From a5f7a5bb3b7f28ba7e4fa246775b29a0e5537255 Mon Sep 17 00:00:00 2001 From: Jinke Han Date: Tue, 8 Sep 2026 15:37:42 +0800 Subject: x86/kprobes: Fix crash when probing CS CALL instructions 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) Signed-off-by: Jinke Han Signed-off-by: Ingo Molnar Reviewed-by: Masami Hiramatsu (Google) Acked-by: Yafang Shao Acked-by: Borislav Petkov Cc: Peter Zijlstra Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000 --- include/clocksource/timer-xilinx.h | 73 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 73 insertions(+) create mode 100644 include/clocksource/timer-xilinx.h (limited to 'include/clocksource/timer-xilinx.h') diff --git a/include/clocksource/timer-xilinx.h b/include/clocksource/timer-xilinx.h new file mode 100644 index 000000000..d116f18de --- /dev/null +++ b/include/clocksource/timer-xilinx.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (C) 2021 Sean Anderson + */ + +#ifndef XILINX_TIMER_H +#define XILINX_TIMER_H + +#include + +#define TCSR0 0x00 +#define TLR0 0x04 +#define TCR0 0x08 +#define TCSR1 0x10 +#define TLR1 0x14 +#define TCR1 0x18 + +#define TCSR_MDT BIT(0) +#define TCSR_UDT BIT(1) +#define TCSR_GENT BIT(2) +#define TCSR_CAPT BIT(3) +#define TCSR_ARHT BIT(4) +#define TCSR_LOAD BIT(5) +#define TCSR_ENIT BIT(6) +#define TCSR_ENT BIT(7) +#define TCSR_TINT BIT(8) +#define TCSR_PWMA BIT(9) +#define TCSR_ENALL BIT(10) +#define TCSR_CASC BIT(11) + +struct clk; +struct device_node; +struct regmap; + +/** + * struct xilinx_timer_priv - Private data for Xilinx AXI timer drivers + * @map: Regmap of the device, possibly with an offset + * @clk: Parent clock + * @max: Maximum value of the counters + */ +struct xilinx_timer_priv { + struct regmap *map; + struct clk *clk; + u64 max; +}; + +/** + * xilinx_timer_tlr_cycles() - Calculate the TLR for a period specified + * in clock cycles + * @priv: The timer's private data + * @tcsr: The value of the TCSR register for this counter + * @cycles: The number of cycles in this period + * + * Callers of this function MUST ensure that @cycles is representable as + * a TLR. + * + * Return: The calculated value for TLR + */ +u32 xilinx_timer_tlr_cycles(struct xilinx_timer_priv *priv, u32 tcsr, + u64 cycles); + +/** + * xilinx_timer_get_period() - Get the current period of a counter + * @priv: The timer's private data + * @tlr: The value of TLR for this counter + * @tcsr: The value of TCSR for this counter + * + * Return: The period, in ns + */ +unsigned int xilinx_timer_get_period(struct xilinx_timer_priv *priv, + u32 tlr, u32 tcsr); + +#endif /* XILINX_TIMER_H */ -- cgit v1.3.1