target/arm: Implement FPSCR.LTPSIZE for M-profile LOB extension

If the M-profile low-overhead-branch extension is implemented, FPSCR
bits [18:16] are a new field LTPSIZE. If MVE is not implemented
(currently always true for us) then this field always reads as 4 and
ignores writes.

These bits used to be the vector-length field for the old
short-vector extension, so we need to take care that they are not
misinterpreted as setting vec_len. We do this with a rearrangement
of the vfp_set_fpscr() code that deals with vec_len, vec_stride
and also the QC bit; this obviates the need for the M-profile
only masking step that we used to have at the start of the function.

We provide a new field in CPUState for LTPSIZE, even though this
will always be 4, in preparation for MVE, so we don't have to
come back later and split it out of the vfp.xregs[FPSCR] value.
(This state struct field will be saved and restored as part of
the FPSCR value via the vmstate_fpscr in machine.c.)

Backports 8128c8e8cc9489a8387c74075974f86dc0222e7f

qemu/target/arm/cpu.c

@@ -251,6 +251,15 @@ static void arm_cpu_reset(CPUState *s)
         uint32_t initial_pc; /* Loaded from 0x4 */
         uint32_t vecbase = 0;
 
+        if (cpu_isar_feature(aa32_lob, cpu)) {
+            /*
+             * LTPSIZE is constant 4 if MVE not implemented, and resets
+             * to an UNKNOWN value if MVE is implemented. We choose to
+             * always reset to 4.
+             */
+            env->v7m.ltpsize = 4;
+        }
+
         if (arm_feature(env, ARM_FEATURE_M_SECURITY)) {
             env->v7m.secure = true;
         } else {

qemu/target/arm/cpu.h

@@ -523,6 +523,7 @@ typedef struct CPUARMState {
         uint32_t fpdscr[M_REG_NUM_BANKS];
         uint32_t cpacr[M_REG_NUM_BANKS];
         uint32_t nsacr;
+        int ltpsize;
     } v7m;
 
     /* Information associated with an exception about to be taken:

qemu/target/arm/vfp_helper.c

@@ -177,6 +177,12 @@ uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env)
             | (env->vfp.vec_len << 16)
             | (env->vfp.vec_stride << 20);
 
+    /*
+     * M-profile LTPSIZE overlaps A-profile Stride; whichever of the
+     * two is not applicable to this CPU will always be zero.
+     */
+    fpscr |= env->v7m.ltpsize << 16;
+
     fpscr |= vfp_get_fpscr_from_host(env);
 
     i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3];