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/include/rdma/ib_cache.h b/include/rdma/ib_cache.h
new file mode 100644
index 000000000..eed46d966
--- /dev/null
+++ b/include/rdma/ib_cache.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/*
+ * Copyright (c) 2004 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Intel Corporation. All rights reserved.
+ * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ */
+
+#ifndef _IB_CACHE_H
+#define _IB_CACHE_H
+
+#include <rdma/ib_verbs.h>
+
+int rdma_query_gid(struct ib_device *device, u32 port_num, int index,
+		   union ib_gid *gid);
+void *rdma_read_gid_hw_context(const struct ib_gid_attr *attr);
+const struct ib_gid_attr *rdma_find_gid(struct ib_device *device,
+					const union ib_gid *gid,
+					enum ib_gid_type gid_type,
+					struct net_device *ndev);
+const struct ib_gid_attr *rdma_find_gid_by_port(struct ib_device *ib_dev,
+						const union ib_gid *gid,
+						enum ib_gid_type gid_type,
+						u32 port,
+						struct net_device *ndev);
+const struct ib_gid_attr *rdma_find_gid_by_filter(
+	struct ib_device *device, const union ib_gid *gid, u32 port_num,
+	bool (*filter)(const union ib_gid *gid, const struct ib_gid_attr *,
+		       void *),
+	void *context);
+
+int rdma_read_gid_l2_fields(const struct ib_gid_attr *attr,
+			    u16 *vlan_id, u8 *smac);
+struct net_device *rdma_read_gid_attr_ndev_rcu(const struct ib_gid_attr *attr);
+
+/**
+ * ib_get_cached_pkey - Returns a cached PKey table entry
+ * @device_handle: The device to query.
+ * @port_num: The port number of the device to query.
+ * @index: The index into the cached PKey table to query.
+ * @pkey: The PKey value found at the specified index.
+ *
+ * ib_get_cached_pkey() fetches the specified PKey table entry stored in
+ * the local software cache.
+ */
+int ib_get_cached_pkey(struct ib_device    *device_handle,
+		       u32                  port_num,
+		       int                  index,
+		       u16                 *pkey);
+
+/**
+ * ib_find_cached_pkey - Returns the PKey table index where a specified
+ *   PKey value occurs.
+ * @device: The device to query.
+ * @port_num: The port number of the device to search for the PKey.
+ * @pkey: The PKey value to search for.
+ * @index: The index into the cached PKey table where the PKey was found.
+ *
+ * ib_find_cached_pkey() searches the specified PKey table in
+ * the local software cache.
+ */
+int ib_find_cached_pkey(struct ib_device    *device,
+			u32                  port_num,
+			u16                  pkey,
+			u16                 *index);
+
+/**
+ * ib_get_cached_lmc - Returns a cached lmc table entry
+ * @device: The device to query.
+ * @port_num: The port number of the device to query.
+ * @lmc: The lmc value for the specified port for that device.
+ *
+ * ib_get_cached_lmc() fetches the specified lmc table entry stored in
+ * the local software cache.
+ */
+int ib_get_cached_lmc(struct ib_device *device,
+		      u32               port_num,
+		      u8                *lmc);
+
+/**
+ * ib_get_cached_port_state - Returns a cached port state table entry
+ * @device: The device to query.
+ * @port_num: The port number of the device to query.
+ * @port_active: port_state for the specified port for that device.
+ *
+ * ib_get_cached_port_state() fetches the specified port_state table entry stored in
+ * the local software cache.
+ */
+int ib_get_cached_port_state(struct ib_device *device,
+			     u32               port_num,
+			      enum ib_port_state *port_active);
+
+bool rdma_is_zero_gid(const union ib_gid *gid);
+const struct ib_gid_attr *rdma_get_gid_attr(struct ib_device *device,
+					    u32 port_num, int index);
+void rdma_put_gid_attr(const struct ib_gid_attr *attr);
+void rdma_hold_gid_attr(const struct ib_gid_attr *attr);
+ssize_t rdma_query_gid_table(struct ib_device *device,
+			     struct ib_uverbs_gid_entry *entries,
+			     size_t max_entries);
+
+#endif /* _IB_CACHE_H */