Merge tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Avi Kivity:
 "Highlights of the changes for this release include support for vfio
  level triggered interrupts, improved big real mode support on older
  Intels, a streamlines guest page table walker, guest APIC speedups,
  PIO optimizations, better overcommit handling, and read-only memory."

* tag 'kvm-3.7-1' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (138 commits)
  KVM: s390: Fix vcpu_load handling in interrupt code
  KVM: x86: Fix guest debug across vcpu INIT reset
  KVM: Add resampling irqfds for level triggered interrupts
  KVM: optimize apic interrupt delivery
  KVM: MMU: Eliminate pointless temporary 'ac'
  KVM: MMU: Avoid access/dirty update loop if all is well
  KVM: MMU: Eliminate eperm temporary
  KVM: MMU: Optimize is_last_gpte()
  KVM: MMU: Simplify walk_addr_generic() loop
  KVM: MMU: Optimize pte permission checks
  KVM: MMU: Update accessed and dirty bits after guest pagetable walk
  KVM: MMU: Move gpte_access() out of paging_tmpl.h
  KVM: MMU: Optimize gpte_access() slightly
  KVM: MMU: Push clean gpte write protection out of gpte_access()
  KVM: clarify kvmclock documentation
  KVM: make processes waiting on vcpu mutex killable
  KVM: SVM: Make use of asm.h
  KVM: VMX: Make use of asm.h
  KVM: VMX: Make lto-friendly
  KVM: x86: lapic: Clean up find_highest_vector() and count_vectors()
  ...

Conflicts:
	arch/s390/include/asm/processor.h
	arch/x86/kvm/i8259.c

2 files changed, 137 insertions, 33 deletions

diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 2ce09aa7d3b3..0a6d6ba44c85 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -101,9 +101,13 @@ struct kvm_userspace_memory_region {
 	__u64 userspace_addr; /* start of the userspace allocated memory */
 };
 
-/* for kvm_memory_region::flags */
-#define KVM_MEM_LOG_DIRTY_PAGES  1UL
-#define KVM_MEMSLOT_INVALID      (1UL << 1)
+/*
+ * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace,
+ * other bits are reserved for kvm internal use which are defined in
+ * include/linux/kvm_host.h.
+ */
+#define KVM_MEM_LOG_DIRTY_PAGES	(1UL << 0)
+#define KVM_MEM_READONLY	(1UL << 1)
 
 /* for KVM_IRQ_LINE */
 struct kvm_irq_level {
@@ -618,6 +622,10 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_PPC_GET_SMMU_INFO 78
 #define KVM_CAP_S390_COW 79
 #define KVM_CAP_PPC_ALLOC_HTAB 80
+#ifdef __KVM_HAVE_READONLY_MEM
+#define KVM_CAP_READONLY_MEM 81
+#endif
+#define KVM_CAP_IRQFD_RESAMPLE 82
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -683,12 +691,21 @@ struct kvm_xen_hvm_config {
 #endif
 
 #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+/*
+ * Available with KVM_CAP_IRQFD_RESAMPLE
+ *
+ * KVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies
+ * the irqfd to operate in resampling mode for level triggered interrupt
+ * emlation.  See Documentation/virtual/kvm/api.txt.
+ */
+#define KVM_IRQFD_FLAG_RESAMPLE (1 << 1)
 
 struct kvm_irqfd {
 	__u32 fd;
 	__u32 gsi;
 	__u32 flags;
-	__u8  pad[20];
+	__u32 resamplefd;
+	__u8  pad[16];
 };
 
 struct kvm_clock_data {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8a59e0abe5fa..93bfc9f9815c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -21,6 +21,7 @@
 #include <linux/slab.h>
 #include <linux/rcupdate.h>
 #include <linux/ratelimit.h>
+#include <linux/err.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -35,6 +36,13 @@
 #endif
 
 /*
+ * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used
+ * in kvm, other bits are visible for userspace which are defined in
+ * include/linux/kvm_h.
+ */
+#define KVM_MEMSLOT_INVALID	(1UL << 16)
+
+/*
  * If we support unaligned MMIO, at most one fragment will be split into two:
  */
 #ifdef KVM_UNALIGNED_MMIO
@@ -49,6 +57,47 @@
 	(KVM_MMIO_SIZE / KVM_USER_MMIO_SIZE + KVM_EXTRA_MMIO_FRAGMENTS)
 
 /*
+ * For the normal pfn, the highest 12 bits should be zero,
+ * so we can mask these bits to indicate the error.
+ */
+#define KVM_PFN_ERR_MASK	(0xfffULL << 52)
+
+#define KVM_PFN_ERR_FAULT	(KVM_PFN_ERR_MASK)
+#define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
+#define KVM_PFN_ERR_BAD		(KVM_PFN_ERR_MASK + 2)
+#define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 3)
+
+static inline bool is_error_pfn(pfn_t pfn)
+{
+	return !!(pfn & KVM_PFN_ERR_MASK);
+}
+
+static inline bool is_noslot_pfn(pfn_t pfn)
+{
+	return pfn == KVM_PFN_ERR_BAD;
+}
+
+static inline bool is_invalid_pfn(pfn_t pfn)
+{
+	return !is_noslot_pfn(pfn) && is_error_pfn(pfn);
+}
+
+#define KVM_HVA_ERR_BAD		(PAGE_OFFSET)
+#define KVM_HVA_ERR_RO_BAD	(PAGE_OFFSET + PAGE_SIZE)
+
+static inline bool kvm_is_error_hva(unsigned long addr)
+{
+	return addr >= PAGE_OFFSET;
+}
+
+#define KVM_ERR_PTR_BAD_PAGE	(ERR_PTR(-ENOENT))
+
+static inline bool is_error_page(struct page *page)
+{
+	return IS_ERR(page);
+}
+
+/*
  * vcpu->requests bit members
  */
 #define KVM_REQ_TLB_FLUSH          0
@@ -70,7 +119,8 @@
 #define KVM_REQ_PMU               16
 #define KVM_REQ_PMI               17
 
-#define KVM_USERSPACE_IRQ_SOURCE_ID	0
+#define KVM_USERSPACE_IRQ_SOURCE_ID		0
+#define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
 
 struct kvm;
 struct kvm_vcpu;
@@ -183,6 +233,18 @@ struct kvm_vcpu {
 	} async_pf;
 #endif
 
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+	/*
+	 * Cpu relax intercept or pause loop exit optimization
+	 * in_spin_loop: set when a vcpu does a pause loop exit
+	 *  or cpu relax intercepted.
+	 * dy_eligible: indicates whether vcpu is eligible for directed yield.
+	 */
+	struct {
+		bool in_spin_loop;
+		bool dy_eligible;
+	} spin_loop;
+#endif
 	struct kvm_vcpu_arch arch;
 };
 
@@ -201,7 +263,6 @@ struct kvm_memory_slot {
 	gfn_t base_gfn;
 	unsigned long npages;
 	unsigned long flags;
-	unsigned long *rmap;
 	unsigned long *dirty_bitmap;
 	struct kvm_arch_memory_slot arch;
 	unsigned long userspace_addr;
@@ -283,6 +344,8 @@ struct kvm {
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
+		struct list_head  resampler_list;
+		struct mutex      resampler_lock;
 	} irqfds;
 	struct list_head ioeventfds;
 #endif
@@ -348,7 +411,7 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
 
-void vcpu_load(struct kvm_vcpu *vcpu);
+int __must_check vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
 int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
@@ -378,23 +441,6 @@ id_to_memslot(struct kvm_memslots *slots, int id)
 	return slot;
 }
 
-#define HPA_MSB ((sizeof(hpa_t) * 8) - 1)
-#define HPA_ERR_MASK ((hpa_t)1 << HPA_MSB)
-static inline int is_error_hpa(hpa_t hpa) { return hpa >> HPA_MSB; }
-
-extern struct page *bad_page;
-extern struct page *fault_page;
-
-extern pfn_t bad_pfn;
-extern pfn_t fault_pfn;
-
-int is_error_page(struct page *page);
-int is_error_pfn(pfn_t pfn);
-int is_hwpoison_pfn(pfn_t pfn);
-int is_fault_pfn(pfn_t pfn);
-int is_noslot_pfn(pfn_t pfn);
-int is_invalid_pfn(pfn_t pfn);
-int kvm_is_error_hva(unsigned long addr);
 int kvm_set_memory_region(struct kvm *kvm,
 			  struct kvm_userspace_memory_region *mem,
 			  int user_alloc);
@@ -415,28 +461,33 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 				int user_alloc);
 bool kvm_largepages_enabled(void);
 void kvm_disable_largepages(void);
-void kvm_arch_flush_shadow(struct kvm *kvm);
+/* flush all memory translations */
+void kvm_arch_flush_shadow_all(struct kvm *kvm);
+/* flush memory translations pointing to 'slot' */
+void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
+				   struct kvm_memory_slot *slot);
 
 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);
+unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_release_page_clean(struct page *page);
 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);
-void kvm_release_pfn_dirty(pfn_t);
+pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
+pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn);
+
+void kvm_release_pfn_dirty(pfn_t pfn);
 void kvm_release_pfn_clean(pfn_t pfn);
 void kvm_set_pfn_dirty(pfn_t pfn);
 void kvm_set_pfn_accessed(pfn_t pfn);
@@ -494,6 +545,7 @@ int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
 				   struct
 				   kvm_userspace_memory_region *mem,
 				   int user_alloc);
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level);
 long kvm_arch_vm_ioctl(struct file *filp,
 		       unsigned int ioctl, unsigned long arg);
 
@@ -573,7 +625,7 @@ void kvm_arch_sync_events(struct kvm *kvm);
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
 
-int kvm_is_mmio_pfn(pfn_t pfn);
+bool kvm_is_mmio_pfn(pfn_t pfn);
 
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
@@ -728,6 +780,12 @@ __gfn_to_memslot(struct kvm_memslots *slots, gfn_t gfn)
 	return search_memslots(slots, gfn);
 }
 
+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 int memslot_id(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn_to_memslot(kvm, gfn)->id;
@@ -740,10 +798,12 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
 		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
 }
 
-static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
-					       gfn_t gfn)
+static inline gfn_t
+hva_to_gfn_memslot(unsigned long hva, struct kvm_memory_slot *slot)
 {
-	return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE;
+	gfn_t gfn_offset = (hva - slot->userspace_addr) >> PAGE_SHIFT;
+
+	return slot->base_gfn + gfn_offset;
 }
 
 static inline gpa_t gfn_to_gpa(gfn_t gfn)
@@ -899,5 +959,32 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 	}
 }
 
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+
+static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
+{
+	vcpu->spin_loop.in_spin_loop = val;
+}
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+	vcpu->spin_loop.dy_eligible = val;
+}
+
+#else /* !CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
+
+static inline void kvm_vcpu_set_in_spin_loop(struct kvm_vcpu *vcpu, bool val)
+{
+}
+
+static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val)
+{
+}
+
+static inline bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+{
+	return true;
+}
+
+#endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */
 #endif