[Qemu-devel] [PATCH] tcg: add ability to dump /tmp/perf-<pid>.map files

["Alex Bennée" <alex.bennee@linaro.org>]

This allows the perf tool to map samples to each individual translation
block. This could be expanded for user space but currently it gives
enough information to find any hotblocks by other means.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>

---

v2:
  - hoist up into translate-all.c
  - don't use pointless glib wrappers
  - use proper format types for portability
  - mark prologue/epilog area
  - rebase
---
 qemu-options.hx | 10 ++++++++++
 translate-all.c | 27 +++++++++++++++++++++++++++
 vl.c            |  6 ++++++
 3 files changed, 43 insertions(+)

diff --git a/qemu-options.hx b/qemu-options.hx
index c2c0823..b8c81e3 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -3220,6 +3220,16 @@ STEXI
 prepend a timestamp to each log message.(default:on)
 ETEXI
 
+DEF("perfmap", 0, QEMU_OPTION_PERFMAP, \
+    "-perfmap        generate a /tmp/perf-${pid}.map file for perf\n",
+    QEMU_ARCH_ALL)
+STEXI
+@item -perfmap
+@findex -perfmap
+This will cause QEMU to generate a map file for Linux perf tools that will allow
+basic profiling information to be broken down into basic blocks.
+ETEXI
+
 HXCOMM This is the last statement. Insert new options before this line!
 STEXI
 @end table
diff --git a/translate-all.c b/translate-all.c
index 5549a85..0c7cbbe 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -27,6 +27,7 @@
 #include <stdio.h>
 #include <string.h>
 #include <inttypes.h>
+#include <glib.h>
 
 #include "config.h"
 
@@ -129,6 +130,25 @@ static void tb_link_page(TranslationBlock *tb, tb_page_addr_t phys_pc,
                          tb_page_addr_t phys_page2);
 static TranslationBlock *tb_find_pc(uintptr_t tc_ptr);
 
+static FILE *tb_perfmap = NULL;
+/* if I could put this in a header easily.... */
+void tb_enable_perfmap(void);
+
+void tb_enable_perfmap(void) {
+    gchar * map_file = g_strdup_printf("/tmp/perf-%d.map", getpid());
+    tb_perfmap = fopen(map_file, "w");
+    g_free(map_file);
+}
+
+static void tb_write_perfmap(tcg_insn_unit *start, int size, target_ulong pc)
+{
+    if (tb_perfmap) {
+        fprintf(tb_perfmap,
+                "%"PRIxPTR" %x subject-"TARGET_FMT_lx"\n",
+                (uintptr_t) start, size, pc);
+    }
+}
+
 void cpu_gen_init(void)
 {
     tcg_context_init(&tcg_ctx); 
@@ -184,6 +204,7 @@ int cpu_gen_code(CPUArchState *env, TranslationBlock *tb, int *gen_code_size_ptr
     s->code_out_len += gen_code_size;
 #endif
 
+    tb_write_perfmap(gen_code_buf, gen_code_size, tb->pc);
 #ifdef DEBUG_DISAS
     if (qemu_loglevel_mask(CPU_LOG_TB_OUT_ASM)) {
         qemu_log("OUT: [size=%d]\n", gen_code_size);
@@ -584,6 +605,12 @@ static inline void code_gen_alloc(size_t tb_size)
             tcg_ctx.code_gen_buffer_size - 1024;
     tcg_ctx.code_gen_buffer_size -= 1024;
 
+    if (tb_perfmap) {
+        fprintf(tb_perfmap,
+                "%"PRIxPTR" %x tcg-prologue-buffer\n",
+                (uintptr_t) tcg_ctx.code_gen_prologue, 1024);
+    }
+
     tcg_ctx.code_gen_buffer_max_size = tcg_ctx.code_gen_buffer_size -
         (TCG_MAX_OP_SIZE * OPC_BUF_SIZE);
     tcg_ctx.code_gen_max_blocks = tcg_ctx.code_gen_buffer_size /
diff --git a/vl.c b/vl.c
index d8c1572..7650ec8 100644
--- a/vl.c
+++ b/vl.c
@@ -118,6 +118,9 @@ int main(int argc, char **argv)
 #include "qapi/string-input-visitor.h"
 #include "qom/object_interfaces.h"
 
+/* Not sure where the best place for this is? */
+extern void tb_enable_perfmap(void);
+
 #define DEFAULT_RAM_SIZE 128
 
 #define MAX_VIRTIO_CONSOLES 1
@@ -3387,6 +3390,9 @@ int main(int argc, char **argv, char **envp)
             case QEMU_OPTION_D:
                 log_file = optarg;
                 break;
+            case QEMU_OPTION_PERFMAP:
+                tb_enable_perfmap();
+                break;
             case QEMU_OPTION_s:
                 add_device_config(DEV_GDB, "tcp::" DEFAULT_GDBSTUB_PORT);
                 break;
-- 
2.0.1