[Qemu-devel] [PULL 24/27] target/arm: Split out FPSCR.QC to a vector field

[Peter Maydell]

From: Richard Henderson <address@hidden>

Change the representation of this field such that it is easy
to set from vector code.

Signed-off-by: Richard Henderson <address@hidden>
Message-id: address@hidden
Reviewed-by: Peter Maydell <address@hidden>
Signed-off-by: Peter Maydell <address@hidden>
---
 target/arm/cpu.h         |  5 ++++-
 target/arm/helper.c      | 19 +++++++++++++++----
 target/arm/neon_helper.c |  2 +-
 target/arm/vec_helper.c  |  2 +-
 4 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index bfc05c796a5..84ae6849c2f 100644
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -577,11 +577,13 @@ typedef struct CPUARMState {
         ARMPredicateReg preg_tmp;
 #endif
 
-        uint32_t xregs[16];
         /* We store these fpcsr fields separately for convenience.  */
+        uint32_t qc[4] QEMU_ALIGNED(16);
         int vec_len;
         int vec_stride;
 
+        uint32_t xregs[16];
+
         /* Scratch space for aa32 neon expansion.  */
         uint32_t scratch[8];
 
@@ -1427,6 +1429,7 @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val);
 #define FPCR_FZ16   (1 << 19)   /* ARMv8.2+, FP16 flush-to-zero */
 #define FPCR_FZ     (1 << 24)   /* Flush-to-zero enable bit */
 #define FPCR_DN     (1 << 25)   /* Default NaN enable bit */
+#define FPCR_QC     (1 << 27)   /* Cumulative saturation bit */
 
 static inline uint32_t vfp_get_fpsr(CPUARMState *env)
 {
diff --git a/target/arm/helper.c b/target/arm/helper.c
index d4b7eca30a7..55e9b77bb10 100644
--- a/target/arm/helper.c
+++ b/target/arm/helper.c
@@ -12704,8 +12704,7 @@ static inline int vfp_exceptbits_from_host(int 
host_bits)
 
 uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env)
 {
-    int i;
-    uint32_t fpscr;
+    uint32_t i, fpscr;
 
     fpscr = env->vfp.xregs[ARM_VFP_FPSCR]
             | (env->vfp.vec_len << 16)
@@ -12716,8 +12715,11 @@ uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env)
     /* FZ16 does not generate an input denormal exception.  */
     i |= (get_float_exception_flags(&env->vfp.fp_status_f16)
           & ~float_flag_input_denormal);
-
     fpscr |= vfp_exceptbits_from_host(i);
+
+    i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3];
+    fpscr |= i ? FPCR_QC : 0;
+
     return fpscr;
 }
 
@@ -12764,10 +12766,19 @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t 
val)
      * (which are stored in fp_status), and the other RES0 bits
      * in between, then we clear all of the low 16 bits.
      */
-    env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xffc80000;
+    env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000;
     env->vfp.vec_len = (val >> 16) & 7;
     env->vfp.vec_stride = (val >> 20) & 3;
 
+    /*
+     * The bit we set within fpscr_q is arbitrary; the register as a
+     * whole being zero/non-zero is what counts.
+     */
+    env->vfp.qc[0] = val & FPCR_QC;
+    env->vfp.qc[1] = 0;
+    env->vfp.qc[2] = 0;
+    env->vfp.qc[3] = 0;
+
     changed ^= val;
     if (changed & (3 << 22)) {
         i = (val >> 22) & 3;
diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c
index 3249005b627..ed1c6fc41ce 100644
--- a/target/arm/neon_helper.c
+++ b/target/arm/neon_helper.c
@@ -15,7 +15,7 @@
 #define SIGNBIT (uint32_t)0x80000000
 #define SIGNBIT64 ((uint64_t)1 << 63)
 
-#define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] |= CPSR_Q
+#define SET_QC() env->vfp.qc[0] = 1
 
 #define NEON_TYPE1(name, type) \
 typedef struct \
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 37f338732e3..65a18af4e0d 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -36,7 +36,7 @@
 #define H4(x)  (x)
 #endif
 
-#define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] |= CPSR_Q
+#define SET_QC() env->vfp.qc[0] = 1
 
 static void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz)
 {
-- 
2.20.1