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, 180 insertions, 0 deletions

diff --git a/fs/proc/stat.c b/fs/proc/stat.c
new file mode 100644
index 000000000..79b42f2bf
--- /dev/null
+++ b/fs/proc/stat.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cpumask.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/sched/stat.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+#include <linux/time.h>
+#include <linux/time_namespace.h>
+#include <linux/irqnr.h>
+#include <linux/sched/cputime.h>
+#include <linux/tick.h>
+
+#ifndef arch_irq_stat_cpu
+#define arch_irq_stat_cpu(cpu) 0
+#endif
+
+static void show_irq_gap(struct seq_file *p, unsigned int gap)
+{
+	static const char zeros[] = " 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0";
+
+	while (gap > 0) {
+		unsigned int inc;
+
+		inc = min_t(unsigned int, gap, ARRAY_SIZE(zeros) / 2);
+		seq_write(p, zeros, 2 * inc);
+		gap -= inc;
+	}
+}
+
+static void show_all_irqs(struct seq_file *p)
+{
+	unsigned int i, next = 0;
+
+	for_each_active_irq(i) {
+		show_irq_gap(p, i - next);
+		seq_put_decimal_ull(p, " ", kstat_irqs_usr(i));
+		next = i + 1;
+	}
+	show_irq_gap(p, irq_get_nr_irqs() - next);
+}
+
+static int show_stat(struct seq_file *p, void *v)
+{
+	int i, j;
+	u64 user, nice, system, idle, iowait, irq, softirq, steal;
+	u64 guest, guest_nice;
+	u64 sum = 0;
+	u64 sum_softirq = 0;
+	unsigned int per_softirq_sums[NR_SOFTIRQS] = {0};
+	struct timespec64 boottime;
+
+	user = nice = system = idle = iowait =
+		irq = softirq = steal = 0;
+	guest = guest_nice = 0;
+	getboottime64(&boottime);
+	/* shift boot timestamp according to the timens offset */
+	timens_sub_boottime(&boottime);
+
+	for_each_possible_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		user		+= cpustat[CPUTIME_USER];
+		nice		+= cpustat[CPUTIME_NICE];
+		system		+= cpustat[CPUTIME_SYSTEM];
+		idle		+= cpustat[CPUTIME_IDLE];
+		iowait		+= cpustat[CPUTIME_IOWAIT];
+		irq		+= cpustat[CPUTIME_IRQ];
+		softirq		+= cpustat[CPUTIME_SOFTIRQ];
+		steal		+= cpustat[CPUTIME_STEAL];
+		guest		+= cpustat[CPUTIME_GUEST];
+		guest_nice	+= cpustat[CPUTIME_GUEST_NICE];
+		sum		+= kstat_cpu_irqs_sum(i);
+		sum		+= arch_irq_stat_cpu(i);
+
+		for (j = 0; j < NR_SOFTIRQS; j++) {
+			unsigned int softirq_stat = kstat_softirqs_cpu(j, i);
+
+			per_softirq_sums[j] += softirq_stat;
+			sum_softirq += softirq_stat;
+		}
+	}
+
+	seq_put_decimal_ull(p, "cpu  ", nsec_to_clock_t(user));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+	seq_putc(p, '\n');
+
+	for_each_online_cpu(i) {
+		struct kernel_cpustat kcpustat;
+		u64 *cpustat = kcpustat.cpustat;
+
+		kcpustat_cpu_fetch(&kcpustat, i);
+
+		/* Copy values here to work around gcc-2.95.3, gcc-2.96 */
+		user		= cpustat[CPUTIME_USER];
+		nice		= cpustat[CPUTIME_NICE];
+		system		= cpustat[CPUTIME_SYSTEM];
+		idle		= cpustat[CPUTIME_IDLE];
+		iowait		= cpustat[CPUTIME_IOWAIT];
+		irq		= cpustat[CPUTIME_IRQ];
+		softirq		= cpustat[CPUTIME_SOFTIRQ];
+		steal		= cpustat[CPUTIME_STEAL];
+		guest		= cpustat[CPUTIME_GUEST];
+		guest_nice	= cpustat[CPUTIME_GUEST_NICE];
+		seq_printf(p, "cpu%d", i);
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
+		seq_putc(p, '\n');
+	}
+	seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
+
+	show_all_irqs(p);
+
+	seq_printf(p,
+		"\nctxt %llu\n"
+		"btime %llu\n"
+		"processes %lu\n"
+		"procs_running %u\n"
+		"procs_blocked %u\n",
+		nr_context_switches(),
+		(unsigned long long)boottime.tv_sec,
+		total_forks,
+		nr_running(),
+		nr_iowait());
+
+	seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq);
+
+	for (i = 0; i < NR_SOFTIRQS; i++)
+		seq_put_decimal_ull(p, " ", per_softirq_sums[i]);
+	seq_putc(p, '\n');
+
+	return 0;
+}
+
+static int stat_open(struct inode *inode, struct file *file)
+{
+	unsigned int size = 1024 + 128 * num_online_cpus();
+
+	/* minimum size to display an interrupt count : 2 bytes */
+	size += 2 * irq_get_nr_irqs();
+	return single_open_size(file, show_stat, NULL, size);
+}
+
+static const struct proc_ops stat_proc_ops = {
+	.proc_flags	= PROC_ENTRY_PERMANENT,
+	.proc_open	= stat_open,
+	.proc_read_iter	= seq_read_iter,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+};
+
+static int __init proc_stat_init(void)
+{
+	proc_create("stat", 0, NULL, &stat_proc_ops);
+	return 0;
+}
+fs_initcall(proc_stat_init);