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, 72 insertions, 0 deletions

diff --git a/drivers/dma-buf/sync_debug.h b/drivers/dma-buf/sync_debug.h
new file mode 100644
index 000000000..c49324505
--- /dev/null
+++ b/drivers/dma-buf/sync_debug.h
@@ -0,0 +1,72 @@
+/*
+ * Sync File validation framework and debug infomation
+ *
+ * Copyright (C) 2012 Google, Inc.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _LINUX_SYNC_H
+#define _LINUX_SYNC_H
+
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/spinlock.h>
+#include <linux/dma-fence.h>
+
+#include <linux/sync_file.h>
+#include <uapi/linux/sync_file.h>
+
+/**
+ * struct sync_timeline - sync object
+ * @kref:		reference count on fence.
+ * @name:		name of the sync_timeline. Useful for debugging
+ * @lock:		lock protecting @pt_list and @value
+ * @pt_tree:		rbtree of active (unsignaled/errored) sync_pts
+ * @pt_list:		list of active (unsignaled/errored) sync_pts
+ * @sync_timeline_list:	membership in global sync_timeline_list
+ */
+struct sync_timeline {
+	struct kref		kref;
+	char			name[32];
+
+	/* protected by lock */
+	u64			context;
+	int			value;
+
+	struct rb_root		pt_tree;
+	struct list_head	pt_list;
+	spinlock_t		lock;
+
+	struct list_head	sync_timeline_list;
+};
+
+static inline struct sync_timeline *dma_fence_parent(struct dma_fence *fence)
+{
+	return container_of(fence->extern_lock, struct sync_timeline, lock);
+}
+
+/**
+ * struct sync_pt - sync_pt object
+ * @base: base fence object
+ * @link: link on the sync timeline's list
+ * @node: node in the sync timeline's tree
+ * @deadline: the earliest fence deadline hint
+ */
+struct sync_pt {
+	struct dma_fence base;
+	struct list_head link;
+	struct rb_node node;
+	ktime_t deadline;
+};
+
+extern const struct file_operations sw_sync_debugfs_fops;
+
+void sync_timeline_debug_add(struct sync_timeline *obj);
+void sync_timeline_debug_remove(struct sync_timeline *obj);
+
+#endif /* _LINUX_SYNC_H */