other half of lazy relocation from glibc dl-trampoline

ldso/ldso/x86_64/resolve.S

@@ -0,0 +1,63 @@
+/*
+ * This function is _not_ called directly.  It is jumped to (so no return
+ * address is on the stack) when attempting to use a symbol that has not yet
+ * been resolved.  The first time a jump symbol (such as a function call inside
+ * a shared library) is used (before it gets resolved) it will jump here to
+ * _dl_linux_resolve.  When we get called the stack looks like this:
+ *	reloc_entry
+ *	tpnt
+ *
+ * This function saves all the registers, puts a copy of reloc_entry and tpnt
+ * on the stack (as function arguments) then make the function call
+ * _dl_linux_resolver(tpnt, reloc_entry).  _dl_linux_resolver() figures out
+ * where the jump symbol is _really_ supposed to have jumped to and returns
+ * that to us.  Once we have that, we overwrite tpnt with this fixed up
+ * address. We then clean up after ourselves, put all the registers back how we
+ * found them, then we jump to where the fixed up address, which is where the
+ * jump symbol that got us here really wanted to jump to in the first place.
+ * found them, then we jump to the fixed up address, which is where the jump
+ * symbol that got us here really wanted to jump to in the first place.
+ *  -Erik Andersen
+ */
+
+/* more info taken from glibc/sysdeps/x86_64/dl-trampoline.S */
+
+.text
+
+.global _dl_linux_resolve
+.type   _dl_linux_resolve,%function
+.align 16
+
+_dl_linux_resolve:
+	subq $56,%rsp
+	/* Preserve registers otherwise clobbered. */
+	movq %rax,   (%rsp)
+	movq %rcx,  8(%rsp)
+	movq %rdx, 16(%rsp)
+	movq %rsi, 24(%rsp)
+	movq %rdi, 32(%rsp)
+	movq %r8,  40(%rsp)
+	movq %r9,  48(%rsp)
+
+	movq 64(%rsp), %rsi  /* Copy args pushed by PLT in register. */
+	movq %rsi, %r11      /* Multiply by 24 */
+	addq %r11, %rsi
+	addq %r11, %rsi
+	shlq $3, %rsi
+	movq 56(%rsp), %rdi  /* %rdi: link_map, %rsi: reloc_offset */
+	call _dl_linux_resolver       /* Call resolver. */
+	movq %rax, %r11      /* Save return value */
+
+	/* Get register content back. */
+	movq 48(%rsp), %r9
+	movq 40(%rsp), %r8
+	movq 32(%rsp), %rdi
+	movq 24(%rsp), %rsi
+	movq 16(%rsp), %rdx
+	movq  8(%rsp), %rcx
+	movq   (%rsp), %rax
+
+	addq $72, %rsp       /* Adjust stack(PLT did 2 pushes) */
+	jmp *%r11            /* Jump to function address. */
+
+.size _dl_linux_resolve,.-_dl_linux_resolve