target/arm: Implement v8.1M branch-future insns (as NOPs)

v8.1M implements a new 'branch future' feature, which is a
set of instructions that request the CPU to perform a branch
"in the future", when it reaches a particular execution address.
In hardware, the expected implementation is that the information
about the branch location and destination is cached and then
acted upon when execution reaches the specified address.
However the architecture permits an implementation to discard
this cached information at any point, and so guest code must
always include a normal branch insn at the branch point as
a fallback. In particular, an implementation is specifically
permitted to treat all BF insns as NOPs (which is equivalent
to discarding the cached information immediately).

For QEMU, implementing this caching of branch information
would be complicated and would not improve the speed of
execution at all, so we make the IMPDEF choice to implement
all BF insns as NOPs.

Backports commit 05903f036edba8e3ed940cc215b8e27fb49265b9

qemu/target/arm/cpu.h

@@ -3328,6 +3328,12 @@ static inline bool isar_feature_aa32_arm_div(const ARMISARegisters *id)
     return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1;
 }
 
+static inline bool isar_feature_aa32_lob(const ARMISARegisters *id)
+{
+    /* (M-profile) low-overhead loops and branch future */
+    return FIELD_EX32(id->id_isar0, ID_ISAR0, CMPBRANCH) >= 3;
+}
+
 static inline bool isar_feature_aa32_jazelle(const ARMISARegisters *id)
 {
     return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0;

qemu/target/arm/t32.decode

@@ -648,4 +648,15 @@ MRC              1110 1110 ... 1 .... .... .... ... 1 .... @mcr
 
 B                1111 0. .......... 10.1 ............         @branch24
 BL               1111 0. .......... 11.1 ............         @branch24
-BLX_i            1111 0. .......... 11.0 ............         @branch24
+{
+  # BLX_i is non-M-profile only
+  BLX_i          1111 0. .......... 11.0 ............         @branch24
+  # M-profile only: loop and branch insns
+  [
+    # All these BF insns have boff != 0b0000; we NOP them all
+    BF           1111 0 boff:4  ------- 1100 - ---------- 1    # BFL
+    BF           1111 0 boff:4 0 ------ 1110 - ---------- 1    # BFCSEL
+    BF           1111 0 boff:4 10 ----- 1110 - ---------- 1    # BF
+    BF           1111 0 boff:4 11 ----- 1110 0 0000000000 1    # BFX, BFLX
+  ]
+}

qemu/target/arm/translate.c

@@ -8227,6 +8227,26 @@ static bool trans_BLX_suffix(DisasContext *s, arg_BLX_suffix *a)
     return true;
 }
 
+static bool trans_BF(DisasContext *s, arg_BF *a)
+{
+    /*
+     * M-profile branch future insns. The architecture permits an
+     * implementation to implement these as NOPs (equivalent to
+     * discarding the LO_BRANCH_INFO cache immediately), and we
+     * take that IMPDEF option because for QEMU a "real" implementation
+     * would be complicated and wouldn't execute any faster.
+     */
+    if (!dc_isar_feature(aa32_lob, s)) {
+        return false;
+    }
+    if (a->boff == 0) {
+        /* SEE "Related encodings" (loop insns) */
+        return false;
+    }
+    /* Handle as NOP */
+    return true;
+}
+
 static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half)
 {
     TCGContext *tcg_ctx = s->uc->tcg_ctx;