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, 226 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c
new file mode 100644
index 000000000..fea8a4f85
--- /dev/null
+++ b/drivers/clocksource/timer-keystone.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Keystone broadcast clock-event
+ *
+ * Copyright 2013 Texas Instruments, Inc.
+ *
+ * Author: Ivan Khoronzhuk <ivan.khoronzhuk@ti.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+
+#define TIMER_NAME			"timer-keystone"
+
+/* Timer register offsets */
+#define TIM12				0x10
+#define TIM34				0x14
+#define PRD12				0x18
+#define PRD34				0x1c
+#define TCR				0x20
+#define TGCR				0x24
+#define INTCTLSTAT			0x44
+
+/* Timer register bitfields */
+#define TCR_ENAMODE_MASK		0xC0
+#define TCR_ENAMODE_ONESHOT_MASK	0x40
+#define TCR_ENAMODE_PERIODIC_MASK	0x80
+
+#define TGCR_TIM_UNRESET_MASK		0x03
+#define INTCTLSTAT_ENINT_MASK		0x01
+
+/**
+ * struct keystone_timer: holds timer's data
+ * @base: timer memory base address
+ * @hz_period: cycles per HZ period
+ * @event_dev: event device based on timer
+ */
+static struct keystone_timer {
+	void __iomem *base;
+	unsigned long hz_period;
+	struct clock_event_device event_dev;
+} timer;
+
+static inline u32 keystone_timer_readl(unsigned long rg)
+{
+	return readl_relaxed(timer.base + rg);
+}
+
+static inline void keystone_timer_writel(u32 val, unsigned long rg)
+{
+	writel_relaxed(val, timer.base + rg);
+}
+
+/**
+ * keystone_timer_barrier: write memory barrier
+ * use explicit barrier to avoid using readl/writel non relaxed function
+ * variants, because in our case non relaxed variants hide the true places
+ * where barrier is needed.
+ */
+static inline void keystone_timer_barrier(void)
+{
+	__iowmb();
+}
+
+/**
+ * keystone_timer_config: configures timer to work in oneshot/periodic modes.
+ * @ mask: mask of the mode to configure
+ * @ period: cycles number to configure for
+ */
+static int keystone_timer_config(u64 period, int mask)
+{
+	u32 tcr;
+	u32 off;
+
+	tcr = keystone_timer_readl(TCR);
+	off = tcr & ~(TCR_ENAMODE_MASK);
+
+	/* set enable mode */
+	tcr |= mask;
+
+	/* disable timer */
+	keystone_timer_writel(off, TCR);
+	/* here we have to be sure the timer has been disabled */
+	keystone_timer_barrier();
+
+	/* reset counter to zero, set new period */
+	keystone_timer_writel(0, TIM12);
+	keystone_timer_writel(0, TIM34);
+	keystone_timer_writel(period & 0xffffffff, PRD12);
+	keystone_timer_writel(period >> 32, PRD34);
+
+	/*
+	 * enable timer
+	 * here we have to be sure that CNTLO, CNTHI, PRDLO, PRDHI registers
+	 * have been written.
+	 */
+	keystone_timer_barrier();
+	keystone_timer_writel(tcr, TCR);
+	return 0;
+}
+
+static void keystone_timer_disable(void)
+{
+	u32 tcr;
+
+	tcr = keystone_timer_readl(TCR);
+
+	/* disable timer */
+	tcr &= ~(TCR_ENAMODE_MASK);
+	keystone_timer_writel(tcr, TCR);
+}
+
+static irqreturn_t keystone_timer_interrupt(int irq, void *dev_id)
+{
+	struct clock_event_device *evt = dev_id;
+
+	evt->event_handler(evt);
+	return IRQ_HANDLED;
+}
+
+static int keystone_set_next_event(unsigned long cycles,
+				  struct clock_event_device *evt)
+{
+	return keystone_timer_config(cycles, TCR_ENAMODE_ONESHOT_MASK);
+}
+
+static int keystone_shutdown(struct clock_event_device *evt)
+{
+	keystone_timer_disable();
+	return 0;
+}
+
+static int keystone_set_periodic(struct clock_event_device *evt)
+{
+	keystone_timer_config(timer.hz_period, TCR_ENAMODE_PERIODIC_MASK);
+	return 0;
+}
+
+static int __init keystone_timer_init(struct device_node *np)
+{
+	struct clock_event_device *event_dev = &timer.event_dev;
+	unsigned long rate;
+	struct clk *clk;
+	int irq, error;
+
+	irq  = irq_of_parse_and_map(np, 0);
+	if (!irq) {
+		pr_err("%s: failed to map interrupts\n", __func__);
+		return -EINVAL;
+	}
+
+	timer.base = of_iomap(np, 0);
+	if (!timer.base) {
+		pr_err("%s: failed to map registers\n", __func__);
+		return -ENXIO;
+	}
+
+	clk = of_clk_get(np, 0);
+	if (IS_ERR(clk)) {
+		pr_err("%s: failed to get clock\n", __func__);
+		iounmap(timer.base);
+		return PTR_ERR(clk);
+	}
+
+	error = clk_prepare_enable(clk);
+	if (error) {
+		pr_err("%s: failed to enable clock\n", __func__);
+		goto err;
+	}
+
+	rate = clk_get_rate(clk);
+
+	/* disable, use internal clock source */
+	keystone_timer_writel(0, TCR);
+	/* here we have to be sure the timer has been disabled */
+	keystone_timer_barrier();
+
+	/* reset timer as 64-bit, no pre-scaler, plus features are disabled */
+	keystone_timer_writel(0, TGCR);
+
+	/* unreset timer */
+	keystone_timer_writel(TGCR_TIM_UNRESET_MASK, TGCR);
+
+	/* init counter to zero */
+	keystone_timer_writel(0, TIM12);
+	keystone_timer_writel(0, TIM34);
+
+	timer.hz_period = DIV_ROUND_UP(rate, HZ);
+
+	/* enable timer interrupts */
+	keystone_timer_writel(INTCTLSTAT_ENINT_MASK, INTCTLSTAT);
+
+	error = request_irq(irq, keystone_timer_interrupt, IRQF_TIMER,
+			    TIMER_NAME, event_dev);
+	if (error) {
+		pr_err("%s: failed to setup irq\n", __func__);
+		goto err;
+	}
+
+	/* setup clockevent */
+	event_dev->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	event_dev->set_next_event = keystone_set_next_event;
+	event_dev->set_state_shutdown = keystone_shutdown;
+	event_dev->set_state_periodic = keystone_set_periodic;
+	event_dev->set_state_oneshot = keystone_shutdown;
+	event_dev->cpumask = cpu_possible_mask;
+	event_dev->owner = THIS_MODULE;
+	event_dev->name = TIMER_NAME;
+	event_dev->irq = irq;
+
+	clockevents_config_and_register(event_dev, rate, 1, ULONG_MAX);
+
+	pr_info("keystone timer clock @%lu Hz\n", rate);
+	return 0;
+err:
+	clk_put(clk);
+	iounmap(timer.base);
+	return error;
+}
+
+TIMER_OF_DECLARE(keystone_timer, "ti,keystone-timer",
+			   keystone_timer_init);