analyzer: add note about valid subscripts [PR106626]

Consider -fanalyzer on:

#include <stdint.h>

int32_t arr[10];

void int_arr_write_element_after_end_off_by_one(int32_t x)
{
  arr[10] = x;
}

Trunk x86_64: https://godbolt.org/z/17zn3qYY4

Currently we emit:

<source>: In function 'int_arr_write_element_after_end_off_by_one':
<source>:7:11: warning: buffer overflow [CWE-787] [-Wanalyzer-out-of-bounds]
    7 |   arr[10] = x;
      |   ~~~~~~~~^~~
  event 1
    |
    |    3 | int32_t arr[10];
    |      |         ^~~
    |      |         |
    |      |         (1) capacity is 40 bytes
    |
    +--> 'int_arr_write_element_after_end_off_by_one': events 2-3
           |
           |    5 | void int_arr_write_element_after_end_off_by_one(int32_t x)
           |      |      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
           |      |      |
           |      |      (2) entry to 'int_arr_write_element_after_end_off_by_one'
           |    6 | {
           |    7 |   arr[10] = x;
           |      |   ~~~~~~~~~~~
           |      |           |
           |      |           (3) out-of-bounds write from byte 40 till byte 43 but 'arr' ends at byte 40
           |
<source>:7:11: note: write of 4 bytes to beyond the end of 'arr'
    7 |   arr[10] = x;
      |   ~~~~~~~~^~~

This is worded in terms of bytes, due to the way -Wanalyzer-out-of-bounds
is implemented, but this isn't what the user wrote.

This patch tries to get closer to the user's code by adding a note about
array bounds when we're referring to an array.  In the above example it
adds this trailing note:

  note: valid subscripts for 'arr' are '[0]' to '[9]'

gcc/analyzer/ChangeLog:
	PR analyzer/106626
	* bounds-checking.cc (out_of_bounds::maybe_describe_array_bounds):
	New.
	(buffer_overflow::emit): Call maybe_describe_array_bounds.
	(buffer_overread::emit): Likewise.
	(buffer_underflow::emit): Likewise.
	(buffer_underread::emit): Likewise.

gcc/testsuite/ChangeLog:
	PR analyzer/106626
	* gcc.dg/analyzer/call-summaries-2.c: Add dg-message for expected
	note about valid indexes.
	* gcc.dg/analyzer/out-of-bounds-1.c: Likewise, fixing up existing
	dg-message directives.
	* gcc.dg/analyzer/out-of-bounds-write-char-arr.c: Likewise.
	* gcc.dg/analyzer/out-of-bounds-write-int-arr.c: Likewise.

Signed-off-by: David Malcolm <dmalcolm@redhat.com>

1 files changed, 42 insertions, 4 deletions

diff --git a/gcc/analyzer/bounds-checking.cc b/gcc/analyzer/bounds-checking.cc
index ad7f431..b02bc79 100644
--- a/gcc/analyzer/bounds-checking.cc
+++ b/gcc/analyzer/bounds-checking.cc
@@ -71,6 +71,34 @@ public:
   }
 
 protected:
+  /* Potentially add a note about valid ways to index this array, such
+     as (given "int arr[10];"):
+       note: valid subscripts for 'arr' are '[0]' to '[9]'
+     We print the '[' and ']' characters so as to express the valid
+     subscripts using C syntax, rather than just as byte ranges,
+     which hopefully is more clear to the user.  */
+  void
+  maybe_describe_array_bounds (location_t loc) const
+  {
+    if (!m_diag_arg)
+      return;
+    tree t = TREE_TYPE (m_diag_arg);
+    if (!t)
+      return;
+    if (TREE_CODE (t) != ARRAY_TYPE)
+      return;
+    tree domain = TYPE_DOMAIN (t);
+    if (!domain)
+      return;
+    tree max_idx = TYPE_MAX_VALUE (domain);
+    if (!max_idx)
+      return;
+    tree min_idx = TYPE_MIN_VALUE (domain);
+    inform (loc,
+	    "valid subscripts for %qE are %<[%E]%> to %<[%E]%>",
+	    m_diag_arg, min_idx, max_idx);
+  }
+
   const region *m_reg;
   tree m_diag_arg;
   byte_range m_out_of_bounds_range;
@@ -165,6 +193,8 @@ public:
 	  inform (rich_loc->get_loc (),
 		  "write to beyond the end of %qE",
 		  m_diag_arg);
+
+	maybe_describe_array_bounds (rich_loc->get_loc ());
       }
 
     return warned;
@@ -245,6 +275,8 @@ public:
 	  inform (rich_loc->get_loc (),
 		  "read from after the end of %qE",
 		  m_diag_arg);
+
+	maybe_describe_array_bounds (rich_loc->get_loc ());
       }
 
     return warned;
@@ -297,8 +329,11 @@ public:
   {
     diagnostic_metadata m;
     m.add_cwe (124);
-    return warning_meta (rich_loc, m, get_controlling_option (),
-			 "buffer underflow");
+    bool warned = warning_meta (rich_loc, m, get_controlling_option (),
+				"buffer underflow");
+    if (warned)
+      maybe_describe_array_bounds (rich_loc->get_loc ());
+    return warned;
   }
 
   label_text describe_final_event (const evdesc::final_event &ev)
@@ -346,8 +381,11 @@ public:
   {
     diagnostic_metadata m;
     m.add_cwe (127);
-    return warning_meta (rich_loc, m, get_controlling_option (),
-			 "buffer underread");
+    bool warned = warning_meta (rich_loc, m, get_controlling_option (),
+				"buffer underread");
+    if (warned)
+      maybe_describe_array_bounds (rich_loc->get_loc ());
+    return warned;
   }
 
   label_text describe_final_event (const evdesc::final_event &ev)