plugins: add inline operation per vcpu

Extends API with three new functions:
qemu_plugin_register_vcpu_{tb, insn, mem}_exec_inline_per_vcpu().

Those functions takes a qemu_plugin_u64 as input.

This allows to have a thread-safe and type-safe version of inline
operations.

Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Pierrick Bouvier <pierrick.bouvier@linaro.org>
Message-Id: <20240304130036.124418-5-pierrick.bouvier@linaro.org>
Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Message-Id: <20240305121005.3528075-18-alex.bennee@linaro.org>

7 files changed, 126 insertions, 2 deletions

diff --git a/accel/tcg/plugin-gen.c b/accel/tcg/plugin-gen.c
index 0f8be53..47e05ec 100644
--- a/accel/tcg/plugin-gen.c
+++ b/accel/tcg/plugin-gen.c
@@ -443,6 +443,13 @@ static TCGOp *append_inline_cb(const struct qemu_plugin_dyn_cb *cb,
     char *ptr = cb->userp;
     size_t elem_size = 0;
     size_t offset = 0;
+    if (!ptr) {
+        /* use inline entry */
+        ptr = cb->inline_insn.entry.score->data->data;
+        elem_size = g_array_get_element_size(cb->inline_insn.entry.score->data);
+        offset = cb->inline_insn.entry.offset;
+    }
+
     op = copy_ld_i32(&begin_op, op);
     op = copy_mul_i32(&begin_op, op, elem_size);
     op = copy_ext_i32_ptr(&begin_op, op);
diff --git a/include/qemu/plugin.h b/include/qemu/plugin.h
index bf96d2c..12a96ce 100644
--- a/include/qemu/plugin.h
+++ b/include/qemu/plugin.h
@@ -92,6 +92,7 @@ struct qemu_plugin_dyn_cb {
     /* fields specific to each dyn_cb type go here */
     union {
         struct {
+            qemu_plugin_u64 entry;
             enum qemu_plugin_op op;
             uint64_t imm;
         } inline_insn;
diff --git a/include/qemu/qemu-plugin.h b/include/qemu/qemu-plugin.h
index ebf9a64..6bbad06 100644
--- a/include/qemu/qemu-plugin.h
+++ b/include/qemu/qemu-plugin.h
@@ -329,6 +329,22 @@ void qemu_plugin_register_vcpu_tb_exec_inline(struct qemu_plugin_tb *tb,
                                               void *ptr, uint64_t imm);
 
 /**
+ * qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu() - execution inline op
+ * @tb: the opaque qemu_plugin_tb handle for the translation
+ * @op: the type of qemu_plugin_op (e.g. ADD_U64)
+ * @entry: entry to run op
+ * @imm: the op data (e.g. 1)
+ *
+ * Insert an inline op on a given scoreboard entry.
+ */
+QEMU_PLUGIN_API
+void qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+    struct qemu_plugin_tb *tb,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm);
+
+/**
  * qemu_plugin_register_vcpu_insn_exec_cb() - register insn execution cb
  * @insn: the opaque qemu_plugin_insn handle for an instruction
  * @cb: callback function
@@ -359,6 +375,22 @@ void qemu_plugin_register_vcpu_insn_exec_inline(struct qemu_plugin_insn *insn,
                                                 void *ptr, uint64_t imm);
 
 /**
+ * qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu() - insn exec inline op
+ * @insn: the opaque qemu_plugin_insn handle for an instruction
+ * @op: the type of qemu_plugin_op (e.g. ADD_U64)
+ * @entry: entry to run op
+ * @imm: the op data (e.g. 1)
+ *
+ * Insert an inline op to every time an instruction executes.
+ */
+QEMU_PLUGIN_API
+void qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm);
+
+/**
  * qemu_plugin_tb_n_insns() - query helper for number of insns in TB
  * @tb: opaque handle to TB passed to callback
  *
@@ -583,7 +615,24 @@ void qemu_plugin_register_vcpu_mem_inline(struct qemu_plugin_insn *insn,
                                           enum qemu_plugin_op op, void *ptr,
                                           uint64_t imm);
 
-
+/**
+ * qemu_plugin_register_vcpu_mem_inline_per_vcpu() - inline op for mem access
+ * @insn: handle for instruction to instrument
+ * @rw: apply to reads, writes or both
+ * @op: the op, of type qemu_plugin_op
+ * @entry: entry to run op
+ * @imm: immediate data for @op
+ *
+ * This registers a inline op every memory access generated by the
+ * instruction.
+ */
+QEMU_PLUGIN_API
+void qemu_plugin_register_vcpu_mem_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_mem_rw rw,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm);
 
 typedef void
 (*qemu_plugin_vcpu_syscall_cb_t)(qemu_plugin_id_t id, unsigned int vcpu_index,
diff --git a/plugins/api.c b/plugins/api.c
index fa1daee..6470f1d 100644
--- a/plugins/api.c
+++ b/plugins/api.c
@@ -111,6 +111,18 @@ void qemu_plugin_register_vcpu_tb_exec_inline(struct qemu_plugin_tb *tb,
     }
 }
 
+void qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu(
+    struct qemu_plugin_tb *tb,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm)
+{
+    if (!tb->mem_only) {
+        plugin_register_inline_op_on_entry(
+            &tb->cbs[PLUGIN_CB_INLINE], 0, op, entry, imm);
+    }
+}
+
 void qemu_plugin_register_vcpu_insn_exec_cb(struct qemu_plugin_insn *insn,
                                             qemu_plugin_vcpu_udata_cb_t cb,
                                             enum qemu_plugin_cb_flags flags,
@@ -136,6 +148,18 @@ void qemu_plugin_register_vcpu_insn_exec_inline(struct qemu_plugin_insn *insn,
     }
 }
 
+void qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm)
+{
+    if (!insn->mem_only) {
+        plugin_register_inline_op_on_entry(
+            &insn->cbs[PLUGIN_CB_INSN][PLUGIN_CB_INLINE], 0, op, entry, imm);
+    }
+}
+
 
 /*
  * We always plant memory instrumentation because they don't finalise until
@@ -148,7 +172,7 @@ void qemu_plugin_register_vcpu_mem_cb(struct qemu_plugin_insn *insn,
                                       void *udata)
 {
     plugin_register_vcpu_mem_cb(&insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_REGULAR],
-                                    cb, flags, rw, udata);
+                                cb, flags, rw, udata);
 }
 
 void qemu_plugin_register_vcpu_mem_inline(struct qemu_plugin_insn *insn,
@@ -160,6 +184,17 @@ void qemu_plugin_register_vcpu_mem_inline(struct qemu_plugin_insn *insn,
                               rw, op, ptr, imm);
 }
 
+void qemu_plugin_register_vcpu_mem_inline_per_vcpu(
+    struct qemu_plugin_insn *insn,
+    enum qemu_plugin_mem_rw rw,
+    enum qemu_plugin_op op,
+    qemu_plugin_u64 entry,
+    uint64_t imm)
+{
+    plugin_register_inline_op_on_entry(
+        &insn->cbs[PLUGIN_CB_MEM][PLUGIN_CB_INLINE], rw, op, entry, imm);
+}
+
 void qemu_plugin_register_vcpu_tb_trans_cb(qemu_plugin_id_t id,
                                            qemu_plugin_vcpu_tb_trans_cb_t cb)
 {
diff --git a/plugins/core.c b/plugins/core.c
index 65d5611..7852590 100644
--- a/plugins/core.c
+++ b/plugins/core.c
@@ -332,6 +332,23 @@ void plugin_register_inline_op(GArray **arr,
     dyn_cb->inline_insn.imm = imm;
 }
 
+void plugin_register_inline_op_on_entry(GArray **arr,
+                                        enum qemu_plugin_mem_rw rw,
+                                        enum qemu_plugin_op op,
+                                        qemu_plugin_u64 entry,
+                                        uint64_t imm)
+{
+    struct qemu_plugin_dyn_cb *dyn_cb;
+
+    dyn_cb = plugin_get_dyn_cb(arr);
+    dyn_cb->userp = NULL;
+    dyn_cb->type = PLUGIN_CB_INLINE;
+    dyn_cb->rw = rw;
+    dyn_cb->inline_insn.entry = entry;
+    dyn_cb->inline_insn.op = op;
+    dyn_cb->inline_insn.imm = imm;
+}
+
 void plugin_register_dyn_cb__udata(GArray **arr,
                                    qemu_plugin_vcpu_udata_cb_t cb,
                                    enum qemu_plugin_cb_flags flags,
@@ -480,6 +497,12 @@ void exec_inline_op(struct qemu_plugin_dyn_cb *cb, int cpu_index)
     char *ptr = cb->userp;
     size_t elem_size = 0;
     size_t offset = 0;
+    if (!ptr) {
+        /* use inline entry */
+        ptr = cb->inline_insn.entry.score->data->data;
+        elem_size = g_array_get_element_size(cb->inline_insn.entry.score->data);
+        offset = cb->inline_insn.entry.offset;
+    }
     uint64_t *val = (uint64_t *)(ptr + offset + cpu_index * elem_size);
 
     switch (cb->inline_insn.op) {
diff --git a/plugins/plugin.h b/plugins/plugin.h
index 3bf1aaf..f6fa10a 100644
--- a/plugins/plugin.h
+++ b/plugins/plugin.h
@@ -73,6 +73,12 @@ void plugin_register_inline_op(GArray **arr,
                                enum qemu_plugin_op op, void *ptr,
                                uint64_t imm);
 
+void plugin_register_inline_op_on_entry(GArray **arr,
+                                        enum qemu_plugin_mem_rw rw,
+                                        enum qemu_plugin_op op,
+                                        qemu_plugin_u64 entry,
+                                        uint64_t imm);
+
 void plugin_reset_uninstall(qemu_plugin_id_t id,
                             qemu_plugin_simple_cb_t cb,
                             bool reset);
diff --git a/plugins/qemu-plugins.symbols b/plugins/qemu-plugins.symbols
index 6204453..0d8141b 100644
--- a/plugins/qemu-plugins.symbols
+++ b/plugins/qemu-plugins.symbols
@@ -28,13 +28,16 @@
   qemu_plugin_register_vcpu_init_cb;
   qemu_plugin_register_vcpu_insn_exec_cb;
   qemu_plugin_register_vcpu_insn_exec_inline;
+  qemu_plugin_register_vcpu_insn_exec_inline_per_vcpu;
   qemu_plugin_register_vcpu_mem_cb;
   qemu_plugin_register_vcpu_mem_inline;
+  qemu_plugin_register_vcpu_mem_inline_per_vcpu;
   qemu_plugin_register_vcpu_resume_cb;
   qemu_plugin_register_vcpu_syscall_cb;
   qemu_plugin_register_vcpu_syscall_ret_cb;
   qemu_plugin_register_vcpu_tb_exec_cb;
   qemu_plugin_register_vcpu_tb_exec_inline;
+  qemu_plugin_register_vcpu_tb_exec_inline_per_vcpu;
   qemu_plugin_register_vcpu_tb_trans_cb;
   qemu_plugin_reset;
   qemu_plugin_scoreboard_free;