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, 313 insertions, 0 deletions

diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
new file mode 100644
index 000000000..e72c43615
--- /dev/null
+++ b/drivers/usb/chipidea/debug.c
@@ -0,0 +1,313 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/usb/ch9.h>
+#include <linux/usb/gadget.h>
+#include <linux/usb/phy.h>
+#include <linux/usb/otg.h>
+#include <linux/usb/otg-fsm.h>
+#include <linux/usb/chipidea.h>
+
+#include "ci.h"
+#include "udc.h"
+#include "bits.h"
+#include "otg.h"
+
+/*
+ * ci_device_show: prints information about device capabilities and status
+ */
+static int ci_device_show(struct seq_file *s, void *data)
+{
+	struct ci_hdrc *ci = s->private;
+	struct usb_gadget *gadget = &ci->gadget;
+
+	seq_printf(s, "speed             = %d\n", gadget->speed);
+	seq_printf(s, "max_speed         = %d\n", gadget->max_speed);
+	seq_printf(s, "is_otg            = %d\n", gadget->is_otg);
+	seq_printf(s, "is_a_peripheral   = %d\n", gadget->is_a_peripheral);
+	seq_printf(s, "b_hnp_enable      = %d\n", gadget->b_hnp_enable);
+	seq_printf(s, "a_hnp_support     = %d\n", gadget->a_hnp_support);
+	seq_printf(s, "a_alt_hnp_support = %d\n", gadget->a_alt_hnp_support);
+	seq_printf(s, "name              = %s\n",
+		   (gadget->name ? gadget->name : ""));
+
+	if (!ci->driver)
+		return 0;
+
+	seq_printf(s, "gadget function   = %s\n",
+		       (ci->driver->function ? ci->driver->function : ""));
+	seq_printf(s, "gadget max speed  = %d\n", ci->driver->max_speed);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ci_device);
+
+/*
+ * ci_port_test_show: reads port test mode
+ */
+static int ci_port_test_show(struct seq_file *s, void *data)
+{
+	struct ci_hdrc *ci = s->private;
+	unsigned long flags;
+	unsigned mode;
+
+	pm_runtime_get_sync(ci->dev);
+	spin_lock_irqsave(&ci->lock, flags);
+	mode = hw_port_test_get(ci);
+	spin_unlock_irqrestore(&ci->lock, flags);
+	pm_runtime_put_sync(ci->dev);
+
+	seq_printf(s, "mode = %u\n", mode);
+
+	return 0;
+}
+
+/*
+ * ci_port_test_write: writes port test mode
+ */
+static ssize_t ci_port_test_write(struct file *file, const char __user *ubuf,
+				  size_t count, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct ci_hdrc *ci = s->private;
+	unsigned long flags;
+	unsigned mode;
+	char buf[32];
+	int ret;
+
+	count = min_t(size_t, sizeof(buf) - 1, count);
+	if (copy_from_user(buf, ubuf, count))
+		return -EFAULT;
+
+	/* sscanf requires a zero terminated string */
+	buf[count] = '\0';
+
+	if (sscanf(buf, "%u", &mode) != 1)
+		return -EINVAL;
+
+	if (mode > 255)
+		return -EBADRQC;
+
+	pm_runtime_get_sync(ci->dev);
+	spin_lock_irqsave(&ci->lock, flags);
+	ret = hw_port_test_set(ci, mode);
+	spin_unlock_irqrestore(&ci->lock, flags);
+	pm_runtime_put_sync(ci->dev);
+
+	return ret ? ret : count;
+}
+
+static int ci_port_test_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ci_port_test_show, inode->i_private);
+}
+
+static const struct file_operations ci_port_test_fops = {
+	.open		= ci_port_test_open,
+	.write		= ci_port_test_write,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+/*
+ * ci_qheads_show: DMA contents of all queue heads
+ */
+static int ci_qheads_show(struct seq_file *s, void *data)
+{
+	struct ci_hdrc *ci = s->private;
+	unsigned long flags;
+	unsigned i, j;
+
+	if (ci->role != CI_ROLE_GADGET) {
+		seq_printf(s, "not in gadget mode\n");
+		return 0;
+	}
+
+	spin_lock_irqsave(&ci->lock, flags);
+	for (i = 0; i < ci->hw_ep_max/2; i++) {
+		struct ci_hw_ep *hweprx = &ci->ci_hw_ep[i];
+		struct ci_hw_ep *hweptx =
+			&ci->ci_hw_ep[i + ci->hw_ep_max/2];
+		seq_printf(s, "EP=%02i: RX=%08X TX=%08X\n",
+			   i, (u32)hweprx->qh.dma, (u32)hweptx->qh.dma);
+		for (j = 0; j < (sizeof(struct ci_hw_qh)/sizeof(u32)); j++)
+			seq_printf(s, " %04X:    %08X    %08X\n", j,
+				   *((u32 *)hweprx->qh.ptr + j),
+				   *((u32 *)hweptx->qh.ptr + j));
+	}
+	spin_unlock_irqrestore(&ci->lock, flags);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ci_qheads);
+
+/*
+ * ci_requests_show: DMA contents of all requests currently queued (all endpts)
+ */
+static int ci_requests_show(struct seq_file *s, void *data)
+{
+	struct ci_hdrc *ci = s->private;
+	unsigned long flags;
+	struct ci_hw_req *req = NULL;
+	struct td_node *node, *tmpnode;
+	unsigned i, j, qsize = sizeof(struct ci_hw_td)/sizeof(u32);
+
+	if (ci->role != CI_ROLE_GADGET) {
+		seq_printf(s, "not in gadget mode\n");
+		return 0;
+	}
+
+	spin_lock_irqsave(&ci->lock, flags);
+	for (i = 0; i < ci->hw_ep_max; i++)
+		list_for_each_entry(req, &ci->ci_hw_ep[i].qh.queue, queue) {
+			list_for_each_entry_safe(node, tmpnode, &req->tds, td) {
+				seq_printf(s, "EP=%02i: TD=%08X %s\n",
+					   i % (ci->hw_ep_max / 2),
+					   (u32)node->dma,
+					   ((i < ci->hw_ep_max/2) ?
+					   "RX" : "TX"));
+
+				for (j = 0; j < qsize; j++)
+					seq_printf(s, " %04X:    %08X\n", j,
+						   *((u32 *)node->ptr + j));
+			}
+		}
+	spin_unlock_irqrestore(&ci->lock, flags);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ci_requests);
+
+static int ci_otg_show(struct seq_file *s, void *unused)
+{
+	struct ci_hdrc *ci = s->private;
+	struct otg_fsm *fsm;
+
+	if (!ci || !ci_otg_is_fsm_mode(ci))
+		return 0;
+
+	fsm = &ci->fsm;
+
+	/* ------ State ----- */
+	seq_printf(s, "OTG state: %s\n\n",
+			usb_otg_state_string(ci->otg.state));
+
+	/* ------ State Machine Variables ----- */
+	seq_printf(s, "a_bus_drop: %d\n", fsm->a_bus_drop);
+
+	seq_printf(s, "a_bus_req: %d\n", fsm->a_bus_req);
+
+	seq_printf(s, "a_srp_det: %d\n", fsm->a_srp_det);
+
+	seq_printf(s, "a_vbus_vld: %d\n", fsm->a_vbus_vld);
+
+	seq_printf(s, "b_conn: %d\n", fsm->b_conn);
+
+	seq_printf(s, "adp_change: %d\n", fsm->adp_change);
+
+	seq_printf(s, "power_up: %d\n", fsm->power_up);
+
+	seq_printf(s, "a_bus_resume: %d\n", fsm->a_bus_resume);
+
+	seq_printf(s, "a_bus_suspend: %d\n", fsm->a_bus_suspend);
+
+	seq_printf(s, "a_conn: %d\n", fsm->a_conn);
+
+	seq_printf(s, "b_bus_req: %d\n", fsm->b_bus_req);
+
+	seq_printf(s, "b_bus_suspend: %d\n", fsm->b_bus_suspend);
+
+	seq_printf(s, "b_se0_srp: %d\n", fsm->b_se0_srp);
+
+	seq_printf(s, "b_ssend_srp: %d\n", fsm->b_ssend_srp);
+
+	seq_printf(s, "b_sess_vld: %d\n", fsm->b_sess_vld);
+
+	seq_printf(s, "b_srp_done: %d\n", fsm->b_srp_done);
+
+	seq_printf(s, "drv_vbus: %d\n", fsm->drv_vbus);
+
+	seq_printf(s, "loc_conn: %d\n", fsm->loc_conn);
+
+	seq_printf(s, "loc_sof: %d\n", fsm->loc_sof);
+
+	seq_printf(s, "adp_prb: %d\n", fsm->adp_prb);
+
+	seq_printf(s, "id: %d\n", fsm->id);
+
+	seq_printf(s, "protocol: %d\n", fsm->protocol);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ci_otg);
+
+static int ci_registers_show(struct seq_file *s, void *unused)
+{
+	struct ci_hdrc *ci = s->private;
+	u32 tmp_reg;
+
+	if (!ci || ci->in_lpm)
+		return -EPERM;
+
+	/* ------ Registers ----- */
+	tmp_reg = hw_read_intr_enable(ci);
+	seq_printf(s, "USBINTR reg: %08x\n", tmp_reg);
+
+	tmp_reg = hw_read_intr_status(ci);
+	seq_printf(s, "USBSTS reg: %08x\n", tmp_reg);
+
+	tmp_reg = hw_read(ci, OP_USBMODE, ~0);
+	seq_printf(s, "USBMODE reg: %08x\n", tmp_reg);
+
+	tmp_reg = hw_read(ci, OP_USBCMD, ~0);
+	seq_printf(s, "USBCMD reg: %08x\n", tmp_reg);
+
+	tmp_reg = hw_read(ci, OP_PORTSC, ~0);
+	seq_printf(s, "PORTSC reg: %08x\n", tmp_reg);
+
+	if (ci->is_otg) {
+		tmp_reg = hw_read_otgsc(ci, ~0);
+		seq_printf(s, "OTGSC reg: %08x\n", tmp_reg);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(ci_registers);
+
+/**
+ * dbg_create_files: initializes the attribute interface
+ * @ci: device
+ *
+ * This function returns an error code
+ */
+void dbg_create_files(struct ci_hdrc *ci)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir(dev_name(ci->dev), usb_debug_root);
+
+	debugfs_create_file("device", S_IRUGO, dir, ci, &ci_device_fops);
+	debugfs_create_file("port_test", S_IRUGO | S_IWUSR, dir, ci, &ci_port_test_fops);
+	debugfs_create_file("qheads", S_IRUGO, dir, ci, &ci_qheads_fops);
+	debugfs_create_file("requests", S_IRUGO, dir, ci, &ci_requests_fops);
+
+	if (ci_otg_is_fsm_mode(ci))
+		debugfs_create_file("otg", S_IRUGO, dir, ci, &ci_otg_fops);
+
+	debugfs_create_file("registers", S_IRUGO, dir, ci, &ci_registers_fops);
+}
+
+/**
+ * dbg_remove_files: destroys the attribute interface
+ * @ci: device
+ */
+void dbg_remove_files(struct ci_hdrc *ci)
+{
+	debugfs_lookup_and_remove(dev_name(ci->dev), usb_debug_root);
+}