plugins: extend execlog to filter matches

Sometimes the whole execlog is just two much so add the ability to
filter by instruction opcode or address.

[AJB: this shows for example

 qemu-system-aarch64 -display none -serial mon:stdio \
   -M virt -cpu max \
   -semihosting-config enable=on \
   -kernel ./tests/tcg/aarch64-softmmu/memory-sve \
   -plugin ./contrib/plugins/libexeclog.so,ifilter=st1w,afilter=0x40001808 -d plugin -D plugin.out

the st1w SVE instruction is not instrumenting its stores.]

Signed-off-by: Alex Bennée <alex.bennee@linaro.org>
Reviewed-by: Alexandre Iooss <erdnaxe@crans.org>
Cc: Robert Henry <robhenry@microsoft.com>
Cc: Aaron Lindsay <aaron@os.amperecomputing.com>
Message-Id: <20220929114231.583801-36-alex.bennee@linaro.org>

contrib/plugins/execlog.c

@@ -20,6 +20,9 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
 /* Store last executed instruction on each vCPU as a GString */
 GArray *last_exec;
 
+static GPtrArray *imatches;
+static GArray *amatches;
+
 /**
  * Add memory read or write information to current instruction log
  */
@@ -85,12 +88,13 @@ static void vcpu_insn_exec(unsigned int cpu_index, void *udata)
 static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
 {
     struct qemu_plugin_insn *insn;
-    uint64_t insn_vaddr;
-    uint32_t insn_opcode;
-    char *insn_disas;
+    bool skip = (imatches || amatches) ? true : false;
 
     size_t n = qemu_plugin_tb_n_insns(tb);
     for (size_t i = 0; i < n; i++) {
+        char *insn_disas;
+        uint64_t insn_vaddr;
+
         /*
          * `insn` is shared between translations in QEMU, copy needed data here.
          * `output` is never freed as it might be used multiple times during
@@ -99,9 +103,39 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
          * a limitation for CISC architectures.
          */
         insn = qemu_plugin_tb_get_insn(tb, i);
-        insn_vaddr = qemu_plugin_insn_vaddr(insn);
-        insn_opcode = *((uint32_t *)qemu_plugin_insn_data(insn));
         insn_disas = qemu_plugin_insn_disas(insn);
+        insn_vaddr = qemu_plugin_insn_vaddr(insn);
+
+        /*
+         * If we are filtering we better check out if we have any
+         * hits. The skip "latches" so we can track memory accesses
+         * after the instruction we care about.
+         */
+        if (skip && imatches) {
+            int j;
+            for (j = 0; j < imatches->len && skip; j++) {
+                char *m = g_ptr_array_index(imatches, j);
+                if (g_str_has_prefix(insn_disas, m)) {
+                    skip = false;
+                }
+            }
+        }
+
+        if (skip && amatches) {
+            int j;
+            for (j = 0; j < amatches->len && skip; j++) {
+                uint64_t v = g_array_index(amatches, uint64_t, j);
+                if (v == insn_vaddr) {
+                    skip = false;
+                }
+            }
+        }
+
+        if (skip) {
+            g_free(insn_disas);
+        } else {
+            uint32_t insn_opcode;
+            insn_opcode = *((uint32_t *)qemu_plugin_insn_data(insn));
             char *output = g_strdup_printf("0x%"PRIx64", 0x%"PRIx32", \"%s\"",
                                            insn_vaddr, insn_opcode, insn_disas);
 
@@ -114,6 +148,8 @@ static void vcpu_tb_trans(qemu_plugin_id_t id, struct qemu_plugin_tb *tb)
             qemu_plugin_register_vcpu_insn_exec_cb(insn, vcpu_insn_exec,
                                                    QEMU_PLUGIN_CB_NO_REGS, output);
         }
+
+    }
 }
 
 /**
@@ -132,6 +168,25 @@ static void plugin_exit(qemu_plugin_id_t id, void *p)
     }
 }
 
+/* Add a match to the array of matches */
+static void parse_insn_match(char *match)
+{
+    if (!imatches) {
+        imatches = g_ptr_array_new();
+    }
+    g_ptr_array_add(imatches, match);
+}
+
+static void parse_vaddr_match(char *match)
+{
+    uint64_t v = g_ascii_strtoull(match, NULL, 16);
+
+    if (!amatches) {
+        amatches = g_array_new(false, true, sizeof(uint64_t));
+    }
+    g_array_append_val(amatches, v);
+}
+
 /**
  * Install the plugin
  */
@@ -145,6 +200,19 @@ QEMU_PLUGIN_EXPORT int qemu_plugin_install(qemu_plugin_id_t id,
      */
     last_exec = g_array_new(FALSE, FALSE, sizeof(GString *));
 
+    for (int i = 0; i < argc; i++) {
+        char *opt = argv[i];
+        g_autofree char **tokens = g_strsplit(opt, "=", 2);
+        if (g_strcmp0(tokens[0], "ifilter") == 0) {
+            parse_insn_match(tokens[1]);
+        } else if (g_strcmp0(tokens[0], "afilter") == 0) {
+            parse_vaddr_match(tokens[1]);
+        } else {
+            fprintf(stderr, "option parsing failed: %s\n", opt);
+            return -1;
+        }
+    }
+
     /* Register translation block and exit callbacks */
     qemu_plugin_register_vcpu_tb_trans_cb(id, vcpu_tb_trans);
     qemu_plugin_register_atexit_cb(id, plugin_exit, NULL);

docs/devel/tcg-plugins.rst

@@ -346,7 +346,7 @@ The execlog tool traces executed instructions with memory access. It can be used
 for debugging and security analysis purposes.
 Please be aware that this will generate a lot of output.
 
-The plugin takes no argument::
+The plugin needs default argument::
 
   qemu-system-arm $(QEMU_ARGS) \
     -plugin ./contrib/plugins/libexeclog.so -d plugin
@@ -364,6 +364,13 @@ which will output an execution trace following this structure::
   0, 0xd34, 0xf9c8f000, "bl #0x10c8"
   0, 0x10c8, 0xfff96c43, "ldr r3, [r0, #0x44]", load, 0x200000e4, RAM
 
+the output can be filtered to only track certain instructions or
+addresses using the `ifilter` or `afilter` options. You can stack the
+arguments if required::
+
+  qemu-system-arm $(QEMU_ARGS) \
+    -plugin ./contrib/plugins/libexeclog.so,ifilter=st1w,afilter=0x40001808 -d plugin
+
 - contrib/plugins/cache.c
 
 Cache modelling plugin that measures the performance of a given L1 cache