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, 45 insertions, 0 deletions

diff --git a/drivers/net/phy/sfp.h b/drivers/net/phy/sfp.h
new file mode 100644
index 000000000..19fe29d84
--- /dev/null
+++ b/drivers/net/phy/sfp.h
@@ -0,0 +1,45 @@
+#ifndef SFP_H
+#define SFP_H
+
+#include <linux/ethtool.h>
+#include <linux/sfp.h>
+
+struct sfp;
+
+struct sfp_quirk {
+	const char *vendor;
+	const char *part;
+	void (*support)(const struct sfp_eeprom_id *id,
+			struct sfp_module_caps *caps);
+	void (*fixup)(struct sfp *sfp);
+	bool part_prefix_match;
+};
+
+struct sfp_socket_ops {
+	void (*attach)(struct sfp *sfp);
+	void (*detach)(struct sfp *sfp);
+	void (*start)(struct sfp *sfp);
+	void (*stop)(struct sfp *sfp);
+	void (*set_signal_rate)(struct sfp *sfp, unsigned int rate_kbd);
+	int (*module_info)(struct sfp *sfp, struct ethtool_modinfo *modinfo);
+	int (*module_eeprom)(struct sfp *sfp, struct ethtool_eeprom *ee,
+			     u8 *data);
+	int (*module_eeprom_by_page)(struct sfp *sfp,
+				     const struct ethtool_module_eeprom *page,
+				     struct netlink_ext_ack *extack);
+};
+
+int sfp_add_phy(struct sfp_bus *bus, struct phy_device *phydev);
+void sfp_remove_phy(struct sfp_bus *bus);
+void sfp_link_up(struct sfp_bus *bus);
+void sfp_link_down(struct sfp_bus *bus);
+int sfp_module_insert(struct sfp_bus *bus, const struct sfp_eeprom_id *id,
+		      const struct sfp_quirk *quirk);
+void sfp_module_remove(struct sfp_bus *bus);
+int sfp_module_start(struct sfp_bus *bus);
+void sfp_module_stop(struct sfp_bus *bus);
+struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp,
+				    const struct sfp_socket_ops *ops);
+void sfp_unregister_socket(struct sfp_bus *bus);
+
+#endif