dynamic linker bootstrap overhaul

this overhaul further reduces the amount of arch-specific code needed
by the dynamic linker and removes a number of assumptions, including:

- that symbolic function references inside libc are bound at link time
  via the linker option -Bsymbolic-functions.

- that libc functions used by the dynamic linker do not require
  access to data symbols.

- that static/internal function calls and data accesses can be made
  without performing any relocations, or that arch-specific startup
  code handled any such relocations needed.

removing these assumptions paves the way for allowing libc.so itself
to be built with stack protector (among other things), and is achieved
by a three-stage bootstrap process:

1. relative relocations are processed with a flat function.
2. symbolic relocations are processed with no external calls/data.
3. main program and dependency libs are processed with a
   fully-functional libc/ldso.

reduction in arch-specific code is achived through the following:

- crt_arch.h, used for generating crt1.o, now provides the entry point
  for the dynamic linker too.

- asm is no longer responsible for skipping the beginning of argv[]
  when ldso is invoked as a command.

- the functionality previously provided by __reloc_self for heavily
  GOT-dependent RISC archs is now the arch-agnostic stage-1.

- arch-specific relocation type codes are mapped directly as macros
  rather than via an inline translation function/switch statement.

2 files changed, 38 insertions, 89 deletions

diff --git a/arch/mips/crt_arch.h b/arch/mips/crt_arch.h
index d4ae52d1..33bde4e6 100644
--- a/arch/mips/crt_arch.h
+++ b/arch/mips/crt_arch.h
@@ -1,21 +1,28 @@
-__asm__("\n\
-.set push\n\
-.set noreorder\n\
-.global __start\n\
-.global _start\n\
-.type   __start, @function\n\
-.type   _start, @function\n\
-__start:\n\
-_start:\n\
-	bal 1f \n\
-	move $fp, $0 \n\
-2:	.gpword 2b \n\
-1:	lw $gp, 0($ra) \n\
-	subu $gp, $ra, $gp \n\
-	move $4, $sp \n\
-	subu $sp, $sp, 16 \n\
-	and $sp, $sp, -8 \n\
-	lw $25, %call16(__cstart)($gp) \n\
-	jalr $25 \n\
-	nop \n\
-.set pop");
+__asm__(
+".set push\n"
+".set noreorder\n"
+".global _" START "\n"
+".global " START "\n"
+".type   _" START ", @function\n"
+".type   " START ", @function\n"
+"_" START ":\n"
+"" START ":\n"
+"	bal 1f \n"
+"	 move $fp, $0 \n"
+"2:	.gpword 2b \n"
+	.gpword " START "_c \n"
+".weak _DYNAMIC \n"
+".hidden _DYNAMIC \n"
+"	.gpword _DYNAMIC \n"
+"1:	lw $gp, 0($ra) \n"
+"	subu $gp, $ra, $gp \n"
+"	move $4, $sp \n"
+"	lw $5, 8($ra) \n"
+"	addu $5, $5, $gp \n"
+"	lw $25, 4($ra) \n"
+"	addu $25, $25, $gp \n"
+"	subu $sp, $sp, 16 \n"
+"	jalr $25 \n"
+"	 and $sp, $sp, -8 \n"
+".set pop \n"
+);
diff --git a/arch/mips/reloc.h b/arch/mips/reloc.h
index 4b81d328..8aa02852 100644
--- a/arch/mips/reloc.h
+++ b/arch/mips/reloc.h
@@ -1,5 +1,3 @@
-#include <string.h>
-#include <elf.h>
 #include <endian.h>
 
 #if __BYTE_ORDER == __LITTLE_ENDIAN
@@ -18,72 +16,16 @@
 
 #define TPOFF_K (-0x7000)
 
-static int remap_rel(int type)
-{
-	switch(type) {
-	case R_MIPS_REL32:
-		return REL_SYM_OR_REL;
-	case R_MIPS_JUMP_SLOT:
-		return REL_PLT;
-	case R_MIPS_COPY:
-		return REL_COPY;
-	case R_MIPS_TLS_DTPMOD32:
-		return REL_DTPMOD;
-	case R_MIPS_TLS_DTPREL32:
-		return REL_DTPOFF;
-	case R_MIPS_TLS_TPREL32:
-		return REL_TPOFF;
-	}
-	return 0;
-}
+#define REL_SYM_OR_REL  R_MIPS_REL32
+#define REL_PLT         R_MIPS_JUMP_SLOT
+#define REL_COPY        R_MIPS_COPY
+#define REL_DTPMOD      R_MIPS_TLS_DTPMOD32
+#define REL_DTPOFF      R_MIPS_TLS_DTPREL32
+#define REL_TPOFF       R_MIPS_TLS_TPREL32
 
-void __reloc_self(int c, size_t *a, size_t *dynv, size_t *got)
-{
-	char *base;
-	size_t t[20], n;
-	for (a+=c+1; *a; a++);
-	for (a++; *a; a+=2) if (*a<20) t[*a] = a[1];
-	base = (char *)t[AT_BASE];
-	if (!base) base = (char *)(t[AT_PHDR] & -t[AT_PAGESZ]);
-	for (a=dynv; *a; a+=2) if (*a-0x70000000UL<20) t[*a&31] = a[1];
-	n = t[DT_MIPS_LOCAL_GOTNO - 0x70000000];
-	for (a=got; n; a++, n--) *a += (size_t)base;
-}
-
-static void do_relocs(struct dso *dso, size_t *rel, size_t rel_size, size_t stride);
-
-static void do_arch_relocs(struct dso *this, struct dso *head)
-{
-	unsigned char *base = this->base;
-	size_t *dynv = this->dynv;
-	size_t dyn[20] = {0};
-	size_t i;
-	size_t rel[2], got=0;
-	Sym *sym;
-
-	for (i=0; dynv[i]; i+=2) {
-		if (dynv[i]-0x70000000UL<20)
-			dyn[dynv[i]&31] = dynv[i+1];
-		else if (dynv[i] == DT_PLTGOT)
-			got = dynv[i+1];
-	}
-	i = dyn[DT_MIPS_LOCAL_GOTNO-0x70000000];
-	if (this->shortname && !strcmp(this->shortname, "libc.so")) {
-		got += sizeof(size_t) * i;
-	} else {
-		for (; i; i--, got+=sizeof(size_t))
-			*(size_t *)(base+got) += (size_t)base;
-	}
-	sym = this->syms + dyn[DT_MIPS_GOTSYM-0x70000000];
-	i = dyn[DT_MIPS_SYMTABNO-0x70000000] - dyn[DT_MIPS_GOTSYM-0x70000000];
-	for (; i; i--, got+=sizeof(size_t), sym++) {
-		rel[0] = got;
-		rel[1] = sym-this->syms << 8 | R_MIPS_JUMP_SLOT;
-		*(size_t *)(base+got) = 0;
-		do_relocs(this, rel, sizeof rel, 2);
-	}
-}
-
-#define NEED_ARCH_RELOCS 1
+#define NEED_MIPS_GOT_RELOCS 1
 #define DYNAMIC_IS_RO 1
 #define ARCH_SYM_REJECT_UND(s) (!((s)->st_other & STO_MIPS_PLT))
+
+#define CRTJMP(pc,sp) __asm__ __volatile__( \
+	"move $sp,%1 ; jr %0" : : "r"(pc), "r"(sp) : "memory" )