References: bsc#1214718

# Commit e2bb28d621584fce15c907002ddc7c6772644b64
# Date 2024-06-20 12:09:32 +0200
# Author Roger Pau Monné <roger.pau@citrix.com>
# Committer Jan Beulich <jbeulich@suse.com>
x86/irq: forward pending interrupts to new destination in fixup_irqs()

fixup_irqs() is used to evacuate interrupts from to be offlined CPUs.  Given
the CPU is to become offline, the normal migration logic used by Xen where the
vector in the previous target(s) is left configured until the interrupt is
received on the new destination is not suitable.

Instead attempt to do as much as possible in order to prevent loosing
interrupts.  If fixup_irqs() is called from the CPU to be offlined (as is
currently the case for CPU hot unplug) attempt to forward pending vectors when
interrupts that target the current CPU are migrated to a different destination.

Additionally, for interrupts that have already been moved from the current CPU
prior to the call to fixup_irqs() but that haven't been delivered to the new
destination (iow: interrupts with move_in_progress set and the current CPU set
in ->arch.old_cpu_mask) also check whether the previous vector is pending and
forward it to the new destination.

This allows us to remove the window with interrupts enabled at the bottom of
fixup_irqs().  Such window wasn't safe anyway: references to the CPU to become
offline are removed from interrupts masks, but the per-CPU vector_irq[] array
is not updated to reflect those changes (as the CPU is going offline anyway).

Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

--- a/xen/arch/x86/include/asm/apic.h
+++ b/xen/arch/x86/include/asm/apic.h
@@ -145,6 +145,11 @@ static __inline bool_t apic_isr_read(u8
             (vector & 0x1f)) & 1;
 }
 
+static inline bool apic_irr_read(unsigned int vector)
+{
+    return apic_read(APIC_IRR + (vector / 32 * 0x10)) & (1U << (vector % 32));
+}
+
 static __inline u32 get_apic_id(void) /* Get the physical APIC id */
 {
     u32 id = apic_read(APIC_ID);
--- a/xen/arch/x86/irq.c
+++ b/xen/arch/x86/irq.c
@@ -2604,7 +2604,7 @@ void fixup_irqs(const cpumask_t *mask, b
 
     for ( irq = 0; irq < nr_irqs; irq++ )
     {
-        bool break_affinity = false, set_affinity = true;
+        bool break_affinity = false, set_affinity = true, check_irr = false;
         unsigned int vector, cpu = smp_processor_id();
         cpumask_t *affinity = this_cpu(scratch_cpumask);
 
@@ -2658,6 +2658,25 @@ void fixup_irqs(const cpumask_t *mask, b
              cpumask_test_cpu(cpu, desc->arch.old_cpu_mask) )
         {
             /*
+             * This to be offlined CPU was the target of an interrupt that's
+             * been moved, and the new destination target hasn't yet
+             * acknowledged any interrupt from it.
+             *
+             * We know the interrupt is configured to target the new CPU at
+             * this point, so we can check IRR for any pending vectors and
+             * forward them to the new destination.
+             *
+             * Note that for the other case of an interrupt movement being in
+             * progress (move_cleanup_count being non-zero) we know the new
+             * destination has already acked at least one interrupt from this
+             * source, and hence there's no need to forward any stale
+             * interrupts.
+             */
+            if ( apic_irr_read(desc->arch.old_vector) )
+                send_IPI_mask(cpumask_of(cpumask_any(desc->arch.cpu_mask)),
+                              desc->arch.vector);
+
+            /*
              * This CPU is going offline, remove it from ->arch.old_cpu_mask
              * and possibly release the old vector if the old mask becomes
              * empty.
@@ -2697,6 +2716,14 @@ void fixup_irqs(const cpumask_t *mask, b
         if ( desc->handler->disable )
             desc->handler->disable(desc);
 
+        /*
+         * If the current CPU is going offline and is (one of) the target(s) of
+         * the interrupt, signal to check whether there are any pending vectors
+         * to be handled in the local APIC after the interrupt has been moved.
+         */
+        if ( !cpu_online(cpu) && cpumask_test_cpu(cpu, desc->arch.cpu_mask) )
+            check_irr = true;
+
         if ( desc->handler->set_affinity )
             desc->handler->set_affinity(desc, affinity);
         else if ( !(warned++) )
@@ -2707,6 +2734,18 @@ void fixup_irqs(const cpumask_t *mask, b
 
         cpumask_copy(affinity, desc->affinity);
 
+        if ( check_irr && apic_irr_read(vector) )
+            /*
+             * Forward pending interrupt to the new destination, this CPU is
+             * going offline and otherwise the interrupt would be lost.
+             *
+             * Do the IRR check as late as possible before releasing the irq
+             * desc in order for any in-flight interrupts to be delivered to
+             * the lapic.
+             */
+            send_IPI_mask(cpumask_of(cpumask_any(desc->arch.cpu_mask)),
+                          desc->arch.vector);
+
         spin_unlock(&desc->lock);
 
         if ( !verbose )
@@ -2718,11 +2757,6 @@ void fixup_irqs(const cpumask_t *mask, b
             printk("Broke affinity for IRQ%u, new: %*pb\n",
                    irq, CPUMASK_PR(affinity));
     }
-
-    /* That doesn't seem sufficient.  Give it 1ms. */
-    local_irq_enable();
-    mdelay(1);
-    local_irq_disable();
 }
 
 void fixup_eoi(void)