target/arm: Implement v8.1M low-overhead-loop instructions

v8.1M's "low-overhead-loop" extension has three instructions
for looping:
 * DLS (start of a do-loop)
 * WLS (start of a while-loop)
 * LE (end of a loop)

The loop-start instructions are both simple operations to start a
loop whose iteration count (if any) is in LR.  The loop-end
instruction handles "decrement iteration count and jump back to loop
start"; it also caches the information about the branch back to the
start of the loop to improve performance of the branch on subsequent
iterations.

As with the branch-future instructions, the architecture permits an
implementation to discard the LO_BRANCH_INFO cache at any time, and
QEMU takes the IMPDEF option to never set it in the first place
(equivalent to discarding it immediately), because for us a "real"
implementation would be unnecessary complexity.

(This implementation only provides the simple looping constructs; the
vector extension MVE (Helium) adds some extra variants to handle
looping across vectors.  We'll add those later when we implement
MVE.)

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20201019151301.2046-8-peter.maydell@linaro.org

2 files changed, 99 insertions, 2 deletions

diff --git a/target/arm/t32.decode b/target/arm/t32.decode
index 3015731..8152739 100644
--- a/target/arm/t32.decode
+++ b/target/arm/t32.decode
@@ -659,4 +659,12 @@ BL               1111 0. .......... 11.1 ............         @branch24
     BF           1111 0 boff:4 10 ----- 1110 - ---------- 1    # BF
     BF           1111 0 boff:4 11 ----- 1110 0 0000000000 1    # BFX, BFLX
   ]
+  [
+    # LE and WLS immediate
+    %lob_imm 1:10 11:1 !function=times_2
+
+    DLS          1111 0 0000 100     rn:4 1110 0000 0000 0001
+    WLS          1111 0 0000 100     rn:4 1100 . .......... 1 imm=%lob_imm
+    LE           1111 0 0000 0 f:1 0 1111 1100 . .......... 1 imm=%lob_imm
+  ]
 }
diff --git a/target/arm/translate.c b/target/arm/translate.c
index a5ebe56..38371db 100644
--- a/target/arm/translate.c
+++ b/target/arm/translate.c
@@ -2490,17 +2490,23 @@ static void gen_goto_tb(DisasContext *s, int n, target_ulong dest)
     s->base.is_jmp = DISAS_NORETURN;
 }
 
-static inline void gen_jmp (DisasContext *s, uint32_t dest)
+/* Jump, specifying which TB number to use if we gen_goto_tb() */
+static inline void gen_jmp_tb(DisasContext *s, uint32_t dest, int tbno)
 {
     if (unlikely(is_singlestepping(s))) {
         /* An indirect jump so that we still trigger the debug exception.  */
         gen_set_pc_im(s, dest);
         s->base.is_jmp = DISAS_JUMP;
     } else {
-        gen_goto_tb(s, 0, dest);
+        gen_goto_tb(s, tbno, dest);
     }
 }
 
+static inline void gen_jmp(DisasContext *s, uint32_t dest)
+{
+    gen_jmp_tb(s, dest, 0);
+}
+
 static inline void gen_mulxy(TCGv_i32 t0, TCGv_i32 t1, int x, int y)
 {
     if (x)
@@ -7991,6 +7997,89 @@ static bool trans_BF(DisasContext *s, arg_BF *a)
     return true;
 }
 
+static bool trans_DLS(DisasContext *s, arg_DLS *a)
+{
+    /* M-profile low-overhead loop start */
+    TCGv_i32 tmp;
+
+    if (!dc_isar_feature(aa32_lob, s)) {
+        return false;
+    }
+    if (a->rn == 13 || a->rn == 15) {
+        /* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
+        return false;
+    }
+
+    /* Not a while loop, no tail predication: just set LR to the count */
+    tmp = load_reg(s, a->rn);
+    store_reg(s, 14, tmp);
+    return true;
+}
+
+static bool trans_WLS(DisasContext *s, arg_WLS *a)
+{
+    /* M-profile low-overhead while-loop start */
+    TCGv_i32 tmp;
+    TCGLabel *nextlabel;
+
+    if (!dc_isar_feature(aa32_lob, s)) {
+        return false;
+    }
+    if (a->rn == 13 || a->rn == 15) {
+        /* CONSTRAINED UNPREDICTABLE: we choose to UNDEF */
+        return false;
+    }
+    if (s->condexec_mask) {
+        /*
+         * WLS in an IT block is CONSTRAINED UNPREDICTABLE;
+         * we choose to UNDEF, because otherwise our use of
+         * gen_goto_tb(1) would clash with the use of TB exit 1
+         * in the dc->condjmp condition-failed codepath in
+         * arm_tr_tb_stop() and we'd get an assertion.
+         */
+        return false;
+    }
+    nextlabel = gen_new_label();
+    tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_R[a->rn], 0, nextlabel);
+    tmp = load_reg(s, a->rn);
+    store_reg(s, 14, tmp);
+    gen_jmp_tb(s, s->base.pc_next, 1);
+
+    gen_set_label(nextlabel);
+    gen_jmp(s, read_pc(s) + a->imm);
+    return true;
+}
+
+static bool trans_LE(DisasContext *s, arg_LE *a)
+{
+    /*
+     * M-profile low-overhead loop end. The architecture permits an
+     * implementation to discard the LO_BRANCH_INFO cache at any time,
+     * and we take the IMPDEF option to never set it in the first place
+     * (equivalent to always discarding it immediately), because for QEMU
+     * a "real" implementation would be complicated and wouldn't execute
+     * any faster.
+     */
+    TCGv_i32 tmp;
+
+    if (!dc_isar_feature(aa32_lob, s)) {
+        return false;
+    }
+
+    if (!a->f) {
+        /* Not loop-forever. If LR <= 1 this is the last loop: do nothing. */
+        arm_gen_condlabel(s);
+        tcg_gen_brcondi_i32(TCG_COND_LEU, cpu_R[14], 1, s->condlabel);
+        /* Decrement LR */
+        tmp = load_reg(s, 14);
+        tcg_gen_addi_i32(tmp, tmp, -1);
+        store_reg(s, 14, tmp);
+    }
+    /* Jump back to the loop start */
+    gen_jmp(s, read_pc(s) - a->imm);
+    return true;
+}
+
 static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half)
 {
     TCGv_i32 addr, tmp;