[PATCH v5 46/55] plugin: add qemu_plugin_insn_disas helper

[Alex Bennée]

Give the plugins access to the QEMU dissasembler so they don't have to
re-invent the wheel. We generate a warning when there are spare bytes
in the decode buffer. This is usually due to the front end loading in
more bytes than decoded.

Signed-off-by: Alex Bennée <address@hidden>
Reviewed-by: Richard Henderson <address@hidden>

---
v5
  - fix plugin_printf to use vprintf with va
  - use __thread storage for string
  - only decode single instruction for bfd case
  - don't assert, warn_report when we have spare bytes in insn buffer
---
 disas.c                      | 110 +++++++++++++++++++++++++++++++++++
 include/disas/disas.h        |   2 +
 include/qemu/qemu-plugin.h   |   9 +++
 plugins/api.c                |   7 +++
 plugins/qemu-plugins.symbols |   1 +
 5 files changed, 129 insertions(+)

diff --git a/disas.c b/disas.c
index 3e2bfa572b..02f68e92ab 100644
--- a/disas.c
+++ b/disas.c
@@ -418,6 +418,7 @@ static bool cap_disas_monitor(disassemble_info *info, 
uint64_t pc, int count)
 # define cap_disas_target(i, p, s)  false
 # define cap_disas_host(i, p, s)  false
 # define cap_disas_monitor(i, p, c)  false
+# define cap_disas_plugin(i, p, c) false
 #endif /* CONFIG_CAPSTONE */
 
 /* Disassemble this for me please... (debugging).  */
@@ -475,6 +476,115 @@ void target_disas(FILE *out, CPUState *cpu, target_ulong 
code,
     }
 }
 
+static __thread GString plugin_disas_output;
+
+static int plugin_printf(FILE *stream, const char *fmt, ...)
+{
+    va_list va;
+    GString *s = &plugin_disas_output;
+    int initial_len = s->len;
+
+    va_start(va, fmt);
+    g_string_append_vprintf(s, fmt, va);
+    va_end(va);
+
+    return s->len - initial_len;
+}
+
+static void plugin_print_address(bfd_vma addr, struct disassemble_info *info)
+{
+    /* does nothing */
+}
+
+
+#ifdef CONFIG_CAPSTONE
+/* Disassemble a single instruction directly into plugin output */
+static
+bool cap_disas_plugin(disassemble_info *info, uint64_t pc, size_t size)
+{
+    uint8_t cap_buf[1024];
+    csh handle;
+    cs_insn *insn;
+    size_t csize = 0;
+    int count;
+    GString *s = &plugin_disas_output;
+
+    if (cap_disas_start(info, &handle) != CS_ERR_OK) {
+        return false;
+    }
+    insn = cap_insn;
+
+    size_t tsize = MIN(sizeof(cap_buf) - csize, size);
+    const uint8_t *cbuf = cap_buf;
+    target_read_memory(pc, cap_buf, tsize, info);
+
+    count = cs_disasm(handle, cbuf, size, 0, 1, &insn);
+
+    if (count) {
+        g_string_printf(s, "%s %s", insn->mnemonic, insn->op_str);
+    } else {
+        g_string_printf(s, "cs_disasm failed");
+    }
+
+    cs_close(&handle);
+    return true;
+}
+#endif
+
+/*
+ * We should only be dissembling one instruction at a time here. If
+ * there is left over it usually indicates the front end has read more
+ * bytes than it needed.
+ */
+char * plugin_disas(CPUState *cpu, uint64_t addr, size_t size)
+{
+    CPUClass *cc = CPU_GET_CLASS(cpu);
+    int count;
+    CPUDebug s;
+    GString *ds = g_string_set_size(&plugin_disas_output, 0);
+
+    g_assert(ds == &plugin_disas_output);
+
+    INIT_DISASSEMBLE_INFO(s.info, NULL, plugin_printf);
+
+    s.cpu = cpu;
+    s.info.read_memory_func = target_read_memory;
+    s.info.buffer_vma = addr;
+    s.info.buffer_length = size;
+    s.info.print_address_func = plugin_print_address;
+    s.info.cap_arch = -1;
+    s.info.cap_mode = 0;
+    s.info.cap_insn_unit = 4;
+    s.info.cap_insn_split = 4;
+
+#ifdef TARGET_WORDS_BIGENDIAN
+    s.info.endian = BFD_ENDIAN_BIG;
+#else
+    s.info.endian = BFD_ENDIAN_LITTLE;
+#endif
+
+    if (cc->disas_set_info) {
+        cc->disas_set_info(cpu, &s.info);
+    }
+
+    if (s.info.cap_arch >= 0 && cap_disas_plugin(&s.info, addr, size)) {
+        return g_strdup(ds->str);
+    }
+
+    if (s.info.print_insn == NULL) {
+        s.info.print_insn = print_insn_od_target;
+    }
+
+    count = s.info.print_insn(addr, &s.info);
+
+    /* The decoder probably read more than it needed it's not critical */
+    if (count < size) {
+        warn_report("%s: %zu bytes left over\n", __func__, size - count);
+    }
+
+    return g_strdup(ds->str);
+}
+
 /* Disassemble this for me please... (debugging). */
 void disas(FILE *out, void *code, unsigned long size)
 {
diff --git a/include/disas/disas.h b/include/disas/disas.h
index ba47e9197c..8481d4a8b3 100644
--- a/include/disas/disas.h
+++ b/include/disas/disas.h
@@ -14,6 +14,8 @@ void target_disas(FILE *out, CPUState *cpu, target_ulong code,
 void monitor_disas(Monitor *mon, CPUState *cpu,
                    target_ulong pc, int nb_insn, int is_physical);
 
+char * plugin_disas(CPUState *cpu, uint64_t addr, size_t size);
+
 /* Look up symbol for debugging purpose.  Returns "" if unknown. */
 const char *lookup_symbol(target_ulong orig_addr);
 #endif
diff --git a/include/qemu/qemu-plugin.h b/include/qemu/qemu-plugin.h
index d9c1ca3b4c..8b403dd615 100644
--- a/include/qemu/qemu-plugin.h
+++ b/include/qemu/qemu-plugin.h
@@ -324,6 +324,15 @@ qemu_plugin_register_vcpu_syscall_ret_cb(qemu_plugin_id_t 
id,
                                          qemu_plugin_vcpu_syscall_ret_cb_t cb);
 
 
+/**
+ * qemu_plugin_insn_disas() - return disassembly string for instruction
+ * @insn: instruction reference
+ *
+ * Returns an allocated string containing the disassembly
+ */
+
+char * qemu_plugin_insn_disas(const struct qemu_plugin_insn *insn);
+
 /**
  * qemu_plugin_vcpu_for_each() - iterate over the existing vCPU
  * @id: plugin ID
diff --git a/plugins/api.c b/plugins/api.c
index fbacd78df6..a9fa229369 100644
--- a/plugins/api.c
+++ b/plugins/api.c
@@ -40,6 +40,7 @@
 #include "sysemu/sysemu.h"
 #include "tcg/tcg.h"
 #include "exec/exec-all.h"
+#include "disas/disas.h"
 #include "plugin.h"
 #ifndef CONFIG_USER_ONLY
 #include "hw/boards.h"
@@ -211,6 +212,12 @@ void *qemu_plugin_insn_haddr(const struct qemu_plugin_insn 
*insn)
     return insn->haddr;
 }
 
+char *qemu_plugin_insn_disas(const struct qemu_plugin_insn *insn)
+{
+    CPUState *cpu = current_cpu;
+    return plugin_disas(cpu, insn->vaddr, insn->data->len);
+}
+
 /*
  * The memory queries allow the plugin to query information about a
  * memory access.
diff --git a/plugins/qemu-plugins.symbols b/plugins/qemu-plugins.symbols
index 40c0d1abd2..267ec381b4 100644
--- a/plugins/qemu-plugins.symbols
+++ b/plugins/qemu-plugins.symbols
@@ -25,6 +25,7 @@
   qemu_plugin_insn_size;
   qemu_plugin_insn_vaddr;
   qemu_plugin_insn_haddr;
+  qemu_plugin_insn_disas;
   qemu_plugin_mem_size_shift;
   qemu_plugin_mem_is_sign_extended;
   qemu_plugin_mem_is_big_endian;
-- 
2.20.1