@@ -259,6 +259,8 @@ typedef struct PCIHostDeviceAddress {
void tcg_exec_init(unsigned long tb_size);
bool tcg_enabled(void);
+void tb_enable_perfmap(void);
+
void cpu_exec_init_all(void);
/* CPU save/load. */
@@ -3348,6 +3348,16 @@ Dump json-encoded vmstate information for current machine type to file
in @var{file}
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
@@ -27,6 +27,7 @@
#include <stdio.h>
#include <string.h>
#include <inttypes.h>
+#include <glib.h>
#include "config.h"
@@ -129,6 +130,24 @@ 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;
+
+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 +203,7 @@ 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);
@@ -670,6 +690,12 @@ 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 /
@@ -118,6 +118,7 @@ int main(int argc, char **argv)
#include "qapi/opts-visitor.h"
#include "qom/object_interfaces.h"
#include "qapi-event.h"
+#include "qemu-common.h"
#define DEFAULT_RAM_SIZE 128
@@ -3385,6 +3386,9 @@ 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;
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 v3: - fix bracket for perf-map - find an include for the tb_enable_perfmap() declaration - checkpatch clean-ups