1 files changed, 49 insertions, 10 deletions

diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c
index ec89a08..9920381 100644
--- a/accel/tcg/plugin-gen.c
+++ b/accel/tcg/plugin-gen.c
@@ -22,13 +22,12 @@
 #include "qemu/osdep.h"
 #include "qemu/plugin.h"
 #include "qemu/log.h"
-#include "cpu.h"
 #include "tcg/tcg.h"
 #include "tcg/tcg-temp-internal.h"
-#include "tcg/tcg-op.h"
-#include "exec/exec-all.h"
+#include "tcg/tcg-op-common.h"
 #include "exec/plugin-gen.h"
 #include "exec/translator.h"
+#include "exec/translation-block.h"
 
 enum plugin_gen_from {
     PLUGIN_GEN_FROM_TB,
@@ -89,32 +88,49 @@ static void gen_enable_mem_helper(struct qemu_plugin_tb *ptb,
     qemu_plugin_add_dyn_cb_arr(arr);
 
     tcg_gen_st_ptr(tcg_constant_ptr((intptr_t)arr), tcg_env,
-                   offsetof(CPUState, neg.plugin_mem_cbs) -
-                   offsetof(ArchCPU, env));
+                   offsetof(CPUState, neg.plugin_mem_cbs) - sizeof(CPUState));
 }
 
 static void gen_disable_mem_helper(void)
 {
     tcg_gen_st_ptr(tcg_constant_ptr(0), tcg_env,
-                   offsetof(CPUState, neg.plugin_mem_cbs) -
-                   offsetof(ArchCPU, env));
+                   offsetof(CPUState, neg.plugin_mem_cbs) - sizeof(CPUState));
 }
 
 static TCGv_i32 gen_cpu_index(void)
 {
+    /*
+     * Optimize when we run with a single vcpu. All values using cpu_index,
+     * including scoreboard index, will be optimized out.
+     * User-mode calls tb_flush when setting this flag. In system-mode, all
+     * vcpus are created before generating code.
+     */
+    if (!tcg_cflags_has(current_cpu, CF_PARALLEL)) {
+        return tcg_constant_i32(current_cpu->cpu_index);
+    }
     TCGv_i32 cpu_index = tcg_temp_ebb_new_i32();
     tcg_gen_ld_i32(cpu_index, tcg_env,
-                   -offsetof(ArchCPU, env) + offsetof(CPUState, cpu_index));
+                   offsetof(CPUState, cpu_index) - sizeof(CPUState));
     return cpu_index;
 }
 
 static void gen_udata_cb(struct qemu_plugin_regular_cb *cb)
 {
     TCGv_i32 cpu_index = gen_cpu_index();
+    enum qemu_plugin_cb_flags cb_flags =
+        tcg_call_to_qemu_plugin_cb_flags(cb->info->flags);
+    TCGv_i32 flags = tcg_constant_i32(cb_flags);
+    TCGv_i32 clear_flags = tcg_constant_i32(QEMU_PLUGIN_CB_NO_REGS);
+    tcg_gen_st_i32(flags, tcg_env,
+           offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
     tcg_gen_call2(cb->f.vcpu_udata, cb->info, NULL,
                   tcgv_i32_temp(cpu_index),
                   tcgv_ptr_temp(tcg_constant_ptr(cb->userp)));
+    tcg_gen_st_i32(clear_flags, tcg_env,
+           offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
     tcg_temp_free_i32(cpu_index);
+    tcg_temp_free_i32(flags);
+    tcg_temp_free_i32(clear_flags);
 }
 
 static TCGv_ptr gen_plugin_u64_ptr(qemu_plugin_u64 entry)
@@ -167,10 +183,20 @@ static void gen_udata_cond_cb(struct qemu_plugin_conditional_cb *cb)
     tcg_gen_ld_i64(val, ptr, 0);
     tcg_gen_brcondi_i64(cond, val, cb->imm, after_cb);
     TCGv_i32 cpu_index = gen_cpu_index();
+    enum qemu_plugin_cb_flags cb_flags =
+        tcg_call_to_qemu_plugin_cb_flags(cb->info->flags);
+    TCGv_i32 flags = tcg_constant_i32(cb_flags);
+    TCGv_i32 clear_flags = tcg_constant_i32(QEMU_PLUGIN_CB_NO_REGS);
+    tcg_gen_st_i32(flags, tcg_env,
+           offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
     tcg_gen_call2(cb->f.vcpu_udata, cb->info, NULL,
                   tcgv_i32_temp(cpu_index),
                   tcgv_ptr_temp(tcg_constant_ptr(cb->userp)));
+    tcg_gen_st_i32(clear_flags, tcg_env,
+           offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
     tcg_temp_free_i32(cpu_index);
+    tcg_temp_free_i32(flags);
+    tcg_temp_free_i32(clear_flags);
     gen_set_label(after_cb);
 
     tcg_temp_free_i64(val);
@@ -204,12 +230,22 @@ static void gen_mem_cb(struct qemu_plugin_regular_cb *cb,
                        qemu_plugin_meminfo_t meminfo, TCGv_i64 addr)
 {
     TCGv_i32 cpu_index = gen_cpu_index();
+    enum qemu_plugin_cb_flags cb_flags =
+        tcg_call_to_qemu_plugin_cb_flags(cb->info->flags);
+    TCGv_i32 flags = tcg_constant_i32(cb_flags);
+    TCGv_i32 clear_flags = tcg_constant_i32(QEMU_PLUGIN_CB_NO_REGS);
+    tcg_gen_st_i32(flags, tcg_env,
+           offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
     tcg_gen_call4(cb->f.vcpu_mem, cb->info, NULL,
                   tcgv_i32_temp(cpu_index),
                   tcgv_i32_temp(tcg_constant_i32(meminfo)),
                   tcgv_i64_temp(addr),
                   tcgv_ptr_temp(tcg_constant_ptr(cb->userp)));
+    tcg_gen_st_i32(clear_flags, tcg_env,
+           offsetof(CPUState, neg.plugin_cb_flags) - sizeof(CPUState));
     tcg_temp_free_i32(cpu_index);
+    tcg_temp_free_i32(flags);
+    tcg_temp_free_i32(clear_flags);
 }
 
 static void inject_cb(struct qemu_plugin_dyn_cb *cb)
@@ -251,7 +287,6 @@ static void inject_mem_cb(struct qemu_plugin_dyn_cb *cb,
         break;
     default:
         g_assert_not_reached();
-        break;
     }
 }
 
@@ -276,7 +311,7 @@ static void plugin_gen_inject(struct qemu_plugin_tb *plugin_tb)
      * that might be live within the existing opcode stream.
      * The simplest solution is to release them all and create new.
      */
-    memset(tcg_ctx->free_temps, 0, sizeof(tcg_ctx->free_temps));
+    tcg_temp_ebb_reset_freed(tcg_ctx);
 
     QTAILQ_FOREACH_SAFE(op, &tcg_ctx->ops, link, next) {
         switch (op->opc) {
@@ -468,4 +503,8 @@ void plugin_gen_tb_end(CPUState *cpu, size_t num_insns)
 
     /* inject the instrumentation at the appropriate places */
     plugin_gen_inject(ptb);
+
+    /* reset plugin translation state (plugin_tb is reused between blocks) */
+    tcg_ctx->plugin_db = NULL;
+    tcg_ctx->plugin_insn = NULL;
 }