ld: Limit cache size and add --max-cache-size=SIZE

When link_info.keep_memory is true, linker caches the relocation
information and symbol tables of input files in memory.  When there
are many input files with many relocations, we may run out of memory.
Add --max-cache-size=SIZE to set the maximum cache size.

bfd/

	PR ld/18028
	* bfd.c (bfd): Add alloc_size.
	* elf-bfd.h (_bfd_elf_link_info_read_relocs): New.
	* elf32-i386.c (elf_i386_check_relocs): Use _bfd_link_keep_memory.
	Update cache_size.
	* elf64-x86-64.c (elf_x86_64_check_relocs): Likewise.
	* elflink.c (_bfd_elf_link_read_relocs): Renamed to ...
	(_bfd_elf_link_info_read_relocs): This.  Update cache_size.
	(_bfd_elf_link_read_relocs): New.
	(_bfd_elf_link_check_relocs): Call _bfd_elf_link_info_read_relocs
	instead of _bfd_elf_link_read_relocs.
	(elf_link_add_object_symbols): Likewise.
	(elf_link_input_bfd): Likewise.
	(init_reloc_cookie_rels): Likewise.
	(init_reloc_cookie): Update cache_size.  Call
	_bfd_elf_link_info_read_relocs instead of
	_bfd_elf_link_read_relocs.
	(link_info_ok): New.
	(elf_gc_smash_unused_vtentry_relocs): Updated.  Call
	_bfd_elf_link_info_read_relocs instead of
	_bfd_elf_link_read_relocs.
	(bfd_elf_gc_sections): Use link_info_ok.  Pass &link_info_ok
	to elf_gc_smash_unused_vtentry_relocs.
	* libbfd-in.h (_bfd_link_keep_memory): New.
	* linker.c (_bfd_link_keep_memory): New.
	* opncls.c (bfd_alloc): Update alloc_size.
	* bfd-in2.h: Regenerated.
	* libbfd.h: Likewise.

include/

	PR ld/18028
	* bfdlink.h (bfd_link_info): Add cache_size and max_cache_size.

ld/

	PR ld/18028
	* NEWS: Mention --max-cache-size=SIZE.
	* ld.texi: Document --max-cache-size=SIZE.
	* ldlex.h (option_values): Add OPTION_MAX_CACHE_SIZE.
	* ldmain.c: (main): Set link_info.max_cache_size to -1.
	* lexsup.c (ld_options): Add --max-cache-size=SIZE.
	(parse_args): Support OPTION_MAX_CACHE_SIZE.
	* testsuite/ld-bootstrap/bootstrap.exp: Add test for
	--max-cache-size=-1.

17 files changed, 158 insertions, 26 deletions

diff --git a/bfd/bfd-in2.h b/bfd/bfd-in2.h
index 9a69831..43d4ff0 100644
--- a/bfd/bfd-in2.h
+++ b/bfd/bfd-in2.h
@@ -6717,6 +6717,9 @@ struct bfd
      be used only for archive elements.  */
   int archive_pass;
 
+  /* The total size of memory from bfd_alloc.  */
+  bfd_size_type alloc_size;
+
   /* Stuff only useful for object files:
      The start address.  */
   bfd_vma start_address;
diff --git a/bfd/bfd.c b/bfd/bfd.c
index 0952aae..eb555ad 100644
--- a/bfd/bfd.c
+++ b/bfd/bfd.c
@@ -286,6 +286,9 @@ CODE_FRAGMENT
 .     be used only for archive elements.  *}
 .  int archive_pass;
 .
+.  {* The total size of memory from bfd_alloc.  *}
+.  bfd_size_type alloc_size;
+.
 .  {* Stuff only useful for object files:
 .     The start address.  *}
 .  bfd_vma start_address;
diff --git a/bfd/elf-bfd.h b/bfd/elf-bfd.h
index 8f985ab..65c08ca 100644
--- a/bfd/elf-bfd.h
+++ b/bfd/elf-bfd.h
@@ -2482,6 +2482,9 @@ extern char *_bfd_elfcore_strndup
 
 extern Elf_Internal_Rela *_bfd_elf_link_read_relocs
   (bfd *, asection *, void *, Elf_Internal_Rela *, bool);
+extern Elf_Internal_Rela *_bfd_elf_link_info_read_relocs
+  (bfd *, struct bfd_link_info *, asection *, void *, Elf_Internal_Rela *,
+   bool);
 
 extern bool _bfd_elf_link_output_relocs
   (bfd *, asection *, Elf_Internal_Shdr *, Elf_Internal_Rela *,
diff --git a/bfd/elf32-i386.c b/bfd/elf32-i386.c
index cf7cd07..1898ba3 100644
--- a/bfd/elf32-i386.c
+++ b/bfd/elf32-i386.c
@@ -1915,13 +1915,14 @@ elf_i386_check_relocs (bfd *abfd,
 
   if (elf_section_data (sec)->this_hdr.contents != contents)
     {
-      if (!converted && !info->keep_memory)
+      if (!converted && !_bfd_link_keep_memory (info))
 	free (contents);
       else
 	{
 	  /* Cache the section contents for elf_link_input_bfd if any
 	     load is converted or --no-keep-memory isn't used.  */
 	  elf_section_data (sec)->this_hdr.contents = contents;
+	  info->cache_size += sec->size;
 	}
     }
 
diff --git a/bfd/elf64-x86-64.c b/bfd/elf64-x86-64.c
index 98fb881..4c55c59 100644
--- a/bfd/elf64-x86-64.c
+++ b/bfd/elf64-x86-64.c
@@ -2365,13 +2365,14 @@ elf_x86_64_check_relocs (bfd *abfd, struct bfd_link_info *info,
 
   if (elf_section_data (sec)->this_hdr.contents != contents)
     {
-      if (!converted && !info->keep_memory)
+      if (!converted && !_bfd_link_keep_memory (info))
 	free (contents);
       else
 	{
 	  /* Cache the section contents for elf_link_input_bfd if any
 	     load is converted or --no-keep-memory isn't used.  */
 	  elf_section_data (sec)->this_hdr.contents = contents;
+	  info->cache_size += sec->size;
 	}
     }
 
diff --git a/bfd/elflink.c b/bfd/elflink.c
index 9a05208..003c954 100644
--- a/bfd/elflink.c
+++ b/bfd/elflink.c
@@ -2619,14 +2619,16 @@ elf_link_read_relocs_from_section (bfd *abfd,
    according to the KEEP_MEMORY argument.  If O has two relocation
    sections (both REL and RELA relocations), then the REL_HDR
    relocations will appear first in INTERNAL_RELOCS, followed by the
-   RELA_HDR relocations.  */
+   RELA_HDR relocations.  If INFO isn't NULL and KEEP_MEMORY is true,
+   update cache_size.  */
 
 Elf_Internal_Rela *
-_bfd_elf_link_read_relocs (bfd *abfd,
-			   asection *o,
-			   void *external_relocs,
-			   Elf_Internal_Rela *internal_relocs,
-			   bool keep_memory)
+_bfd_elf_link_info_read_relocs (bfd *abfd,
+				struct bfd_link_info *info,
+				asection *o,
+				void *external_relocs,
+				Elf_Internal_Rela *internal_relocs,
+				bool keep_memory)
 {
   void *alloc1 = NULL;
   Elf_Internal_Rela *alloc2 = NULL;
@@ -2646,7 +2648,11 @@ _bfd_elf_link_read_relocs (bfd *abfd,
 
       size = (bfd_size_type) o->reloc_count * sizeof (Elf_Internal_Rela);
       if (keep_memory)
-	internal_relocs = alloc2 = (Elf_Internal_Rela *) bfd_alloc (abfd, size);
+	{
+	  internal_relocs = alloc2 = (Elf_Internal_Rela *) bfd_alloc (abfd, size);
+	  if (info)
+	    info->cache_size += size;
+	}
       else
 	internal_relocs = alloc2 = (Elf_Internal_Rela *) bfd_malloc (size);
       if (internal_relocs == NULL)
@@ -2710,6 +2716,22 @@ _bfd_elf_link_read_relocs (bfd *abfd,
   return NULL;
 }
 
+/* This is similar to _bfd_elf_link_info_read_relocs, except for that
+   NULL is passed to _bfd_elf_link_info_read_relocs for pointer to
+   struct bfd_link_info.  */
+
+Elf_Internal_Rela *
+_bfd_elf_link_read_relocs (bfd *abfd,
+			   asection *o,
+			   void *external_relocs,
+			   Elf_Internal_Rela *internal_relocs,
+			   bool keep_memory)
+{
+  return _bfd_elf_link_info_read_relocs (abfd, NULL, o, external_relocs,
+					 internal_relocs, keep_memory);
+
+}
+
 /* Compute the size of, and allocate space for, REL_HDR which is the
    section header for a section containing relocations for O.  */
 
@@ -4026,8 +4048,10 @@ _bfd_elf_link_check_relocs (bfd *abfd, struct bfd_link_info *info)
 	      || bfd_is_abs_section (o->output_section))
 	    continue;
 
-	  internal_relocs = _bfd_elf_link_read_relocs (abfd, o, NULL, NULL,
-						       info->keep_memory);
+	  internal_relocs = _bfd_elf_link_info_read_relocs (abfd, info,
+							    o, NULL,
+							    NULL,
+							    _bfd_link_keep_memory (info));
 	  if (internal_relocs == NULL)
 	    return false;
 
@@ -5356,9 +5380,10 @@ elf_link_add_object_symbols (bfd *abfd, struct bfd_link_info *info)
 		  && (s->flags & SEC_DEBUGGING) != 0))
 	    continue;
 
-	  internal_relocs = _bfd_elf_link_read_relocs (abfd, s, NULL,
-						       NULL,
-						       info->keep_memory);
+	  internal_relocs = _bfd_elf_link_info_read_relocs (abfd, info,
+							    s, NULL,
+							    NULL,
+							    _bfd_link_keep_memory (info));
 	  if (internal_relocs == NULL)
 	    goto error_free_vers;
 
@@ -11186,8 +11211,10 @@ elf_link_input_bfd (struct elf_final_link_info *flinfo, bfd *input_bfd)
 
 	  /* Get the swapped relocs.  */
 	  internal_relocs
-	    = _bfd_elf_link_read_relocs (input_bfd, o, flinfo->external_relocs,
-					 flinfo->internal_relocs, false);
+	    = _bfd_elf_link_info_read_relocs (input_bfd, flinfo->info, o,
+					      flinfo->external_relocs,
+					      flinfo->internal_relocs,
+					      false);
 	  if (internal_relocs == NULL
 	      && o->reloc_count > 0)
 	    return false;
@@ -13279,8 +13306,12 @@ init_reloc_cookie (struct elf_reloc_cookie *cookie,
 	  info->callbacks->einfo (_("%P%X: can not read symbols: %E\n"));
 	  return false;
 	}
-      if (info->keep_memory)
-	symtab_hdr->contents = (bfd_byte *) cookie->locsyms;
+      if (_bfd_link_keep_memory (info) )
+	{
+	  symtab_hdr->contents = (bfd_byte *) cookie->locsyms;
+	  info->cache_size += (cookie->locsymcount
+			       * sizeof (Elf_External_Sym_Shndx));
+	}
     }
   return true;
 }
@@ -13312,8 +13343,9 @@ init_reloc_cookie_rels (struct elf_reloc_cookie *cookie,
     }
   else
     {
-      cookie->rels = _bfd_elf_link_read_relocs (abfd, sec, NULL, NULL,
-						info->keep_memory);
+      cookie->rels = _bfd_elf_link_info_read_relocs (abfd, info, sec,
+						     NULL, NULL,
+						     _bfd_link_keep_memory (info));
       if (cookie->rels == NULL)
 	return false;
       cookie->rel = cookie->rels;
@@ -13881,14 +13913,22 @@ elf_gc_propagate_vtable_entries_used (struct elf_link_hash_entry *h, void *okp)
   return true;
 }
 
+struct link_info_ok
+{
+  struct bfd_link_info *info;
+  bool ok;
+};
+
 static bool
-elf_gc_smash_unused_vtentry_relocs (struct elf_link_hash_entry *h, void *okp)
+elf_gc_smash_unused_vtentry_relocs (struct elf_link_hash_entry *h,
+				    void *ptr)
 {
   asection *sec;
   bfd_vma hstart, hend;
   Elf_Internal_Rela *relstart, *relend, *rel;
   const struct elf_backend_data *bed;
   unsigned int log_file_align;
+  struct link_info_ok *info = (struct link_info_ok *) ptr;
 
   /* Take care of both those symbols that do not describe vtables as
      well as those that are not loaded.  */
@@ -13904,9 +13944,10 @@ elf_gc_smash_unused_vtentry_relocs (struct elf_link_hash_entry *h, void *okp)
   hstart = h->root.u.def.value;
   hend = hstart + h->size;
 
-  relstart = _bfd_elf_link_read_relocs (sec->owner, sec, NULL, NULL, true);
+  relstart = _bfd_elf_link_info_read_relocs (sec->owner, info->info,
+					     sec, NULL, NULL, true);
   if (!relstart)
-    return *(bool *) okp = false;
+    return info->ok = false;
   bed = get_elf_backend_data (sec->owner);
   log_file_align = bed->s->log_file_align;
 
@@ -14029,6 +14070,7 @@ bfd_elf_gc_sections (bfd *abfd, struct bfd_link_info *info)
   elf_gc_mark_hook_fn gc_mark_hook;
   const struct elf_backend_data *bed = get_elf_backend_data (abfd);
   struct elf_link_hash_table *htab;
+  struct link_info_ok info_ok;
 
   if (!bed->can_gc_sections
       || !is_elf_hash_table (info->hash))
@@ -14070,8 +14112,10 @@ bfd_elf_gc_sections (bfd *abfd, struct bfd_link_info *info)
     return false;
 
   /* Kill the vtable relocations that were not used.  */
-  elf_link_hash_traverse (htab, elf_gc_smash_unused_vtentry_relocs, &ok);
-  if (!ok)
+  info_ok.info = info;
+  info_ok.ok = true;
+  elf_link_hash_traverse (htab, elf_gc_smash_unused_vtentry_relocs, &info_ok);
+  if (!info_ok.ok)
     return false;
 
   /* Mark dynamically referenced symbols.  */
diff --git a/bfd/libbfd-in.h b/bfd/libbfd-in.h
index 1f7e221..89d2997 100644
--- a/bfd/libbfd-in.h
+++ b/bfd/libbfd-in.h
@@ -894,6 +894,9 @@ extern bfd_byte * _bfd_write_unsigned_leb128
 
 extern struct bfd_link_info *_bfd_get_link_info (bfd *);
 
+extern bool _bfd_link_keep_memory (struct bfd_link_info *)
+  ATTRIBUTE_HIDDEN;
+
 #if GCC_VERSION >= 7000
 #define _bfd_mul_overflow(a, b, res) __builtin_mul_overflow (a, b, res)
 #else
diff --git a/bfd/libbfd.h b/bfd/libbfd.h
index c37ddc0..6949641 100644
--- a/bfd/libbfd.h
+++ b/bfd/libbfd.h
@@ -899,6 +899,9 @@ extern bfd_byte * _bfd_write_unsigned_leb128
 
 extern struct bfd_link_info *_bfd_get_link_info (bfd *);
 
+extern bool _bfd_link_keep_memory (struct bfd_link_info *)
+  ATTRIBUTE_HIDDEN;
+
 #if GCC_VERSION >= 7000
 #define _bfd_mul_overflow(a, b, res) __builtin_mul_overflow (a, b, res)
 #else
diff --git a/bfd/linker.c b/bfd/linker.c
index c350cd3..755ff19 100644
--- a/bfd/linker.c
+++ b/bfd/linker.c
@@ -3535,3 +3535,38 @@ _bfd_nolink_bfd_define_start_stop (struct bfd_link_info *info ATTRIBUTE_UNUSED,
 {
   return (struct bfd_link_hash_entry *) _bfd_ptr_bfd_null_error (sec->owner);
 }
+
+/* Return false if linker should avoid caching relocation infomation
+   and symbol tables of input files in memory.  */
+
+bool
+_bfd_link_keep_memory (struct bfd_link_info * info)
+{
+  bfd *abfd;
+  bfd_size_type size;
+
+  if (!info->keep_memory)
+    return false;
+
+  if (info->max_cache_size == (bfd_size_type) -1)
+    return true;
+
+  abfd = info->input_bfds;
+  size = info->cache_size;
+  do
+    {
+      if (size >= info->max_cache_size)
+	{
+	  /* Over the limit.  Reduce the memory usage.  */
+	  info->keep_memory = false;
+	  return false;
+	}
+      if (!abfd)
+	break;
+      size += abfd->alloc_size;
+      abfd = abfd->link.next;
+    }
+  while (1);
+
+  return true;
+}
diff --git a/bfd/opncls.c b/bfd/opncls.c
index 4fb7932..96ff1e9 100644
--- a/bfd/opncls.c
+++ b/bfd/opncls.c
@@ -1032,6 +1032,8 @@ bfd_alloc (bfd *abfd, bfd_size_type size)
   ret = objalloc_alloc ((struct objalloc *) abfd->memory, ul_size);
   if (ret == NULL)
     bfd_set_error (bfd_error_no_memory);
+  else
+    abfd->alloc_size += size;
   return ret;
 }
 
diff --git a/include/bfdlink.h b/include/bfdlink.h
index 7f1b12d..5496858 100644
--- a/include/bfdlink.h
+++ b/include/bfdlink.h
@@ -682,6 +682,13 @@ struct bfd_link_info
 
   /* The version information.  */
   struct bfd_elf_version_tree *version_info;
+
+  /* Size of cache.  Backend can use it to keep strace cache size.   */
+  bfd_size_type cache_size;
+
+  /* The maximum cache size.  Backend can use cache_size and and
+     max_cache_size to decide if keep_memory should be honored.  */
+  bfd_size_type max_cache_size;
 };
 
 /* Some forward-definitions used by some callbacks.  */
diff --git a/ld/NEWS b/ld/NEWS
index 11bc574..92dd4fd 100644
--- a/ld/NEWS
+++ b/ld/NEWS
@@ -1,5 +1,8 @@
 -*- text -*-
 
+* Add --max-cache-size=SIZE to set the the maximum cache size to SIZE
+  bytes.
+
 Changes in 2.37:
 
 * arm-symbianelf support removed.
diff --git a/ld/ld.texi b/ld/ld.texi
index dd8f571..67c5083 100644
--- a/ld/ld.texi
+++ b/ld/ld.texi
@@ -2839,6 +2839,12 @@ has been used.
 The @option{--reduce-memory-overheads} switch may be also be used to
 enable other tradeoffs in future versions of the linker.
 
+@kindex --max-cache-size=@var{size}
+@item --max-cache-size=@var{size}
+@command{ld} normally caches the relocation information and symbol tables
+of input files in memory with the unlimited size.  This option sets the
+maximum cache size to @var{size}.
+
 @kindex --build-id
 @kindex --build-id=@var{style}
 @item --build-id
diff --git a/ld/ldlex.h b/ld/ldlex.h
index 9e8bf5f..9707d57 100644
--- a/ld/ldlex.h
+++ b/ld/ldlex.h
@@ -140,6 +140,7 @@ enum option_values
   OPTION_WARN_TEXTREL,
   OPTION_WARN_ALTERNATE_EM,
   OPTION_REDUCE_MEMORY_OVERHEADS,
+  OPTION_MAX_CACHE_SIZE,
 #if BFD_SUPPORTS_PLUGINS
   OPTION_PLUGIN,
   OPTION_PLUGIN_OPT,
diff --git a/ld/ldmain.c b/ld/ldmain.c
index 42660eb..e4c6774 100644
--- a/ld/ldmain.c
+++ b/ld/ldmain.c
@@ -331,6 +331,7 @@ main (int argc, char **argv)
 
   link_info.allow_undefined_version = true;
   link_info.keep_memory = true;
+  link_info.max_cache_size = (bfd_size_type) -1;
   link_info.combreloc = true;
   link_info.strip_discarded = true;
   link_info.prohibit_multiple_definition_absolute = false;
diff --git a/ld/lexsup.c b/ld/lexsup.c
index 00274c5..c128fe3 100644
--- a/ld/lexsup.c
+++ b/ld/lexsup.c
@@ -433,6 +433,10 @@ static const struct ld_option ld_options[] =
      OPTION_REDUCE_MEMORY_OVERHEADS},
     '\0', NULL, N_("Reduce memory overheads, possibly taking much longer"),
     TWO_DASHES },
+  { {"max-cache-size=SIZE", required_argument, NULL,
+    OPTION_MAX_CACHE_SIZE},
+    '\0', NULL, N_("Set the maximum cache size to SIZE bytes"),
+    TWO_DASHES },
   { {"relax", no_argument, NULL, OPTION_RELAX},
     '\0', NULL, N_("Reduce code size by using target specific optimizations"), TWO_DASHES },
   { {"no-relax", no_argument, NULL, OPTION_NO_RELAX},
@@ -1631,6 +1635,17 @@ parse_args (unsigned argc, char **argv)
 	    config.hash_table_size = 1021;
 	  break;
 
+	case OPTION_MAX_CACHE_SIZE:
+	  {
+	    char *end;
+	    bfd_size_type cache_size = strtoul (optarg, &end, 0);
+	    if (*end != '\0')
+	      einfo (_("%F%P: invalid cache memory size: %s\n"),
+		     optarg);
+	    link_info.max_cache_size = cache_size;
+	  }
+	  break;
+
 	case OPTION_HASH_SIZE:
 	  {
 	    bfd_size_type new_size;
diff --git a/ld/testsuite/ld-bootstrap/bootstrap.exp b/ld/testsuite/ld-bootstrap/bootstrap.exp
index b21b48a..9c27c5f 100644
--- a/ld/testsuite/ld-bootstrap/bootstrap.exp
+++ b/ld/testsuite/ld-bootstrap/bootstrap.exp
@@ -55,7 +55,8 @@ if [check_plugin_api_available] {
 # really test -r.  Use ld1 to link a fresh ld, ld2.  Use ld2 to link a
 # new ld, ld3.  ld2 and ld3 should be identical.
 set test_flags {"" "strip" "--static" "-Wl,--traditional-format"
-		"-Wl,--no-keep-memory" "-Wl,--relax"}
+		"-Wl,--no-keep-memory" "-Wl,--relax"
+		"-Wl,--max-cache-size=-1"}
 if { [istarget "powerpc-*-*"] } {
     lappend test_flags "-Wl,--ppc476-workaround"
 }