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, 72 insertions, 0 deletions

diff --git a/drivers/pci/controller/pci-host-common.h b/drivers/pci/controller/pci-host-common.h
new file mode 100644
index 000000000..51afd65d3
--- /dev/null
+++ b/drivers/pci/controller/pci-host-common.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Common library for PCI host controller drivers
+ *
+ * Copyright (C) 2014 ARM Limited
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#ifndef _PCI_HOST_COMMON_H
+#define _PCI_HOST_COMMON_H
+
+#include <linux/delay.h>
+#include "../pci.h"
+
+struct pci_ecam_ops;
+
+/**
+ * struct pci_host_perst - PERST# GPIO descriptor
+ * @list: List node for linking multiple PERST# GPIOs
+ * @desc: GPIO descriptor for PERST# signal
+ *
+ * This structure holds a single PERST# GPIO descriptor.
+ */
+struct pci_host_perst {
+	struct list_head	list;
+	struct gpio_desc	*desc;
+};
+
+/**
+ * struct pci_host_port - Generic Root Port properties
+ * @list: List node for linking multiple ports
+ * @perst: List of PERST# GPIO descriptors for this port and its children
+ *
+ * This structure contains common properties that can be parsed from
+ * Root Port device tree nodes.
+ */
+struct pci_host_port {
+	struct list_head	list;
+	struct list_head	perst;
+};
+
+void pci_host_common_delete_ports(void *data);
+int pci_host_common_parse_ports(struct device *dev,
+				struct pci_host_bridge *bridge);
+int pci_host_common_probe(struct platform_device *pdev);
+int pci_host_common_init(struct platform_device *pdev,
+			 struct pci_host_bridge *bridge,
+			 const struct pci_ecam_ops *ops);
+void pci_host_common_remove(struct platform_device *pdev);
+void pci_host_handle_link_down(struct pci_dev *port);
+
+struct pci_config_window *pci_host_common_ecam_create(struct device *dev,
+	struct pci_host_bridge *bridge, const struct pci_ecam_ops *ops);
+
+bool pci_host_common_d3cold_possible(struct pci_host_bridge *bridge,
+				     bool *pme_capable);
+
+/**
+ * pci_host_common_link_train_delay - Wait 100 ms if link speed > 5 GT/s
+ * @max_link_speed: the maximum link speed (2 = 5.0 GT/s, 3 = 8.0 GT/s, ...)
+ *
+ * Must be called after Link training completes and before the first
+ * Configuration Request is sent.
+ */
+static inline void pci_host_common_link_train_delay(int max_link_speed)
+{
+	if (max_link_speed > 2)
+		msleep(PCIE_RESET_CONFIG_WAIT_MS);
+}
+
+#endif