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, 242 insertions, 0 deletions

diff --git a/lib/kunit/debugfs.c b/lib/kunit/debugfs.c
new file mode 100644
index 000000000..442b2ceb9
--- /dev/null
+++ b/lib/kunit/debugfs.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2020, Oracle and/or its affiliates.
+ *    Author: Alan Maguire <alan.maguire@oracle.com>
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+
+#include <kunit/test.h>
+#include <kunit/test-bug.h>
+
+#include "string-stream.h"
+#include "debugfs.h"
+
+#define KUNIT_DEBUGFS_ROOT             "kunit"
+#define KUNIT_DEBUGFS_RESULTS          "results"
+#define KUNIT_DEBUGFS_RUN              "run"
+
+/*
+ * Create a debugfs representation of test suites:
+ *
+ * Path						Semantics
+ * /sys/kernel/debug/kunit/<testsuite>/results	Show results of last run for
+ *						testsuite
+ * /sys/kernel/debug/kunit/<testsuite>/run	Write to this file to trigger
+ *						testsuite to run
+ *
+ */
+
+static struct dentry *debugfs_rootdir;
+
+void kunit_debugfs_cleanup(void)
+{
+	debugfs_remove_recursive(debugfs_rootdir);
+}
+
+void kunit_debugfs_init(void)
+{
+	if (!debugfs_rootdir)
+		debugfs_rootdir = debugfs_create_dir(KUNIT_DEBUGFS_ROOT, NULL);
+}
+
+static void debugfs_print_result(struct seq_file *seq, struct string_stream *log)
+{
+	struct string_stream_fragment *frag_container;
+
+	if (!log)
+		return;
+
+	/*
+	 * Walk the fragments so we don't need to allocate a temporary
+	 * buffer to hold the entire string.
+	 */
+	spin_lock(&log->lock);
+	list_for_each_entry(frag_container, &log->fragments, node)
+		seq_printf(seq, "%s", frag_container->fragment);
+	spin_unlock(&log->lock);
+}
+
+/*
+ * /sys/kernel/debug/kunit/<testsuite>/results shows all results for testsuite.
+ */
+static int debugfs_print_results(struct seq_file *seq, void *v)
+{
+	struct kunit_suite *suite = (struct kunit_suite *)seq->private;
+	enum kunit_status success;
+	struct kunit_case *test_case;
+
+	if (!suite)
+		return 0;
+
+	success = kunit_suite_has_succeeded(suite);
+
+	/* Print KTAP header so the debugfs log can be parsed as valid KTAP. */
+	seq_puts(seq, "KTAP version 1\n");
+	seq_puts(seq, "1..1\n");
+
+	if (suite->status != KUNIT_SKIPPED) {
+		/* Print suite header because it is not stored in the test logs. */
+		seq_puts(seq,
+			 KUNIT_SUBTEST_INDENT "KTAP version 1\n");
+		seq_printf(seq,
+			   KUNIT_SUBTEST_INDENT "# Subtest: %s\n",
+			   suite->name);
+		seq_printf(seq,
+			   KUNIT_SUBTEST_INDENT "1..%zd\n",
+			   kunit_suite_num_test_cases(suite));
+
+		kunit_suite_for_each_test_case(suite, test_case)
+			debugfs_print_result(seq, test_case->log);
+	}
+
+	debugfs_print_result(seq, suite->log);
+
+	if (suite->status != KUNIT_SKIPPED)
+		seq_printf(seq, "%s %d %s\n",
+			   kunit_status_to_ok_not_ok(success), 1, suite->name);
+	else
+		seq_printf(seq, "%s %d %s # SKIP %s\n",
+			   kunit_status_to_ok_not_ok(success), 1, suite->name,
+			   suite->status_comment);
+	return 0;
+}
+
+static int debugfs_release(struct inode *inode, struct file *file)
+{
+	return single_release(inode, file);
+}
+
+static int debugfs_results_open(struct inode *inode, struct file *file)
+{
+	struct kunit_suite *suite;
+
+	suite = (struct kunit_suite *)inode->i_private;
+
+	return single_open(file, debugfs_print_results, suite);
+}
+
+/*
+ * Print a usage message to the debugfs "run" file
+ * (/sys/kernel/debug/kunit/<testsuite>/run) if opened.
+ */
+static int debugfs_print_run(struct seq_file *seq, void *v)
+{
+	struct kunit_suite *suite = (struct kunit_suite *)seq->private;
+
+	seq_puts(seq, "Write to this file to trigger the test suite to run.\n");
+	seq_printf(seq, "usage: echo \"any string\" > /sys/kernel/debugfs/kunit/%s/run\n",
+			suite->name);
+	return 0;
+}
+
+/*
+ * The debugfs "run" file (/sys/kernel/debug/kunit/<testsuite>/run)
+ * contains no information. Write to the file to trigger the test suite
+ * to run.
+ */
+static int debugfs_run_open(struct inode *inode, struct file *file)
+{
+	struct kunit_suite *suite;
+
+	suite = (struct kunit_suite *)inode->i_private;
+
+	return single_open(file, debugfs_print_run, suite);
+}
+
+/*
+ * Trigger a test suite to run by writing to the suite's "run" debugfs
+ * file found at: /sys/kernel/debug/kunit/<testsuite>/run
+ *
+ * Note: what is written to this file will not be saved.
+ */
+static ssize_t debugfs_run(struct file *file,
+		const char __user *buf, size_t count, loff_t *ppos)
+{
+	struct inode *f_inode = file->f_inode;
+	struct kunit_suite *suite = (struct kunit_suite *) f_inode->i_private;
+
+	__kunit_test_suites_init(&suite, 1, true);
+
+	return count;
+}
+
+static const struct file_operations debugfs_results_fops = {
+	.open = debugfs_results_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = debugfs_release,
+};
+
+static const struct file_operations debugfs_run_fops = {
+	.open = debugfs_run_open,
+	.read = seq_read,
+	.write = debugfs_run,
+	.llseek = seq_lseek,
+	.release = debugfs_release,
+};
+
+void kunit_debugfs_create_suite(struct kunit_suite *suite)
+{
+	struct kunit_case *test_case;
+	struct string_stream *stream;
+
+	/* If suite log already allocated, do not create new debugfs files. */
+	if (suite->log)
+		return;
+
+	/*
+	 * Allocate logs before creating debugfs representation.
+	 * The suite->log and test_case->log pointer are expected to be NULL
+	 * if there isn't a log, so only set it if the log stream was created
+	 * successfully.
+	 */
+	stream = alloc_string_stream(GFP_KERNEL);
+	if (IS_ERR(stream))
+		return;
+
+	string_stream_set_append_newlines(stream, true);
+	suite->log = stream;
+
+	kunit_suite_for_each_test_case(suite, test_case) {
+		stream = alloc_string_stream(GFP_KERNEL);
+		if (IS_ERR(stream))
+			goto err;
+
+		string_stream_set_append_newlines(stream, true);
+		test_case->log = stream;
+	}
+
+	suite->debugfs = debugfs_create_dir(suite->name, debugfs_rootdir);
+
+	debugfs_create_file(KUNIT_DEBUGFS_RESULTS, S_IFREG | 0444,
+			    suite->debugfs,
+			    suite, &debugfs_results_fops);
+
+	/* Do not create file to re-run test if test runs on init */
+	if (!suite->is_init) {
+		debugfs_create_file(KUNIT_DEBUGFS_RUN, S_IFREG | 0644,
+				    suite->debugfs,
+				    suite, &debugfs_run_fops);
+	}
+	return;
+
+err:
+	string_stream_destroy(suite->log);
+	suite->log = NULL;
+	kunit_suite_for_each_test_case(suite, test_case) {
+		string_stream_destroy(test_case->log);
+		test_case->log = NULL;
+	}
+}
+
+void kunit_debugfs_destroy_suite(struct kunit_suite *suite)
+{
+	struct kunit_case *test_case;
+
+	debugfs_remove_recursive(suite->debugfs);
+	string_stream_destroy(suite->log);
+	kunit_suite_for_each_test_case(suite, test_case)
+		string_stream_destroy(test_case->log);
+}