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, 240 insertions, 0 deletions

diff --git a/drivers/w1/w1_int.c b/drivers/w1/w1_int.c
new file mode 100644
index 000000000..19a0ea28e
--- /dev/null
+++ b/drivers/w1/w1_int.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (c) 2004 Evgeniy Polyakov <zbr@ioremap.net>
+ */
+
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/sched/signal.h>
+#include <linux/export.h>
+#include <linux/moduleparam.h>
+
+#include "w1_internal.h"
+#include "w1_netlink.h"
+
+static int w1_search_count = -1; /* Default is continual scan */
+module_param_named(search_count, w1_search_count, int, 0);
+
+static int w1_enable_pullup = 1;
+module_param_named(enable_pullup, w1_enable_pullup, int, 0);
+
+static struct w1_master *w1_alloc_dev(u32 id, int slave_count, int slave_ttl,
+				       struct device_driver *driver,
+				       struct device *device)
+{
+	struct w1_master *dev;
+	int err;
+
+	/*
+	 * We are in process context(kernel thread), so can sleep.
+	 */
+	dev = kzalloc(sizeof(struct w1_master) + sizeof(struct w1_bus_master), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+
+	dev->bus_master = (struct w1_bus_master *)(dev + 1);
+
+	dev->owner		= THIS_MODULE;
+	dev->max_slave_count	= slave_count;
+	dev->slave_count	= 0;
+	dev->attempts		= 0;
+	dev->initialized	= 0;
+	dev->id			= id;
+	dev->slave_ttl		= slave_ttl;
+	dev->search_count	= w1_search_count;
+	dev->enable_pullup	= w1_enable_pullup;
+
+	/* For __w1_remove_master_device to decrement
+	 */
+	atomic_set(&dev->refcnt, 1);
+
+	INIT_LIST_HEAD(&dev->slist);
+	INIT_LIST_HEAD(&dev->async_list);
+	mutex_init(&dev->mutex);
+	mutex_init(&dev->bus_mutex);
+	mutex_init(&dev->list_mutex);
+
+	memcpy(&dev->dev, device, sizeof(struct device));
+	dev_set_name(&dev->dev, "w1_bus_master%u", dev->id);
+	snprintf(dev->name, sizeof(dev->name), "w1_bus_master%u", dev->id);
+	dev->dev.init_name = dev->name;
+
+	dev->driver = driver;
+
+	dev->seq = 1;
+
+	err = device_register(&dev->dev);
+	if (err) {
+		pr_err("Failed to register master device. err=%d\n", err);
+		put_device(&dev->dev);
+		dev = NULL;
+	}
+
+	return dev;
+}
+
+static void w1_free_dev(struct w1_master *dev)
+{
+	device_unregister(&dev->dev);
+}
+
+/**
+ * w1_add_master_device() - registers a new master device
+ * @master:	master bus device to register
+ */
+int w1_add_master_device(struct w1_bus_master *master)
+{
+	struct w1_master *dev, *entry;
+	int retval = 0;
+	struct w1_netlink_msg msg;
+	int id, found;
+
+	/* validate minimum functionality */
+	if (!(master->touch_bit && master->reset_bus) &&
+	    !(master->write_bit && master->read_bit) &&
+	    !(master->write_byte && master->read_byte && master->reset_bus)) {
+		pr_err("w1_add_master_device: invalid function set\n");
+		return(-EINVAL);
+	}
+
+	/* Lock until the device is added (or not) to w1_masters. */
+	mutex_lock(&w1_mlock);
+	/* Search for the first available id (starting at 1). */
+	id = 0;
+	do {
+		++id;
+		found = 0;
+		list_for_each_entry(entry, &w1_masters, w1_master_entry) {
+			if (entry->id == id) {
+				found = 1;
+				break;
+			}
+		}
+	} while (found);
+
+	dev = w1_alloc_dev(id, w1_max_slave_count, w1_max_slave_ttl,
+		&w1_master_driver, &w1_master_device);
+	if (!dev) {
+		mutex_unlock(&w1_mlock);
+		return -ENOMEM;
+	}
+
+	retval =  w1_create_master_attributes(dev);
+	if (retval) {
+		mutex_unlock(&w1_mlock);
+		goto err_out_free_dev;
+	}
+
+	memcpy(dev->bus_master, master, sizeof(struct w1_bus_master));
+
+	dev->initialized = 1;
+
+	dev->thread = kthread_run(&w1_process, dev, "%s", dev->name);
+	if (IS_ERR(dev->thread)) {
+		retval = PTR_ERR(dev->thread);
+		dev_err(&dev->dev,
+			 "Failed to create new kernel thread. err=%d\n",
+			 retval);
+		mutex_unlock(&w1_mlock);
+		goto err_out_rm_attr;
+	}
+
+	list_add(&dev->w1_master_entry, &w1_masters);
+	mutex_unlock(&w1_mlock);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.id.mst.id = dev->id;
+	msg.type = W1_MASTER_ADD;
+	w1_netlink_send(dev, &msg);
+
+	return 0;
+
+#if 0 /* Thread cleanup code, not required currently. */
+err_out_kill_thread:
+	set_bit(W1_ABORT_SEARCH, &dev->flags);
+	kthread_stop(dev->thread);
+#endif
+err_out_rm_attr:
+	w1_destroy_master_attributes(dev);
+err_out_free_dev:
+	w1_free_dev(dev);
+
+	return retval;
+}
+EXPORT_SYMBOL(w1_add_master_device);
+
+void __w1_remove_master_device(struct w1_master *dev)
+{
+	struct w1_netlink_msg msg;
+	struct w1_slave *sl, *sln;
+
+	mutex_lock(&w1_mlock);
+	list_del(&dev->w1_master_entry);
+	mutex_unlock(&w1_mlock);
+
+	set_bit(W1_ABORT_SEARCH, &dev->flags);
+	kthread_stop(dev->thread);
+
+	mutex_lock(&dev->mutex);
+	mutex_lock(&dev->list_mutex);
+	list_for_each_entry_safe(sl, sln, &dev->slist, w1_slave_entry) {
+		mutex_unlock(&dev->list_mutex);
+		w1_slave_detach(sl);
+		mutex_lock(&dev->list_mutex);
+	}
+	w1_destroy_master_attributes(dev);
+	mutex_unlock(&dev->list_mutex);
+	mutex_unlock(&dev->mutex);
+	atomic_dec(&dev->refcnt);
+
+	while (atomic_read(&dev->refcnt)) {
+		dev_info(&dev->dev, "Waiting for %s to become free: refcnt=%d.\n",
+				dev->name, atomic_read(&dev->refcnt));
+
+		if (msleep_interruptible(1000))
+			flush_signals(current);
+		mutex_lock(&dev->list_mutex);
+		w1_process_callbacks(dev);
+		mutex_unlock(&dev->list_mutex);
+	}
+	mutex_lock(&dev->list_mutex);
+	w1_process_callbacks(dev);
+	mutex_unlock(&dev->list_mutex);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.id.mst.id = dev->id;
+	msg.type = W1_MASTER_REMOVE;
+	w1_netlink_send(dev, &msg);
+
+	w1_free_dev(dev);
+}
+
+/**
+ * w1_remove_master_device() - unregister a master device
+ * @bm:	master bus device to remove
+ */
+void w1_remove_master_device(struct w1_bus_master *bm)
+{
+	struct w1_master *dev, *found = NULL;
+
+	list_for_each_entry(dev, &w1_masters, w1_master_entry) {
+		if (!dev->initialized)
+			continue;
+
+		if (dev->bus_master->data == bm->data) {
+			found = dev;
+			break;
+		}
+	}
+
+	if (!found) {
+		pr_err("Device doesn't exist.\n");
+		return;
+	}
+
+	__w1_remove_master_device(found);
+}
+EXPORT_SYMBOL(w1_remove_master_device);