[xen stable-4.20] x86/HPET: replace handle_hpet_broadcast()'s on-stack cpumask_t

[patchbot@xxxxxxx]

commit 550d82d40b6f299d472bedaa0f8a1d1dd2e3234e
Author:     Jan Beulich <jbeulich@xxxxxxxx>
AuthorDate: Mon Nov 10 16:01:08 2025 +0100
Commit:     Jan Beulich <jbeulich@xxxxxxxx>
CommitDate: Mon Nov 10 16:01:08 2025 +0100

    x86/HPET: replace handle_hpet_broadcast()'s on-stack cpumask_t
    
    With large NR_CPUS on-stack cpumask_t variables are problematic. Now that
    the IRQ handler can't be invoked in a nested manner anymore, we can
    instead use a per-CPU variable. While we can't use scratch_cpumask in code
    invoked from IRQ handlers, simply amend that one with a HPET-special form.
    (Note that only one of the two IRQ handling functions can come into play
    at any one time.)
    
    Fixes: 996576b965cc ("xen: allow up to 16383 cpus")
    Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>
    Reviewed-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
    master commit: 80c7c6716476b009188271350a9fc04fa763362e
    master date: 2025-10-29 09:02:53 +0100
---
 xen/arch/x86/hpet.c            | 8 ++++----
 xen/arch/x86/include/asm/smp.h | 1 +
 xen/arch/x86/smpboot.c         | 7 +++++++
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/xen/arch/x86/hpet.c b/xen/arch/x86/hpet.c
index 8838e89944..fe714ca12c 100644
--- a/xen/arch/x86/hpet.c
+++ b/xen/arch/x86/hpet.c
@@ -196,7 +196,7 @@ static void evt_do_broadcast(cpumask_t *mask)
 
 static void cf_check handle_hpet_broadcast(struct hpet_event_channel *ch)
 {
-    cpumask_t mask;
+    cpumask_t *scratch = this_cpu(hpet_scratch_cpumask);
     s_time_t now, next_event;
     unsigned int cpu;
     unsigned long flags;
@@ -209,7 +209,7 @@ again:
     spin_unlock_irqrestore(&ch->lock, flags);
 
     next_event = STIME_MAX;
-    cpumask_clear(&mask);
+    cpumask_clear(scratch);
     now = NOW();
 
     /* find all expired events */
@@ -218,13 +218,13 @@ again:
         s_time_t deadline = ACCESS_ONCE(per_cpu(timer_deadline, cpu));
 
         if ( deadline <= now )
-            __cpumask_set_cpu(cpu, &mask);
+            __cpumask_set_cpu(cpu, scratch);
         else if ( deadline < next_event )
             next_event = deadline;
     }
 
     /* wakeup the cpus which have an expired event. */
-    evt_do_broadcast(&mask);
+    evt_do_broadcast(scratch);
 
     if ( next_event != STIME_MAX )
     {
diff --git a/xen/arch/x86/include/asm/smp.h b/xen/arch/x86/include/asm/smp.h
index c8c7960134..60eb4ac254 100644
--- a/xen/arch/x86/include/asm/smp.h
+++ b/xen/arch/x86/include/asm/smp.h
@@ -22,6 +22,7 @@
 DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_mask);
 DECLARE_PER_CPU(cpumask_var_t, cpu_core_mask);
 DECLARE_PER_CPU(cpumask_var_t, scratch_cpumask);
+DECLARE_PER_CPU(cpumask_var_t, hpet_scratch_cpumask);
 DECLARE_PER_CPU(cpumask_var_t, send_ipi_cpumask);
 
 /*
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index 348e0b9581..8742e30561 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -52,6 +52,9 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_mask);
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, scratch_cpumask);
 static cpumask_t scratch_cpu0mask;
 
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, hpet_scratch_cpumask);
+static cpumask_t hpet_scratch_cpu0mask;
+
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, send_ipi_cpumask);
 static cpumask_t send_ipi_cpu0mask;
 
@@ -989,6 +992,8 @@ static void cpu_smpboot_free(unsigned int cpu, bool remove)
         FREE_CPUMASK_VAR(per_cpu(cpu_core_mask, cpu));
         if ( per_cpu(scratch_cpumask, cpu) != &scratch_cpu0mask )
             FREE_CPUMASK_VAR(per_cpu(scratch_cpumask, cpu));
+        if ( per_cpu(hpet_scratch_cpumask, cpu) != &hpet_scratch_cpu0mask )
+            FREE_CPUMASK_VAR(per_cpu(hpet_scratch_cpumask, cpu));
         if ( per_cpu(send_ipi_cpumask, cpu) != &send_ipi_cpu0mask )
             FREE_CPUMASK_VAR(per_cpu(send_ipi_cpumask, cpu));
     }
@@ -1119,6 +1124,7 @@ static int cpu_smpboot_alloc(unsigned int cpu)
     if ( !(cond_zalloc_cpumask_var(&per_cpu(cpu_sibling_mask, cpu)) &&
            cond_zalloc_cpumask_var(&per_cpu(cpu_core_mask, cpu)) &&
            cond_alloc_cpumask_var(&per_cpu(scratch_cpumask, cpu)) &&
+           cond_alloc_cpumask_var(&per_cpu(hpet_scratch_cpumask, cpu)) &&
            cond_alloc_cpumask_var(&per_cpu(send_ipi_cpumask, cpu))) )
         goto out;
 
@@ -1246,6 +1252,7 @@ void __init smp_prepare_boot_cpu(void)
     cpumask_set_cpu(cpu, &cpu_present_map);
 #if NR_CPUS > 2 * BITS_PER_LONG
     per_cpu(scratch_cpumask, cpu) = &scratch_cpu0mask;
+    per_cpu(hpet_scratch_cpumask, cpu) = &hpet_scratch_cpu0mask;
     per_cpu(send_ipi_cpumask, cpu) = &send_ipi_cpu0mask;
 #endif
 
--
generated by git-patchbot for /home/xen/git/xen.git#stable-4.20