xen-devel.lists.xenproject.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] relax vCPU pinned checks
@ 2011-01-05  9:01 Jan Beulich
  0 siblings, 0 replies; only message in thread
From: Jan Beulich @ 2011-01-05  9:01 UTC (permalink / raw)
  To: xen-devel@lists.xensource.com

[-- Attachment #1: Type: text/plain, Size: 1614 bytes --]

Both writing of certain MSRs and VCPUOP_get_physid make sense also for
dynamically (perhaps temporarily) pinned vcpus.

Likely a couple of other MSR writes (MSR_K8_HWCR, MSR_AMD64_NB_CFG,
MSR_FAM10H_MMIO_CONF_BASE) would make sense to be restricted by an
is_pinned() check too, possibly also some MSR reads.

Signed-off-by: Jan Beulich <jbeulich@novell.com>

--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1036,7 +1036,7 @@ arch_do_vcpu_op(
         struct vcpu_get_physid cpu_id;
 
         rc = -EINVAL;
-        if ( !v->domain->is_pinned )
+        if ( !is_pinned(v) )
             break;
 
         cpu_id.phys_id =
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -2335,7 +2335,7 @@ static int emulate_privileged_op(struct 
         case MSR_IA32_THERM_CONTROL:
             if ( boot_cpu_data.x86_vendor != X86_VENDOR_INTEL )
                 goto fail;
-            if ( (v->domain->domain_id != 0) || !v->domain->is_pinned )
+            if ( (v->domain->domain_id != 0) || !is_pinned(v) )
                 break;
             if ( wrmsr_safe(regs->ecx, msr_content) != 0 )
                 goto fail;
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -634,6 +634,8 @@ void watchdog_domain_destroy(struct doma
 
 #define is_hvm_domain(d) ((d)->is_hvm)
 #define is_hvm_vcpu(v)   (is_hvm_domain(v->domain))
+#define is_pinned(v)     ((v)->domain->is_pinned || \
+                          cpus_weight((v)->cpu_affinity) == 1)
 #define need_iommu(d)    ((d)->need_iommu)
 
 void set_vcpu_migration_delay(unsigned int delay);




[-- Attachment #2: relax-pinned-checks.patch --]
[-- Type: text/plain, Size: 1608 bytes --]

Both writing of certain MSRs and VCPUOP_get_physid make sense also for
dynamically (perhaps temporarily) pinned vcpus.

Likely a couple of other MSR writes (MSR_K8_HWCR, MSR_AMD64_NB_CFG,
MSR_FAM10H_MMIO_CONF_BASE) would make sense to be restricted by an
is_pinned() check too, possibly also some MSR reads.

Signed-off-by: Jan Beulich <jbeulich@novell.com>

--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -1036,7 +1036,7 @@ arch_do_vcpu_op(
         struct vcpu_get_physid cpu_id;
 
         rc = -EINVAL;
-        if ( !v->domain->is_pinned )
+        if ( !is_pinned(v) )
             break;
 
         cpu_id.phys_id =
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -2335,7 +2335,7 @@ static int emulate_privileged_op(struct 
         case MSR_IA32_THERM_CONTROL:
             if ( boot_cpu_data.x86_vendor != X86_VENDOR_INTEL )
                 goto fail;
-            if ( (v->domain->domain_id != 0) || !v->domain->is_pinned )
+            if ( (v->domain->domain_id != 0) || !is_pinned(v) )
                 break;
             if ( wrmsr_safe(regs->ecx, msr_content) != 0 )
                 goto fail;
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -634,6 +634,8 @@ void watchdog_domain_destroy(struct doma
 
 #define is_hvm_domain(d) ((d)->is_hvm)
 #define is_hvm_vcpu(v)   (is_hvm_domain(v->domain))
+#define is_pinned(v)     ((v)->domain->is_pinned || \
+                          cpus_weight((v)->cpu_affinity) == 1)
 #define need_iommu(d)    ((d)->need_iommu)
 
 void set_vcpu_migration_delay(unsigned int delay);

[-- Attachment #3: Type: text/plain, Size: 138 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel

^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2011-01-05  9:01 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2011-01-05  9:01 [PATCH] relax vCPU pinned checks Jan Beulich

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).