about summary refs log tree commit diff
path: root/elf
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2018-07-16 14:08:15 -0700
committerH.J. Lu <hjl.tools@gmail.com>2018-07-16 14:08:27 -0700
commitf753fa7dea3367bd3eb7b543103ff8cda182a3fa (patch)
tree8663f1df2145cba958bfdb7d3d1c4b467c58cd48 /elf
parent52b2a80fae89d2a99ac3d1866a73c8bbf7b608ff (diff)
downloadglibc-f753fa7dea3367bd3eb7b543103ff8cda182a3fa.tar.gz
glibc-f753fa7dea3367bd3eb7b543103ff8cda182a3fa.tar.xz
glibc-f753fa7dea3367bd3eb7b543103ff8cda182a3fa.zip
x86: Support IBT and SHSTK in Intel CET [BZ #21598]
Intel Control-flow Enforcement Technology (CET) instructions:

https://software.intel.com/sites/default/files/managed/4d/2a/control-flow-en
forcement-technology-preview.pdf

includes Indirect Branch Tracking (IBT) and Shadow Stack (SHSTK).

GNU_PROPERTY_X86_FEATURE_1_IBT is added to GNU program property to
indicate that all executable sections are compatible with IBT when
ENDBR instruction starts each valid target where an indirect branch
instruction can land.  Linker sets GNU_PROPERTY_X86_FEATURE_1_IBT on
output only if it is set on all relocatable inputs.

On an IBT capable processor, the following steps should be taken:

1. When loading an executable without an interpreter, enable IBT and
lock IBT if GNU_PROPERTY_X86_FEATURE_1_IBT is set on the executable.
2. When loading an executable with an interpreter, enable IBT if
GNU_PROPERTY_X86_FEATURE_1_IBT is set on the interpreter.
  a. If GNU_PROPERTY_X86_FEATURE_1_IBT isn't set on the executable,
     disable IBT.
  b. Lock IBT.
3. If IBT is enabled, when loading a shared object without
GNU_PROPERTY_X86_FEATURE_1_IBT:
  a. If legacy interwork is allowed, then mark all pages in executable
     PT_LOAD segments in legacy code page bitmap.  Failure of legacy code
     page bitmap allocation causes an error.
  b. If legacy interwork isn't allowed, it causes an error.

GNU_PROPERTY_X86_FEATURE_1_SHSTK is added to GNU program property to
indicate that all executable sections are compatible with SHSTK where
return address popped from shadow stack always matches return address
popped from normal stack.  Linker sets GNU_PROPERTY_X86_FEATURE_1_SHSTK
on output only if it is set on all relocatable inputs.

On a SHSTK capable processor, the following steps should be taken:

1. When loading an executable without an interpreter, enable SHSTK if
GNU_PROPERTY_X86_FEATURE_1_SHSTK is set on the executable.
2. When loading an executable with an interpreter, enable SHSTK if
GNU_PROPERTY_X86_FEATURE_1_SHSTK is set on interpreter.
  a. If GNU_PROPERTY_X86_FEATURE_1_SHSTK isn't set on the executable
     or any shared objects loaded via the DT_NEEDED tag, disable SHSTK.
  b. Otherwise lock SHSTK.
3. After SHSTK is enabled, it is an error to load a shared object
without GNU_PROPERTY_X86_FEATURE_1_SHSTK.

To enable CET support in glibc, --enable-cet is required to configure
glibc.  When CET is enabled, both compiler and assembler must support
CET.  Otherwise, it is a configure-time error.

To support CET run-time control,

1. _dl_x86_feature_1 is added to the writable ld.so namespace to indicate
if IBT or SHSTK are enabled at run-time.  It should be initialized by
init_cpu_features.
2. For dynamic executables:
   a. A l_cet field is added to struct link_map to indicate if IBT or
      SHSTK is enabled in an ELF module.  _dl_process_pt_note or
      _rtld_process_pt_note is called to process PT_NOTE segment for
      GNU program property and set l_cet.
   b. _dl_open_check is added to check IBT and SHSTK compatibilty when
      dlopening a shared object.
3. Replace i386 _dl_runtime_resolve and _dl_runtime_profile with
_dl_runtime_resolve_shstk and _dl_runtime_profile_shstk, respectively if
SHSTK is enabled.

CET run-time control can be changed via GLIBC_TUNABLES with

$ export GLIBC_TUNABLES=glibc.tune.x86_shstk=[permissive|on|off]
$ export GLIBC_TUNABLES=glibc.tune.x86_ibt=[permissive|on|off]

1. permissive: SHSTK is disabled when dlopening a legacy ELF module.
2. on: IBT or SHSTK are always enabled, regardless if there are IBT or
SHSTK bits in GNU program property.
3. off: IBT or SHSTK are always disabled, regardless if there are IBT or
SHSTK bits in GNU program property.

<cet.h> from CET-enabled GCC is automatically included by assembly codes
to add GNU_PROPERTY_X86_FEATURE_1_IBT and GNU_PROPERTY_X86_FEATURE_1_SHSTK
to GNU program property.  _CET_ENDBR is added at the entrance of all
assembly functions whose address may be taken.  _CET_NOTRACK is used to
insert NOTRACK prefix with indirect jump table to support IBT.  It is
defined as notrack when _CET_NOTRACK is defined in <cet.h>.

	 [BZ #21598]
	* configure.ac: Add --enable-cet.
	* configure: Regenerated.
	* elf/Makefille (all-built-dso): Add a comment.
	* elf/dl-load.c (filebuf): Moved before "dynamic-link.h".
	Include <dl-prop.h>.
	(_dl_map_object_from_fd): Call _dl_process_pt_note on PT_NOTE
	segment.
	* elf/dl-open.c: Include <dl-prop.h>.
	(dl_open_worker): Call _dl_open_check.
	* elf/rtld.c: Include <dl-prop.h>.
	(dl_main): Call _rtld_process_pt_note on PT_NOTE segment.  Call
	_rtld_main_check.
	* sysdeps/generic/dl-prop.h: New file.
	* sysdeps/i386/dl-cet.c: Likewise.
	* sysdeps/unix/sysv/linux/x86/cpu-features.c: Likewise.
	* sysdeps/unix/sysv/linux/x86/dl-cet.h: Likewise.
	* sysdeps/x86/cet-tunables.h: Likewise.
	* sysdeps/x86/check-cet.awk: Likewise.
	* sysdeps/x86/configure: Likewise.
	* sysdeps/x86/configure.ac: Likewise.
	* sysdeps/x86/dl-cet.c: Likewise.
	* sysdeps/x86/dl-procruntime.c: Likewise.
	* sysdeps/x86/dl-prop.h: Likewise.
	* sysdeps/x86/libc-start.h: Likewise.
	* sysdeps/x86/link_map.h: Likewise.
	* sysdeps/i386/dl-trampoline.S (_dl_runtime_resolve): Add
	_CET_ENDBR.
	(_dl_runtime_profile): Likewise.
	(_dl_runtime_resolve_shstk): New.
	(_dl_runtime_profile_shstk): Likewise.
	* sysdeps/linux/x86/Makefile (sysdep-dl-routines): Add dl-cet
	if CET is enabled.
	(CFLAGS-.o): Add -fcf-protection if CET is enabled.
	(CFLAGS-.os): Likewise.
	(CFLAGS-.op): Likewise.
	(CFLAGS-.oS): Likewise.
	(asm-CPPFLAGS): Add -fcf-protection -include cet.h if CET
	is enabled.
	(tests-special): Add $(objpfx)check-cet.out.
	(cet-built-dso): New.
	(+$(cet-built-dso:=.note)): Likewise.
	(common-generated): Add $(cet-built-dso:$(common-objpfx)%=%.note).
	($(objpfx)check-cet.out): New.
	(generated): Add check-cet.out.
	* sysdeps/x86/cpu-features.c: Include <dl-cet.h> and
	<cet-tunables.h>.
	(TUNABLE_CALLBACK (set_x86_ibt)): New prototype.
	(TUNABLE_CALLBACK (set_x86_shstk)): Likewise.
	(init_cpu_features): Call get_cet_status to check CET status
	and update dl_x86_feature_1 with CET status.  Call
	TUNABLE_CALLBACK (set_x86_ibt) and TUNABLE_CALLBACK
	(set_x86_shstk).  Disable and lock CET in libc.a.
	* sysdeps/x86/cpu-tunables.c: Include <cet-tunables.h>.
	(TUNABLE_CALLBACK (set_x86_ibt)): New function.
	(TUNABLE_CALLBACK (set_x86_shstk)): Likewise.
	* sysdeps/x86/sysdep.h (_CET_NOTRACK): New.
	(_CET_ENDBR): Define if not defined.
	(ENTRY): Add _CET_ENDBR.
	* sysdeps/x86/dl-tunables.list (glibc.tune): Add x86_ibt and
	x86_shstk.
	* sysdeps/x86_64/dl-trampoline.h (_dl_runtime_resolve): Add
	_CET_ENDBR.
	(_dl_runtime_profile): Likewise.
Diffstat (limited to 'elf')
-rw-r--r--elf/Makefile2
-rw-r--r--elf/dl-load.c60
-rw-r--r--elf/dl-open.c3
-rw-r--r--elf/rtld.c9
4 files changed, 49 insertions, 25 deletions
diff --git a/elf/Makefile b/elf/Makefile
index 41cc3681be..84107f6dbb 100644
--- a/elf/Makefile
+++ b/elf/Makefile
@@ -1058,6 +1058,8 @@ $(objpfx)tst-piemod1.so: $(libsupport)
 $(objpfx)tst-pie1: $(objpfx)tst-piemod1.so
 
 ifeq (yes,$(build-shared))
+# NB: Please keep cet-built-dso in sysdeps/x86/Makefile in sync with
+# all-built-dso here.
 all-built-dso := $(common-objpfx)elf/ld.so $(common-objpfx)libc.so \
 		 $(filter-out $(common-objpfx)linkobj/libc.so, \
 			      $(sort $(wildcard $(addprefix $(common-objpfx), \
diff --git a/elf/dl-load.c b/elf/dl-load.c
index 09185ab68d..c51e4b3718 100644
--- a/elf/dl-load.c
+++ b/elf/dl-load.c
@@ -30,6 +30,32 @@
 #include <sys/param.h>
 #include <sys/stat.h>
 #include <sys/types.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
+   cases the program header follows the ELF header directly.  If this
+   is not the case all bets are off and we can make the header
+   arbitrarily large and still won't get it read.  This means the only
+   question is how large are the ELF and program header combined.  The
+   ELF header 32-bit files is 52 bytes long and in 64-bit files is 64
+   bytes long.  Each program header entry is again 32 and 56 bytes
+   long respectively.  I.e., even with a file which has 10 program
+   header entries we only have to read 372B/624B respectively.  Add to
+   this a bit of margin for program notes and reading 512B and 832B
+   for 32-bit and 64-bit files respecitvely is enough.  If this
+   heuristic should really fail for some file the code in
+   `_dl_map_object_from_fd' knows how to recover.  */
+struct filebuf
+{
+  ssize_t len;
+#if __WORDSIZE == 32
+# define FILEBUF_SIZE 512
+#else
+# define FILEBUF_SIZE 832
+#endif
+  char buf[FILEBUF_SIZE] __attribute__ ((aligned (__alignof (ElfW(Ehdr)))));
+};
+
 #include "dynamic-link.h"
 #include <abi-tag.h>
 #include <stackinfo.h>
@@ -44,6 +70,7 @@
 #include <dl-unmap-segments.h>
 #include <dl-machine-reject-phdr.h>
 #include <dl-sysdep-open.h>
+#include <dl-prop.h>
 #include <not-cancel.h>
 
 #include <endian.h>
@@ -69,31 +96,6 @@ int __stack_prot attribute_hidden attribute_relro
 #endif
 
 
-/* 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
-   cases the program header follows the ELF header directly.  If this
-   is not the case all bets are off and we can make the header
-   arbitrarily large and still won't get it read.  This means the only
-   question is how large are the ELF and program header combined.  The
-   ELF header 32-bit files is 52 bytes long and in 64-bit files is 64
-   bytes long.  Each program header entry is again 32 and 56 bytes
-   long respectively.  I.e., even with a file which has 10 program
-   header entries we only have to read 372B/624B respectively.  Add to
-   this a bit of margin for program notes and reading 512B and 832B
-   for 32-bit and 64-bit files respecitvely is enough.  If this
-   heuristic should really fail for some file the code in
-   `_dl_map_object_from_fd' knows how to recover.  */
-struct filebuf
-{
-  ssize_t len;
-#if __WORDSIZE == 32
-# define FILEBUF_SIZE 512
-#else
-# define FILEBUF_SIZE 832
-#endif
-  char buf[FILEBUF_SIZE] __attribute__ ((aligned (__alignof (ElfW(Ehdr)))));
-};
-
 /* This is the decomposed LD_LIBRARY_PATH search path.  */
 static struct r_search_path_struct env_path_list attribute_relro;
 
@@ -1152,6 +1154,14 @@ _dl_map_object_from_fd (const char *name, const char *origname, int fd,
 	  l->l_relro_addr = ph->p_vaddr;
 	  l->l_relro_size = ph->p_memsz;
 	  break;
+
+	case PT_NOTE:
+	  if (_dl_process_pt_note (l, ph, fd, fbp))
+	    {
+	      errstring = N_("cannot process note segment");
+	      goto call_lose;
+	    }
+	  break;
 	}
 
     if (__glibc_unlikely (nloadcmds == 0))
diff --git a/elf/dl-open.c b/elf/dl-open.c
index 9dde4acfbc..f6c8ef1043 100644
--- a/elf/dl-open.c
+++ b/elf/dl-open.c
@@ -35,6 +35,7 @@
 #include <libc-internal.h>
 
 #include <dl-dst.h>
+#include <dl-prop.h>
 
 
 /* We must be careful not to leave us in an inconsistent state.  Thus we
@@ -291,6 +292,8 @@ dl_open_worker (void *a)
   _dl_debug_state ();
   LIBC_PROBE (map_complete, 3, args->nsid, r, new);
 
+  _dl_open_check (new);
+
   /* Print scope information.  */
   if (__glibc_unlikely (GLRO(dl_debug_mask) & DL_DEBUG_SCOPES))
     _dl_show_scope (new, 0);
diff --git a/elf/rtld.c b/elf/rtld.c
index 8c732adb68..1b0c74739f 100644
--- a/elf/rtld.c
+++ b/elf/rtld.c
@@ -38,6 +38,7 @@
 #include <dl-cache.h>
 #include <dl-osinfo.h>
 #include <dl-procinfo.h>
+#include <dl-prop.h>
 #include <tls.h>
 #include <stap-probe.h>
 #include <stackinfo.h>
@@ -1241,6 +1242,12 @@ of this helper program; chances are you did not intend to run this program.\n\
 	main_map->l_relro_addr = ph->p_vaddr;
 	main_map->l_relro_size = ph->p_memsz;
 	break;
+
+      case PT_NOTE:
+	if (_rtld_process_pt_note (main_map, ph))
+	  _dl_error_printf ("\
+ERROR: '%s': cannot process note segment.\n", _dl_argv[0]);
+	break;
       }
 
   /* Adjust the address of the TLS initialization image in case
@@ -2110,6 +2117,8 @@ ERROR: ld.so: object '%s' cannot be loaded as audit interface: %s; ignored.\n",
 	_dl_show_scope (l, 0);
     }
 
+  _rtld_main_check (main_map, _dl_argv[0]);
+
   if (prelinked)
     {
       if (main_map->l_info [ADDRIDX (DT_GNU_CONFLICT)] != NULL)