[PATCH v3] drivers: hv: vmbus: Use kthread for vmbus interrupts on PREEMPT_RT

From: Jan Kiszka <[email protected]>

Resolves the following lockdep report when booting PREEMPT_RT on Hyper-V
with related guest support enabled:

[    1.127941] hv_vmbus: registering driver hyperv_drm

[    1.132518] =============================
[    1.132519] [ BUG: Invalid wait context ]
[    1.132521] 6.19.0-rc8+ #9 Not tainted
[    1.132524] -----------------------------
[    1.132525] swapper/0/0 is trying to lock:
[    1.132526] ffff8b9381bb3c90 (&channel->sched_lock){....}-{3:3}, at: vmbus_chan_sched+0xc4/0x2b0
[    1.132543] other info that might help us debug this:
[    1.132544] context-{2:2}
[    1.132545] 1 lock held by swapper/0/0:
[    1.132547]  #0: ffffffffa010c4c0 (rcu_read_lock){....}-{1:3}, at: vmbus_chan_sched+0x31/0x2b0
[    1.132557] stack backtrace:
[    1.132560] CPU: 0 UID: 0 PID: 0 Comm: swapper/0 Not tainted 6.19.0-rc8+ #9 PREEMPT_{RT,(lazy)}
[    1.132565] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 09/25/2025
[    1.132567] Call Trace:
[    1.132570]  <IRQ>
[    1.132573]  dump_stack_lvl+0x6e/0xa0
[    1.132581]  __lock_acquire+0xee0/0x21b0
[    1.132592]  lock_acquire+0xd5/0x2d0
[    1.132598]  ? vmbus_chan_sched+0xc4/0x2b0
[    1.132606]  ? lock_acquire+0xd5/0x2d0
[    1.132613]  ? vmbus_chan_sched+0x31/0x2b0
[    1.132619]  rt_spin_lock+0x3f/0x1f0
[    1.132623]  ? vmbus_chan_sched+0xc4/0x2b0
[    1.132629]  ? vmbus_chan_sched+0x31/0x2b0
[    1.132634]  vmbus_chan_sched+0xc4/0x2b0
[    1.132641]  vmbus_isr+0x2c/0x150
[    1.132648]  __sysvec_hyperv_callback+0x5f/0xa0
[    1.132654]  sysvec_hyperv_callback+0x88/0xb0
[    1.132658]  </IRQ>
[    1.132659]  <TASK>
[    1.132660]  asm_sysvec_hyperv_callback+0x1a/0x20

As code paths that handle vmbus IRQs use sleepy locks under PREEMPT_RT,
the vmbus_isr execution needs to be moved into thread context. Open-
coding this allows to skip the IPI that irq_work would additionally
bring and which we do not need, being an IRQ, never an NMI.

This affects both x86 and arm64, therefore hook into the common driver
logic.

Signed-off-by: Jan Kiszka <[email protected]>
---

Changes in v3:
 - move logic to generic vmbus driver, targeting arm64 as well
 - annotate non-RT path with lockdep_hardirq_threaded
 - only teardown if setup ran

Changes in v2:
 - reorder vmbus_irq_pending clearing to fix a race condition

 drivers/hv/vmbus_drv.c | 66 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 65 insertions(+), 1 deletion(-)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 6785ad63a9cb..749a2e68af05 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -25,6 +25,7 @@
 #include <linux/cpu.h>
 #include <linux/sched/isolation.h>
 #include <linux/sched/task_stack.h>
+#include <linux/smpboot.h>
 
 #include <linux/delay.h>
 #include <linux/panic_notifier.h>
@@ -1350,7 +1351,7 @@ static void vmbus_message_sched(struct hv_per_cpu_context *hv_cpu, void *message
 	}
 }
 
-void vmbus_isr(void)
+static void __vmbus_isr(void)
 {
 	struct hv_per_cpu_context *hv_cpu
 		= this_cpu_ptr(hv_context.cpu_context);
@@ -1363,6 +1364,53 @@ void vmbus_isr(void)
 
 	add_interrupt_randomness(vmbus_interrupt);
 }
+
+static DEFINE_PER_CPU(bool, vmbus_irq_pending);
+static DEFINE_PER_CPU(struct task_struct *, vmbus_irqd);
+
+static void vmbus_irqd_wake(void)
+{
+	struct task_struct *tsk = __this_cpu_read(vmbus_irqd);
+
+	__this_cpu_write(vmbus_irq_pending, true);
+	wake_up_process(tsk);
+}
+
+static void vmbus_irqd_setup(unsigned int cpu)
+{
+	sched_set_fifo(current);
+}
+
+static int vmbus_irqd_should_run(unsigned int cpu)
+{
+	return __this_cpu_read(vmbus_irq_pending);
+}
+
+static void run_vmbus_irqd(unsigned int cpu)
+{
+	__this_cpu_write(vmbus_irq_pending, false);
+	__vmbus_isr();
+}
+
+static bool vmbus_irq_initialized;
+
+static struct smp_hotplug_thread vmbus_irq_threads = {
+	.store                  = &vmbus_irqd,
+	.setup			= vmbus_irqd_setup,
+	.thread_should_run      = vmbus_irqd_should_run,
+	.thread_fn              = run_vmbus_irqd,
+	.thread_comm            = "vmbus_irq/%u",
+};
+
+void vmbus_isr(void)
+{
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		vmbus_irqd_wake();
+	} else {
+		lockdep_hardirq_threaded();
+		__vmbus_isr();
+	}
+}
 EXPORT_SYMBOL_FOR_MODULES(vmbus_isr, "mshv_vtl");
 
 static irqreturn_t vmbus_percpu_isr(int irq, void *dev_id)
@@ -1462,6 +1510,13 @@ static int vmbus_bus_init(void)
 	 * the VMbus interrupt handler.
 	 */
 
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && !vmbus_irq_initialized) {
+		ret = smpboot_register_percpu_thread(&vmbus_irq_threads);
+		if (ret)
+			goto err_kthread;
+		vmbus_irq_initialized = true;
+	}
+
 	if (vmbus_irq == -1) {
 		hv_setup_vmbus_handler(vmbus_isr);
 	} else {
@@ -1507,6 +1562,11 @@ static int vmbus_bus_init(void)
 		free_percpu(vmbus_evt);
 	}
 err_setup:
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && vmbus_irq_initialized) {
+		smpboot_unregister_percpu_thread(&vmbus_irq_threads);
+		vmbus_irq_initialized = false;
+	}
+err_kthread:
 	bus_unregister(&hv_bus);
 	return ret;
 }
@@ -2976,6 +3036,10 @@ static void __exit vmbus_exit(void)
 		free_percpu_irq(vmbus_irq, vmbus_evt);
 		free_percpu(vmbus_evt);
 	}
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && vmbus_irq_initialized) {
+		smpboot_unregister_percpu_thread(&vmbus_irq_threads);
+		vmbus_irq_initialized = false;
+	}
 	for_each_online_cpu(cpu) {
 		struct hv_per_cpu_context *hv_cpu
 			= per_cpu_ptr(hv_context.cpu_context, cpu);
-- 
2.47.3