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, 140 insertions, 0 deletions

diff --git a/drivers/clocksource/timer-mediatek-cpux.c b/drivers/clocksource/timer-mediatek-cpux.c
new file mode 100644
index 000000000..a8e3df4c0
--- /dev/null
+++ b/drivers/clocksource/timer-mediatek-cpux.c
@@ -0,0 +1,140 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * MediaTek SoCs CPUX General Purpose Timer handling
+ *
+ * Based on timer-mediatek.c:
+ * Copyright (C) 2014 Matthias Brugger <matthias.bgg@gmail.com>
+ *
+ * Copyright (C) 2022 Collabora Ltd.
+ *                    AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/irqreturn.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+#include "timer-of.h"
+
+#define TIMER_SYNC_TICKS        3
+
+/* cpux mcusys wrapper */
+#define CPUX_CON_REG		0x0
+#define CPUX_IDX_REG		0x4
+
+/* cpux */
+#define CPUX_IDX_GLOBAL_CTRL	0x0
+ #define CPUX_ENABLE		BIT(0)
+ #define CPUX_CLK_DIV_MASK	GENMASK(10, 8)
+ #define CPUX_CLK_DIV1		BIT(8)
+ #define CPUX_CLK_DIV2		BIT(9)
+ #define CPUX_CLK_DIV4		BIT(10)
+#define CPUX_IDX_GLOBAL_IRQ	0x30
+
+static u32 mtk_cpux_readl(u32 reg_idx, struct timer_of *to)
+{
+	writel(reg_idx, timer_of_base(to) + CPUX_IDX_REG);
+	return readl(timer_of_base(to) + CPUX_CON_REG);
+}
+
+static void mtk_cpux_writel(u32 val, u32 reg_idx, struct timer_of *to)
+{
+	writel(reg_idx, timer_of_base(to) + CPUX_IDX_REG);
+	writel(val, timer_of_base(to) + CPUX_CON_REG);
+}
+
+static void mtk_cpux_set_irq(struct timer_of *to, bool enable)
+{
+	const unsigned long *irq_mask = cpumask_bits(cpu_possible_mask);
+	u32 val;
+
+	val = mtk_cpux_readl(CPUX_IDX_GLOBAL_IRQ, to);
+
+	if (enable)
+		val |= *irq_mask;
+	else
+		val &= ~(*irq_mask);
+
+	mtk_cpux_writel(val, CPUX_IDX_GLOBAL_IRQ, to);
+}
+
+static int mtk_cpux_clkevt_shutdown(struct clock_event_device *clkevt)
+{
+	/* Clear any irq */
+	mtk_cpux_set_irq(to_timer_of(clkevt), false);
+
+	/*
+	 * Disabling CPUXGPT timer will crash the platform, especially
+	 * if Trusted Firmware is using it (usually, for sleep states),
+	 * so we only mask the IRQ and call it a day.
+	 */
+	return 0;
+}
+
+static int mtk_cpux_clkevt_resume(struct clock_event_device *clkevt)
+{
+	mtk_cpux_set_irq(to_timer_of(clkevt), true);
+	return 0;
+}
+
+static struct timer_of to = {
+	/*
+	 * There are per-cpu interrupts for the CPUX General Purpose Timer
+	 * but since this timer feeds the AArch64 System Timer we can rely
+	 * on the CPU timer PPIs as well, so we don't declare TIMER_OF_IRQ.
+	 */
+	.flags = TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name = "mtk-cpuxgpt",
+		.cpumask = cpu_possible_mask,
+		.rating = 10,
+		.set_state_shutdown = mtk_cpux_clkevt_shutdown,
+		.tick_resume = mtk_cpux_clkevt_resume,
+	},
+};
+
+static int __init mtk_cpux_init(struct device_node *node)
+{
+	u32 freq, val;
+	int ret;
+
+	/* If this fails, bad things are about to happen... */
+	ret = timer_of_init(node, &to);
+	if (ret) {
+		WARN(1, "Cannot start CPUX timers.\n");
+		return ret;
+	}
+
+	/*
+	 * Check if we're given a clock with the right frequency for this
+	 * timer, otherwise warn but keep going with the setup anyway, as
+	 * that makes it possible to still boot the kernel, even though
+	 * it may not work correctly (random lockups, etc).
+	 * The reason behind this is that having an early UART may not be
+	 * possible for everyone and this gives a chance to retrieve kmsg
+	 * for eventual debugging even on consumer devices.
+	 */
+	freq = timer_of_rate(&to);
+	if (freq > 13000000)
+		WARN(1, "Requested unsupported timer frequency %u\n", freq);
+
+	/* Clock input is 26MHz, set DIV2 to achieve 13MHz clock */
+	val = mtk_cpux_readl(CPUX_IDX_GLOBAL_CTRL, &to);
+	val &= ~CPUX_CLK_DIV_MASK;
+	val |= CPUX_CLK_DIV2;
+	mtk_cpux_writel(val, CPUX_IDX_GLOBAL_CTRL, &to);
+
+	/* Enable all CPUXGPT timers */
+	val = mtk_cpux_readl(CPUX_IDX_GLOBAL_CTRL, &to);
+	mtk_cpux_writel(val | CPUX_ENABLE, CPUX_IDX_GLOBAL_CTRL, &to);
+
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	return 0;
+}
+TIMER_OF_DECLARE(mtk_mt6795, "mediatek,mt6795-systimer", mtk_cpux_init);