tcg: distribute tcg_time into TCG contexts
When we implemented per-vCPU TCG contexts, we forgot to also
distribute the tcg_time counter, which has remained as a global
accessed without any serialization, leading to potentially missed
counts.
Fix it by distributing the field over the TCG contexts, embedding
it into TCGProfile with a field called "cpu_exec_time", which is more
descriptive than "tcg_time". Add a function to query this value
directly, and for completeness, fill in the field in
tcg_profile_snapshot, even though its callers do not use it.
Signed-off-by: Emilio G. Cota <cota@braap.org>
Message-Id: <20181010144853.13005-5-cota@braap.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
diff --git a/tcg/tcg.h b/tcg/tcg.h
index d80ef2a..c59f254 100644
--- a/tcg/tcg.h
+++ b/tcg/tcg.h
@@ -629,6 +629,7 @@
QEMU_BUILD_BUG_ON(NB_OPS > (1 << 8));
typedef struct TCGProfile {
+ int64_t cpu_exec_time;
int64_t tb_count1;
int64_t tb_count;
int64_t op_count; /* total insn count */
@@ -1002,6 +1003,7 @@
#define tcg_check_temp_count() 0
#endif
+int64_t tcg_cpu_exec_time(void);
void tcg_dump_info(FILE *f, fprintf_function cpu_fprintf);
void tcg_dump_op_count(FILE *f, fprintf_function cpu_fprintf);
