1 files changed, 285 insertions, 66 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 23fb4d51a5da..5cadcea035e0 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -115,6 +115,8 @@ static void __init_or_module add_nops(void *insns, unsigned int len)
 }
 
 extern s32 __retpoline_sites[], __retpoline_sites_end[];
+extern s32 __return_sites[], __return_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);
@@ -337,7 +339,7 @@ next:
 	}
 }
 
-#if defined(CONFIG_RETPOLINE) && defined(CONFIG_STACK_VALIDATION)
+#if defined(CONFIG_RETPOLINE) && defined(CONFIG_OBJTOOL)
 
 /*
  * CALL/JMP *%\reg
@@ -389,7 +391,7 @@ 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 +409,7 @@ 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 +440,9 @@ 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 */
@@ -451,6 +453,15 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 		return ret;
 	i += ret;
 
+	/*
+	 * The compiler is supposed to EMIT an INT3 after every unconditional
+	 * JMP instruction due to AMD BTC. However, if the compiler is too old
+	 * or SLS isn't enabled, we still need an INT3 after indirect JMPs
+	 * even on Intel.
+	 */
+	if (op == JMP32_INSN_OPCODE && i < insn->length)
+		bytes[i++] = INT3_INSN_OPCODE;
+
 	for (; i < insn->length;)
 		bytes[i++] = BYTES_NOP1;
 
@@ -506,11 +517,116 @@ void __init_or_module noinline apply_retpolines(s32 *start, s32 *end)
 	}
 }
 
-#else /* !RETPOLINES || !CONFIG_STACK_VALIDATION */
+#ifdef CONFIG_RETHUNK
+/*
+ * Rewrite the compiler generated return thunk tail-calls.
+ *
+ * For example, convert:
+ *
+ *   JMP __x86_return_thunk
+ *
+ * into:
+ *
+ *   RET
+ */
+static int patch_return(void *addr, struct insn *insn, u8 *bytes)
+{
+	int i = 0;
+
+	if (cpu_feature_enabled(X86_FEATURE_RETHUNK))
+		return -1;
+
+	bytes[i++] = RET_INSN_OPCODE;
+
+	for (; i < insn->length;)
+		bytes[i++] = INT3_INSN_OPCODE;
+
+	return i;
+}
+
+void __init_or_module noinline apply_returns(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *dest = NULL, *addr = (void *)s + *s;
+		struct insn insn;
+		int len, ret;
+		u8 bytes[16];
+		u8 op;
+
+		ret = insn_decode_kernel(&insn, addr);
+		if (WARN_ON_ONCE(ret < 0))
+			continue;
+
+		op = insn.opcode.bytes[0];
+		if (op == JMP32_INSN_OPCODE)
+			dest = addr + insn.length + insn.immediate.value;
+
+		if (__static_call_fixup(addr, op, dest) ||
+		    WARN_ONCE(dest != &__x86_return_thunk,
+			      "missing return thunk: %pS-%pS: %*ph",
+			      addr, dest, 5, addr))
+			continue;
+
+		DPRINTK("return thunk at: %pS (%px) len: %d to: %pS",
+			addr, addr, insn.length,
+			addr + insn.length + insn.immediate.value);
+
+		len = patch_return(addr, &insn, bytes);
+		if (len == insn.length) {
+			DUMP_BYTES(((u8*)addr),  len, "%px: orig: ", addr);
+			DUMP_BYTES(((u8*)bytes), len, "%px: repl: ", addr);
+			text_poke_early(addr, bytes, len);
+		}
+	}
+}
+#else
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+#endif /* CONFIG_RETHUNK */
+
+#else /* !CONFIG_RETPOLINE || !CONFIG_OBJTOOL */
 
 void __init_or_module noinline apply_retpolines(s32 *start, s32 *end) { }
+void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_RETPOLINE && CONFIG_OBJTOOL */
+
+#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);
+	}
+}
 
-#endif /* CONFIG_RETPOLINE && CONFIG_STACK_VALIDATION */
+#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,
@@ -713,34 +829,39 @@ asm (
 "	.pushsection	.init.text, \"ax\", @progbits\n"
 "	.type		int3_magic, @function\n"
 "int3_magic:\n"
+	ANNOTATE_NOENDBR
 "	movl	$1, (%" _ASM_ARG1 ")\n"
-"	ret\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 +874,12 @@ 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");
@@ -824,6 +939,7 @@ void __init alternative_instructions(void)
 	 * those can rewrite the retpoline thunks.
 	 */
 	apply_retpolines(__retpoline_sites, __retpoline_sites_end);
+	apply_returns(__return_sites, __return_sites_end);
 
 	/*
 	 * Then patch alternatives, such that those paravirt calls that are in
@@ -831,6 +947,8 @@ 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)) {
@@ -956,7 +1074,21 @@ static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
 __ro_after_init struct mm_struct *poking_mm;
 __ro_after_init unsigned long poking_addr;
 
-static void *__text_poke(void *addr, const void *opcode, size_t len)
+static void text_poke_memcpy(void *dst, const void *src, size_t len)
+{
+	memcpy(dst, src, len);
+}
+
+static void text_poke_memset(void *dst, const void *src, size_t len)
+{
+	int c = *(const int *)src;
+
+	memset(dst, c, len);
+}
+
+typedef void text_poke_f(void *dst, const void *src, size_t len);
+
+static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t len)
 {
 	bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
 	struct page *pages[2] = {NULL};
@@ -1021,7 +1153,7 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 	prev = use_temporary_mm(poking_mm);
 
 	kasan_disable_current();
-	memcpy((u8 *)poking_addr + offset_in_page(addr), opcode, len);
+	func((u8 *)poking_addr + offset_in_page(addr), src, len);
 	kasan_enable_current();
 
 	/*
@@ -1049,11 +1181,13 @@ static void *__text_poke(void *addr, const void *opcode, size_t len)
 			   (cross_page_boundary ? 2 : 1) * PAGE_SIZE,
 			   PAGE_SHIFT, false);
 
-	/*
-	 * If the text does not match what we just wrote then something is
-	 * fundamentally screwy; there's nothing we can really do about that.
-	 */
-	BUG_ON(memcmp(addr, opcode, len));
+	if (func == text_poke_memcpy) {
+		/*
+		 * If the text does not match what we just wrote then something is
+		 * fundamentally screwy; there's nothing we can really do about that.
+		 */
+		BUG_ON(memcmp(addr, src, len));
+	}
 
 	local_irq_restore(flags);
 	pte_unmap_unlock(ptep, ptl);
@@ -1080,7 +1214,7 @@ void *text_poke(void *addr, const void *opcode, size_t len)
 {
 	lockdep_assert_held(&text_mutex);
 
-	return __text_poke(addr, opcode, len);
+	return __text_poke(text_poke_memcpy, addr, opcode, len);
 }
 
 /**
@@ -1099,7 +1233,72 @@ void *text_poke(void *addr, const void *opcode, size_t len)
  */
 void *text_poke_kgdb(void *addr, const void *opcode, size_t len)
 {
-	return __text_poke(addr, opcode, len);
+	return __text_poke(text_poke_memcpy, 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(text_poke_memcpy, (void *)ptr, opcode + patched, s);
+		patched += s;
+	}
+	mutex_unlock(&text_mutex);
+	return addr;
+}
+
+/**
+ * text_poke_set - memset into (an unused part of) RX memory
+ * @addr: address to modify
+ * @c: the byte to fill the area with
+ * @len: length to copy, could be more than 2x PAGE_SIZE
+ *
+ * This is useful to overwrite unused regions of RX memory with illegal
+ * instructions.
+ */
+void *text_poke_set(void *addr, int c, 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(text_poke_memset, (void *)ptr, (void *)&c, s);
+		patched += s;
+	}
+	mutex_unlock(&text_mutex);
+	return addr;
 }
 
 static void do_sync_core(void *info)
@@ -1113,10 +1312,13 @@ void text_poke_sync(void)
 }
 
 struct text_poke_loc {
-	s32 rel_addr; /* addr := _stext + rel_addr */
-	s32 rel32;
+	/* addr := _stext + rel_addr */
+	s32 rel_addr;
+	s32 disp;
+	u8 len;
 	u8 opcode;
 	const u8 text[POKE_MAX_OPCODE_SIZE];
+	/* see text_poke_bp_batch() */
 	u8 old;
 };
 
@@ -1126,21 +1328,23 @@ struct bp_patching_desc {
 	atomic_t refs;
 };
 
-static struct bp_patching_desc *bp_desc;
+static struct bp_patching_desc bp_desc;
 
 static __always_inline
-struct bp_patching_desc *try_get_desc(struct bp_patching_desc **descp)
+struct bp_patching_desc *try_get_desc(void)
 {
-	struct bp_patching_desc *desc = __READ_ONCE(*descp); /* rcu_dereference */
+	struct bp_patching_desc *desc = &bp_desc;
 
-	if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
+	if (!arch_atomic_inc_not_zero(&desc->refs))
 		return NULL;
 
 	return desc;
 }
 
-static __always_inline void put_desc(struct bp_patching_desc *desc)
+static __always_inline void put_desc(void)
 {
+	struct bp_patching_desc *desc = &bp_desc;
+
 	smp_mb__before_atomic();
 	arch_atomic_dec(&desc->refs);
 }
@@ -1165,7 +1369,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 {
 	struct bp_patching_desc *desc;
 	struct text_poke_loc *tp;
-	int len, ret = 0;
+	int ret = 0;
 	void *ip;
 
 	if (user_mode(regs))
@@ -1173,15 +1377,15 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 
 	/*
 	 * Having observed our INT3 instruction, we now must observe
-	 * bp_desc:
+	 * bp_desc with non-zero refcount:
 	 *
-	 *	bp_desc = desc			INT3
+	 *	bp_desc.refs = 1		INT3
 	 *	WMB				RMB
-	 *	write INT3			if (desc)
+	 *	write INT3			if (bp_desc.refs != 0)
 	 */
 	smp_rmb();
 
-	desc = try_get_desc(&bp_desc);
+	desc = try_get_desc();
 	if (!desc)
 		return 0;
 
@@ -1205,8 +1409,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 			goto out_put;
 	}
 
-	len = text_opcode_size(tp->opcode);
-	ip += len;
+	ip += tp->len;
 
 	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
@@ -1221,12 +1424,12 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 		break;
 
 	case CALL_INSN_OPCODE:
-		int3_emulate_call(regs, (long)ip + tp->rel32);
+		int3_emulate_call(regs, (long)ip + tp->disp);
 		break;
 
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
-		int3_emulate_jmp(regs, (long)ip + tp->rel32);
+		int3_emulate_jmp(regs, (long)ip + tp->disp);
 		break;
 
 	default:
@@ -1236,7 +1439,7 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
 	ret = 1;
 
 out_put:
-	put_desc(desc);
+	put_desc();
 	return ret;
 }
 
@@ -1267,18 +1470,20 @@ static int tp_vec_nr;
  */
 static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
-	struct bp_patching_desc desc = {
-		.vec = tp,
-		.nr_entries = nr_entries,
-		.refs = ATOMIC_INIT(1),
-	};
 	unsigned char int3 = INT3_INSN_OPCODE;
 	unsigned int i;
 	int do_sync;
 
 	lockdep_assert_held(&text_mutex);
 
-	smp_store_release(&bp_desc, &desc); /* rcu_assign_pointer */
+	bp_desc.vec = tp;
+	bp_desc.nr_entries = nr_entries;
+
+	/*
+	 * Corresponds to the implicit memory barrier in try_get_desc() to
+	 * ensure reading a non-zero refcount provides up to date bp_desc data.
+	 */
+	atomic_set_release(&bp_desc.refs, 1);
 
 	/*
 	 * Corresponding read barrier in int3 notifier for making sure the
@@ -1301,7 +1506,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 	 */
 	for (do_sync = 0, i = 0; i < nr_entries; i++) {
 		u8 old[POKE_MAX_OPCODE_SIZE] = { tp[i].old, };
-		int len = text_opcode_size(tp[i].opcode);
+		int len = tp[i].len;
 
 		if (len - INT3_INSN_SIZE > 0) {
 			memcpy(old + INT3_INSN_SIZE,
@@ -1366,33 +1571,47 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
 		text_poke_sync();
 
 	/*
-	 * Remove and synchronize_rcu(), except we have a very primitive
-	 * refcount based completion.
+	 * Remove and wait for refs to be zero.
 	 */
-	WRITE_ONCE(bp_desc, NULL); /* RCU_INIT_POINTER */
-	if (!atomic_dec_and_test(&desc.refs))
-		atomic_cond_read_acquire(&desc.refs, !VAL);
+	if (!atomic_dec_and_test(&bp_desc.refs))
+		atomic_cond_read_acquire(&bp_desc.refs, !VAL);
 }
 
 static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 			       const void *opcode, size_t len, const void *emulate)
 {
 	struct insn insn;
-	int ret;
+	int ret, i;
 
 	memcpy((void *)tp->text, opcode, len);
 	if (!emulate)
 		emulate = opcode;
 
 	ret = insn_decode_kernel(&insn, emulate);
-
 	BUG_ON(ret < 0);
-	BUG_ON(len != insn.length);
 
 	tp->rel_addr = addr - (void *)_stext;
+	tp->len = len;
 	tp->opcode = insn.opcode.bytes[0];
 
 	switch (tp->opcode) {
+	case RET_INSN_OPCODE:
+	case JMP32_INSN_OPCODE:
+	case JMP8_INSN_OPCODE:
+		/*
+		 * Control flow instructions without implied execution of the
+		 * next instruction can be padded with INT3.
+		 */
+		for (i = insn.length; i < len; i++)
+			BUG_ON(tp->text[i] != INT3_INSN_OPCODE);
+		break;
+
+	default:
+		BUG_ON(len != insn.length);
+	};
+
+
+	switch (tp->opcode) {
 	case INT3_INSN_OPCODE:
 	case RET_INSN_OPCODE:
 		break;
@@ -1400,7 +1619,7 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 	case CALL_INSN_OPCODE:
 	case JMP32_INSN_OPCODE:
 	case JMP8_INSN_OPCODE:
-		tp->rel32 = insn.immediate.value;
+		tp->disp = insn.immediate.value;
 		break;
 
 	default: /* assume NOP */
@@ -1408,13 +1627,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 		case 2: /* NOP2 -- emulate as JMP8+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP8_INSN_OPCODE;
-			tp->rel32 = 0;
+			tp->disp = 0;
 			break;
 
 		case 5: /* NOP5 -- emulate as JMP32+0 */
 			BUG_ON(memcmp(emulate, x86_nops[len], len));
 			tp->opcode = JMP32_INSN_OPCODE;
-			tp->rel32 = 0;
+			tp->disp = 0;
 			break;
 
 		default: /* unknown instruction */