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

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - some cleanups
   - direct physical timer assignment
   - cache sanitization for 32-bit guests

  s390:
   - interrupt cleanup
   - introduction of the Guest Information Block
   - preparation for processor subfunctions in cpu models

  PPC:
   - bug fixes and improvements, especially related to machine checks
     and protection keys

  x86:
   - many, many cleanups, including removing a bunch of MMU code for
     unnecessary optimizations
   - AVIC fixes

  Generic:
   - memcg accounting"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (147 commits)
  kvm: vmx: fix formatting of a comment
  KVM: doc: Document the life cycle of a VM and its resources
  MAINTAINERS: Add KVM selftests to existing KVM entry
  Revert "KVM/MMU: Flush tlb directly in the kvm_zap_gfn_range()"
  KVM: PPC: Book3S: Add count cache flush parameters to kvmppc_get_cpu_char()
  KVM: PPC: Fix compilation when KVM is not enabled
  KVM: Minor cleanups for kvm_main.c
  KVM: s390: add debug logging for cpu model subfunctions
  KVM: s390: implement subfunction processor calls
  arm64: KVM: Fix architecturally invalid reset value for FPEXC32_EL2
  KVM: arm/arm64: Remove unused timer variable
  KVM: PPC: Book3S: Improve KVM reference counting
  KVM: PPC: Book3S HV: Fix build failure without IOMMU support
  Revert "KVM: Eliminate extra function calls in kvm_get_dirty_log_protect()"
  x86: kvmguest: use TSC clocksource if invariant TSC is exposed
  KVM: Never start grow vCPU halt_poll_ns from value below halt_poll_ns_grow_start
  KVM: Expose the initial start value in grow_halt_poll_ns() as a module parameter
  KVM: grow_halt_poll_ns() should never shrink vCPU halt_poll_ns
  KVM: x86/mmu: Consolidate kvm_mmu_zap_all() and kvm_mmu_zap_mmio_sptes()
  KVM: x86/mmu: WARN if zapping a MMIO spte results in zapping children
  ...

3 files changed, 73 insertions, 20 deletions

diff --git a/include/clocksource/arm_arch_timer.h b/include/clocksource/arm_arch_timer.h
index 349e5957c949..702967d996bb 100644
--- a/include/clocksource/arm_arch_timer.h
+++ b/include/clocksource/arm_arch_timer.h
@@ -74,6 +74,7 @@ enum arch_timer_spi_nr {
 struct arch_timer_kvm_info {
 	struct timecounter timecounter;
 	int virtual_irq;
+	int physical_irq;
 };
 
 struct arch_timer_mem_frame {
diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h
index 33771352dcd6..05a18dd265b5 100644
--- a/include/kvm/arm_arch_timer.h
+++ b/include/kvm/arm_arch_timer.h
@@ -22,7 +22,22 @@
 #include <linux/clocksource.h>
 #include <linux/hrtimer.h>
 
+enum kvm_arch_timers {
+	TIMER_PTIMER,
+	TIMER_VTIMER,
+	NR_KVM_TIMERS
+};
+
+enum kvm_arch_timer_regs {
+	TIMER_REG_CNT,
+	TIMER_REG_CVAL,
+	TIMER_REG_TVAL,
+	TIMER_REG_CTL,
+};
+
 struct arch_timer_context {
+	struct kvm_vcpu			*vcpu;
+
 	/* Registers: control register, timer value */
 	u32				cnt_ctl;
 	u64				cnt_cval;
@@ -30,30 +45,36 @@ struct arch_timer_context {
 	/* Timer IRQ */
 	struct kvm_irq_level		irq;
 
+	/* Virtual offset */
+	u64				cntvoff;
+
+	/* Emulated Timer (may be unused) */
+	struct hrtimer			hrtimer;
+
 	/*
-	 * We have multiple paths which can save/restore the timer state
-	 * onto the hardware, so we need some way of keeping track of
-	 * where the latest state is.
-	 *
-	 * loaded == true:  State is loaded on the hardware registers.
-	 * loaded == false: State is stored in memory.
+	 * We have multiple paths which can save/restore the timer state onto
+	 * the hardware, so we need some way of keeping track of where the
+	 * latest state is.
 	 */
-	bool			loaded;
+	bool				loaded;
 
-	/* Virtual offset */
-	u64			cntvoff;
+	/* Duplicated state from arch_timer.c for convenience */
+	u32				host_timer_irq;
+	u32				host_timer_irq_flags;
+};
+
+struct timer_map {
+	struct arch_timer_context *direct_vtimer;
+	struct arch_timer_context *direct_ptimer;
+	struct arch_timer_context *emul_ptimer;
 };
 
 struct arch_timer_cpu {
-	struct arch_timer_context	vtimer;
-	struct arch_timer_context	ptimer;
+	struct arch_timer_context timers[NR_KVM_TIMERS];
 
 	/* Background timer used when the guest is not running */
 	struct hrtimer			bg_timer;
 
-	/* Physical timer emulation */
-	struct hrtimer			phys_timer;
-
 	/* Is the timer enabled */
 	bool			enabled;
 };
@@ -76,9 +97,6 @@ int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr);
 
 bool kvm_timer_is_pending(struct kvm_vcpu *vcpu);
 
-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_load(struct kvm_vcpu *vcpu);
@@ -88,7 +106,19 @@ void kvm_timer_init_vhe(void);
 
 bool kvm_arch_timer_get_input_level(int vintid);
 
-#define vcpu_vtimer(v)	(&(v)->arch.timer_cpu.vtimer)
-#define vcpu_ptimer(v)	(&(v)->arch.timer_cpu.ptimer)
+#define vcpu_timer(v)	(&(v)->arch.timer_cpu)
+#define vcpu_get_timer(v,t)	(&vcpu_timer(v)->timers[(t)])
+#define vcpu_vtimer(v)	(&(v)->arch.timer_cpu.timers[TIMER_VTIMER])
+#define vcpu_ptimer(v)	(&(v)->arch.timer_cpu.timers[TIMER_PTIMER])
+
+#define arch_timer_ctx_index(ctx)	((ctx) - vcpu_timer((ctx)->vcpu)->timers)
+
+u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu,
+			      enum kvm_arch_timers tmr,
+			      enum kvm_arch_timer_regs treg);
+void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu,
+				enum kvm_arch_timers tmr,
+				enum kvm_arch_timer_regs treg,
+				u64 val);
 
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c38cc5eb7e73..9d55c63db09b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -48,6 +48,27 @@
  */
 #define KVM_MEMSLOT_INVALID	(1UL << 16)
 
+/*
+ * Bit 63 of the memslot generation number is an "update in-progress flag",
+ * e.g. is temporarily set for the duration of install_new_memslots().
+ * This flag effectively creates a unique generation number that is used to
+ * mark cached memslot data, e.g. MMIO accesses, as potentially being stale,
+ * i.e. may (or may not) have come from the previous memslots generation.
+ *
+ * This is necessary because the actual memslots update is not atomic with
+ * respect to the generation number update.  Updating the generation number
+ * first would allow a vCPU to cache a spte from the old memslots using the
+ * new generation number, and updating the generation number after switching
+ * to the new memslots would allow cache hits using the old generation number
+ * to reference the defunct memslots.
+ *
+ * This mechanism is used to prevent getting hits in KVM's caches while a
+ * memslot update is in-progress, and to prevent cache hits *after* updating
+ * the actual generation number against accesses that were inserted into the
+ * cache *before* the memslots were updated.
+ */
+#define KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS	BIT_ULL(63)
+
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
@@ -634,7 +655,7 @@ void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
 			   struct kvm_memory_slot *dont);
 int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
 			    unsigned long npages);
-void kvm_arch_memslots_updated(struct kvm *kvm, struct kvm_memslots *slots);
+void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				struct kvm_memory_slot *memslot,
 				const struct kvm_userspace_memory_region *mem,
@@ -1182,6 +1203,7 @@ extern bool kvm_rebooting;
 
 extern unsigned int halt_poll_ns;
 extern unsigned int halt_poll_ns_grow;
+extern unsigned int halt_poll_ns_grow_start;
 extern unsigned int halt_poll_ns_shrink;
 
 struct kvm_device {