1 files changed, 90 insertions, 18 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 5007c3ffe96f..d374cb3cf024 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -115,6 +115,7 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 }
 
 extern s32 __retpoline_sites[], __retpoline_sites_end[];
+extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_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);
@@ -389,7 +390,7 @@ static int emit_indirect(int op, int reg, u8 *bytes)
  *
  *   CALL *%\reg
  *
- * It also tries to inline spectre_v2=retpoline,amd when size permits.
+ * It also tries to inline spectre_v2=retpoline,lfence when size permits.
  */
 static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 {
@@ -407,7 +408,7 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 	BUG_ON(reg == 4);
 
 	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE) &&
-	    !cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD))
+	    !cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE))
 		return -1;
 
 	op = insn->opcode.bytes[0];
@@ -438,9 +439,9 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 	}
 
 	/*
-	 * For RETPOLINE_AMD: prepend the indirect CALL/JMP with an LFENCE.
+	 * For RETPOLINE_LFENCE: prepend the indirect CALL/JMP with an LFENCE.
 	 */
-	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_AMD)) {
+	if (cpu_feature_enabled(X86_FEATURE_RETPOLINE_LFENCE)) {
 		bytes[i++] = 0x0f;
 		bytes[i++] = 0xae;
 		bytes[i++] = 0xe8; /* LFENCE */
@@ -512,6 +513,42 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
 
 #endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */
 
+#ifdef CONFIG_X86_KERNEL_IBT
+
+/*
+ * Generated by: objtool --ibt
+ */
+void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		u32 endbr, poison = gen_endbr_poison();
+		void *addr = (void *)s + *s;
+
+		if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
+			continue;
+
+		if (WARN_ON_ONCE(!is_endbr(endbr)))
+			continue;
+
+		DPRINTK("ENDBR at: %pS (%px)", addr, addr);
+
+		/*
+		 * When we have IBT, the lack of ENDBR will trigger #CP
+		 */
+		DUMP_BYTES(((u8*)addr), 4, "%px: orig: ", addr);
+		DUMP_BYTES(((u8*)&poison), 4, "%px: repl: ", addr);
+		text_poke_early(addr, &poison, 4);
+	}
+}
+
+#else
+
+void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_X86_KERNEL_IBT */
+
 #ifdef CONFIG_SMP
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
 				  u8 *text, u8 *text_end)
@@ -713,34 +750,39 @@ asm (
 "	.pushsection	.init.text, \"ax\", @progbits\n"
 "	.type		int3_magic, @function\n"
 "int3_magic:\n"
+	ANNOTATE_NOENDBR
 "	movl	$1, (%" _ASM_ARG1 ")\n"
 	ASM_RET
 "	.size		int3_magic, .-int3_magic\n"
 "	.popsection\n"
 );
 
-extern __initdata unsigned long int3_selftest_ip; /* defined in asm below */
+extern void int3_selftest_ip(void); /* defined in asm below */
 
 static int __init
 int3_exception_notify(struct notifier_block *self, unsigned long val, void *data)
 {
+	unsigned long selftest = (unsigned long)&int3_selftest_ip;
 	struct die_args *args = data;
 	struct pt_regs *regs = args->regs;
 
+	OPTIMIZER_HIDE_VAR(selftest);
+
 	if (!regs || user_mode(regs))
 		return NOTIFY_DONE;
 
 	if (val != DIE_INT3)
 		return NOTIFY_DONE;
 
-	if (regs->ip - INT3_INSN_SIZE != int3_selftest_ip)
+	if (regs->ip - INT3_INSN_SIZE != selftest)
 		return NOTIFY_DONE;
 
 	int3_emulate_call(regs, (unsigned long)&int3_magic);
 	return NOTIFY_STOP;
 }
 
-static void __init int3_selftest(void)
+/* Must be noinline to ensure uniqueness of int3_selftest_ip. */
+static noinline void __init int3_selftest(void)
 {
 	static __initdata struct notifier_block int3_exception_nb = {
 		.notifier_call	= int3_exception_notify,
@@ -753,18 +795,12 @@ static void __init int3_selftest(void)
 	/*
 	 * Basically: int3_magic(&val); but really complicated :-)
 	 *
-	 * Stick the address of the INT3 instruction into int3_selftest_ip,
-	 * then trigger the INT3, padded with NOPs to match a CALL instruction
-	 * length.
+	 * INT3 padded with NOP to CALL_INSN_SIZE. The int3_exception_nb
+	 * notifier above will emulate CALL for us.
 	 */
-	asm volatile ("1: int3; nop; nop; nop; nop\n\t"
-		      ".pushsection .init.data,\"aw\"\n\t"
-		      ".align " __ASM_SEL(4, 8) "\n\t"
-		      ".type int3_selftest_ip, @object\n\t"
-		      ".size int3_selftest_ip, " __ASM_SEL(4, 8) "\n\t"
-		      "int3_selftest_ip:\n\t"
-		      __ASM_SEL(.long, .quad) " 1b\n\t"
-		      ".popsection\n\t"
+	asm volatile ("int3_selftest_ip:\n\t"
+		      ANNOTATE_NOENDBR
+		      "    int3; nop; nop; nop; nop\n\t"
 		      : ASM_CALL_CONSTRAINT
 		      : __ASM_SEL_RAW(a, D) (&val)
 		      : "memory");
@@ -831,6 +867,8 @@ void __init alternative_instructions(void)
 	 */
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
+	apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end);
+
 #ifdef CONFIG_SMP
 	/* Patch to UP if other cpus not imminent. */
 	if (!noreplace_smp && (num_present_cpus() == 1 || setup_max_cpus <= 1)) {
@@ -1102,6 +1140,40 @@ void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
 	return __text_poke(addr, opcode, len);
 }
 
+/**
+ * text_poke_copy - Copy instructions into (an unused part of) RX memory
+ * @addr: address to modify
+ * @opcode: source of the copy
+ * @len: length to copy, could be more than 2x PAGE_SIZE
+ *
+ * Not safe against concurrent execution; useful for JITs to dump
+ * new code blocks into unused regions of RX memory. Can be used in
+ * conjunction with synchronize_rcu_tasks() to wait for existing
+ * execution to quiesce after having made sure no existing functions
+ * pointers are live.
+ */
+void *text_poke_copy(void *addr, const void *opcode, size_t len)
+{
+	unsigned long start = (unsigned long)addr;
+	size_t patched = 0;
+
+	if (WARN_ON_ONCE(core_kernel_text(start)))
+		return NULL;
+
+	mutex_lock(&text_mutex);
+	while (patched < len) {
+		unsigned long ptr = start + patched;
+		size_t s;
+
+		s = min_t(size_t, PAGE_SIZE * 2 - offset_in_page(ptr), len - patched);
+
+		__text_poke((void *)ptr, opcode + patched, s);
+		patched += s;
+	}
+	mutex_unlock(&text_mutex);
+	return addr;
+}
+
 static void do_sync_core(void *info)
 {
 	sync_core();