solve tccelf problem on FreeBSD

On Sun, Nov 22, 2009 at 05:43:14PM +0100, Luigi Rizzo wrote:
> Hi,
> there is a well known problem with tcc and FreeBSD in the generation
> of elf objects -- see
> http://lists.gnu.org/archive/html/tinycc-devel/2005-07/msg00070.html
>
> Apparently Sergey Lyubka has tried a partial fix to the problem.
> I was wondering if Sergey or someone can post some more detail on
> what needs to be done so we can try to help fixing this issue

I think i have managed to solve the problem and produce
almost valid elf files on FreeBSD. The two patches attached
address a few problems (trying to explain to the
best of my knowledge; i am not very familiar with ELF and
the FreeBSD ELF conventions):

1. ELF file format
  tcc produces an ELF executable which is good for linux but
  not for FreeBSD. It misses the PHDR section which is almost
  mandatory for shared executables, puts in the .dynsym section
  some relocation info that FreeBSD expects to be in .got,
  and expect the relocation sections to be contiguous.

  patch-tccelf.c tries to address the above problem using
  conditional sections (so hopefully can be imported upstream)
  and also adds the ability to override the name of the dynamic
  loader through an environment variable (this is important to
  debug tcc).

2. predefined macros

  patch-libtcc.c adds/fixes some predefined macros when compiling
  on FreeBSD: these are __FreeBSD__ and the usual set of
  __i386__ and __unix__ variants.
  It also sets __INTEL_COMPILER so we can grab the __aligned
  macro from cdefs.h , otherwise many programs would fail

The resulting elf file is still not 100% correct -- if you strip it,
the program will not run (presumably there is some dangling reference).
Other than that, program do seem to run correctly.

It would be nice to integrate these patches in the main repository.
The FreeBSD specific code is in #ifdef so it should not harm
linux users
	cheers
	luigi

1 files changed, 80 insertions, 10 deletions

diff --git a/tccelf.c b/tccelf.c
index 3b881b0..dc0c948 100644
--- a/tccelf.c
+++ b/tccelf.c
@@ -1302,7 +1302,7 @@ static void tcc_add_linker_symbols(TCCState *s1)
 
 /* name of ELF interpreter */
 #if defined __FreeBSD__
-static const char elf_interp[] = "/usr/libexec/ld-elf.so.1";
+static const char elf_interp[] = "/libexec/ld-elf.so.1";
 #elif defined TCC_ARM_EABI
 static const char elf_interp[] = "/lib/ld-linux.so.3";
 #elif defined(TCC_TARGET_X86_64)
@@ -1335,6 +1335,31 @@ static void tcc_output_binary(TCCState *s1, FILE *f,
     }
 }
 
+#if defined(__FreeBSD__)
+#define	HAVE_PHDR	1
+#define	EXTRA_RELITEMS	14
+
+/* move the relocation value from .dynsym to .got */
+void patch_dynsym_undef(TCCState *s1, Section *s)
+{
+    uint32_t *gotd = (void *)s1->got->data;
+    ElfW(Sym) *sym, *sym_end;
+
+    gotd += 3;	// dummy entries in .got
+    /* relocate symbols in .dynsym */
+    sym_end = (ElfW(Sym) *)(s->data + s->data_offset);
+    for (sym = (ElfW(Sym) *)s->data + 1; sym < sym_end; sym++) {
+	if (sym->st_shndx == SHN_UNDEF) {
+	    *gotd++ = sym->st_value + 6; // XXX 6 is magic ?
+	    sym->st_value = 0;
+	}
+    }
+}
+#else
+#define	HAVE_PHDR	0
+#define	EXTRA_RELITEMS	9
+#endif
+
 /* output an ELF file */
 /* XXX: suppress unneeded sections */
 int elf_output_file(TCCState *s1, const char *filename)
@@ -1353,7 +1378,8 @@ int elf_output_file(TCCState *s1, const char *filename)
     ElfW(Sym) *sym;
     int type, file_type;
     unsigned long rel_addr, rel_size;
-    
+    unsigned long bss_addr, bss_size;
+
     file_type = s1->output_type;
     s1->nb_errors = 0;
 
@@ -1377,16 +1403,20 @@ int elf_output_file(TCCState *s1, const char *filename)
             const char *name;
             int sym_index, index;
             ElfW(Sym) *esym, *sym_end;
-            
+
             if (file_type == TCC_OUTPUT_EXE) {
                 char *ptr;
+		/* allow override the dynamic loader */
+		const char *elfint = getenv("LD_SO");
+		if (elfint == NULL)
+		    elfint = elf_interp;
                 /* add interpreter section only if executable */
                 interp = new_section(s1, ".interp", SHT_PROGBITS, SHF_ALLOC);
                 interp->sh_addralign = 1;
-                ptr = section_ptr_add(interp, sizeof(elf_interp));
-                strcpy(ptr, elf_interp);
+                ptr = section_ptr_add(interp, 1+strlen(elfint));
+                strcpy(ptr, elfint);
             }
-        
+
             /* add dynamic symbol table */
             s1->dynsym = new_symtab(s1, ".dynsym", SHT_DYNSYM, SHF_ALLOC,
                                     ".dynstr", 
@@ -1543,7 +1573,7 @@ int elf_output_file(TCCState *s1, const char *filename)
 
             /* add necessary space for other entries */
             saved_dynamic_data_offset = dynamic->data_offset;
-            dynamic->data_offset += sizeof(ElfW(Dyn)) * 9;
+            dynamic->data_offset += sizeof(ElfW(Dyn)) * EXTRA_RELITEMS;
         } else {
             /* still need to build got entries in case of static link */
             build_got_entries(s1);
@@ -1572,7 +1602,7 @@ int elf_output_file(TCCState *s1, const char *filename)
         break;
     case TCC_OUTPUT_EXE:
         if (!s1->static_link)
-            phnum = 4;
+            phnum = 4 + HAVE_PHDR;
         else
             phnum = 2;
         break;
@@ -1649,10 +1679,11 @@ int elf_output_file(TCCState *s1, const char *filename)
         rel_size = 0;
         rel_addr = 0;
 
+	bss_addr = bss_size = 0;
         /* leave one program header for the program interpreter */
         ph = &phdr[0];
         if (interp)
-            ph++;
+            ph += 1 + HAVE_PHDR;
 
         for(j = 0; j < 2; j++) {
             ph->p_type = PT_LOAD;
@@ -1714,9 +1745,20 @@ int elf_output_file(TCCState *s1, const char *filename)
                     }
                     /* update dynamic relocation infos */
                     if (s->sh_type == SHT_RELX) {
+#if defined(__FreeBSD__)
+                        if (!strcmp(strsec->data + s->sh_name, ".rel.got")) { // rel_size == 0) {
+                            rel_addr = addr;
+			    rel_size += s->sh_size;	// XXX only first rel.
+			}
+                        if (!strcmp(strsec->data + s->sh_name, ".rel.bss")) { // rel_size == 0) {
+                            bss_addr = addr;
+			    bss_size = s->sh_size;	// XXX only first rel.
+			}
+#else
                         if (rel_size == 0)
                             rel_addr = addr;
                         rel_size += s->sh_size;
+#endif
                     }
                     addr += s->sh_size;
                     if (s->sh_type != SHT_NOBITS)
@@ -1743,7 +1785,22 @@ int elf_output_file(TCCState *s1, const char *filename)
         /* if interpreter, then add corresponing program header */
         if (interp) {
             ph = &phdr[0];
-            
+
+#if defined(__FreeBSD__)
+	    {
+		int len = phnum * sizeof(ElfW(Phdr));
+
+		ph->p_type = PT_PHDR;
+		ph->p_offset = sizeof(ElfW(Ehdr));
+		ph->p_vaddr = interp->sh_addr - len;
+		ph->p_paddr = ph->p_vaddr;
+		ph->p_filesz = ph->p_memsz = len;
+		ph->p_flags = PF_R | PF_X;
+		ph->p_align = 4; // interp->sh_addralign;
+		ph++;
+	    }
+#endif
+
             ph->p_type = PT_INTERP;
             ph->p_offset = interp->sh_offset;
             ph->p_vaddr = interp->sh_addr;
@@ -1844,10 +1901,19 @@ int elf_output_file(TCCState *s1, const char *filename)
             put_dt(dynamic, DT_RELASZ, rel_size);
             put_dt(dynamic, DT_RELAENT, sizeof(ElfW_Rel));
 #else
+#if defined(__FreeBSD__)
+            put_dt(dynamic, DT_PLTGOT, s1->got->sh_addr);
+            put_dt(dynamic, DT_PLTRELSZ, rel_size);
+            put_dt(dynamic, DT_JMPREL, rel_addr);
+            put_dt(dynamic, DT_PLTREL, DT_REL);
+            put_dt(dynamic, DT_REL, bss_addr);
+            put_dt(dynamic, DT_RELSZ, bss_size);
+#else
             put_dt(dynamic, DT_REL, rel_addr);
             put_dt(dynamic, DT_RELSZ, rel_size);
             put_dt(dynamic, DT_RELENT, sizeof(ElfW_Rel));
 #endif
+#endif
             if (s1->do_debug)
                 put_dt(dynamic, DT_DEBUG, 0);
             put_dt(dynamic, DT_NULL, 0);
@@ -1979,6 +2045,10 @@ int elf_output_file(TCCState *s1, const char *filename)
         for(i=1;i<s1->nb_sections;i++) {
             s = s1->sections[section_order[i]];
             if (s->sh_type != SHT_NOBITS) {
+#if defined(__FreeBSD__)
+		if (s->sh_type == SHT_DYNSYM)
+		    patch_dynsym_undef(s1, s);
+#endif
                 while (offset < s->sh_offset) {
                     fputc(0, f);
                     offset++;