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, 143 insertions, 0 deletions

diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
new file mode 100644
index 000000000..7961172a7
--- /dev/null
+++ b/drivers/dma/virt-dma.c
@@ -0,0 +1,143 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Virtual DMA channel support for DMAengine
+ *
+ * Copyright (C) 2012 Russell King
+ */
+#include <linux/device.h>
+#include <linux/dmaengine.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+
+#include "virt-dma.h"
+
+static struct virt_dma_desc *to_virt_desc(struct dma_async_tx_descriptor *tx)
+{
+	return container_of(tx, struct virt_dma_desc, tx);
+}
+
+dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *tx)
+{
+	struct virt_dma_chan *vc = to_virt_chan(tx->chan);
+	struct virt_dma_desc *vd = to_virt_desc(tx);
+	unsigned long flags;
+	dma_cookie_t cookie;
+
+	spin_lock_irqsave(&vc->lock, flags);
+	cookie = dma_cookie_assign(tx);
+
+	list_move_tail(&vd->node, &vc->desc_submitted);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n",
+		vc, vd, cookie);
+
+	return cookie;
+}
+EXPORT_SYMBOL_GPL(vchan_tx_submit);
+
+/**
+ * vchan_tx_desc_free - free a reusable descriptor
+ * @tx: the transfer
+ *
+ * This function frees a previously allocated reusable descriptor. The only
+ * other way is to clear the DMA_CTRL_REUSE flag and submit one last time the
+ * transfer.
+ *
+ * Returns 0 upon success
+ */
+int vchan_tx_desc_free(struct dma_async_tx_descriptor *tx)
+{
+	struct virt_dma_chan *vc = to_virt_chan(tx->chan);
+	struct virt_dma_desc *vd = to_virt_desc(tx);
+	unsigned long flags;
+
+	spin_lock_irqsave(&vc->lock, flags);
+	list_del(&vd->node);
+	spin_unlock_irqrestore(&vc->lock, flags);
+
+	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: freeing\n",
+		vc, vd, vd->tx.cookie);
+	vc->desc_free(vd);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vchan_tx_desc_free);
+
+struct virt_dma_desc *vchan_find_desc(struct virt_dma_chan *vc,
+	dma_cookie_t cookie)
+{
+	struct virt_dma_desc *vd;
+
+	list_for_each_entry(vd, &vc->desc_issued, node)
+		if (vd->tx.cookie == cookie)
+			return vd;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(vchan_find_desc);
+
+/*
+ * This tasklet handles the completion of a DMA descriptor by
+ * calling its callback and freeing it.
+ */
+static void vchan_complete(struct tasklet_struct *t)
+{
+	struct virt_dma_chan *vc = from_tasklet(vc, t, task);
+	struct virt_dma_desc *vd, *_vd;
+	struct dmaengine_desc_callback cb;
+	LIST_HEAD(head);
+
+	spin_lock_irq(&vc->lock);
+	list_splice_tail_init(&vc->desc_completed, &head);
+	vd = vc->cyclic;
+	if (vd) {
+		vc->cyclic = NULL;
+		dmaengine_desc_get_callback(&vd->tx, &cb);
+	} else {
+		memset(&cb, 0, sizeof(cb));
+	}
+	spin_unlock_irq(&vc->lock);
+
+	dmaengine_desc_callback_invoke(&cb, &vd->tx_result);
+
+	list_for_each_entry_safe(vd, _vd, &head, node) {
+		dmaengine_desc_get_callback(&vd->tx, &cb);
+
+		list_del(&vd->node);
+		dmaengine_desc_callback_invoke(&cb, &vd->tx_result);
+		vchan_vdesc_fini(vd);
+	}
+}
+
+void vchan_dma_desc_free_list(struct virt_dma_chan *vc, struct list_head *head)
+{
+	struct virt_dma_desc *vd, *_vd;
+
+	list_for_each_entry_safe(vd, _vd, head, node) {
+		list_del(&vd->node);
+		vchan_vdesc_fini(vd);
+	}
+}
+EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
+
+void vchan_init(struct virt_dma_chan *vc, struct dma_device *dmadev)
+{
+	dma_cookie_init(&vc->chan);
+
+	spin_lock_init(&vc->lock);
+	INIT_LIST_HEAD(&vc->desc_allocated);
+	INIT_LIST_HEAD(&vc->desc_submitted);
+	INIT_LIST_HEAD(&vc->desc_issued);
+	INIT_LIST_HEAD(&vc->desc_completed);
+	INIT_LIST_HEAD(&vc->desc_terminated);
+
+	tasklet_setup(&vc->task, vchan_complete);
+
+	vc->chan.device = dmadev;
+	list_add_tail(&vc->chan.device_node, &dmadev->channels);
+}
+EXPORT_SYMBOL_GPL(vchan_init);
+
+MODULE_AUTHOR("Russell King");
+MODULE_DESCRIPTION("Virtual DMA channel support for DMAengine");
+MODULE_LICENSE("GPL");