From b8ddeb88480b6087528be6405183496af4d527c2 Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 23 Dec 2022 20:57:31 -0800
Subject: [PATCH] vvp: Handle null-bytes in the string literal VPI support

The VPI API for string literals does not correctly handle the case where a
null-byte ('\0') appears in the string literal. It uses strlen() to
calculate the length of the literal, which will give the wrong result if
there is a null-byte in the string literal. Instead of using strlen() use
the stored length to fix this.

In addition when formatting a string literal as a string ignore any
null-bytes. The LRM is not entirely clear what should happen to null-bytes
when formatting a value as a string. But the behavior of ignoring the
null-bytes is consistent with the rules of SystemVerilog for converting a
string literal to a SV string.

This problem can occur when a string literal gets null-byte left-padded due
to width of its context of its expression, but then optimization removes
part of the expression and only leaves the padded string literal.

E.g.
```
$display(0 ? "Yes" : "No");
```

will be transformed into

```
$display("\000No");
```

There is also one subtle change in behavior associated with this. The empty
string ("") is supposed to be equivalent to 8'h00. So e.g.
`$display(":%s:", "")` should print ": :" since the width of the empty
string is 1 byte and the %s modifier prints a string with the width of the
value, left-padding with spaces if necessary. The current implementation
will print "::" though. This change requires to update the marco_with_args
gold file.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
---
 ivtest/gold/macro_with_args.gold |  2 +-
 vvp/vpi_const.cc                 | 19 ++++++++++++++++---
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/ivtest/gold/macro_with_args.gold b/ivtest/gold/macro_with_args.gold
index c13571aa5..b0a34d36c 100644
--- a/ivtest/gold/macro_with_args.gold
+++ b/ivtest/gold/macro_with_args.gold
@@ -1,4 +1,4 @@
 first..last first,last last..first
-(a)..(c) (a,b,c) (c)..(a)
+(a )..(c ) (a,b,c) (c )..(a )
 sumsqr(3,4)  = 25
 sumsqr(5,12) = 169
diff --git a/vvp/vpi_const.cc b/vvp/vpi_const.cc
index 3fccb82b8..175c4e5fe 100644
--- a/vvp/vpi_const.cc
+++ b/vvp/vpi_const.cc
@@ -93,7 +93,7 @@ int __vpiStringConst::vpi_get(int code)
 {
       switch (code) {
           case vpiSize:
-	    return strlen(value_)*8;
+	    return value_len_ * 8;
 
           case vpiSigned:
 	      return 0;
@@ -121,7 +121,7 @@ void __vpiStringConst::vpi_get_value(p_vpi_value vp)
 {
       unsigned uint_value;
       p_vpi_vecval vecp;
-      unsigned size = strlen(value_);
+      unsigned size = value_len_;
       char*rbuf = 0;
       char*cp;
 
@@ -131,9 +131,22 @@ void __vpiStringConst::vpi_get_value(p_vpi_value vp)
 	    vp->format = vpiStringVal;
 	    // fallthrough
 	  case vpiStringVal:
+	    cp = value_;
 	    rbuf = (char *) need_result_buf(size + 1, RBUF_VAL);
-	    strcpy(rbuf, value_);
 	    vp->value.str = rbuf;
+
+	    for (unsigned int i = 0; i < size; i++) {
+		  // Ignore leading null-bytes and replace other null-bytes with space.
+		  // The LRM is not entirely clear on how null bytes should be handled.
+		  // This is the implementation chosen for iverilog.
+		  if (*cp)
+			*rbuf++ = *cp;
+		  else if (rbuf != vp->value.str)
+			*rbuf++ = ' ';
+
+		  cp++;
+	    }
+	    *rbuf = '\0';
 	    break;
 
           case vpiDecStrVal: