target/arm: Store FPSR and FPCR in separate CPU state fields

Now that we have refactored the set/get functions so that the FPSCR
format is no longer the authoritative one, we can keep FPSR and FPCR
in separate CPU state fields.

As well as the get and set functions, we also have a scattering of
places in the code which directly access vfp.xregs[ARM_VFP_FPSCR] to
extract single fields which are stored there.  These all change to
directly access either vfp.fpsr or vfp.fpcr, depending on the
location of the field.  (Most commonly, this is the NZCV flags.)

We make the field in the CPU state struct 64 bits, because
architecturally FPSR and FPCR are 64 bits.  However we leave the
types of the arguments and return values of the get/set functions as
32 bits, since we don't need to make that change with the current
architecture and various callsites would be unable to handle
set bits in the high half (for instance the gdbstub protocol
assumes they're only 32 bit registers).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240628142347.1283015-7-peter.maydell@linaro.org

diff --git a/target/arm/cpu.h b/target/arm/cpu.h
index b1b48c1d7758737289ae58c066787cd16931899f..53232239197fcacc038bd7c6f6b673c12e237e69 100644 (file)
--- a/target/arm/cpu.h
+++ b/target/arm/cpu.h
@@ -619,6 +619,13 @@ typedef struct CPUArchState {
         int vec_len;
         int vec_stride;
 
+        /*
+         * Floating point status and control registers. Some bits are
+         * stored separately in other fields or in the float_status below.
+         */
+        uint64_t fpsr;
+        uint64_t fpcr;
+
         uint32_t xregs[16];
 
         /* Scratch space for aa32 neon expansion.  */

diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c
index 8b99736aad1ef8206df3832992a56af33223a2e0..234f395b0939ce1086cf7d660db482a524423870 100644 (file)
--- a/target/arm/tcg/mve_helper.c
+++ b/target/arm/tcg/mve_helper.c
@@ -1115,21 +1115,21 @@ static void do_vadc(CPUARMState *env, uint32_t *d, uint32_t *n, uint32_t *m,
 
     if (update_flags) {
         /* Store C, clear NZV. */
-        env->vfp.xregs[ARM_VFP_FPSCR] &= ~FPCR_NZCV_MASK;
-        env->vfp.xregs[ARM_VFP_FPSCR] |= carry_in * FPCR_C;
+        env->vfp.fpsr &= ~FPCR_NZCV_MASK;
+        env->vfp.fpsr |= carry_in * FPCR_C;
     }
     mve_advance_vpt(env);
 }
 
 void HELPER(mve_vadc)(CPUARMState *env, void *vd, void *vn, void *vm)
 {
-    bool carry_in = env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_C;
+    bool carry_in = env->vfp.fpsr & FPCR_C;
     do_vadc(env, vd, vn, vm, 0, carry_in, false);
 }
 
 void HELPER(mve_vsbc)(CPUARMState *env, void *vd, void *vn, void *vm)
 {
-    bool carry_in = env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_C;
+    bool carry_in = env->vfp.fpsr & FPCR_C;
     do_vadc(env, vd, vn, vm, -1, carry_in, false);
 }
 
@@ -3343,7 +3343,7 @@ static void do_vcvt_sh(CPUARMState *env, void *vd, void *vm, int top)
     uint32_t *m = vm;
     uint16_t r;
     uint16_t mask = mve_element_mask(env);
-    bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP);
+    bool ieee = !(env->vfp.fpcr & FPCR_AHP);
     unsigned e;
     float_status *fpst;
     float_status scratch_fpst;
@@ -3373,7 +3373,7 @@ static void do_vcvt_hs(CPUARMState *env, void *vd, void *vm, int top)
     uint16_t *m = vm;
     uint32_t r;
     uint16_t mask = mve_element_mask(env);
-    bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP);
+    bool ieee = !(env->vfp.fpcr & FPCR_AHP);
     unsigned e;
     float_status *fpst;
     float_status scratch_fpst;

diff --git a/target/arm/tcg/translate-m-nocp.c b/target/arm/tcg/translate-m-nocp.c
index f564d06ccf11a4036ba870a5b0c071b1d8650fb6..875f6a8725d249ed40756f83859f927a1afbcf03 100644 (file)
--- a/target/arm/tcg/translate-m-nocp.c
+++ b/target/arm/tcg/translate-m-nocp.c
@@ -341,10 +341,10 @@ static bool gen_M_fp_sysreg_write(DisasContext *s, int regno,
                                  16, 16, qc);
         }
         tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK);
-        fpscr = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]);
+        fpscr = load_cpu_field_low32(vfp.fpsr);
         tcg_gen_andi_i32(fpscr, fpscr, ~FPCR_NZCV_MASK);
         tcg_gen_or_i32(fpscr, fpscr, tmp);
-        store_cpu_field(fpscr, vfp.xregs[ARM_VFP_FPSCR]);
+        store_cpu_field_low32(fpscr, vfp.fpsr);
         break;
     }
     case ARM_VFP_FPCXT_NS:
@@ -465,7 +465,7 @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno,
          * Read just NZCV; this is a special case to avoid the
          * helper call for the "VMRS to CPSR.NZCV" insn.
          */
-        tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]);
+        tmp = load_cpu_field_low32(vfp.fpsr);
         tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK);
         storefn(s, opaque, tmp, true);
         break;

diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c
index 39ec971ff70ae50411845d094a05cb046912e327..0d9788e81031c93ad3ae5fea05c11eb89deaacd9 100644 (file)
--- a/target/arm/tcg/translate-vfp.c
+++ b/target/arm/tcg/translate-vfp.c
@@ -833,7 +833,7 @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a)
             break;
         case ARM_VFP_FPSCR:
             if (a->rt == 15) {
-                tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]);
+                tmp = load_cpu_field_low32(vfp.fpsr);
                 tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK);
             } else {
                 tmp = tcg_temp_new_i32();

diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h
index aba21f730fe10c53d38feab751a96d8775698d1d..a8672c857c101c37c0b39a0bb733af675ecfa93d 100644 (file)
--- a/target/arm/tcg/translate.h
+++ b/target/arm/tcg/translate.h
@@ -351,8 +351,7 @@ static inline TCGv_i32 get_ahp_flag(void)
 {
     TCGv_i32 ret = tcg_temp_new_i32();
 
-    tcg_gen_ld_i32(ret, tcg_env,
-                   offsetof(CPUARMState, vfp.xregs[ARM_VFP_FPSCR]));
+    tcg_gen_ld_i32(ret, tcg_env, offsetoflow32(CPUARMState, vfp.fpcr));
     tcg_gen_extract_i32(ret, ret, 26, 1);
 
     return ret;

diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c
index 678de5eb6f700ff4d54ef7087214190bdc25e3fa..a8c89a910f63148401009b8b46ae7920e2087f07 100644 (file)
--- a/target/arm/vfp_helper.c
+++ b/target/arm/vfp_helper.c
@@ -115,7 +115,7 @@ static void vfp_set_fpsr_to_host(CPUARMState *env, uint32_t val)
 
 static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val)
 {
-    uint32_t changed = env->vfp.xregs[ARM_VFP_FPSCR];
+    uint64_t changed = env->vfp.fpcr;
 
     changed ^= val;
     if (changed & (3 << 22)) {
@@ -175,7 +175,7 @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val)
 
 uint32_t vfp_get_fpcr(CPUARMState *env)
 {
-    uint32_t fpcr = (env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_MASK)
+    uint32_t fpcr = env->vfp.fpcr
         | (env->vfp.vec_len << 16)
         | (env->vfp.vec_stride << 20);
 
@@ -190,7 +190,7 @@ uint32_t vfp_get_fpcr(CPUARMState *env)
 
 uint32_t vfp_get_fpsr(CPUARMState *env)
 {
-    uint32_t fpsr = env->vfp.xregs[ARM_VFP_FPSCR] & FPSR_MASK;
+    uint32_t fpsr = env->vfp.fpsr;
     uint32_t i;
 
     fpsr |= vfp_get_fpsr_from_host(env);
@@ -229,15 +229,13 @@ void vfp_set_fpsr(CPUARMState *env, uint32_t val)
     }
 
     /*
-     * The only FPSR bits we keep in vfp.xregs[FPSCR] are NZCV:
+     * The only FPSR bits we keep in vfp.fpsr are NZCV:
      * the exception flags IOC|DZC|OFC|UFC|IXC|IDC are stored in
      * fp_status, and QC is in vfp.qc[]. Store the NZCV bits there,
-     * and zero any of the other FPSR bits (but preserve the FPCR
-     * bits).
+     * and zero any of the other FPSR bits.
      */
     val &= FPCR_NZCV_MASK;
-    env->vfp.xregs[ARM_VFP_FPSCR] &= ~FPSR_MASK;
-    env->vfp.xregs[ARM_VFP_FPSCR] |= val;
+    env->vfp.fpsr = val;
 }
 
 void vfp_set_fpcr(CPUARMState *env, uint32_t val)
@@ -271,14 +269,13 @@ void vfp_set_fpcr(CPUARMState *env, uint32_t val)
      * 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.xregs[FPSCR] are AHP, DN, FZ, RMode
+     * The FPCR bits we keep in vfp.fpcr are AHP, DN, FZ, RMode
      * 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;
-    env->vfp.xregs[ARM_VFP_FPSCR] &= ~FPCR_MASK;
-    env->vfp.xregs[ARM_VFP_FPSCR] |= val;
+    env->vfp.fpcr = val;
 }
 
 void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val)
@@ -356,8 +353,7 @@ static void softfloat_to_vfp_compare(CPUARMState *env, FloatRelation cmp)
     default:
         g_assert_not_reached();
     }
-    env->vfp.xregs[ARM_VFP_FPSCR] =
-        deposit32(env->vfp.xregs[ARM_VFP_FPSCR], 28, 4, flags);
+    env->vfp.fpsr = deposit64(env->vfp.fpsr, 28, 4, flags); /* NZCV */
 }
 
 /* XXX: check quiet/signaling case */
@@ -1160,8 +1156,7 @@ uint32_t HELPER(vjcvt)(float64 value, CPUARMState *env)
     uint32_t z = (pair >> 32) == 0;
 
     /* Store Z, clear NCV, in FPSCR.NZCV.  */
-    env->vfp.xregs[ARM_VFP_FPSCR]
-        = (env->vfp.xregs[ARM_VFP_FPSCR] & ~CPSR_NZCV) | (z * CPSR_Z);
+    env->vfp.fpsr = (env->vfp.fpsr & ~FPCR_NZCV_MASK) | (z * FPCR_Z);
 
     return result;
 }