6zPdZ+2JZbIEu1Czeparddu/Zlq
# OR0CMVo2Lj/C6OakEU1/YRTKBKiNBaN1eVHi7gjzTDBdbMMC7ZlNuimpFAbthmSC
# szHzkgX8LXHzJqe4vip27yOMFBRPxvst/CXcEoPnjsLEQhLlKjOeFiHuEI+DUvaI
# 24AJ5b0FDdSOEcaFkxFD6gxW8E77MiNtBncfxDxTMKHs/4yFGiDihSPnOCANn3Kk
# zpQIwl0KJAPTA6Cldck9lY7MsKgGPTUNhEThadZlInbp4Uc6T1bvNDtB9b7osDfy
# FeposcM1+GBeuSde0yD6oQ==
# =P3wv
# -----END PGP SIGNATURE-----
# gpg: Signature made Tue 11 Feb 2025 11:24:04 EST
# gpg:                using RSA key E1A5C593CD419DE28E8315CF3C2525ED14360CDE
# gpg:                issuer "peter.maydell@linaro.org"
# gpg: Good signature from "Peter Maydell <peter.maydell@linaro.org>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@gmail.com>" [full]
# gpg:                 aka "Peter Maydell <pmaydell@chiark.greenend.org.uk>" [full]
# gpg:                 aka "Peter Maydell <peter@archaic.org.uk>" [unknown]
# Primary key fingerprint: E1A5 C593 CD41 9DE2 8E83  15CF 3C25 25ED 1436 0CDE

* tag 'pull-target-arm-20250211' of https://git.linaro.org/people/pmaydell/qemu-arm: (68 commits)
  target/arm: Sink fp_status and fpcr access into do_fmlal*
  target/arm: Read fz16 from env->vfp.fpcr
  target/arm: Simplify DO_VFP_cmp in vfp_helper.c
  target/arm: Simplify fp_status indexing in mve_helper.c
  target/arm: Remove fp_status_a32
  target/arm: Remove fp_status_a64
  target/arm: Remove fp_status_f16_a32
  target/arm: Remove fp_status_f16_a64
  target/arm: Remove ah_fp_status
  target/arm: Remove ah_fp_status_f16
  target/arm: Remove standard_fp_status
  target/arm: Remove standard_fp_status_f16
  target/arm: Introduce CPUARMState.vfp.fp_status[]
  target/arm: Enable FEAT_RPRES for -cpu max
  target/arm: Implement increased precision FRSQRTE
  target/arm: Implement increased precision FRECPE
  target/arm: Plumb FEAT_RPRES frecpe and frsqrte through to new helper
  target/arm: Enable FEAT_AFP for '-cpu max'
  target/arm: Handle FPCR.AH in SVE FMLSLB, FMLSLT (vectors)
  target/arm: Handle FPCR.AH in SVE FMLSL (indexed)
  ...

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

1 files changed, 60 insertions, 6 deletions

diff --git a/fpu/softfloat.c b/fpu/softfloat.c
index 26f3a8dc87..f4fed9bfda 100644
--- a/fpu/softfloat.c
+++ b/fpu/softfloat.c
@@ -404,12 +404,16 @@ float64_gen2(float64 xa, float64 xb, float_status *s,
 /*
  * Classify a floating point number. Everything above float_class_qnan
  * is a NaN so cls >= float_class_qnan is any NaN.
+ *
+ * Note that we canonicalize denormals, so most code should treat
+ * class_normal and class_denormal identically.
  */
 
 typedef enum __attribute__ ((__packed__)) {
     float_class_unclassified,
     float_class_zero,
     float_class_normal,
+    float_class_denormal, /* input was a non-squashed denormal */
     float_class_inf,
     float_class_qnan,  /* all NaNs from here */
     float_class_snan,
@@ -420,12 +424,14 @@ typedef enum __attribute__ ((__packed__)) {
 enum {
     float_cmask_zero    = float_cmask(float_class_zero),
     float_cmask_normal  = float_cmask(float_class_normal),
+    float_cmask_denormal = float_cmask(float_class_denormal),
     float_cmask_inf     = float_cmask(float_class_inf),
     float_cmask_qnan    = float_cmask(float_class_qnan),
     float_cmask_snan    = float_cmask(float_class_snan),
 
     float_cmask_infzero = float_cmask_zero | float_cmask_inf,
     float_cmask_anynan  = float_cmask_qnan | float_cmask_snan,
+    float_cmask_anynorm = float_cmask_normal | float_cmask_denormal,
 };
 
 /* Flags for parts_minmax. */
@@ -460,6 +466,20 @@ static inline __attribute__((unused)) bool is_qnan(FloatClass c)
 }
 
 /*
+ * Return true if the float_cmask has only normals in it
+ * (including input denormals that were canonicalized)
+ */
+static inline bool cmask_is_only_normals(int cmask)
+{
+    return !(cmask & ~float_cmask_anynorm);
+}
+
+static inline bool is_anynorm(FloatClass c)
+{
+    return float_cmask(c) & float_cmask_anynorm;
+}
+
+/*
  * Structure holding all of the decomposed parts of a float.
  * The exponent is unbiased and the fraction is normalized.
  *
@@ -1729,6 +1749,7 @@ static float64 float64r32_round_pack_canonical(FloatParts64 *p,
      */
     switch (p->cls) {
     case float_class_normal:
+    case float_class_denormal:
         if (unlikely(p->exp == 0)) {
             /*
              * The result is denormal for float32, but can be represented
@@ -1817,6 +1838,7 @@ static floatx80 floatx80_round_pack_canonical(FloatParts128 *p,
 
     switch (p->cls) {
     case float_class_normal:
+    case float_class_denormal:
         if (s->floatx80_rounding_precision == floatx80_precision_x) {
             parts_uncanon_normal(p, s, fmt);
             frac = p->frac_hi;
@@ -2696,6 +2718,9 @@ static void parts_float_to_ahp(FloatParts64 *a, float_status *s)
                                   float16_params_ahp.frac_size + 1);
         break;
 
+    case float_class_denormal:
+        float_raise(float_flag_input_denormal_used, s);
+        break;
     case float_class_normal:
     case float_class_zero:
         break;
@@ -2710,6 +2735,9 @@ static void parts64_float_to_float(FloatParts64 *a, float_status *s)
     if (is_nan(a->cls)) {
         parts_return_nan(a, s);
     }
+    if (a->cls == float_class_denormal) {
+        float_raise(float_flag_input_denormal_used, s);
+    }
 }
 
 static void parts128_float_to_float(FloatParts128 *a, float_status *s)
@@ -2717,6 +2745,9 @@ static void parts128_float_to_float(FloatParts128 *a, float_status *s)
     if (is_nan(a->cls)) {
         parts_return_nan(a, s);
     }
+    if (a->cls == float_class_denormal) {
+        float_raise(float_flag_input_denormal_used, s);
+    }
 }
 
 #define parts_float_to_float(P, S) \
@@ -2729,12 +2760,21 @@ static void parts_float_to_float_narrow(FloatParts64 *a, FloatParts128 *b,
     a->sign = b->sign;
     a->exp = b->exp;
 
-    if (a->cls == float_class_normal) {
+    switch (a->cls) {
+    case float_class_denormal:
+        float_raise(float_flag_input_denormal_used, s);
+        /* fall through */
+    case float_class_normal:
         frac_truncjam(a, b);
-    } else if (is_nan(a->cls)) {
+        break;
+    case float_class_snan:
+    case float_class_qnan:
         /* Discard the low bits of the NaN. */
         a->frac = b->frac_hi;
         parts_return_nan(a, s);
+        break;
+    default:
+        break;
     }
 }
 
@@ -2749,6 +2789,9 @@ static void parts_float_to_float_widen(FloatParts128 *a, FloatParts64 *b,
     if (is_nan(a->cls)) {
         parts_return_nan(a, s);
     }
+    if (a->cls == float_class_denormal) {
+        float_raise(float_flag_input_denormal_used, s);
+    }
 }
 
 float32 float16_to_float32(float16 a, bool ieee, float_status *s)
@@ -3218,6 +3261,7 @@ static Int128 float128_to_int128_scalbn(float128 a, FloatRoundMode rmode,
         return int128_zero();
 
     case float_class_normal:
+    case float_class_denormal:
         if (parts_round_to_int_normal(&p, rmode, scale, 128 - 2)) {
             flags = float_flag_inexact;
         }
@@ -3645,6 +3689,7 @@ static Int128 float128_to_uint128_scalbn(float128 a, FloatRoundMode rmode,
         return int128_zero();
 
     case float_class_normal:
+    case float_class_denormal:
         if (parts_round_to_int_normal(&p, rmode, scale, 128 - 2)) {
             flags = float_flag_inexact;
             if (p.cls == float_class_zero) {
@@ -4386,7 +4431,11 @@ float32_hs_compare(float32 xa, float32 xb, float_status *s, bool is_quiet)
         goto soft;
     }
 
-    float32_input_flush2(&ua.s, &ub.s, s);
+    if (unlikely(float32_is_denormal(ua.s) || float32_is_denormal(ub.s))) {
+        /* We may need to set the input_denormal_used flag */
+        goto soft;
+    }
+
     if (isgreaterequal(ua.h, ub.h)) {
         if (isgreater(ua.h, ub.h)) {
             return float_relation_greater;
@@ -4436,7 +4485,11 @@ float64_hs_compare(float64 xa, float64 xb, float_status *s, bool is_quiet)
         goto soft;
     }
 
-    float64_input_flush2(&ua.s, &ub.s, s);
+    if (unlikely(float64_is_denormal(ua.s) || float64_is_denormal(ub.s))) {
+        /* We may need to set the input_denormal_used flag */
+        goto soft;
+    }
+
     if (isgreaterequal(ua.h, ub.h)) {
         if (isgreater(ua.h, ub.h)) {
             return float_relation_greater;
@@ -5231,6 +5284,8 @@ float32 float32_exp2(float32 a, float_status *status)
     float32_unpack_canonical(&xp, a, status);
     if (unlikely(xp.cls != float_class_normal)) {
         switch (xp.cls) {
+        case float_class_denormal:
+            break;
         case float_class_snan:
         case float_class_qnan:
             parts_return_nan(&xp, status);
@@ -5240,9 +5295,8 @@ float32 float32_exp2(float32 a, float_status *status)
         case float_class_zero:
             return float32_one;
         default:
-            break;
+            g_assert_not_reached();
         }
-        g_assert_not_reached();
     }
 
     float_raise(float_flag_inexact, status);