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, 244 insertions, 0 deletions

diff --git a/drivers/thermal/thermal_thresholds.c b/drivers/thermal/thermal_thresholds.c
new file mode 100644
index 000000000..970b8fd33
--- /dev/null
+++ b/drivers/thermal/thermal_thresholds.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2024 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * Thermal thresholds
+ */
+#include <linux/list.h>
+#include <linux/list_sort.h>
+#include <linux/slab.h>
+
+#include "thermal_core.h"
+#include "thermal_thresholds.h"
+
+int thermal_thresholds_init(struct thermal_zone_device *tz)
+{
+	INIT_LIST_HEAD(&tz->user_thresholds);
+
+	return 0;
+}
+
+static void __thermal_thresholds_flush(struct thermal_zone_device *tz)
+{
+	struct list_head *thresholds = &tz->user_thresholds;
+	struct user_threshold *entry, *tmp;
+
+	list_for_each_entry_safe(entry, tmp, thresholds, list_node) {
+		list_del(&entry->list_node);
+		kfree(entry);
+	}
+}
+
+void thermal_thresholds_flush(struct thermal_zone_device *tz)
+{
+	lockdep_assert_held(&tz->lock);
+
+	__thermal_thresholds_flush(tz);
+
+	thermal_notify_threshold_flush(tz);
+
+	__thermal_zone_device_update(tz, THERMAL_TZ_FLUSH_THRESHOLDS);
+}
+
+void thermal_thresholds_exit(struct thermal_zone_device *tz)
+{
+	__thermal_thresholds_flush(tz);
+}
+
+static int __thermal_thresholds_cmp(void *data,
+				    const struct list_head *l1,
+				    const struct list_head *l2)
+{
+	struct user_threshold *t1 = container_of(l1, struct user_threshold, list_node);
+	struct user_threshold *t2 = container_of(l2, struct user_threshold, list_node);
+
+	return t1->temperature - t2->temperature;
+}
+
+static struct user_threshold *__thermal_thresholds_find(const struct list_head *thresholds,
+							int temperature)
+{
+	struct user_threshold *t;
+
+	list_for_each_entry(t, thresholds, list_node)
+		if (t->temperature == temperature)
+			return t;
+
+	return NULL;
+}
+
+static bool thermal_thresholds_handle_raising(struct list_head *thresholds, int temperature,
+					      int last_temperature)
+{
+	struct user_threshold *t;
+
+	list_for_each_entry(t, thresholds, list_node) {
+
+		if (!(t->direction & THERMAL_THRESHOLD_WAY_UP))
+		    continue;
+
+		if (temperature >= t->temperature &&
+		    last_temperature < t->temperature)
+			return true;
+	}
+
+	return false;
+}
+
+static bool thermal_thresholds_handle_dropping(struct list_head *thresholds, int temperature,
+					       int last_temperature)
+{
+	struct user_threshold *t;
+
+	list_for_each_entry_reverse(t, thresholds, list_node) {
+
+		if (!(t->direction & THERMAL_THRESHOLD_WAY_DOWN))
+		    continue;
+
+		if (temperature <= t->temperature &&
+		    last_temperature > t->temperature)
+			return true;
+	}
+
+	return false;
+}
+
+static void thermal_threshold_find_boundaries(struct list_head *thresholds, int temperature,
+					      int *low, int *high)
+{
+	struct user_threshold *t;
+
+	list_for_each_entry(t, thresholds, list_node) {
+		if (temperature < t->temperature &&
+		    (t->direction & THERMAL_THRESHOLD_WAY_UP) &&
+		    *high > t->temperature)
+			*high = t->temperature;
+	}
+
+	list_for_each_entry_reverse(t, thresholds, list_node) {
+		if (temperature > t->temperature &&
+		    (t->direction & THERMAL_THRESHOLD_WAY_DOWN) &&
+		    *low < t->temperature)
+			*low = t->temperature;
+	}
+}
+
+void thermal_thresholds_handle(struct thermal_zone_device *tz, int *low, int *high)
+{
+	struct list_head *thresholds = &tz->user_thresholds;
+
+	int temperature = tz->temperature;
+	int last_temperature = tz->last_temperature;
+
+	lockdep_assert_held(&tz->lock);
+
+	thermal_threshold_find_boundaries(thresholds, temperature, low, high);
+
+	/*
+	 * We need a second update in order to detect a threshold being crossed
+	 */
+	if (last_temperature == THERMAL_TEMP_INVALID)
+		return;
+
+	/*
+	 * The temperature is stable, so obviously we can not have
+	 * crossed a threshold.
+	 */
+	if (last_temperature == temperature)
+		return;
+
+	/*
+	 * Since last update the temperature:
+	 * - increased : thresholds are crossed the way up
+	 * - decreased : thresholds are crossed the way down
+	 */
+	if (temperature > last_temperature) {
+		if (thermal_thresholds_handle_raising(thresholds,
+						      temperature, last_temperature))
+			thermal_notify_threshold_up(tz);
+	} else {
+		if (thermal_thresholds_handle_dropping(thresholds,
+						       temperature, last_temperature))
+			thermal_notify_threshold_down(tz);
+	}
+}
+
+int thermal_thresholds_add(struct thermal_zone_device *tz,
+			   int temperature, int direction)
+{
+	struct list_head *thresholds = &tz->user_thresholds;
+	struct user_threshold *t;
+
+	lockdep_assert_held(&tz->lock);
+
+	t = __thermal_thresholds_find(thresholds, temperature);
+	if (t) {
+		if (t->direction == direction)
+			return -EEXIST;
+
+		t->direction |= direction;
+	} else {
+
+		t = kmalloc_obj(*t);
+		if (!t)
+			return -ENOMEM;
+
+		INIT_LIST_HEAD(&t->list_node);
+		t->temperature = temperature;
+		t->direction = direction;
+		list_add(&t->list_node, thresholds);
+		list_sort(NULL, thresholds, __thermal_thresholds_cmp);
+	}
+
+	thermal_notify_threshold_add(tz, temperature, direction);
+
+	__thermal_zone_device_update(tz, THERMAL_TZ_ADD_THRESHOLD);
+
+	return 0;
+}
+
+int thermal_thresholds_delete(struct thermal_zone_device *tz,
+			      int temperature, int direction)
+{
+	struct list_head *thresholds = &tz->user_thresholds;
+	struct user_threshold *t;
+
+	lockdep_assert_held(&tz->lock);
+
+	t = __thermal_thresholds_find(thresholds, temperature);
+	if (!t)
+		return -ENOENT;
+
+	if (t->direction == direction) {
+		list_del(&t->list_node);
+		kfree(t);
+	} else {
+		t->direction &= ~direction;
+	}
+
+	thermal_notify_threshold_delete(tz, temperature, direction);
+
+	__thermal_zone_device_update(tz, THERMAL_TZ_DEL_THRESHOLD);
+
+	return 0;
+}
+
+int thermal_thresholds_for_each(struct thermal_zone_device *tz,
+				int (*cb)(struct user_threshold *, void *arg), void *arg)
+{
+	struct list_head *thresholds = &tz->user_thresholds;
+	struct user_threshold *entry;
+	int ret;
+
+	guard(thermal_zone)(tz);
+
+	list_for_each_entry(entry, thresholds, list_node) {
+		ret = cb(entry, arg);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}