[PULL,01/25] target/arm: Allow setting the FPCR.EBF bit for FEAT_EBF16

Commit Message

Peter Maydell Sept. 5, 2024, 1 p.m. UTC

FEAT_EBF16 adds one new bit to the FPCR floating point control
register.  Allow this bit to be read and written when the ID
registers indicate the presence of the feature.

Note that because this new bit is not in FPSCR_FPCR_MASK the bit is
not visible in the AArch32 FPSCR, and FPSCR writes do not affect it.

Signed-off-by: Peter Maydell <[e-mail]>
Reviewed-by: Richard Henderson <[e-mail]>
---
 target/arm/cpu-features.h | 5 +++++
 target/arm/cpu.h          | 1 +
 target/arm/vfp_helper.c   | 8 ++++++--
 3 files changed, 12 insertions(+), 2 deletions(-)

Patch

diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h
index c59ca104fe1..cfb82c23cad 100644
--- a/target/arm/cpu-features.h
+++ b/target/arm/cpu-features.h
@@ -556,6 +556,11 @@  static inline bool isar_feature_aa64_bf16(const ARMISARegisters *id)
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) != 0;
 }
 
+static inline bool isar_feature_aa64_ebf16(const ARMISARegisters *id)
+{
+    return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, BF16) > 1;
+}
+
 static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id)
 {
     return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0;
diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index 9a3fd595621..f065756c5c7 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -1707,6 +1707,7 @@  void vfp_set_fpscr(CPUARMState *env, uint32_t val);
 #define FPCR_OFE    (1 << 10)   /* Overflow exception trap enable */
 #define FPCR_UFE    (1 << 11)   /* Underflow exception trap enable */
 #define FPCR_IXE    (1 << 12)   /* Inexact exception trap enable */
+#define FPCR_EBF    (1 << 13)   /* Extended BFloat16 behaviors */
 #define FPCR_IDE    (1 << 15)   /* Input Denormal exception trap enable */
 #define FPCR_LEN_MASK (7 << 16) /* LEN, A-profile only */
 #define FPCR_FZ16   (1 << 19)   /* ARMv8.2+, FP16 flush-to-zero */
diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index b3698da8ca7..203d37303bd 100644
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -254,6 +254,10 @@  static void vfp_set_fpcr_masked(CPUARMState *env, uint32_t val, uint32_t mask)
         val &= ~FPCR_FZ16;
     }
 
+    if (!cpu_isar_feature(aa64_ebf16, cpu)) {
+        val &= ~FPCR_EBF;
+    }
+
     vfp_set_fpcr_to_host(env, val, mask);
 
     if (mask & (FPCR_LEN_MASK | FPCR_STRIDE_MASK)) {
@@ -278,12 +282,12 @@  static void vfp_set_fpcr_masked(CPUARMState *env, uint32_t val, uint32_t mask)
      * We don't implement trapped exception handling, so the
      * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!)
      *
-     * The FPCR bits we keep in vfp.fpcr are AHP, DN, FZ, RMode
+     * The FPCR bits we keep in vfp.fpcr are AHP, DN, FZ, RMode, EBF
      * and FZ16. Len, Stride and LTPSIZE we just handled. Store those bits
      * there, and zero any of the other FPCR bits and the RES0 and RAZ/WI
      * bits.
      */
-    val &= FPCR_AHP | FPCR_DN | FPCR_FZ | FPCR_RMODE_MASK | FPCR_FZ16;
+    val &= FPCR_AHP | FPCR_DN | FPCR_FZ | FPCR_RMODE_MASK | FPCR_FZ16 | FPCR_EBF;
     env->vfp.fpcr &= ~mask;
     env->vfp.fpcr |= val;
 }