[PATCH 1/5] stdlib: Sync canonicalize with gnulib [BZ #10635] [BZ #26592] [BZ #26241]

[Adhemerval Zanella]

It sync with gnulib version d9c121346 with the following difference
require fix a glibc build:

--- ../../gnulib/gnulib-lib/lib/canonicalize-lgpl.c
+++ stdlib/canonicalize.c
@@ -46,7 +46,7 @@
 # define FILE_SYSTEM_PREFIX_LEN(name) 0
 # define IS_ABSOLUTE_FILE_NAME(name) ISSLASH(*(name))
 # define ISSLASH(c) ((c) == '/')
-# define freea(p) ((void) (p))
+# define FUNC_REALPATH_WORKS 1
 #else
 # define __canonicalize_file_name canonicalize_file_name
 # define __realpath realpath
@@ -270,7 +270,7 @@
               buf[n] = '\0';

               char *extra_buf = extra_buffer.data;
-              idx_t end_idx;
+              idx_t end_idx = 0;
               if (end_in_extra_buffer)
                 end_idx = end - extra_buf;
               idx_t len = strlen (end);

It shows the following testcase failures:

FAIL: stdlib/test-canon
azanella@birita:~/Projects/glibc/build/x86_64-linux-gnu$ cat 
stdlib/test-canon.out
stdlib/test-canon: flunked test 30 (expected resolved `./doesExist/someFile', 
got `[builddir]/stdlib/doesExist/someFile/')
stdlib/test-canon: flunked test 31 (expected `NULL', got 
`[builddir]/stdlib/doesExist')
2 errors.

(the [builddir] the build directory I used)

This regression will be fixed in the last commit of this set.

The sync also fixes BZ#26592 and BZ#26241.
---
 stdlib/canonicalize.c | 456 +++++++++++++++++++++++++++---------------
 1 file changed, 297 insertions(+), 159 deletions(-)

diff --git a/stdlib/canonicalize.c b/stdlib/canonicalize.c
index 3fcb399a5d..66685f4526 100644
--- a/stdlib/canonicalize.c
+++ b/stdlib/canonicalize.c
@@ -16,43 +16,126 @@
    License along with the GNU C Library; if not, see
    <https://www.gnu.org/licenses/>.  */
 
-#include <assert.h>
+#ifndef _LIBC
+/* Don't use __attribute__ __nonnull__ in this compilation unit.  Otherwise gcc
+   optimizes away the name == NULL test below.  */
+# define _GL_ARG_NONNULL(params)
+
+# define _GL_USE_STDLIB_ALLOC 1
+# include <libc-config.h>
+#endif
+
+/* Specification.  */
 #include <stdlib.h>
-#include <string.h>
-#include <unistd.h>
-#include <limits.h>
-#include <sys/stat.h>
+
 #include <errno.h>
+#include <limits.h>
+#include <stdbool.h>
 #include <stddef.h>
+#include <string.h>
+#include <sys/stat.h>
+#include <unistd.h>
+
+#include <scratch_buffer.h>
+
+#ifdef _LIBC
+# include <eloop-threshold.h>
+# include <shlib-compat.h>
+typedef ptrdiff_t idx_t;
+# define IDX_MAX PTRDIFF_MAX
+# define FILE_SYSTEM_PREFIX_LEN(name) 0
+# define IS_ABSOLUTE_FILE_NAME(name) ISSLASH(*(name))
+# define ISSLASH(c) ((c) == '/')
+# define FUNC_REALPATH_WORKS 1
+#else
+# define __canonicalize_file_name canonicalize_file_name
+# define __realpath realpath
+# include "idx.h"
+# include "pathmax.h"
+# include "filename.h"
+# if defined _WIN32 && !defined __CYGWIN__
+#  define __getcwd _getcwd
+# elif HAVE_GETCWD
+#  if IN_RELOCWRAPPER
+    /* When building the relocatable program wrapper, use the system's getcwd
+       function, not the gnulib override, otherwise we would get a link error.
+     */
+#   undef getcwd
+#  endif
+#  if defined VMS && !defined getcwd
+    /* We want the directory in Unix syntax, not in VMS syntax.
+       The gnulib override of 'getcwd' takes 2 arguments; the original VMS
+       'getcwd' takes 3 arguments.  */
+#   define __getcwd(buf, max) getcwd (buf, max, 0)
+#  else
+#   define __getcwd getcwd
+#  endif
+# else
+#  define __getcwd(buf, max) getwd (buf)
+# endif
+# define __mempcpy mempcpy
+# define __pathconf pathconf
+# define __rawmemchr rawmemchr
+# define __readlink readlink
+# ifndef MAXSYMLINKS
+#  ifdef SYMLOOP_MAX
+#   define MAXSYMLINKS SYMLOOP_MAX
+#  else
+#   define MAXSYMLINKS 20
+#  endif
+# endif
+# define __eloop_threshold() MAXSYMLINKS
+#endif
+
+#ifndef DOUBLE_SLASH_IS_DISTINCT_ROOT
+# define DOUBLE_SLASH_IS_DISTINCT_ROOT 0
+#endif
+
+#if !FUNC_REALPATH_WORKS || defined _LIBC
 
-#include <eloop-threshold.h>
-#include <shlib-compat.h>
+static idx_t
+get_path_max (void)
+{
+# ifdef PATH_MAX
+  long int path_max = PATH_MAX;
+# else
+  /* The caller invoked realpath with a null RESOLVED, even though
+     PATH_MAX is not defined as a constant.  The glibc manual says
+     programs should not do this, and POSIX says the behavior is undefined.
+     Historically, glibc here used the result of pathconf, or 1024 if that
+     failed; stay consistent with this (dubious) historical practice.  */
+  int err = errno;
+  long int path_max = __pathconf ("/", _PC_PATH_MAX);
+  __set_errno (err);
+# endif
+  return path_max < 0 ? 1024 : path_max <= IDX_MAX ? path_max : IDX_MAX;
+}
 
 /* Return the canonical absolute name of file NAME.  A canonical name
-   does not contain any `.', `..' components nor any repeated path
-   separators ('/') or symlinks.  All path components must exist.  If
+   does not contain any ".", ".." components nor any repeated file name
+   separators ('/') or symlinks.  All file name components must exist.  If
    RESOLVED is null, the result is malloc'd; otherwise, if the
-   canonical name is PATH_MAX chars or more, returns null with `errno'
+   canonical name is PATH_MAX chars or more, returns null with 'errno'
    set to ENAMETOOLONG; if the name fits in fewer than PATH_MAX chars,
    returns the name in RESOLVED.  If the name cannot be resolved and
-   RESOLVED is non-NULL, it contains the path of the first component
-   that cannot be resolved.  If the path can be resolved, RESOLVED
+   RESOLVED is non-NULL, it contains the name of the first component
+   that cannot be resolved.  If the name can be resolved, RESOLVED
    holds the same value as the value returned.  */
 
 char *
 __realpath (const char *name, char *resolved)
 {
-  char *rpath, *dest, *extra_buf = NULL;
-  const char *start, *end, *rpath_limit;
-  long int path_max;
+  char *dest;
+  char const *start;
+  char const *end;
   int num_links = 0;
 
   if (name == NULL)
     {
       /* As per Single Unix Specification V2 we must return an error if
-        either parameter is a null pointer.  We extend this to allow
-        the RESOLVED parameter to be NULL in case the we are expected to
-        allocate the room for the return value.  */
+         either parameter is a null pointer.  We extend this to allow
+         the RESOLVED parameter to be NULL in case the we are expected to
+         allocate the room for the return value.  */
       __set_errno (EINVAL);
       return NULL;
     }
@@ -60,166 +143,221 @@ __realpath (const char *name, char *resolved)
   if (name[0] == '\0')
     {
       /* As per Single Unix Specification V2 we must return an error if
-        the name argument points to an empty string.  */
+         the name argument points to an empty string.  */
       __set_errno (ENOENT);
       return NULL;
     }
 
-#ifdef PATH_MAX
-  path_max = PATH_MAX;
-#else
-  path_max = __pathconf (name, _PC_PATH_MAX);
-  if (path_max <= 0)
-    path_max = 1024;
-#endif
-
-  if (resolved == NULL)
-    {
-      rpath = malloc (path_max);
-      if (rpath == NULL)
-       return NULL;
-    }
-  else
-    rpath = resolved;
-  rpath_limit = rpath + path_max;
-
-  if (name[0] != '/')
+  struct scratch_buffer extra_buffer, link_buffer;
+  struct scratch_buffer rname_buffer;
+  struct scratch_buffer *rname_buf = &rname_buffer;
+  scratch_buffer_init (&extra_buffer);
+  scratch_buffer_init (&link_buffer);
+  scratch_buffer_init (rname_buf);
+  char *rname_on_stack = rname_buf->data;
+  char *rname = rname_on_stack;
+  bool end_in_extra_buffer = false;
+  bool failed = true;
+
+  /* This is always zero for Posix hosts, but can be 2 for MS-Windows
+     and MS-DOS X:/foo/bar file names.  */
+  idx_t prefix_len = FILE_SYSTEM_PREFIX_LEN (name);
+
+  if (!IS_ABSOLUTE_FILE_NAME (name))
     {
-      if (!__getcwd (rpath, path_max))
-       {
-         rpath[0] = '\0';
-         goto error;
-       }
-      dest = __rawmemchr (rpath, '\0');
+      while (!__getcwd (rname, rname_buf->length))
+        {
+          if (errno != ERANGE)
+            {
+              dest = rname;
+              goto error;
+            }
+          if (!scratch_buffer_grow (rname_buf))
+            goto error_nomem;
+          rname = rname_buf->data;
+        }
+      dest = __rawmemchr (rname, '\0');
+      start = name;
+      prefix_len = FILE_SYSTEM_PREFIX_LEN (rname);
     }
   else
     {
-      rpath[0] = '/';
-      dest = rpath + 1;
+      dest = __mempcpy (rname, name, prefix_len);
+      *dest++ = '/';
+      if (DOUBLE_SLASH_IS_DISTINCT_ROOT)
+        {
+          if (prefix_len == 0 /* implies ISSLASH (name[0]) */
+              && ISSLASH (name[1]) && !ISSLASH (name[2]))
+            *dest++ = '/';
+          *dest = '\0';
+        }
+      start = name + prefix_len;
     }
 
-  for (start = end = name; *start; start = end)
+  for ( ; *start; start = end)
     {
-      struct stat64 st;
-      int n;
-
-      /* Skip sequence of multiple path-separators.  */
-      while (*start == '/')
-       ++start;
-
-      /* Find end of path component.  */
-      for (end = start; *end && *end != '/'; ++end)
-       /* Nothing.  */;
-
-      if (end - start == 0)
-       break;
-      else if (end - start == 1 && start[0] == '.')
-       /* nothing */;
-      else if (end - start == 2 && start[0] == '.' && start[1] == '.')
-       {
-         /* Back up to previous component, ignore if at root already.  */
-         if (dest > rpath + 1)
-           while ((--dest)[-1] != '/');
-       }
+      /* Skip sequence of multiple file name separators.  */
+      while (ISSLASH (*start))
+        ++start;
+
+      /* Find end of component.  */
+      for (end = start; *end && !ISSLASH (*end); ++end)
+        /* Nothing.  */;
+
+      /* Length of this file name component; it can be zero if a file
+         name ends in '/'.  */
+      idx_t startlen = end - start;
+
+      if (startlen == 1 && start[0] == '.')
+        /* nothing */;
+      else if (startlen == 2 && start[0] == '.' && start[1] == '.')
+        {
+          /* Back up to previous component, ignore if at root already.  */
+          if (dest > rname + prefix_len + 1)
+            for (--dest; dest > rname && !ISSLASH (dest[-1]); --dest)
+              continue;
+          if (DOUBLE_SLASH_IS_DISTINCT_ROOT
+              && dest == rname + 1 && !prefix_len
+              && ISSLASH (*dest) && !ISSLASH (dest[1]))
+            dest++;
+        }
       else
-       {
-         size_t new_size;
-
-         if (dest[-1] != '/')
-           *dest++ = '/';
-
-         if (dest + (end - start) >= rpath_limit)
-           {
-             ptrdiff_t dest_offset = dest - rpath;
-             char *new_rpath;
-
-             if (resolved)
-               {
-                 __set_errno (ENAMETOOLONG);
-                 if (dest > rpath + 1)
-                   dest--;
-                 *dest = '\0';
-                 goto error;
-               }
-             new_size = rpath_limit - rpath;
-             if (end - start + 1 > path_max)
-               new_size += end - start + 1;
-             else
-               new_size += path_max;
-             new_rpath = (char *) realloc (rpath, new_size);
-             if (new_rpath == NULL)
-               goto error;
-             rpath = new_rpath;
-             rpath_limit = rpath + new_size;
-
-             dest = rpath + dest_offset;
-           }
-
-         dest = __mempcpy (dest, start, end - start);
-         *dest = '\0';
-
-         if (__lstat64 (rpath, &st) < 0)
-           goto error;
-
-         if (S_ISLNK (st.st_mode))
-           {
-             char *buf = __alloca (path_max);
-             size_t len;
-
-             if (++num_links > __eloop_threshold ())
-               {
-                 __set_errno (ELOOP);
-                 goto error;
-               }
-
-             n = __readlink (rpath, buf, path_max - 1);
-             if (n < 0)
-               goto error;
-             buf[n] = '\0';
-
-             if (!extra_buf)
-               extra_buf = __alloca (path_max);
-
-             len = strlen (end);
-             if (path_max - n <= len)
-               {
-                 __set_errno (ENAMETOOLONG);
-                 goto error;
-               }
-
-             /* Careful here, end may be a pointer into extra_buf... */
-             memmove (&extra_buf[n], end, len + 1);
-             name = end = memcpy (extra_buf, buf, n);
-
-             if (buf[0] == '/')
-               dest = rpath + 1;       /* It's an absolute symlink */
-             else
-               /* Back up to previous component, ignore if at root already: */
-               if (dest > rpath + 1)
-                 while ((--dest)[-1] != '/');
-           }
-         else if (!S_ISDIR (st.st_mode) && *end != '\0')
-           {
-             __set_errno (ENOTDIR);
-             goto error;
-           }
-       }
+        {
+          if (!ISSLASH (dest[-1]))
+            *dest++ = '/';
+
+          while (rname + rname_buf->length - dest <= startlen)
+            {
+              idx_t dest_offset = dest - rname;
+              if (!scratch_buffer_grow_preserve (rname_buf))
+                goto error_nomem;
+              rname = rname_buf->data;
+              dest = rname + dest_offset;
+            }
+
+          dest = __mempcpy (dest, start, startlen);
+          *dest = '\0';
+
+          /* If STARTLEN == 0, RNAME ends in '/'; use stat rather than
+             readlink, because readlink might fail with EINVAL without
+             checking whether RNAME sans '/' is valid.  */
+          struct stat st;
+          char *buf = NULL;
+          ssize_t n;
+          if (startlen != 0)
+            {
+              while (true)
+                {
+                  buf = link_buffer.data;
+                  idx_t bufsize = link_buffer.length;
+                  n = __readlink (rname, buf, bufsize - 1);
+                  if (n < bufsize - 1)
+                    break;
+                  if (!scratch_buffer_grow (&link_buffer))
+                    goto error_nomem;
+                }
+              if (n < 0)
+                buf = NULL;
+            }
+          if (buf)
+            {
+              if (++num_links > __eloop_threshold ())
+                {
+                  __set_errno (ELOOP);
+                  goto error;
+                }
+
+              buf[n] = '\0';
+
+              char *extra_buf = extra_buffer.data;
+              idx_t end_idx = 0;
+              if (end_in_extra_buffer)
+                end_idx = end - extra_buf;
+              idx_t len = strlen (end);
+              while (extra_buffer.length <= len + n)
+                {
+                  if (!scratch_buffer_grow_preserve (&extra_buffer))
+                    goto error_nomem;
+                  extra_buf = extra_buffer.data;
+                }
+              if (end_in_extra_buffer)
+                end = extra_buf + end_idx;
+
+              /* Careful here, end may be a pointer into extra_buf... */
+              memmove (&extra_buf[n], end, len + 1);
+              name = end = memcpy (extra_buf, buf, n);
+              end_in_extra_buffer = true;
+
+              if (IS_ABSOLUTE_FILE_NAME (buf))
+                {
+                  idx_t pfxlen = FILE_SYSTEM_PREFIX_LEN (buf);
+
+                  dest = __mempcpy (rname, buf, pfxlen);
+                  *dest++ = '/'; /* It's an absolute symlink */
+                  if (DOUBLE_SLASH_IS_DISTINCT_ROOT)
+                    {
+                      if (ISSLASH (buf[1]) && !ISSLASH (buf[2]) && !pfxlen)
+                        *dest++ = '/';
+                      *dest = '\0';
+                    }
+                  /* Install the new prefix to be in effect hereafter.  */
+                  prefix_len = pfxlen;
+                }
+              else
+                {
+                  /* Back up to previous component, ignore if at root
+                     already: */
+                  if (dest > rname + prefix_len + 1)
+                    for (--dest; dest > rname && !ISSLASH (dest[-1]); --dest)
+                      continue;
+                  if (DOUBLE_SLASH_IS_DISTINCT_ROOT && dest == rname + 1
+                      && ISSLASH (*dest) && !ISSLASH (dest[1]) && !prefix_len)
+                    dest++;
+                }
+            }
+          else if (! (startlen == 0
+                      ? stat (rname, &st) == 0 || errno == EOVERFLOW
+                      : errno == EINVAL))
+            goto error;
+        }
     }
-  if (dest > rpath + 1 && dest[-1] == '/')
+  if (dest > rname + prefix_len + 1 && ISSLASH (dest[-1]))
     --dest;
-  *dest = '\0';
-
-  assert (resolved == NULL || resolved == rpath);
-  return rpath;
+  if (DOUBLE_SLASH_IS_DISTINCT_ROOT && dest == rname + 1 && !prefix_len
+      && ISSLASH (*dest) && !ISSLASH (dest[1]))
+    dest++;
+  failed = false;
 
 error:
-  assert (resolved == NULL || resolved == rpath);
-  if (resolved == NULL)
-    free (rpath);
-  return NULL;
+  *dest++ = '\0';
+  if (resolved != NULL && dest - rname <= get_path_max ())
+    rname = strcpy (resolved, rname);
+
+error_nomem:
+  scratch_buffer_free (&extra_buffer);
+  scratch_buffer_free (&link_buffer);
+  if (failed || rname == resolved)
+    scratch_buffer_free (rname_buf);
+
+  if (failed)
+    return NULL;
+
+  if (rname == resolved)
+    return rname;
+  idx_t rname_size = dest - rname;
+  if (rname == rname_on_stack)
+    {
+      rname = malloc (rname_size);
+      if (rname == NULL)
+        return NULL;
+      return memcpy (rname, rname_on_stack, rname_size);
+    }
+  char *result = realloc (rname, rname_size);
+  return result != NULL ? result : rname;
 }
 libc_hidden_def (__realpath)
 versioned_symbol (libc, __realpath, realpath, GLIBC_2_3);
+#endif /* !FUNC_REALPATH_WORKS || defined _LIBC */
 
 
 #if SHLIB_COMPAT(libc, GLIBC_2_0, GLIBC_2_3)
-- 
2.25.1