Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "Fixes and features for 3.18.

  Apart from the usual cleanups, here is the summary of new features:

   - s390 moves closer towards host large page support

   - PowerPC has improved support for debugging (both inside the guest
     and via gdbstub) and support for e6500 processors

   - ARM/ARM64 support read-only memory (which is necessary to put
     firmware in emulated NOR flash)

   - x86 has the usual emulator fixes and nested virtualization
     improvements (including improved Windows support on Intel and
     Jailhouse hypervisor support on AMD), adaptive PLE which helps
     overcommitting of huge guests.  Also included are some patches that
     make KVM more friendly to memory hot-unplug, and fixes for rare
     caching bugs.

  Two patches have trivial mm/ parts that were acked by Rik and Andrew.

  Note: I will soon switch to a subkey for signing purposes"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (157 commits)
  kvm: do not handle APIC access page if in-kernel irqchip is not in use
  KVM: s390: count vcpu wakeups in stat.halt_wakeup
  KVM: s390/facilities: allow TOD-CLOCK steering facility bit
  KVM: PPC: BOOK3S: HV: CMA: Reserve cma region only in hypervisor mode
  arm/arm64: KVM: Report correct FSC for unsupported fault types
  arm/arm64: KVM: Fix VTTBR_BADDR_MASK and pgd alloc
  kvm: Fix kvm_get_page_retry_io __gup retval check
  arm/arm64: KVM: Fix set_clear_sgi_pend_reg offset
  kvm: x86: Unpin and remove kvm_arch->apic_access_page
  kvm: vmx: Implement set_apic_access_page_addr
  kvm: x86: Add request bit to reload APIC access page address
  kvm: Add arch specific mmu notifier for page invalidation
  kvm: Rename make_all_cpus_request() to kvm_make_all_cpus_request() and make it non-static
  kvm: Fix page ageing bugs
  kvm/x86/mmu: Pass gfn and level to rmapp callback.
  x86: kvm: use alternatives for VMCALL vs. VMMCALL if kernel text is read-only
  kvm: x86: use macros to compute bank MSRs
  KVM: x86: Remove debug assertion of non-PAE reserved bits
  kvm: don't take vcpu mutex for obviously invalid vcpu ioctls
  kvm: Faults which trigger IO release the mmap_sem
  ...

4 files changed, 52 insertions, 18 deletions

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a4c33b34fe3f..28be31f49250 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -136,12 +136,11 @@ static inline bool is_error_page(struct page *page)
 #define KVM_REQ_GLOBAL_CLOCK_UPDATE 22
 #define KVM_REQ_ENABLE_IBS        23
 #define KVM_REQ_DISABLE_IBS       24
+#define KVM_REQ_APIC_PAGE_RELOAD  25
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
 
-struct kvm;
-struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 
 extern spinlock_t kvm_lock;
@@ -200,6 +199,17 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
+/*
+ * Carry out a gup that requires IO. Allow the mm to relinquish the mmap
+ * semaphore if the filemap/swap has to wait on a page lock. pagep == NULL
+ * controls whether we retry the gup one more time to completion in that case.
+ * Typically this is called after a FAULT_FLAG_RETRY_NOWAIT in the main tdp
+ * handler.
+ */
+int kvm_get_user_page_io(struct task_struct *tsk, struct mm_struct *mm,
+			 unsigned long addr, bool write_fault,
+			 struct page **pagep);
+
 enum {
 	OUTSIDE_GUEST_MODE,
 	IN_GUEST_MODE,
@@ -325,8 +335,6 @@ struct kvm_kernel_irq_routing_entry {
 	struct hlist_node link;
 };
 
-struct kvm_irq_routing_table;
-
 #ifndef KVM_PRIVATE_MEM_SLOTS
 #define KVM_PRIVATE_MEM_SLOTS 0
 #endif
@@ -528,6 +536,8 @@ 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_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
+unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
+				      bool *writable);
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 void kvm_set_page_accessed(struct page *page);
@@ -579,6 +589,7 @@ void kvm_flush_remote_tlbs(struct kvm *kvm);
 void kvm_reload_remote_mmus(struct kvm *kvm);
 void kvm_make_mclock_inprogress_request(struct kvm *kvm);
 void kvm_make_scan_ioapic_request(struct kvm *kvm);
+bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
@@ -624,6 +635,8 @@ void kvm_arch_exit(void);
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu);
 
+void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
+
 void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
@@ -632,8 +645,8 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu);
 
-int kvm_arch_hardware_enable(void *garbage);
-void kvm_arch_hardware_disable(void *garbage);
+int kvm_arch_hardware_enable(void);
+void kvm_arch_hardware_disable(void);
 int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
@@ -1034,8 +1047,6 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 
 extern bool kvm_rebooting;
 
-struct kvm_device_ops;
-
 struct kvm_device {
 	struct kvm_device_ops *ops;
 	struct kvm *kvm;
@@ -1068,12 +1079,10 @@ struct kvm_device_ops {
 void kvm_device_get(struct kvm_device *dev);
 void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
+int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type);
 
 extern struct kvm_device_ops kvm_mpic_ops;
 extern struct kvm_device_ops kvm_xics_ops;
-extern struct kvm_device_ops kvm_vfio_ops;
-extern struct kvm_device_ops kvm_arm_vgic_v2_ops;
-extern struct kvm_device_ops kvm_flic_ops;
 
 #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
 
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index b0bcce0ddc95..b606bb689a3e 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -17,6 +17,20 @@
 #ifndef __KVM_TYPES_H__
 #define __KVM_TYPES_H__
 
+struct kvm;
+struct kvm_async_pf;
+struct kvm_device_ops;
+struct kvm_interrupt;
+struct kvm_irq_routing_table;
+struct kvm_memory_slot;
+struct kvm_one_reg;
+struct kvm_run;
+struct kvm_userspace_memory_region;
+struct kvm_vcpu;
+struct kvm_vcpu_init;
+
+enum kvm_mr_change;
+
 #include <asm/types.h>
 
 /*
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8981cc882ed2..0f4196a0bc20 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1985,6 +1985,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma,
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
 #define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 #define FOLL_MIGRATION	0x400	/* wait for page to replace migration entry */
+#define FOLL_TRIED	0x800	/* a retry, previous pass started an IO */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 27288692241e..88787bb4b3b9 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -57,10 +57,13 @@ struct mmu_notifier_ops {
 	 * pte. This way the VM will provide proper aging to the
 	 * accesses to the page through the secondary MMUs and not
 	 * only to the ones through the Linux pte.
+	 * Start-end is necessary in case the secondary MMU is mapping the page
+	 * at a smaller granularity than the primary MMU.
 	 */
 	int (*clear_flush_young)(struct mmu_notifier *mn,
 				 struct mm_struct *mm,
-				 unsigned long address);
+				 unsigned long start,
+				 unsigned long end);
 
 	/*
 	 * test_young is called to check the young/accessed bitflag in
@@ -175,7 +178,8 @@ extern void mmu_notifier_unregister_no_release(struct mmu_notifier *mn,
 extern void __mmu_notifier_mm_destroy(struct mm_struct *mm);
 extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
-					  unsigned long address);
+					  unsigned long start,
+					  unsigned long end);
 extern int __mmu_notifier_test_young(struct mm_struct *mm,
 				     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,
@@ -194,10 +198,11 @@ static inline void mmu_notifier_release(struct mm_struct *mm)
 }
 
 static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
-					  unsigned long address)
+					  unsigned long start,
+					  unsigned long end)
 {
 	if (mm_has_notifiers(mm))
-		return __mmu_notifier_clear_flush_young(mm, address);
+		return __mmu_notifier_clear_flush_young(mm, start, end);
 	return 0;
 }
 
@@ -255,7 +260,9 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	unsigned long ___address = __address;				\
 	__young = ptep_clear_flush_young(___vma, ___address, __ptep);	\
 	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
-						  ___address);		\
+						  ___address,		\
+						  ___address +		\
+							PAGE_SIZE);	\
 	__young;							\
 })
 
@@ -266,7 +273,9 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	unsigned long ___address = __address;				\
 	__young = pmdp_clear_flush_young(___vma, ___address, __pmdp);	\
 	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
-						  ___address);		\
+						  ___address,		\
+						  ___address +		\
+							PMD_SIZE);	\
 	__young;							\
 })
 
@@ -301,7 +310,8 @@ static inline void mmu_notifier_release(struct mm_struct *mm)
 }
 
 static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
-					  unsigned long address)
+					  unsigned long start,
+					  unsigned long end)
 {
 	return 0;
 }