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, 252 insertions, 0 deletions

diff --git a/drivers/soc/rockchip/grf.c b/drivers/soc/rockchip/grf.c
new file mode 100644
index 000000000..b459607c1
--- /dev/null
+++ b/drivers/soc/rockchip/grf.c
@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Rockchip Generic Register Files setup
+ *
+ * Copyright (c) 2016 Heiko Stuebner <heiko@sntech.de>
+ */
+
+#include <linux/err.h>
+#include <linux/hw_bitfield.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+
+struct rockchip_grf_value {
+	const char *desc;
+	u32 reg;
+	u32 val;
+};
+
+struct rockchip_grf_info {
+	const struct rockchip_grf_value *values;
+	int num_values;
+};
+
+#define RK3036_GRF_SOC_CON0		0x140
+
+static const struct rockchip_grf_value rk3036_defaults[] __initconst = {
+	/*
+	 * Disable auto jtag/sdmmc switching that causes issues with the
+	 * clock-framework and the mmc controllers making them unreliable.
+	 */
+	{ "jtag switching", RK3036_GRF_SOC_CON0, FIELD_PREP_WM16_CONST(BIT(11), 0) },
+};
+
+static const struct rockchip_grf_info rk3036_grf __initconst = {
+	.values = rk3036_defaults,
+	.num_values = ARRAY_SIZE(rk3036_defaults),
+};
+
+#define RK3128_GRF_SOC_CON0		0x140
+#define RK3128_GRF_SOC_CON1		0x144
+
+static const struct rockchip_grf_value rk3128_defaults[] __initconst = {
+	{ "jtag switching", RK3128_GRF_SOC_CON0, FIELD_PREP_WM16_CONST(BIT(8), 0) },
+	{ "vpu main clock", RK3128_GRF_SOC_CON1, FIELD_PREP_WM16_CONST(BIT(10), 0) },
+};
+
+static const struct rockchip_grf_info rk3128_grf __initconst = {
+	.values = rk3128_defaults,
+	.num_values = ARRAY_SIZE(rk3128_defaults),
+};
+
+#define RK3228_GRF_SOC_CON6		0x418
+
+static const struct rockchip_grf_value rk3228_defaults[] __initconst = {
+	{ "jtag switching", RK3228_GRF_SOC_CON6, FIELD_PREP_WM16_CONST(BIT(8), 0) },
+};
+
+static const struct rockchip_grf_info rk3228_grf __initconst = {
+	.values = rk3228_defaults,
+	.num_values = ARRAY_SIZE(rk3228_defaults),
+};
+
+#define RK3288_GRF_SOC_CON0		0x244
+#define RK3288_GRF_SOC_CON2		0x24c
+
+static const struct rockchip_grf_value rk3288_defaults[] __initconst = {
+	{ "jtag switching", RK3288_GRF_SOC_CON0, FIELD_PREP_WM16_CONST(BIT(12), 0) },
+	{ "pwm select", RK3288_GRF_SOC_CON2, FIELD_PREP_WM16_CONST(BIT(0), 1) },
+};
+
+static const struct rockchip_grf_info rk3288_grf __initconst = {
+	.values = rk3288_defaults,
+	.num_values = ARRAY_SIZE(rk3288_defaults),
+};
+
+#define RK3328_GRF_SOC_CON4		0x410
+
+static const struct rockchip_grf_value rk3328_defaults[] __initconst = {
+	{ "jtag switching", RK3328_GRF_SOC_CON4, FIELD_PREP_WM16_CONST(BIT(12), 0) },
+};
+
+static const struct rockchip_grf_info rk3328_grf __initconst = {
+	.values = rk3328_defaults,
+	.num_values = ARRAY_SIZE(rk3328_defaults),
+};
+
+#define RK3368_GRF_SOC_CON15		0x43c
+
+static const struct rockchip_grf_value rk3368_defaults[] __initconst = {
+	{ "jtag switching", RK3368_GRF_SOC_CON15, FIELD_PREP_WM16_CONST(BIT(13), 0) },
+	{ "pwm select", RK3368_GRF_SOC_CON15, FIELD_PREP_WM16_CONST(BIT(12), 1) },
+};
+
+static const struct rockchip_grf_info rk3368_grf __initconst = {
+	.values = rk3368_defaults,
+	.num_values = ARRAY_SIZE(rk3368_defaults),
+};
+
+#define RK3368_PMUGRF_SOC_CON0		0x100
+
+static const struct rockchip_grf_value rk3368_pmugrf_defaults[] __initconst = {
+	{ "pwm2 select", RK3368_PMUGRF_SOC_CON0, FIELD_PREP_WM16_CONST(BIT(7), 0) },
+};
+
+static const struct rockchip_grf_info rk3368_pmugrf __initconst = {
+	.values = rk3368_pmugrf_defaults,
+	.num_values = ARRAY_SIZE(rk3368_pmugrf_defaults),
+};
+
+#define RK3399_GRF_SOC_CON7		0xe21c
+
+static const struct rockchip_grf_value rk3399_defaults[] __initconst = {
+	{ "jtag switching", RK3399_GRF_SOC_CON7, FIELD_PREP_WM16_CONST(BIT(12), 0) },
+};
+
+static const struct rockchip_grf_info rk3399_grf __initconst = {
+	.values = rk3399_defaults,
+	.num_values = ARRAY_SIZE(rk3399_defaults),
+};
+
+#define RK3566_GRF_USB3OTG0_CON1	0x0104
+
+static const struct rockchip_grf_value rk3566_defaults[] __initconst = {
+	{ "usb3otg port switch", RK3566_GRF_USB3OTG0_CON1, FIELD_PREP_WM16_CONST(BIT(12), 0) },
+	{ "usb3otg clock switch", RK3566_GRF_USB3OTG0_CON1, FIELD_PREP_WM16_CONST(BIT(7), 1) },
+	{ "usb3otg disable usb3", RK3566_GRF_USB3OTG0_CON1, FIELD_PREP_WM16_CONST(BIT(0), 1) },
+};
+
+static const struct rockchip_grf_info rk3566_pipegrf __initconst = {
+	.values = rk3566_defaults,
+	.num_values = ARRAY_SIZE(rk3566_defaults),
+};
+
+#define RK3576_SYSGRF_SOC_CON1		0x0004
+
+static const struct rockchip_grf_value rk3576_defaults_sys_grf[] __initconst = {
+	{ "i3c0 weakpull", RK3576_SYSGRF_SOC_CON1, FIELD_PREP_WM16_CONST(GENMASK(7, 6), 3) },
+	{ "i3c1 weakpull", RK3576_SYSGRF_SOC_CON1, FIELD_PREP_WM16_CONST(GENMASK(9, 8), 3) },
+};
+
+static const struct rockchip_grf_info rk3576_sysgrf __initconst = {
+	.values = rk3576_defaults_sys_grf,
+	.num_values = ARRAY_SIZE(rk3576_defaults_sys_grf),
+};
+
+#define RK3576_IOCGRF_MISC_CON		0x40F0
+
+static const struct rockchip_grf_value rk3576_defaults_ioc_grf[] __initconst = {
+	{ "jtag switching", RK3576_IOCGRF_MISC_CON, FIELD_PREP_WM16_CONST(BIT(1), 0) },
+};
+
+static const struct rockchip_grf_info rk3576_iocgrf __initconst = {
+	.values = rk3576_defaults_ioc_grf,
+	.num_values = ARRAY_SIZE(rk3576_defaults_ioc_grf),
+};
+
+#define RK3588_GRF_SOC_CON6		0x0318
+
+static const struct rockchip_grf_value rk3588_defaults[] __initconst = {
+	{ "jtag switching", RK3588_GRF_SOC_CON6, FIELD_PREP_WM16_CONST(BIT(14), 0) },
+};
+
+static const struct rockchip_grf_info rk3588_sysgrf __initconst = {
+	.values = rk3588_defaults,
+	.num_values = ARRAY_SIZE(rk3588_defaults),
+};
+
+static const struct of_device_id rockchip_grf_dt_match[] __initconst = {
+	{
+		.compatible = "rockchip,rk3036-grf",
+		.data = (void *)&rk3036_grf,
+	}, {
+		.compatible = "rockchip,rk3128-grf",
+		.data = (void *)&rk3128_grf,
+	}, {
+		.compatible = "rockchip,rk3228-grf",
+		.data = (void *)&rk3228_grf,
+	}, {
+		.compatible = "rockchip,rk3288-grf",
+		.data = (void *)&rk3288_grf,
+	}, {
+		.compatible = "rockchip,rk3328-grf",
+		.data = (void *)&rk3328_grf,
+	}, {
+		.compatible = "rockchip,rk3368-grf",
+		.data = (void *)&rk3368_grf,
+	}, {
+		.compatible = "rockchip,rk3368-pmugrf",
+		.data = (void *)&rk3368_pmugrf,
+	}, {
+		.compatible = "rockchip,rk3399-grf",
+		.data = (void *)&rk3399_grf,
+	}, {
+		.compatible = "rockchip,rk3566-pipe-grf",
+		.data = (void *)&rk3566_pipegrf,
+	}, {
+		.compatible = "rockchip,rk3576-sys-grf",
+		.data = (void *)&rk3576_sysgrf,
+	}, {
+		.compatible = "rockchip,rk3576-ioc-grf",
+		.data = (void *)&rk3576_iocgrf,
+	}, {
+		.compatible = "rockchip,rk3588-sys-grf",
+		.data = (void *)&rk3588_sysgrf,
+	},
+	{ /* sentinel */ },
+};
+
+static int __init rockchip_grf_init(void)
+{
+	const struct rockchip_grf_info *grf_info;
+	const struct of_device_id *match;
+	struct device_node *np;
+	struct regmap *grf;
+	int ret, i;
+
+	for_each_matching_node_and_match(np, rockchip_grf_dt_match, &match) {
+		if (!of_device_is_available(np))
+			continue;
+		if (!match || !match->data) {
+			pr_err("%s: missing grf data\n", __func__);
+			of_node_put(np);
+			return -EINVAL;
+		}
+
+		grf_info = match->data;
+
+		grf = syscon_node_to_regmap(np);
+		if (IS_ERR(grf)) {
+			pr_err("%s: could not get grf syscon\n", __func__);
+			of_node_put(np);
+			return PTR_ERR(grf);
+		}
+
+		for (i = 0; i < grf_info->num_values; i++) {
+			const struct rockchip_grf_value *val = &grf_info->values[i];
+
+			pr_debug("%s: adjusting %s in %#6x to %#10x\n", __func__,
+				val->desc, val->reg, val->val);
+			ret = regmap_write(grf, val->reg, val->val);
+			if (ret < 0)
+				pr_err("%s: write to %#6x failed with %d\n",
+					__func__, val->reg, ret);
+		}
+	}
+
+	return 0;
+}
+postcore_initcall(rockchip_grf_init);