tcg: add perfmap and jitdump

Add ability to dump /tmp/perf-<pid>.map and jit-<pid>.dump.
The first one allows the perf tool to map samples to each individual
translation block. The second one adds the ability to resolve symbol
names, line numbers and inspect JITed code.

Example of use:

    perf record qemu-x86_64 -perfmap ./a.out
    perf report

or

    perf record -k 1 qemu-x86_64 -jitdump ./a.out
    DEBUGINFOD_URLS= perf inject -j -i perf.data -o perf.data.jitted
    perf report -i perf.data.jitted

Co-developed-by: Vanderson M. do Rosario <vandersonmr2@gmail.com>
Co-developed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Ilya Leoshkevich <iii@linux.ibm.com>
Message-Id: <20230112152013.125680-4-iii@linux.ibm.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

1 files changed, 2 insertions, 0 deletions

diff --git a/tcg/tcg.c b/tcg/tcg.c
index da91779..9b7df71 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -61,6 +61,7 @@
 #include "exec/log.h"
 #include "tcg/tcg-ldst.h"
 #include "tcg-internal.h"
+#include "accel/tcg/perf.h"
 
 /* Forward declarations for functions declared in tcg-target.c.inc and
    used here. */
@@ -913,6 +914,7 @@ void tcg_prologue_init(TCGContext *s)
 #endif
 
     prologue_size = tcg_current_code_size(s);
+    perf_report_prologue(s->code_gen_ptr, prologue_size);
 
 #ifndef CONFIG_TCG_INTERPRETER
     flush_idcache_range((uintptr_t)tcg_splitwx_to_rx(s->code_buf),