[binutils-gdb] PR22714, Assembler preprocessor loses track of \@

[Alan Modra <amodra at sourceware dot org>]

https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;h=ab1fadc6b2f057b817e1fc093650b63d9f6dd6c5

commit ab1fadc6b2f057b817e1fc093650b63d9f6dd6c5
Author: Alan Modra <amodra@gmail.com>
Date:   Wed Jan 31 13:34:18 2018 +1030

    PR22714, Assembler preprocessor loses track of \@
    
    The PR22714 testcase is such that the input buffer processed by
    do_scrub_chars ends on this line
    
    1: bug "Returning to usermode but unexpected PSR bits set?", \@
    
    right at the backslash.  (The line is part of a macro definition.)
    The next input buffer then starts with '@' which starts a comment on
    ARM, and the check for \@ fails due to to == tostart.  Now it would be
    possible to simply access to[-1] in this particular case, but that's
    ugly, and to be absolutely safe from people deliberately trying to
    crash gas we'd need the read.c:read_a_source_file buffer passed to
    do_scrub_chars to have a single byte pad at the start.
    
    	PR 22714
    	* app.c (last_char): New static var.
    	(struct app_save): Add last_char field.
    	(app_push, app_pop): Handle it.
    	(do_scrub_chars): Use last_char in test for "\@".  Set last_char.

Diff:
---
 gas/ChangeLog |  8 ++++++++
 gas/app.c     | 22 +++++++++++++++++++++-
 2 files changed, 29 insertions(+), 1 deletion(-)

diff --git a/gas/ChangeLog b/gas/ChangeLog
index 4fc81fa..fe30bad 100644
--- a/gas/ChangeLog
+++ b/gas/ChangeLog
@@ -1,3 +1,11 @@
+2018-01-31  Alan Modra  <amodra@gmail.com>
+
+	PR 22714
+	* app.c (last_char): New static var.
+	(struct app_save): Add last_char field.
+	(app_push, app_pop): Handle it.
+	(do_scrub_chars): Use last_char in test for "\@".  Set last_char.
+
 2018-01-29  Eric Botcazou  <ebotcazou@adacore.com>
 
 	PR gas/22738
diff --git a/gas/app.c b/gas/app.c
index da39421..9cafff0 100644
--- a/gas/app.c
+++ b/gas/app.c
@@ -55,6 +55,9 @@ static const char mri_pseudo[] = ".mri 0";
 static const char   symver_pseudo[] = ".symver";
 static const char * symver_state;
 #endif
+#ifdef TC_ARM
+static char last_char;
+#endif
 
 static char lex[256];
 static const char symbol_chars[] =
@@ -242,6 +245,9 @@ struct app_save
 #if defined TC_ARM && defined OBJ_ELF
   const char * symver_state;
 #endif
+#ifdef TC_ARM
+  char last_char;
+#endif
 };
 
 char *
@@ -271,6 +277,9 @@ app_push (void)
 #if defined TC_ARM && defined OBJ_ELF
   saved->symver_state = symver_state;
 #endif
+#ifdef TC_ARM
+  saved->last_char = last_char;
+#endif
 
   /* do_scrub_begin() is not useful, just wastes time.  */
 
@@ -310,6 +319,9 @@ app_pop (char *arg)
 #if defined TC_ARM && defined OBJ_ELF
   symver_state = saved->symver_state;
 #endif
+#ifdef TC_ARM
+  last_char = saved->last_char;
+#endif
 
   free (arg);
 }
@@ -1285,7 +1297,7 @@ do_scrub_chars (size_t (*get) (char *, size_t), char *tostart, size_t tolen)
 #ifdef TC_ARM
 	  /* For the ARM, care is needed not to damage occurrences of \@
 	     by stripping the @ onwards.  Yuck.  */
-	  if (to > tostart && *(to - 1) == '\\')
+	  if ((to > tostart ? to[-1] : last_char) == '\\')
 	    /* Do not treat the @ as a start-of-comment.  */
 	    goto de_fault;
 #endif
@@ -1465,6 +1477,10 @@ do_scrub_chars (size_t (*get) (char *, size_t), char *tostart, size_t tolen)
 
  fromeof:
   /* We have reached the end of the input.  */
+#ifdef TC_ARM
+  if (to > tostart)
+    last_char = to[-1];
+#endif
   return to - tostart;
 
  tofull:
@@ -1478,5 +1494,9 @@ do_scrub_chars (size_t (*get) (char *, size_t), char *tostart, size_t tolen)
   else
     saved_input = NULL;
 
+#ifdef TC_ARM
+  if (to > tostart)
+    last_char = to[-1];
+#endif
   return to - tostart;
 }