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, 237 insertions, 0 deletions

diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
new file mode 100644
index 000000000..59d9eabc8
--- /dev/null
+++ b/drivers/dma/virt-dma.h
@@ -0,0 +1,237 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Virtual DMA channel support for DMAengine
+ *
+ * Copyright (C) 2012 Russell King
+ */
+#ifndef VIRT_DMA_H
+#define VIRT_DMA_H
+
+#include <linux/dmaengine.h>
+#include <linux/interrupt.h>
+
+#include "dmaengine.h"
+
+struct virt_dma_desc {
+	struct dma_async_tx_descriptor tx;
+	struct dmaengine_result tx_result;
+	/* protected by vc.lock */
+	struct list_head node;
+};
+
+struct virt_dma_chan {
+	struct dma_chan	chan;
+	struct tasklet_struct task;
+	void (*desc_free)(struct virt_dma_desc *);
+
+	spinlock_t lock;
+
+	/* protected by vc.lock */
+	struct list_head desc_allocated;
+	struct list_head desc_submitted;
+	struct list_head desc_issued;
+	struct list_head desc_completed;
+	struct list_head desc_terminated;
+
+	struct virt_dma_desc *cyclic;
+};
+
+static inline struct virt_dma_chan *to_virt_chan(struct dma_chan *chan)
+{
+	return container_of(chan, struct virt_dma_chan, chan);
+}
+
+void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head);
+void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev);
+struct virt_dma_desc *vchan_find_desc(struct virt_dma_chan *, dma_cookie_t);
+extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
+extern int vchan_tx_desc_free(struct dma_async_tx_descriptor *);
+
+/**
+ * vchan_tx_prep - prepare a descriptor
+ * @vc: virtual channel allocating this descriptor
+ * @vd: virtual descriptor to prepare
+ * @tx_flags: flags argument passed in to prepare function
+ */
+static inline struct dma_async_tx_descriptor *vchan_tx_prep(struct virt_dma_chan *vc,
+	struct virt_dma_desc *vd, unsigned long tx_flags)
+{
+	unsigned long flags;
+
+	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
+	vd->tx.flags = tx_flags;
+	vd->tx.tx_submit = vchan_tx_submit;
+	vd->tx.desc_free = vchan_tx_desc_free;
+
+	vd->tx_result.result = DMA_TRANS_NOERROR;
+	vd->tx_result.residue = 0;
+
+	spin_lock_irqsave(&vc->lock, flags);
+	list_add_tail(&vd->node, &vc->desc_allocated);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	return &vd->tx;
+}
+
+/**
+ * vchan_issue_pending - move submitted descriptors to issued list
+ * @vc: virtual channel to update
+ *
+ * vc.lock must be held by caller
+ */
+static inline bool vchan_issue_pending(struct virt_dma_chan *vc)
+{
+	lockdep_assert_held(&vc->lock);
+
+	list_splice_tail_init(&vc->desc_submitted, &vc->desc_issued);
+	return !list_empty(&vc->desc_issued);
+}
+
+/**
+ * vchan_cookie_complete - report completion of a descriptor
+ * @vd: virtual descriptor to update
+ *
+ * vc.lock must be held by caller
+ */
+static inline void vchan_cookie_complete(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+	dma_cookie_t cookie;
+
+	lockdep_assert_held(&vc->lock);
+
+	cookie = vd->tx.cookie;
+	dma_cookie_complete(&vd->tx);
+	dev_vdbg(vc->chan.device->dev, "txd %p[%x]: marked complete\n",
+		 vd, cookie);
+	list_add_tail(&vd->node, &vc->desc_completed);
+
+	tasklet_schedule(&vc->task);
+}
+
+/**
+ * vchan_vdesc_fini - Free or reuse a descriptor
+ * @vd: virtual descriptor to free/reuse
+ */
+static inline void vchan_vdesc_fini(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+
+	if (dmaengine_desc_test_reuse(&vd->tx)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&vc->lock, flags);
+		list_add(&vd->node, &vc->desc_allocated);
+		spin_unlock_irqrestore(&vc->lock, flags);
+	} else {
+		vc->desc_free(vd);
+	}
+}
+
+/**
+ * vchan_cyclic_callback - report the completion of a period
+ * @vd: virtual descriptor
+ */
+static inline void vchan_cyclic_callback(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+
+	vc->cyclic = vd;
+	tasklet_schedule(&vc->task);
+}
+
+/**
+ * vchan_terminate_vdesc - Disable pending cyclic callback
+ * @vd: virtual descriptor to be terminated
+ *
+ * vc.lock must be held by caller
+ */
+static inline void vchan_terminate_vdesc(struct virt_dma_desc *vd)
+{
+	struct virt_dma_chan *vc = to_virt_chan(vd->tx.chan);
+
+	lockdep_assert_held(&vc->lock);
+
+	list_add_tail(&vd->node, &vc->desc_terminated);
+
+	if (vc->cyclic == vd)
+		vc->cyclic = NULL;
+}
+
+/**
+ * vchan_next_desc - peek at the next descriptor to be processed
+ * @vc: virtual channel to obtain descriptor from
+ *
+ * vc.lock must be held by caller
+ */
+static inline struct virt_dma_desc *vchan_next_desc(struct virt_dma_chan *vc)
+{
+	lockdep_assert_held(&vc->lock);
+
+	return list_first_entry_or_null(&vc->desc_issued,
+					struct virt_dma_desc, node);
+}
+
+/**
+ * vchan_get_all_descriptors - obtain all submitted and issued descriptors
+ * @vc: virtual channel to get descriptors from
+ * @head: list of descriptors found
+ *
+ * vc.lock must be held by caller
+ *
+ * Removes all submitted and issued descriptors from internal lists, and
+ * provides a list of all descriptors found
+ */
+static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
+	struct list_head *head)
+{
+	lockdep_assert_held(&vc->lock);
+
+	list_splice_tail_init(&vc->desc_allocated, head);
+	list_splice_tail_init(&vc->desc_submitted, head);
+	list_splice_tail_init(&vc->desc_issued, head);
+	list_splice_tail_init(&vc->desc_completed, head);
+	list_splice_tail_init(&vc->desc_terminated, head);
+}
+
+static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
+{
+	struct virt_dma_desc *vd;
+	unsigned long flags;
+	LIST_HEAD(head);
+
+	spin_lock_irqsave(&vc->lock, flags);
+	vchan_get_all_descriptors(vc, &head);
+	list_for_each_entry(vd, &head, node)
+		dmaengine_desc_clear_reuse(&vd->tx);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	vchan_dma_desc_free_list(vc, &head);
+}
+
+/**
+ * vchan_synchronize() - synchronize callback execution to the current context
+ * @vc: virtual channel to synchronize
+ *
+ * Makes sure that all scheduled or active callbacks have finished running. For
+ * proper operation the caller has to ensure that no new callbacks are scheduled
+ * after the invocation of this function started.
+ * Free up the terminated cyclic descriptor to prevent memory leakage.
+ */
+static inline void vchan_synchronize(struct virt_dma_chan *vc)
+{
+	LIST_HEAD(head);
+	unsigned long flags;
+
+	tasklet_kill(&vc->task);
+
+	spin_lock_irqsave(&vc->lock, flags);
+
+	list_splice_tail_init(&vc->desc_terminated, &head);
+
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	vchan_dma_desc_free_list(vc, &head);
+}
+
+#endif