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>

39 files changed, 165 insertions, 109 deletions

diff --git a/elf/Makefile b/elf/Makefile
index 414fdbdec8..3f7f89508e 100644
--- a/elf/Makefile
+++ b/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 \
diff --git a/elf/dl-load.c b/elf/dl-load.c
index 8d351153c8..25ea4f7a4e 100644
--- a/elf/dl-load.c
+++ b/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.  */
diff --git a/elf/dl-runtime.c b/elf/dl-runtime.c
index 32a8bfcf74..fe7deda32a 100644
--- a/elf/dl-runtime.c
+++ b/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 */
diff --git a/elf/dl-support.c b/elf/dl-support.c
index 44a54dea07..31a608df87 100644
--- a/elf/dl-support.c
+++ b/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[] =
diff --git a/elf/dl-profstub.c b/elf/libc-dl-profstub.c
index 8fb8aaa88e..8fb8aaa88e 100644
--- a/elf/dl-profstub.c
+++ b/elf/libc-dl-profstub.c
diff --git a/include/dlfcn.h b/include/dlfcn.h
index ae25f05303..a44420fa37 100644
--- a/include/dlfcn.h
+++ b/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
diff --git a/sysdeps/aarch64/dl-machine.h b/sysdeps/aarch64/dl-machine.h
index 4170b9269f..a56eb96a79 100644
--- a/sysdeps/aarch64/dl-machine.h
+++ b/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
diff --git a/sysdeps/aarch64/dl-trampoline.S b/sysdeps/aarch64/dl-trampoline.S
index a3474ba741..fc82151ba2 100644
--- a/sysdeps/aarch64/dl-trampoline.S
+++ b/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
diff --git a/sysdeps/alpha/dl-machine.h b/sysdeps/alpha/dl-machine.h
index ed5389e3c5..7fe2afca93 100644
--- a/sysdeps/alpha/dl-machine.h
+++ b/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;
diff --git a/sysdeps/alpha/dl-trampoline.S b/sysdeps/alpha/dl-trampoline.S
index f8c3d33906..5dffa62587 100644
--- a/sysdeps/alpha/dl-trampoline.S
+++ b/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 */
diff --git a/sysdeps/arm/dl-machine.h b/sysdeps/arm/dl-machine.h
index d720c02c96..a68679e653 100644
--- a/sysdeps/arm/dl-machine.h
+++ b/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;
diff --git a/sysdeps/arm/dl-trampoline.S b/sysdeps/arm/dl-trampoline.S
index 23c2476917..2df5b7ee36 100644
--- a/sysdeps/arm/dl-trampoline.S
+++ b/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
diff --git a/sysdeps/hppa/dl-machine.h b/sysdeps/hppa/dl-machine.h
index 4e6e70b3c9..993593de5d 100644
--- a/sysdeps/hppa/dl-machine.h
+++ b/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))
-		{
-		  /* 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;
-		    }
-		}
-	      else
+#ifdef SHARED
+	      extern void _dl_runtime_profile (void);
+	      if (__glibc_unlikely (profile))
 		{
 		  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;
diff --git