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, 304 insertions, 0 deletions

diff --git a/net/wireless/debugfs.c b/net/wireless/debugfs.c
new file mode 100644
index 000000000..f9e7fff1e
--- /dev/null
+++ b/net/wireless/debugfs.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * cfg80211 debugfs
+ *
+ * Copyright 2009	Luis R. Rodriguez <lrodriguez@atheros.com>
+ * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
+ * Copyright (C) 2023 Intel Corporation
+ */
+
+#include <linux/slab.h>
+#include "core.h"
+#include "debugfs.h"
+
+#define DEBUGFS_READONLY_FILE(name, buflen, fmt, value...)		\
+static ssize_t name## _read(struct file *file, char __user *userbuf,	\
+			    size_t count, loff_t *ppos)			\
+{									\
+	struct wiphy *wiphy = file->private_data;			\
+	char buf[buflen];						\
+	int res;							\
+									\
+	res = scnprintf(buf, buflen, fmt "\n", ##value);		\
+	return simple_read_from_buffer(userbuf, count, ppos, buf, res);	\
+}									\
+									\
+static const struct file_operations name## _ops = {			\
+	.read = name## _read,						\
+	.open = simple_open,						\
+	.llseek = generic_file_llseek,					\
+}
+
+#define DEBUGFS_RADIO_READONLY_FILE(name, buflen, fmt, value...)	\
+static ssize_t name## _read(struct file *file, char __user *userbuf,	\
+			    size_t count, loff_t *ppos)			\
+{									\
+	struct wiphy_radio_cfg *radio_cfg = file->private_data;		\
+	char buf[buflen];						\
+	int res;							\
+									\
+	res = scnprintf(buf, buflen, fmt "\n", ##value);		\
+	return simple_read_from_buffer(userbuf, count, ppos, buf, res);	\
+}									\
+									\
+static const struct file_operations name## _ops = {			\
+	.read = name## _read,						\
+	.open = simple_open,						\
+	.llseek = generic_file_llseek,					\
+}
+
+DEBUGFS_READONLY_FILE(rts_threshold, 20, "%d",
+		      wiphy->rts_threshold);
+DEBUGFS_READONLY_FILE(fragmentation_threshold, 20, "%d",
+		      wiphy->frag_threshold);
+DEBUGFS_READONLY_FILE(short_retry_limit, 20, "%d",
+		      wiphy->retry_short);
+DEBUGFS_READONLY_FILE(long_retry_limit, 20, "%d",
+		      wiphy->retry_long);
+
+DEBUGFS_RADIO_READONLY_FILE(radio_rts_threshold, 20, "%d",
+			    radio_cfg->rts_threshold);
+
+static int ht_print_chan(struct ieee80211_channel *chan,
+			 char *buf, int buf_size, int offset)
+{
+	if (WARN_ON(offset > buf_size))
+		return 0;
+
+	if (chan->flags & IEEE80211_CHAN_DISABLED)
+		return scnprintf(buf + offset,
+				 buf_size - offset,
+				 "%d Disabled\n",
+				 chan->center_freq);
+
+	return scnprintf(buf + offset,
+			 buf_size - offset,
+			 "%d HT40 %c%c\n",
+			 chan->center_freq,
+			 (chan->flags & IEEE80211_CHAN_NO_HT40MINUS) ?
+				' ' : '-',
+			 (chan->flags & IEEE80211_CHAN_NO_HT40PLUS) ?
+				' ' : '+');
+}
+
+static ssize_t ht40allow_map_read(struct file *file,
+				  char __user *user_buf,
+				  size_t count, loff_t *ppos)
+{
+	struct wiphy *wiphy = file->private_data;
+	char *buf;
+	unsigned int offset = 0, buf_size = PAGE_SIZE, i;
+	enum nl80211_band band;
+	struct ieee80211_supported_band *sband;
+	ssize_t r;
+
+	buf = kzalloc(buf_size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	for (band = 0; band < NUM_NL80211_BANDS; band++) {
+		sband = wiphy->bands[band];
+		if (!sband)
+			continue;
+		for (i = 0; i < sband->n_channels; i++)
+			offset += ht_print_chan(&sband->channels[i],
+						buf, buf_size, offset);
+	}
+
+	r = simple_read_from_buffer(user_buf, count, ppos, buf, offset);
+
+	kfree(buf);
+
+	return r;
+}
+
+static const struct file_operations ht40allow_map_ops = {
+	.read = ht40allow_map_read,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
+#define DEBUGFS_ADD(name)						\
+	debugfs_create_file(#name, 0444, phyd, &rdev->wiphy, &name## _ops)
+
+#define DEBUGFS_RADIO_ADD(name, radio_idx)				\
+	debugfs_create_file(#name, 0444, radiod,			\
+			    &rdev->wiphy.radio_cfg[radio_idx],		\
+			    &name## _ops)
+
+void cfg80211_debugfs_rdev_add(struct cfg80211_registered_device *rdev)
+{
+	struct dentry *phyd = rdev->wiphy.debugfsdir;
+	struct dentry *radiod;
+	u8 i;
+
+	DEBUGFS_ADD(rts_threshold);
+	DEBUGFS_ADD(fragmentation_threshold);
+	DEBUGFS_ADD(short_retry_limit);
+	DEBUGFS_ADD(long_retry_limit);
+	DEBUGFS_ADD(ht40allow_map);
+
+	for (i = 0; i < rdev->wiphy.n_radio; i++) {
+		radiod = rdev->wiphy.radio_cfg[i].radio_debugfsdir;
+		DEBUGFS_RADIO_ADD(radio_rts_threshold, i);
+	}
+}
+
+struct debugfs_read_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t bufsize;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_read_work(struct wiphy *wiphy,
+					   struct wiphy_work *work)
+{
+	struct debugfs_read_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->bufsize, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_read_cancel(struct dentry *dentry,
+					     void *data)
+{
+	struct debugfs_read_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_read(struct wiphy *wiphy, struct file *file,
+				  char *buf, size_t bufsize,
+				  char __user *userbuf, size_t count,
+				  loff_t *ppos,
+				  ssize_t (*handler)(struct wiphy *wiphy,
+						     struct file *file,
+						     char *buf,
+						     size_t bufsize,
+						     void *data),
+				  void *data)
+{
+	struct debugfs_read_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.bufsize = bufsize,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_read_cancel,
+		.cancel_data = &work,
+	};
+
+	/* don't leak stack data or whatever */
+	memset(buf, 0, bufsize);
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_read_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	if (work.ret < 0)
+		return work.ret;
+
+	if (WARN_ON(work.ret > bufsize))
+		return -EINVAL;
+
+	return simple_read_from_buffer(userbuf, count, ppos, buf, work.ret);
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_read);
+
+struct debugfs_write_work {
+	struct wiphy_work work;
+	ssize_t (*handler)(struct wiphy *wiphy,
+			   struct file *file,
+			   char *buf,
+			   size_t count,
+			   void *data);
+	struct wiphy *wiphy;
+	struct file *file;
+	char *buf;
+	size_t count;
+	void *data;
+	ssize_t ret;
+	struct completion completion;
+};
+
+static void wiphy_locked_debugfs_write_work(struct wiphy *wiphy,
+					    struct wiphy_work *work)
+{
+	struct debugfs_write_work *w = container_of(work, typeof(*w), work);
+
+	w->ret = w->handler(w->wiphy, w->file, w->buf, w->count, w->data);
+	complete(&w->completion);
+}
+
+static void wiphy_locked_debugfs_write_cancel(struct dentry *dentry,
+					      void *data)
+{
+	struct debugfs_write_work *w = data;
+
+	wiphy_work_cancel(w->wiphy, &w->work);
+	complete(&w->completion);
+}
+
+ssize_t wiphy_locked_debugfs_write(struct wiphy *wiphy,
+				   struct file *file, char *buf, size_t bufsize,
+				   const char __user *userbuf, size_t count,
+				   ssize_t (*handler)(struct wiphy *wiphy,
+						      struct file *file,
+						      char *buf,
+						      size_t count,
+						      void *data),
+				   void *data)
+{
+	struct debugfs_write_work work = {
+		.handler = handler,
+		.wiphy = wiphy,
+		.file = file,
+		.buf = buf,
+		.count = count,
+		.data = data,
+		.ret = -ENODEV,
+		.completion = COMPLETION_INITIALIZER_ONSTACK(work.completion),
+	};
+	struct debugfs_cancellation cancellation = {
+		.cancel = wiphy_locked_debugfs_write_cancel,
+		.cancel_data = &work,
+	};
+
+	/* mostly used for strings so enforce NUL-termination for safety */
+	if (count >= bufsize)
+		return -EINVAL;
+
+	memset(buf, 0, bufsize);
+
+	if (copy_from_user(buf, userbuf, count))
+		return -EFAULT;
+
+	wiphy_work_init(&work.work, wiphy_locked_debugfs_write_work);
+	wiphy_work_queue(wiphy, &work.work);
+
+	debugfs_enter_cancellation(file, &cancellation);
+	wait_for_completion(&work.completion);
+	debugfs_leave_cancellation(file, &cancellation);
+
+	return work.ret;
+}
+EXPORT_SYMBOL_GPL(wiphy_locked_debugfs_write);