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, 114 insertions, 0 deletions

diff --git a/include/drm/drm_suballoc.h b/include/drm/drm_suballoc.h
new file mode 100644
index 000000000..29befdda3
--- /dev/null
+++ b/include/drm/drm_suballoc.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+/*
+ * Copyright 2011 Red Hat Inc.
+ * Copyright © 2022 Intel Corporation
+ */
+#ifndef _DRM_SUBALLOC_H_
+#define _DRM_SUBALLOC_H_
+
+#include <drm/drm_mm.h>
+
+#include <linux/dma-fence.h>
+#include <linux/types.h>
+
+#define DRM_SUBALLOC_MAX_QUEUES 32
+/**
+ * struct drm_suballoc_manager - fenced range allocations
+ * @wq: Wait queue for sleeping allocations on contention.
+ * @hole: Pointer to first hole node.
+ * @olist: List of allocated ranges.
+ * @flist: Array[fence context hash] of queues of fenced allocated ranges.
+ * @size: Size of the managed range.
+ * @align: Default alignment for the managed range.
+ */
+struct drm_suballoc_manager {
+	wait_queue_head_t wq;
+	struct list_head *hole;
+	struct list_head olist;
+	struct list_head flist[DRM_SUBALLOC_MAX_QUEUES];
+	size_t size;
+	size_t align;
+};
+
+/**
+ * struct drm_suballoc - Sub-allocated range
+ * @olist: List link for list of allocated ranges.
+ * @flist: List linkk for the manager fenced allocated ranges queues.
+ * @manager: The drm_suballoc_manager.
+ * @soffset: Start offset.
+ * @eoffset: End offset + 1 so that @eoffset - @soffset = size.
+ * @fence: The fence protecting the allocation.
+ */
+struct drm_suballoc {
+	struct list_head olist;
+	struct list_head flist;
+	struct drm_suballoc_manager *manager;
+	size_t soffset;
+	size_t eoffset;
+	struct dma_fence *fence;
+};
+
+void drm_suballoc_manager_init(struct drm_suballoc_manager *sa_manager,
+			       size_t size, size_t align);
+
+void drm_suballoc_manager_fini(struct drm_suballoc_manager *sa_manager);
+
+struct drm_suballoc *drm_suballoc_alloc(gfp_t gfp);
+
+int drm_suballoc_insert(struct drm_suballoc_manager *sa_manager,
+			struct drm_suballoc *sa, size_t size, bool intr,
+			size_t align);
+
+struct drm_suballoc *
+drm_suballoc_new(struct drm_suballoc_manager *sa_manager, size_t size,
+		 gfp_t gfp, bool intr, size_t align);
+
+void drm_suballoc_free(struct drm_suballoc *sa, struct dma_fence *fence);
+
+/**
+ * drm_suballoc_soffset - Range start.
+ * @sa: The struct drm_suballoc.
+ *
+ * Return: The start of the allocated range.
+ */
+static inline size_t drm_suballoc_soffset(struct drm_suballoc *sa)
+{
+	return sa->soffset;
+}
+
+/**
+ * drm_suballoc_eoffset - Range end.
+ * @sa: The struct drm_suballoc.
+ *
+ * Return: The end of the allocated range + 1.
+ */
+static inline size_t drm_suballoc_eoffset(struct drm_suballoc *sa)
+{
+	return sa->eoffset;
+}
+
+/**
+ * drm_suballoc_size - Range size.
+ * @sa: The struct drm_suballoc.
+ *
+ * Return: The size of the allocated range.
+ */
+static inline size_t drm_suballoc_size(struct drm_suballoc *sa)
+{
+	return sa->eoffset - sa->soffset;
+}
+
+#ifdef CONFIG_DEBUG_FS
+void drm_suballoc_dump_debug_info(struct drm_suballoc_manager *sa_manager,
+				  struct drm_printer *p,
+				  unsigned long long suballoc_base);
+#else
+static inline void
+drm_suballoc_dump_debug_info(struct drm_suballoc_manager *sa_manager,
+			     struct drm_printer *p,
+			     unsigned long long suballoc_base)
+{ }
+
+#endif
+
+#endif /* _DRM_SUBALLOC_H_ */