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, 135 insertions, 0 deletions

diff --git a/drivers/crypto/qce/dma.c b/drivers/crypto/qce/dma.c
new file mode 100644
index 000000000..68cafd474
--- /dev/null
+++ b/drivers/crypto/qce/dma.c
@@ -0,0 +1,135 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2012-2014, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <crypto/scatterwalk.h>
+
+#include "dma.h"
+
+static void qce_dma_release(void *data)
+{
+	struct qce_dma_data *dma = data;
+
+	dma_release_channel(dma->txchan);
+	dma_release_channel(dma->rxchan);
+	kfree(dma->result_buf);
+}
+
+int devm_qce_dma_request(struct device *dev, struct qce_dma_data *dma)
+{
+	int ret;
+
+	dma->txchan = dma_request_chan(dev, "tx");
+	if (IS_ERR(dma->txchan))
+		return dev_err_probe(dev, PTR_ERR(dma->txchan),
+				     "Failed to get TX DMA channel\n");
+
+	dma->rxchan = dma_request_chan(dev, "rx");
+	if (IS_ERR(dma->rxchan)) {
+		ret = dev_err_probe(dev, PTR_ERR(dma->rxchan),
+				    "Failed to get RX DMA channel\n");
+		goto error_rx;
+	}
+
+	dma->result_buf = kmalloc(QCE_RESULT_BUF_SZ + QCE_IGNORE_BUF_SZ,
+				  GFP_KERNEL);
+	if (!dma->result_buf) {
+		ret = -ENOMEM;
+		goto error_nomem;
+	}
+
+	dma->ignore_buf = dma->result_buf + QCE_RESULT_BUF_SZ;
+
+	return devm_add_action_or_reset(dev, qce_dma_release, dma);
+
+error_nomem:
+	dma_release_channel(dma->rxchan);
+error_rx:
+	dma_release_channel(dma->txchan);
+	return ret;
+}
+
+struct scatterlist *
+qce_sgtable_add(struct sg_table *sgt, struct scatterlist *new_sgl,
+		unsigned int max_len)
+{
+	struct scatterlist *sg = sgt->sgl, *sg_last = NULL;
+	unsigned int new_len;
+
+	while (sg) {
+		if (!sg_page(sg))
+			break;
+		sg = sg_next(sg);
+	}
+
+	if (!sg)
+		return ERR_PTR(-EINVAL);
+
+	while (new_sgl && sg && max_len) {
+		new_len = new_sgl->length > max_len ? max_len : new_sgl->length;
+		sg_set_page(sg, sg_page(new_sgl), new_len, new_sgl->offset);
+		sg_last = sg;
+		sg = sg_next(sg);
+		new_sgl = sg_next(new_sgl);
+		max_len -= new_len;
+	}
+
+	return sg_last;
+}
+
+static int qce_dma_prep_sg(struct dma_chan *chan, struct scatterlist *sg,
+			   int nents, unsigned long flags,
+			   enum dma_transfer_direction dir,
+			   dma_async_tx_callback cb, void *cb_param)
+{
+	struct dma_async_tx_descriptor *desc;
+	dma_cookie_t cookie;
+
+	if (!sg || !nents)
+		return -EINVAL;
+
+	desc = dmaengine_prep_slave_sg(chan, sg, nents, dir, flags);
+	if (!desc)
+		return -EINVAL;
+
+	desc->callback = cb;
+	desc->callback_param = cb_param;
+	cookie = dmaengine_submit(desc);
+
+	return dma_submit_error(cookie);
+}
+
+int qce_dma_prep_sgs(struct qce_dma_data *dma, struct scatterlist *rx_sg,
+		     int rx_nents, struct scatterlist *tx_sg, int tx_nents,
+		     dma_async_tx_callback cb, void *cb_param)
+{
+	struct dma_chan *rxchan = dma->rxchan;
+	struct dma_chan *txchan = dma->txchan;
+	unsigned long flags = DMA_PREP_INTERRUPT | DMA_CTRL_ACK;
+	int ret;
+
+	ret = qce_dma_prep_sg(rxchan, rx_sg, rx_nents, flags, DMA_MEM_TO_DEV,
+			     NULL, NULL);
+	if (ret)
+		return ret;
+
+	return qce_dma_prep_sg(txchan, tx_sg, tx_nents, flags, DMA_DEV_TO_MEM,
+			       cb, cb_param);
+}
+
+void qce_dma_issue_pending(struct qce_dma_data *dma)
+{
+	dma_async_issue_pending(dma->rxchan);
+	dma_async_issue_pending(dma->txchan);
+}
+
+int qce_dma_terminate_all(struct qce_dma_data *dma)
+{
+	int ret;
+
+	ret = dmaengine_terminate_all(dma->rxchan);
+	return ret ?: dmaengine_terminate_all(dma->txchan);
+}