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, 47 insertions, 0 deletions

diff --git a/drivers/crypto/qce/dma.h b/drivers/crypto/qce/dma.h
new file mode 100644
index 000000000..316291850
--- /dev/null
+++ b/drivers/crypto/qce/dma.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2011-2014, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DMA_H_
+#define _DMA_H_
+
+#include <linux/dmaengine.h>
+
+/* maximum data transfer block size between BAM and CE */
+#define QCE_BAM_BURST_SIZE		64
+
+#define QCE_AUTHIV_REGS_CNT		16
+#define QCE_AUTH_BYTECOUNT_REGS_CNT	4
+#define QCE_CNTRIV_REGS_CNT		4
+
+struct qce_result_dump {
+	u32 auth_iv[QCE_AUTHIV_REGS_CNT];
+	u32 auth_byte_count[QCE_AUTH_BYTECOUNT_REGS_CNT];
+	u32 encr_cntr_iv[QCE_CNTRIV_REGS_CNT];
+	u32 status;
+	u32 status2;
+};
+
+#define QCE_IGNORE_BUF_SZ	(2 * QCE_BAM_BURST_SIZE)
+#define QCE_RESULT_BUF_SZ	\
+		ALIGN(sizeof(struct qce_result_dump), QCE_BAM_BURST_SIZE)
+
+struct qce_dma_data {
+	struct dma_chan *txchan;
+	struct dma_chan *rxchan;
+	struct qce_result_dump *result_buf;
+	void *ignore_buf;
+};
+
+int devm_qce_dma_request(struct device *dev, struct qce_dma_data *dma);
+int qce_dma_prep_sgs(struct qce_dma_data *dma, struct scatterlist *sg_in,
+		     int in_ents, struct scatterlist *sg_out, int out_ents,
+		     dma_async_tx_callback cb, void *cb_param);
+void qce_dma_issue_pending(struct qce_dma_data *dma);
+int qce_dma_terminate_all(struct qce_dma_data *dma);
+struct scatterlist *
+qce_sgtable_add(struct sg_table *sgt, struct scatterlist *sg_add,
+		unsigned int max_len);
+
+#endif /* _DMA_H_ */