elf: Remove LD_PROFILE for static binaries

The _dl_non_dynamic_init does not parse LD_PROFILE, which does not
enable profile for dlopen objects.  Since dlopen is deprecated for
static objects, it is better to remove the support.

It also allows to trim down libc.a of profile support.

Checked on x86_64-linux-gnu.
Reviewed-by: Siddhesh Poyarekar <siddhesh@sourceware.org>

elf/Makefile

@@ -37,12 +37,12 @@ routines = \
   dl-iteratephdr \
   dl-libc \
   dl-origin \
-  dl-profstub \
   dl-reloc-static-pie \
   dl-support \
   dl-sym \
   dl-sysdep \
   enbl-secure \
+  libc-dl-profstub  \
   libc-dl_find_object \
   libc_early_init \
   rtld_static_init \
@@ -72,7 +72,6 @@ dl-routines = \
   dl-open \
   dl-origin \
   dl-printf \
-  dl-profile \
   dl-reloc \
   dl-runtime \
   dl-scope \
@@ -117,7 +116,11 @@ elide-routines.os = \
   # elide-routines.os
 
 # These object files are only included in the dynamically-linked libc.
-shared-only-routines = libc-dl_find_object
+shared-only-routines = \
+  libc-dl-profile \
+  libc-dl-profstub \
+  libc-dl_find_object \
+  # shared-only-routines
 
 # ld.so uses those routines, plus some special stuff for being the program
 # interpreter and operating independent of libc.
@@ -135,6 +138,7 @@ rtld-routines = \
   dl-libc_freeres \
   dl-minimal \
   dl-mutex \
+  dl-profile \
   dl-sysdep \
   dl-usage \
   rtld \

elf/dl-load.c

@@ -1443,11 +1443,6 @@ cannot enable executable stack as shared object requires");
      name by which the DSO is actually known.  Add that as well.  */
   if (__glibc_unlikely (origname != NULL))
     add_name_to_object (l, origname);
-#else
-  /* Audit modules only exist when linking is dynamic so ORIGNAME
-     cannot be non-NULL.  */
-  assert (origname == NULL);
-#endif
 
   /* When we profile the SONAME might be needed for something else but
      loading.  Add it right away.  */
@@ -1455,6 +1450,11 @@ cannot enable executable stack as shared object requires");
       && l->l_info[DT_SONAME] != NULL)
     add_name_to_object (l, ((const char *) D_PTR (l, l_info[DT_STRTAB])
 			    + l->l_info[DT_SONAME]->d_un.d_val));
+#else
+  /* Audit modules only exist when linking is dynamic so ORIGNAME
+     cannot be non-NULL.  */
+  assert (origname == NULL);
+#endif
 
   /* If we have newly loaded libc.so, update the namespace
      description.  */

elf/dl-runtime.c

@@ -162,14 +162,14 @@ _dl_fixup (
   return elf_machine_fixup_plt (l, result, refsym, sym, reloc, rel_addr, value);
 }
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 DL_FIXUP_VALUE_TYPE
 __attribute ((noinline))
 DL_ARCH_FIXUP_ATTRIBUTE
 _dl_profile_fixup (
-#ifdef ELF_MACHINE_RUNTIME_FIXUP_ARGS
+# ifdef ELF_MACHINE_RUNTIME_FIXUP_ARGS
 		   ELF_MACHINE_RUNTIME_FIXUP_ARGS,
-#endif
+# endif
 		   struct link_map *l, ElfW(Word) reloc_arg,
 		   ElfW(Addr) retaddr, void *regs, long int *framesizep)
 {
@@ -309,14 +309,12 @@ _dl_profile_fixup (
       /* And now perhaps the relocation addend.  */
       value = elf_machine_plt_value (l, reloc, value);
 
-#ifdef SHARED
       /* Auditing checkpoint: we have a new binding.  Provide the
 	 auditing libraries the possibility to change the value and
 	 tell us whether further auditing is wanted.  */
       if (defsym != NULL && GLRO(dl_naudit) > 0)
 	_dl_audit_symbind (l, reloc_result, reloc, defsym, &value, result,
 			   true);
-#endif
 
       /* Store the result for later runs.  */
       if (__glibc_likely (! GLRO(dl_bind_not)))
@@ -335,11 +333,9 @@ _dl_profile_fixup (
   long int framesize = -1;
 
 
-#ifdef SHARED
   /* Auditing checkpoint: report the PLT entering and allow the
      auditors to change the value.  */
   _dl_audit_pltenter (l, reloc_result, &value, regs, &framesize);
-#endif
 
   /* Store the frame size information.  */
   *framesizep = framesize;
@@ -349,4 +345,4 @@ _dl_profile_fixup (
   return value;
 }
 
-#endif /* PROF */
+#endif /* !defined PROF && defined SHARED */

elf/dl-support.c

@@ -60,10 +60,6 @@ int _dl_dynamic_weak;
 /* If nonzero print warnings about problematic situations.  */
 int _dl_verbose;
 
-/* We never do profiling.  */
-const char *_dl_profile;
-const char *_dl_profile_output;
-
 /* Names of shared object for which the RUNPATHs and RPATHs should be
    ignored.  */
 const char *_dl_inhibit_rpath;
@@ -301,11 +297,6 @@ _dl_non_dynamic_init (void)
 
   _dl_dynamic_weak = *(getenv ("LD_DYNAMIC_WEAK") ?: "") == '\0';
 
-  _dl_profile_output = getenv ("LD_PROFILE_OUTPUT");
-  if (_dl_profile_output == NULL || _dl_profile_output[0] == '\0')
-    _dl_profile_output
-      = &"/var/tmp\0/var/profile"[__libc_enable_secure ? 9 : 0];
-
   if (__libc_enable_secure)
     {
       static const char unsecure_envvars[] =

include/dlfcn.h

@@ -135,5 +135,10 @@ extern int __dladdr1 (const void *address, Dl_info *info,
 extern int __dlinfo (void *handle, int request, void *arg);
 extern char *__dlerror (void);
 
+#ifndef SHARED
+# undef DL_CALL_FCT
+# define DL_CALL_FCT(fctp, args) ((fctp) args)
+#endif
+
 #endif
 #endif

sysdeps/aarch64/dl-machine.h

@@ -68,7 +68,6 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
     {
       ElfW(Addr) *got;
       extern void _dl_runtime_resolve (ElfW(Word));
-      extern void _dl_runtime_profile (ElfW(Word));
 
       got = (ElfW(Addr) *) D_PTR (l, l_info[DT_PLTGOT]);
       if (got[1])
@@ -83,6 +82,8 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.  In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.  */
+#ifdef SHARED
+      extern void _dl_runtime_profile (ElfW(Word));
       if ( profile)
 	{
 	   got[2] = (ElfW(Addr)) &_dl_runtime_profile;
@@ -94,6 +95,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	{
 	  /* This function will get called to fix up the GOT entry
 	     indicated by the offset on the stack, and then jump to

sysdeps/aarch64/dl-trampoline.S

@@ -122,7 +122,7 @@ _dl_runtime_resolve:
 
 	cfi_endproc
 	.size _dl_runtime_resolve, .-_dl_runtime_resolve
-#ifndef PROF
+#if !defined PROF && defined SHARED
 	.globl _dl_runtime_profile
 	.type _dl_runtime_profile, #function
 	cfi_startproc

sysdeps/alpha/dl-machine.h

@@ -75,9 +75,7 @@ elf_machine_runtime_setup (struct link_map *map, struct r_scope_elem *scope[],
 			   int lazy, int profile)
 {
   extern char _dl_runtime_resolve_new[] attribute_hidden;
-  extern char _dl_runtime_profile_new[] attribute_hidden;
   extern char _dl_runtime_resolve_old[] attribute_hidden;
-  extern char _dl_runtime_profile_old[] attribute_hidden;
 
   struct pltgot {
     char *resolve;
@@ -109,6 +107,9 @@ elf_machine_runtime_setup (struct link_map *map, struct r_scope_elem *scope[],
   else
     resolve = _dl_runtime_resolve_old;
 
+#ifdef SHARED
+  extern char _dl_runtime_profile_new[] attribute_hidden;
+  extern char _dl_runtime_profile_old[] attribute_hidden;
   if (__builtin_expect (profile, 0))
     {
       if (secureplt)
@@ -123,6 +124,7 @@ elf_machine_runtime_setup (struct link_map *map, struct r_scope_elem *scope[],
 	  GL(dl_profile_map) = map;
 	}
     }
+#endif
 
   pg->resolve = resolve;
   pg->link = map;

sysdeps/alpha/dl-trampoline.S

@@ -89,6 +89,7 @@ _dl_runtime_resolve_new:
 	.globl	_dl_runtime_profile_new
 	.type	_dl_runtime_profile_new, @function
 
+#ifdef SHARED
 #undef FRAMESIZE
 #define FRAMESIZE	20*8
 
@@ -207,6 +208,7 @@ _dl_runtime_profile_new:
 
 	cfi_endproc
 	.size	_dl_runtime_profile_new, .-_dl_runtime_profile_new
+#endif /* SHARED */
 
 	.align	4
 	.globl	_dl_runtime_resolve_old
@@ -340,6 +342,7 @@ _dl_runtime_resolve_old:
 	.usepv	_dl_runtime_profile_old, no
 	.type	_dl_runtime_profile_old, @function
 
+#ifdef SHARED
 	/* We save the registers in a different order than desired by
 	   .mask/.fmask, so we have to use explicit cfi directives.  */
 	cfi_startproc
@@ -538,3 +541,4 @@ _dl_runtime_profile_old:
 
 	cfi_endproc
 	.size	_dl_runtime_profile_old, .-_dl_runtime_profile_old
+#endif /* SHARED */

sysdeps/arm/dl-machine.h

@@ -65,7 +65,6 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 {
   Elf32_Addr *got;
   extern void _dl_runtime_resolve (Elf32_Word);
-  extern void _dl_runtime_profile (Elf32_Word);
 
   if (l->l_info[DT_JMPREL] && lazy)
     {
@@ -88,6 +87,8 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.  In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.  */
+#ifdef SHARED
+      extern void _dl_runtime_profile (Elf32_Word);
       if (profile)
 	{
 	  got[2] = (Elf32_Addr) &_dl_runtime_profile;
@@ -99,6 +100,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	/* This function will get called to fix up the GOT entry indicated by
 	   the offset on the stack, and then jump to the resolved address.  */
 	got[2] = (Elf32_Addr) &_dl_runtime_resolve;

sysdeps/arm/dl-trampoline.S

@@ -70,7 +70,7 @@ _dl_runtime_resolve:
 	cfi_endproc
 	.size _dl_runtime_resolve, .-_dl_runtime_resolve
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 	.globl _dl_runtime_profile
 	.type _dl_runtime_profile, #function
 	CFI_SECTIONS

sysdeps/hppa/dl-machine.h

@@ -195,7 +195,6 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
   end_jmprel = jmprel + l->l_info[DT_PLTRELSZ]->d_un.d_val;
 
   extern void _dl_runtime_resolve (void);
-  extern void _dl_runtime_profile (void);
 
   /* Linking lazily */
   if (lazy)
@@ -235,22 +234,9 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	      got[1] = (Elf32_Addr) l;
 
 	      /* This function will be called to perform the relocation. */
-	      if (__builtin_expect (!profile, 1))
+#ifdef SHARED
-		{
+	      extern void _dl_runtime_profile (void);
-		  /* If a static application called us, then _dl_runtime_resolve is not
+	      if (__glibc_unlikely (profile))
-		     a function descriptor, but the *real* address of the function... */
-		  if((unsigned long) &_dl_runtime_resolve & 3)
-		    {
-		      got[-2] = (Elf32_Addr) ((struct fdesc *)
-				  ((unsigned long) &_dl_runtime_resolve & ~3))->ip;
-		    }
-		  else
-		    {
-		      /* Static executable! */
-		      got[-2] = (Elf32_Addr) &_dl_runtime_resolve;
-		    }
-		}
-	      else
 		{
 		  if (GLRO(dl_profile) != NULL
 		      && _dl_name_match_p (GLRO(dl_profile), l))
@@ -272,6 +258,22 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 		      got[-2] = (Elf32_Addr) &_dl_runtime_profile;
 		    }
 		}
+	      else
+#endif
+		{
+		  /* If a static application called us, then _dl_runtime_resolve is not
+		     a function descriptor, but the *real* address of the function... */
+		  if((unsigned long) &_dl_runtime_resolve & 3)
+		    {
+		      got[-2] = (Elf32_Addr) ((struct fdesc *)
+				  ((unsigned long) &_dl_runtime_resolve & ~3))->ip;
+		    }
+		  else
+		    {
+		      /* Static executable! */
+		      got[-2] = (Elf32_Addr) &_dl_runtime_resolve;
+		    }
+		}
 	      /* Plunk in the gp of this function descriptor so we
 		 can make the call to _dl_runtime_xxxxxx */
 	      got[-1] = ltp;

sysdeps/hppa/dl-trampoline.S

@@ -156,6 +156,7 @@ _dl_runtime_resolve:
 	cfi_endproc
 	.size   _dl_runtime_resolve, . - _dl_runtime_resolve
 
+#ifdef SHARED
         .text
         .global _dl_runtime_profile
         .type _dl_runtime_profile,@function
@@ -359,3 +360,4 @@ L(cont):
         .PROCEND
 	cfi_endproc
 	.size   _dl_runtime_profile, . - _dl_runtime_profile
+#endif

sysdeps/i386/dl-machine.h

@@ -92,6 +92,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.  In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.  */
+#ifdef SHARED
       if (__glibc_unlikely (profile))
 	{
 	  got[2] = (shstk_enabled
@@ -105,6 +106,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	/* This function will get called to fix up the GOT entry indicated by
 	   the offset on the stack, and then jump to the resolved address.  */
 	got[2] = (shstk_enabled

sysdeps/i386/dl-trampoline.S

@@ -70,7 +70,7 @@ _dl_runtime_resolve_shstk:
 	cfi_endproc
 	.size _dl_runtime_resolve_shstk, .-_dl_runtime_resolve_shstk
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 # The SHSTK compatible version.
 	.globl _dl_runtime_profile_shstk
 	.type _dl_runtime_profile_shstk, @function

sysdeps/ia64/dl-machine.h

@@ -121,9 +121,8 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
       reserve[0] = (Elf64_Addr) l;
 
       /* This function will be called to perform the relocation.  */
-      if (!profile)
+#ifdef SHARED
-	doit = (Elf64_Addr) ELF_PTR_TO_FDESC (&_dl_runtime_resolve)->ip;
+      if (__glibc_unlikely (profile))
-      else
 	{
 	  if (GLRO(dl_profile) != NULL
 	      && _dl_name_match_p (GLRO(dl_profile), l))
@@ -134,6 +133,11 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    }
 	  doit = (Elf64_Addr) ELF_PTR_TO_FDESC (&_dl_runtime_profile)->ip;
 	}
+      else
+#endif
+	{
+	  doit = (Elf64_Addr) ELF_PTR_TO_FDESC (&_dl_runtime_resolve)->ip;
+	}
 
       reserve[1] = doit;
       reserve[2] = gp;

sysdeps/ia64/dl-trampoline.S

@@ -188,7 +188,7 @@ END(_dl_runtime_resolve)
 #define PLTENTER_FRAME_SIZE (4*8 + 8*8 + 8*16 + 2*8 + 16)
 #define PLTEXIT_FRAME_SIZE (PLTENTER_FRAME_SIZE + 4*8 + 8*16)
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 ENTRY(_dl_runtime_profile)
 	{ .mii
 	  .prologue

sysdeps/loongarch/dl-machine.h

@@ -287,15 +287,16 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.  In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.  */
+#ifdef SHARED
       if (profile != 0)
 	{
-#if !defined __loongarch_soft_float
+# if !defined __loongarch_soft_float
 	  if (SUPPORT_LASX)
 	    gotplt[0] = (ElfW(Addr)) &_dl_runtime_profile_lasx;
 	  else if (SUPPORT_LSX)
 	    gotplt[0] = (ElfW(Addr)) &_dl_runtime_profile_lsx;
 	  else
-#endif
+# endif
 	    gotplt[0] = (ElfW(Addr)) &_dl_runtime_profile;
 
 	  if (GLRO(dl_profile) != NULL
@@ -305,6 +306,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	{
 	  /* This function will get called to fix up the GOT entry
 	     indicated by the offset on the stack, and then jump to

sysdeps/loongarch/dl-trampoline.h

@@ -126,6 +126,7 @@ ENTRY (_dl_runtime_resolve)
 	jirl	zero, t1, 0
 END (_dl_runtime_resolve)
 
+#ifdef SHARED
 #include "dl-link.h"
 
 ENTRY (_dl_runtime_profile)
@@ -367,3 +368,4 @@ ENTRY (_dl_runtime_profile)
 	jirl	zero, ra, 0
 
 END (_dl_runtime_profile)
+#endif /* SHARED */

sysdeps/m68k/dl-machine.h

@@ -75,7 +75,6 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 {
   Elf32_Addr *got;
   extern void _dl_runtime_resolve (Elf32_Word);
-  extern void _dl_runtime_profile (Elf32_Word);
 
   if (l->l_info[DT_JMPREL] && lazy)
     {
@@ -93,6 +92,8 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.  In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.  */
+#ifdef SHARED
+      extern void _dl_runtime_profile (Elf32_Word);
       if (profile)
 	{
 	  got[2] = (Elf32_Addr) &_dl_runtime_profile;
@@ -106,6 +107,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    }
 	}
       else
+#endif
 	/* This function will get called to fix up the GOT entry indicated by
 	   the offset on the stack, and then jump to the resolved address.  */
 	got[2] = (Elf32_Addr) &_dl_runtime_resolve;

sysdeps/m68k/dl-trampoline.S

@@ -60,6 +60,7 @@ _dl_runtime_resolve:
 	cfi_endproc
 	.size _dl_runtime_resolve, . - _dl_runtime_resolve
 
+#ifdef SHARED
 	.text
 	.globl _dl_runtime_profile
 	.type _dl_runtime_profile, @function
@@ -220,3 +221,4 @@ _dl_runtime_profile:
 	rts
 	cfi_endproc
 	.size _dl_runtime_profile, . - _dl_runtime_profile
+#endif /* SHARED */

sysdeps/powerpc/powerpc32/dl-machine.c

@@ -226,7 +226,7 @@ __elf_machine_runtime_setup (struct link_map *map, int lazy, int profile)
 	  Elf32_Word dlrr;
 	  Elf32_Word offset;
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 	  dlrr = (Elf32_Word) (profile
 			       ? _dl_prof_resolve
 			       : _dl_runtime_resolve);

sysdeps/powerpc/powerpc32/dl-machine.h

@@ -188,15 +188,19 @@ elf_machine_runtime_setup (struct link_map *map, struct r_scope_elem *scope[],
       extern void _dl_runtime_resolve (void);
       extern void _dl_prof_resolve (void);
 
-      if (__glibc_likely (!profile))
+#ifdef SHARED
-	dlrr = _dl_runtime_resolve;
+      if (__glibc_unlikely (profile))
-      else
 	{
 	  if (GLRO(dl_profile) != NULL
 	      &&_dl_name_match_p (GLRO(dl_profile), map))
 	    GL(dl_profile_map) = map;
 	  dlrr = _dl_prof_resolve;
 	}
+      else
+#endif
+	{
+	  dlrr = _dl_runtime_resolve;
+	}
       got = (Elf32_Addr *) map->l_info[DT_PPC(GOT)]->d_un.d_ptr;
       glink = got[1];
       got[1] = (Elf32_Addr) dlrr;

sysdeps/powerpc/powerpc32/dl-trampoline.S

@@ -70,7 +70,7 @@ _dl_runtime_resolve:
 	cfi_endproc
 	.size	 _dl_runtime_resolve,.-_dl_runtime_resolve
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 	.align 2
 	.globl _dl_prof_resolve
 	.type _dl_prof_resolve,@function

sysdeps/powerpc/powerpc64/dl-machine.h

@@ -362,13 +362,19 @@ elf_machine_runtime_setup (struct link_map *map, struct r_scope_elem *scope[],
 	  Elf64_Word offset;
 	  Elf64_Addr dlrr;
 
-	  dlrr = (Elf64_Addr) (profile ? _dl_profile_resolve
+#ifdef SHARED
-				       : _dl_runtime_resolve);
+	  if (__glibc_unlikely (profile))
-	  if (profile && GLRO(dl_profile) != NULL
+	    {
-	      && _dl_name_match_p (GLRO(dl_profile), map))
+	      dlrr = (Elf64_Addr) _dl_profile_resolve;
-	    /* This is the object we are looking for.  Say that we really
+	      if (profile && GLRO(dl_profile) != NULL
-	       want profiling and the timers are started.  */
+		  && _dl_name_match_p (GLRO(dl_profile), map))
-	    GL(dl_profile_map) = map;
+		/* This is the object we are looking for.  Say that we really
+		   want profiling and the timers are started.  */
+		GL(dl_profile_map) = map;
+	    }
+	  else
+#endif
+	    dlrr = (Elf64_Addr) _dl_runtime_resolve;
 
 #if _CALL_ELF != 2
 	  /* We need to stuff the address/TOC of _dl_runtime_resolve

sysdeps/powerpc/powerpc64/dl-trampoline.S

@@ -195,7 +195,7 @@ END(_dl_runtime_resolve)
    and r11 contains the link_map (from PLT0+16).  The link_map becomes
    parm1 (r3) and the index (r0) needs to be converted to an offset
    (index * 24) in parm2 (r4).  */
-#ifndef PROF
+#if !defined PROF && defined SHARED
 	.hidden _dl_profile_resolve
 ENTRY (_dl_profile_resolve, 4)
 /* Spill r30, r31 to preserve the link_map* and reloc_addr, in case we

sysdeps/s390/s390-32/dl-machine.h

@@ -124,16 +124,17 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.  In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.  */
+#ifdef SHARED
       if (__glibc_unlikely (profile))
 	{
-#if defined HAVE_S390_VX_ASM_SUPPORT
+# if defined HAVE_S390_VX_ASM_SUPPORT
 	  if (GLRO(dl_hwcap) & HWCAP_S390_VX)
 	    got[2] = (Elf32_Addr) &_dl_runtime_profile_vx;
 	  else
 	    got[2] = (Elf32_Addr) &_dl_runtime_profile;
-#else
+# else
 	  got[2] = (Elf32_Addr) &_dl_runtime_profile;
-#endif
+# endif
 
 	  if (GLRO(dl_profile) != NULL
 	      && _dl_name_match_p (GLRO(dl_profile), l))
@@ -142,6 +143,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	{
 	  /* This function will get called to fix up the GOT entry indicated by
 	     the offset on the stack, and then jump to the resolved address.  */

sysdeps/s390/s390-32/dl-trampoline.h

@@ -148,7 +148,7 @@ _dl_runtime_resolve:
 #undef F0_OFF
 #undef F2_OFF
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 # define SIZEOF_STRUCT_LA_S390_32_REGS 168
 # define REGS_OFF -264
 # define R2_OFF -264

sysdeps/s390/s390-64/dl-machine.h

@@ -111,16 +111,17 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.	 In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.	*/
+#ifdef SHARED
       if (__glibc_unlikely (profile))
 	{
-#if defined HAVE_S390_VX_ASM_SUPPORT
+# if defined HAVE_S390_VX_ASM_SUPPORT
 	  if (GLRO(dl_hwcap) & HWCAP_S390_VX)
 	    got[2] = (Elf64_Addr) &_dl_runtime_profile_vx;
 	  else
 	    got[2] = (Elf64_Addr) &_dl_runtime_profile;
-#else
+# else
 	  got[2] = (Elf64_Addr) &_dl_runtime_profile;
-#endif
+# endif
 
 	  if (GLRO(dl_profile) != NULL
 	      && _dl_name_match_p (GLRO(dl_profile), l))
@@ -129,6 +130,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	{
 	  /* This function will get called to fix up the GOT entry indicated by
 	     the offset on the stack, and then jump to the resolved address.  */

sysdeps/s390/s390-64/dl-trampoline.h

@@ -150,7 +150,7 @@ _dl_runtime_resolve:
 #undef F4_OFF
 #undef F6_OFF
 
-#ifndef PROF
+#if !defined PROF && defined SHARED
 # define SIZEOF_STRUCT_LA_S390_64_REGS 200
 # define REGS_OFF -360
 # define R2_OFF -360

sysdeps/sh/dl-machine.h

@@ -101,6 +101,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 to intercept the calls to collect information.	 In this case we
 	 don't store the address in the GOT so that all future calls also
 	 end in this function.	*/
+#ifdef SHARED
       if (profile)
 	{
 	  got[2] = (Elf32_Addr) &_dl_runtime_profile;
@@ -110,6 +111,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	/* This function will get called to fix up the GOT entry indicated by
 	   the offset on the stack, and then jump to the resolved address.  */
 	got[2] = (Elf32_Addr) &_dl_runtime_resolve;

sysdeps/sh/dl-trampoline.S

@@ -142,6 +142,7 @@ _dl_runtime_resolve:
 	.size _dl_runtime_resolve, .-_dl_runtime_resolve
 
 
+#ifdef SHARED
 	.globl _dl_runtime_profile
 	.type _dl_runtime_profile,@function
 	cfi_startproc
@@ -428,3 +429,4 @@ _dl_runtime_profile:
 8:	.long _dl_audit_pltexit
 #endif
 	.size _dl_runtime_profile, .-_dl_runtime_profile
+#endif /* SHARED */

sysdeps/sparc/sparc32/dl-machine.h

@@ -116,7 +116,8 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	 bits of %g1 with an offset into the .rela.plt section and jump to
 	 the beginning of the PLT.  */
       plt = (Elf32_Addr *) D_PTR (l, l_info[DT_PLTGOT]);
-      if (__builtin_expect(profile, 0))
+#ifdef SHARED
+      if (__glibc_unlikely (profile))
 	{
 	  rfunc = (Elf32_Addr) &_dl_runtime_profile;
 
@@ -125,6 +126,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	{
 	  rfunc = (Elf32_Addr) &_dl_runtime_resolve;
 	}

sysdeps/sparc/sparc32/dl-trampoline.S

@@ -47,6 +47,7 @@ _dl_runtime_resolve:
 
 	.size	_dl_runtime_resolve, .-_dl_runtime_resolve
 
+#ifdef SHARED
 	/* For the profiling cases we pass in our stack frame
 	 * as the base of the La_sparc32_regs, so it looks
 	 * like:
@@ -185,3 +186,4 @@ _dl_runtime_profile:
 	cfi_endproc
 
 	.size	_dl_runtime_profile, .-_dl_runtime_profile
+#endif

sysdeps/sparc/sparc64/dl-machine.h

@@ -136,7 +136,8 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
       Elf64_Addr res0_addr, res1_addr;
       unsigned int *plt = (void *) D_PTR (l, l_info[DT_PLTGOT]);
 
-      if (__builtin_expect(profile, 0))
+#ifdef SHARED
+      if (__glibc_unlikely (profile))
 	{
 	  res0_addr = (Elf64_Addr) &_dl_runtime_profile_0;
 	  res1_addr = (Elf64_Addr) &_dl_runtime_profile_1;
@@ -146,6 +147,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	{
 	  res0_addr = (Elf64_Addr) &_dl_runtime_resolve_0;
 	  res1_addr = (Elf64_Addr) &_dl_runtime_resolve_1;

sysdeps/sparc/sparc64/dl-trampoline.S

@@ -92,6 +92,7 @@ _dl_runtime_resolve_1:
 
 	.size	_dl_runtime_resolve_1, .-_dl_runtime_resolve_1
 
+#ifdef SHARED
 	/* For the profiling cases we pass in our stack frame
 	 * as the base of the La_sparc64_regs, so it looks
 	 * like:
@@ -323,3 +324,4 @@ _dl_runtime_profile_1:
 	cfi_endproc
 
 	.size	_dl_runtime_resolve_1, .-_dl_runtime_resolve_1
+#endif

sysdeps/x86_64/dl-machine.h

@@ -89,6 +89,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 
       const struct cpu_features* cpu_features = __get_cpu_features ();
 
+#ifdef SHARED
       /* The got[2] entry contains the address of a function which gets
 	 called to get the address of a so far unresolved function and
 	 jump to it.  The profiling extension of the dynamic linker allows
@@ -111,6 +112,7 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
 	    GL(dl_profile_map) = l;
 	}
       else
+#endif
 	{
 	  /* This function will get called to fix up the GOT entry
 	     indicated by the offset on the stack, and then jump to

sysdeps/x86_64/dl-trampoline.S

@@ -53,45 +53,49 @@
 
 #define RESTORE_AVX
 
-#define VEC_SIZE		64
+#ifdef SHARED
-#define VMOVA			vmovdqa64
+# define VEC_SIZE		64
-#define VEC(i)			zmm##i
+# define VMOVA			vmovdqa64
-#define _dl_runtime_profile	_dl_runtime_profile_avx512
+# define VEC(i)			zmm##i
-# define SECTION(p)		p##.evex512
+# define _dl_runtime_profile	_dl_runtime_profile_avx512
-#include "dl-trampoline.h"
+#  define SECTION(p)		p##.evex512
-#undef _dl_runtime_profile
-#undef VEC
-#undef VMOVA
-#undef VEC_SIZE
-#undef SECTION
-
-#if MINIMUM_X86_ISA_LEVEL <= AVX_X86_ISA_LEVEL
-# define VEC_SIZE		32
-# define VMOVA			vmovdqa
-# define VEC(i)			ymm##i
-# define SECTION(p)		p##.avx
-# define _dl_runtime_profile	_dl_runtime_profile_avx
 # include "dl-trampoline.h"
 # undef _dl_runtime_profile
 # undef VEC
 # undef VMOVA
 # undef VEC_SIZE
 # undef SECTION
-#endif
+
+# if MINIMUM_X86_ISA_LEVEL <= AVX_X86_ISA_LEVEL
+#  define VEC_SIZE		32
+#  define VMOVA			vmovdqa
+#  define VEC(i)			ymm##i
+#  define SECTION(p)		p##.avx
+#  define _dl_runtime_profile	_dl_runtime_profile_avx
+#  include "dl-trampoline.h"
+#  undef _dl_runtime_profile
+#  undef VEC
+#  undef VMOVA
+#  undef VEC_SIZE
+#  undef SECTION
+# endif
+
+# if MINIMUM_X86_ISA_LEVEL < AVX_X86_ISA_LEVEL
+/* movaps/movups is 1-byte shorter.  */
+#  define VEC_SIZE		16
+#  define VMOVA			movaps
+#  define VEC(i)			xmm##i
+#  define _dl_runtime_profile	_dl_runtime_profile_sse
+#  undef RESTORE_AVX
+#  include "dl-trampoline.h"
+#  undef _dl_runtime_profile
+#  undef VEC
+#  undef VMOVA
+#  undef VEC_SIZE
+# endif
+#endif /* SHARED */
 
 #if MINIMUM_X86_ISA_LEVEL < AVX_X86_ISA_LEVEL
-/* movaps/movups is 1-byte shorter.  */
-# define VEC_SIZE		16
-# define VMOVA			movaps
-# define VEC(i)			xmm##i
-# define _dl_runtime_profile	_dl_runtime_profile_sse
-# undef RESTORE_AVX
-# include "dl-trampoline.h"
-# undef _dl_runtime_profile
-# undef VEC
-# undef VMOVA
-# undef VEC_SIZE
-
 # define USE_FXSAVE
 # define STATE_SAVE_ALIGNMENT	16
 # define _dl_runtime_resolve	_dl_runtime_resolve_fxsave