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, 145 insertions, 0 deletions

diff --git a/drivers/dma/dw/dw.c b/drivers/dma/dw/dw.c
new file mode 100644
index 000000000..676614288
--- /dev/null
+++ b/drivers/dma/dw/dw.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2007-2008 Atmel Corporation
+// Copyright (C) 2010-2011 ST Microelectronics
+// Copyright (C) 2013,2018 Intel Corporation
+
+#include <linux/bitops.h>
+#include <linux/dmaengine.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include "internal.h"
+
+static void dw_dma_initialize_chan(struct dw_dma_chan *dwc)
+{
+	struct dw_dma *dw = to_dw_dma(dwc->chan.device);
+	u32 cfghi = is_slave_direction(dwc->direction) ? 0 : DWC_CFGH_FIFO_MODE;
+	u32 cfglo = DWC_CFGL_CH_PRIOR(dwc->priority);
+	bool hs_polarity = dwc->dws.hs_polarity;
+
+	cfghi |= DWC_CFGH_DST_PER(dwc->dws.dst_id);
+	cfghi |= DWC_CFGH_SRC_PER(dwc->dws.src_id);
+	cfghi |= DWC_CFGH_PROTCTL(dw->pdata->protctl);
+
+	/* Set polarity of handshake interface */
+	cfglo |= hs_polarity ? DWC_CFGL_HS_DST_POL | DWC_CFGL_HS_SRC_POL : 0;
+
+	channel_writel(dwc, CFG_LO, cfglo);
+	channel_writel(dwc, CFG_HI, cfghi);
+}
+
+static void dw_dma_suspend_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo | DWC_CFGL_CH_SUSP);
+}
+
+static void dw_dma_resume_chan(struct dw_dma_chan *dwc, bool drain)
+{
+	u32 cfglo = channel_readl(dwc, CFG_LO);
+
+	channel_writel(dwc, CFG_LO, cfglo & ~DWC_CFGL_CH_SUSP);
+}
+
+static u32 dw_dma_bytes2block(struct dw_dma_chan *dwc,
+			      size_t bytes, unsigned int width, size_t *len)
+{
+	u32 block;
+
+	if ((bytes >> width) > dwc->block_size) {
+		block = dwc->block_size;
+		*len = dwc->block_size << width;
+	} else {
+		block = bytes >> width;
+		*len = bytes;
+	}
+
+	return block;
+}
+
+static size_t dw_dma_block2bytes(struct dw_dma_chan *dwc, u32 block, u32 width)
+{
+	return DWC_CTLH_BLOCK_TS(block) << width;
+}
+
+static inline u8 dw_dma_encode_maxburst(u32 maxburst)
+{
+	/*
+	 * Fix burst size according to dw_dmac. We need to convert them as:
+	 * 1 -> 0, 4 -> 1, 8 -> 2, 16 -> 3.
+	 */
+	return maxburst > 1 ? fls(maxburst) - 2 : 0;
+}
+
+static u32 dw_dma_prepare_ctllo(struct dw_dma_chan *dwc)
+{
+	struct dma_slave_config	*sconfig = &dwc->dma_sconfig;
+	u8 smsize = 0, dmsize = 0;
+	u8 sms, dms;
+
+	if (dwc->direction == DMA_MEM_TO_DEV) {
+		sms = dwc->dws.m_master;
+		dms = dwc->dws.p_master;
+		dmsize = dw_dma_encode_maxburst(sconfig->dst_maxburst);
+	} else if (dwc->direction == DMA_DEV_TO_MEM) {
+		sms = dwc->dws.p_master;
+		dms = dwc->dws.m_master;
+		smsize = dw_dma_encode_maxburst(sconfig->src_maxburst);
+	} else /* DMA_MEM_TO_MEM */ {
+		sms = dwc->dws.m_master;
+		dms = dwc->dws.m_master;
+	}
+
+	return DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN |
+	       DWC_CTLL_DST_MSIZE(dmsize) | DWC_CTLL_SRC_MSIZE(smsize) |
+	       DWC_CTLL_DMS(dms) | DWC_CTLL_SMS(sms);
+}
+
+static void dw_dma_set_device_name(struct dw_dma *dw, int id)
+{
+	snprintf(dw->name, sizeof(dw->name), "dw:dmac%d", id);
+}
+
+static void dw_dma_disable(struct dw_dma *dw)
+{
+	do_dw_dma_off(dw);
+}
+
+static void dw_dma_enable(struct dw_dma *dw)
+{
+	do_dw_dma_on(dw);
+}
+
+int dw_dma_probe(struct dw_dma_chip *chip)
+{
+	struct dw_dma *dw;
+
+	dw = devm_kzalloc(chip->dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	/* Channel operations */
+	dw->initialize_chan = dw_dma_initialize_chan;
+	dw->suspend_chan = dw_dma_suspend_chan;
+	dw->resume_chan = dw_dma_resume_chan;
+	dw->prepare_ctllo = dw_dma_prepare_ctllo;
+	dw->bytes2block = dw_dma_bytes2block;
+	dw->block2bytes = dw_dma_block2bytes;
+
+	/* Device operations */
+	dw->set_device_name = dw_dma_set_device_name;
+	dw->disable = dw_dma_disable;
+	dw->enable = dw_dma_enable;
+
+	chip->dw = dw;
+	return do_dma_probe(chip);
+}
+EXPORT_SYMBOL_GPL(dw_dma_probe);
+
+int dw_dma_remove(struct dw_dma_chip *chip)
+{
+	return do_dma_remove(chip);
+}
+EXPORT_SYMBOL_GPL(dw_dma_remove);