objtool: Detect non-relocated text references

When kernel IBT is enabled, objtool detects all text references in order
to determine which functions can be indirectly branched to.

In text, such references look like one of the following:

mov $0x0,%rax R_X86_64_32S .init.text+0x7e0a0
lea 0x0(%rip),%rax R_X86_64_PC32 autoremove_wake_function-0x4

Either way the function pointer is denoted by a relocation, so objtool
just reads that.

However there are some "lea xxx(%rip)" cases which don't use relocations
because they're referencing code in the same translation unit. Objtool
doesn't have visibility to those.

The only currently known instances of that are a few hand-coded asm text
references which don't actually need ENDBR. So it's not actually a
problem at the moment.

However if we enable -fpie, the compiler would start generating them and
there would definitely be bugs in the IBT sealing.

Detect non-relocated text references and handle them appropriately.

[ Note: I removed the manual static_call_tramp check -- that should
already be handled by the noendbr check. ]

Reported-by: Ard Biesheuvel <[e-mail]>
Tested-by: Ard Biesheuvel <[e-mail]>
Acked-by: Peter Zijlstra (Intel) <[e-mail]>
Signed-off-by: Josh Poimboeuf <[e-mail]>

arch/x86/kernel/acpi/wakeup_64.S

···
 
 	.align 4
 .Lresume_point:
+	ANNOTATE_NOENDBR
 	/* We don't restore %rax, it must be 0 anyway */
 	movq	$saved_context, %rax
 	movq	saved_context_cr4(%rax), %rbx

arch/x86/kernel/head_64.S

···
 	lretq
 
 .Lon_kernel_cs:
+	ANNOTATE_NOENDBR
 	UNWIND_HINT_END_OF_STACK
 
 #ifdef CONFIG_AMD_MEM_ENCRYPT

tools/objtool/arch/x86/decode.c

···
 		if (!rex_w)
 			break;
 
-		/* skip RIP relative displacement */
-		if (is_RIP())
-			break;
-
 		/* skip nontrivial SIB */
 		if (have_SIB()) {
 			modrm_rm = sib_base;
 			if (sib_index != CFI_SP)
 				break;
+		}
+
+		/* lea disp(%rip), %dst */
+		if (is_RIP()) {
+			insn->type = INSN_LEA_RIP;
+			break;
 		}
 
 		/* lea disp(%src), %dst */
···
 		break;
 	}
 
-	insn->immediate = ins.immediate.nbytes ? ins.immediate.value : 0;
+	if (ins.immediate.nbytes)
+		insn->immediate = ins.immediate.value;
+	else if (ins.displacement.nbytes)
+		insn->immediate = ins.displacement.value;
 
 	return 0;
 }

tools/objtool/check.c

···
 	return insn->offset == sym->offset + sym->len;
 }
 
+static int __validate_ibt_insn(struct objtool_file *file, struct instruction *insn,
+			       struct instruction *dest)
+{
+	if (dest->type == INSN_ENDBR) {
+		mark_endbr_used(dest);
+		return 0;
+	}
+
+	if (insn_func(dest) && insn_func(insn) &&
+	    insn_func(dest)->pfunc == insn_func(insn)->pfunc) {
+		/*
+		 * Anything from->to self is either _THIS_IP_ or
+		 * IRET-to-self.
+		 *
+		 * There is no sane way to annotate _THIS_IP_ since the
+		 * compiler treats the relocation as a constant and is
+		 * happy to fold in offsets, skewing any annotation we
+		 * do, leading to vast amounts of false-positives.
+		 *
+		 * There's also compiler generated _THIS_IP_ through
+		 * KCOV and such which we have no hope of annotating.
+		 *
+		 * As such, blanket accept self-references without
+		 * issue.
+		 */
+		return 0;
+	}
+
+	/*
+	 * Accept anything ANNOTATE_NOENDBR.
+	 */
+	if (dest->noendbr)
+		return 0;
+
+	/*
+	 * Accept if this is the instruction after a symbol
+	 * that is (no)endbr -- typical code-range usage.
+	 */
+	if (noendbr_range(file, dest))
+		return 0;
+
+	WARN_INSN(insn, "relocation to !ENDBR: %s", offstr(dest->sec, dest->offset));
+	return 1;
+}
+
 static int validate_ibt_insn(struct objtool_file *file, struct instruction *insn)
 {
 	struct instruction *dest;
···
 	 * direct/indirect branches:
 	 */
 	switch (insn->type) {
+
 	case INSN_CALL:
 	case INSN_CALL_DYNAMIC:
 	case INSN_JUMP_CONDITIONAL:
···
 	case INSN_RETURN:
 	case INSN_NOP:
 		return 0;
+
+	case INSN_LEA_RIP:
+		if (!insn_reloc(file, insn)) {
+			/* local function pointer reference without reloc */
+
+			off = arch_jump_destination(insn);
+
+			dest = find_insn(file, insn->sec, off);
+			if (!dest) {
+				WARN_INSN(insn, "corrupt function pointer reference");
+				return 1;
+			}
+
+			return __validate_ibt_insn(file, insn, dest);
+		}
+		break;
+
 	default:
 		break;
 	}
···
 	     reloc = find_reloc_by_dest_range(file->elf, insn->sec,
 					      reloc_offset(reloc) + 1,
 					      (insn->offset + insn->len) - (reloc_offset(reloc) + 1))) {
-
-		/*
-		 * static_call_update() references the trampoline, which
-		 * doesn't have (or need) ENDBR.  Skip warning in that case.
-		 */
-		if (reloc->sym->static_call_tramp)
-			continue;
 
 		off = reloc->sym->offset;
 		if (reloc_type(reloc) == R_X86_64_PC32 ||
···
 		if (!dest)
 			continue;
 
-		if (dest->type == INSN_ENDBR) {
-			mark_endbr_used(dest);
-			continue;
-		}
-
-		if (insn_func(dest) && insn_func(insn) &&
-		    insn_func(dest)->pfunc == insn_func(insn)->pfunc) {
-			/*
-			 * Anything from->to self is either _THIS_IP_ or
-			 * IRET-to-self.
-			 *
-			 * There is no sane way to annotate _THIS_IP_ since the
-			 * compiler treats the relocation as a constant and is
-			 * happy to fold in offsets, skewing any annotation we
-			 * do, leading to vast amounts of false-positives.
-			 *
-			 * There's also compiler generated _THIS_IP_ through
-			 * KCOV and such which we have no hope of annotating.
-			 *
-			 * As such, blanket accept self-references without
-			 * issue.
-			 */
-			continue;
-		}
-
-		/*
-		 * Accept anything ANNOTATE_NOENDBR.
-		 */
-		if (dest->noendbr)
-			continue;
-
-		/*
-		 * Accept if this is the instruction after a symbol
-		 * that is (no)endbr -- typical code-range usage.
-		 */
-		if (noendbr_range(file, dest))
-			continue;
-
-		WARN_INSN(insn, "relocation to !ENDBR: %s", offstr(dest->sec, dest->offset));
-
-		warnings++;
+		warnings += __validate_ibt_insn(file, insn, dest);
 	}
 
 	return warnings;

tools/objtool/include/objtool/arch.h

···
 	INSN_CLD,
 	INSN_TRAP,
 	INSN_ENDBR,
+	INSN_LEA_RIP,
 	INSN_OTHER,
 };