gas: bpf: do not allow referring to register names as symbols in operands

2023-11-18  Jose E. Marchesi  <jemarch@gnu.org>

	* config/tc-bpf.c (parse_bpf_register): Move before
	bpf_parse_name.
	(bpf_parse_name): Do not allow using symbols that are also
	register names as operands in pseudo-c syntax.
	* testsuite/gas/bpf/regs-for-symbols-pseudoc.d: New file.
	* testsuite/gas/bpf/regs-for-symbols-pseudoc.s: Likewise.
	* testsuite/gas/bpf/regs-for-symbols-pseudoc.l: Likewise.
	* doc/c-bpf.texi (BPF Registers): Document that it is not possible
	to refer to register names as symbols in instruction operands.

7 files changed, 102 insertions, 49 deletions

diff --git a/gas/ChangeLog b/gas/ChangeLog
index cbe2a57..9f966be 100644
--- a/gas/ChangeLog
+++ b/gas/ChangeLog
@@ -1,3 +1,15 @@
+2023-11-18  Jose E. Marchesi  <jemarch@gnu.org>
+
+	* config/tc-bpf.c (parse_bpf_register): Move before
+	bpf_parse_name.
+	(bpf_parse_name): Do not allow using symbols that are also
+	register names as operands in pseudo-c syntax.
+	* testsuite/gas/bpf/regs-for-symbols-pseudoc.d: New file.
+	* testsuite/gas/bpf/regs-for-symbols-pseudoc.s: Likewise.
+	* testsuite/gas/bpf/regs-for-symbols-pseudoc.l: Likewise.
+	* doc/c-bpf.texi (BPF Registers): Document that it is not possible
+	to refer to register names as symbols in instruction operands.
+
 2023-11-15  YunQiang Su  <yunqiang.su@cipunited.com>
 
 	* testsuite/gas/mips/mips.exp (mips_arch_create): Add "--defsym
diff --git a/gas/config/tc-bpf.c b/gas/config/tc-bpf.c
index 3122f80..45abc3c 100644
--- a/gas/config/tc-bpf.c
+++ b/gas/config/tc-bpf.c
@@ -1255,6 +1255,54 @@ parse_expression (char *s, expressionS *exp)
   return s;
 }
 
+/* Parse a BPF register name and return the corresponding register
+   number.  Return NULL in case of parse error, or a pointer to the
+   first character in S that is not part of the register name.  */
+
+static char *
+parse_bpf_register (char *s, char rw, uint8_t *regno)
+{
+  if (asm_dialect == DIALECT_NORMAL)
+    {
+      rw = 'r';
+      if (*s != '%')
+	return NULL;
+      s += 1;
+
+      if (*s == 'f' && *(s + 1) == 'p')
+	{
+	  *regno = 10;
+	  s += 2;
+	  return s;
+	}
+    }
+
+  if (*s != rw)
+    return NULL;
+  s += 1;
+
+  if (*s == '1')
+    {
+      if (*(s + 1) == '0')
+        {
+          *regno = 10;
+          s += 2;
+        }
+      else
+        {
+          *regno = 1;
+          s += 1;
+        }
+    }
+  else if (*s >= '0' && *s <= '9')
+    {
+      *regno = *s - '0';
+      s += 1;
+    }
+
+  return s;
+}
+
 /* Symbols created by this parse, but not yet committed to the real
    symbol table.  */
 static symbolS *deferred_sym_rootP;
@@ -1283,6 +1331,23 @@ bpf_parse_name (const char *name, expressionS *exp, enum expr_mode mode)
 
   gas_assert (mode == expr_normal);
 
+  /* Pseudo-C syntax uses unprefixed register names like r2 or w3.
+     Since many instructions take either a register or an
+     immediate/expression, we should not allow references to symbols
+     with these names in operands.  */
+  if (asm_dialect == DIALECT_PSEUDOC)
+    {
+      uint8_t regno;
+
+      if (parse_bpf_register ((char *) name, 'r', &regno)
+          || parse_bpf_register ((char *) name, 'w', &regno))
+        {
+          as_bad (_("unexpected register name `%s' in expression"),
+                  name);
+          return false;
+        }
+    }
+
   if (symbol_find (name) != NULL)
     return false;
 
@@ -1320,54 +1385,6 @@ bpf_parse_name (const char *name, expressionS *exp, enum expr_mode mode)
   return true;
 }
 
-/* Parse a BPF register name and return the corresponding register
-   number.  Return NULL in case of parse error, or a pointer to the
-   first character in S that is not part of the register name.  */
-
-static char *
-parse_bpf_register (char *s, char rw, uint8_t *regno)
-{
-  if (asm_dialect == DIALECT_NORMAL)
-    {
-      rw = 'r';
-      if (*s != '%')
-	return NULL;
-      s += 1;
-
-      if (*s == 'f' && *(s + 1) == 'p')
-	{
-	  *regno = 10;
-	  s += 2;
-	  return s;
-	}
-    }
-
-  if (*s != rw)
-    return NULL;
-  s += 1;
-
-  if (*s == '1')
-    {
-      if (*(s + 1) == '0')
-        {
-          *regno = 10;
-          s += 2;
-        }
-      else
-        {
-          *regno = 1;
-          s += 1;
-        }
-    }
-  else if (*s >= '0' && *s <= '9')
-    {
-      *regno = *s - '0';
-      s += 1;
-    }
-
-  return s;
-}
-
 /* Collect a parse error message.  */
 
 static int partial_match_length = 0;
diff --git a/gas/doc/c-bpf.texi b/gas/doc/c-bpf.texi
index bdd9fde..25ae231 100644
--- a/gas/doc/c-bpf.texi
+++ b/gas/doc/c-bpf.texi
@@ -113,7 +113,12 @@ Read-only frame pointer register.
 
 @noindent
 Note that in the Pseudo-C syntax register names are not preceded by
-@code{%} characters.
+@code{%} characters.  A consequence of that is that in contexts like
+instruction operands, where both register names and expressions
+involving symbols are expected, there is no way to disambiguate
+between them.  In order to keep things simple, this assembler does not
+allow to refer to symbols whose names collide with register names in
+instruction operands.
 
 @node BPF Directives
 @section BPF Directives
diff --git a/gas/testsuite/gas/bpf/bpf.exp b/gas/testsuite/gas/bpf/bpf.exp
index fcbeccd..5bcd8c4 100644
--- a/gas/testsuite/gas/bpf/bpf.exp
+++ b/gas/testsuite/gas/bpf/bpf.exp
@@ -73,6 +73,10 @@ if {[istarget bpf*-*-*]} {
     run_dump_test disp32-overflow
     run_dump_test imm32-overflow
 
+    # In Pseudo-C it is not possible to refer to symbols
+    # as operands that have the same name than registers.
+    run_dump_test regs-for-symbols-pseudoc
+
     # Test that parser does not create undefined symbols
     run_dump_test asm-extra-sym-1
 }
diff --git a/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.d b/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.d
new file mode 100644
index 0000000..d99ec8f
--- /dev/null
+++ b/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.d
@@ -0,0 +1,3 @@
+#as: -EL -mdialect=pseudoc
+#source: regs-for-symbols-pseudoc.s
+#error_output: regs-for-symbols-pseudoc.l
diff --git a/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.l b/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.l
new file mode 100644
index 0000000..eeda735
--- /dev/null
+++ b/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.l
@@ -0,0 +1,8 @@
+.*: Assembler messages:
+.*:1: Error: unexpected register name `w3' in expression
+.*:2: Error: unexpected register name `r3' in expression
+.*:2: Error: unexpected register name `r3' in expression
+.*:3: Error: unexpected register name `r3' in expression
+.*:3: Error: unexpected register name `r3' in expression
+.*:4: Error: unexpected register name `r3' in expression
+.*:4: Error: unexpected register name `r3' in expression
diff --git a/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.s b/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.s
new file mode 100644
index 0000000..693787d
--- /dev/null
+++ b/gas/testsuite/gas/bpf/regs-for-symbols-pseudoc.s
@@ -0,0 +1,4 @@
+        goto w3
+        r2 = r3 ll
+        r2 = r3+1 ll
+        r2 = 1+r3 ll