Add backtrace support for error reporting

Add some support for automatically showing backtraces in certain error
situations in the server.  Backtraces are shown on assertion failure;
also, a new setting backtrace_functions can be set to a list of C
function names, and all ereport()s and elog()s from the mentioned
functions will have backtraces generated.  Finally, the function
errbacktrace() can be manually added to an ereport() call to generate a
backtrace for that call.

Authors: Peter Eisentraut, Álvaro Herrera
Discussion: https://postgr.es/m//5f48cb47-bf1e-05b6-7aae-3bf2cd01586d@2ndquadrant.com
Discussion: https://postgr.es/m/CAMsr+YGL+yfWE=JvbUbnpWtrRZNey7hJ07+zT4bYJdVp4Szdrg@mail.gmail.com

Author: alvherre

configure

@@ -11607,6 +11607,63 @@ if test "$ac_res" != no; then :
 
 fi
 
+# *BSD:
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for library containing backtrace_symbols" >&5
+$as_echo_n "checking for library containing backtrace_symbols... " >&6; }
+if ${ac_cv_search_backtrace_symbols+:} false; then :
+  $as_echo_n "(cached) " >&6
+else
+  ac_func_search_save_LIBS=$LIBS
+cat confdefs.h - <<_ACEOF >conftest.$ac_ext
+/* end confdefs.h.  */
+
+/* Override any GCC internal prototype to avoid an error.
+   Use char because int might match the return type of a GCC
+   builtin and then its argument prototype would still apply.  */
+#ifdef __cplusplus
+extern "C"
+#endif
+char backtrace_symbols ();
+int
+main ()
+{
+return backtrace_symbols ();
+  ;
+  return 0;
+}
+_ACEOF
+for ac_lib in '' execinfo; do
+  if test -z "$ac_lib"; then
+    ac_res="none required"
+  else
+    ac_res=-l$ac_lib
+    LIBS="-l$ac_lib  $ac_func_search_save_LIBS"
+  fi
+  if ac_fn_c_try_link "$LINENO"; then :
+  ac_cv_search_backtrace_symbols=$ac_res
+fi
+rm -f core conftest.err conftest.$ac_objext \
+    conftest$ac_exeext
+  if ${ac_cv_search_backtrace_symbols+:} false; then :
+  break
+fi
+done
+if ${ac_cv_search_backtrace_symbols+:} false; then :
+
+else
+  ac_cv_search_backtrace_symbols=no
+fi
+rm conftest.$ac_ext
+LIBS=$ac_func_search_save_LIBS
+fi
+{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $ac_cv_search_backtrace_symbols" >&5
+$as_echo "$ac_cv_search_backtrace_symbols" >&6; }
+ac_res=$ac_cv_search_backtrace_symbols
+if test "$ac_res" != no; then :
+  test "$ac_res" = "none required" || LIBS="$ac_res $LIBS"
+
+fi
+
 
 if test "$with_readline" = yes; then
 
@@ -12705,7 +12762,7 @@ $as_echo "#define HAVE_STDBOOL_H 1" >>confdefs.h
 fi
 
 
-for ac_header in atomic.h copyfile.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h mbarrier.h poll.h sys/epoll.h sys/ipc.h sys/prctl.h sys/procctl.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/sockio.h sys/tas.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h
+for ac_header in atomic.h copyfile.h execinfo.h fp_class.h getopt.h ieeefp.h ifaddrs.h langinfo.h mbarrier.h poll.h sys/epoll.h sys/ipc.h sys/prctl.h sys/procctl.h sys/pstat.h sys/resource.h sys/select.h sys/sem.h sys/shm.h sys/sockio.h sys/tas.h sys/un.h termios.h ucred.h utime.h wchar.h wctype.h
 do :
   as_ac_Header=`$as_echo "ac_cv_header_$ac_header" | $as_tr_sh`
 ac_fn_c_check_header_mongrel "$LINENO" "$ac_header" "$as_ac_Header" "$ac_includes_default"
@@ -14935,7 +14992,7 @@ fi
 LIBS_including_readline="$LIBS"
 LIBS=`echo "$LIBS" | sed -e 's/-ledit//g' -e 's/-lreadline//g'`
 
-for ac_func in cbrt clock_gettime copyfile fdatasync getifaddrs getpeerucred getrlimit mbstowcs_l memset_s memmove poll posix_fallocate ppoll pstat pthread_is_threaded_np readlink setproctitle setproctitle_fast setsid shm_open strchrnul strsignal symlink sync_file_range uselocale utime utimes wcstombs_l
+for ac_func in backtrace_symbols cbrt clock_gettime copyfile fdatasync getifaddrs getpeerucred getrlimit mbstowcs_l memset_s memmove poll posix_fallocate ppoll pstat pthread_is_threaded_np readlink setproctitle setproctitle_fast setsid shm_open strchrnul strsignal symlink sync_file_range uselocale utime utimes wcstombs_l
 do :
   as_ac_var=`$as_echo "ac_cv_func_$ac_func" | $as_tr_sh`
 ac_fn_c_check_func "$LINENO" "$ac_func" "$as_ac_var"

configure.in

@@ -1133,6 +1133,8 @@ AC_SEARCH_LIBS(sched_yield, rt)
 AC_SEARCH_LIBS(gethostbyname_r, nsl)
 # Cygwin:
 AC_SEARCH_LIBS(shmget, cygipc)
+# *BSD:
+AC_SEARCH_LIBS(backtrace_symbols, execinfo)
 
 if test "$with_readline" = yes; then
   PGAC_CHECK_READLINE
@@ -1275,6 +1277,7 @@ AC_HEADER_STDBOOL
 AC_CHECK_HEADERS(m4_normalize([
 	atomic.h
 	copyfile.h
+	execinfo.h
 	fp_class.h
 	getopt.h
 	ieeefp.h
@@ -1608,6 +1611,7 @@ LIBS_including_readline="$LIBS"
 LIBS=`echo "$LIBS" | sed -e 's/-ledit//g' -e 's/-lreadline//g'`
 
 AC_CHECK_FUNCS(m4_normalize([
+	backtrace_symbols
 	cbrt
 	clock_gettime
 	copyfile

doc/src/sgml/config.sgml

@@ -9489,6 +9489,32 @@ dynamic_library_path = 'C:\tools\postgresql;H:\my_project\lib;$libdir'
       </listitem>
      </varlistentry>
 
+     <varlistentry id="guc-backtrace-functions" xreflabel="backtrace_functions">
+      <term><varname>backtrace_functions</varname> (<type>string</type>)
+      <indexterm>
+        <primary><varname>backtrace_functions</varname> configuration parameter</primary>
+      </indexterm>
+      </term>
+      <listitem>
+       <para>
+        This parameter contains a comma-separated list of C function names.
+        If an error is raised and the name of the internal C function where
+        the error happens matches a value in the list, then a backtrace is
+        written to the server log together with the error message.  This can
+        be used to debug specific areas of the source code.
+       </para>
+
+       <para>
+        Backtrace support is not available on all platforms, and the quality
+        of the backtraces depends on compilation options.
+       </para>
+
+       <para>
+        This parameter can only be set by superusers.
+       </para>
+      </listitem>
+     </varlistentry>
+
      <varlistentry id="guc-ignore-system-indexes" xreflabel="ignore_system_indexes">
       <term><varname>ignore_system_indexes</varname> (<type>boolean</type>)
       <indexterm>

src/backend/utils/error/assert.c

@@ -18,6 +18,9 @@
 #include "postgres.h"
 
 #include <unistd.h>
+#ifdef HAVE_EXECINFO_H
+#include <execinfo.h>
+#endif
 
 /*
  * ExceptionalCondition - Handles the failure of an Assert()
@@ -42,6 +45,16 @@ ExceptionalCondition(const char *conditionName,
 	/* Usually this shouldn't be needed, but make sure the msg went out */
 	fflush(stderr);
 
+#ifdef HAVE_BACKTRACE_SYMBOLS
+	{
+		void	   *buf[100];
+		int			nframes;
+
+		nframes = backtrace(buf, lengthof(buf));
+		backtrace_symbols_fd(buf, nframes, fileno(stderr));
+	}
+#endif
+
 #ifdef SLEEP_ON_ASSERT
 
 	/*

src/backend/utils/error/elog.c

@@ -62,6 +62,9 @@
 #ifdef HAVE_SYSLOG
 #include <syslog.h>
 #endif
+#ifdef HAVE_EXECINFO_H
+#include <execinfo.h>
+#endif
 
 #include "access/transam.h"
 #include "access/xact.h"
@@ -167,6 +170,7 @@ static char formatted_log_time[FORMATTED_TS_LEN];
 
 
 static const char *err_gettext(const char *str) pg_attribute_format_arg(1);
+static pg_noinline void set_backtrace(ErrorData *edata, int num_skip);
 static void set_errdata_field(MemoryContextData *cxt, char **ptr, const char *str);
 static void write_console(const char *line, int len);
 static void setup_formatted_log_time(void);
@@ -398,6 +402,32 @@ errstart(int elevel, const char *filename, int lineno,
 	return true;
 }
 
+/*
+ * Checks whether the given funcname matches backtrace_functions; see
+ * check_backtrace_functions.
+ */
+static bool
+matches_backtrace_functions(const char *funcname)
+{
+	char	   *p;
+
+	if (!backtrace_symbol_list || funcname == NULL || funcname[0] == '\0')
+		return false;
+
+	p = backtrace_symbol_list;
+	for (;;)
+	{
+		if (*p == '\0')		/* end of backtrace_symbol_list */
+			break;
+
+		if (strcmp(funcname, p) == 0)
+			return true;
+		p += strlen(p) + 1;
+	}
+
+	return false;
+}
+
 /*
  * errfinish --- end an error-reporting cycle
  *
@@ -424,6 +454,12 @@ errfinish(int dummy,...)
 	 */
 	oldcontext = MemoryContextSwitchTo(ErrorContext);
 
+	if (!edata->backtrace &&
+		edata->funcname &&
+		backtrace_functions &&
+		matches_backtrace_functions(edata->funcname))
+		set_backtrace(edata, 2);
+
 	/*
 	 * Call any context callback functions.  Errors occurring in callback
 	 * functions will be treated as recursive errors --- this ensures we will
@@ -488,6 +524,8 @@ errfinish(int dummy,...)
 		pfree(edata->hint);
 	if (edata->context)
 		pfree(edata->context);
+	if (edata->backtrace)
+		pfree(edata->backtrace);
 	if (edata->schema_name)
 		pfree(edata->schema_name);
 	if (edata->table_name)
@@ -798,6 +836,65 @@ errmsg(const char *fmt,...)
 	return 0;					/* return value does not matter */
 }
 
+/*
+ * Add a backtrace to the containing ereport() call.  This is intended to be
+ * added temporarily during debugging.
+ */
+int
+errbacktrace(void)
+{
+	ErrorData   *edata = &errordata[errordata_stack_depth];
+	MemoryContext oldcontext;
+
+	Assert(false);
+
+	recursion_depth++;
+	CHECK_STACK_DEPTH();
+	oldcontext = MemoryContextSwitchTo(edata->assoc_context);
+
+	set_backtrace(edata, 1);
+
+	MemoryContextSwitchTo(oldcontext);
+	recursion_depth--;
+
+	return 0;
+}
+
+/*
+ * Compute backtrace data and add it to the supplied ErrorData.  num_skip
+ * specifies how many inner frames to skip.  Use this to avoid showing the
+ * internal backtrace support functions in the backtrace.  This requires that
+ * this and related functions are not inlined.
+ */
+static void
+set_backtrace(ErrorData *edata, int num_skip)
+{
+	StringInfoData errtrace;
+
+	initStringInfo(&errtrace);
+
+#ifdef HAVE_BACKTRACE_SYMBOLS
+	{
+		void	   *buf[100];
+		int			nframes;
+		char	  **strfrms;
+
+		nframes = backtrace(buf, lengthof(buf));
+		strfrms = backtrace_symbols(buf, nframes);
+		if (strfrms == NULL)
+			return;
+
+		for (int i = num_skip; i < nframes; i++)
+			appendStringInfo(&errtrace, "\n%s", strfrms[i]);
+		free(strfrms);
+	}
+#else
+	appendStringInfoString(&errtrace,
+						   "backtrace generation is not supported by this installation");
+#endif
+
+	edata->backtrace = errtrace.data;
+}
 
 /*
  * errmsg_internal --- add a primary error message text to the current error
@@ -1353,6 +1450,11 @@ elog_finish(int elevel, const char *fmt,...)
 	recursion_depth++;
 	oldcontext = MemoryContextSwitchTo(edata->assoc_context);
 
+	if (!edata->backtrace &&
+		edata->funcname &&
+		matches_backtrace_functions(edata->funcname))
+		set_backtrace(edata, 2);
+
 	edata->message_id = fmt;
 	EVALUATE_MESSAGE(edata->domain, message, false, false);
 
@@ -1509,6 +1611,8 @@ CopyErrorData(void)
 		newedata->hint = pstrdup(newedata->hint);
 	if (newedata->context)
 		newedata->context = pstrdup(newedata->context);
+	if (newedata->backtrace)
+		newedata->backtrace = pstrdup(newedata->backtrace);
 	if (newedata->schema_name)
 		newedata->schema_name = pstrdup(newedata->schema_name);
 	if (newedata->table_name)
@@ -1547,6 +1651,8 @@ FreeErrorData(ErrorData *edata)
 		pfree(edata->hint);
 	if (edata->context)
 		pfree(edata->context);
+	if (edata->backtrace)
+		pfree(edata->backtrace);
 	if (edata->schema_name)
 		pfree(edata->schema_name);
 	if (edata->table_name)
@@ -1622,6 +1728,8 @@ ThrowErrorData(ErrorData *edata)
 		newedata->hint = pstrdup(edata->hint);
 	if (edata->context)
 		newedata->context = pstrdup(edata->context);
+	if (edata->backtrace)
+		newedata->backtrace = pstrdup(edata->backtrace);
 	/* assume message_id is not available */
 	if (edata->schema_name)
 		newedata->schema_name = pstrdup(edata->schema_name);
@@ -1689,6 +1797,8 @@ ReThrowError(ErrorData *edata)
 		newedata->hint = pstrdup(newedata->hint);
 	if (newedata->context)
 		newedata->context = pstrdup(newedata->context);
+	if (newedata->backtrace)
+		newedata->backtrace = pstrdup(newedata->backtrace);
 	if (newedata->schema_name)
 		newedata->schema_name = pstrdup(newedata->schema_name);
 	if (newedata->table_name)
@@ -2914,6 +3024,13 @@ send_message_to_server_log(ErrorData *edata)
 			append_with_tabs(&buf, edata->context);
 			appendStringInfoChar(&buf, '\n');
 		}
+		if (edata->backtrace)
+		{
+			log_line_prefix(&buf, edata);
+			appendStringInfoString(&buf, _("BACKTRACE:  "));
+			append_with_tabs(&buf, edata->backtrace);
+			appendStringInfoChar(&buf, '\n');
+		}
 		if (Log_error_verbosity >= PGERROR_VERBOSE)
 		{
 			/* assume no newlines in funcname or filename... */