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, 153 insertions, 0 deletions

diff --git a/include/drm/drm_managed.h b/include/drm/drm_managed.h
new file mode 100644
index 000000000..72d0d68be
--- /dev/null
+++ b/include/drm/drm_managed.h
@@ -0,0 +1,153 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#ifndef _DRM_MANAGED_H_
+#define _DRM_MANAGED_H_
+
+#include <linux/gfp.h>
+#include <linux/overflow.h>
+#include <linux/types.h>
+
+struct drm_device;
+struct mutex;
+
+typedef void (*drmres_release_t)(struct drm_device *dev, void *res);
+
+/**
+ * drmm_add_action - add a managed release action to a &drm_device
+ * @dev: DRM device
+ * @action: function which should be called when @dev is released
+ * @data: opaque pointer, passed to @action
+ *
+ * This function adds the release @action with optional parameter @data to the
+ * list of cleanup actions for @dev. The cleanup actions will be run in reverse
+ * order in the final drm_dev_put() call for @dev.
+ */
+#define drmm_add_action(dev, action, data) \
+	__drmm_add_action(dev, action, data, #action)
+
+int __must_check __drmm_add_action(struct drm_device *dev,
+				   drmres_release_t action,
+				   void *data, const char *name);
+
+/**
+ * drmm_add_action_or_reset - add a managed release action to a &drm_device
+ * @dev: DRM device
+ * @action: function which should be called when @dev is released
+ * @data: opaque pointer, passed to @action
+ *
+ * Similar to drmm_add_action(), with the only difference that upon failure
+ * @action is directly called for any cleanup work necessary on failures.
+ */
+#define drmm_add_action_or_reset(dev, action, data) \
+	__drmm_add_action_or_reset(dev, action, data, #action)
+
+int __must_check __drmm_add_action_or_reset(struct drm_device *dev,
+					    drmres_release_t action,
+					    void *data, const char *name);
+
+void drmm_release_action(struct drm_device *dev,
+			 drmres_release_t action,
+			 void *data);
+
+void *drmm_kmalloc(struct drm_device *dev, size_t size, gfp_t gfp) __malloc;
+
+/**
+ * drmm_kzalloc - &drm_device managed kzalloc()
+ * @dev: DRM device
+ * @size: size of the memory allocation
+ * @gfp: GFP allocation flags
+ *
+ * This is a &drm_device managed version of kzalloc(). The allocated memory is
+ * automatically freed on the final drm_dev_put(). Memory can also be freed
+ * before the final drm_dev_put() by calling drmm_kfree().
+ */
+static inline void *drmm_kzalloc(struct drm_device *dev, size_t size, gfp_t gfp)
+{
+	return drmm_kmalloc(dev, size, gfp | __GFP_ZERO);
+}
+
+/**
+ * drmm_kmalloc_array - &drm_device managed kmalloc_array()
+ * @dev: DRM device
+ * @n: number of array elements to allocate
+ * @size: size of array member
+ * @flags: GFP allocation flags
+ *
+ * This is a &drm_device managed version of kmalloc_array(). The allocated
+ * memory is automatically freed on the final drm_dev_put() and works exactly
+ * like a memory allocation obtained by drmm_kmalloc().
+ */
+static inline void *drmm_kmalloc_array(struct drm_device *dev,
+				       size_t n, size_t size, gfp_t flags)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
+		return NULL;
+
+	return drmm_kmalloc(dev, bytes, flags);
+}
+
+/**
+ * drmm_kcalloc - &drm_device managed kcalloc()
+ * @dev: DRM device
+ * @n: number of array elements to allocate
+ * @size: size of array member
+ * @flags: GFP allocation flags
+ *
+ * This is a &drm_device managed version of kcalloc(). The allocated memory is
+ * automatically freed on the final drm_dev_put() and works exactly like a
+ * memory allocation obtained by drmm_kmalloc().
+ */
+static inline void *drmm_kcalloc(struct drm_device *dev,
+				 size_t n, size_t size, gfp_t flags)
+{
+	return drmm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
+}
+
+char *drmm_kstrdup(struct drm_device *dev, const char *s, gfp_t gfp);
+
+void drmm_kfree(struct drm_device *dev, void *data);
+
+void __drmm_mutex_release(struct drm_device *dev, void *res);
+
+/**
+ * drmm_mutex_init - &drm_device-managed mutex_init()
+ * @dev: DRM device
+ * @lock: lock to be initialized
+ *
+ * Returns:
+ * 0 on success, or a negative errno code otherwise.
+ *
+ * This is a &drm_device-managed version of mutex_init(). The initialized
+ * lock is automatically destroyed on the final drm_dev_put().
+ */
+#define drmm_mutex_init(dev, lock) ({					     \
+	mutex_init(lock);						     \
+	drmm_add_action_or_reset(dev, __drmm_mutex_release, lock);	     \
+})									     \
+
+void __drmm_workqueue_release(struct drm_device *device, void *wq);
+
+/**
+ * drmm_alloc_ordered_workqueue - &drm_device managed alloc_ordered_workqueue()
+ * @dev: DRM device
+ * @fmt: printf format for the name of the workqueue
+ * @flags: WQ_* flags (only WQ_FREEZABLE and WQ_MEM_RECLAIM are meaningful)
+ * @args: args for @fmt
+ *
+ * This is a &drm_device-managed version of alloc_ordered_workqueue(). The
+ * allocated workqueue is automatically destroyed on the final drm_dev_put().
+ *
+ * Returns: workqueue on success, negative ERR_PTR otherwise.
+ */
+#define drmm_alloc_ordered_workqueue(dev, fmt, flags, args...)					\
+	({											\
+		struct workqueue_struct *wq = alloc_ordered_workqueue(fmt, flags, ##args);	\
+		wq ? ({										\
+			int ret = drmm_add_action_or_reset(dev, __drmm_workqueue_release, wq);	\
+			ret ? ERR_PTR(ret) : wq;						\
+		}) : ERR_PTR(-ENOMEM);								\
+	})
+
+#endif