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, 168 insertions, 0 deletions

diff --git a/drivers/edac/edac_module.c b/drivers/edac/edac_module.c
new file mode 100644
index 000000000..1c9f62382
--- /dev/null
+++ b/drivers/edac/edac_module.c
@@ -0,0 +1,168 @@
+/*
+ * edac_module.c
+ *
+ * (C) 2007 www.softwarebitmaker.com
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ *
+ * Author: Doug Thompson <dougthompson@xmission.com>
+ *
+ */
+#include <linux/edac.h>
+
+#include "edac_mc.h"
+#include "edac_module.h"
+
+#define EDAC_VERSION "Ver: 3.0.0"
+
+#ifdef CONFIG_EDAC_DEBUG
+
+static int edac_set_debug_level(const char *buf,
+				const struct kernel_param *kp)
+{
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (val > 4)
+		return -EINVAL;
+
+	return param_set_int(buf, kp);
+}
+
+/* Values of 0 to 4 will generate output */
+int edac_debug_level = 2;
+EXPORT_SYMBOL_GPL(edac_debug_level);
+
+module_param_call(edac_debug_level, edac_set_debug_level, param_get_int,
+		  &edac_debug_level, 0644);
+MODULE_PARM_DESC(edac_debug_level, "EDAC debug level: [0-4], default: 2");
+#endif
+
+/*
+ * edac_op_state_to_string()
+ */
+char *edac_op_state_to_string(int opstate)
+{
+	if (opstate == OP_RUNNING_POLL)
+		return "POLLED";
+	else if (opstate == OP_RUNNING_INTERRUPT)
+		return "INTERRUPT";
+	else if (opstate == OP_RUNNING_POLL_INTR)
+		return "POLL-INTR";
+	else if (opstate == OP_ALLOC)
+		return "ALLOC";
+	else if (opstate == OP_OFFLINE)
+		return "OFFLINE";
+
+	return "UNKNOWN";
+}
+
+/*
+ * sysfs object: /sys/devices/system/edac
+ *	need to export to other files
+ */
+static const struct bus_type edac_subsys = {
+	.name = "edac",
+	.dev_name = "edac",
+};
+
+static int edac_subsys_init(void)
+{
+	int err;
+
+	/* create the /sys/devices/system/edac directory */
+	err = subsys_system_register(&edac_subsys, NULL);
+	if (err)
+		printk(KERN_ERR "Error registering toplevel EDAC sysfs dir\n");
+
+	return err;
+}
+
+static void edac_subsys_exit(void)
+{
+	bus_unregister(&edac_subsys);
+}
+
+/* return pointer to the 'edac' node in sysfs */
+const struct bus_type *edac_get_sysfs_subsys(void)
+{
+	return &edac_subsys;
+}
+EXPORT_SYMBOL_GPL(edac_get_sysfs_subsys);
+/*
+ * edac_init
+ *      module initialization entry point
+ */
+static int __init edac_init(void)
+{
+	int err = 0;
+
+	edac_printk(KERN_INFO, EDAC_MC, EDAC_VERSION "\n");
+
+	err = edac_subsys_init();
+	if (err)
+		return err;
+
+	/*
+	 * Harvest and clear any boot/initialization PCI parity errors
+	 *
+	 * FIXME: This only clears errors logged by devices present at time of
+	 *      module initialization.  We should also do an initial clear
+	 *      of each newly hotplugged device.
+	 */
+	edac_pci_clear_parity_errors();
+
+	err = edac_mc_sysfs_init();
+	if (err)
+		goto err_sysfs;
+
+	edac_debugfs_init();
+
+	err = edac_workqueue_setup();
+	if (err) {
+		edac_printk(KERN_ERR, EDAC_MC, "Failure initializing workqueue\n");
+		goto err_wq;
+	}
+
+	return 0;
+
+err_wq:
+	edac_debugfs_exit();
+	edac_mc_sysfs_exit();
+
+err_sysfs:
+	edac_subsys_exit();
+
+	return err;
+}
+
+/*
+ * edac_exit()
+ *      module exit/termination function
+ */
+static void __exit edac_exit(void)
+{
+	edac_dbg(0, "\n");
+
+	/* tear down the various subsystems */
+	edac_workqueue_teardown();
+	edac_mc_sysfs_exit();
+	edac_debugfs_exit();
+	edac_subsys_exit();
+}
+
+/*
+ * Inform the kernel of our entry and exit points
+ */
+subsys_initcall(edac_init);
+module_exit(edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Doug Thompson www.softwarebitmaker.com, et al");
+MODULE_DESCRIPTION("Core library routines for EDAC reporting");