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, 101 insertions, 0 deletions

diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h
new file mode 100644
index 000000000..ac8ce3179
--- /dev/null
+++ b/drivers/xen/gntdev-common.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Common functionality of grant device.
+ *
+ * Copyright (c) 2006-2007, D G Murray.
+ *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_COMMON_H
+#define _GNTDEV_COMMON_H
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
+#include <linux/types.h>
+#include <xen/interface/event_channel.h>
+#include <xen/grant_table.h>
+
+struct gntdev_dmabuf_priv;
+
+struct gntdev_priv {
+	/* Maps with visible offsets in the file descriptor. */
+	struct list_head maps;
+	/* lock protects maps and freeable_maps. */
+	struct mutex lock;
+
+	/* Free instances of struct gntdev_copy_batch. */
+	struct gntdev_copy_batch *batch;
+	struct mutex batch_lock;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/* Device for which DMA memory is allocated. */
+	struct device *dma_dev;
+#endif
+
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+#endif
+};
+
+struct gntdev_unmap_notify {
+	int flags;
+	/* Address relative to the start of the gntdev_grant_map. */
+	int addr;
+	evtchn_port_t event;
+};
+
+struct gntdev_grant_map {
+	atomic_t in_use;
+	struct mmu_interval_notifier notifier;
+	bool notifier_init;
+	struct list_head next;
+	int index;
+	int count;
+	int flags;
+	refcount_t users;
+	struct gntdev_unmap_notify notify;
+	struct ioctl_gntdev_grant_ref *grants;
+	struct gnttab_map_grant_ref   *map_ops;
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_map_grant_ref   *kmap_ops;
+	struct gnttab_unmap_grant_ref *kunmap_ops;
+	bool *being_removed;
+	struct page **pages;
+	unsigned long pages_vm_start;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/*
+	 * If dmabuf_vaddr is not NULL then this mapping is backed by DMA
+	 * capable memory.
+	 */
+
+	struct device *dma_dev;
+	/* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */
+	int dma_flags;
+	void *dma_vaddr;
+	dma_addr_t dma_bus_addr;
+	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
+	xen_pfn_t *frames;
+#endif
+
+	/* Number of live grants */
+	atomic_t live_grants;
+	/* Needed to avoid allocation in __unmap_grant_pages */
+	struct gntab_unmap_queue_data unmap_data;
+};
+
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags);
+
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add);
+
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map);
+
+bool gntdev_test_page_count(unsigned int count);
+
+int gntdev_map_grant_pages(struct gntdev_grant_map *map);
+
+#endif