Merge branch 'mpi-master' into wip-k-fmlpwip-k-fmlp

Conflicts:
	litmus/sched_cedf.c

1 files changed, 150 insertions, 35 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c13cc48697aa..31ebb59cbd2f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -16,6 +16,8 @@
 #include <linux/mm.h>
 #include <linux/preempt.h>
 #include <linux/msi.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -25,6 +27,10 @@
 
 #include <asm/kvm_host.h>
 
+#ifndef KVM_MMIO_SIZE
+#define KVM_MMIO_SIZE 8
+#endif
+
 /*
  * vcpu->requests bit members
  */
@@ -36,9 +42,11 @@
 #define KVM_REQ_PENDING_TIMER      5
 #define KVM_REQ_UNHALT             6
 #define KVM_REQ_MMU_SYNC           7
-#define KVM_REQ_KVMCLOCK_UPDATE    8
+#define KVM_REQ_CLOCK_UPDATE       8
 #define KVM_REQ_KICK               9
 #define KVM_REQ_DEACTIVATE_FPU    10
+#define KVM_REQ_EVENT             11
+#define KVM_REQ_APF_HALT          12
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID     0
 
@@ -73,23 +81,52 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
                               struct kvm_io_device *dev);
 
+#ifdef CONFIG_KVM_ASYNC_PF
+struct kvm_async_pf {
+        struct work_struct work;
+        struct list_head link;
+        struct list_head queue;
+        struct kvm_vcpu *vcpu;
+        struct mm_struct *mm;
+        gva_t gva;
+        unsigned long addr;
+        struct kvm_arch_async_pf arch;
+        struct page *page;
+        bool done;
+};
+
+void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu);
+void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu);
+int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
+                       struct kvm_arch_async_pf *arch);
+int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
+#endif
+
+enum {
+        OUTSIDE_GUEST_MODE,
+        IN_GUEST_MODE,
+        EXITING_GUEST_MODE
+};
+
 struct kvm_vcpu {
         struct kvm *kvm;
 #ifdef CONFIG_PREEMPT_NOTIFIERS
         struct preempt_notifier preempt_notifier;
 #endif
+        int cpu;
         int vcpu_id;
-        struct mutex mutex;
-        int   cpu;
-        atomic_t guest_mode;
-        struct kvm_run *run;
+        int srcu_idx;
+        int mode;
         unsigned long requests;
         unsigned long guest_debug;
-        int srcu_idx;
+
+        struct mutex mutex;
+        struct kvm_run *run;
 
         int fpu_active;
         int guest_fpu_loaded, guest_xcr0_loaded;
         wait_queue_head_t wq;
+        struct pid *pid;
         int sigset_active;
         sigset_t sigset;
         struct kvm_vcpu_stat stat;
@@ -99,29 +136,47 @@ struct kvm_vcpu {
         int mmio_read_completed;
         int mmio_is_write;
         int mmio_size;
-        unsigned char mmio_data[8];
+        int mmio_index;
+        unsigned char mmio_data[KVM_MMIO_SIZE];
         gpa_t mmio_phys_addr;
 #endif
 
+#ifdef CONFIG_KVM_ASYNC_PF
+        struct {
+                u32 queued;
+                struct list_head queue;
+                struct list_head done;
+                spinlock_t lock;
+        } async_pf;
+#endif
+
         struct kvm_vcpu_arch arch;
 };
 
+static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
+{
+        return cmpxchg(&vcpu->mode, IN_GUEST_MODE, EXITING_GUEST_MODE);
+}
+
 /*
  * Some of the bitops functions do not support too long bitmaps.
  * This number must be determined not to exceed such limits.
  */
 #define KVM_MEM_MAX_NR_PAGES ((1UL << 31) - 1)
 
+struct kvm_lpage_info {
+        unsigned long rmap_pde;
+        int write_count;
+};
+
 struct kvm_memory_slot {
         gfn_t base_gfn;
         unsigned long npages;
         unsigned long flags;
         unsigned long *rmap;
         unsigned long *dirty_bitmap;
-        struct {
-                unsigned long rmap_pde;
-                int write_count;
-        } *lpage_info[KVM_NR_PAGE_SIZES - 1];
+        unsigned long *dirty_bitmap_head;
+        struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
         unsigned long userspace_addr;
         int user_alloc;
         int id;
@@ -168,13 +223,13 @@ struct kvm_irq_routing_table {};
 
 struct kvm_memslots {
         int nmemslots;
+        u64 generation;
         struct kvm_memory_slot memslots[KVM_MEMORY_SLOTS +
                                         KVM_PRIVATE_MEM_SLOTS];
 };
 
 struct kvm {
         spinlock_t mmu_lock;
-        raw_spinlock_t requests_lock;
         struct mutex slots_lock;
         struct mm_struct *mm; /* userspace tied to this vm */
         struct kvm_memslots *memslots;
@@ -185,6 +240,7 @@ struct kvm {
 #endif
         struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
         atomic_t online_vcpus;
+        int last_boosted_vcpu;
         struct list_head vm_list;
         struct mutex lock;
         struct kvm_io_bus *buses[KVM_NR_BUSES];
@@ -205,7 +261,11 @@ struct kvm {
 
         struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
-        struct kvm_irq_routing_table *irq_routing;
+        /*
+         * Update side is protected by irq_lock and,
+         * if configured, irqfds.lock.
+         */
+        struct kvm_irq_routing_table __rcu *irq_routing;
         struct hlist_head mask_notifier_list;
         struct hlist_head irq_ack_notifier_list;
 #endif
@@ -215,6 +275,7 @@ struct kvm {
         unsigned long mmu_notifier_seq;
         long mmu_notifier_count;
 #endif
+        long tlbs_dirty;
 };
 
 /* The guest did something we don't support. */
@@ -235,9 +296,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 }
 
 #define kvm_for_each_vcpu(idx, vcpup, kvm) \
-        for (idx = 0, vcpup = kvm_get_vcpu(kvm, idx); \
-             idx < atomic_read(&kvm->online_vcpus) && vcpup; \
-             vcpup = kvm_get_vcpu(kvm, ++idx))
+        for (idx = 0; \
+             idx < atomic_read(&kvm->online_vcpus) && \
+             (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \
+             idx++)
 
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
@@ -289,6 +351,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 void kvm_disable_largepages(void);
 void kvm_arch_flush_shadow(struct kvm *kvm);
 
+int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
+                            int nr_pages);
+
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 void kvm_release_page_clean(struct page *page);
@@ -296,10 +361,15 @@ void kvm_release_page_dirty(struct page *page);
 void kvm_set_page_dirty(struct page *page);
 void kvm_set_page_accessed(struct page *page);
 
+pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr);
+pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn);
+pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async,
+                       bool write_fault, bool *writable);
 pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
+pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
+                      bool *writable);
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
                          struct kvm_memory_slot *slot, gfn_t gfn);
-int memslot_id(struct kvm *kvm, gfn_t gfn);
 void kvm_release_pfn_dirty(pfn_t);
 void kvm_release_pfn_clean(pfn_t pfn);
 void kvm_set_pfn_dirty(pfn_t pfn);
@@ -315,18 +385,25 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data,
                          int offset, int len);
 int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
                     unsigned long len);
+int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+                           void *data, unsigned long len);
+int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+                              gpa_t gpa);
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
+void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot,
+                             gfn_t gfn);
 
 void kvm_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
+
 void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 
@@ -392,7 +469,19 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
-struct  kvm *kvm_arch_create_vm(void);
+#ifndef __KVM_HAVE_ARCH_VM_ALLOC
+static inline struct kvm *kvm_arch_alloc_vm(void)
+{
+        return kzalloc(sizeof(struct kvm), GFP_KERNEL);
+}
+
+static inline void kvm_arch_free_vm(struct kvm *kvm)
+{
+        kfree(kvm);
+}
+#endif
+
+int kvm_arch_init_vm(struct kvm *kvm);
 void kvm_arch_destroy_vm(struct kvm *kvm);
 void kvm_free_all_assigned_devices(struct kvm *kvm);
 void kvm_arch_sync_events(struct kvm *kvm);
@@ -408,16 +497,8 @@ struct kvm_irq_ack_notifier {
         void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
 };
 
-#define KVM_ASSIGNED_MSIX_PENDING               0x1
-struct kvm_guest_msix_entry {
-        u32 vector;
-        u16 entry;
-        u16 flags;
-};
-
 struct kvm_assigned_dev_kernel {
         struct kvm_irq_ack_notifier ack_notifier;
-        struct work_struct interrupt_work;
         struct list_head list;
         int assigned_dev_id;
         int host_segnr;
@@ -428,13 +509,15 @@ struct kvm_assigned_dev_kernel {
         bool host_irq_disabled;
         struct msix_entry *host_msix_entries;
         int guest_irq;
-        struct kvm_guest_msix_entry *guest_msix_entries;
+        struct msix_entry *guest_msix_entries;
         unsigned long irq_requested_type;
         int irq_source_id;
         int flags;
         struct pci_dev *dev;
         struct kvm *kvm;
-        spinlock_t assigned_dev_lock;
+        spinlock_t intx_lock;
+        char irq_name[32];
+        struct pci_saved_state *pci_saved_state;
 };
 
 struct kvm_irq_mask_notifier {
@@ -456,6 +539,8 @@ void kvm_get_intr_delivery_bitmask(struct kvm_ioapic *ioapic,
                                    unsigned long *deliver_bitmask);
 #endif
 int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level);
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *irq_entry, struct kvm *kvm,
+                int irq_source_id, int level);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
                                    struct kvm_irq_ack_notifier *kian);
@@ -477,8 +562,7 @@ int kvm_deassign_device(struct kvm *kvm,
                         struct kvm_assigned_dev_kernel *assigned_dev);
 #else /* CONFIG_IOMMU_API */
 static inline int kvm_iommu_map_pages(struct kvm *kvm,
-                                      gfn_t base_gfn,
-                                      unsigned long npages)
+                                      struct kvm_memory_slot *slot)
 {
         return 0;
 }
@@ -508,8 +592,17 @@ static inline int kvm_deassign_device(struct kvm *kvm,
 
 static inline void kvm_guest_enter(void)
 {
+        BUG_ON(preemptible());
         account_system_vtime(current);
         current->flags |= PF_VCPU;
+        /* KVM does not hold any references to rcu protected data when it
+         * switches CPU into a guest mode. In fact switching to a guest mode
+         * is very similar to exiting to userspase from rcu point of view. In
+         * addition CPU may stay in a guest mode for quite a long time (up to
+         * one time slice). Lets treat guest mode as quiescent state, just like
+         * we do with user-mode execution.
+         */
+        rcu_virt_note_context_switch(smp_processor_id());
 }
 
 static inline void kvm_guest_exit(void)
@@ -518,11 +611,27 @@ static inline void kvm_guest_exit(void)
         current->flags &= ~PF_VCPU;
 }
 
+static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
+{
+        return gfn_to_memslot(kvm, gfn)->id;
+}
+
+static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
+                                               gfn_t gfn)
+{
+        return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+}
+
 static inline gpa_t gfn_to_gpa(gfn_t gfn)
 {
         return (gpa_t)gfn << PAGE_SHIFT;
 }
 
+static inline gfn_t gpa_to_gfn(gpa_t gpa)
+{
+        return (gfn_t)(gpa >> PAGE_SHIFT);
+}
+
 static inline hpa_t pfn_to_hpa(pfn_t pfn)
 {
         return (hpa_t)pfn << PAGE_SHIFT;
@@ -587,17 +696,28 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags);
 void kvm_irqfd_release(struct kvm *kvm);
+void kvm_irq_routing_update(struct kvm *, struct kvm_irq_routing_table *);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
 #else
 
 static inline void kvm_eventfd_init(struct kvm *kvm) {}
+
 static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
 {
         return -EINVAL;
 }
 
 static inline void kvm_irqfd_release(struct kvm *kvm) {}
+
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
+static inline void kvm_irq_routing_update(struct kvm *kvm,
+                                          struct kvm_irq_routing_table *irq_rt)
+{
+        rcu_assign_pointer(kvm->irq_routing, irq_rt);
+}
+#endif
+
 static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
         return -ENOSYS;
@@ -632,11 +752,6 @@ static inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
         set_bit(req, &vcpu->requests);
 }
 
-static inline bool kvm_make_check_request(int req, struct kvm_vcpu *vcpu)
-{
-        return test_and_set_bit(req, &vcpu->requests);
-}
-
 static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 {
         if (test_bit(req, &vcpu->requests)) {