mips dynamic linker support

not heavily tested, but the basics are working. the basic concept is
that the dynamic linker entry point code invokes a pure-PIC (no global
accesses) C function in reloc.h to perform the early GOT relocations
needed to make the dynamic linker itself functional, then invokes
__dynlink like on other archs. since mips uses some ugly arch-specific
hacks to optimize relocating the GOT (rather than just using the
normal DT_REL[A] tables like on other archs), the dynamic linker has
been modified slightly to support calling arch-specific relocation
code in reloc.h.

most of the actual mips-specific behavior was developed by reading the
output of readelf on libc.so and simple executable files. i could not
find good reference information on which relocation types need to be
supported or their semantics, so it's possible that some legitimate
usage cases will not work yet.

arch/mips/reloc.h

@@ -4,7 +4,7 @@
 #define ETC_LDSO_PATH "/etc/ld-musl-mips.path"
 
 #define IS_COPY(x) ((x)==R_MIPS_COPY)
-#define IS_PLT(x) ((x)==R_MIPS_JUMP_SLOT)
+#define IS_PLT(x) 1
 
 static inline void do_single_reloc(size_t *reloc_addr, int type, size_t sym_val, size_t sym_size, unsigned char *base_addr, size_t addend)
 {
@@ -13,11 +13,61 @@ static inline void do_single_reloc(size_t *reloc_addr, int type, size_t sym_val,
 		*reloc_addr = sym_val;
 		break;
 	case R_MIPS_REL32:
-		// FIXME: how do symbolic relocs come in here ?
-		*reloc_addr += (size_t)base_addr;
+		if (sym_val) *reloc_addr += sym_val;
+		else *reloc_addr += (size_t)base_addr;
 		break;
 	case R_MIPS_COPY:
 		memcpy(reloc_addr, (void *)sym_val, sym_size);
 		break;
 	}
 }
+
+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] & -4096);
+	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(unsigned char *base, size_t *rel, size_t rel_size, size_t stride, Sym *syms, char *strings, struct dso *dso);
+
+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(base, rel, sizeof rel, 2, this->syms, this->strings, head);
+	}
+}
+
+#define NEED_ARCH_RELOCS 1
+#define DYNAMIC_IS_RO 1

src/ldso/dynlink.c

@@ -487,6 +487,9 @@ static void reloc_all(struct dso *p)
 	for (; p; p=p->next) {
 		if (p->relocated) continue;
 		decode_vec(p->dynv, dyn, DYN_CNT);
+#ifdef NEED_ARCH_RELOCS
+		do_arch_relocs(p, head);
+#endif
 		do_relocs(p, (void *)(p->base+dyn[DT_JMPREL]), dyn[DT_PLTRELSZ],
 			2+(dyn[DT_PLTREL]==DT_RELA));
 		do_relocs(p, (void *)(p->base+dyn[DT_REL]), dyn[DT_RELSZ], 2);

src/ldso/mips/start.s

+.hidden _DYNAMIC
+.hidden __reloc_self
+.set noreorder
+.set nomacro
+.global _start
+.type _start,@function
+_start:
+	move $fp, $0
+
+	bgezal $0, 1f
+	nop
+2:	.gpword 2b
+	.gpword _DYNAMIC
+	.gpword __reloc_self
+1:	lw $gp, 0($ra)
+	subu $gp, $ra, $gp
+
+	lw $4, 0($sp)
+	addiu $5, $sp, 4
+	lw $6, 4($ra)
+	addu $6, $6, $gp
+	addiu $7, $gp, -0x7ff0
+	subu $sp, $sp, 16
+	lw $25, 8($ra)
+	add $25, $25, $gp
+	jalr $25
+	nop
+
+	lw $25, %call16(__dynlink)($gp)
+	lw $4, 16($sp)
+	addiu $5, $sp, 20
+	jalr $25
+	nop
+
+	add $sp, $sp, 16
+	li $6, -1
+1:	lw $4, ($sp)
+	lw $5, 4($sp)
+	bne $5, $6, 2f
+	nop
+	addu $sp, $sp, 4
+	addu $4, $4, -4
+	b 1b
+	nop
+2:	sw $4, ($sp)
+	jr $2