Merge tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights include
  - full big real mode emulation on pre-Westmere Intel hosts (can be
    disabled with emulate_invalid_guest_state=0)
  - relatively small ppc and s390 updates
  - PCID/INVPCID support in guests
  - EOI avoidance; 3.6 guests should perform better on 3.6 hosts on
    interrupt intensive workloads)
  - Lockless write faults during live migration
  - EPT accessed/dirty bits support for new Intel processors"

Fix up conflicts in:
 - Documentation/virtual/kvm/api.txt:

   Stupid subchapter numbering, added next to each other.

 - arch/powerpc/kvm/booke_interrupts.S:

   PPC asm changes clashing with the KVM fixes

 - arch/s390/include/asm/sigp.h, arch/s390/kvm/sigp.c:

   Duplicated commits through the kvm tree and the s390 tree, with
   subsequent edits in the KVM tree.

* tag 'kvm-3.6-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (93 commits)
  KVM: fix race with level interrupts
  x86, hyper: fix build with !CONFIG_KVM_GUEST
  Revert "apic: fix kvm build on UP without IOAPIC"
  KVM guest: switch to apic_set_eoi_write, apic_write
  apic: add apic_set_eoi_write for PV use
  KVM: VMX: Implement PCID/INVPCID for guests with EPT
  KVM: Add x86_hyper_kvm to complete detect_hypervisor_platform check
  KVM: PPC: Critical interrupt emulation support
  KVM: PPC: e500mc: Fix tlbilx emulation for 64-bit guests
  KVM: PPC64: booke: Set interrupt computation mode for 64-bit host
  KVM: PPC: bookehv: Add ESR flag to Data Storage Interrupt
  KVM: PPC: bookehv64: Add support for std/ld emulation.
  booke: Added crit/mc exception handler for e500v2
  booke/bookehv: Add host crit-watchdog exception support
  KVM: MMU: document mmu-lock and fast page fault
  KVM: MMU: fix kvm_mmu_pagetable_walk tracepoint
  KVM: MMU: trace fast page fault
  KVM: MMU: fast path of handling guest page fault
  KVM: MMU: introduce SPTE_MMU_WRITEABLE bit
  KVM: MMU: fold tlb flush judgement into mmu_spte_update
  ...

4 files changed, 47 insertions, 43 deletions

diff --git a/virt/kvm/ioapic.c b/virt/kvm/ioapic.c
index 26fd54dc459e..ef61d529a6c4 100644
--- a/virt/kvm/ioapic.c
+++ b/virt/kvm/ioapic.c
@@ -191,7 +191,8 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
         return kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe);
 }
 
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+                       int level)
 {
         u32 old_irr;
         u32 mask = 1 << irq;
@@ -201,9 +202,11 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
         spin_lock(&ioapic->lock);
         old_irr = ioapic->irr;
         if (irq >= 0 && irq < IOAPIC_NUM_PINS) {
+                int irq_level = __kvm_irq_line_state(&ioapic->irq_states[irq],
+                                                     irq_source_id, level);
                 entry = ioapic->redirtbl[irq];
-                level ^= entry.fields.polarity;
-                if (!level)
+                irq_level ^= entry.fields.polarity;
+                if (!irq_level)
                         ioapic->irr &= ~mask;
                 else {
                         int edge = (entry.fields.trig_mode == IOAPIC_EDGE_TRIG);
@@ -221,6 +224,16 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level)
         return ret;
 }
 
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
+{
+        int i;
+
+        spin_lock(&ioapic->lock);
+        for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
+                __clear_bit(irq_source_id, &ioapic->irq_states[i]);
+        spin_unlock(&ioapic->lock);
+}
+
 static void __kvm_ioapic_update_eoi(struct kvm_ioapic *ioapic, int vector,
                                      int trigger_mode)
 {
diff --git a/virt/kvm/ioapic.h b/virt/kvm/ioapic.h
index 32872a09b63f..a30abfe6ed16 100644
--- a/virt/kvm/ioapic.h
+++ b/virt/kvm/ioapic.h
@@ -74,7 +74,9 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode);
 bool kvm_ioapic_handles_vector(struct kvm *kvm, int vector);
 int kvm_ioapic_init(struct kvm *kvm);
 void kvm_ioapic_destroy(struct kvm *kvm);
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int level);
+int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
+                       int level);
+void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic);
 int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
                 struct kvm_lapic_irq *irq);
diff --git a/virt/kvm/irq_comm.c b/virt/kvm/irq_comm.c
index 5afb43114020..83402d74a767 100644
--- a/virt/kvm/irq_comm.c
+++ b/virt/kvm/irq_comm.c
@@ -33,26 +33,12 @@
 
 #include "ioapic.h"
 
-static inline int kvm_irq_line_state(unsigned long *irq_state,
-                                     int irq_source_id, int level)
-{
-        /* Logical OR for level trig interrupt */
-        if (level)
-                set_bit(irq_source_id, irq_state);
-        else
-                clear_bit(irq_source_id, irq_state);
-
-        return !!(*irq_state);
-}
-
 static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
                            struct kvm *kvm, int irq_source_id, int level)
 {
 #ifdef CONFIG_X86
         struct kvm_pic *pic = pic_irqchip(kvm);
-        level = kvm_irq_line_state(&pic->irq_states[e->irqchip.pin],
-                                   irq_source_id, level);
-        return kvm_pic_set_irq(pic, e->irqchip.pin, level);
+        return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
 #else
         return -1;
 #endif
@@ -62,10 +48,7 @@ static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
                               struct kvm *kvm, int irq_source_id, int level)
 {
         struct kvm_ioapic *ioapic = kvm->arch.vioapic;
-        level = kvm_irq_line_state(&ioapic->irq_states[e->irqchip.pin],
-                                   irq_source_id, level);
-
-        return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, level);
+        return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level);
 }
 
 inline static bool kvm_is_dm_lowest_prio(struct kvm_lapic_irq *irq)
@@ -249,8 +232,6 @@ unlock:
 
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 {
-        int i;
-
         ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 
         mutex_lock(&kvm->irq_lock);
@@ -263,14 +244,10 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
         if (!irqchip_in_kernel(kvm))
                 goto unlock;
 
-        for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++) {
-                clear_bit(irq_source_id, &kvm->arch.vioapic->irq_states[i]);
-                if (i >= 16)
-                        continue;
+        kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
 #ifdef CONFIG_X86
-                clear_bit(irq_source_id, &pic_irqchip(kvm)->irq_states[i]);
+        kvm_pic_clear_all(pic_irqchip(kvm), irq_source_id);
 #endif
-        }
 unlock:
         mutex_unlock(&kvm->irq_lock);
 }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 44ee7124b16d..246852397e30 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -516,16 +516,32 @@ out_err_nodisable:
         return ERR_PTR(r);
 }
 
+/*
+ * Avoid using vmalloc for a small buffer.
+ * Should not be used when the size is statically known.
+ */
+void *kvm_kvzalloc(unsigned long size)
+{
+        if (size > PAGE_SIZE)
+                return vzalloc(size);
+        else
+                return kzalloc(size, GFP_KERNEL);
+}
+
+void kvm_kvfree(const void *addr)
+{
+        if (is_vmalloc_addr(addr))
+                vfree(addr);
+        else
+                kfree(addr);
+}
+
 static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 {
         if (!memslot->dirty_bitmap)
                 return;
 
-        if (2 * kvm_dirty_bitmap_bytes(memslot) > PAGE_SIZE)
-                vfree(memslot->dirty_bitmap);
-        else
-                kfree(memslot->dirty_bitmap);
-
+        kvm_kvfree(memslot->dirty_bitmap);
         memslot->dirty_bitmap = NULL;
 }
 
@@ -617,11 +633,7 @@ static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot)
 #ifndef CONFIG_S390
         unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
 
-        if (dirty_bytes > PAGE_SIZE)
-                memslot->dirty_bitmap = vzalloc(dirty_bytes);
-        else
-                memslot->dirty_bitmap = kzalloc(dirty_bytes, GFP_KERNEL);
-
+        memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes);
         if (!memslot->dirty_bitmap)
                 return -ENOMEM;
 
@@ -1586,7 +1598,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
          */
         for (pass = 0; pass < 2 && !yielded; pass++) {
                 kvm_for_each_vcpu(i, vcpu, kvm) {
-                        if (!pass && i < last_boosted_vcpu) {
+                        if (!pass && i <= last_boosted_vcpu) {
                                 i = last_boosted_vcpu;
                                 continue;
                         } else if (pass && i > last_boosted_vcpu)
@@ -2213,7 +2225,7 @@ static long kvm_dev_ioctl_check_extension_generic(long arg)
         case KVM_CAP_SIGNAL_MSI:
 #endif
                 return 1;
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
+#ifdef KVM_CAP_IRQ_ROUTING
         case KVM_CAP_IRQ_ROUTING:
                 return KVM_MAX_IRQ_ROUTES;
 #endif