Received-SPF: pass (google.com: domain of linux-kernel+bounces-126336-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: Borislav Petkov <bp@alien8.de>
To: X86 ML <x86@kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>
Subject: [PATCH v2 2/4] x86/alternatives: Get rid of __optimize_nops()
Date: Sun, 31 Mar 2024 20:00:40 +0200
Message-ID: <20240331180042.13933-3-bp@alien8.de>
In-Reply-To: <20240331180042.13933-1-bp@alien8.de>
References: <20240331180042.13933-1-bp@alien8.de>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable

From: "Borislav Petkov (AMD)" <bp@alien8.de>

There's no need to carve out bits of the NOP optimization functionality
and look at JMP opcodes - simply do one more NOPs optimization pass
at the end of patching.

A lot simpler code.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 arch/x86/kernel/alternative.c | 59 ++++++++++-------------------------
 1 file changed, 16 insertions(+), 43 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.=
c
index ec94f1359c00..4b3378c71518 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -216,47 +216,12 @@ static int skip_nops(u8 *buf, int offset, int len)
 	return offset;
 }
=20
-/*
- * Optimize a sequence of NOPs, possibly preceded by an unconditional ju=
mp
- * to the end of the NOP sequence into a single NOP.
- */
-static bool
-__optimize_nops(const u8 * const instr, u8 *buf, size_t len, struct insn=
 *insn, int *next, int *prev, int *target)
-{
-	int i =3D *next - insn->length;
-
-	switch (insn->opcode.bytes[0]) {
-	case JMP8_INSN_OPCODE:
-	case JMP32_INSN_OPCODE:
-		*prev =3D i;
-		*target =3D *next + insn->immediate.value;
-		return false;
-	}
-
-	if (insn_is_nop(insn)) {
-		int nop =3D i;
-
-		*next =3D skip_nops(buf, *next, len);
-		if (*target && *next =3D=3D *target)
-			nop =3D *prev;
-
-		add_nop(buf + nop, *next - nop);
-		DUMP_BYTES(ALT, buf, len, "%px: [%d:%d) optimized NOPs: ", instr, nop,=
 *next);
-		return true;
-	}
-
-	*target =3D 0;
-	return false;
-}
-
 /*
  * "noinline" to cause control flow change and thus invalidate I$ and
  * cause refetch after modification.
  */
-static void __init_or_module noinline optimize_nops(const u8 * const ins=
tr, u8 *buf, size_t len)
+static void noinline optimize_nops(const u8 * const instr, u8 *buf, size=
_t len)
 {
-	int prev, target =3D 0;
-
 	for (int next, i =3D 0; i < len; i =3D next) {
 		struct insn insn;
=20
@@ -265,7 +230,14 @@ static void __init_or_module noinline optimize_nops(=
const u8 * const instr, u8 *
=20
 		next =3D i + insn.length;
=20
-		__optimize_nops(instr, buf, len, &insn, &next, &prev, &target);
+		if (insn_is_nop(&insn)) {
+			int nop =3D i;
+
+			next =3D skip_nops(buf, next, len);
+
+			add_nop(buf + nop, next - nop);
+			DUMP_BYTES(ALT, buf, len, "%px: [%d:%d) optimized NOPs: ", instr, nop=
, next);
+		}
 	}
 }
=20
@@ -339,10 +311,8 @@ bool need_reloc(unsigned long offset, u8 *src, size_=
t src_len)
 	return (target < src || target > src + src_len);
 }
=20
-void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, =
u8 *repl, size_t repl_len)
+static void __apply_relocation(u8 *buf, const u8 * const instr, size_t i=
nstrlen, u8 *repl, size_t repl_len)
 {
-	int prev, target =3D 0;
-
 	for (int next, i =3D 0; i < instrlen; i =3D next) {
 		struct insn insn;
=20
@@ -351,9 +321,6 @@ void apply_relocation(u8 *buf, const u8 * const instr=
, size_t instrlen, u8 *repl
=20
 		next =3D i + insn.length;
=20
-		if (__optimize_nops(instr, buf, instrlen, &insn, &next, &prev, &target=
))
-			continue;
-
 		switch (insn.opcode.bytes[0]) {
 		case 0x0f:
 			if (insn.opcode.bytes[1] < 0x80 ||
@@ -398,6 +365,12 @@ void apply_relocation(u8 *buf, const u8 * const inst=
r, size_t instrlen, u8 *repl
 	}
 }
=20
+void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, =
u8 *repl, size_t repl_len)
+{
+	__apply_relocation(buf, instr, instrlen, repl, repl_len);
+	optimize_nops(instr, buf, repl_len);
+}
+
 /* Low-level backend functions usable from alternative code replacements=
 */
 DEFINE_ASM_FUNC(nop_func, "", .entry.text);
 EXPORT_SYMBOL_GPL(nop_func);
--=20
2.43.0