[PATCH v2 1/5] strip: Adapt src/strip -o -f on mips

["Ying Huang" <ying.huang@oss.cipunited.com>]

From: Ying Huang <ying.huang@oss.cipunited.com>

In mips64 little-endian, r_info consists of four byte fields(contains
three reloc types) and a 32-bit symbol index. In order to adapt
GELF_R_SYM and GELF_R_TYPE, need convert raw data to get correct symbol
index and type.

  libelf/elf_getdata.c: Some eu-utils use read-mmap method to map file,
so we need to malloc and memcpy raw data to avoid segment fault. After
modification, the correct value are saved in the malloced memory not in
process address space.
  libelf/elf_updata.c: Because we converted the relocation info in mips
order when we call elf_getdata.c, so we need to convert the modified data
in original order bits before writing the data to the file.
---
 backends/Makefile.am    |   6 +-
 backends/mips_init.c    |  52 ++++++++++++++++
 backends/mips_reloc.def |  93 ++++++++++++++++++++++++++++
 backends/mips_symbol.c  |  63 +++++++++++++++++++
 libebl/eblopenbackend.c |   2 +
 libelf/elf_getdata.c    | 132 +++++++++++++++++++++++++++++++++++++++-
 libelf/elf_update.c     |  53 ++++++++++++++++
 libelf/libelfP.h        |   3 +
 8 files changed, 400 insertions(+), 4 deletions(-)
 create mode 100644 backends/mips_init.c
 create mode 100644 backends/mips_reloc.def
 create mode 100644 backends/mips_symbol.c

diff --git a/backends/Makefile.am b/backends/Makefile.am
index bbb2aac7..b946fd30 100644
--- a/backends/Makefile.am
+++ b/backends/Makefile.am
@@ -37,7 +37,7 @@ AM_CPPFLAGS += -I$(top_srcdir)/libebl -I$(top_srcdir)/libasm \
 noinst_LIBRARIES = libebl_backends.a libebl_backends_pic.a
 
 modules = i386 sh x86_64 ia64 alpha arm aarch64 sparc ppc ppc64 s390 \
-	  m68k bpf riscv csky loongarch arc
+	  m68k bpf riscv csky loongarch arc mips
 
 i386_SRCS = i386_init.c i386_symbol.c i386_corenote.c i386_cfi.c \
 	    i386_retval.c i386_regs.c i386_auxv.c \
@@ -102,12 +102,14 @@ loongarch_SRCS = loongarch_init.c loongarch_symbol.c loongarch_cfi.c \
 
 arc_SRCS = arc_init.c arc_symbol.c
 
+mips_SRCS = mips_init.c mips_symbol.c
+
 libebl_backends_a_SOURCES = $(i386_SRCS) $(sh_SRCS) $(x86_64_SRCS) \
 			    $(ia64_SRCS) $(alpha_SRCS) $(arm_SRCS) \
 			    $(aarch64_SRCS) $(sparc_SRCS) $(ppc_SRCS) \
 			    $(ppc64_SRCS) $(s390_SRCS) \
 			    $(m68k_SRCS) $(bpf_SRCS) $(riscv_SRCS) $(csky_SRCS) \
-			    $(loongarch_SRCS) $(arc_SRCS)
+			    $(loongarch_SRCS) $(arc_SRCS) $(mips_SRCS)
 
 libebl_backends_pic_a_SOURCES =
 am_libebl_backends_pic_a_OBJECTS = $(libebl_backends_a_SOURCES:.c=.os)
diff --git a/backends/mips_init.c b/backends/mips_init.c
new file mode 100644
index 00000000..e26da609
--- /dev/null
+++ b/backends/mips_init.c
@@ -0,0 +1,52 @@
+/* Initialization of MIPS specific backend library.
+   Copyright (C) 2023 CIP United Inc.
+   This file is part of elfutils.
+
+   This file is free software; you can redistribute it and/or modify
+   it under the terms of either
+
+     * the GNU Lesser General Public License as published by the Free
+       Software Foundation; either version 3 of the License, or (at
+       your option) any later version
+
+   or
+
+     * the GNU General Public License as published by the Free
+       Software Foundation; either version 2 of the License, or (at
+       your option) any later version
+
+   or both in parallel, as here.
+
+   elfutils is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   You should have received copies of the GNU General Public License and
+   the GNU Lesser General Public License along with this program.  If
+   not, see <http://www.gnu.org/licenses/>.  */
+
+#ifdef HAVE_CONFIG_H
+# include <config.h>
+#endif
+
+#define BACKEND		mips_
+#define RELOC_PREFIX	R_MIPS_
+#include "libebl_CPU.h"
+#include "libelfP.h"
+
+#define RELOC_TYPE_ID(type) ((type) & 0xff)
+
+/* This defines the common reloc hooks based on mips_reloc.def.  */
+#include "common-reloc.c"
+
+Ebl *
+mips_init (Elf *elf __attribute__ ((unused)),
+	   GElf_Half machine __attribute__ ((unused)),
+	   Ebl *eh)
+{
+  /* We handle it.  */
+  mips_init_reloc (eh);
+  HOOK (eh, reloc_simple_type);
+  return eh;
+}
diff --git a/backends/mips_reloc.def b/backends/mips_reloc.def
new file mode 100644
index 00000000..8cb66a54
--- /dev/null
+++ b/backends/mips_reloc.def
@@ -0,0 +1,93 @@
+/* List the relocation types for MIPS.  -*- C -*-
+   Copyright (C) 2023 CIP United Inc.
+   This file is part of elfutils.
+
+   This file is free software; you can redistribute it and/or modify
+   it under the terms of either
+
+     * the GNU Lesser General Public License as published by the Free
+       Software Foundation; either version 3 of the License, or (at
+       your option) any later version
+
+   or
+
+     * the GNU General Public License as published by the Free
+       Software Foundation; either version 2 of the License, or (at
+       your option) any later version
+
+   or both in parallel, as here.
+
+   elfutils is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   You should have received copies of the GNU General Public License and
+   the GNU Lesser General Public License along with this program.  If
+   not, see <http://www.gnu.org/licenses/>.  */
+
+/*	    NAME,		REL|EXEC|DYN	*/
+
+
+RELOC_TYPE (NONE,		REL|EXEC|DYN)
+RELOC_TYPE (16,		        REL|EXEC|DYN)
+RELOC_TYPE (32,	                REL)
+RELOC_TYPE (REL32,	        REL|EXEC|DYN)
+RELOC_TYPE (26,		        REL|DYN)
+RELOC_TYPE (HI16,	        REL)
+RELOC_TYPE (LO16,		REL|EXEC|DYN)
+RELOC_TYPE (GPREL16,		REL|EXEC|DYN)
+RELOC_TYPE (LITERAL,		REL|EXEC|DYN)
+RELOC_TYPE (GOT16,		REL|EXEC|DYN)
+RELOC_TYPE (PC16,		REL)
+RELOC_TYPE (CALL16,		REL)
+RELOC_TYPE (GPREL32,		REL)
+RELOC_TYPE (SHIFT5,		REL)
+RELOC_TYPE (SHIFT6,		REL)
+RELOC_TYPE (64,		        REL)
+RELOC_TYPE (GOT_DISP,		REL)
+RELOC_TYPE (GOT_PAGE,		REL)
+RELOC_TYPE (GOT_OFST,		REL)
+RELOC_TYPE (GOT_HI16,		REL)
+RELOC_TYPE (GOT_LO16,		REL)
+RELOC_TYPE (SUB,		REL)
+RELOC_TYPE (INSERT_A,		REL)
+RELOC_TYPE (INSERT_B,		REL)
+RELOC_TYPE (DELETE,		REL)
+RELOC_TYPE (HIGHER,		REL)
+RELOC_TYPE (HIGHEST,		REL)
+RELOC_TYPE (CALL_HI16,		REL)
+RELOC_TYPE (CALL_LO16,		REL)
+RELOC_TYPE (SCN_DISP,		REL)
+RELOC_TYPE (REL16,		REL)
+RELOC_TYPE (ADD_IMMEDIATE,	REL)
+RELOC_TYPE (PJUMP,		REL)
+RELOC_TYPE (RELGOT,		REL)
+RELOC_TYPE (JALR,		REL)
+RELOC_TYPE (TLS_DTPMOD32,	DYN)
+RELOC_TYPE (TLS_DTPREL32,	REL)
+RELOC_TYPE (TLS_DTPMOD64,	DYN)
+RELOC_TYPE (TLS_DTPREL64,	REL)
+RELOC_TYPE (TLS_GD,		REL)
+RELOC_TYPE (TLS_LDM,		REL)
+RELOC_TYPE (TLS_DTPREL_HI16,	REL)
+RELOC_TYPE (TLS_DTPREL_LO16,	REL)
+RELOC_TYPE (TLS_GOTTPREL,	REL)
+RELOC_TYPE (TLS_TPREL32,	REL)
+RELOC_TYPE (TLS_TPREL64,	REL)
+RELOC_TYPE (TLS_TPREL_HI16,	REL)
+RELOC_TYPE (TLS_TPREL_LO16,	REL)
+RELOC_TYPE (GLOB_DAT,		REL)
+RELOC_TYPE (PC21_S2,		REL)
+RELOC_TYPE (PC26_S2,		REL)
+RELOC_TYPE (PC18_S3,		REL)
+RELOC_TYPE (PC19_S2,		REL)
+RELOC_TYPE (PCHI16,		REL)
+RELOC_TYPE (PCLO16,		REL)
+RELOC_TYPE (COPY,		REL)
+RELOC_TYPE (JUMP_SLOT,		REL)
+RELOC_TYPE (PC32,		REL)
+RELOC_TYPE (EH,			REL)
+RELOC_TYPE (GNU_REL16_S2,	REL)
+RELOC_TYPE (GNU_VTINHERIT,	REL)
+RELOC_TYPE (GNU_VTENTRY,	REL)
diff --git a/backends/mips_symbol.c b/backends/mips_symbol.c
new file mode 100644
index 00000000..a9dd5c09
--- /dev/null
+++ b/backends/mips_symbol.c
@@ -0,0 +1,63 @@
+/* MIPS specific symbolic name handling.
+   Copyright (C) 2023 CIP United Inc.
+   This file is part of elfutils.
+
+   This file is free software; you can redistribute it and/or modify
+   it under the terms of either
+
+     * the GNU Lesser General Public License as published by the Free
+       Software Foundation; either version 3 of the License, or (at
+       your option) any later version
+
+   or
+
+     * the GNU General Public License as published by the Free
+       Software Foundation; either version 2 of the License, or (at
+       your option) any later version
+
+   or both in parallel, as here.
+
+   elfutils is distributed in the hope that it will be useful, but
+   WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+   General Public License for more details.
+
+   You should have received copies of the GNU General Public License and
+   the GNU Lesser General Public License along with this program.  If
+   not, see <http://www.gnu.org/licenses/>.  */
+
+#ifdef HAVE_CONFIG_H
+# include <config.h>
+#endif
+
+#include <system.h>
+
+#include <elf.h>
+#include <stddef.h>
+#include <string.h>
+#include <stdio.h>
+#define BACKEND		mips_
+#include "libebl_CPU.h"
+#include "libelfP.h"
+
+/* Check for the simple reloc types.  */
+Elf_Type
+mips_reloc_simple_type (Ebl *ebl, int type,
+			   int *addsub __attribute__ ((unused)))
+{
+  int typeNew = type;
+  if(ebl->elf->class == ELFCLASS64)
+    typeNew = ELF64_MIPS_R_TYPE1(type);
+  switch (typeNew)
+    {
+    case R_MIPS_64:
+      return ELF_T_XWORD;
+    case R_MIPS_32:
+      return ELF_T_WORD;
+    case R_MIPS_16:
+      return ELF_T_HALF;
+
+    default:
+      return ELF_T_NUM;
+    }
+}
diff --git a/libebl/eblopenbackend.c b/libebl/eblopenbackend.c
index 084a1544..a5f7467a 100644
--- a/libebl/eblopenbackend.c
+++ b/libebl/eblopenbackend.c
@@ -57,6 +57,7 @@ Ebl *riscv_init (Elf *, GElf_Half, Ebl *);
 Ebl *csky_init (Elf *, GElf_Half, Ebl *);
 Ebl *loongarch_init (Elf *, GElf_Half, Ebl *);
 Ebl *arc_init (Elf *, GElf_Half, Ebl *);
+Ebl *mips_init (Elf *, GElf_Half, Ebl *);
 
 /* This table should contain the complete list of architectures as far
    as the ELF specification is concerned.  */
@@ -154,6 +155,7 @@ static const struct
   { csky_init, "elf_csky", "csky", 4, EM_CSKY, ELFCLASS32, ELFDATA2LSB },
   { loongarch_init, "elf_loongarch", "loongarch", 9, EM_LOONGARCH, ELFCLASS64, ELFDATA2LSB },
   { arc_init, "elf_arc", "arc", 3, EM_ARCV2, ELFCLASS32, ELFDATA2LSB },
+  { mips_init, "elf_mips", "mips", 4, EM_MIPS, 0, 0 },
 };
 #define nmachines (sizeof (machines) / sizeof (machines[0]))
 
diff --git a/libelf/elf_getdata.c b/libelf/elf_getdata.c
index 7c3ac043..942ba536 100644
--- a/libelf/elf_getdata.c
+++ b/libelf/elf_getdata.c
@@ -133,6 +133,119 @@ __libelf_data_type (GElf_Ehdr *ehdr, int sh_type, GElf_Xword align)
     }
 }
 
+/* Convert the data in the current section.  */
+static void
+convert_data_for_mips64el (Elf_Scn *scn, int eclass,
+	      int data, size_t size, Elf_Type type)
+{
+  /* Do we need to convert the data and/or adjust for alignment?  */
+  if (data == MY_ELFDATA || type == ELF_T_BYTE)
+    {
+      /* In order to adapt macro GELF_R_SYM and GELF_R_TYPE on mips64, need to convert
+	relocation info(raw data). Some eu-utils use read-mmap method to map file, so
+	we need to malloc and memcpy raw data to avoid segment fault. After modification,
+	the correct value are saved in the malloced memory not in process address space. */
+      scn->data_base = malloc (size);
+      if (scn->data_base == NULL)
+	{
+	   __libelf_seterrno (ELF_E_NOMEM);
+	  return;
+	}
+
+      /* The copy will be appropriately aligned for direct access.  */
+      memcpy (scn->data_base, scn->rawdata_base, size);
+    }
+  else
+    {
+      xfct_t fp;
+
+      scn->data_base = malloc (size);
+      if (scn->data_base == NULL)
+	{
+	  __libelf_seterrno (ELF_E_NOMEM);
+	  return;
+	}
+
+      /* Make sure the source is correctly aligned for the conversion
+	 function to directly access the data elements.  */
+      char *rawdata_source;
+      /* In order to adapt macro GELF_R_SYM and GELF_R_TYPE on mips64, need to convert
+	relocation info(raw data). Some eu-utils use read-mmap method to map file, so
+	we need to malloc and memcpy raw data to avoid segment fault. After modification,
+	the correct value are saved in the malloced memory not in process address space. */
+      rawdata_source = malloc (size);
+      if (rawdata_source == NULL)
+	{
+	  __libelf_seterrno (ELF_E_NOMEM);
+	  return;
+	}
+
+      /* The copy will be appropriately aligned for direct access.  */
+      memcpy (rawdata_source, scn->rawdata_base, size);
+
+      /* Get the conversion function.  */
+      fp = __elf_xfctstom[eclass - 1][type];
+
+      fp (scn->data_base, rawdata_source, size, 0);
+
+      if (rawdata_source != scn->rawdata_base)
+	free (rawdata_source);
+    }
+
+  scn->data_list.data.d.d_buf = scn->data_base;
+  scn->data_list.data.d.d_size = size;
+  scn->data_list.data.d.d_type = type;
+  scn->data_list.data.d.d_off = scn->rawdata.d.d_off;
+  scn->data_list.data.d.d_align = scn->rawdata.d.d_align;
+  scn->data_list.data.d.d_version = scn->rawdata.d.d_version;
+
+  scn->data_list.data.s = scn;
+
+  /* In mips64 little-endian, r_info consists of four byte fields(contains
+     three reloc types) and a 32-bit symbol index. In order to adapt
+     GELF_R_SYM and GELF_R_TYPE, need to convert r_info to get correct symbol
+     index and type. */
+  /* references:
+     https://www.linux-mips.org/pub/linux/mips/doc/ABI/elf64-2.4.pdf
+     Page40 && Page41 */
+  GElf_Shdr shdr_mem;
+  GElf_Shdr *shdr = gelf_getshdr (scn, &shdr_mem);
+  if (shdr->sh_type == SHT_REL)
+    {
+      size_t sh_entsize = gelf_fsize (scn->elf, ELF_T_REL, 1, EV_CURRENT);
+      int nentries = shdr->sh_size / sh_entsize;
+      for (int cnt = 0; cnt < nentries; ++cnt)
+	{
+	  Elf_Data_Scn *data_scn = (Elf_Data_Scn *) &scn->data_list.data.d;
+	  Elf64_Rel *value = &((Elf64_Rel *) data_scn->d.d_buf)[cnt];
+	  Elf64_Xword info = value->r_info;
+	  value->r_info = (((info & 0xffffffff) << 32)
+			| ((info >> 56) & 0xff)
+			| ((info >> 40) & 0xff00)
+			| ((info >> 24) & 0xff0000)
+			| ((info >> 8) & 0xff000000));
+	  ((Elf64_Rel *) data_scn->d.d_buf)[cnt] = *value;
+	}
+    }
+    else if (shdr->sh_type == SHT_RELA)
+      {
+	size_t sh_entsize = gelf_fsize (scn->elf, ELF_T_RELA, 1, EV_CURRENT);
+	int nentries = shdr->sh_size / sh_entsize;
+	for (int cnt = 0; cnt < nentries; cnt++)
+	  {
+	    Elf_Data_Scn *data_scn = (Elf_Data_Scn *) &scn->data_list.data.d;
+	    Elf64_Rela *value = &((Elf64_Rela *) data_scn->d.d_buf)[cnt];
+	    Elf64_Xword info = value->r_info;
+	    value->r_info = (((info & 0xffffffff) << 32)
+			| ((info >> 56) & 0xff)
+			| ((info >> 40) & 0xff00)
+			| ((info >> 24) & 0xff0000)
+			| ((info >> 8) & 0xff000000));
+	    ((Elf64_Rela *) data_scn->d.d_buf)[cnt] = *value;
+	  }
+      }
+}
+
 /* Convert the data in the current section.  */
 static void
 convert_data (Elf_Scn *scn, int eclass,
@@ -451,8 +564,23 @@ __libelf_set_data_list_rdlock (Elf_Scn *scn, int wrlocked)
 	    return;
 	}
 
-      /* Convert according to the version and the type.   */
-      convert_data (scn, elf->class,
+      GElf_Shdr shdr_mem;
+      GElf_Shdr *shdr = gelf_getshdr (scn, &shdr_mem);
+      GElf_Ehdr ehdr_mem;
+      GElf_Ehdr *ehdr = gelf_getehdr (scn->elf, &ehdr_mem);
+      if (shdr != NULL && (shdr->sh_type == SHT_RELA || shdr->sh_type == SHT_REL) &&
+	  scn->elf->class == ELFCLASS64 && ehdr != NULL &&
+	  ehdr->e_machine == EM_MIPS && ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+	convert_data_for_mips64el (scn, elf->class,
+		    (elf->class == ELFCLASS32
+		     || (offsetof (struct Elf, state.elf32.ehdr)
+			 == offsetof (struct Elf, state.elf64.ehdr))
+		     ? elf->state.elf32.ehdr->e_ident[EI_DATA]
+		     : elf->state.elf64.ehdr->e_ident[EI_DATA]),
+		    scn->rawdata.d.d_size, scn->rawdata.d.d_type);
+      else
+	/* Convert according to the version and the type.   */
+	convert_data (scn, elf->class,
 		    (elf->class == ELFCLASS32
 		     || (offsetof (struct Elf, state.elf32.ehdr)
 			 == offsetof (struct Elf, state.elf64.ehdr))
diff --git a/libelf/elf_update.c b/libelf/elf_update.c
index 56af3a1c..aec19b7c 100644
--- a/libelf/elf_update.c
+++ b/libelf/elf_update.c
@@ -228,7 +228,60 @@ elf_update (Elf *elf, Elf_Cmd cmd)
 	  size = -1;
 	}
       else
+	{
+	  /* Because we converted the relocation info in mips order when we call elf_getdata.c,
+	     so we need to convert the modified data in original order bits before writing the
+	     data to the file. */
+	  Elf_Scn *scn = NULL;
+	  while ((scn = elf_nextscn (elf, scn)) != NULL)
+	    {
+	      GElf_Shdr shdr_mem;
+	      GElf_Shdr *shdr = gelf_getshdr (scn, &shdr_mem);
+	      GElf_Ehdr ehdr_mem;
+	      GElf_Ehdr *ehdr = gelf_getehdr (scn->elf, &ehdr_mem);
+	      if (shdr != NULL && (shdr->sh_type == SHT_RELA || shdr->sh_type == SHT_REL) &&
+		scn->elf->class == ELFCLASS64 &&
+		ehdr != NULL && ehdr->e_machine == EM_MIPS && ehdr->e_ident[EI_DATA] == ELFDATA2LSB)
+		{
+		  Elf_Data *d = elf_getdata (scn, NULL);
+		  if (shdr->sh_type == SHT_REL)
+		    {
+		      size_t sh_entsize = gelf_fsize (scn->elf, ELF_T_REL, 1, EV_CURRENT);
+		      int nentries = shdr->sh_size / sh_entsize;
+		      for (int cnt = 0; cnt < nentries; ++cnt)
+			{
+			  Elf_Data_Scn *data_scn = (Elf_Data_Scn *) d;
+			  Elf64_Rel *value = &((Elf64_Rel *) data_scn->d.d_buf)[cnt];
+			  Elf64_Xword info = value->r_info;
+			  value->r_info = (info >> 32
+					| ((info << 56) & 0xff00000000000000)
+					| ((info << 40) & 0xff000000000000)
+					| ((info << 24) & 0xff0000000000)
+					| ((info << 8) & 0xff00000000));
+			  ((Elf64_Rel *) data_scn->d.d_buf)[cnt] = *value;
+			}
+		    }
+		  else if (shdr->sh_type == SHT_RELA)
+		    {
+		      size_t sh_entsize = gelf_fsize (scn->elf, ELF_T_RELA, 1, EV_CURRENT);
+		      int nentries = shdr->sh_size / sh_entsize;
+		      for (int cnt = 0; cnt < nentries; cnt++)
+			{
+			  Elf_Data_Scn *data_scn = (Elf_Data_Scn *) d;
+			  Elf64_Rela *value = &((Elf64_Rela *) data_scn->d.d_buf)[cnt];
+			  Elf64_Xword info = value->r_info;
+			  value->r_info = (info >> 32
+					| ((info << 56) & 0xff00000000000000)
+					| ((info << 40) & 0xff000000000000)
+					| ((info << 24) & 0xff0000000000)
+					| ((info << 8) & 0xff00000000));
+			  ((Elf64_Rela *) data_scn->d.d_buf)[cnt] = *value;
+			}
+		    }
+		}
+	    }
 	size = write_file (elf, size, change_bo, shnum);
+      }
     }
 
  out:
diff --git a/libelf/libelfP.h b/libelf/libelfP.h
index ed061abb..bdd2cc6a 100644
--- a/libelf/libelfP.h
+++ b/libelf/libelfP.h
@@ -617,4 +617,7 @@ extern void __libelf_reset_rawdata (Elf_Scn *scn, void *buf, size_t size,
 #define INVALID_NDX(ndx, type, data) \
   unlikely ((data)->d_size / sizeof (type) <= (unsigned int) (ndx))
 
+#define ELF64_MIPS_R_TYPE1(i)          ((i) & 0xff)
+#define ELF64_MIPS_R_TYPE2(i)           (((i) >> 8) & 0xff)
+#define ELF64_MIPS_R_TYPE3(i)           (((i) >> 16) & 0xff)
 #endif  /* libelfP.h */
-- 
2.30.2