[Qemu-devel] [PATCH v2] cpu-exec: Do not invalidate original TB in cpu_exec_nocache()

[Sergey Fedorov]

Instead of invalidating an original TB in cpu_exec_nocache()
prematurely, just save a link to it in the temporary generated TB. If
cpu_io_recompile() is raised subsequently from the temporary TB,
invalidate the original one as well. That allows reusing the original TB
each time cpu_exec_nocache() is called to handle expired instruction
counter in icount mode.

Signed-off-by: Sergey Fedorov <address@hidden>
---

v2:
 * take tcg_ctx.tb_ctx.tb_invalidated_flag into account

 cpu-exec.c              | 8 ++------
 include/exec/exec-all.h | 2 ++
 translate-all.c         | 8 ++++++++
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/cpu-exec.c b/cpu-exec.c
index 2ffeb6e..f3468e8 100644
--- a/cpu-exec.c
+++ b/cpu-exec.c
@@ -231,19 +231,15 @@ static void cpu_exec_nocache(CPUArchState *env, int 
max_cycles,
 {
     CPUState *cpu = ENV_GET_CPU(env);
     TranslationBlock *tb;
-    target_ulong pc = orig_tb->pc;
-    target_ulong cs_base = orig_tb->cs_base;
-    uint64_t flags = orig_tb->flags;
 
     /* Should never happen.
        We only end up here when an existing TB is too long.  */
     if (max_cycles > CF_COUNT_MASK)
         max_cycles = CF_COUNT_MASK;
 
-    /* tb_gen_code can flush our orig_tb, invalidate it now */
-    tb_phys_invalidate(orig_tb, -1);
-    tb = tb_gen_code(cpu, pc, cs_base, flags,
+    tb = tb_gen_code(cpu, orig_tb->pc, orig_tb->cs_base, orig_tb->flags,
                      max_cycles | CF_NOCACHE);
+    tb->orig_tb = tcg_ctx.tb_ctx.tb_invalidated_flag ? NULL : orig_tb;
     cpu->current_tb = tb;
     /* execute the generated code */
     trace_exec_tb_nocache(tb, tb->pc);
diff --git a/include/exec/exec-all.h b/include/exec/exec-all.h
index 2573e8c..2aab8c3 100644
--- a/include/exec/exec-all.h
+++ b/include/exec/exec-all.h
@@ -155,6 +155,8 @@ struct TranslationBlock {
     void *tc_ptr;    /* pointer to the translated code */
     /* next matching tb for physical address. */
     struct TranslationBlock *phys_hash_next;
+    /* original tb when cflags has CF_NOCACHE */
+    struct TranslationBlock *orig_tb;
     /* first and second physical page containing code. The lower bit
        of the pointer tells the index in page_next[] */
     struct TranslationBlock *page_next[2];
diff --git a/translate-all.c b/translate-all.c
index b6b0e1c..5520f93 100644
--- a/translate-all.c
+++ b/translate-all.c
@@ -1532,6 +1532,14 @@ void cpu_io_recompile(CPUState *cpu, uintptr_t retaddr)
     cs_base = tb->cs_base;
     flags = tb->flags;
     tb_phys_invalidate(tb, -1);
+    if (tb->cflags & CF_NOCACHE) {
+        if (tb->orig_tb) {
+            /* Invalidate original TB if this TB was generated in
+             * cpu_exec_nocache() */
+            tb_phys_invalidate(tb->orig_tb, -1);
+        }
+        tb_free(tb);
+    }
     /* FIXME: In theory this could raise an exception.  In practice
        we have already translated the block once so it's probably ok.  */
     tb_gen_code(cpu, pc, cs_base, flags, cflags);
-- 
1.9.1