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, 293 insertions, 0 deletions

diff --git a/drivers/pinctrl/pinctrl-generic.c b/drivers/pinctrl/pinctrl-generic.c
new file mode 100644
index 000000000..fd6bdb740
--- /dev/null
+++ b/drivers/pinctrl/pinctrl-generic.c
@@ -0,0 +1,293 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#define pr_fmt(fmt) "generic pinconfig core: " fmt
+
+#include <linux/array_size.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+
+#include <linux/pinctrl/pinconf-generic.h>
+#include <linux/pinctrl/pinconf.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "core.h"
+#include "pinconf.h"
+#include "pinctrl-utils.h"
+#include "pinmux.h"
+
+int pinctrl_generic_to_map(struct pinctrl_dev *pctldev, struct device_node *parent,
+			   struct device_node *np, struct pinctrl_map **maps,
+			   unsigned int *num_maps, unsigned int *num_reserved_maps,
+			   const char **group_names, unsigned int ngroups,
+			   void *data, unsigned int *pins, unsigned int npins)
+{
+	struct device *dev = pctldev->dev;
+	unsigned int num_configs;
+	const char *group_name;
+	unsigned long *configs;
+	int ret, reserve = 1;
+
+	group_name = devm_kasprintf(dev, GFP_KERNEL, "%pOFn.%pOFn", parent, np);
+	if (!group_name)
+		return -ENOMEM;
+
+	group_names[ngroups] = group_name;
+
+	ret = pinctrl_utils_reserve_map(pctldev, maps, num_reserved_maps, num_maps, reserve);
+	if (ret)
+		return ret;
+
+	ret = pinctrl_utils_add_map_mux(pctldev, maps, num_reserved_maps, num_maps, group_name,
+					parent->name);
+	if (ret < 0)
+		goto err_free_map;
+
+	ret = pinctrl_generic_add_group(pctldev, group_name, pins, npins, data);
+	if (ret < 0) {
+		dev_err_probe(dev, ret, "failed to add group %s: %d\n",
+				     group_name, ret);
+		goto err_free_map;
+	}
+
+	ret = pinconf_generic_parse_dt_config(np, pctldev, &configs, &num_configs);
+	if (ret) {
+		dev_err_probe(dev, ret, "failed to parse pin config of group %s\n",
+			group_name);
+		goto err_free_map;
+	}
+
+	if (num_configs == 0)
+		return 0;
+
+	ret = pinctrl_utils_reserve_map(pctldev, maps, num_reserved_maps, num_maps, reserve);
+	if (ret)
+		goto err_free_map;
+
+	ret = pinctrl_utils_add_map_configs(pctldev, maps, num_reserved_maps, num_maps, group_name,
+					    configs,
+			num_configs, PIN_MAP_TYPE_CONFIGS_GROUP);
+	kfree(configs);
+	if (ret)
+		goto err_free_map;
+
+	return 0;
+
+err_free_map:
+	pinctrl_utils_free_map(pctldev, *maps, *num_maps);
+	*maps = NULL;
+	*num_maps = 0;
+	*num_reserved_maps = 0;
+	return ret;
+};
+EXPORT_SYMBOL_GPL(pinctrl_generic_to_map);
+
+static int pinctrl_generic_pins_function_dt_subnode_to_map(struct pinctrl_dev *pctldev,
+							   struct device_node *parent,
+							   struct device_node *np,
+							   struct pinctrl_map **maps,
+							   unsigned int *num_maps,
+							   unsigned int *num_reserved_maps,
+							   const char **group_names,
+							   unsigned int ngroups)
+{
+	struct device *dev = pctldev->dev;
+	unsigned int pin, *pins;
+	const char **functions;
+	int npins, ret;
+
+	npins = of_property_count_u32_elems(np, "pins");
+
+	if (npins < 1) {
+		dev_err(dev, "invalid pinctrl group %pOFn.%pOFn %d\n",
+			parent, np, npins);
+		return npins;
+	}
+
+	pins = devm_kcalloc(dev, npins, sizeof(*pins), GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+
+	functions = devm_kcalloc(dev, npins, sizeof(*functions), GFP_KERNEL);
+	if (!functions)
+		return -ENOMEM;
+
+	for (int i = 0; i < npins; i++) {
+		ret = of_property_read_u32_index(np, "pins", i, &pin);
+		if (ret)
+			return ret;
+
+		pins[i] = pin;
+
+		ret = of_property_read_string(np, "function", &functions[i]);
+		if (ret)
+			return ret;
+	}
+
+	return pinctrl_generic_to_map(pctldev, parent, np, maps, num_maps,
+				      num_reserved_maps, group_names, ngroups,
+				      functions, pins, npins);
+}
+
+static int pinctrl_generic_pinmux_dt_subnode_to_map(struct pinctrl_dev *pctldev,
+						    struct device_node *parent,
+						    struct device_node *np,
+						    struct pinctrl_map **maps,
+						    unsigned int *num_maps,
+						    unsigned int *num_reserved_maps,
+						    const char **group_names,
+						    unsigned int ngroups)
+{
+	struct device *dev = pctldev->dev;
+	unsigned int *pins, *muxes;
+	int npins, ret;
+
+	npins = of_property_count_u32_elems(np, "pinmux");
+
+	if (npins < 1) {
+		dev_err(dev, "invalid pinctrl group %pOFn.%pOFn %d\n",
+			parent, np, npins);
+		return npins;
+	}
+
+	pins = devm_kcalloc(dev, npins, sizeof(*pins), GFP_KERNEL);
+	if (!pins)
+		return -ENOMEM;
+
+	muxes = devm_kcalloc(dev, npins, sizeof(*muxes), GFP_KERNEL);
+	if (!muxes)
+		return -ENOMEM;
+
+	for (int i = 0; i < npins; i++) {
+		unsigned int pinmux;
+
+		ret = of_property_read_u32_index(np, "pinmux", i, &pinmux);
+		if (ret)
+			return ret;
+
+		pins[i] = pinmux >> 16;
+		muxes[i] = pinmux & GENMASK(15, 0);
+	}
+
+	return pinctrl_generic_to_map(pctldev, parent, np, maps, num_maps,
+				      num_reserved_maps, group_names, ngroups,
+				      muxes, pins, npins);
+}
+
+static int pinctrl_generic_dt_node_to_map(struct pinctrl_dev *pctldev,
+					  struct device_node *np,
+					  struct pinctrl_map **maps,
+					  unsigned int *num_maps,
+					  int (dt_subnode_to_map)(
+						  struct pinctrl_dev *,
+						  struct device_node *,
+						  struct device_node *,
+						  struct pinctrl_map **,
+						  unsigned int *,
+						  unsigned int *,
+						  const char **,
+						  unsigned int))
+{
+	struct device *dev = pctldev->dev;
+	struct device_node *child_np;
+	const char **group_names;
+	unsigned int num_reserved_maps = 0;
+	int ngroups = 0;
+	int ret;
+
+	*maps = NULL;
+	*num_maps = 0;
+
+	/*
+	 * Check if this is actually the pins node, or a parent containing
+	 * multiple pins nodes.
+	 */
+	if (!of_property_present(np, "pins"))
+		goto parent;
+
+	group_names = devm_kcalloc(dev, 1, sizeof(*group_names), GFP_KERNEL);
+	if (!group_names)
+		return -ENOMEM;
+
+	ret = dt_subnode_to_map(pctldev, np, np, maps, num_maps,
+				&num_reserved_maps, group_names, ngroups);
+	if (ret) {
+		pinctrl_utils_free_map(pctldev, *maps, *num_maps);
+		return dev_err_probe(dev, ret, "error figuring out mappings for %s\n", np->name);
+	}
+
+	ret = pinmux_generic_add_function(pctldev, np->name, group_names, 1, NULL);
+	if (ret < 0) {
+		pinctrl_utils_free_map(pctldev, *maps, *num_maps);
+		return dev_err_probe(dev, ret, "error adding function %s\n", np->name);
+	}
+
+	return 0;
+
+parent:
+	for_each_available_child_of_node(np, child_np)
+		ngroups += 1;
+
+	group_names = devm_kcalloc(dev, ngroups, sizeof(*group_names), GFP_KERNEL);
+	if (!group_names)
+		return -ENOMEM;
+
+	ngroups = 0;
+	for_each_available_child_of_node_scoped(np, child_np) {
+		ret = dt_subnode_to_map(pctldev, np, child_np, maps, num_maps,
+					&num_reserved_maps, group_names, ngroups);
+		if (ret) {
+			pinctrl_utils_free_map(pctldev, *maps, *num_maps);
+			return dev_err_probe(dev, ret, "error figuring out mappings for %s\n",
+					     np->name);
+		}
+
+		ngroups++;
+	}
+
+	ret = pinmux_generic_add_function(pctldev, np->name, group_names, ngroups, NULL);
+	if (ret < 0) {
+		pinctrl_utils_free_map(pctldev, *maps, *num_maps);
+		return dev_err_probe(dev, ret, "error adding function %s\n", np->name);
+	}
+
+	return 0;
+}
+
+/*
+ * For platforms that do not define groups or functions in the driver, but
+ * instead use the devicetree to describe them. This function will, unlike
+ * pinconf_generic_dt_node_to_map() etc which rely on driver defined groups
+ * and functions, create them in addition to parsing pinconf properties and
+ * adding mappings.
+ */
+int pinctrl_generic_pins_function_dt_node_to_map(struct pinctrl_dev *pctldev,
+						 struct device_node *np,
+						 struct pinctrl_map **maps,
+						 unsigned int *num_maps)
+{
+	return pinctrl_generic_dt_node_to_map(pctldev, np, maps, num_maps,
+					      &pinctrl_generic_pins_function_dt_subnode_to_map);
+}
+EXPORT_SYMBOL_GPL(pinctrl_generic_pins_function_dt_node_to_map);
+
+/*
+ * For platforms that do not define groups or functions in the driver, but
+ * instead use the devicetree to describe them. This function will, unlike
+ * pinconf_generic_dt_node_to_map() etc which rely on driver defined groups
+ * and functions, create them in addition to parsing pinconf properties and
+ * adding mappings.
+ *
+ * It assumes that the upper 16 bits of the pinmux items contain the pin
+ * and the lower 16 the mux setting.
+ */
+int pinctrl_generic_pinmux_dt_node_to_map(struct pinctrl_dev *pctldev,
+					  struct device_node *np,
+					  struct pinctrl_map **maps,
+					  unsigned int *num_maps)
+{
+	return pinctrl_generic_dt_node_to_map(pctldev, np, maps, num_maps,
+					      &pinctrl_generic_pinmux_dt_subnode_to_map);
+};
+EXPORT_SYMBOL_GPL(pinctrl_generic_pinmux_dt_node_to_map);