[Xen-devel] [PATCH v3 4/5] x86/smp: use a dedicated scratch cpumask in send_IPI_mask

[Roger Pau Monne <roger.pau@xxxxxxxxxx>]

Using scratch_cpumask in send_IPI_mask is not safe because it can be
called from interrupt context, and hence Xen would have to make sure
all the users of the scratch cpumask disable interrupts while using
it.

Instead introduce a new cpumask to be used by send_IPI_mask, and
disable interrupts while using it.

Note that such mask cannot be used when non-maskable interrupts are
being serviced (#NMI or #MC) and hence fallback to not using the
shorthand in that case, like it was done previously.

Fixes: 5500d265a2a8 ('x86/smp: use APIC ALLBUT destination shorthand when 
possible')
Reported-by: Sander Eikelenboom <linux@xxxxxxxxxxxxxx>
Signed-off-by: Roger Pau Monné <roger.pau@xxxxxxxxxx>
---
Changes since v2:
 - Fallback to the previous IPI sending mechanism in #MC or #NMI
   context.

Changes since v1:
 - Don't use the shorthand when in #MC or #NMI context.
---
 xen/arch/x86/smp.c     | 27 ++++++++++++++++++++++++++-
 xen/arch/x86/smpboot.c |  9 ++++++++-
 2 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/xen/arch/x86/smp.c b/xen/arch/x86/smp.c
index 55d08c9d52..53e0de2a70 100644
--- a/xen/arch/x86/smp.c
+++ b/xen/arch/x86/smp.c
@@ -59,6 +59,7 @@ static void send_IPI_shortcut(unsigned int shortcut, int 
vector,
     apic_write(APIC_ICR, cfg);
 }
 
+DECLARE_PER_CPU(cpumask_var_t, send_ipi_cpumask);
 /*
  * send_IPI_mask(cpumask, vector): sends @vector IPI to CPUs in @cpumask,
  * excluding the local CPU. @cpumask may be empty.
@@ -67,7 +68,21 @@ static void send_IPI_shortcut(unsigned int shortcut, int 
vector,
 void send_IPI_mask(const cpumask_t *mask, int vector)
 {
     bool cpus_locked = false;
-    cpumask_t *scratch = this_cpu(scratch_cpumask);
+    cpumask_t *scratch = this_cpu(send_ipi_cpumask);
+    unsigned long flags;
+
+    if ( in_mc() || in_nmi() )
+    {
+        /*
+         * When in #NMI or #MC context fallback to the old (and simpler) IPI
+         * sending routine, and avoid doing any performance optimizations (like
+         * using a shorthand). Sending an IPI from such contexts is likely a
+         * sign of a crash, and hence we would like to avoid as much complexity
+         * as possible in order to make sure the IPI is delivered.
+         */
+        alternative_vcall(genapic.send_IPI_mask, mask, vector);
+        return;
+    }
 
     /*
      * This can only be safely used when no CPU hotplug or unplug operations
@@ -81,7 +96,15 @@ void send_IPI_mask(const cpumask_t *mask, int vector)
          local_irq_is_enabled() && (cpus_locked = get_cpu_maps()) &&
          (park_offline_cpus ||
           cpumask_equal(&cpu_online_map, &cpu_present_map)) )
+    {
+        /*
+         * send_IPI_mask can be called from interrupt context, and hence we
+         * need to disable interrupts in order to protect the per-cpu
+         * send_ipi_cpumask while being used.
+         */
+        local_irq_save(flags);
         cpumask_or(scratch, mask, cpumask_of(smp_processor_id()));
+    }
     else
     {
         if ( cpus_locked )
@@ -89,6 +112,7 @@ void send_IPI_mask(const cpumask_t *mask, int vector)
             put_cpu_maps();
             cpus_locked = false;
         }
+        local_irq_save(flags);
         cpumask_clear(scratch);
     }
 
@@ -97,6 +121,7 @@ void send_IPI_mask(const cpumask_t *mask, int vector)
     else
         alternative_vcall(genapic.send_IPI_mask, mask, vector);
 
+    local_irq_restore(flags);
     if ( cpus_locked )
         put_cpu_maps();
 }
diff --git a/xen/arch/x86/smpboot.c b/xen/arch/x86/smpboot.c
index e83e4564a4..82e89201b3 100644
--- a/xen/arch/x86/smpboot.c
+++ b/xen/arch/x86/smpboot.c
@@ -57,6 +57,9 @@ 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, send_ipi_cpumask);
+static cpumask_t send_ipi_cpu0mask;
+
 cpumask_t cpu_online_map __read_mostly;
 EXPORT_SYMBOL(cpu_online_map);
 
@@ -930,6 +933,8 @@ 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(send_ipi_cpumask, cpu) != &send_ipi_cpu0mask )
+            FREE_CPUMASK_VAR(per_cpu(send_ipi_cpumask, cpu));
     }
 
     cleanup_cpu_root_pgt(cpu);
@@ -1034,7 +1039,8 @@ 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(scratch_cpumask, cpu)) &&
+           cond_alloc_cpumask_var(&per_cpu(send_ipi_cpumask, cpu))) )
         goto out;
 
     rc = 0;
@@ -1175,6 +1181,7 @@ 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(send_ipi_cpumask, cpu) = &send_ipi_cpu0mask;
 #endif
 
     get_cpu_info()->use_pv_cr3 = false;
-- 
2.25.0


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel