linux-kernel - [tip: x86/core] x86,retpoline: Optimize patch

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [day] [month] [year] [list]
Message-ID: <175757609204.709179.6413279343921603547.tip-bot2@tip-bot2>
Date: Thu, 11 Sep 2025 07:34:52 -0000
From: "tip-bot2 for Peter Zijlstra" <tip-bot2@...utronix.de>
To: linux-tip-commits@...r.kernel.org
Cc: "Peter Zijlstra (Intel)" <peterz@...radead.org>, x86@...nel.org,
 linux-kernel@...r.kernel.org
Subject: [tip: x86/core] x86,retpoline: Optimize patch_retpoline()

The following commit has been merged into the x86/core branch of tip:

Commit-ID:     4a1e02b15ac174c3c6d5e358e67c4ba980e7b336
Gitweb:        https://git.kernel.org/tip/4a1e02b15ac174c3c6d5e358e67c4ba980e7b336
Author:        Peter Zijlstra <peterz@...radead.org>
AuthorDate:    Tue, 02 Sep 2025 11:20:35 +02:00
Committer:     Peter Zijlstra <peterz@...radead.org>
CommitterDate: Thu, 04 Sep 2025 21:59:09 +02:00

x86,retpoline: Optimize patch_retpoline()

Currently the very common retpoline: "CS CALL __x86_indirect_thunk_r11"
is transformed into "CALL *R11; NOP3" for eIBRS/BHI_NO parts.

Similarly, paranoid fineibt has: "CALL *R11; NOP".

Recognise that CS stuffing can avoid the extra NOP. However, due to
prefix decode penalties, make sure to not emit too many CS prefixes.
Notably: "CS CALL __x86_indirect_thunk_rax" must not become "CS CS CS
CS CALL *RAX". Prefix decode penalties are typically many more cycles
than decoding an extra NOP.

Additionally, if the retpoline is a tail-call, the "JMP *%\reg" should
be followed by INT3 for straight-line-speculation mitigation, since
emit_indirect() now has a length argument, move this into
emit_indirect() such that other users (paranoid-fineibt) also do this.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Link: https://lkml.kernel.org/r/20250902104627.GM4068168@noisy.programming.kicks-ass.net
---
 arch/x86/kernel/alternative.c | 42 +++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 3d6a884..69fb818 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -713,20 +713,33 @@ static inline bool is_jcc32(struct insn *insn)
 #if defined(CONFIG_MITIGATION_RETPOLINE) && defined(CONFIG_OBJTOOL)
 
 /*
- * CALL/JMP *%\reg
+ * [CS]{,3} CALL/JMP *%\reg [INT3]*
  */
-static int emit_indirect(int op, int reg, u8 *bytes)
+static int emit_indirect(int op, int reg, u8 *bytes, int len)
 {
+	int cs = 0, bp = 0;
 	int i = 0;
 	u8 modrm;
 
+	/*
+	 * Set @len to the excess bytes after writing the instruction.
+	 */
+	len -= 2 + (reg >= 8);
+	WARN_ON_ONCE(len < 0);
+
 	switch (op) {
 	case CALL_INSN_OPCODE:
 		modrm = 0x10; /* Reg = 2; CALL r/m */
+		/*
+		 * Additional NOP is better than prefix decode penalty.
+		 */
+		if (len <= 3)
+			cs = len;
 		break;
 
 	case JMP32_INSN_OPCODE:
 		modrm = 0x20; /* Reg = 4; JMP r/m */
+		bp = len;
 		break;
 
 	default:
@@ -734,6 +747,9 @@ static int emit_indirect(int op, int reg, u8 *bytes)
 		return -1;
 	}
 
+	while (cs--)
+		bytes[i++] = 0x2e; /* CS-prefix */
+
 	if (reg >= 8) {
 		bytes[i++] = 0x41; /* REX.B prefix */
 		reg -= 8;
@@ -745,6 +761,9 @@ static int emit_indirect(int op, int reg, u8 *bytes)
 	bytes[i++] = 0xff; /* opcode */
 	bytes[i++] = modrm;
 
+	while (bp--)
+		bytes[i++] = 0xcc; /* INT3 */
+
 	return i;
 }
 
@@ -918,20 +937,11 @@ static int patch_retpoline(void *addr, struct insn *insn, u8 *bytes)
 		return emit_its_trampoline(addr, insn, reg, bytes);
 #endif
 
-	ret = emit_indirect(op, reg, bytes + i);
+	ret = emit_indirect(op, reg, bytes + i, insn->length - i);
 	if (ret < 0)
 		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 MITIGATION_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;
 
@@ -1421,8 +1431,7 @@ asm(	".pushsection .rodata				\n"
 	"#fineibt_caller_size:                          \n"
 	"	jne	fineibt_paranoid_start+0xd	\n"
 	"fineibt_paranoid_ind:				\n"
-	"	call	*%r11				\n"
-	"	nop					\n"
+	"	cs call	*%r11				\n"
 	"fineibt_paranoid_end:				\n"
 	".popsection					\n"
 );
@@ -1724,8 +1733,9 @@ static int cfi_rewrite_callers(s32 *start, s32 *end)
 			emit_paranoid_trampoline(addr + fineibt_caller_size,
 						 &insn, 11, bytes + fineibt_caller_size);
 		} else {
-			ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind);
-			if (WARN_ON_ONCE(ret != 3))
+			int len = fineibt_paranoid_size - fineibt_paranoid_ind;
+			ret = emit_indirect(op, 11, bytes + fineibt_paranoid_ind, len);
+			if (WARN_ON_ONCE(ret != len))
 				continue;
 		}