trace: add some tcg tracing support

This adds a couple of tcg specific trace-events which are useful for
tracing execution though tcg generated blocks. It's been tested with
lttng user space tracing but is generic enough for all systems. The tcg
events are:

  * translate_block - when a subject block is translated
  * exec_tb - when a translated block is entered
  * exec_tb_exit - when we exit the translated code
  * exec_tb_nocache - special case translations

Of course we can only trace the entrance to the first block of a chain
as each block will jump directly to the next when it can. See the -d
nochain patch to allow more complete tracing at the expense of
performance.

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>

cpu-exec.c

@@ -18,6 +18,7 @@
  */
 #include "config.h"
 #include "cpu.h"
+#include "trace.h"
 #include "disas/disas.h"
 #include "tcg.h"
 #include "qemu/atomic.h"
@@ -168,6 +169,9 @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, uint8_t *tb_ptr)
 #endif /* DEBUG_DISAS */
 
     next_tb = tcg_qemu_tb_exec(env, tb_ptr);
+    trace_exec_tb_exit((void *) (next_tb & ~TB_EXIT_MASK),
+                       next_tb & TB_EXIT_MASK);
+
     if ((next_tb & TB_EXIT_MASK) > TB_EXIT_IDX1) {
         /* We didn't start executing this TB (eg because the instruction
          * counter hit zero); we must restore the guest PC to the address
@@ -208,6 +212,7 @@ static void cpu_exec_nocache(CPUArchState *env, int max_cycles,
                      max_cycles);
     cpu->current_tb = tb;
     /* execute the generated code */
+    trace_exec_tb_nocache(tb, tb->pc);
     cpu_tb_exec(cpu, tb->tc_ptr);
     cpu->current_tb = NULL;
     tb_phys_invalidate(tb, -1);
@@ -749,6 +754,7 @@ int cpu_exec(CPUArchState *env)
                 cpu->current_tb = tb;
                 barrier();
                 if (likely(!cpu->exit_request)) {
+                    trace_exec_tb(tb, tb->pc);
                     tc_ptr = tb->tc_ptr;
                     /* execute the generated code */
                     next_tb = cpu_tb_exec(cpu, tc_ptr);

trace-events

@@ -1265,6 +1265,15 @@ kvm_failed_spr_get(int str, const char *msg) "Warning: Unable to retrieve SPR %d
 kvm_failed_reg_get(uint64_t id, const char *msg) "Warning: Unable to retrieve ONEREG %" PRIu64 " from KVM: %s"
 kvm_failed_reg_set(uint64_t id, const char *msg) "Warning: Unable to set ONEREG %" PRIu64 " to KVM: %s"
 
+# TCG related tracing (mostly disabled by default)
+# cpu-exec.c
+disable exec_tb(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
+disable exec_tb_nocache(void *tb, uintptr_t pc) "tb:%p pc=0x%"PRIxPTR
+disable exec_tb_exit(void *next_tb, unsigned int flags) "tb:%p flags=%x"
+
+# translate-all.c
+translate_block(void *tb, uintptr_t pc, uint8_t *tb_code) "tb:%p, pc:0x%"PRIxPTR", tb_code:%p"
+
 # memory.c
 memory_region_ops_read(void *mr, uint64_t addr, uint64_t value, unsigned size) "mr %p addr %#"PRIx64" value %#"PRIx64" size %u"
 memory_region_ops_write(void *mr, uint64_t addr, uint64_t value, unsigned size) "mr %p addr %#"PRIx64" value %#"PRIx64" size %u"

translate-all.c

@@ -33,6 +33,7 @@
 #include "qemu-common.h"
 #define NO_CPU_IO_DEFS
 #include "cpu.h"
+#include "trace.h"
 #include "disas/disas.h"
 #include "tcg.h"
 #if defined(CONFIG_USER_ONLY)
@@ -158,6 +159,8 @@ int cpu_gen_code(CPUArchState *env, TranslationBlock *tb, int *gen_code_size_ptr
 
     gen_intermediate_code(env, tb);
 
+    trace_translate_block(tb, tb->pc, tb->tc_ptr);
+
     /* generate machine code */
     gen_code_buf = tb->tc_ptr;
     tb->tb_next_offset[0] = 0xffff;