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

Pull KVM update from Paolo Bonzini:
 "Fairly small update, but there are some interesting new features.

  Common:
     Optional support for adding a small amount of polling on each HLT
     instruction executed in the guest (or equivalent for other
     architectures).  This can improve latency up to 50% on some
     scenarios (e.g. O_DSYNC writes or TCP_RR netperf tests).  This
     also has to be enabled manually for now, but the plan is to
     auto-tune this in the future.

  ARM/ARM64:
     The highlights are support for GICv3 emulation and dirty page
     tracking

  s390:
     Several optimizations and bugfixes.  Also a first: a feature
     exposed by KVM (UUID and long guest name in /proc/sysinfo) before
     it is available in IBM's hypervisor! :)

  MIPS:
     Bugfixes.

  x86:
     Support for PML (page modification logging, a new feature in
     Broadwell Xeons that speeds up dirty page tracking), nested
     virtualization improvements (nested APICv---a nice optimization),
     usual round of emulation fixes.

     There is also a new option to reduce latency of the TSC deadline
     timer in the guest; this needs to be tuned manually.

     Some commits are common between this pull and Catalin's; I see you
     have already included his tree.

  Powerpc:
     Nothing yet.

     The KVM/PPC changes will come in through the PPC maintainers,
     because I haven't received them yet and I might end up being
     offline for some part of next week"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (130 commits)
  KVM: ia64: drop kvm.h from installed user headers
  KVM: x86: fix build with !CONFIG_SMP
  KVM: x86: emulate: correct page fault error code for NoWrite instructions
  KVM: Disable compat ioctl for s390
  KVM: s390: add cpu model support
  KVM: s390: use facilities and cpu_id per KVM
  KVM: s390/CPACF: Choose crypto control block format
  s390/kernel: Update /proc/sysinfo file with Extended Name and UUID
  KVM: s390: reenable LPP facility
  KVM: s390: floating irqs: fix user triggerable endless loop
  kvm: add halt_poll_ns module parameter
  kvm: remove KVM_MMIO_SIZE
  KVM: MIPS: Don't leak FPU/DSP to guest
  KVM: MIPS: Disable HTW while in guest
  KVM: nVMX: Enable nested posted interrupt processing
  KVM: nVMX: Enable nested virtual interrupt delivery
  KVM: nVMX: Enable nested apic register virtualization
  KVM: nVMX: Make nested control MSRs per-cpu
  KVM: nVMX: Enable nested virtualize x2apic mode
  KVM: nVMX: Prepare for using hardware MSR bitmap
  ...

3 files changed, 57 insertions, 7 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index eb181178fe0..57a9d94fe16 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -208,6 +208,7 @@ struct x86_emulate_ops {
 
 	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
 			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index d89c6b828c9..a236e39cc38 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -38,8 +38,6 @@
 #define KVM_PRIVATE_MEM_SLOTS 3
 #define KVM_MEM_SLOTS_NUM (KVM_USER_MEM_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 
-#define KVM_MMIO_SIZE 16
-
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
 
@@ -51,7 +49,7 @@
 			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
 
 #define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL
-#define CR3_PCID_INVD		 (1UL << 63)
+#define CR3_PCID_INVD		 BIT_64(63)
 #define CR4_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
@@ -160,6 +158,18 @@ enum {
 #define DR7_FIXED_1	0x00000400
 #define DR7_VOLATILE	0xffff2bff
 
+#define PFERR_PRESENT_BIT 0
+#define PFERR_WRITE_BIT 1
+#define PFERR_USER_BIT 2
+#define PFERR_RSVD_BIT 3
+#define PFERR_FETCH_BIT 4
+
+#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
+#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
+#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
+
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
 /*
@@ -615,6 +625,8 @@ struct kvm_arch {
 	#ifdef CONFIG_KVM_MMU_AUDIT
 	int audit_point;
 	#endif
+
+	bool boot_vcpu_runs_old_kvmclock;
 };
 
 struct kvm_vm_stat {
@@ -643,6 +655,7 @@ struct kvm_vcpu_stat {
 	u32 irq_window_exits;
 	u32 nmi_window_exits;
 	u32 halt_exits;
+	u32 halt_successful_poll;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
 	u32 irq_exits;
@@ -787,6 +800,31 @@ struct kvm_x86_ops {
 	int (*check_nested_events)(struct kvm_vcpu *vcpu, bool external_intr);
 
 	void (*sched_in)(struct kvm_vcpu *kvm, int cpu);
+
+	/*
+	 * Arch-specific dirty logging hooks. These hooks are only supposed to
+	 * be valid if the specific arch has hardware-accelerated dirty logging
+	 * mechanism. Currently only for PML on VMX.
+	 *
+	 *  - slot_enable_log_dirty:
+	 *	called when enabling log dirty mode for the slot.
+	 *  - slot_disable_log_dirty:
+	 *	called when disabling log dirty mode for the slot.
+	 *	also called when slot is created with log dirty disabled.
+	 *  - flush_log_dirty:
+	 *	called before reporting dirty_bitmap to userspace.
+	 *  - enable_log_dirty_pt_masked:
+	 *	called when reenabling log dirty for the GFNs in the mask after
+	 *	corresponding bits are cleared in slot->dirty_bitmap.
+	 */
+	void (*slot_enable_log_dirty)(struct kvm *kvm,
+				      struct kvm_memory_slot *slot);
+	void (*slot_disable_log_dirty)(struct kvm *kvm,
+				       struct kvm_memory_slot *slot);
+	void (*flush_log_dirty)(struct kvm *kvm);
+	void (*enable_log_dirty_pt_masked)(struct kvm *kvm,
+					   struct kvm_memory_slot *slot,
+					   gfn_t offset, unsigned long mask);
 };
 
 struct kvm_arch_async_pf {
@@ -819,10 +857,17 @@ void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
-void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
-				     struct kvm_memory_slot *slot,
-				     gfn_t gfn_offset, unsigned long mask);
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm,
+				      struct kvm_memory_slot *memslot);
+void kvm_mmu_slot_leaf_clear_dirty(struct kvm *kvm,
+				   struct kvm_memory_slot *memslot);
+void kvm_mmu_slot_largepage_remove_write_access(struct kvm *kvm,
+					struct kvm_memory_slot *memslot);
+void kvm_mmu_slot_set_dirty(struct kvm *kvm,
+			    struct kvm_memory_slot *memslot);
+void kvm_mmu_clear_dirty_pt_masked(struct kvm *kvm,
+				   struct kvm_memory_slot *slot,
+				   gfn_t gfn_offset, unsigned long mask);
 void kvm_mmu_zap_all(struct kvm *kvm);
 void kvm_mmu_invalidate_mmio_sptes(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 45afaee9555..da772edd19a 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -69,6 +69,7 @@
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
 #define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
+#define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
 
 
@@ -121,6 +122,7 @@ enum vmcs_field {
 	GUEST_LDTR_SELECTOR             = 0x0000080c,
 	GUEST_TR_SELECTOR               = 0x0000080e,
 	GUEST_INTR_STATUS               = 0x00000810,
+	GUEST_PML_INDEX			= 0x00000812,
 	HOST_ES_SELECTOR                = 0x00000c00,
 	HOST_CS_SELECTOR                = 0x00000c02,
 	HOST_SS_SELECTOR                = 0x00000c04,
@@ -140,6 +142,8 @@ enum vmcs_field {
 	VM_EXIT_MSR_LOAD_ADDR_HIGH      = 0x00002009,
 	VM_ENTRY_MSR_LOAD_ADDR          = 0x0000200a,
 	VM_ENTRY_MSR_LOAD_ADDR_HIGH     = 0x0000200b,
+	PML_ADDRESS			= 0x0000200e,
+	PML_ADDRESS_HIGH		= 0x0000200f,
 	TSC_OFFSET                      = 0x00002010,
 	TSC_OFFSET_HIGH                 = 0x00002011,
 	VIRTUAL_APIC_PAGE_ADDR          = 0x00002012,