[glibc/maskray/clang] elf: Assume disjointed .rela.dyn and .rela.plt for loader

[glibc/maskray/clang] elf: Assume disjointed .rela.dyn and .rela.plt for loader

[Fangrui Song]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=f64f4ce069300f33e26b025ebb0233d5ca3957a5

commit f64f4ce069300f33e26b025ebb0233d5ca3957a5
Author: Adhemerval Zanella <adhemerval.zanella@linaro.org>
Date:   Fri Oct 29 10:29:54 2021 -0300

    elf: Assume disjointed .rela.dyn and .rela.plt for loader
    
    The patch removes the the ELF_DURING_STARTUP optimization and assume
    both .rel.dyn and .rel.plt might not be subsequent.  This allows some
    code simplification since relocation will be handled independently
    where it is done on bootstrap.
    
    At least on x86_64_64, I can not measure any performance implications.
    Running 10000 time the command
    
      LD_DEBUG=statistics ./elf/ld.so ./libc.so
    
    And filtering the "total startup time in dynamic loader" result,
    the geometric mean is:
    
                      patched       master
      Ryzen 7 5900x     24140        24952
      i7-4510U          45957        45982
    
    (The results do show some variation, I did not make any statistical
    analysis).
    
    It also allows build arm with lld, since it inserts ".ARM.exidx"
    between ".rel.dyn" and ".rel.plt" for the loader.
    
    Checked on x86_64-linux-gnu and arm-linux-gnueabihf.
    
    Reviewed-by: H.J. Lu <hjl.tools@gmail.com>

Diff:
---
 elf/dynamic-link.h | 32 +++++++++-----------------------
 1 file changed, 9 insertions(+), 23 deletions(-)

diff --git a/elf/dynamic-link.h b/elf/dynamic-link.h
index ac4cc70dea..f619615e5c 100644
--- a/elf/dynamic-link.h
+++ b/elf/dynamic-link.h
@@ -65,12 +65,6 @@ elf_machine_lazy_rel (struct link_map *map, struct r_scope_elem *scope[],
 
 #ifdef RESOLVE_MAP
 
-# if defined RTLD_BOOTSTRAP || defined STATIC_PIE_BOOTSTRAP
-#  define ELF_DURING_STARTUP (1)
-# else
-#  define ELF_DURING_STARTUP (0)
-# endif
-
 /* Get the definitions of `elf_dynamic_do_rel' and `elf_dynamic_do_rela'.
    These functions are almost identical, so we use cpp magic to avoid
    duplicating their code.  It cannot be done in a more general function
@@ -106,9 +100,8 @@ elf_machine_lazy_rel (struct link_map *map, struct r_scope_elem *scope[],
 									      \
 	if (ranges[0].start + ranges[0].size == (start + size))		      \
 	  ranges[0].size -= size;					      \
-	if (ELF_DURING_STARTUP						      \
-	    || (!(do_lazy)						      \
-		&& (ranges[0].start + ranges[0].size) == start))	      \
+	if (!(do_lazy)							      \
+	    && (ranges[0].start + ranges[0].size) == start)		      \
 	  {								      \
 	    /* Combine processing the sections.  */			      \
 	    ranges[0].size += size;					      \
@@ -121,20 +114,13 @@ elf_machine_lazy_rel (struct link_map *map, struct r_scope_elem *scope[],
 	  }								      \
       }									      \
 									      \
-    if (ELF_DURING_STARTUP)						      \
-      elf_dynamic_do_##reloc ((map), scope, ranges[0].start, ranges[0].size,  \
-			      ranges[0].nrelative, 0, skip_ifunc);  \
-    else								      \
-      {									      \
-	int ranges_index;						      \
-	for (ranges_index = 0; ranges_index < 2; ++ranges_index)	      \
-	  elf_dynamic_do_##reloc ((map), scope,				      \
-				  ranges[ranges_index].start,		      \
-				  ranges[ranges_index].size,		      \
-				  ranges[ranges_index].nrelative,	      \
-				  ranges[ranges_index].lazy,		      \
-				  skip_ifunc);		      \
-      }									      \
+      for (int ranges_index = 0; ranges_index < 2; ++ranges_index)	      \
+        elf_dynamic_do_##reloc ((map), scope,				      \
+				ranges[ranges_index].start,		      \
+				ranges[ranges_index].size,		      \
+				ranges[ranges_index].nrelative,		      \
+				ranges[ranges_index].lazy,		      \
+				skip_ifunc);				      \
   } while (0)
 
 # if ELF_MACHINE_NO_REL || ELF_MACHINE_NO_RELA