[PATCH] x86: mshyperv: Use kthread for vmbus interrupts on PREEMPT_RT

[Jan Kiszka <jan.kiszka@siemens.com>]

From: Jan Kiszka <jan.kiszka@siemens.com>

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 complete vmbus_handler 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.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---

This should resolve what was once brought forward via [1]. If it 
actually resolves all remaining compatibility issues of the hyperv 
support with RT is not yet clear, though. So far, lockdep is happy when 
using this plus [2].

[1] https://lore.kernel.org/all/20230809-b4-rt_preempt-fix-v1-0-7283bbdc8b14@gmail.com/
[2] https://lore.kernel.org/lkml/0c7fb5cd-fb21-4760-8593-e04bade84744@siemens.com/

 arch/x86/kernel/cpu/mshyperv.c | 52 ++++++++++++++++++++++++++++++++--
 1 file changed, 50 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 579fb2c64cfd..1194ca452c52 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
 #include <linux/irq.h>
 #include <linux/kexec.h>
 #include <linux/random.h>
+#include <linux/smpboot.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <hyperv/hvhdk.h>
@@ -150,6 +151,43 @@ static void (*hv_stimer0_handler)(void);
 static void (*hv_kexec_handler)(void);
 static void (*hv_crash_handler)(struct pt_regs *regs);
 
+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)
+{
+	vmbus_handler();
+	__this_cpu_write(vmbus_irq_pending, false);
+}
+
+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",
+};
+
 DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
@@ -158,8 +196,12 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_hyperv_callback)
 	if (mshv_handler)
 		mshv_handler();
 
-	if (vmbus_handler)
-		vmbus_handler();
+	if (vmbus_handler) {
+		if (IS_ENABLED(CONFIG_PREEMPT_RT))
+			vmbus_irqd_wake();
+		else
+			vmbus_handler();
+	}
 
 	if (ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED)
 		apic_eoi();
@@ -174,6 +216,10 @@ void hv_setup_mshv_handler(void (*handler)(void))
 
 void hv_setup_vmbus_handler(void (*handler)(void))
 {
+	if (IS_ENABLED(CONFIG_PREEMPT_RT) && !vmbus_irq_initialized) {
+		BUG_ON(smpboot_register_percpu_thread(&vmbus_irq_threads));
+		vmbus_irq_initialized = true;
+	}
 	vmbus_handler = handler;
 }
 
@@ -181,6 +227,8 @@ void hv_remove_vmbus_handler(void)
 {
 	/* We have no way to deallocate the interrupt gate */
 	vmbus_handler = NULL;
+	smpboot_unregister_percpu_thread(&vmbus_irq_threads);
+	vmbus_irq_initialized = false;
 }
 
 /*
-- 
2.51.0