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, 122 insertions, 0 deletions

diff --git a/drivers/dma/dw/of.c b/drivers/dma/dw/of.c
new file mode 100644
index 000000000..523ca8068
--- /dev/null
+++ b/drivers/dma/dw/of.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Platform driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2007-2008 Atmel Corporation
+ * Copyright (C) 2010-2011 ST Microelectronics
+ * Copyright (C) 2013 Intel Corporation
+ */
+
+#include <linux/of.h>
+#include <linux/of_dma.h>
+#include <linux/platform_device.h>
+
+#include "internal.h"
+
+static struct dma_chan *dw_dma_of_xlate(struct of_phandle_args *dma_spec,
+					struct of_dma *ofdma)
+{
+	struct dw_dma *dw = ofdma->of_dma_data;
+	struct dw_dma_slave slave = {
+		.dma_dev = dw->dma.dev,
+	};
+	dma_cap_mask_t cap;
+
+	if (dma_spec->args_count < 3 || dma_spec->args_count > 4)
+		return NULL;
+
+	slave.src_id = dma_spec->args[0];
+	slave.dst_id = dma_spec->args[0];
+	slave.m_master = dma_spec->args[1];
+	slave.p_master = dma_spec->args[2];
+	if (dma_spec->args_count >= 4)
+		slave.channels = dma_spec->args[3];
+
+	if (WARN_ON(slave.src_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.dst_id >= DW_DMA_MAX_NR_REQUESTS ||
+		    slave.m_master >= dw->pdata->nr_masters ||
+		    slave.p_master >= dw->pdata->nr_masters ||
+		    slave.channels >= BIT(dw->pdata->nr_channels)))
+		return NULL;
+
+	dma_cap_zero(cap);
+	dma_cap_set(DMA_SLAVE, cap);
+
+	/* TODO: there should be a simpler way to do this */
+	return dma_request_channel(cap, dw_dma_filter, &slave);
+}
+
+struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct dw_dma_platform_data *pdata;
+	u32 tmp, arr[DW_DMA_MAX_NR_MASTERS];
+	u32 nr_masters;
+	u32 nr_channels;
+
+	if (of_property_read_u32(np, "dma-masters", &nr_masters))
+		return NULL;
+	if (nr_masters < 1 || nr_masters > DW_DMA_MAX_NR_MASTERS)
+		return NULL;
+
+	if (of_property_read_u32(np, "dma-channels", &nr_channels))
+		return NULL;
+	if (nr_channels > DW_DMA_MAX_NR_CHANNELS)
+		return NULL;
+
+	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	pdata->nr_masters = nr_masters;
+	pdata->nr_channels = nr_channels;
+
+	of_property_read_u32(np, "chan_allocation_order", &pdata->chan_allocation_order);
+	of_property_read_u32(np, "chan_priority", &pdata->chan_priority);
+
+	of_property_read_u32(np, "block_size", &pdata->block_size);
+
+	/* Try deprecated property first */
+	if (!of_property_read_u32_array(np, "data_width", arr, nr_masters)) {
+		for (tmp = 0; tmp < nr_masters; tmp++)
+			pdata->data_width[tmp] = BIT(arr[tmp] & 0x07);
+	}
+
+	/* If "data_width" and "data-width" both provided use the latter one */
+	of_property_read_u32_array(np, "data-width", pdata->data_width, nr_masters);
+
+	memset32(pdata->multi_block, 1, nr_channels);
+	of_property_read_u32_array(np, "multi-block", pdata->multi_block, nr_channels);
+
+	memset32(pdata->max_burst, DW_DMA_MAX_BURST, nr_channels);
+	of_property_read_u32_array(np, "snps,max-burst-len", pdata->max_burst, nr_channels);
+
+	of_property_read_u32(np, "snps,dma-protection-control", &pdata->protctl);
+	if (pdata->protctl > CHAN_PROTCTL_MASK)
+		return NULL;
+
+	return pdata;
+}
+
+void dw_dma_of_controller_register(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+	int ret;
+
+	if (!dev->of_node)
+		return;
+
+	ret = of_dma_controller_register(dev->of_node, dw_dma_of_xlate, dw);
+	if (ret)
+		dev_err(dev, "could not register of_dma_controller\n");
+}
+
+void dw_dma_of_controller_free(struct dw_dma *dw)
+{
+	struct device *dev = dw->dma.dev;
+
+	if (!dev->of_node)
+		return;
+
+	of_dma_controller_free(dev->of_node);
+}