[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[PATCH v3 for-4.21 3/9] x86/HPET: replace handle_hpet_broadcast()'s on-stack cpumask_t


  • To: "xen-devel@xxxxxxxxxxxxxxxxxxxx" <xen-devel@xxxxxxxxxxxxxxxxxxxx>
  • From: Jan Beulich <jbeulich@xxxxxxxx>
  • Date: Thu, 23 Oct 2025 17:51:06 +0200
  • Autocrypt: addr=jbeulich@xxxxxxxx; keydata= xsDiBFk3nEQRBADAEaSw6zC/EJkiwGPXbWtPxl2xCdSoeepS07jW8UgcHNurfHvUzogEq5xk hu507c3BarVjyWCJOylMNR98Yd8VqD9UfmX0Hb8/BrA+Hl6/DB/eqGptrf4BSRwcZQM32aZK 7Pj2XbGWIUrZrd70x1eAP9QE3P79Y2oLrsCgbZJfEwCgvz9JjGmQqQkRiTVzlZVCJYcyGGsD /0tbFCzD2h20ahe8rC1gbb3K3qk+LpBtvjBu1RY9drYk0NymiGbJWZgab6t1jM7sk2vuf0Py O9Hf9XBmK0uE9IgMaiCpc32XV9oASz6UJebwkX+zF2jG5I1BfnO9g7KlotcA/v5ClMjgo6Gl MDY4HxoSRu3i1cqqSDtVlt+AOVBJBACrZcnHAUSuCXBPy0jOlBhxPqRWv6ND4c9PH1xjQ3NP nxJuMBS8rnNg22uyfAgmBKNLpLgAGVRMZGaGoJObGf72s6TeIqKJo/LtggAS9qAUiuKVnygo 3wjfkS9A3DRO+SpU7JqWdsveeIQyeyEJ/8PTowmSQLakF+3fote9ybzd880fSmFuIEJldWxp Y2ggPGpiZXVsaWNoQHN1c2UuY29tPsJgBBMRAgAgBQJZN5xEAhsDBgsJCAcDAgQVAggDBBYC AwECHgECF4AACgkQoDSui/t3IH4J+wCfQ5jHdEjCRHj23O/5ttg9r9OIruwAn3103WUITZee e7Sbg12UgcQ5lv7SzsFNBFk3nEQQCACCuTjCjFOUdi5Nm244F+78kLghRcin/awv+IrTcIWF hUpSs1Y91iQQ7KItirz5uwCPlwejSJDQJLIS+QtJHaXDXeV6NI0Uef1hP20+y8qydDiVkv6l IreXjTb7DvksRgJNvCkWtYnlS3mYvQ9NzS9PhyALWbXnH6sIJd2O9lKS1Mrfq+y0IXCP10eS FFGg+Av3IQeFatkJAyju0PPthyTqxSI4lZYuJVPknzgaeuJv/2NccrPvmeDg6Coe7ZIeQ8Yj t0ARxu2xytAkkLCel1Lz1WLmwLstV30g80nkgZf/wr+/BXJW/oIvRlonUkxv+IbBM3dX2OV8 AmRv1ySWPTP7AAMFB/9PQK/VtlNUJvg8GXj9ootzrteGfVZVVT4XBJkfwBcpC/XcPzldjv+3 HYudvpdNK3lLujXeA5fLOH+Z/G9WBc5pFVSMocI71I8bT8lIAzreg0WvkWg5V2WZsUMlnDL9 mpwIGFhlbM3gfDMs7MPMu8YQRFVdUvtSpaAs8OFfGQ0ia3LGZcjA6Ik2+xcqscEJzNH+qh8V m5jjp28yZgaqTaRbg3M/+MTbMpicpZuqF4rnB0AQD12/3BNWDR6bmh+EkYSMcEIpQmBM51qM EKYTQGybRCjpnKHGOxG0rfFY1085mBDZCH5Kx0cl0HVJuQKC+dV2ZY5AqjcKwAxpE75MLFkr wkkEGBECAAkFAlk3nEQCGwwACgkQoDSui/t3IH7nnwCfcJWUDUFKdCsBH/E5d+0ZnMQi+G0A nAuWpQkjM1ASeQwSHEeAWPgskBQL
  • Cc: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>, Roger Pau Monné <roger.pau@xxxxxxxxxx>, Oleksii Kurochko <oleksii.kurochko@xxxxxxxxx>
  • Delivery-date: Thu, 23 Oct 2025 15:51:13 +0000
  • List-id: Xen developer discussion <xen-devel.lists.xenproject.org>

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>
---
While doing this I noticed that this and all pre-existing uses of
DEFINE_PER_CPU_READ_MOSTLY() aren't quite right: When the type is
cpumask_var_t, the variable is read-mostly only when NR_CPUS <=
2 * BITS_PER_LONG. That'll want sorting separately, though.

It is important for this to not be moved ahead of "x86/HPET: use single,
global, low-priority vector for broadcast IRQ", as the original call here
from set_channel_irq_affinity() may not use the new variable (it would
need to use scratch_cpumask instead).
---
v2: New.

--- a/xen/arch/x86/hpet.c
+++ b/xen/arch/x86/hpet.c
@@ -196,7 +196,7 @@ static void evt_do_broadcast(cpumask_t *
 
 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 )
     {
--- 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);
 
 /*
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -55,6 +55,9 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t
 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;
 
@@ -976,6 +979,8 @@ static void cpu_smpboot_free(unsigned in
         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));
     }
@@ -1112,6 +1117,7 @@ static int cpu_smpboot_alloc(unsigned in
     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;
 
@@ -1239,6 +1245,7 @@ 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
 




 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.