[Xen-devel] [PATCH v2] x86/vpmu: add cpu hot unplug notifier for vpmu

[Luwei Kang <luwei.kang@xxxxxxxxx>]

Currently, Hot unplug a physical CPU with vpmu enabled may cause
system hang due to send a remote call to an offlined pCPU. This
patch add a cpu hot unplug notifer to save vpmu context before
cpu offline.

Consider one scenario, hot unplug pCPU N with vpmu enabled.
The vcpu which running on this pCPU will be switch to other
online cpu. A remote call will be send to pCPU N to save the 
vpmu context before loading the vpmu context on this pCPU.
System will hang in function on_select_cpus() because of that pCPU
is offlined and can not do any respond.

Signed-off-by: Luwei Kang <luwei.kang@xxxxxxxxx>
---
v2:
 1.fix some typo and coding style;
 2.change "swith" to "if" in cpu_callback() because of there just have one case;
 3.add VPMU_CONTEX_LOADED check before send remote call in vpmu_arch_destroy();
---
 xen/arch/x86/cpu/vpmu.c | 42 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 39 insertions(+), 3 deletions(-)

diff --git a/xen/arch/x86/cpu/vpmu.c b/xen/arch/x86/cpu/vpmu.c
index 03401fd..57a0e9d 100644
--- a/xen/arch/x86/cpu/vpmu.c
+++ b/xen/arch/x86/cpu/vpmu.c
@@ -21,6 +21,7 @@
 #include <xen/xenoprof.h>
 #include <xen/event.h>
 #include <xen/guest_access.h>
+#include <xen/cpu.h>
 #include <asm/regs.h>
 #include <asm/types.h>
 #include <asm/msr.h>
@@ -581,9 +582,14 @@ static void vpmu_arch_destroy(struct vcpu *v)
 
     if ( vpmu->arch_vpmu_ops && vpmu->arch_vpmu_ops->arch_vpmu_destroy )
     {
-        /* Unload VPMU first. This will stop counters */
-        on_selected_cpus(cpumask_of(vcpu_vpmu(v)->last_pcpu),
-                         vpmu_save_force, v, 1);
+        /*
+         * Unload VPMU first if VPMU_CONTEXT_LOADED being set.
+         * This will stop counters.
+         */
+        if ( vpmu_is_set(vpmu, VPMU_CONTEXT_LOADED) )
+            on_selected_cpus(cpumask_of(vcpu_vpmu(v)->last_pcpu),
+                             vpmu_save_force, v, 1);
+
          vpmu->arch_vpmu_ops->arch_vpmu_destroy(v);
     }
 }
@@ -835,6 +841,33 @@ long do_xenpmu_op(unsigned int op, 
XEN_GUEST_HANDLE_PARAM(xen_pmu_params_t) arg)
     return ret;
 }
 
+static int cpu_callback(
+    struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+    unsigned int cpu = (unsigned long)hcpu;
+    struct vcpu *vcpu = per_cpu(last_vcpu, cpu);
+    struct vpmu_struct *vpmu;
+
+    if ( !vcpu )
+        return NOTIFY_DONE;
+
+    vpmu = vcpu_vpmu(vcpu);
+    if ( !vpmu_is_set(vpmu, VPMU_CONTEXT_ALLOCATED) )
+        return NOTIFY_DONE;
+
+    if ( action == CPU_DYING )
+    {
+        vpmu_save_force(vcpu);
+        vpmu_reset(vpmu, VPMU_CONTEXT_LOADED);
+    }
+
+    return NOTIFY_DONE;
+}
+
+static struct notifier_block vpmu_cpu_nfb = {
+    .notifier_call = cpu_callback
+};
+
 static int __init vpmu_init(void)
 {
     int vendor = current_cpu_data.x86_vendor;
@@ -872,8 +905,11 @@ static int __init vpmu_init(void)
     }
 
     if ( vpmu_mode != XENPMU_MODE_OFF )
+    {
+        register_cpu_notifier(&vpmu_cpu_nfb);
         printk(XENLOG_INFO "VPMU: version " __stringify(XENPMU_VER_MAJ) "."
                __stringify(XENPMU_VER_MIN) "\n");
+    }
     else
         opt_vpmu_enabled = 0;
 
-- 
1.8.3.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
https://lists.xen.org/xen-devel