[Qemu-devel] Less interrupt overhead patch

[Torbjörn Andersson]

Hi all. 

I have been using QEMU for some time now and I have found that interrupts
cost more than necessary.

The TB-chaining is lost, at least partially, at the arrival of an interrupt.
These chain links are then recreated at some time in the future, with a
performance penalty.

My proposed solution is to skip unlinking TBs recursively and simply flag
that there is an interrupt request pending. Then we check interrupt flag in
goto_tb and skip jumping to the next TB. I think the code shows this change
quite well.

My experience is that this results in better overall performance. However, I
guess targets with very little interrupts will be somewhat slower.
Unfortunately, I have no structured measurements worth sending, so you will
have to do some tests on your own. If you find this patch not resulting in
improved overall performance, then please reply and explain why.

Regarding the code, I have done some small changes in all targets, but I
guess it's possible to isolate the change in tcg-op.h and exec. However, the
type name of the CPU state struct is not the same in all targets.

Signed-off-by: Torbjörn Anderson <address@hidden>

Index: target-arm/translate.c
===================================================================
--- target-arm/translate.c      (revision 5661)
+++ target-arm/translate.c      (working copy)
@@ -3376,7 +3376,14 @@
 
     tb = s->tb;
     if ((tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK)) {
+        uint32_t offset = offsetof(CPUARMState, interrupt_request);
+        TCGv tmp = new_tmp();
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        dead_tmp(tmp);
         tcg_gen_goto_tb(n);
+        gen_set_label(label);
         gen_set_pc_im(dest);
         tcg_gen_exit_tb((long)tb + n);
     } else {
Index: target-sh4/translate.c
===================================================================
--- target-sh4/translate.c      (revision 5661)
+++ target-sh4/translate.c      (working copy)
@@ -264,7 +264,14 @@
     if ((tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK) &&
        !ctx->singlestep_enabled) {
        /* Use a direct jump if in same page and singlestep not enabled */
+        uint32_t offset = offsetof(CPUState, interrupt_request);
+        TCGv tmp = tcg_temp_new(TCG_TYPE_I32);
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        tcg_temp_free(tmp);
         tcg_gen_goto_tb(n);
+        gen_set_label(label);
         tcg_gen_movi_i32(cpu_pc, dest);
         tcg_gen_exit_tb((long) tb + n);
     } else {
Index: exec.c
===================================================================
--- exec.c      (revision 5661)
+++ exec.c      (working copy)
@@ -1495,15 +1495,6 @@
             cpu_abort(env, "Raised interrupt while not in I/O function");
         }
 #endif
-    } else {
-        tb = env->current_tb;
-        /* if the cpu is currently executing code, we must unlink it and
-           all the potentially executing TB */
-        if (tb && !testandset(&interrupt_lock)) {
-            env->current_tb = NULL;
-            tb_reset_jump_recursive(tb);
-            resetlock(&interrupt_lock);
-        }
     }
 #endif
 }
Index: target-mips/translate.c
===================================================================
--- target-mips/translate.c     (revision 5661)
+++ target-mips/translate.c     (working copy)
@@ -2438,7 +2438,14 @@
     TranslationBlock *tb;
     tb = ctx->tb;
     if ((tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK)) {
+        uint32_t offset = offsetof(CPUState, interrupt_request);
+        TCGv tmp = tcg_temp_new(TCG_TYPE_I32);
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        tcg_temp_free(tmp);
         tcg_gen_goto_tb(n);
+        gen_set_label(label);
         gen_save_pc(dest);
         tcg_gen_exit_tb((long)tb + n);
     } else {
Index: target-m68k/translate.c
===================================================================
--- target-m68k/translate.c     (revision 5661)
+++ target-m68k/translate.c     (working copy)
@@ -876,7 +876,14 @@
         gen_exception(s, dest, EXCP_DEBUG);
     } else if ((tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK) ||
                (s->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK)) {
+        uint32_t offset = offsetof(CPUState, interrupt_request);
+        TCGv tmp = tcg_temp_new(TCG_TYPE_I32);
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        tcg_temp_free(tmp);
         tcg_gen_goto_tb(n);
+        gen_set_label(label);
         tcg_gen_movi_i32(QREG_PC, dest);
         tcg_gen_exit_tb((long)tb + n);
     } else {
Index: target-i386/translate.c
===================================================================
--- target-i386/translate.c     (revision 5661)
+++ target-i386/translate.c     (working copy)
@@ -2212,8 +2212,15 @@
     /* NOTE: we handle the case where the TB spans two pages here */
     if ((pc & TARGET_PAGE_MASK) == (tb->pc & TARGET_PAGE_MASK) ||
         (pc & TARGET_PAGE_MASK) == ((s->pc - 1) & TARGET_PAGE_MASK))  {
+        uint32_t offset = offsetof(CPUX86State, interrupt_request);
+        TCGv tmp = tcg_temp_new(TCG_TYPE_I32);
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        tcg_temp_free(tmp);
         /* jump to same page: we can use a direct jump */
         tcg_gen_goto_tb(tb_num);
+        gen_set_label(label);
         gen_jmp_im(eip);
         tcg_gen_exit_tb((long)tb + tb_num);
     } else {
Index: target-cris/translate.c
===================================================================
--- target-cris/translate.c     (revision 5663)
+++ target-cris/translate.c     (working copy)
@@ -643,7 +643,14 @@
        TranslationBlock *tb;
        tb = dc->tb;
        if ((tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK)) {
-               tcg_gen_goto_tb(n);
+        uint32_t offset = offsetof(CPUState, interrupt_request);
+        TCGv tmp = tcg_temp_new(TCG_TYPE_I32);
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        tcg_temp_free(tmp);
+           tcg_gen_goto_tb(n);
+        gen_set_label(label);
                tcg_gen_movi_tl(env_pc, dest);
                tcg_gen_exit_tb((long)tb + n);
        } else {
Index: target-sparc/translate.c
===================================================================
--- target-sparc/translate.c    (revision 5661)
+++ target-sparc/translate.c    (working copy)
@@ -226,7 +226,14 @@
     if ((pc & TARGET_PAGE_MASK) == (tb->pc & TARGET_PAGE_MASK) &&
         (npc & TARGET_PAGE_MASK) == (tb->pc & TARGET_PAGE_MASK))  {
         /* jump to same page: we can use a direct jump */
+        uint32_t offset = offsetof(CPUState, interrupt_request);
+        TCGv tmp = tcg_temp_new(TCG_TYPE_I32);
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        tcg_temp_free(tmp);
         tcg_gen_goto_tb(tb_num);
+        gen_set_label(label);
         tcg_gen_movi_tl(cpu_pc, pc);
         tcg_gen_movi_tl(cpu_npc, npc);
         tcg_gen_exit_tb((long)tb + tb_num);
Index: target-ppc/translate.c
===================================================================
--- target-ppc/translate.c      (revision 5661)
+++ target-ppc/translate.c      (working copy)
@@ -3463,7 +3463,14 @@
 #endif
     if ((tb->pc & TARGET_PAGE_MASK) == (dest & TARGET_PAGE_MASK) &&
         likely(!ctx->singlestep_enabled)) {
+        uint32_t offset = offsetof(CPUState, interrupt_request);
+        TCGv tmp = tcg_temp_new(TCG_TYPE_I32);
+        tcg_gen_ld_i32(tmp, cpu_env, offset);
+        int label = gen_new_label();
+        tcg_gen_brcondi_i32(TCG_COND_GT, tmp, 0, label);
+        tcg_temp_free(tmp);
         tcg_gen_goto_tb(n);
+        gen_set_label(label);
         tcg_gen_movi_tl(cpu_nip, dest & ~3);
         tcg_gen_exit_tb((long)tb + n);
     } else {