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 --- samples/rust/rust_dma.rs | 142 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 142 insertions(+) create mode 100644 samples/rust/rust_dma.rs (limited to 'samples/rust/rust_dma.rs') diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs new file mode 100644 index 000000000..bd60034de --- /dev/null +++ b/samples/rust/rust_dma.rs @@ -0,0 +1,142 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Rust DMA api test (based on QEMU's `pci-testdev`). +//! +//! To make this driver probe, QEMU must be run with `-device pci-testdev`. + +use kernel::{ + device::Core, + dma::{ + Coherent, + DataDirection, + Device, + DmaMask, // + }, + io::{ + io_project, + io_read, + Io, // + }, + page, + pci, + prelude::*, + scatterlist::{ + Owned, + SGTable, // + }, + sync::aref::ARef, // +}; + +#[pin_data(PinnedDrop)] +struct DmaSampleDriver { + pdev: ARef, + ca: Coherent<[MyStruct]>, + #[pin] + sgt: SGTable>>, +} + +const TEST_VALUES: [(u32, u32); 5] = [ + (0xa, 0xb), + (0xc, 0xd), + (0xe, 0xf), + (0xab, 0xba), + (0xcd, 0xef), +]; + +#[derive(FromBytes, IntoBytes)] +struct MyStruct { + h: u32, + b: u32, +} + +impl MyStruct { + fn new(h: u32, b: u32) -> Self { + Self { h, b } + } +} +// SAFETY: All bit patterns are acceptable values for `MyStruct`. +unsafe impl kernel::transmute::AsBytes for MyStruct {} +// SAFETY: Instances of `MyStruct` have no uninitialized portions. +unsafe impl kernel::transmute::FromBytes for MyStruct {} + +kernel::pci_device_table!( + PCI_TABLE, + ::IdInfo, + [(pci::DeviceId::from_id(pci::Vendor::REDHAT, 0x5), ())] +); + +impl pci::Driver for DmaSampleDriver { + type IdInfo = (); + type Data<'bound> = Self; + const ID_TABLE: pci::IdTable = &PCI_TABLE; + + fn probe<'bound>( + pdev: &'bound pci::Device>, + _info: Option<&'bound Self::IdInfo>, + ) -> impl PinInit + 'bound { + pin_init::pin_init_scope(move || { + dev_info!(pdev, "Probe DMA test driver.\n"); + + let mask = DmaMask::new::<64>(); + + // SAFETY: There are no concurrent calls to DMA allocation and mapping primitives. + unsafe { pdev.dma_set_mask_and_coherent(mask)? }; + + let ca: Coherent<[MyStruct]> = + Coherent::zeroed_slice(pdev.as_ref(), TEST_VALUES.len(), GFP_KERNEL)?; + + for (i, value) in TEST_VALUES.into_iter().enumerate() { + io_project!(ca, [panic: i]).copy_write(MyStruct::new(value.0, value.1)); + } + + let size = 4 * page::PAGE_SIZE; + let pages = VVec::with_capacity(size, GFP_KERNEL)?; + + let sgt = SGTable::new(pdev.as_ref(), pages, DataDirection::ToDevice, GFP_KERNEL); + + Ok(try_pin_init!(Self { + pdev: pdev.into(), + ca, + sgt <- sgt, + })) + }) + } +} + +impl DmaSampleDriver { + fn check_dma(&self) { + for (i, value) in TEST_VALUES.into_iter().enumerate() { + let val0 = io_read!(self.ca, [panic: i].h); + let val1 = io_read!(self.ca, [panic: i].b); + + assert_eq!(val0, value.0); + assert_eq!(val1, value.1); + } + } +} + +#[pinned_drop] +impl PinnedDrop for DmaSampleDriver { + fn drop(self: Pin<&mut Self>) { + dev_info!(self.pdev, "Unload DMA test driver.\n"); + + self.check_dma(); + + for (i, entry) in self.sgt.iter().enumerate() { + dev_info!( + self.pdev, + "Entry[{}]: DMA address: {:#x}", + i, + entry.dma_address(), + ); + } + } +} + +kernel::module_pci_driver! { + type: DmaSampleDriver, + name: "rust_dma", + authors: ["Abdiel Janulgue"], + description: "Rust DMA test", + license: "GPL v2", +} -- cgit v1.3.1