Re: [PATCH v12 02/15] accel: collecting TB execution count

[Richard Henderson]

On 5/18/23 06:57, Fei Wu wrote:
> +void HELPER(inc_exec_freq)(void *ptr)
> +{
> +    TBStatistics *stats = (TBStatistics *) ptr;
> +    tcg_debug_assert(stats);
> +    ++stats->executions.normal;
> +}
...
> +static inline void gen_tb_exec_count(TranslationBlock *tb)
> +{
> +    if (tb_stats_enabled(tb, TB_EXEC_STATS)) {
> +        TCGv_ptr ptr = tcg_temp_new_ptr();
> +        tcg_gen_movi_ptr(ptr, (intptr_t)tb->tb_stats);
> +        gen_helper_inc_exec_freq(ptr);
> +    }
> +}

This is 3 host instructions, easily expanded inline:

--- a/accel/tcg/translator.c
+++ b/accel/tcg/translator.c
@@ -11,6 +11,7 @@
 #include "qemu/error-report.h"
 #include "tcg/tcg.h"
 #include "tcg/tcg-op.h"
+#include "tcg/tcg-temp-internal.h"
 #include "exec/exec-all.h"
 #include "exec/gen-icount.h"
 #include "exec/log.h"
@@ -18,6 +19,30 @@
 #include "exec/plugin-gen.h"
 #include "exec/replay-core.h"

+
+static void gen_tb_exec_count(TranslationBlock *tb)
+{
+    if (tb_stats_enabled(tb, TB_EXEC_STATS)) {
+        TCGv_ptr ptr = tcg_temp_ebb_new_ptr();
+
+        tcg_gen_movi_ptr(ptr, (intptr_t)&tb->tb_stats->executions.normal);
+        if (sizeof(tb->tb_stats->executions.normal) == 4) {
+            TCGv_i32 t = tcg_temp_ebb_new_i32();
+            tcg_gen_ld_i32(t, ptr, 0);
+            tcg_gen_addi_i32(t, t, 1);
+            tcg_gen_st_i32(t, ptr, 0);
+            tcg_temp_free_i32(t);
+        } else {
+            TCGv_i64 t = tcg_temp_ebb_new_i64();
+            tcg_gen_ld_i64(t, ptr, 0);
+            tcg_gen_addi_i64(t, t, 1);
+            tcg_gen_st_i64(t, ptr, 0);
+            tcg_temp_free_i64(t);
+        }
+        tcg_temp_free_ptr(ptr);
+    }
+}
+
 bool translator_use_goto_tb(DisasContextBase *db, target_ulong dest)
 {
     /* Suppress goto_tb if requested. */


I'm not expecially keen on embedding the TBStatistics pointer directly like this; for most 
hosts we will have to put this constant into the constant pool.  Whereas the pointer 
already exists at tb->tb_stats, and tb is at a constant displacement prior to the code, so 
we already have mechanisms for generating pc-relative addresses.

However, that's premature optimization.  Let's get it working first.


r~