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, 226 insertions, 0 deletions

diff --git a/drivers/vfio/virqfd.c b/drivers/vfio/virqfd.c
new file mode 100644
index 000000000..59105a0ac
--- /dev/null
+++ b/drivers/vfio/virqfd.c
@@ -0,0 +1,226 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VFIO generic eventfd code for IRQFD support.
+ * Derived from drivers/vfio/pci/vfio_pci_intrs.c
+ *
+ * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
+ *     Author: Alex Williamson <alex.williamson@redhat.com>
+ */
+
+#include <linux/vfio.h>
+#include <linux/eventfd.h>
+#include <linux/file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "vfio.h"
+
+static struct workqueue_struct *vfio_irqfd_cleanup_wq;
+static DEFINE_SPINLOCK(virqfd_lock);
+
+int __init vfio_virqfd_init(void)
+{
+	vfio_irqfd_cleanup_wq =
+		create_singlethread_workqueue("vfio-irqfd-cleanup");
+	if (!vfio_irqfd_cleanup_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void vfio_virqfd_exit(void)
+{
+	destroy_workqueue(vfio_irqfd_cleanup_wq);
+}
+
+static void virqfd_deactivate(struct virqfd *virqfd)
+{
+	queue_work(vfio_irqfd_cleanup_wq, &virqfd->shutdown);
+}
+
+static int virqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
+{
+	struct virqfd *virqfd = container_of(wait, struct virqfd, wait);
+	__poll_t flags = key_to_poll(key);
+
+	if (flags & EPOLLIN) {
+		u64 cnt;
+		eventfd_ctx_do_read(virqfd->eventfd, &cnt);
+
+		/* An event has been signaled, call function */
+		if ((!virqfd->handler ||
+		     virqfd->handler(virqfd->opaque, virqfd->data)) &&
+		    virqfd->thread)
+			schedule_work(&virqfd->inject);
+	}
+
+	if (flags & EPOLLHUP) {
+		unsigned long flags;
+		spin_lock_irqsave(&virqfd_lock, flags);
+
+		/*
+		 * The eventfd is closing, if the virqfd has not yet been
+		 * queued for release, as determined by testing whether the
+		 * virqfd pointer to it is still valid, queue it now.  As
+		 * with kvm irqfds, we know we won't race against the virqfd
+		 * going away because we hold the lock to get here.
+		 */
+		if (*(virqfd->pvirqfd) == virqfd) {
+			*(virqfd->pvirqfd) = NULL;
+			virqfd_deactivate(virqfd);
+		}
+
+		spin_unlock_irqrestore(&virqfd_lock, flags);
+	}
+
+	return 0;
+}
+
+static void virqfd_ptable_queue_proc(struct file *file,
+				     wait_queue_head_t *wqh, poll_table *pt)
+{
+	struct virqfd *virqfd = container_of(pt, struct virqfd, pt);
+	add_wait_queue(wqh, &virqfd->wait);
+}
+
+static void virqfd_shutdown(struct work_struct *work)
+{
+	struct virqfd *virqfd = container_of(work, struct virqfd, shutdown);
+	u64 cnt;
+
+	eventfd_ctx_remove_wait_queue(virqfd->eventfd, &virqfd->wait, &cnt);
+	flush_work(&virqfd->inject);
+	eventfd_ctx_put(virqfd->eventfd);
+
+	kfree(virqfd);
+}
+
+static void virqfd_inject(struct work_struct *work)
+{
+	struct virqfd *virqfd = container_of(work, struct virqfd, inject);
+	if (virqfd->thread)
+		virqfd->thread(virqfd->opaque, virqfd->data);
+}
+
+static void virqfd_flush_inject(struct work_struct *work)
+{
+	struct virqfd *virqfd = container_of(work, struct virqfd, flush_inject);
+
+	flush_work(&virqfd->inject);
+}
+
+int vfio_virqfd_enable(void *opaque,
+		       int (*handler)(void *, void *),
+		       void (*thread)(void *, void *),
+		       void *data, struct virqfd **pvirqfd, int fd)
+{
+	struct eventfd_ctx *ctx;
+	struct virqfd *virqfd;
+	int ret = 0;
+	__poll_t events;
+
+	virqfd = kzalloc_obj(*virqfd, GFP_KERNEL_ACCOUNT);
+	if (!virqfd)
+		return -ENOMEM;
+
+	virqfd->pvirqfd = pvirqfd;
+	virqfd->opaque = opaque;
+	virqfd->handler = handler;
+	virqfd->thread = thread;
+	virqfd->data = data;
+
+	INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
+	INIT_WORK(&virqfd->inject, virqfd_inject);
+	INIT_WORK(&virqfd->flush_inject, virqfd_flush_inject);
+
+	CLASS(fd, irqfd)(fd);
+	if (fd_empty(irqfd)) {
+		ret = -EBADF;
+		goto err_fd;
+	}
+
+	ctx = eventfd_ctx_fileget(fd_file(irqfd));
+	if (IS_ERR(ctx)) {
+		ret = PTR_ERR(ctx);
+		goto err_fd;
+	}
+
+	virqfd->eventfd = ctx;
+
+	/*
+	 * virqfds can be released by closing the eventfd or directly
+	 * through ioctl.  These are both done through a workqueue, so
+	 * we update the pointer to the virqfd under lock to avoid
+	 * pushing multiple jobs to release the same virqfd.
+	 */
+	spin_lock_irq(&virqfd_lock);
+
+	if (*pvirqfd) {
+		spin_unlock_irq(&virqfd_lock);
+		ret = -EBUSY;
+		goto err_busy;
+	}
+	*pvirqfd = virqfd;
+
+	spin_unlock_irq(&virqfd_lock);
+
+	/*
+	 * Install our own custom wake-up handling so we are notified via
+	 * a callback whenever someone signals the underlying eventfd.
+	 */
+	init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
+	init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
+
+	events = vfs_poll(fd_file(irqfd), &virqfd->pt);
+
+	/*
+	 * Check if there was an event already pending on the eventfd
+	 * before we registered and trigger it as if we didn't miss it.
+	 */
+	if (events & EPOLLIN) {
+		if ((!handler || handler(opaque, data)) && thread)
+			schedule_work(&virqfd->inject);
+	}
+	return 0;
+err_busy:
+	eventfd_ctx_put(ctx);
+err_fd:
+	kfree(virqfd);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vfio_virqfd_enable);
+
+void vfio_virqfd_disable(struct virqfd **pvirqfd)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&virqfd_lock, flags);
+
+	if (*pvirqfd) {
+		virqfd_deactivate(*pvirqfd);
+		*pvirqfd = NULL;
+	}
+
+	spin_unlock_irqrestore(&virqfd_lock, flags);
+
+	/*
+	 * Block until we know all outstanding shutdown jobs have completed.
+	 * Even if we don't queue the job, flush the wq to be sure it's
+	 * been released.
+	 */
+	flush_workqueue(vfio_irqfd_cleanup_wq);
+}
+EXPORT_SYMBOL_GPL(vfio_virqfd_disable);
+
+void vfio_virqfd_flush_thread(struct virqfd **pvirqfd)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&virqfd_lock, flags);
+	if (*pvirqfd && (*pvirqfd)->thread)
+		queue_work(vfio_irqfd_cleanup_wq, &(*pvirqfd)->flush_inject);
+	spin_unlock_irqrestore(&virqfd_lock, flags);
+
+	flush_workqueue(vfio_irqfd_cleanup_wq);
+}
+EXPORT_SYMBOL_GPL(vfio_virqfd_flush_thread);