Merge tag 'stable/for-linus-3.10-rc0-tag-two' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen

Pull Xen bug-fixes from Konrad Rzeszutek Wilk:
 - More fixes in the vCPU PVHVM hotplug path.
 - Add more documentation.
 - Fix various ARM related issues in the Xen generic drivers.
 - Updates in the xen-pciback driver per Bjorn's updates.
 - Mask the x2APIC feature for PV guests.

* tag 'stable/for-linus-3.10-rc0-tag-two' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen:
  xen/pci: Used cached MSI-X capability offset
  xen/pci: Use PCI_MSIX_TABLE_BIR, not PCI_MSIX_FLAGS_BIRMASK
  xen: clear IRQ_NOAUTOEN and IRQ_NOREQUEST
  xen: mask x2APIC feature in PV
  xen: SWIOTLB is only used on x86
  xen/spinlock: Fix check from greater than to be also be greater or equal to.
  xen/smp/pvhvm: Don't point per_cpu(xen_vpcu, 33 and larger) to shared_info
  xen/vcpu: Document the xen_vcpu_info and xen_vcpu
  xen/vcpu/pvhvm: Fix vcpu hotplugging hanging.

3 files changed, 52 insertions, 5 deletions

diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
index 4a9be6ddf054..48e8461057ba 100644
--- a/arch/x86/pci/xen.c
+++ b/arch/x86/pci/xen.c
@@ -295,11 +295,10 @@ static int xen_initdom_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
                         int pos;
                         u32 table_offset, bir;
 
-                        pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-
+                        pos = dev->msix_cap;
                         pci_read_config_dword(dev, pos + PCI_MSIX_TABLE,
                                               &table_offset);
-                        bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
+                        bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR);
 
                         map_irq.table_base = pci_resource_start(dev, bir);
                         map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 53d4f680c9b5..a492be2635ac 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -85,7 +85,29 @@
 
 EXPORT_SYMBOL_GPL(hypercall_page);
 
+/*
+ * Pointer to the xen_vcpu_info structure or
+ * &HYPERVISOR_shared_info->vcpu_info[cpu]. See xen_hvm_init_shared_info
+ * and xen_vcpu_setup for details. By default it points to share_info->vcpu_info
+ * but if the hypervisor supports VCPUOP_register_vcpu_info then it can point
+ * to xen_vcpu_info. The pointer is used in __xen_evtchn_do_upcall to
+ * acknowledge pending events.
+ * Also more subtly it is used by the patched version of irq enable/disable
+ * e.g. xen_irq_enable_direct and xen_iret in PV mode.
+ *
+ * The desire to be able to do those mask/unmask operations as a single
+ * instruction by using the per-cpu offset held in %gs is the real reason
+ * vcpu info is in a per-cpu pointer and the original reason for this
+ * hypercall.
+ *
+ */
 DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
+
+/*
+ * Per CPU pages used if hypervisor supports VCPUOP_register_vcpu_info
+ * hypercall. This can be used both in PV and PVHVM mode. The structure
+ * overrides the default per_cpu(xen_vcpu, cpu) value.
+ */
 DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
 
 enum xen_domain_type xen_domain_type = XEN_NATIVE;
@@ -157,6 +179,21 @@ static void xen_vcpu_setup(int cpu)
 
         BUG_ON(HYPERVISOR_shared_info == &xen_dummy_shared_info);
 
+        /*
+         * This path is called twice on PVHVM - first during bootup via
+         * smp_init -> xen_hvm_cpu_notify, and then if the VCPU is being
+         * hotplugged: cpu_up -> xen_hvm_cpu_notify.
+         * As we can only do the VCPUOP_register_vcpu_info once lets
+         * not over-write its result.
+         *
+         * For PV it is called during restore (xen_vcpu_restore) and bootup
+         * (xen_setup_vcpu_info_placement). The hotplug mechanism does not
+         * use this function.
+         */
+        if (xen_hvm_domain()) {
+                if (per_cpu(xen_vcpu, cpu) == &per_cpu(xen_vcpu_info, cpu))
+                        return;
+        }
         if (cpu < MAX_VIRT_CPUS)
                 per_cpu(xen_vcpu,cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
 
@@ -172,7 +209,12 @@ static void xen_vcpu_setup(int cpu)
 
         /* Check to see if the hypervisor will put the vcpu_info
            structure where we want it, which allows direct access via
-           a percpu-variable. */
+           a percpu-variable.
+           N.B. This hypercall can _only_ be called once per CPU. Subsequent
+           calls will error out with -EINVAL. This is due to the fact that
+           hypervisor has no unregister variant and this hypercall does not
+           allow to over-write info.mfn and info.offset.
+         */
         err = HYPERVISOR_vcpu_op(VCPUOP_register_vcpu_info, cpu, &info);
 
         if (err) {
@@ -387,6 +429,9 @@ static void __init xen_init_cpuid_mask(void)
                 cpuid_leaf1_edx_mask &=
                         ~((1 << X86_FEATURE_APIC) |  /* disable local APIC */
                           (1 << X86_FEATURE_ACPI));  /* disable ACPI */
+
+        cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_X2APIC % 32));
+
         ax = 1;
         cx = 0;
         xen_cpuid(&ax, &bx, &cx, &dx);
@@ -1603,6 +1648,9 @@ void __ref xen_hvm_init_shared_info(void)
          * online but xen_hvm_init_shared_info is run at resume time too and
          * in that case multiple vcpus might be online. */
         for_each_online_cpu(cpu) {
+                /* Leave it to be NULL. */
+                if (cpu >= MAX_VIRT_CPUS)
+                        continue;
                 per_cpu(xen_vcpu, cpu) = &HYPERVISOR_shared_info->vcpu_info[cpu];
         }
 }
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 8b54603ce816..3002ec1bb71a 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -364,7 +364,7 @@ void __cpuinit xen_init_lock_cpu(int cpu)
         int irq;
         const char *name;
 
-        WARN(per_cpu(lock_kicker_irq, cpu) > 0, "spinlock on CPU%d exists on IRQ%d!\n",
+        WARN(per_cpu(lock_kicker_irq, cpu) >= 0, "spinlock on CPU%d exists on IRQ%d!\n",
              cpu, per_cpu(lock_kicker_irq, cpu));
 
         /*