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, 136 insertions, 0 deletions

diff --git a/drivers/dax/dax-private.h b/drivers/dax/dax-private.h
new file mode 100644
index 000000000..607a53a91
--- /dev/null
+++ b/drivers/dax/dax-private.h
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright(c) 2016 Intel Corporation. All rights reserved.
+ */
+#ifndef __DAX_PRIVATE_H__
+#define __DAX_PRIVATE_H__
+
+#include <linux/device.h>
+#include <linux/cdev.h>
+#include <linux/idr.h>
+
+/* private routines between core files */
+struct dax_device;
+struct dax_device *inode_dax(struct inode *inode);
+struct inode *dax_inode(struct dax_device *dax_dev);
+int dax_bus_init(void);
+void dax_bus_exit(void);
+
+/**
+ * struct dax_region - mapping infrastructure for dax devices
+ * @id: kernel-wide unique region for a memory range
+ * @target_node: effective numa node if this memory range is onlined
+ * @kref: to pin while other agents have a need to do lookups
+ * @dev: parent device backing this region
+ * @align: allocation and mapping alignment for child dax devices
+ * @ida: instance id allocator
+ * @res: resource tree to track instance allocations
+ * @seed: allow userspace to find the first unbound seed device
+ * @youngest: allow userspace to find the most recently created device
+ */
+struct dax_region {
+	int id;
+	int target_node;
+	struct kref kref;
+	struct device *dev;
+	unsigned int align;
+	struct ida ida;
+	struct resource res;
+	struct device *seed;
+	struct device *youngest;
+};
+
+/**
+ * struct dax_mapping - device to display mapping range attributes
+ * @dev: device representing this range
+ * @range_id: index within dev_dax ranges array
+ * @id: ida of this mapping
+ */
+struct dax_mapping {
+	struct device dev;
+	int range_id;
+	int id;
+};
+
+/**
+ * struct dev_dax_range - tuple represenging a range of memory used by dev_dax
+ * @pgoff: page offset
+ * @range: resource-span
+ * @mapping: reference to the dax_mapping for this range
+ */
+struct dev_dax_range {
+	unsigned long pgoff;
+	struct range range;
+	struct dax_mapping *mapping;
+};
+
+/**
+ * struct dev_dax - instance data for a subdivision of a dax region, and
+ * data while the device is activated in the driver.
+ * @region: parent region
+ * @dax_dev: core dax functionality
+ * @cached_size: size of daxdev cached by fsdev_dax
+ * @align: alignment of this instance
+ * @target_node: effective numa node if dev_dax memory range is onlined
+ * @dyn_id: is this a dynamic or statically created instance
+ * @id: ida allocated id when the dax_region is not static
+ * @ida: mapping id allocator
+ * @dev: device core
+ * @pgmap: pgmap for memmap setup / lifetime (driver owned)
+ * @memmap_on_memory: allow kmem to put the memmap in the memory
+ * @nr_range: size of @ranges
+ * @ranges: range tuples of memory used
+ */
+struct dev_dax {
+	struct dax_region *region;
+	struct dax_device *dax_dev;
+	u64 cached_size;
+	unsigned int align;
+	int target_node;
+	bool dyn_id;
+	int id;
+	struct ida ida;
+	struct device dev;
+	struct dev_pagemap *pgmap;
+	bool memmap_on_memory;
+	int nr_range;
+	struct dev_dax_range *ranges;
+};
+
+/*
+ * While run_dax() is potentially a generic operation that could be
+ * defined in include/linux/dax.h we don't want to grow any users
+ * outside of drivers/dax/
+ */
+void run_dax(struct dax_device *dax_dev);
+
+static inline struct dev_dax *to_dev_dax(struct device *dev)
+{
+	return container_of(dev, struct dev_dax, dev);
+}
+
+static inline struct dax_mapping *to_dax_mapping(struct device *dev)
+{
+	return container_of(dev, struct dax_mapping, dev);
+}
+
+phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff, unsigned long size);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline bool dax_align_valid(unsigned long align)
+{
+	if (align == PUD_SIZE && IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
+		return true;
+	if (align == PMD_SIZE && has_transparent_hugepage())
+		return true;
+	if (align == PAGE_SIZE)
+		return true;
+	return false;
+}
+#else
+static inline bool dax_align_valid(unsigned long align)
+{
+	return align == PAGE_SIZE;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif