elf: Fix GL(dl_phdr) and GL(dl_phnum) for static builds [BZ #29864]
Checks
Commit Message
The 73fc4e28b9464f0e refactor did not add the GL(dl_phdr) and
GL(dl_phnum) for static build, relying on the __ehdr_start symbol,
which is always added by the static linker, to get the correct values.
This is problematic in some ways:
- The segment may see its in-memory size differ from its in-file
size (or the binary may have holes). The Linux has fixed is to
provide concise values for both AT_PHDR and AT_PHNUM (commit
0da1d5002745c - "fs/binfmt_elf: Fix AT_PHDR for unusual ELF files")
- Some archs (alpha for instance) the hidden weak reference is not
correctly pulled by the static linker and __ehdr_start address
end up being 0, which makes GL(dl_phdr) and GL(dl_phnum) have both
invalid values (and triggering a segfault later on libc.so while
accessing TLS variables).
The safer fix is to just restore the previous behavior to setup
GL(dl_phdr) and GL(dl_phnum) for static based on kernel auxv. The
__ehdr_start fallback can also be simplified by not assuming weak
linkage (as for PIE).
The libc-static.c auxv init logic is moved to dl-support.c, since
the later is build without SHARED and then GLRO macro is defined
to access the variables directly.
The _dl_phdr is also assumed to be always non NULL, since an invalid
NULL values does not trigger TLS initialization (which is used in
various libc systems).
Checked on aarch64-linux-gnu, x86_64-linux-gnu, and i686-linux-gnu.
---
csu/libc-start.c | 21 ----------
csu/libc-tls.c | 25 ++++++------
elf/dl-support.c | 52 ++++++++++++++++---------
sysdeps/unix/sysv/linux/dl-parse_auxv.h | 1 +
4 files changed, 46 insertions(+), 53 deletions(-)
Comments
* Adhemerval Zanella:
> diff --git a/elf/dl-support.c b/elf/dl-support.c
> index 614b5b3e0c..b5ec5bd6d1 100644
> --- a/elf/dl-support.c
> +++ b/elf/dl-support.c
> @@ -250,12 +250,27 @@ _dl_aux_init (ElfW(auxv_t) *av)
> #endif
>
> _dl_auxv = av;
> - dl_parse_auxv_t auxv_values;
> - /* Use an explicit initialization loop here because memset may not
> - be available yet. */
> - for (int i = 0; i < array_length (auxv_values); ++i)
> - auxv_values[i] = 0;
> + dl_parse_auxv_t auxv_values = { 0, };
Is this really safe? If so, it should still be in a separate commit.
> diff --git a/sysdeps/unix/sysv/linux/dl-parse_auxv.h b/sysdeps/unix/sysv/linux/dl-parse_auxv.h
> index bf9374371e..2bf3a0ca6b 100644
> --- a/sysdeps/unix/sysv/linux/dl-parse_auxv.h
> +++ b/sysdeps/unix/sysv/linux/dl-parse_auxv.h
> @@ -21,6 +21,7 @@
> #include <fpu_control.h>
> #include <ldsodefs.h>
> #include <link.h>
> +#include <dl-auxv.h> /* For DL_PLATFORM_AUXV */
>
> typedef ElfW(Addr) dl_parse_auxv_t[AT_MINSIGSTKSZ + 1];
Why is this change needed?
Thanks,
Florian
On 11/01/23 11:27, Florian Weimer wrote:
> * Adhemerval Zanella:
>
>> diff --git a/elf/dl-support.c b/elf/dl-support.c
>> index 614b5b3e0c..b5ec5bd6d1 100644
>> --- a/elf/dl-support.c
>> +++ b/elf/dl-support.c
>> @@ -250,12 +250,27 @@ _dl_aux_init (ElfW(auxv_t) *av)
>> #endif
>>
>> _dl_auxv = av;
>> - dl_parse_auxv_t auxv_values;
>> - /* Use an explicit initialization loop here because memset may not
>> - be available yet. */
>> - for (int i = 0; i < array_length (auxv_values); ++i)
>> - auxv_values[i] = 0;
>> + dl_parse_auxv_t auxv_values = { 0, };
>
> Is this really safe? If so, it should still be in a separate commit.
It should be since 5355f9ca7b10183ce06e8a18003ba30f43774858, but I will
recheck. I can move it to another patch, but I think it is a lefover of
the -fno-tree-loop-distribute-patterns removal.
>
>> diff --git a/sysdeps/unix/sysv/linux/dl-parse_auxv.h b/sysdeps/unix/sysv/linux/dl-parse_auxv.h
>> index bf9374371e..2bf3a0ca6b 100644
>> --- a/sysdeps/unix/sysv/linux/dl-parse_auxv.h
>> +++ b/sysdeps/unix/sysv/linux/dl-parse_auxv.h
>> @@ -21,6 +21,7 @@
>> #include <fpu_control.h>
>> #include <ldsodefs.h>
>> #include <link.h>
>> +#include <dl-auxv.h> /* For DL_PLATFORM_AUXV */
>>
>> typedef ElfW(Addr) dl_parse_auxv_t[AT_MINSIGSTKSZ + 1];
>
> Why is this change needed?
Hum, it might a leftover of development. I will check.
@@ -262,28 +262,7 @@ LIBC_START_MAIN (int (*main) (int, char **, char ** MAIN_AUXVEC_DECL),
}
# endif
_dl_aux_init (auxvec);
- if (GL(dl_phdr) == NULL)
# endif
- {
- /* Starting from binutils-2.23, the linker will define the
- magic symbol __ehdr_start to point to our own ELF header
- if it is visible in a segment that also includes the phdrs.
- So we can set up _dl_phdr and _dl_phnum even without any
- information from auxv. */
-
- extern const ElfW(Ehdr) __ehdr_start
-# if BUILD_PIE_DEFAULT
- __attribute__ ((visibility ("hidden")));
-# else
- __attribute__ ((weak, visibility ("hidden")));
- if (&__ehdr_start != NULL)
-# endif
- {
- assert (__ehdr_start.e_phentsize == sizeof *GL(dl_phdr));
- GL(dl_phdr) = (const void *) &__ehdr_start + __ehdr_start.e_phoff;
- GL(dl_phnum) = __ehdr_start.e_phnum;
- }
- }
__tunables_init (__environ);
@@ -119,19 +119,18 @@ __libc_setup_tls (void)
__tls_pre_init_tp ();
/* Look through the TLS segment if there is any. */
- if (_dl_phdr != NULL)
- for (phdr = _dl_phdr; phdr < &_dl_phdr[_dl_phnum]; ++phdr)
- if (phdr->p_type == PT_TLS)
- {
- /* Remember the values we need. */
- memsz = phdr->p_memsz;
- filesz = phdr->p_filesz;
- initimage = (void *) phdr->p_vaddr + main_map->l_addr;
- align = phdr->p_align;
- if (phdr->p_align > max_align)
- max_align = phdr->p_align;
- break;
- }
+ for (phdr = _dl_phdr; phdr < &_dl_phdr[_dl_phnum]; ++phdr)
+ if (phdr->p_type == PT_TLS)
+ {
+ /* Remember the values we need. */
+ memsz = phdr->p_memsz;
+ filesz = phdr->p_filesz;
+ initimage = (void *) phdr->p_vaddr + main_map->l_addr;
+ align = phdr->p_align;
+ if (phdr->p_align > max_align)
+ max_align = phdr->p_align;
+ break;
+ }
/* Calculate the size of the static TLS surplus, with 0 auditors. */
_dl_tls_static_surplus_init (0);
@@ -250,12 +250,27 @@ _dl_aux_init (ElfW(auxv_t) *av)
#endif
_dl_auxv = av;
- dl_parse_auxv_t auxv_values;
- /* Use an explicit initialization loop here because memset may not
- be available yet. */
- for (int i = 0; i < array_length (auxv_values); ++i)
- auxv_values[i] = 0;
+ dl_parse_auxv_t auxv_values = { 0, };
_dl_parse_auxv (av, auxv_values);
+
+ _dl_phdr = (void*) auxv_values[AT_PHDR];
+ _dl_phnum = auxv_values[AT_PHNUM];
+
+ if (_dl_phdr == NULL)
+ {
+ /* Starting from binutils-2.23, the linker will define the
+ magic symbol __ehdr_start to point to our own ELF header
+ if it is visible in a segment that also includes the phdrs.
+ So we can set up _dl_phdr and _dl_phnum even without any
+ information from auxv. */
+
+ extern const ElfW(Ehdr) __ehdr_start attribute_hidden;
+ assert (__ehdr_start.e_phentsize == sizeof *GL(dl_phdr));
+ _dl_phdr = (const void *) &__ehdr_start + __ehdr_start.e_phoff;
+ _dl_phnum = __ehdr_start.e_phnum;
+ }
+
+ assert (_dl_phdr != NULL);
}
#endif
@@ -324,20 +339,19 @@ _dl_non_dynamic_init (void)
if (_dl_platform != NULL)
_dl_platformlen = strlen (_dl_platform);
- if (_dl_phdr != NULL)
- for (const ElfW(Phdr) *ph = _dl_phdr; ph < &_dl_phdr[_dl_phnum]; ++ph)
- switch (ph->p_type)
- {
- /* Check if the stack is nonexecutable. */
- case PT_GNU_STACK:
- _dl_stack_flags = ph->p_flags;
- break;
-
- case PT_GNU_RELRO:
- _dl_main_map.l_relro_addr = ph->p_vaddr;
- _dl_main_map.l_relro_size = ph->p_memsz;
- break;
- }
+ for (const ElfW(Phdr) *ph = _dl_phdr; ph < &_dl_phdr[_dl_phnum]; ++ph)
+ switch (ph->p_type)
+ {
+ /* Check if the stack is nonexecutable. */
+ case PT_GNU_STACK:
+ _dl_stack_flags = ph->p_flags;
+ break;
+
+ case PT_GNU_RELRO:
+ _dl_main_map.l_relro_addr = ph->p_vaddr;
+ _dl_main_map.l_relro_size = ph->p_memsz;
+ break;
+ }
call_function_static_weak (_dl_find_object_init);
@@ -21,6 +21,7 @@
#include <fpu_control.h>
#include <ldsodefs.h>
#include <link.h>
+#include <dl-auxv.h> /* For DL_PLATFORM_AUXV */
typedef ElfW(Addr) dl_parse_auxv_t[AT_MINSIGSTKSZ + 1];