1 files changed, 240 insertions, 13 deletions

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index b4ac4e58c010..91b0e63a6238 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -116,6 +116,7 @@ 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 __cfi_sites[], __cfi_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[];
@@ -656,6 +657,28 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { }
 
 #ifdef CONFIG_X86_KERNEL_IBT
 
+static void poison_endbr(void *addr, bool warn)
+{
+	u32 endbr, poison = gen_endbr_poison();
+
+	if (WARN_ON_ONCE(get_kernel_nofault(endbr, addr)))
+		return;
+
+	if (!is_endbr(endbr)) {
+		WARN_ON_ONCE(warn);
+		return;
+	}
+
+	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);
+}
+
 /*
  * Generated by: objtool --ibt
  */
@@ -664,31 +687,232 @@ 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;
+		poison_endbr(addr, true);
+		if (IS_ENABLED(CONFIG_FINEIBT))
+			poison_endbr(addr - 16, false);
+	}
+}
+
+#else
+
+void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) { }
+
+#endif /* CONFIG_X86_KERNEL_IBT */
+
+#ifdef CONFIG_FINEIBT
+/*
+ * kCFI						FineIBT
+ *
+ * __cfi_\func:					__cfi_\func:
+ *	movl   $0x12345678,%eax		// 5	     endbr64			// 4
+ *	nop					     subl   $0x12345678,%r10d   // 7
+ *	nop					     jz     1f			// 2
+ *	nop					     ud2			// 2
+ *	nop					1:   nop			// 1
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *	nop
+ *
+ *
+ * caller:					caller:
+ *	movl	$(-0x12345678),%r10d	 // 6	     movl   $0x12345678,%r10d	// 6
+ *	addl	$-15(%r11),%r10d	 // 4	     sub    $16,%r11		// 4
+ *	je	1f			 // 2	     nop4			// 4
+ *	ud2				 // 2
+ * 1:	call	__x86_indirect_thunk_r11 // 5	     call   *%r11; nop2;	// 5
+ *
+ */
+
+asm(	".pushsection .rodata			\n"
+	"fineibt_preamble_start:		\n"
+	"	endbr64				\n"
+	"	subl	$0x12345678, %r10d	\n"
+	"	je	fineibt_preamble_end	\n"
+	"	ud2				\n"
+	"	nop				\n"
+	"fineibt_preamble_end:			\n"
+	".popsection\n"
+);
+
+extern u8 fineibt_preamble_start[];
+extern u8 fineibt_preamble_end[];
+
+#define fineibt_preamble_size (fineibt_preamble_end - fineibt_preamble_start)
+#define fineibt_preamble_hash 7
+
+asm(	".pushsection .rodata			\n"
+	"fineibt_caller_start:			\n"
+	"	movl	$0x12345678, %r10d	\n"
+	"	sub	$16, %r11		\n"
+	ASM_NOP4
+	"fineibt_caller_end:			\n"
+	".popsection				\n"
+);
+
+extern u8 fineibt_caller_start[];
+extern u8 fineibt_caller_end[];
+
+#define fineibt_caller_size (fineibt_caller_end - fineibt_caller_start)
+#define fineibt_caller_hash 2
+
+#define fineibt_caller_jmp (fineibt_caller_size - 2)
+
+static u32 decode_preamble_hash(void *addr)
+{
+	u8 *p = addr;
+
+	/* b8 78 56 34 12          mov    $0x12345678,%eax */
+	if (p[0] == 0xb8)
+		return *(u32 *)(addr + 1);
+
+	return 0; /* invalid hash value */
+}
+
+static u32 decode_caller_hash(void *addr)
+{
+	u8 *p = addr;
+
+	/* 41 ba 78 56 34 12       mov    $0x12345678,%r10d */
+	if (p[0] == 0x41 && p[1] == 0xba)
+		return -*(u32 *)(addr + 2);
+
+	/* e8 0c 78 56 34 12	   jmp.d8  +12 */
+	if (p[0] == JMP8_INSN_OPCODE && p[1] == fineibt_caller_jmp)
+		return -*(u32 *)(addr + 2);
+
+	return 0; /* invalid hash value */
+}
+
+/* .retpoline_sites */
+static int cfi_disable_callers(s32 *start, s32 *end)
+{
+	/*
+	 * Disable kCFI by patching in a JMP.d8, this leaves the hash immediate
+	 * in tact for later usage. Also see decode_caller_hash() and
+	 * cfi_rewrite_callers().
+	 */
+	const u8 jmp[] = { JMP8_INSN_OPCODE, fineibt_caller_jmp };
+	s32 *s;
 
-		if (WARN_ON_ONCE(!is_endbr(endbr)))
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		addr -= fineibt_caller_size;
+		hash = decode_caller_hash(addr);
+		if (!hash) /* nocfi callers */
 			continue;
 
-		DPRINTK("ENDBR at: %pS (%px)", addr, addr);
+		text_poke_early(addr, jmp, 2);
+	}
 
-		/*
-		 * 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);
+	return 0;
+}
+
+/* .cfi_sites */
+static int cfi_rewrite_preamble(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		hash = decode_preamble_hash(addr);
+		if (WARN(!hash, "no CFI hash found at: %pS %px %*ph\n",
+			 addr, addr, 5, addr))
+			return -EINVAL;
+
+		text_poke_early(addr, fineibt_preamble_start, fineibt_preamble_size);
+		WARN_ON(*(u32 *)(addr + fineibt_preamble_hash) != 0x12345678);
+		text_poke_early(addr + fineibt_preamble_hash, &hash, 4);
 	}
+
+	return 0;
+}
+
+/* .retpoline_sites */
+static int cfi_rewrite_callers(s32 *start, s32 *end)
+{
+	s32 *s;
+
+	for (s = start; s < end; s++) {
+		void *addr = (void *)s + *s;
+		u32 hash;
+
+		addr -= fineibt_caller_size;
+		hash = decode_caller_hash(addr);
+		if (hash) {
+			text_poke_early(addr, fineibt_caller_start, fineibt_caller_size);
+			WARN_ON(*(u32 *)(addr + fineibt_caller_hash) != 0x12345678);
+			text_poke_early(addr + fineibt_caller_hash, &hash, 4);
+		}
+		/* rely on apply_retpolines() */
+	}
+
+	return 0;
+}
+
+static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
+{
+	int ret;
+
+	if (WARN_ONCE(fineibt_preamble_size != 16,
+		      "FineIBT preamble wrong size: %ld", fineibt_preamble_size))
+		return;
+
+	if (!HAS_KERNEL_IBT || !cpu_feature_enabled(X86_FEATURE_IBT))
+		return;
+
+	/*
+	 * Rewrite the callers to not use the __cfi_ stubs, such that we might
+	 * rewrite them. This disables all CFI. If this succeeds but any of the
+	 * later stages fails, we're without CFI.
+	 */
+	ret = cfi_disable_callers(start_retpoline, end_retpoline);
+	if (ret)
+		goto err;
+
+	ret = cfi_rewrite_preamble(start_cfi, end_cfi);
+	if (ret)
+		goto err;
+
+	ret = cfi_rewrite_callers(start_retpoline, end_retpoline);
+	if (ret)
+		goto err;
+
+	if (builtin)
+		pr_info("Using FineIBT CFI\n");
+
+	return;
+
+err:
+	pr_err("Something went horribly wrong trying to rewrite the CFI implementation.\n");
 }
 
 #else
 
-void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) { }
+static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+			    s32 *start_cfi, s32 *end_cfi, bool builtin)
+{
+}
 
-#endif /* CONFIG_X86_KERNEL_IBT */
+#endif
+
+void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline,
+		   s32 *start_cfi, s32 *end_cfi)
+{
+	return __apply_fineibt(start_retpoline, end_retpoline,
+			       start_cfi, end_cfi,
+			       /* .builtin = */ false);
+}
 
 #ifdef CONFIG_SMP
 static void alternatives_smp_lock(const s32 *start, const s32 *end,
@@ -996,6 +1220,9 @@ void __init alternative_instructions(void)
 	 */
 	apply_paravirt(__parainstructions, __parainstructions_end);
 
+	__apply_fineibt(__retpoline_sites, __retpoline_sites_end,
+			__cfi_sites, __cfi_sites_end, true);
+
 	/*
 	 * Rewrite the retpolines, must be done before alternatives since
 	 * those can rewrite the retpoline thunks.