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, 120 insertions, 0 deletions

diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
new file mode 100644
index 000000000..9dd475cf4
--- /dev/null
+++ b/include/sound/memalloc.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>
+ *                   Takashi Iwai <tiwai@suse.de>
+ * 
+ *  Generic memory allocators
+ */
+
+#ifndef __SOUND_MEMALLOC_H
+#define __SOUND_MEMALLOC_H
+
+#include <linux/dma-direction.h>
+#include <asm/page.h>
+
+struct device;
+struct vm_area_struct;
+struct sg_table;
+
+/*
+ * buffer device info
+ */
+struct snd_dma_device {
+	int type;			/* SNDRV_DMA_TYPE_XXX */
+	enum dma_data_direction dir;	/* DMA direction */
+	bool need_sync;			/* explicit sync needed? */
+	struct device *dev;		/* generic device */
+};
+
+/*
+ * buffer types
+ */
+#define SNDRV_DMA_TYPE_UNKNOWN		0	/* not defined */
+#define SNDRV_DMA_TYPE_CONTINUOUS	1	/* continuous no-DMA memory */
+#define SNDRV_DMA_TYPE_DEV		2	/* generic device continuous */
+#define SNDRV_DMA_TYPE_DEV_WC		5	/* continuous write-combined */
+#ifdef CONFIG_GENERIC_ALLOCATOR
+#define SNDRV_DMA_TYPE_DEV_IRAM		4	/* generic device iram-buffer */
+#else
+#define SNDRV_DMA_TYPE_DEV_IRAM	SNDRV_DMA_TYPE_DEV
+#endif
+#define SNDRV_DMA_TYPE_VMALLOC		7	/* vmalloc'ed buffer */
+#define SNDRV_DMA_TYPE_NONCONTIG	8	/* non-coherent SG buffer */
+#define SNDRV_DMA_TYPE_NONCOHERENT	9	/* non-coherent buffer */
+#ifdef CONFIG_SND_DMA_SGBUF
+#define SNDRV_DMA_TYPE_DEV_SG		3	/* S/G pages */
+#define SNDRV_DMA_TYPE_DEV_WC_SG	6	/* SG write-combined */
+#else
+#define SNDRV_DMA_TYPE_DEV_SG	SNDRV_DMA_TYPE_DEV /* no SG-buf support */
+#define SNDRV_DMA_TYPE_DEV_WC_SG	SNDRV_DMA_TYPE_DEV_WC
+#endif
+
+/*
+ * info for buffer allocation
+ */
+struct snd_dma_buffer {
+	struct snd_dma_device dev;	/* device type */
+	unsigned char *area;	/* virtual pointer */
+	dma_addr_t addr;	/* physical address */
+	size_t bytes;		/* buffer size in bytes */
+	void *private_data;	/* private for allocator; don't touch */
+};
+
+/*
+ * return the pages matching with the given byte size
+ */
+static inline unsigned int snd_sgbuf_aligned_pages(size_t size)
+{
+	return (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+}
+
+/* allocate/release a buffer */
+int snd_dma_alloc_dir_pages(int type, struct device *dev,
+			    enum dma_data_direction dir, size_t size,
+			    struct snd_dma_buffer *dmab);
+
+static inline int snd_dma_alloc_pages(int type, struct device *dev,
+				      size_t size, struct snd_dma_buffer *dmab)
+{
+	return snd_dma_alloc_dir_pages(type, dev, DMA_BIDIRECTIONAL, size, dmab);
+}
+
+int snd_dma_alloc_pages_fallback(int type, struct device *dev, size_t size,
+                                 struct snd_dma_buffer *dmab);
+void snd_dma_free_pages(struct snd_dma_buffer *dmab);
+int snd_dma_buffer_mmap(struct snd_dma_buffer *dmab,
+			struct vm_area_struct *area);
+
+enum snd_dma_sync_mode { SNDRV_DMA_SYNC_CPU, SNDRV_DMA_SYNC_DEVICE };
+#ifdef CONFIG_HAS_DMA
+void snd_dma_buffer_sync(struct snd_dma_buffer *dmab,
+			 enum snd_dma_sync_mode mode);
+#else
+static inline void snd_dma_buffer_sync(struct snd_dma_buffer *dmab,
+				       enum snd_dma_sync_mode mode) {}
+#endif
+
+dma_addr_t snd_sgbuf_get_addr(struct snd_dma_buffer *dmab, size_t offset);
+struct page *snd_sgbuf_get_page(struct snd_dma_buffer *dmab, size_t offset);
+unsigned int snd_sgbuf_get_chunk_size(struct snd_dma_buffer *dmab,
+				      unsigned int ofs, unsigned int size);
+
+/* device-managed memory allocator */
+struct snd_dma_buffer *snd_devm_alloc_dir_pages(struct device *dev, int type,
+						enum dma_data_direction dir,
+						size_t size);
+
+static inline struct snd_dma_buffer *
+snd_devm_alloc_pages(struct device *dev, int type, size_t size)
+{
+	return snd_devm_alloc_dir_pages(dev, type, DMA_BIDIRECTIONAL, size);
+}
+
+static inline struct sg_table *
+snd_dma_noncontig_sg_table(struct snd_dma_buffer *dmab)
+{
+	return dmab->private_data;
+}
+
+#endif /* __SOUND_MEMALLOC_H */
+