x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

1 files changed, 256 insertions, 0 deletions

diff --git a/drivers/thunderbolt/cap.c b/drivers/thunderbolt/cap.c
new file mode 100644
index 000000000..4ab22d529
--- /dev/null
+++ b/drivers/thunderbolt/cap.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Thunderbolt driver - capabilities lookup
+ *
+ * Copyright (c) 2014 Andreas Noever <andreas.noever@gmail.com>
+ * Copyright (C) 2018, Intel Corporation
+ */
+
+#include <linux/slab.h>
+#include <linux/errno.h>
+
+#include "tb.h"
+
+#define CAP_OFFSET_MAX		0xff
+#define VSE_CAP_OFFSET_MAX	0xffff
+#define TMU_ACCESS_EN		BIT(20)
+
+static int tb_port_enable_tmu(struct tb_port *port, bool enable)
+{
+	struct tb_switch *sw = port->sw;
+	u32 value, offset;
+	int ret;
+
+	/*
+	 * Legacy devices need to have TMU access enabled before port
+	 * space can be fully accessed.
+	 */
+	if (tb_switch_is_light_ridge(sw))
+		offset = 0x26;
+	else if (tb_switch_is_eagle_ridge(sw))
+		offset = 0x2a;
+	else
+		return 0;
+
+	ret = tb_sw_read(sw, &value, TB_CFG_SWITCH, offset, 1);
+	if (ret)
+		return ret;
+
+	if (enable)
+		value |= TMU_ACCESS_EN;
+	else
+		value &= ~TMU_ACCESS_EN;
+
+	return tb_sw_write(sw, &value, TB_CFG_SWITCH, offset, 1);
+}
+
+static void tb_port_dummy_read(struct tb_port *port)
+{
+	/*
+	 * When reading from next capability pointer location in port
+	 * config space the read data is not cleared on LR. To avoid
+	 * reading stale data on next read perform one dummy read after
+	 * port capabilities are walked.
+	 */
+	if (tb_switch_is_light_ridge(port->sw)) {
+		u32 dummy;
+
+		tb_port_read(port, &dummy, TB_CFG_PORT, 0, 1);
+	}
+}
+
+/**
+ * tb_port_next_cap() - Return next capability in the linked list
+ * @port: Port to find the capability for
+ * @offset: Previous capability offset (%0 for start)
+ *
+ * Finds dword offset of the next capability in port config space
+ * capability list. When passed %0 in @offset parameter, first entry
+ * will be returned, if it exists.
+ *
+ * Return:
+ * * Double word offset of the first or next capability - On success.
+ * * %0 - If no next capability is found.
+ * * Negative errno - Another error occurred.
+ */
+int tb_port_next_cap(struct tb_port *port, unsigned int offset)
+{
+	struct tb_cap_any header;
+	int ret;
+
+	if (!offset)
+		return port->config.first_cap_offset;
+
+	ret = tb_port_read(port, &header, TB_CFG_PORT, offset, 1);
+	if (ret)
+		return ret;
+
+	return header.basic.next;
+}
+
+static int __tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap)
+{
+	int offset = 0;
+
+	do {
+		struct tb_cap_any header;
+		int ret;
+
+		offset = tb_port_next_cap(port, offset);
+		if (offset < 0)
+			return offset;
+
+		ret = tb_port_read(port, &header, TB_CFG_PORT, offset, 1);
+		if (ret)
+			return ret;
+
+		if (header.basic.cap == cap)
+			return offset;
+	} while (offset > 0);
+
+	return -ENOENT;
+}
+
+/**
+ * tb_port_find_cap() - Find port capability
+ * @port: Port to find the capability for
+ * @cap: Capability to look
+ *
+ * Return:
+ * * Offset to the start of capability - On success.
+ * * %-ENOENT - If no such capability was found.
+ * * Negative errno - Another error occurred.
+ */
+int tb_port_find_cap(struct tb_port *port, enum tb_port_cap cap)
+{
+	int ret;
+
+	ret = tb_port_enable_tmu(port, true);
+	if (ret)
+		return ret;
+
+	ret = __tb_port_find_cap(port, cap);
+
+	tb_port_dummy_read(port);
+	tb_port_enable_tmu(port, false);
+
+	return ret;
+}
+
+/**
+ * tb_switch_next_cap() - Return next capability in the linked list
+ * @sw: Switch to find the capability for
+ * @offset: Previous capability offset (%0 for start)
+ *
+ * Finds dword offset of the next capability in port config space
+ * capability list. When passed %0 in @offset parameter, first entry
+ * will be returned, if it exists.
+ *
+ * Return:
+ * * Double word offset of the first or next capability - On success.
+ * * %0 - If no next capability is found.
+ * * Negative errno - Another error occurred.
+ */
+int tb_switch_next_cap(struct tb_switch *sw, unsigned int offset)
+{
+	struct tb_cap_any header;
+	int ret;
+
+	if (!offset)
+		return sw->config.first_cap_offset;
+
+	ret = tb_sw_read(sw, &header, TB_CFG_SWITCH, offset, 2);
+	if (ret)
+		return ret;
+
+	switch (header.basic.cap) {
+	case TB_SWITCH_CAP_TMU:
+		ret = header.basic.next;
+		break;
+
+	case TB_SWITCH_CAP_VSE:
+		if (!header.extended_short.length)
+			ret = header.extended_long.next;
+		else
+			ret = header.extended_short.next;
+		break;
+
+	default:
+		tb_sw_dbg(sw, "unknown capability %#x at %#x\n",
+			  header.basic.cap, offset);
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret >= VSE_CAP_OFFSET_MAX ? 0 : ret;
+}
+
+/**
+ * tb_switch_find_cap() - Find switch capability
+ * @sw: Switch to find the capability for
+ * @cap: Capability to look
+ *
+ * Return:
+ * * Offset to the start of capability - On success.
+ * * %-ENOENT - If no such capability was found.
+ * * Negative errno - Another error occurred.
+ */
+int tb_switch_find_cap(struct tb_switch *sw, enum tb_switch_cap cap)
+{
+	int offset = 0;
+
+	do {
+		struct tb_cap_any header;
+		int ret;
+
+		offset = tb_switch_next_cap(sw, offset);
+		if (offset < 0)
+			return offset;
+
+		ret = tb_sw_read(sw, &header, TB_CFG_SWITCH, offset, 1);
+		if (ret)
+			return ret;
+
+		if (header.basic.cap == cap)
+			return offset;
+	} while (offset);
+
+	return -ENOENT;
+}
+
+/**
+ * tb_switch_find_vse_cap() - Find switch vendor specific capability
+ * @sw: Switch to find the capability for
+ * @vsec: Vendor specific capability to look
+ *
+ * This function enumerates vendor specific capabilities (VSEC) of a
+ * switch and returns offset when capability matching @vsec is found.
+ *
+ * Return:
+ * * Offset of capability - On success.
+ * * %-ENOENT - If capability was not found.
+ * * Negative errno - Another error occurred.
+ */
+int tb_switch_find_vse_cap(struct tb_switch *sw, enum tb_switch_vse_cap vsec)
+{
+	int offset = 0;
+
+	do {
+		struct tb_cap_any header;
+		int ret;
+
+		offset = tb_switch_next_cap(sw, offset);
+		if (offset < 0)
+			return offset;
+
+		ret = tb_sw_read(sw, &header, TB_CFG_SWITCH, offset, 1);
+		if (ret)
+			return ret;
+
+		if (header.extended_short.cap == TB_SWITCH_CAP_VSE &&
+		    header.extended_short.vsec_id == vsec)
+			return offset;
+	} while (offset);
+
+	return -ENOENT;
+}