Received-SPF: pass (google.com: domain of linux-kernel+bounces-51436-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: Jinghao Jia <jinghao7@illinois.edu>
To: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>,
        Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
        Borislav Petkov <bp@alien8.de>,
        Dave Hansen <dave.hansen@linux.intel.com>, x86@kernel.org,
        "H. Peter Anvin" <hpa@zytor.com>,
        Peter Zijlstra <peterz@infradead.org>, Xin Li <xin@zytor.com>
Cc: linux-trace-kernel@vger.kernel.org, linux-kernel@vger.kernel.org,
        Jinghao Jia <jinghao7@illinois.edu>
Subject: [PATCH v2 2/3] x86/kprobes: Prohibit kprobing on INT and UD
Date: Sat,  3 Feb 2024 21:12:59 -0600
Message-ID: <20240204031300.830475-3-jinghao7@illinois.edu>
In-Reply-To: <20240204031300.830475-1-jinghao7@illinois.edu>
References: <20240204031300.830475-1-jinghao7@illinois.edu>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Both INT (INT n, INT1, INT3, INTO) and UD (UD0, UD1, UD2) serve special
purposes in the kernel, e.g., INT3 is used by KGDB and UD2 is involved
in LLVM-KCFI instrumentation. At the same time, attaching kprobes on
these instructions (particularly UD) will pollute the stack trace dumped
in the kernel ring buffer, since the exception is triggered in the copy
buffer rather than the original location.

Check for INT and UD in can_probe and reject any kprobes trying to
attach to these instructions.

Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinghao Jia <jinghao7@illinois.edu>
---
 arch/x86/kernel/kprobes/core.c | 48 +++++++++++++++++++++++++++-------
 1 file changed, 39 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 644d416441fb..7a08d6a486c8 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -252,7 +252,28 @@ unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long add
 	return __recover_probed_insn(buf, addr);
 }
 
-/* Check if paddr is at an instruction boundary */
+/* Check if insn is INT or UD */
+static inline bool is_exception_insn(struct insn *insn)
+{
+	/* UD uses 0f escape */
+	if (insn->opcode.bytes[0] == 0x0f) {
+		/* UD0 / UD1 / UD2 */
+		return insn->opcode.bytes[1] == 0xff ||
+		       insn->opcode.bytes[1] == 0xb9 ||
+		       insn->opcode.bytes[1] == 0x0b;
+	}
+
+	/* INT3 / INT n / INTO / INT1 */
+	return insn->opcode.bytes[0] == 0xcc ||
+	       insn->opcode.bytes[0] == 0xcd ||
+	       insn->opcode.bytes[0] == 0xce ||
+	       insn->opcode.bytes[0] == 0xf1;
+}
+
+/*
+ * Check if paddr is at an instruction boundary and that instruction can
+ * be probed
+ */
 static bool can_probe(unsigned long paddr)
 {
 	unsigned long addr, __addr, offset = 0;
@@ -291,6 +312,22 @@ static bool can_probe(unsigned long paddr)
 #endif
 		addr += insn.length;
 	}
+
+	/* Check if paddr is at an instruction boundary */
+	if (addr != paddr)
+		return false;
+
+	__addr = recover_probed_instruction(buf, addr);
+	if (!__addr)
+		return false;
+
+	if (insn_decode_kernel(&insn, (void *)__addr) < 0)
+		return false;
+
+	/* INT and UD are special and should not be kprobed */
+	if (is_exception_insn(&insn))
+		return false;
+
 	if (IS_ENABLED(CONFIG_CFI_CLANG)) {
 		/*
 		 * The compiler generates the following instruction sequence
@@ -305,13 +342,6 @@ static bool can_probe(unsigned long paddr)
 		 * Also, these movl and addl are used for showing expected
 		 * type. So those must not be touched.
 		 */
-		__addr = recover_probed_instruction(buf, addr);
-		if (!__addr)
-			return false;
-
-		if (insn_decode_kernel(&insn, (void *)__addr) < 0)
-			return false;
-
 		if (insn.opcode.value == 0xBA)
 			offset = 12;
 		else if (insn.opcode.value == 0x3)
@@ -325,7 +355,7 @@ static bool can_probe(unsigned long paddr)
 	}
 
 out:
-	return (addr == paddr);
+	return true;
 }
 
 /* If x86 supports IBT (ENDBR) it must be skipped. */
-- 
2.43.0