Detect ld.so and libc.so version inconsistency during startup

The files NEWS, include/link.h, and sysdeps/generic/ldsodefs.h
contribute to the version fingerprint used for detection.  The
fingerprint can be further refined using the --with-extra-version-id
configure argument.

_dl_call_libc_early_init is replaced with _dl_lookup_libc_early_init.
The new function is used store a pointer to libc.so's
__libc_early_init function in the libc_map_early_init member of the
ld.so namespace structure.  This function pointer can then be called
directly, so the separate invocation function is no longer needed.

The versioned symbol lookup needs the symbol versioning data
structures, so the initialization of libc_map and libc_map_early_init
is now done from _dl_check_map_versions, after this information
becomes available.  (_dl_map_object_from_fd does not set this up
in time, so the initialization code had to be moved from there.)
This means that the separate initialization code can be removed from
dl_main because _dl_check_map_versions covers all maps, including
the initial executable loaded by the kernel.  The lookup still happens
before relocation and the invocation of IFUNC resolvers, so IFUNC
resolvers are protected from ABI mismatch.

The __libc_early_init function pointer is not protected because
so little code runs between the pointer write and the invocation
(only dynamic linker code and IFUNC resolvers).

Reviewed-by: Carlos O'Donell <carlos@redhat.com>

8 files changed, 49 insertions, 44 deletions

diff --git a/elf/Makefile b/elf/Makefile
index 3928a08..bc68150 100644
--- a/elf/Makefile
+++ b/elf/Makefile
@@ -52,7 +52,6 @@ routines = \
 # The core dynamic linking functions are in libc for the static and
 # profiled libraries.
 dl-routines = \
-  dl-call-libc-early-init \
   dl-close \
   dl-debug \
   dl-debug-symbols \
@@ -65,6 +64,7 @@ dl-routines = \
   dl-load \
   dl-lookup \
   dl-lookup-direct \
+  dl-lookup_libc_early_init \
   dl-minimal-malloc \
   dl-misc \
   dl-object \
diff --git a/elf/Versions b/elf/Versions
index a9ff278..6260c0f 100644
--- a/elf/Versions
+++ b/elf/Versions
@@ -29,8 +29,8 @@ libc {
     __placeholder_only_for_empty_version_map;
   }
   GLIBC_PRIVATE {
-    # functions used in other libraries
-    __libc_early_init;
+    # A pattern is needed here because the suffix is dynamically generated.
+    __libc_early_init_*;
 
     # Internal error handling support.  Interposes the functions in ld.so.
     _dl_signal_exception; _dl_catch_exception;
diff --git a/elf/dl-load.c b/elf/dl-load.c
index 1ad0868..00e08b5 100644
--- a/elf/dl-load.c
+++ b/elf/dl-load.c
@@ -31,7 +31,6 @@
 #include <sys/param.h>
 #include <sys/stat.h>
 #include <sys/types.h>
-#include <gnu/lib-names.h>
 
 /* Type for the buffer we put the ELF header and hopefully the program
    header.  This buffer does not really have to be too large.  In most
@@ -1466,14 +1465,6 @@ cannot enable executable stack as shared object requires");
     add_name_to_object (l, ((const char *) D_PTR (l, l_info[DT_STRTAB])
 			    + l->l_info[DT_SONAME]->d_un.d_val));
 
-  /* If we have newly loaded libc.so, update the namespace
-     description.  */
-  if (GL(dl_ns)[nsid].libc_map == NULL
-      && l->l_info[DT_SONAME] != NULL
-      && strcmp (((const char *) D_PTR (l, l_info[DT_STRTAB])
-		  + l->l_info[DT_SONAME]->d_un.d_val), LIBC_SO) == 0)
-    GL(dl_ns)[nsid].libc_map = l;
-
   /* _dl_close can only eventually undo the module ID assignment (via
      remove_slotinfo) if this function returns a pointer to a link
      map.  Therefore, delay this step until all possibilities for
diff --git a/elf/dl-call-libc-early-init.c b/elf/dl-lookup_libc_early_init.c
index ee9860e..64bc287 100644
--- a/elf/dl-call-libc-early-init.c
+++ b/elf/dl-lookup_libc_early_init.c
@@ -1,4 +1,4 @@
-/* Invoke the early initialization function in libc.so.
+/* Find the address of the __libc_early_init function.
    Copyright (C) 2020-2022 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
 
@@ -16,26 +16,21 @@
    License along with the GNU C Library; if not, see
    <https://www.gnu.org/licenses/>.  */
 
-#include <assert.h>
 #include <ldsodefs.h>
 #include <libc-early-init.h>
 #include <link.h>
 #include <stddef.h>
 
-void
-_dl_call_libc_early_init (struct link_map *libc_map, _Bool initial)
+__typeof (__libc_early_init) *
+_dl_lookup_libc_early_init (struct link_map *libc_map)
 {
-  /* There is nothing to do if we did not actually load libc.so.  */
-  if (libc_map == NULL)
-    return;
-
   const ElfW(Sym) *sym
-    = _dl_lookup_direct (libc_map, "__libc_early_init",
-                         0x069682ac, /* dl_new_hash output.  */
+    = _dl_lookup_direct (libc_map, LIBC_EARLY_INIT_NAME_STRING,
+                         LIBC_EARLY_INIT_GNU_HASH,
                          "GLIBC_PRIVATE",
                          0x0963cf85); /* _dl_elf_hash output.  */
-  assert (sym != NULL);
-  __typeof (__libc_early_init) *early_init
-    = DL_SYMBOL_ADDRESS (libc_map, sym);
-  early_init (initial);
+  if (sym == NULL)
+    _dl_signal_error (0, libc_map->l_name, NULL, "\
+ld.so/libc.so mismatch detected (upgrade in progress?)");
+  return DL_SYMBOL_ADDRESS (libc_map, sym);
 }
diff --git a/elf/dl-open.c b/elf/dl-open.c
index a23e659..dcc2413 100644
--- a/elf/dl-open.c
+++ b/elf/dl-open.c
@@ -760,8 +760,8 @@ dl_open_worker_begin (void *a)
   if (!args->libc_already_loaded)
     {
       /* dlopen cannot be used to load an initial libc by design.  */
-      struct link_map *libc_map = GL(dl_ns)[args->nsid].libc_map;
-      _dl_call_libc_early_init (libc_map, false);
+      if (GL(dl_ns)[args->nsid].libc_map != NULL)
+	GL(dl_ns)[args->nsid].libc_map_early_init (false);
     }
 
   args->worker_continue = true;
diff --git a/elf/dl-version.c b/elf/dl-version.c
index cda0889..d9ec44e 100644
--- a/elf/dl-version.c
+++ b/elf/dl-version.c
@@ -23,6 +23,8 @@
 #include <string.h>
 #include <ldsodefs.h>
 #include <_itoa.h>
+#include <gnu/lib-names.h>
+#include <libc-early-init.h>
 
 #include <assert.h>
 
@@ -359,6 +361,22 @@ _dl_check_map_versions (struct link_map *map, int verbose, int trace_mode)
 	}
     }
 
+  /* Detect a libc.so loaded into this namespace.  The
+     __libc_early_init lookup below means that we have to do this
+     after parsing the version data.  */
+  if (GL(dl_ns)[map->l_ns].libc_map == NULL
+      && map->l_info[DT_SONAME] != NULL
+      && strcmp (((const char *) D_PTR (map, l_info[DT_STRTAB])
+		  + map->l_info[DT_SONAME]->d_un.d_val), LIBC_SO) == 0)
+    {
+      /* Look up this symbol early to trigger a mismatch error before
+	 relocation (which may call IFUNC resolvers, and those can
+	 have an internal ABI dependency).  */
+      GL(dl_ns)[map->l_ns].libc_map_early_init
+	= _dl_lookup_libc_early_init (map);
+      GL(dl_ns)[map->l_ns].libc_map = map;
+    }
+
   /* When there is a DT_VERNEED entry with libc.so on DT_NEEDED, issue
      an error if there is a DT_RELR entry without GLIBC_ABI_DT_RELR
      dependency.  */
diff --git a/elf/libc-early-init.h b/elf/libc-early-init.h
index a8edfad..ac8c204 100644
--- a/elf/libc-early-init.h
+++ b/elf/libc-early-init.h
@@ -19,12 +19,9 @@
 #ifndef _LIBC_EARLY_INIT_H
 #define _LIBC_EARLY_INIT_H
 
-struct link_map;
+#include <libc_early_init_name.h>
 
-/* If LIBC_MAP is not NULL, look up the __libc_early_init symbol in it
-   and call this function, with INITIAL as the argument.  */
-void _dl_call_libc_early_init (struct link_map *libc_map, _Bool initial)
-  attribute_hidden;
+struct link_map;
 
 /* In the shared case, this function is defined in libc.so and invoked
    from ld.so (or on the fist static dlopen) after complete relocation
@@ -33,6 +30,18 @@ void _dl_call_libc_early_init (struct link_map *libc_map, _Bool initial)
    startup code.  If INITIAL is true, the libc being initialized is
    the libc for the main program.  INITIAL is false for libcs loaded
    for audit modules, dlmopen, and static dlopen.  */
-void __libc_early_init (_Bool initial);
+void __libc_early_init (_Bool initial)
+#ifdef SHARED
+/* Redirect to the actual implementation name.  */
+  __asm__ (LIBC_EARLY_INIT_NAME_STRING)
+#endif
+  ;
+
+/* Attempts to find the appropriately named __libc_early_init function
+   in LIBC_MAP.  On lookup failure, an exception is signaled,
+   indicating an ld.so/libc.so mismatch.  */
+__typeof (__libc_early_init) *_dl_lookup_libc_early_init (struct link_map *
+                                                          libc_map)
+  attribute_hidden;
 
 #endif /* _LIBC_EARLY_INIT_H */
diff --git a/elf/rtld.c b/elf/rtld.c
index cbbaf4a..910075c 100644
--- a/elf/rtld.c
+++ b/elf/rtld.c
@@ -1707,15 +1707,6 @@ dl_main (const ElfW(Phdr) *phdr,
       /* Extract the contents of the dynamic section for easy access.  */
       elf_get_dynamic_info (main_map, false, false);
 
-      /* If the main map is libc.so, update the base namespace to
-	 refer to this map.  If libc.so is loaded later, this happens
-	 in _dl_map_object_from_fd.  */
-      if (main_map->l_info[DT_SONAME] != NULL
-	  && (strcmp (((const char *) D_PTR (main_map, l_info[DT_STRTAB])
-		      + main_map->l_info[DT_SONAME]->d_un.d_val), LIBC_SO)
-	      == 0))
-	GL(dl_ns)[LM_ID_BASE].libc_map = main_map;
-
       /* Set up our cache of pointers into the hash table.  */
       _dl_setup_hash (main_map);
     }
@@ -2386,7 +2377,8 @@ dl_main (const ElfW(Phdr) *phdr,
   /* Relocation is complete.  Perform early libc initialization.  This
      is the initial libc, even if audit modules have been loaded with
      other libcs.  */
-  _dl_call_libc_early_init (GL(dl_ns)[LM_ID_BASE].libc_map, true);
+  if (GL(dl_ns)[LM_ID_BASE].libc_map != NULL)
+    GL(dl_ns)[LM_ID_BASE].libc_map_early_init (true);
 
   /* Do any necessary cleanups for the startup OS interface code.
      We do these now so that no calls are made after rtld re-relocation