Re: [PATCH] Support -z initfirst for multiple shared libraries

[d wk <dwksrc at gmail dot com>]

Apologies, I renamed `node' to `new_node' at the last moment and broke
the patch. It should be easy to figure out, but here's a fixed version.

----[ cut here ]----
Support -z initfirst for multiple shared libraries (run in load order).

This is particularly useful when combined with LD_PRELOAD, as it is then
possible to run constructors before any code in other libraries runs.
---
 elf/dl-init.c              |  9 ++++++++-
 elf/dl-load.c              | 19 ++++++++++++++++++-
 elf/dl-support.c           |  4 ++--
 sysdeps/generic/ldsodefs.h |  7 +++++--
 4 files changed, 33 insertions(+), 6 deletions(-)

diff --git a/elf/dl-init.c b/elf/dl-init.c
index 818c3aa..da59d1f 100644
--- a/elf/dl-init.c
+++ b/elf/dl-init.c
@@ -84,7 +84,14 @@ _dl_init (struct link_map *main_map, int argc, char
**argv, char **env)

   if (__glibc_unlikely (GL(dl_initfirst) != NULL))
     {
-      call_init (GL(dl_initfirst), argc, argv, env);
+      struct initfirst_list *initfirst;
+      for(initfirst = GL(dl_initfirst); initfirst; initfirst = initfirst->next)
+        {
+          call_init (initfirst->which, argc, argv, env);
+        }
+
+      /* We do not try to free this list, as the memory will not be reclaimed
+         by the allocator unless there were no intervening malloc()'s.  */
       GL(dl_initfirst) = NULL;
     }

diff --git a/elf/dl-load.c b/elf/dl-load.c
index c0d6249..5288b8f 100644
--- a/elf/dl-load.c
+++ b/elf/dl-load.c
@@ -1388,7 +1388,24 @@ cannot enable executable stack as shared object
requires");

   /* Remember whether this object must be initialized first.  */
   if (l->l_flags_1 & DF_1_INITFIRST)
-    GL(dl_initfirst) = l;
+    {
+      struct initfirst_list *new_node = malloc(sizeof(*new_node));
+      struct initfirst_list *it = GL(dl_initfirst);
+      new_node->which = l;
+      new_node->next = NULL;
+
+      /* We append to the end of the linked list. Whichever library was loaded
+         first has higher initfirst priority. This means that LD_PRELOAD
+         initfirst overrides initfirst in libraries linked normally.  */
+      if (!it)
+        GL(dl_initfirst) = new_node;
+      else
+        {
+          while (it->next)
+            it = it->next;
+          it->next = new_node;
+        }
+    }

   /* Finally the file information.  */
   l->l_file_id = id;
diff --git a/elf/dl-support.c b/elf/dl-support.c
index c30194c..d8b8acc 100644
--- a/elf/dl-support.c
+++ b/elf/dl-support.c
@@ -147,8 +147,8 @@ struct r_search_path_elem *_dl_all_dirs;
 /* All directories after startup.  */
 struct r_search_path_elem *_dl_init_all_dirs;

-/* The object to be initialized first.  */
-struct link_map *_dl_initfirst;
+/* The list of objects to be initialized first.  */
+struct initfirst_list *_dl_initfirst;

 /* Descriptor to write debug messages to.  */
 int _dl_debug_fd = STDERR_FILENO;
diff --git a/sysdeps/generic/ldsodefs.h b/sysdeps/generic/ldsodefs.h
index ddec0be..198c089 100644
--- a/sysdeps/generic/ldsodefs.h
+++ b/sysdeps/generic/ldsodefs.h
@@ -326,8 +326,11 @@ struct rtld_global
   /* Incremented whenever something may have been added to dl_loaded.  */
   EXTERN unsigned long long _dl_load_adds;

-  /* The object to be initialized first.  */
-  EXTERN struct link_map *_dl_initfirst;
+  /* The list of objects to be initialized first.  */
+  EXTERN struct initfirst_list {
+    struct link_map *which;
+    struct initfirst_list *next;
+  } *_dl_initfirst;

 #if HP_SMALL_TIMING_AVAIL
   /* Start time on CPU clock.  */
-- 
1.9.1


On Tue, Apr 26, 2016 at 4:58 PM, d wk <dwksrc@gmail.com> wrote:
> Hello libc developers,
>
> In a project of mine, I needed to run some code before any constructors
> from any system libraries (such as libc or libpthread). The linker/loader
> -z initfirst feature is perfect for this, but it only supports one shared
> library. Unfortunately libpthread also uses this feature (I assume the
> feature exists because pthread needed it), so my project was incompatible
> with libpthread.
>
> So, I wrote a small patch which changes the single dl_initfirst variable
> into a linked list. This patch does not change the size of any data
> structures (it's ABI compatible), just turns dl_initfirst into a list. The
> list is not freed (the allocator wouldn't free it anyway), and insertion
> into the list is quadratic, but I expect there will never be more than
> a handful of initfirst libraries!
>
> This patch records initfirst libraries in load order, so LD_PRELOAD
> libraries will have their constructors called before libpthread. If the
> opposite behaviour is desired, the LD_PRELOAD'd library can always declare
> a dependency on libpthread. Normally LD_PRELOAD constructors are run last,
> which is very inconvenient when trying to inject new functionality, and
> I expect anyone using -z initfirst with LD_PRELOAD to really want to run
> first. The patch is written against latest glibc 2.23 (I also tested on
> glibc 2.21, and it's not quite compatible with 2.17 since the other data
> structures changed).
>
> I was not the first person to run into this problem,
> someone wanted the same thing on stack overflow two years
> ago. You can see my answer there with a complete test case.
> http://stackoverflow.com/questions/19796383/linux-ld-preload-z-initfirst/36143861
>
> Hope you will accept this patch. Comments welcome. Thanks,
>
> ~ dwk.
>
>
> ----[ cut here ]----
> Support -z initfirst for multiple shared libraries (run in load order).
>
> This is particularly useful when combined with LD_PRELOAD, as it is then
> possible to run constructors before any code in other libraries runs.
> ---
>  elf/dl-init.c              |  9 ++++++++-
>  elf/dl-load.c              | 19 ++++++++++++++++++-
>  elf/dl-support.c           |  4 ++--
>  sysdeps/generic/ldsodefs.h |  7 +++++--
>  4 files changed, 33 insertions(+), 6 deletions(-)
>
> diff --git a/elf/dl-init.c b/elf/dl-init.c
> index 818c3aa..da59d1f 100644
> --- a/elf/dl-init.c
> +++ b/elf/dl-init.c
> @@ -84,7 +84,14 @@ _dl_init (struct link_map *main_map, int argc, char
> **argv, char **env)
>
>    if (__glibc_unlikely (GL(dl_initfirst) != NULL))
>      {
> -      call_init (GL(dl_initfirst), argc, argv, env);
> +      struct initfirst_list *initfirst;
> +      for(initfirst = GL(dl_initfirst); initfirst; initfirst = initfirst->next)
> +        {
> +          call_init (initfirst->which, argc, argv, env);
> +        }
> +
> +      /* We do not try to free this list, as the memory will not be reclaimed
> +         by the allocator unless there were no intervening malloc()'s.  */
>        GL(dl_initfirst) = NULL;
>      }
>
> diff --git a/elf/dl-load.c b/elf/dl-load.c
> index c0d6249..1efabbf 100644
> --- a/elf/dl-load.c
> +++ b/elf/dl-load.c
> @@ -1388,7 +1388,24 @@ cannot enable executable stack as shared object
> requires");
>
>    /* Remember whether this object must be initialized first.  */
>    if (l->l_flags_1 & DF_1_INITFIRST)
> -    GL(dl_initfirst) = l;
> +    {
> +      struct initfirst_list *new_node = malloc(sizeof(*node));
> +      struct initfirst_list *it = GL(dl_initfirst);
> +      new_node->which = l;
> +      new_node->next = NULL;
> +
> +      /* We append to the end of the linked list. Whichever library was loaded
> +         first has higher initfirst priority. This means that LD_PRELOAD
> +         initfirst overrides initfirst in libraries linked normally.  */
> +      if (!it)
> +        GL(dl_initfirst) = new_node;
> +      else
> +        {
> +          while (it->next)
> +            it = it->next;
> +          it->next = new_node;
> +        }
> +    }
>
>    /* Finally the file information.  */
>    l->l_file_id = id;
> diff --git a/elf/dl-support.c b/elf/dl-support.c
> index c30194c..d8b8acc 100644
> --- a/elf/dl-support.c
> +++ b/elf/dl-support.c
> @@ -147,8 +147,8 @@ struct r_search_path_elem *_dl_all_dirs;
>  /* All directories after startup.  */
>  struct r_search_path_elem *_dl_init_all_dirs;
>
> -/* The object to be initialized first.  */
> -struct link_map *_dl_initfirst;
> +/* The list of objects to be initialized first.  */
> +struct initfirst_list *_dl_initfirst;
>
>  /* Descriptor to write debug messages to.  */
>  int _dl_debug_fd = STDERR_FILENO;
> diff --git a/sysdeps/generic/ldsodefs.h b/sysdeps/generic/ldsodefs.h
> index ddec0be..198c089 100644
> --- a/sysdeps/generic/ldsodefs.h
> +++ b/sysdeps/generic/ldsodefs.h
> @@ -326,8 +326,11 @@ struct rtld_global
>    /* Incremented whenever something may have been added to dl_loaded.  */
>    EXTERN unsigned long long _dl_load_adds;
>
> -  /* The object to be initialized first.  */
> -  EXTERN struct link_map *_dl_initfirst;
> +  /* The list of objects to be initialized first.  */
> +  EXTERN struct initfirst_list {
> +    struct link_map *which;
> +    struct initfirst_list *next;
> +  } *_dl_initfirst;
>
>  #if HP_SMALL_TIMING_AVAIL
>    /* Start time on CPU clock.  */
> --
> 1.9.1