libcpp: Fix up #__VA_OPT__ handling [PR103415]

Hi!

stringify_arg uses pfile->u_buff to create the string literal.
Unfortunately, paste_tokens -> _cpp_lex_direct -> lex_number -> _cpp_unaligned_alloc
can in some cases use pfile->u_buff too, which results in losing everything
prepared for the string literal until the token pasting.

The following patch fixes that by not calling paste_token during the
construction of the string literal, but doing that before.  All the tokens
we are processing have been pushed into a token buffer using
tokens_buff_add_token so it is fine if we paste some of them in that buffer
(successful pasting creates a new token in that buffer), move following
tokens if any to make it contiguous, pop (throw away) the extra tokens at
the end and then do stringify_arg.

Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?

2021-11-26  Jakub Jelinek  <jakub@redhat.com>

	PR preprocessor/103415
libcpp/
	* macro.c (stringify_arg): Remove va_opt argument and va_opt handling.
	(replace_args): Adjust callers.  For #__VA_OPT__, perform token
	pasting in a separate loop before stringify_arg call.
gcc/testsuite/
	* c-c++-common/cpp/va-opt-8.c: New test.


	Jakub

On 11/26/21 04:33, Jakub Jelinek wrote:
> Hi!
> 
> stringify_arg uses pfile->u_buff to create the string literal.
> Unfortunately, paste_tokens -> _cpp_lex_direct -> lex_number -> _cpp_unaligned_alloc
> can in some cases use pfile->u_buff too, which results in losing everything
> prepared for the string literal until the token pasting.
> 
> The following patch fixes that by not calling paste_token during the
> construction of the string literal, but doing that before.  All the tokens
> we are processing have been pushed into a token buffer using
> tokens_buff_add_token so it is fine if we paste some of them in that buffer
> (successful pasting creates a new token in that buffer), move following
> tokens if any to make it contiguous, pop (throw away) the extra tokens at
> the end and then do stringify_arg.

Please add some of this explanation to the "paste any tokens" comment in 
the code.

> Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk?
> 
> 2021-11-26  Jakub Jelinek  <jakub@redhat.com>
> 
> 	PR preprocessor/103415
> libcpp/
> 	* macro.c (stringify_arg): Remove va_opt argument and va_opt handling.
> 	(replace_args): Adjust callers.  For #__VA_OPT__, perform token
> 	pasting in a separate loop before stringify_arg call.
> gcc/testsuite/
> 	* c-c++-common/cpp/va-opt-8.c: New test.
> 
> --- libcpp/macro.c.jj	2021-11-23 10:26:30.595792246 +0100
> +++ libcpp/macro.c	2021-11-25 17:55:39.149217299 +0100
> @@ -295,7 +295,7 @@ static cpp_context *next_context (cpp_re
>   static const cpp_token *padding_token (cpp_reader *, const cpp_token *);
>   static const cpp_token *new_string_token (cpp_reader *, uchar *, unsigned int);
>   static const cpp_token *stringify_arg (cpp_reader *, const cpp_token **,
> -				       unsigned int, bool);
> +				       unsigned int);
>   static void paste_all_tokens (cpp_reader *, const cpp_token *);
>   static bool paste_tokens (cpp_reader *, location_t,
>   			  const cpp_token **, const cpp_token *);
> @@ -834,8 +834,7 @@ cpp_quote_string (uchar *dest, const uch
>   /* Convert a token sequence FIRST to FIRST+COUNT-1 to a single string token
>      according to the rules of the ISO C #-operator.  */
>   static const cpp_token *
> -stringify_arg (cpp_reader *pfile, const cpp_token **first, unsigned int count,
> -	       bool va_opt)
> +stringify_arg (cpp_reader *pfile, const cpp_token **first, unsigned int count)
>   {
>     unsigned char *dest;
>     unsigned int i, escape_it, backslash_count = 0;
> @@ -852,24 +851,6 @@ stringify_arg (cpp_reader *pfile, const
>       {
>         const cpp_token *token = first[i];
>   
> -      if (va_opt && (token->flags & PASTE_LEFT))
> -	{
> -	  location_t virt_loc = pfile->invocation_location;
> -	  const cpp_token *rhs;
> -	  do
> -	    {
> -	      if (i == count)
> -		abort ();
> -	      rhs = first[++i];
> -	      if (!paste_tokens (pfile, virt_loc, &token, rhs))
> -		{
> -		  --i;
> -		  break;
> -		}
> -	    }
> -	  while (rhs->flags & PASTE_LEFT);
> -	}
> -
>         if (token->type == CPP_PADDING)
>   	{
>   	  if (source == NULL
> @@ -1945,8 +1926,7 @@ replace_args (cpp_reader *pfile, cpp_has
>   	if (src->flags & STRINGIFY_ARG)
>   	  {
>   	    if (!arg->stringified)
> -	      arg->stringified = stringify_arg (pfile, arg->first, arg->count,
> -						false);
> +	      arg->stringified = stringify_arg (pfile, arg->first, arg->count);
>   	  }
>   	else if ((src->flags & PASTE_LEFT)
>   		 || (src != macro->exp.tokens && (src[-1].flags & PASTE_LEFT)))
> @@ -2066,11 +2046,49 @@ replace_args (cpp_reader *pfile, cpp_has
>   		{
>   		  unsigned int count
>   		    = start ? paste_flag - start : tokens_buff_count (buff);
> -		  const cpp_token *t
> -		    = stringify_arg (pfile,
> -				     start ? start + 1
> -				     : (const cpp_token **) (buff->base),
> -				     count, true);
> +		  const cpp_token **first
> +		    = start ? start + 1
> +			    : (const cpp_token **) (buff->base);
> +		  unsigned int i, j;
> +
> +		  /* Paste any tokens that need to be pasted.  */
> +		  for (i = 0, j = 0; i < count; i++, j++)
> +		    {
> +		      const cpp_token *token = first[i];
> +
> +		      if (token->flags & PASTE_LEFT)
> +			{
> +			  location_t virt_loc = pfile->invocation_location;
> +			  const cpp_token *rhs;
> +			  unsigned short flags = token->flags;
> +			  do
> +			    {
> +			      if (i == count)
> +				abort ();
> +			      rhs = first[++i];
> +			      if (!paste_tokens (pfile, virt_loc, &token, rhs))
> +				{
> +				  --i;
> +				  break;
> +				}
> +			    }
> +			  while (rhs->flags & PASTE_LEFT);
> +			  if ((flags & PREV_WHITE)
> +			      && (token->flags & PREV_WHITE) == 0)
> +			    const_cast<cpp_token *>(token)->flags
> +			      |= PREV_WHITE;

Hmm, shouldn't paste_tokens handle copying PREV_WHITE?

> +			}
> +
> +		      first[j] = token;
> +		    }
> +		  if (j != i)
> +		    {
> +		      while (i-- != j)
> +			tokens_buff_remove_last_token (buff);
> +		      count = j;
> +		    }
> +
> +		  const cpp_token *t = stringify_arg (pfile, first, count);
>   		  while (count--)
>   		    tokens_buff_remove_last_token (buff);
>   		  if (src->flags & PASTE_LEFT)
> --- gcc/testsuite/c-c++-common/cpp/va-opt-8.c.jj	2021-11-25 18:03:19.243595714 +0100
> +++ gcc/testsuite/c-c++-common/cpp/va-opt-8.c	2021-11-25 18:02:12.712553219 +0100
> @@ -0,0 +1,18 @@
> +/* PR preprocessor/103415 */
> +/* { dg-do run } */
> +/* { dg-options "-std=gnu99" { target c } } */
> +/* { dg-options "-std=c++20" { target c++ } } */
> +
> +#define n(x, ...) = #__VA_OPT__(x##3)
> +#define o(x, ...) #__VA_OPT__(x##__VA_ARGS__##9)
> +const char *c n(1 2, 4);
> +const char *d = o(5  6, 7	8);
> +
> +int
> +main ()
> +{
> +  if (__builtin_strcmp (c, "1 23")
> +      || __builtin_strcmp (d, "5 67 89"))
> +    __builtin_abort ();
> +  return 0;
> +}
> 
> 	Jakub
>