x86/alternative: Implement .retpoline_sites support

Rewrite retpoline thunk call sites to be indirect calls for
spectre_v2=off. This ensures spectre_v2=off is as near to a
RETPOLINE=n build as possible.

This is the replacement for objtool writing alternative entries to
ensure the same and achieves feature-parity with the previous
approach.

One noteworthy feature is that it relies on the thunks to be in
machine order to compute the register index.

Specifically, this does not yet address the Jcc __x86_indirect_thunk_*
calls generated by clang, a future patch will add this.

Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Reviewed-by: Borislav Petkov <[e-mail]>
Acked-by: Josh Poimboeuf <[e-mail]>
Tested-by: Alexei Starovoitov <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

arch/um/kernel/um_arch.c

···
 	os_check_bugs();
 }
 
+void apply_retpolines(s32 *start, s32 *end)
+{
+}
+
 void apply_alternatives(struct alt_instr *start, struct alt_instr *end)
 {
 }

arch/x86/include/asm/alternative.h

···
 
 extern void alternative_instructions(void);
 extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+extern void apply_retpolines(s32 *start, s32 *end);
 
 struct module;
 

arch/x86/kernel/alternative.c

···
 #include <asm/io.h>
 #include <asm/fixmap.h>
 #include <asm/paravirt.h>
+#include <asm/asm-prototypes.h>
 
 int __read_mostly alternatives_patched;
 
···
 	}
 }
 
+extern s32 __retpoline_sites[], __retpoline_sites_end[];
 extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
 extern s32 __smp_locks[], __smp_locks_end[];
 void text_poke_early(void *addr, const void *opcode, size_t len);
···
  * "noinline" to cause control flow change and thus invalidate I$ and
  * cause refetch after modification.
  */
-static void __init_or_module noinline optimize_nops(struct alt_instr *a, u8 *instr)
+static void __init_or_module noinline optimize_nops(u8 *instr, size_t len)
 {
 	struct insn insn;
 	int i = 0;
···
 		 * optimized.
 		 */
 		if (insn.length == 1 && insn.opcode.bytes[0] == 0x90)
-			i += optimize_nops_range(instr, a->instrlen, i);
+			i += optimize_nops_range(instr, len, i);
 		else
 			i += insn.length;
 
-		if (i >= a->instrlen)
+		if (i >= len)
 			return;
 	}
 }
···
 		text_poke_early(instr, insn_buff, insn_buff_sz);
 
 next:
-		optimize_nops(a, instr);
+		optimize_nops(instr, a->instrlen);
 	}
 }
+
+#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION)
+
+/*
+ * CALL/JMP *%\reg
+ */
+static int emit_indirect(int op, int reg, u8 *bytes)
+{
+	int i = 0;
+	u8 modrm;
+
+	switch (op) {
+	case CALL_INSN_OPCODE:
+		modrm = 0x10; /* Reg = 2; CALL r/m */
+		break;
+
+	case JMP32_INSN_OPCODE:
+		modrm = 0x20; /* Reg = 4; JMP r/m */
+		break;
+
+	default:
+		WARN_ON_ONCE(1);
+		return -1;
+	}
+
+	if (reg >= 8) {
+		bytes[i++] = 0x41; /* REX.B prefix */
+		reg -= 8;
+	}
+
+	modrm |= 0xc0; /* Mod = 3 */
+	modrm += reg;
+
+	bytes[i++] = 0xff; /* opcode */
+	bytes[i++] = modrm;
+
+	return i;
+}
+
+/*
+ * Rewrite the compiler generated retpoline thunk calls.
+ *
+ * For spectre_v2=off (!X86_FEATURE_RETPOLINE), rewrite them into immediate
+ * indirect instructions, avoiding the extra indirection.
+ *
+ * For example, convert:
+ *
+ *   CALL __x86_indirect_thunk_\reg
+ *
+ * into:
+ *
+ *   CALL *%\reg
+ *
+ */
+static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
+{
+	retpoline_thunk_t *target;
+	int reg, i = 0;
+
+	target = addr + insn->length + insn->immediate.value;
+	reg = target - __x86_indirect_thunk_array;
+
+	if (WARN_ON_ONCE(reg & ~0xf))
+		return -1;
+
+	/* If anyone ever does: CALL/JMP *%rsp, we're in deep trouble. */
+	BUG_ON(reg == 4);
+
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE))
+		return -1;
+
+	i = emit_indirect(insn->opcode.bytes[0], reg, bytes);
+	if (i < 0)
+		return i;
+
+	for (; i < insn->length;)
+		bytes[i++] = BYTES_NOP1;
+
+	return i;
+}
+
+/*
+ * Generated by 'objtool --retpoline'.
+ */
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		struct insn insn;
+		int len, ret;
+		u8 bytes[16];
+		u8 op1, op2;
+
+		ret = insn_decode_kernel(&insn, addr);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op1 = insn.opcode.bytes[0];
+		op2 = insn.opcode.bytes[1];
+
+		switch (op1) {
+		case CALL_INSN_OPCODE:
+		case JMP32_INSN_OPCODE:
+			break;
+
+		default:
+			WARN_ON_ONCE(1);
+			continue;
+		}
+
+		len = patch_retpoline(addr, &insn, bytes);
+		if (len == insn.length) {
+			optimize_nops(bytes, len);
+			text_poke_early(addr, bytes, len);
+		}
+	}
+}
+
+#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */
+
+void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */
 
 #ifdef CONFIG_SMP
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
···
 	 * call with the direct call.
 	 */
 	apply_paravirt(__parainstructions, __parainstructions_end);
+
+	/*
+	 * Rewrite the retpolines, must be done before alternatives since
+	 * those can rewrite the retpoline thunks.
+	 */
+	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
 
 	/*
 	 * Then patch alternatives, such that those paravirt calls that are in

arch/x86/kernel/module.c

···
 		    struct module *me)
 {
 	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
-		*para = NULL, *orc = NULL, *orc_ip = NULL;
+		*para = NULL, *orc = NULL, *orc_ip = NULL,
+		*retpolines = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
···
 			orc = s;
 		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
 			orc_ip = s;
+		if (!strcmp(".retpoline_sites", secstrings + s->sh_name))
+			retpolines = s;
 	}
 
+	if (retpolines) {
+		void *rseg = (void *)retpolines->sh_addr;
+		apply_retpolines(rseg, rseg + retpolines->sh_size);
+	}
 	if (alt) {
 		/* patch .altinstructions */
 		void *aseg = (void *)alt->sh_addr;