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

Pull KVM updates from Paolo Bonzini:
 "4.11 is going to be a relatively large release for KVM, with a little
  over 200 commits and noteworthy changes for most architectures.

  ARM:
   - GICv3 save/restore
   - cache flushing fixes
   - working MSI injection for GICv3 ITS
   - physical timer emulation

  MIPS:
   - various improvements under the hood
   - support for SMP guests
   - a large rewrite of MMU emulation. KVM MIPS can now use MMU
     notifiers to support copy-on-write, KSM, idle page tracking,
     swapping, ballooning and everything else. KVM_CAP_READONLY_MEM is
     also supported, so that writes to some memory regions can be
     treated as MMIO. The new MMU also paves the way for hardware
     virtualization support.

  PPC:
   - support for POWER9 using the radix-tree MMU for host and guest
   - resizable hashed page table
   - bugfixes.

  s390:
   - expose more features to the guest
   - more SIMD extensions
   - instruction execution protection
   - ESOP2

  x86:
   - improved hashing in the MMU
   - faster PageLRU tracking for Intel CPUs without EPT A/D bits
   - some refactoring of nested VMX entry/exit code, preparing for live
     migration support of nested hypervisors
   - expose yet another AVX512 CPUID bit
   - host-to-guest PTP support
   - refactoring of interrupt injection, with some optimizations thrown
     in and some duct tape removed.
   - remove lazy FPU handling
   - optimizations of user-mode exits
   - optimizations of vcpu_is_preempted() for KVM guests

  generic:
   - alternative signaling mechanism that doesn't pound on
     tsk->sighand->siglock"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (195 commits)
  x86/kvm: Provide optimized version of vcpu_is_preempted() for x86-64
  x86/paravirt: Change vcp_is_preempted() arg type to long
  KVM: VMX: use correct vmcs_read/write for guest segment selector/base
  x86/kvm/vmx: Defer TR reload after VM exit
  x86/asm/64: Drop __cacheline_aligned from struct x86_hw_tss
  x86/kvm/vmx: Simplify segment_base()
  x86/kvm/vmx: Get rid of segment_base() on 64-bit kernels
  x86/kvm/vmx: Don't fetch the TSS base from the GDT
  x86/asm: Define the kernel TSS limit in a macro
  kvm: fix page struct leak in handle_vmon
  KVM: PPC: Book3S HV: Disable HPT resizing on POWER9 for now
  KVM: Return an error code only as a constant in kvm_get_dirty_log()
  KVM: Return an error code only as a constant in kvm_get_dirty_log_protect()
  KVM: Return directly after a failed copy_from_user() in kvm_vm_compat_ioctl()
  KVM: x86: remove code for lazy FPU handling
  KVM: race-free exit from KVM_RUN without POSIX signals
  KVM: PPC: Book3S HV: Turn "KVM guest htab" message into a debug message
  KVM: PPC: Book3S PR: Ratelimit copy data failure error messages
  KVM: Support vCPU-based gfn->hva cache
  KVM: use separate generations for each address space
  ...

6 files changed, 102 insertions, 35 deletions

diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 5c970ce67949..fe797d6ef89d 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -23,20 +23,24 @@
 #include <linux/hrtimer.h>
 #include <linux/workqueue.h>
 
-struct arch_timer_kvm {
+struct arch_timer_context {
+	/* Registers: control register, timer value */
+	u32				cnt_ctl;
+	u64				cnt_cval;
+
+	/* Timer IRQ */
+	struct kvm_irq_level		irq;
+
+	/* Active IRQ state caching */
+	bool				active_cleared_last;
+
 	/* Virtual offset */
 	u64			cntvoff;
 };
 
 struct arch_timer_cpu {
-	/* Registers: control register, timer value */
-	u32				cntv_ctl;	/* Saved/restored */
-	u64				cntv_cval;	/* Saved/restored */
-
-	/*
-	 * Anything that is not used directly from assembly code goes
-	 * here.
-	 */
+	struct arch_timer_context	vtimer;
+	struct arch_timer_context	ptimer;
 
 	/* Background timer used when the guest is not running */
 	struct hrtimer			timer;
@@ -47,21 +51,15 @@ struct arch_timer_cpu {
 	/* Background timer active */
 	bool				armed;
 
-	/* Timer IRQ */
-	struct kvm_irq_level		irq;
-
-	/* Active IRQ state caching */
-	bool				active_cleared_last;
-
 	/* Is the timer enabled */
 	bool			enabled;
 };
 
 int kvm_timer_hyp_init(void);
 int kvm_timer_enable(struct kvm_vcpu *vcpu);
-void kvm_timer_init(struct kvm *kvm);
 int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu,
-			 const struct kvm_irq_level *irq);
+			 const struct kvm_irq_level *virt_irq,
+			 const struct kvm_irq_level *phys_irq);
 void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu);
 void kvm_timer_flush_hwstate(struct kvm_vcpu *vcpu);
 void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu);
@@ -70,11 +68,16 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu);
 u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid);
 int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value);
 
-bool kvm_timer_should_fire(struct kvm_vcpu *vcpu);
+bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx);
 void kvm_timer_schedule(struct kvm_vcpu *vcpu);
 void kvm_timer_unschedule(struct kvm_vcpu *vcpu);
 
+u64 kvm_phys_timer_read(void);
+
 void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu);
 
 void kvm_timer_init_vhe(void);
+
+#define vcpu_vtimer(v)	(&(v)->arch.timer_cpu.vtimer)
+#define vcpu_ptimer(v)	(&(v)->arch.timer_cpu.ptimer)
 #endif
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 002f0922cd92..b72dd2ad5f44 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -71,6 +71,8 @@ struct vgic_global {
 
 	/* GIC system register CPU interface */
 	struct static_key_false gicv3_cpuif;
+
+	u32			ich_vtr_el2;
 };
 
 extern struct vgic_global kvm_vgic_global_state;
@@ -101,9 +103,10 @@ struct vgic_irq {
 					 */
 
 	u32 intid;			/* Guest visible INTID */
-	bool pending;
 	bool line_level;		/* Level only */
-	bool soft_pending;		/* Level only */
+	bool pending_latch;		/* The pending latch state used to calculate
+					 * the pending state for both level
+					 * and edge triggered IRQs. */
 	bool active;			/* not used for LPIs */
 	bool enabled;
 	bool hw;			/* Tied to HW IRQ */
@@ -165,6 +168,8 @@ struct vgic_its {
 	struct list_head	collection_list;
 };
 
+struct vgic_state_iter;
+
 struct vgic_dist {
 	bool			in_kernel;
 	bool			ready;
@@ -212,6 +217,9 @@ struct vgic_dist {
 	spinlock_t		lpi_list_lock;
 	struct list_head	lpi_list_head;
 	int			lpi_list_count;
+
+	/* used by vgic-debug */
+	struct vgic_state_iter *iter;
 };
 
 struct vgic_v2_cpu_if {
@@ -269,6 +277,12 @@ struct vgic_cpu {
 	u64 pendbaser;
 
 	bool lpis_enabled;
+
+	/* Cache guest priority bits */
+	u32 num_pri_bits;
+
+	/* Cache guest interrupt ID bits */
+	u32 num_id_bits;
 };
 
 extern struct static_key_false vgic_v2_cpuif_trap;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 725e86b506f3..672cfef72fc8 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -349,8 +349,30 @@
 /*
  * CPU interface registers
  */
-#define ICC_CTLR_EL1_EOImode_drop_dir	(0U << 1)
-#define ICC_CTLR_EL1_EOImode_drop	(1U << 1)
+#define ICC_CTLR_EL1_EOImode_SHIFT	(1)
+#define ICC_CTLR_EL1_EOImode_drop_dir	(0U << ICC_CTLR_EL1_EOImode_SHIFT)
+#define ICC_CTLR_EL1_EOImode_drop	(1U << ICC_CTLR_EL1_EOImode_SHIFT)
+#define ICC_CTLR_EL1_EOImode_MASK	(1 << ICC_CTLR_EL1_EOImode_SHIFT)
+#define ICC_CTLR_EL1_CBPR_SHIFT		0
+#define ICC_CTLR_EL1_CBPR_MASK		(1 << ICC_CTLR_EL1_CBPR_SHIFT)
+#define ICC_CTLR_EL1_PRI_BITS_SHIFT	8
+#define ICC_CTLR_EL1_PRI_BITS_MASK	(0x7 << ICC_CTLR_EL1_PRI_BITS_SHIFT)
+#define ICC_CTLR_EL1_ID_BITS_SHIFT	11
+#define ICC_CTLR_EL1_ID_BITS_MASK	(0x7 << ICC_CTLR_EL1_ID_BITS_SHIFT)
+#define ICC_CTLR_EL1_SEIS_SHIFT		14
+#define ICC_CTLR_EL1_SEIS_MASK		(0x1 << ICC_CTLR_EL1_SEIS_SHIFT)
+#define ICC_CTLR_EL1_A3V_SHIFT		15
+#define ICC_CTLR_EL1_A3V_MASK		(0x1 << ICC_CTLR_EL1_A3V_SHIFT)
+#define ICC_PMR_EL1_SHIFT		0
+#define ICC_PMR_EL1_MASK		(0xff << ICC_PMR_EL1_SHIFT)
+#define ICC_BPR0_EL1_SHIFT		0
+#define ICC_BPR0_EL1_MASK		(0x7 << ICC_BPR0_EL1_SHIFT)
+#define ICC_BPR1_EL1_SHIFT		0
+#define ICC_BPR1_EL1_MASK		(0x7 << ICC_BPR1_EL1_SHIFT)
+#define ICC_IGRPEN0_EL1_SHIFT		0
+#define ICC_IGRPEN0_EL1_MASK		(1 << ICC_IGRPEN0_EL1_SHIFT)
+#define ICC_IGRPEN1_EL1_SHIFT		0
+#define ICC_IGRPEN1_EL1_MASK		(1 << ICC_IGRPEN1_EL1_SHIFT)
 #define ICC_SRE_EL1_SRE			(1U << 0)
 
 /*
@@ -379,14 +401,29 @@
 #define ICH_HCR_EN			(1 << 0)
 #define ICH_HCR_UIE			(1 << 1)
 
-#define ICH_VMCR_CTLR_SHIFT		0
-#define ICH_VMCR_CTLR_MASK		(0x21f << ICH_VMCR_CTLR_SHIFT)
+#define ICH_VMCR_CBPR_SHIFT		4
+#define ICH_VMCR_CBPR_MASK		(1 << ICH_VMCR_CBPR_SHIFT)
+#define ICH_VMCR_EOIM_SHIFT		9
+#define ICH_VMCR_EOIM_MASK		(1 << ICH_VMCR_EOIM_SHIFT)
 #define ICH_VMCR_BPR1_SHIFT		18
 #define ICH_VMCR_BPR1_MASK		(7 << ICH_VMCR_BPR1_SHIFT)
 #define ICH_VMCR_BPR0_SHIFT		21
 #define ICH_VMCR_BPR0_MASK		(7 << ICH_VMCR_BPR0_SHIFT)
 #define ICH_VMCR_PMR_SHIFT		24
 #define ICH_VMCR_PMR_MASK		(0xffUL << ICH_VMCR_PMR_SHIFT)
+#define ICH_VMCR_ENG0_SHIFT		0
+#define ICH_VMCR_ENG0_MASK		(1 << ICH_VMCR_ENG0_SHIFT)
+#define ICH_VMCR_ENG1_SHIFT		1
+#define ICH_VMCR_ENG1_MASK		(1 << ICH_VMCR_ENG1_SHIFT)
+
+#define ICH_VTR_PRI_BITS_SHIFT		29
+#define ICH_VTR_PRI_BITS_MASK		(7 << ICH_VTR_PRI_BITS_SHIFT)
+#define ICH_VTR_ID_BITS_SHIFT		23
+#define ICH_VTR_ID_BITS_MASK		(7 << ICH_VTR_ID_BITS_SHIFT)
+#define ICH_VTR_SEIS_SHIFT		22
+#define ICH_VTR_SEIS_MASK		(1 << ICH_VTR_SEIS_SHIFT)
+#define ICH_VTR_A3V_SHIFT		21
+#define ICH_VTR_A3V_MASK		(1 << ICH_VTR_A3V_SHIFT)
 
 #define ICC_IAR1_EL1_SPURIOUS		0x3ff
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 1c5190dab2c1..8d69d5150748 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -45,7 +45,6 @@
  * include/linux/kvm_h.
  */
 #define KVM_MEMSLOT_INVALID	(1UL << 16)
-#define KVM_MEMSLOT_INCOHERENT	(1UL << 17)
 
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
@@ -222,7 +221,6 @@ struct kvm_vcpu {
 	struct mutex mutex;
 	struct kvm_run *run;
 
-	int fpu_active;
 	int guest_fpu_loaded, guest_xcr0_loaded;
 	struct swait_queue_head wq;
 	struct pid *pid;
@@ -642,18 +640,18 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
 			  unsigned long len);
 int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
-int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			   void *data, unsigned long len);
+int kvm_vcpu_read_guest_cached(struct kvm_vcpu *vcpu, struct gfn_to_hva_cache *ghc,
+			       void *data, unsigned long len);
 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_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			   void *data, int offset, unsigned long len);
-int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
-			      gpa_t gpa, unsigned long len);
+int kvm_vcpu_write_guest_cached(struct kvm_vcpu *v, struct gfn_to_hva_cache *ghc,
+				void *data, unsigned long len);
+int kvm_vcpu_write_guest_offset_cached(struct kvm_vcpu *v, struct gfn_to_hva_cache *ghc,
+				       void *data, int offset, unsigned long len);
+int kvm_vcpu_gfn_to_hva_cache_init(struct kvm_vcpu *v, struct gfn_to_hva_cache *ghc,
+				   gpa_t gpa, unsigned long len);
 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);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index e0035808c814..f51d5082a377 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -218,7 +218,8 @@ struct kvm_hyperv_exit {
 struct kvm_run {
 	/* in */
 	__u8 request_interrupt_window;
-	__u8 padding1[7];
+	__u8 immediate_exit;
+	__u8 padding1[6];
 
 	/* out */
 	__u32 exit_reason;
@@ -685,6 +686,13 @@ struct kvm_ppc_smmu_info {
 	struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ];
 };
 
+/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */
+struct kvm_ppc_resize_hpt {
+	__u64 flags;
+	__u32 shift;
+	__u32 pad;
+};
+
 #define KVMIO 0xAE
 
 /* machine type bits, to be used as argument to KVM_CREATE_VM */
@@ -871,8 +879,10 @@ struct kvm_ppc_smmu_info {
 #define KVM_CAP_S390_USER_INSTR0 130
 #define KVM_CAP_MSI_DEVID 131
 #define KVM_CAP_PPC_HTM 132
+#define KVM_CAP_SPAPR_RESIZE_HPT 133
 #define KVM_CAP_PPC_MMU_RADIX 134
 #define KVM_CAP_PPC_MMU_HASH_V3 135
+#define KVM_CAP_IMMEDIATE_EXIT 136
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1189,6 +1199,9 @@ struct kvm_s390_ucas_mapping {
 #define KVM_ARM_SET_DEVICE_ADDR	  _IOW(KVMIO,  0xab, struct kvm_arm_device_addr)
 /* Available with KVM_CAP_PPC_RTAS */
 #define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO,  0xac, struct kvm_rtas_token_args)
+/* Available with KVM_CAP_SPAPR_RESIZE_HPT */
+#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt)
+#define KVM_PPC_RESIZE_HPT_COMMIT  _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt)
 /* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */
 #define KVM_PPC_CONFIGURE_V3_MMU  _IOW(KVMIO,  0xaf, struct kvm_ppc_mmuv3_cfg)
 /* Available with KVM_CAP_PPC_RADIX_MMU */
diff --git a/include/uapi/linux/kvm_para.h b/include/uapi/linux/kvm_para.h
index bf6cd7d5cac2..fed506aeff62 100644
--- a/include/uapi/linux/kvm_para.h
+++ b/include/uapi/linux/kvm_para.h
@@ -14,6 +14,7 @@
 #define KVM_EFAULT		EFAULT
 #define KVM_E2BIG		E2BIG
 #define KVM_EPERM		EPERM
+#define KVM_EOPNOTSUPP		95
 
 #define KVM_HC_VAPIC_POLL_IRQ		1
 #define KVM_HC_MMU_OP			2
@@ -23,6 +24,7 @@
 #define KVM_HC_MIPS_GET_CLOCK_FREQ	6
 #define KVM_HC_MIPS_EXIT_VM		7
 #define KVM_HC_MIPS_CONSOLE_OUTPUT	8
+#define KVM_HC_CLOCK_PAIRING		9
 
 /*
  * hypercalls use architecture specific