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

Pull KVM updates from Paolo Bonzini:
 "Much x86 work was pushed out to 5.12, but ARM more than made up for it.

  ARM:
   - PSCI relay at EL2 when "protected KVM" is enabled
   - New exception injection code
   - Simplification of AArch32 system register handling
   - Fix PMU accesses when no PMU is enabled
   - Expose CSV3 on non-Meltdown hosts
   - Cache hierarchy discovery fixes
   - PV steal-time cleanups
   - Allow function pointers at EL2
   - Various host EL2 entry cleanups
   - Simplification of the EL2 vector allocation

  s390:
   - memcg accouting for s390 specific parts of kvm and gmap
   - selftest for diag318
   - new kvm_stat for when async_pf falls back to sync

  x86:
   - Tracepoints for the new pagetable code from 5.10
   - Catch VFIO and KVM irqfd events before userspace
   - Reporting dirty pages to userspace with a ring buffer
   - SEV-ES host support
   - Nested VMX support for wait-for-SIPI activity state
   - New feature flag (AVX512 FP16)
   - New system ioctl to report Hyper-V-compatible paravirtualization features

  Generic:
   - Selftest improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (171 commits)
  KVM: SVM: fix 32-bit compilation
  KVM: SVM: Add AP_JUMP_TABLE support in prep for AP booting
  KVM: SVM: Provide support to launch and run an SEV-ES guest
  KVM: SVM: Provide an updated VMRUN invocation for SEV-ES guests
  KVM: SVM: Provide support for SEV-ES vCPU loading
  KVM: SVM: Provide support for SEV-ES vCPU creation/loading
  KVM: SVM: Update ASID allocation to support SEV-ES guests
  KVM: SVM: Set the encryption mask for the SVM host save area
  KVM: SVM: Add NMI support for an SEV-ES guest
  KVM: SVM: Guest FPU state save/restore not needed for SEV-ES guest
  KVM: SVM: Do not report support for SMM for an SEV-ES guest
  KVM: x86: Update __get_sregs() / __set_sregs() to support SEV-ES
  KVM: SVM: Add support for CR8 write traps for an SEV-ES guest
  KVM: SVM: Add support for CR4 write traps for an SEV-ES guest
  KVM: SVM: Add support for CR0 write traps for an SEV-ES guest
  KVM: SVM: Add support for EFER write traps for an SEV-ES guest
  KVM: SVM: Support string IO operations for an SEV-ES guest
  KVM: SVM: Support MMIO for an SEV-ES guest
  KVM: SVM: Create trace events for VMGEXIT MSR protocol processing
  KVM: SVM: Create trace events for VMGEXIT processing
  ...

10 files changed, 271 insertions, 7 deletions

diff --git a/include/kvm/arm_pmu.h b/include/kvm/arm_pmu.h
index 1d94acd0bc85..fc85f50fa0e9 100644
--- a/include/kvm/arm_pmu.h
+++ b/include/kvm/arm_pmu.h
@@ -24,13 +24,11 @@ struct kvm_pmu {
 	int irq_num;
 	struct kvm_pmc pmc[ARMV8_PMU_MAX_COUNTERS];
 	DECLARE_BITMAP(chained, ARMV8_PMU_MAX_COUNTER_PAIRS);
-	bool ready;
 	bool created;
 	bool irq_level;
 	struct irq_work overflow_work;
 };
 
-#define kvm_arm_pmu_v3_ready(v)		((v)->arch.pmu.ready)
 #define kvm_arm_pmu_irq_initialized(v)	((v)->arch.pmu.irq_num >= VGIC_NR_SGIS)
 u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx);
 void kvm_pmu_set_counter_value(struct kvm_vcpu *vcpu, u64 select_idx, u64 val);
@@ -61,7 +59,6 @@ int kvm_arm_pmu_v3_enable(struct kvm_vcpu *vcpu);
 struct kvm_pmu {
 };
 
-#define kvm_arm_pmu_v3_ready(v)		(false)
 #define kvm_arm_pmu_irq_initialized(v)	(false)
 static inline u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu,
 					    u64 select_idx)
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index a8d8fdcd3723..3d74f1060bd1 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -402,6 +402,7 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq,
 				 struct kvm_kernel_irq_routing_entry *irq_entry);
 
 int vgic_v4_load(struct kvm_vcpu *vcpu);
+void vgic_v4_commit(struct kvm_vcpu *vcpu);
 int vgic_v4_put(struct kvm_vcpu *vcpu, bool need_db);
 
 #endif /* __KVM_ARM_VGIC_H */
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index dc4fd8a6644d..fa0a524baed0 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -41,6 +41,7 @@ struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
 __u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
+void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
 
 DECLARE_PER_CPU(int, eventfd_wake_count);
 
@@ -82,6 +83,11 @@ static inline bool eventfd_signal_count(void)
 	return false;
 }
 
+static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
+{
+
+}
+
 #endif
 
 #endif /* _LINUX_EVENTFD_H */
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 6976b8331b60..943c3411ca10 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -39,6 +39,8 @@ struct its_vpe {
 	irq_hw_number_t		vpe_db_lpi;
 	/* VPE resident */
 	bool			resident;
+	/* VPT parse complete */
+	bool			ready;
 	union {
 		/* GICv4.0 implementations */
 		struct {
@@ -104,6 +106,7 @@ enum its_vcpu_info_cmd_type {
 	PROP_UPDATE_AND_INV_VLPI,
 	SCHEDULE_VPE,
 	DESCHEDULE_VPE,
+	COMMIT_VPE,
 	INVALL_VPE,
 	PROP_UPDATE_VSGI,
 };
@@ -129,6 +132,7 @@ int its_alloc_vcpu_irqs(struct its_vm *vm);
 void its_free_vcpu_irqs(struct its_vm *vm);
 int its_make_vpe_resident(struct its_vpe *vpe, bool g0en, bool g1en);
 int its_make_vpe_non_resident(struct its_vpe *vpe, bool db);
+int its_commit_vpe(struct its_vpe *vpe);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
new file mode 100644
index 000000000000..120e5e90fa1d
--- /dev/null
+++ b/include/linux/kvm_dirty_ring.h
@@ -0,0 +1,103 @@
+#ifndef KVM_DIRTY_RING_H
+#define KVM_DIRTY_RING_H
+
+#include <linux/kvm.h>
+
+/**
+ * kvm_dirty_ring: KVM internal dirty ring structure
+ *
+ * @dirty_index: free running counter that points to the next slot in
+ *               dirty_ring->dirty_gfns, where a new dirty page should go
+ * @reset_index: free running counter that points to the next dirty page
+ *               in dirty_ring->dirty_gfns for which dirty trap needs to
+ *               be reenabled
+ * @size:        size of the compact list, dirty_ring->dirty_gfns
+ * @soft_limit:  when the number of dirty pages in the list reaches this
+ *               limit, vcpu that owns this ring should exit to userspace
+ *               to allow userspace to harvest all the dirty pages
+ * @dirty_gfns:  the array to keep the dirty gfns
+ * @index:       index of this dirty ring
+ */
+struct kvm_dirty_ring {
+	u32 dirty_index;
+	u32 reset_index;
+	u32 size;
+	u32 soft_limit;
+	struct kvm_dirty_gfn *dirty_gfns;
+	int index;
+};
+
+#if (KVM_DIRTY_LOG_PAGE_OFFSET == 0)
+/*
+ * If KVM_DIRTY_LOG_PAGE_OFFSET not defined, kvm_dirty_ring.o should
+ * not be included as well, so define these nop functions for the arch.
+ */
+static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
+{
+	return 0;
+}
+
+static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
+				       int index, u32 size)
+{
+	return 0;
+}
+
+static inline struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm)
+{
+	return NULL;
+}
+
+static inline int kvm_dirty_ring_reset(struct kvm *kvm,
+				       struct kvm_dirty_ring *ring)
+{
+	return 0;
+}
+
+static inline void kvm_dirty_ring_push(struct kvm_dirty_ring *ring,
+				       u32 slot, u64 offset)
+{
+}
+
+static inline struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring,
+						   u32 offset)
+{
+	return NULL;
+}
+
+static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
+{
+}
+
+static inline bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring)
+{
+	return true;
+}
+
+#else /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+u32 kvm_dirty_ring_get_rsvd_entries(void);
+int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
+struct kvm_dirty_ring *kvm_dirty_ring_get(struct kvm *kvm);
+
+/*
+ * called with kvm->slots_lock held, returns the number of
+ * processed pages.
+ */
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
+
+/*
+ * returns =0: successfully pushed
+ *         <0: unable to push, need to wait
+ */
+void kvm_dirty_ring_push(struct kvm_dirty_ring *ring, u32 slot, u64 offset);
+
+/* for use in vm_operations_struct */
+struct page *kvm_dirty_ring_get_page(struct kvm_dirty_ring *ring, u32 offset);
+
+void kvm_dirty_ring_free(struct kvm_dirty_ring *ring);
+bool kvm_dirty_ring_soft_full(struct kvm_dirty_ring *ring);
+
+#endif /* KVM_DIRTY_LOG_PAGE_OFFSET == 0 */
+
+#endif	/* KVM_DIRTY_RING_H */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 7f2e2a09ebbd..f3b1013fb22c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -34,6 +34,7 @@
 #include <linux/kvm_types.h>
 
 #include <asm/kvm_host.h>
+#include <linux/kvm_dirty_ring.h>
 
 #ifndef KVM_MAX_VCPU_ID
 #define KVM_MAX_VCPU_ID KVM_MAX_VCPUS
@@ -319,6 +320,7 @@ struct kvm_vcpu {
 	bool preempted;
 	bool ready;
 	struct kvm_vcpu_arch arch;
+	struct kvm_dirty_ring dirty_ring;
 };
 
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)
@@ -349,6 +351,11 @@ struct kvm_memory_slot {
 	u16 as_id;
 };
 
+static inline bool kvm_slot_dirty_track_enabled(struct kvm_memory_slot *slot)
+{
+	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
+}
+
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)
 {
 	return ALIGN(memslot->npages, BITS_PER_LONG) / 8;
@@ -505,6 +512,7 @@ struct kvm {
 	struct srcu_struct irq_srcu;
 	pid_t userspace_pid;
 	unsigned int max_halt_poll_ns;
+	u32 dirty_ring_size;
 };
 
 #define kvm_err(fmt, ...) \
@@ -792,13 +800,12 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			offset_in_page(__gpa), v);			\
 })
 
-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);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
-void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
+void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
 struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
@@ -1478,4 +1485,14 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
 }
 #endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
 
+/*
+ * This defines how many reserved entries we want to keep before we
+ * kick the vcpu to the userspace to avoid dirty ring full.  This
+ * value can be tuned to higher if e.g. PML is enabled on the host.
+ */
+#define  KVM_DIRTY_RING_RSVD_ENTRIES  64
+
+/* Max number of entries allowed for each kvm dirty ring */
+#define  KVM_DIRTY_RING_MAX_ENTRIES  65536
+
 #endif
diff --git a/include/linux/psci.h b/include/linux/psci.h
index 2a1bfb890e58..4ca0060a3fc4 100644
--- a/include/linux/psci.h
+++ b/include/linux/psci.h
@@ -34,6 +34,15 @@ struct psci_operations {
 
 extern struct psci_operations psci_ops;
 
+struct psci_0_1_function_ids {
+	u32 cpu_suspend;
+	u32 cpu_on;
+	u32 cpu_off;
+	u32 migrate;
+};
+
+struct psci_0_1_function_ids get_psci_0_1_function_ids(void);
+
 #if defined(CONFIG_ARM_PSCI_FW)
 int __init psci_dt_init(void);
 #else
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 27fb99cfeb02..fe10e8570a52 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -22,6 +22,7 @@ int default_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int
 #define WQ_FLAG_BOOKMARK	0x04
 #define WQ_FLAG_CUSTOM		0x08
 #define WQ_FLAG_DONE		0x10
+#define WQ_FLAG_PRIORITY	0x20
 
 /*
  * A single wait-queue entry structure:
@@ -164,11 +165,20 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 
 extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
 static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
-	list_add(&wq_entry->entry, &wq_head->head);
+	struct list_head *head = &wq_head->head;
+	struct wait_queue_entry *wq;
+
+	list_for_each_entry(wq, &wq_head->head, entry) {
+		if (!(wq->flags & WQ_FLAG_PRIORITY))
+			break;
+		head = &wq->entry;
+	}
+	list_add(&wq_entry->entry, head);
 }
 
 /*
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 26cfb0fa8e7e..49d7d0fe29f6 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -399,6 +399,69 @@ TRACE_EVENT(kvm_halt_poll_ns,
 #define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \
 	trace_kvm_halt_poll_ns(false, vcpu_id, new, old)
 
+TRACE_EVENT(kvm_dirty_ring_push,
+	TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset),
+	TP_ARGS(ring, slot, offset),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+		__field(u32, slot)
+		__field(u64, offset)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+		__entry->slot           = slot;
+		__entry->offset         = offset;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x "
+		  "slot %u offset 0x%llx (used %u)",
+		  __entry->index, __entry->dirty_index,
+		  __entry->reset_index,  __entry->slot, __entry->offset,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_reset,
+	TP_PROTO(struct kvm_dirty_ring *ring),
+	TP_ARGS(ring),
+
+	TP_STRUCT__entry(
+		__field(int, index)
+		__field(u32, dirty_index)
+		__field(u32, reset_index)
+	),
+
+	TP_fast_assign(
+		__entry->index          = ring->index;
+		__entry->dirty_index    = ring->dirty_index;
+		__entry->reset_index    = ring->reset_index;
+	),
+
+	TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)",
+		  __entry->index, __entry->dirty_index, __entry->reset_index,
+		  __entry->dirty_index - __entry->reset_index)
+);
+
+TRACE_EVENT(kvm_dirty_ring_exit,
+	TP_PROTO(struct kvm_vcpu *vcpu),
+	TP_ARGS(vcpu),
+
+	TP_STRUCT__entry(
+	    __field(int, vcpu_id)
+	),
+
+	TP_fast_assign(
+	    __entry->vcpu_id = vcpu->vcpu_id;
+	),
+
+	TP_printk("vcpu %d", __entry->vcpu_id)
+);
+
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index ca41220b40b8..886802b8ffba 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -250,6 +250,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_ARM_NISV         28
 #define KVM_EXIT_X86_RDMSR        29
 #define KVM_EXIT_X86_WRMSR        30
+#define KVM_EXIT_DIRTY_RING_FULL  31
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -1053,6 +1054,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_SYS_HYPERV_CPUID 191
+#define KVM_CAP_DIRTY_LOG_RING 192
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1511,7 +1514,7 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
 #define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
 
-/* Available with KVM_CAP_HYPERV_CPUID */
+/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */
 #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
 
 /* Available with KVM_CAP_ARM_SVE */
@@ -1557,6 +1560,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_X86_MSR_FILTER */
 #define KVM_X86_SET_MSR_FILTER	_IOW(KVMIO,  0xc6, struct kvm_msr_filter)
 
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc7)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */
@@ -1710,4 +1716,52 @@ struct kvm_hyperv_eventfd {
 #define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE    (1 << 0)
 #define KVM_DIRTY_LOG_INITIALLY_SET            (1 << 1)
 
+/*
+ * Arch needs to define the macro after implementing the dirty ring
+ * feature.  KVM_DIRTY_LOG_PAGE_OFFSET should be defined as the
+ * starting page offset of the dirty ring structures.
+ */
+#ifndef KVM_DIRTY_LOG_PAGE_OFFSET
+#define KVM_DIRTY_LOG_PAGE_OFFSET 0
+#endif
+
+/*
+ * KVM dirty GFN flags, defined as:
+ *
+ * |---------------+---------------+--------------|
+ * | bit 1 (reset) | bit 0 (dirty) | Status       |
+ * |---------------+---------------+--------------|
+ * |             0 |             0 | Invalid GFN  |
+ * |             0 |             1 | Dirty GFN    |
+ * |             1 |             X | GFN to reset |
+ * |---------------+---------------+--------------|
+ *
+ * Lifecycle of a dirty GFN goes like:
+ *
+ *      dirtied         harvested        reset
+ * 00 -----------> 01 -------------> 1X -------+
+ *  ^                                          |
+ *  |                                          |
+ *  +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion after harvesting an entry.  Also, it must not skip any
+ * dirty bits, so that dirty bits are always harvested in sequence.
+ */
+#define KVM_DIRTY_GFN_F_DIRTY           BIT(0)
+#define KVM_DIRTY_GFN_F_RESET           BIT(1)
+#define KVM_DIRTY_GFN_F_MASK            0x3
+
+/*
+ * KVM dirty rings should be mapped at KVM_DIRTY_LOG_PAGE_OFFSET of
+ * per-vcpu mmaped regions as an array of struct kvm_dirty_gfn.  The
+ * size of the gfn buffer is decided by the first argument when
+ * enabling KVM_CAP_DIRTY_LOG_RING.
+ */
+struct kvm_dirty_gfn {
+	__u32 flags;
+	__u32 slot;
+	__u64 offset;
+};
+
 #endif /* __LINUX_KVM_H */