Received-SPF: pass (google.com: domain of linux-kernel+bounces-63815-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
Date: Tue, 13 Feb 2024 15:35:59 -0000
From: "tip-bot2 for Borislav Petkov (AMD)" <tip-bot2@linutronix.de>
Sender: tip-bot2@linutronix.de
Reply-to: linux-kernel@vger.kernel.org
To: linux-tip-commits@vger.kernel.org
Subject:
 [tip: x86/alternatives] x86/alternatives: Get rid of __optimize_nops()
Cc: "Borislav Petkov (AMD)" <bp@alien8.de>, x86@kernel.org,
 linux-kernel@vger.kernel.org
In-Reply-To: <20240130105941.19707-3-bp@alien8.de>
References: <20240130105941.19707-3-bp@alien8.de>
Precedence: bulk
MIME-Version: 1.0
Message-ID: <170783855963.398.15553842134757811644.tip-bot2@tip-bot2>
Robot-ID: <tip-bot2@linutronix.de>
Robot-Unsubscribe:
 Contact <mailto:tglx@linutronix.de> to get blacklisted from these emails
Precedence: bulk
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit

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

Commit-ID:     f9265b75648165f61467a7ea3c9bbae33be7ce27
Gitweb:        https://git.kernel.org/tip/f9265b75648165f61467a7ea3c9bbae33be7ce27
Author:        Borislav Petkov (AMD) <bp@alien8.de>
AuthorDate:    Tue, 30 Jan 2024 11:59:39 +01:00
Committer:     Borislav Petkov (AMD) <bp@alien8.de>
CommitterDate: Tue, 13 Feb 2024 16:25:46 +01:00

x86/alternatives: Get rid of __optimize_nops()

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>
Link: https://lore.kernel.org/r/20240130105941.19707-3-bp@alien8.de
---
 arch/x86/kernel/alternative.c | 52 ++++++----------------------------
 1 file changed, 10 insertions(+), 42 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 835e343..cdbece3 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -217,46 +217,11 @@ static int skip_nops(u8 *buf, int offset, int len)
 }
 
 /*
- * Optimize a sequence of NOPs, possibly preceded by an unconditional jump
- * to the end of the NOP sequence into a single NOP.
- */
-static bool __init_or_module
-__optimize_nops(const u8 * const instr, u8 *buf, size_t len, struct insn *insn, int *next, int *prev, int *target)
-{
-	int i = *next - insn->length;
-
-	switch (insn->opcode.bytes[0]) {
-	case JMP8_INSN_OPCODE:
-	case JMP32_INSN_OPCODE:
-		*prev = i;
-		*target = *next + insn->immediate.value;
-		return false;
-	}
-
-	if (insn_is_nop(insn)) {
-		int nop = i;
-
-		*next = skip_nops(buf, *next, len);
-		if (*target && *next == *target)
-			nop = *prev;
-
-		add_nop(buf + nop, *next - nop);
-		DUMP_BYTES(ALT, buf, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, *next);
-		return true;
-	}
-
-	*target = 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 instr, u8 *buf, size_t len)
 {
-	int prev, target = 0;
-
 	for (int next, i = 0; i < len; i = next) {
 		struct insn insn;
 
@@ -265,7 +230,14 @@ static void __init_or_module noinline optimize_nops(const u8 * const instr, u8 *
 
 		next = i + insn.length;
 
-		__optimize_nops(instr, buf, len, &insn, &next, &prev, &target);
+		if (insn_is_nop(&insn)) {
+			int nop = i;
+
+			next = skip_nops(buf, next, len);
+
+			add_nop(buf + nop, next - nop);
+			DUMP_BYTES(ALT, buf, len, "%px: [%d:%d) optimized NOPs: ", instr, nop, next);
+		}
 	}
 }
 
@@ -342,8 +314,6 @@ bool need_reloc(unsigned long offset, u8 *src, size_t src_len)
 static void __init_or_module noinline
 apply_relocation(const u8 * const instr, u8 *buf, size_t len, u8 *src, size_t src_len)
 {
-	int prev, target = 0;
-
 	for (int next, i = 0; i < len; i = next) {
 		struct insn insn;
 
@@ -352,9 +322,6 @@ apply_relocation(const u8 * const instr, u8 *buf, size_t len, u8 *src, size_t sr
 
 		next = i + insn.length;
 
-		if (__optimize_nops(instr, buf, len, &insn, &next, &prev, &target))
-			continue;
-
 		switch (insn.opcode.bytes[0]) {
 		case 0x0f:
 			if (insn.opcode.bytes[1] < 0x80 ||
@@ -533,7 +500,8 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 		for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
 			insn_buff[insn_buff_sz] = 0x90;
 
-		apply_relocation(instr, insn_buff, a->instrlen, replacement, a->replacementlen);
+		apply_relocation(instr, insn_buff, a->instrlen, replacement, insn_buff_sz);
+		optimize_nops(instr, insn_buff, insn_buff_sz);
 
 		DUMP_BYTES(ALT, instr, a->instrlen, "%px:   old_insn: ", instr);
 		DUMP_BYTES(ALT, replacement, a->replacementlen, "%px:   rpl_insn: ", replacement);