Hexagon (target/hexagon) Use direct block chaining for direct jump/branch

Direct block chaining is documented here
https://qemu.readthedocs.io/en/latest/devel/tcg.html#direct-block-chaining

Recall that Hexagon allows packets with multiple jumps where only the
first one with a true predicate will actually jump.  We can  use
tcg_gen_goto_tb/tcg_gen_exit_tb when the packet contains a single
PC-relative branch or jump.  If not, we use tcg_gen_lookup_and_goto_ptr.

We add the following to DisasContext in order to delay the branching
until the end of packet commit (in gen_end_tb)
    branch_cond
        The TCGCond condition under which the branch is taken
        When branch_cond == TCG_COND_NEVER, there isn't a single
        direct branch in this packet.
        When branch_cond != TCG_COND_ALWAYS, the value is in
        hex_branch_taken
    branch_dest
        The destination of the branch

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Taylor Simpson <tsimpson@quicinc.com>
Message-Id: <20221108162906.3166-11-tsimpson@quicinc.com>

3 files changed, 46 insertions, 2 deletions

diff --git a/target/hexagon/genptr.c b/target/hexagon/genptr.c
index be9c715ea8..ee0f86fab2 100644
--- a/target/hexagon/genptr.c
+++ b/target/hexagon/genptr.c
@@ -484,7 +484,17 @@ static void gen_write_new_pc_pcrel(DisasContext *ctx, int pc_off,
                                    TCGCond cond, TCGv pred)
 {
     target_ulong dest = ctx->pkt->pc + pc_off;
-    gen_write_new_pc_addr(ctx, tcg_constant_tl(dest), cond, pred);
+    if (ctx->pkt->pkt_has_multi_cof) {
+        gen_write_new_pc_addr(ctx, tcg_constant_tl(dest), cond, pred);
+    } else {
+        /* Defer this jump to the end of the TB */
+        ctx->branch_cond = TCG_COND_ALWAYS;
+        if (pred != NULL) {
+            ctx->branch_cond = cond;
+            tcg_gen_mov_tl(hex_branch_taken, pred);
+        }
+        ctx->branch_dest = dest;
+    }
 }
 
 static void gen_compare(TCGCond cond, TCGv res, TCGv arg1, TCGv arg2)
diff --git a/target/hexagon/translate.c b/target/hexagon/translate.c
index fa6415936c..f5ef54f039 100644
--- a/target/hexagon/translate.c
+++ b/target/hexagon/translate.c
@@ -116,10 +116,41 @@ static void gen_exec_counters(DisasContext *ctx)
                     hex_gpr[HEX_REG_QEMU_HVX_CNT], ctx->num_hvx_insns);
 }
 
+static bool use_goto_tb(DisasContext *ctx, target_ulong dest)
+{
+    return translator_use_goto_tb(&ctx->base, dest);
+}
+
+static void gen_goto_tb(DisasContext *ctx, int idx, target_ulong dest)
+{
+    if (use_goto_tb(ctx, dest)) {
+        tcg_gen_goto_tb(idx);
+        tcg_gen_movi_tl(hex_gpr[HEX_REG_PC], dest);
+        tcg_gen_exit_tb(ctx->base.tb, idx);
+    } else {
+        tcg_gen_movi_tl(hex_gpr[HEX_REG_PC], dest);
+        tcg_gen_lookup_and_goto_ptr();
+    }
+}
+
 static void gen_end_tb(DisasContext *ctx)
 {
     gen_exec_counters(ctx);
-    tcg_gen_exit_tb(NULL, 0);
+
+    if (ctx->branch_cond != TCG_COND_NEVER) {
+        if (ctx->branch_cond != TCG_COND_ALWAYS) {
+            TCGLabel *skip = gen_new_label();
+            tcg_gen_brcondi_tl(ctx->branch_cond, hex_branch_taken, 0, skip);
+            gen_goto_tb(ctx, 0, ctx->branch_dest);
+            gen_set_label(skip);
+            gen_goto_tb(ctx, 1, ctx->next_PC);
+        } else {
+            gen_goto_tb(ctx, 0, ctx->branch_dest);
+        }
+    } else {
+        tcg_gen_lookup_and_goto_ptr();
+    }
+
     ctx->base.is_jmp = DISAS_NORETURN;
 }
 
@@ -807,6 +838,7 @@ static void hexagon_tr_init_disas_context(DisasContextBase *dcbase,
     ctx->num_packets = 0;
     ctx->num_insns = 0;
     ctx->num_hvx_insns = 0;
+    ctx->branch_cond = TCG_COND_NEVER;
 }
 
 static void hexagon_tr_tb_start(DisasContextBase *db, CPUState *cpu)
diff --git a/target/hexagon/translate.h b/target/hexagon/translate.h
index 96509a4da7..aacf0b0921 100644
--- a/target/hexagon/translate.h
+++ b/target/hexagon/translate.h
@@ -57,6 +57,8 @@ typedef struct DisasContext {
     bool qreg_is_predicated[NUM_QREGS];
     int qreg_log_idx;
     bool pre_commit;
+    TCGCond branch_cond;
+    target_ulong branch_dest;
 } DisasContext;
 
 static inline void ctx_log_reg_write(DisasContext *ctx, int rnum)