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, 66 insertions, 0 deletions

diff --git a/io_uring/filetable.h b/io_uring/filetable.h
new file mode 100644
index 000000000..c348233a3
--- /dev/null
+++ b/io_uring/filetable.h
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_FILE_TABLE_H
+#define IOU_FILE_TABLE_H
+
+#include <linux/io_uring_types.h>
+#include "rsrc.h"
+
+bool io_alloc_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table, unsigned nr_files);
+void io_free_file_tables(struct io_ring_ctx *ctx, struct io_file_table *table);
+
+int io_fixed_fd_install(struct io_kiocb *req, unsigned int issue_flags,
+			struct file *file, unsigned int file_slot);
+int __io_fixed_fd_install(struct io_ring_ctx *ctx, struct file *file,
+				unsigned int file_slot);
+int io_fixed_fd_remove(struct io_ring_ctx *ctx, unsigned int offset);
+
+int io_register_file_alloc_range(struct io_ring_ctx *ctx,
+				 struct io_uring_file_index_range __user *arg);
+
+io_req_flags_t io_file_get_flags(struct file *file);
+
+static inline void io_file_bitmap_clear(struct io_file_table *table, int bit)
+{
+	WARN_ON_ONCE(!test_bit(bit, table->bitmap));
+	__clear_bit(bit, table->bitmap);
+	table->alloc_hint = bit;
+}
+
+static inline void io_file_bitmap_set(struct io_file_table *table, int bit)
+{
+	WARN_ON_ONCE(test_bit(bit, table->bitmap));
+	__set_bit(bit, table->bitmap);
+	table->alloc_hint = bit + 1;
+}
+
+#define FFS_NOWAIT		0x1UL
+#define FFS_ISREG		0x2UL
+#define FFS_MASK		~(FFS_NOWAIT|FFS_ISREG)
+
+static inline unsigned int io_slot_flags(struct io_rsrc_node *node)
+{
+
+	return (node->file_ptr & ~FFS_MASK) << REQ_F_SUPPORT_NOWAIT_BIT;
+}
+
+static inline struct file *io_slot_file(struct io_rsrc_node *node)
+{
+	return (struct file *)(node->file_ptr & FFS_MASK);
+}
+
+static inline void io_fixed_file_set(struct io_rsrc_node *node,
+				     struct file *file)
+{
+	node->file_ptr = (unsigned long)file |
+		(io_file_get_flags(file) >> REQ_F_SUPPORT_NOWAIT_BIT);
+}
+
+static inline void io_file_table_set_alloc_range(struct io_ring_ctx *ctx,
+						 unsigned off, unsigned len)
+{
+	ctx->file_alloc_start = off;
+	ctx->file_alloc_end = off + len;
+	ctx->file_table.alloc_hint = ctx->file_alloc_start;
+}
+
+#endif