x86/alternative: Relax text_poke_bp() constraint

stable inclusion
from stable-v5.10.133
commit 1f6e6683c46612baf01555e214d863aaa03c399b
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I5PTAS
CVE: CVE-2022-29900,CVE-2022-23816,CVE-2022-29901

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=1f6e6683c46612baf01555e214d863aaa03c399b

--------------------------------

commit 26c44b77 upstream.

Currently, text_poke_bp() is very strict to only allow patching a
single instruction; however with straight-line-speculation it will be
required to patch: ret; int3, which is two instructions.

As such, relax the constraints a little to allow int3 padding for all
instructions that do not imply the execution of the next instruction,
ie: RET, JMP.d8 and JMP.d32.

While there, rename the text_poke_loc::rel32 field to ::disp.

Note: this fills up the text_poke_loc structure which is now a round
  16 bytes big.

  [ bp: Put comments ontop instead of on the side. ]
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20211204134908.082342723@infradead.orgSigned-off-by: NSasha Levin <sashal@kernel.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NBen Hutchings <ben@decadent.org.uk>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: NLin Yujun <linyujun809@huawei.com>
Reviewed-by: NZhang Jianhua <chris.zjh@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

arch/x86/kernel/alternative.c

@@ -1193,10 +1193,13 @@ 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;
 };
 
@@ -1211,7 +1214,8 @@ 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 *desc = __READ_ONCE(*descp); /* rcu_dereference */
+	/* rcu_dereference */
+	struct bp_patching_desc *desc = __READ_ONCE(*descp);
 
 	if (!desc || !arch_atomic_inc_not_zero(&desc->refs))
 		return NULL;
@@ -1245,7 +1249,7 @@ 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))
@@ -1285,8 +1289,7 @@ 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:
@@ -1301,12 +1304,12 @@ 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:
@@ -1381,7 +1384,7 @@ 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,
@@ -1458,20 +1461,36 @@ 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:
@@ -1480,7 +1499,7 @@ 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 */
@@ -1488,13 +1507,13 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
 		case 2: /* NOP2 -- emulate as JMP8+0 */
 			BUG_ON(memcmp(emulate, ideal_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, ideal_nops[NOP_ATOMIC5], len));
 			tp->opcode = JMP32_INSN_OPCODE;
-			tp->rel32 = 0;
+			tp->disp = 0;
 			break;
 
 		default: /* unknown instruction */