KVM: Dirty ring interface

index ffcd96fc02d0..ef523e760743 100644
@@ -244,9 +244,6 @@ TRACE_EVENT(
 		  __entry->access)
 );
 
-#define __spte_satisfied(__spte)				\
-	(__entry->retry && is_writable_pte(__entry->__spte))
-
 TRACE_EVENT(
 	fast_page_fault,
 	TP_PROTO(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u32 error_code,

@@ -274,12 +271,10 @@ TRACE_EVENT(
 	),
 
 	TP_printk("vcpu %d gva %llx error_code %s sptep %p old %#llx"
-		  " new %llx spurious %d fixed %d", __entry->vcpu_id,
+		  " new %llx ret %d", __entry->vcpu_id,
 		  __entry->cr2_or_gpa, __print_flags(__entry->error_code, "|",
 		  kvm_mmu_trace_pferr_flags), __entry->sptep,
-		  __entry->old_spte, __entry->new_spte,
-		  __spte_satisfied(old_spte), __spte_satisfied(new_spte)
-	)
+		  __entry->old_spte, __entry->new_spte, __entry->retry)
 );
 
 TRACE_EVENT(

index 01276e3d01b9..5e7bbaf7a36b 100644
@@ -346,6 +346,7 @@ struct kvm_memory_slot {
 	unsigned long userspace_addr;
 	u32 flags;
 	short id;
+	u16 as_id;
 };
 
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)

index 74bdb7bf3295..ebdd98a30e82 100644
@@ -1243,6 +1243,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (!mem->memory_size)
 		return kvm_delete_memslot(kvm, mem, &old, as_id);
 
+	new.as_id = as_id;
 	new.id = id;
 	new.base_gfn = mem->guest_phys_addr >> PAGE_SHIFT;
 	new.npages = mem->memory_size >> PAGE_SHIFT;

index 42a2d0d3984a..39477f8f3f2c 100644
@@ -1650,7 +1650,8 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
 
 int kvm_is_in_guest(void);
 
-int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
+void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
+				     u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 

index e80daa98682f..86e9621ba026 100644
@@ -235,7 +235,9 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
  */
 static int avic_update_access_page(struct kvm *kvm, bool activate)
 {
-	int ret = 0;
+	void __user *ret;
+	int r = 0;
+
 
 	mutex_lock(&kvm->slots_lock);
 	/*

@@ -251,13 +253,16 @@ static int avic_update_access_page(struct kvm *kvm, bool activate)
 				      APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
 				      APIC_DEFAULT_PHYS_BASE,
 				      activate ? PAGE_SIZE : 0);
-	if (ret)
+	if (IS_ERR(ret)) {
+		r = PTR_ERR(ret);
 		goto out;
+	}
+
 
 	kvm->arch.apic_access_page_done = activate;
 out:
 	mutex_unlock(&kvm->slots_lock);
-	return ret;
+	return r;
 }
 
 static int avic_init_backing_page(struct kvm_vcpu *vcpu)

146 lines not on this page · raw message

84 lines not on this page · raw message

index ebdd98a30e82..a7460e93d457 100644
@@ -144,7 +144,9 @@ static void hardware_disable_all(void);
 
 static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
 
-static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+				    struct kvm_memory_slot *memslot,
+				    gfn_t gfn);
 
 __visible bool kvm_rebooting;
 EXPORT_SYMBOL_GPL(kvm_rebooting);

@@ -2120,7 +2122,8 @@ int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_map);
 
-static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
+static void __kvm_unmap_gfn(struct kvm *kvm,
+			struct kvm_memory_slot *memslot,
 			struct kvm_host_map *map,
 			struct gfn_to_pfn_cache *cache,
 			bool dirty, bool atomic)

@@ -2145,7 +2148,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 #endif
 
 	if (dirty)
-		mark_page_dirty_in_slot(memslot, map->gfn);
+		mark_page_dirty_in_slot(kvm, memslot, map->gfn);
 
 	if (cache)
 		cache->dirty |= dirty;

@@ -2159,7 +2162,7 @@ static void __kvm_unmap_gfn(struct kvm_memory_slot *memslot,
 int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, 
 		  struct gfn_to_pfn_cache *cache, bool dirty, bool atomic)
 {
-	__kvm_unmap_gfn(gfn_to_memslot(vcpu->kvm, map->gfn), map,
+	__kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map,
 			cache, dirty, atomic);
 	return 0;
 }

@@ -2167,8 +2170,8 @@ EXPORT_SYMBOL_GPL(kvm_unmap_gfn);
 
 void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty)
 {
-	__kvm_unmap_gfn(kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), map, NULL,
-			dirty, false);
+	__kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn),
+			map, NULL, dirty, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
 

@@ -2342,7 +2345,8 @@ int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa,
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic);
 
-static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
+static int __kvm_write_guest_page(struct kvm *kvm,
+				  struct kvm_memory_slot *memslot, gfn_t gfn,
 			          const void *data, int offset, int len)
 {
 	int r;

@@ -2354,7 +2358,7 @@ static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn,
 	r = __copy_to_user((void __user *)addr + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 	return 0;
 }
 

@@ -2363,7 +2367,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_write_guest_page);
 

@@ -2372,7 +2376,7 @@ int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
 {
 	struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 
-	return __kvm_write_guest_page(slot, gfn, data, offset, len);
+	return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page);
 

@@ -2491,7 +2495,7 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT);
+	mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT);
 
 	return 0;
 }

@@ -2558,7 +2562,8 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
 }
 EXPORT_SYMBOL_GPL(kvm_clear_guest);
 
-static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot,
+static void mark_page_dirty_in_slot(struct kvm *kvm,
+				    struct kvm_memory_slot *memslot,
 				    gfn_t gfn)
 {
 	if (memslot && memslot->dirty_bitmap) {

@@ -2573,7 +2578,7 @@ void mark_page_dirty(struct kvm *kvm, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = gfn_to_memslot(kvm, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(mark_page_dirty);
 

@@ -2582,7 +2587,7 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn)
 	struct kvm_memory_slot *memslot;
 
 	memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
-	mark_page_dirty_in_slot(memslot, gfn);
+	mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty);
 

index 39477f8f3f2c..02ddcf664d13 100644
@@ -1197,6 +1197,7 @@ struct kvm_x86_ops {
 					   struct kvm_memory_slot *slot,
 					   gfn_t offset, unsigned long mask);
 	int (*write_log_dirty)(struct kvm_vcpu *vcpu);
+	int (*cpu_dirty_log_size)(void);
 
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;

@@ -1698,4 +1699,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
 #define GET_SMSTATE(type, buf, offset)		\
 	(*(type *)((buf) + (offset) - 0x7e00))
 
+int kvm_cpu_dirty_log_size(void);
+
 #endif /* _ASM_X86_KVM_HOST_H */

index 3f3f780c8c65..99b15ce39e75 100644
@@ -12,6 +12,7 @@
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+#define KVM_DIRTY_LOG_PAGE_OFFSET 64
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1

index 8071952e9cf2..94d84a383b80 100644
@@ -1753,6 +1753,14 @@ int kvm_arch_write_log_dirty(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+int kvm_cpu_dirty_log_size(void)
+{
+	if (kvm_x86_ops.cpu_dirty_log_size)
+		return kvm_x86_ops.cpu_dirty_log_size();
+
+	return 0;
+}
+
 bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
 				    struct kvm_memory_slot *slot, u64 gfn)
 {

index ad1d9120283e..3bd6304784a4 100644
@@ -7703,6 +7703,11 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 	return supported & BIT(bit);
 }
 
+static int vmx_cpu_dirty_log_size(void)
+{
+	return enable_pml ? PML_ENTITY_NUM : 0;
+}
+
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.hardware_unsetup = hardware_unsetup,
 

@@ -7838,6 +7843,7 @@ static struct kvm_x86_ops vmx_x86_ops __initdata = {
 	.nested_get_evmcs_version = NULL,
 	.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
 	.apic_init_signal_blocked = vmx_apic_init_signal_blocked,
+	.cpu_dirty_log_size = vmx_cpu_dirty_log_size,
 };
 
 static __init int hardware_setup(void)

@@ -7955,6 +7961,7 @@ static __init int hardware_setup(void)
 		vmx_x86_ops.slot_disable_log_dirty = NULL;
 		vmx_x86_ops.flush_log_dirty = NULL;
 		vmx_x86_ops.enable_log_dirty_pt_masked = NULL;
+		vmx_x86_ops.cpu_dirty_log_size = NULL;
 	}
 
 	if (!cpu_has_vmx_preemption_timer())

@@ -8019,7 +8026,6 @@ static struct kvm_x86_init_ops vmx_init_ops __initdata = {
 	.disabled_by_bios = vmx_disabled_by_bios,
 	.check_processor_compatibility = vmx_check_processor_compat,
 	.hardware_setup = hardware_setup,
-
 	.runtime_ops = &vmx_x86_ops,
 };
 

index 5c106ca948ed..3e56134a70fb 100644
@@ -8207,6 +8207,15 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	bool req_immediate_exit = false;
 
+	/* Forbid vmenter if vcpu dirty ring is soft-full */
+	if (unlikely(vcpu->kvm->dirty_ring_size &&
+		     kvm_dirty_ring_soft_full(&vcpu->dirty_ring))) {
+		vcpu->run->exit_reason = KVM_EXIT_DIRTY_RING_FULL;
+		trace_kvm_dirty_ring_exit(vcpu);
+		r = 0;
+		goto out;
+	}
+
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
 			if (unlikely(!kvm_x86_ops.get_vmcs12_pages(vcpu))) {

103 lines not on this page · raw message

index 5e7bbaf7a36b..a7eaef494f45 100644
@@ -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 ready;
 	struct kvm_vcpu_arch arch;
 	struct dentry *debugfs_dentry;
+	struct kvm_dirty_ring dirty_ring;
 };
 
 static inline int kvm_vcpu_exiting_guest_mode(struct kvm_vcpu *vcpu)

@@ -504,6 +506,7 @@ struct kvm {
 	struct srcu_struct srcu;
 	struct srcu_struct irq_srcu;
 	pid_t userspace_pid;
+	u32 dirty_ring_size;
 };
 
 #define kvm_err(fmt, ...) \

@@ -1422,4 +1425,14 @@ int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
 				uintptr_t data, const char *name,
 				struct task_struct **thread_ptr);
 
+/*
+ * 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

84 lines not on this page · raw message

75 lines not on this page · raw message

197 lines not on this page · raw message

185 lines not on this page · raw message

index daca53ed5a74..9639cf8d8c9c 100644
@@ -1355,6 +1355,10 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 	unsigned long n;
 	unsigned long any = 0;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -EINVAL;
+
 	*memslot = NULL;
 	*is_dirty = 0;
 

@@ -1416,6 +1420,10 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log)
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -EINVAL;
+
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)

@@ -1524,6 +1532,10 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm,
 	unsigned long *dirty_bitmap_buffer;
 	bool flush;
 
+	/* Dirty ring tracking is exclusive to dirty log tracking */
+	if (kvm->dirty_ring_size)
+		return -EINVAL;
+
 	as_id = log->slot >> 16;
 	id = (u16)log->slot;
 	if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)

index 94d84a383b80..ebc86f661db3 100644
@@ -1276,8 +1276,8 @@ gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu, gfn_t gfn,
 	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return NULL;
-	if (no_dirty_log && slot->dirty_bitmap)
-		return NULL;
+	if (no_dirty_log && kvm_slot_dirty_track_enabled(slot))
+		return false;
 
 	return slot;
 }

index a7eaef494f45..5081c6e2ae06 100644
@@ -351,6 +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;

index 9639cf8d8c9c..ae7ba67eab63 100644
@@ -1294,7 +1294,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* Allocate/free page dirty bitmap as needed */
 	if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
 		new.dirty_bitmap = NULL;
-	else if (!new.dirty_bitmap) {
+	else if (!new.dirty_bitmap && !kvm->dirty_ring_size) {
 		r = kvm_alloc_dirty_bitmap(&new);
 		if (r)
 			return r;

@@ -2581,7 +2581,7 @@ static void mark_page_dirty_in_slot(struct kvm *kvm,
 				    struct kvm_memory_slot *memslot,
 				    gfn_t gfn)
 {
-	if (memslot && memslot->dirty_bitmap) {
+	if (memslot && kvm_slot_dirty_track_enabled(memslot)) {
 		unsigned long rel_gfn = gfn - memslot->base_gfn;
 		u32 slot = (memslot->as_id << 16) | memslot->id;
 

index 752ec158ac59..6a8275a22861 100644
@@ -195,7 +195,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 				    page);
 		}
 
-		if (test_bit_le(page, bmap)) {
+		if (test_and_clear_bit_le(page, bmap)) {
 			host_dirty_count++;
 			/*
 			 * If the bit is set, the value written onto

index 428c7dde6b4b..74f150c69ee6 100644
@@ -236,6 +236,7 @@ struct kvm_hyperv_exit {
 #define KVM_EXIT_IOAPIC_EOI       26
 #define KVM_EXIT_HYPERV           27
 #define KVM_EXIT_ARM_NISV         28
+#define KVM_EXIT_DIRTY_RING_FULL  29
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */

@@ -1017,6 +1018,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_VCPU_RESETS 179
 #define KVM_CAP_S390_PROTECTED 180
 #define KVM_CAP_PPC_SECURE_GUEST 181
+#define KVM_CAP_DIRTY_LOG_RING 182
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

@@ -1518,6 +1520,9 @@ struct kvm_pv_cmd {
 /* Available with KVM_CAP_S390_PROTECTED */
 #define KVM_S390_PV_COMMAND		_IOWR(KVMIO, 0xc5, struct kvm_pv_cmd)
 
+/* Available with KVM_CAP_DIRTY_LOG_RING */
+#define KVM_RESET_DIRTY_RINGS		_IO(KVMIO, 0xc6)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */

@@ -1671,4 +1676,52 @@ 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         collected        reset
+ * 00 -----------> 01 -------------> 1X -------+
+ *  ^                                          |
+ *  |                                          |
+ *  +------------------------------------------+
+ *
+ * The userspace program is only responsible for the 01->1X state
+ * conversion (to collect dirty bits).  Also, it must not skip any
+ * dirty bits so that dirty bits are always collected 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 */

deleted file mode 100644
index 11672ec6f74e..000000000000
@@ -1,6 +0,0 @@
-#define USE_CLEAR_DIRTY_LOG
-#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
-#define KVM_DIRTY_LOG_INITIALLY_SET         (1 << 1)
-#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
-		KVM_DIRTY_LOG_INITIALLY_SET)
-#include "dirty_log_test.c"

259 lines not on this page · raw message

index 139ccb550618..a2160946bcf5 100644
@@ -178,6 +178,15 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
 }
 
+static void default_after_vcpu_run(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
+		    "Invalid guest sync status: exit_reason=%s\n",
+		    exit_reason_str(run->exit_reason));
+}
+
 struct log_mode {
 	const char *name;
 	/* Return true if this mode is supported, otherwise false */

@@ -187,16 +196,20 @@ struct log_mode {
 	/* Hook to collect the dirty pages into the bitmap provided */
 	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
 				     void *bitmap, uint32_t num_pages);
+	/* Hook to call when after each vcpu run */
+	void (*after_vcpu_run)(struct kvm_vm *vm);
 } log_modes[LOG_MODE_NUM] = {
 	{
 		.name = "dirty-log",
 		.collect_dirty_pages = dirty_log_collect_dirty_pages,
+		.after_vcpu_run = default_after_vcpu_run,
 	},
 	{
 		.name = "clear-log",
 		.supported = clear_log_supported,
 		.create_vm_done = clear_log_create_vm_done,
 		.collect_dirty_pages = clear_log_collect_dirty_pages,
+		.after_vcpu_run = default_after_vcpu_run,
 	},
 };
 

@@ -247,6 +260,14 @@ static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
 }
 
+static void log_mode_after_vcpu_run(struct kvm_vm *vm)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->after_vcpu_run)
+		mode->after_vcpu_run(vm);
+}
+
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;

@@ -261,25 +282,16 @@ static void *vcpu_worker(void *data)
 	struct kvm_vm *vm = data;
 	uint64_t *guest_array;
 	uint64_t pages_count = 0;
-	struct kvm_run *run;
-
-	run = vcpu_state(vm, VCPU_ID);
 
 	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
-	generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 
 	while (!READ_ONCE(host_quit)) {
+		generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
+		pages_count += TEST_PAGES_PER_LOOP;
 		/* Let the guest dirty the random pages */
 		ret = _vcpu_run(vm, VCPU_ID);
 		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
-		if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
-			pages_count += TEST_PAGES_PER_LOOP;
-			generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
-		} else {
-			TEST_FAIL("Invalid guest sync status: "
-				  "exit_reason=%s\n",
-				  exit_reason_str(run->exit_reason));
-		}
+		log_mode_after_vcpu_run(vm);
 	}
 
 	pr_info("Dirtied %"PRIu64" pages\n", pages_count);

index a2160946bcf5..531431cff4fc 100644
@@ -12,8 +12,10 @@
 #include <unistd.h>
 #include <time.h>
 #include <pthread.h>
+#include <semaphore.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
+#include <asm/barrier.h>
 
 #include "test_util.h"
 #include "kvm_util.h"

@@ -57,6 +59,8 @@
 # define test_and_clear_bit_le	test_and_clear_bit
 #endif
 
+#define TEST_DIRTY_RING_COUNT		1024
+
 /*
  * Guest/Host shared variables. Ensure addr_gva2hva() and/or
  * sync_global_to/from_guest() are used when accessing from

@@ -128,6 +132,10 @@ static uint64_t host_dirty_count;
 static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
+/* Whether dirty ring reset is requested, or finished */
+static sem_t dirty_ring_vcpu_stop;
+static sem_t dirty_ring_vcpu_cont;
+
 enum log_mode_t {
 	/* Only use KVM_GET_DIRTY_LOG for logging */
 	LOG_MODE_DIRTY_LOG = 0,

@@ -135,6 +143,9 @@ enum log_mode_t {
 	/* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
 	LOG_MODE_CLEAR_LOG = 1,
 
+	/* Use dirty ring for logging */
+	LOG_MODE_DIRTY_RING = 2,
+
 	LOG_MODE_NUM,
 
 	/* Run all supported modes */

@@ -187,6 +198,120 @@ static void default_after_vcpu_run(struct kvm_vm *vm)
 		    exit_reason_str(run->exit_reason));
 }
 
+static bool dirty_ring_supported(void)
+{
+	return kvm_check_cap(KVM_CAP_DIRTY_LOG_RING);
+}
+
+static void dirty_ring_create_vm_done(struct kvm_vm *vm)
+{
+	/*
+	 * Switch to dirty ring mode after VM creation but before any
+	 * of the vcpu creation.
+	 */
+	vm_enable_dirty_ring(vm, TEST_DIRTY_RING_COUNT *
+			     sizeof(struct kvm_dirty_gfn));
+}
+
+static inline bool dirty_gfn_is_dirtied(struct kvm_dirty_gfn *gfn)
+{
+	return gfn->flags == KVM_DIRTY_GFN_F_DIRTY;
+}
+
+static inline void dirty_gfn_set_collected(struct kvm_dirty_gfn *gfn)
+{
+	gfn->flags = KVM_DIRTY_GFN_F_RESET;
+}
+
+static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
+				       int slot, void *bitmap,
+				       uint32_t num_pages, uint32_t *fetch_index)
+{
+	struct kvm_dirty_gfn *cur;
+	uint32_t count = 0;
+
+	while (true) {
+		cur = &dirty_gfns[*fetch_index % TEST_DIRTY_RING_COUNT];
+		if (!dirty_gfn_is_dirtied(cur))
+			break;
+		TEST_ASSERT(cur->slot == slot, "Slot number didn't match: "
+			    "%u != %u", cur->slot, slot);
+		TEST_ASSERT(cur->offset < num_pages, "Offset overflow: "
+			    "0x%llx >= 0x%x", cur->offset, num_pages);
+		pr_info("fetch 0x%x page %llu\n", *fetch_index, cur->offset);
+		set_bit(cur->offset, bitmap);
+		dirty_gfn_set_collected(cur);
+		(*fetch_index)++;
+		count++;
+	}
+
+	return count;
+}
+
+static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					   void *bitmap, uint32_t num_pages)
+{
+	/* We only have one vcpu */
+	static uint32_t fetch_index = 0;
+	uint32_t count = 0, cleared;
+
+	/*
+	 * Before fetching the dirty pages, we need a vmexit of the
+	 * worker vcpu to make sure the hardware dirty buffers were
+	 * flushed.  This is not needed for dirty-log/clear-log tests
+	 * because get dirty log will natually do so.
+	 *
+	 * For now we do it in the simple way - we simply wait until
+	 * the vcpu uses up the soft dirty ring, then it'll always
+	 * do a vmexit to make sure that PML buffers will be flushed.
+	 * In real hypervisors, we probably need a vcpu kick or to
+	 * stop the vcpus (before the final sync) to make sure we'll
+	 * get all the existing dirty PFNs even cached in hardware.
+	 */
+	sem_wait(&dirty_ring_vcpu_stop);
+
+	/* Only have one vcpu */
+	count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID),
+				       slot, bitmap, num_pages, &fetch_index);
+
+	cleared = kvm_vm_reset_dirty_ring(vm);
+
+	/* Cleared pages should be the same as collected */
+	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
+		    "with collected (%u)", cleared, count);
+
+	pr_info("Notifying vcpu to continue\n");
+	sem_post(&dirty_ring_vcpu_cont);
+
+	pr_info("Iteration %ld collected %u pages\n", iteration, count);
+}
+
+static void dirty_ring_after_vcpu_run(struct kvm_vm *vm)
+{
+	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+
+	/* A ucall-sync or ring-full event is allowed */
+	if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
+		/* We should allow this to continue */
+		;
+	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL) {
+		sem_post(&dirty_ring_vcpu_stop);
+		pr_info("vcpu stops because dirty ring full...\n");
+		sem_wait(&dirty_ring_vcpu_cont);
+		pr_info("vcpu continues now.\n");
+	} else {
+		TEST_ASSERT(false, "Invalid guest sync status: "
+			    "exit_reason=%s\n",
+			    exit_reason_str(run->exit_reason));
+	}
+}
+
+static void dirty_ring_before_vcpu_join(void)
+{
+	/* Kick another round of vcpu just to make sure it will quit */
+	sem_post(&dirty_ring_vcpu_cont);
+}
+
 struct log_mode {
 	const char *name;
 	/* Return true if this mode is supported, otherwise false */

@@ -198,6 +323,7 @@ struct log_mode {
 				     void *bitmap, uint32_t num_pages);
 	/* Hook to call when after each vcpu run */
 	void (*after_vcpu_run)(struct kvm_vm *vm);
+	void (*before_vcpu_join) (void);
 } log_modes[LOG_MODE_NUM] = {
 	{
 		.name = "dirty-log",

@@ -211,6 +337,14 @@ struct log_mode {
 		.collect_dirty_pages = clear_log_collect_dirty_pages,
 		.after_vcpu_run = default_after_vcpu_run,
 	},
+	{
+		.name = "dirty-ring",
+		.supported = dirty_ring_supported,
+		.create_vm_done = dirty_ring_create_vm_done,
+		.collect_dirty_pages = dirty_ring_collect_dirty_pages,
+		.before_vcpu_join = dirty_ring_before_vcpu_join,
+		.after_vcpu_run = dirty_ring_after_vcpu_run,
+	},
 };
 
 /*

@@ -268,6 +402,14 @@ static void log_mode_after_vcpu_run(struct kvm_vm *vm)
 		mode->after_vcpu_run(vm);
 }
 
+static void log_mode_before_vcpu_join(void)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->before_vcpu_join)
+		mode->before_vcpu_join();
+}
+
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;

@@ -318,14 +460,65 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 		}
 
 		if (test_and_clear_bit_le(page, bmap)) {
+			bool matched;
+
 			host_dirty_count++;
+
 			/*
 			 * If the bit is set, the value written onto
 			 * the corresponding page should be either the
 			 * previous iteration number or the current one.
 			 */
-			TEST_ASSERT(*value_ptr == iteration ||
-				    *value_ptr == iteration - 1,
+			matched = (*value_ptr == iteration ||
+				   *value_ptr == iteration - 1);
+
+			if (host_log_mode == LOG_MODE_DIRTY_RING && !matched) {
+				if (*value_ptr == iteration - 2) {
+					/*
+					 * Short answer: this case is special
+					 * only for dirty ring test where the
+					 * page is the last page before a kvm
+					 * dirty ring full in iteration N-2.
+					 *
+					 * Long answer: Assuming ring size R,
+					 * one possible condition is:
+					 *
+					 *      main thr       vcpu thr
+					 *      --------       --------
+					 *    iter=1
+					 *                   write 1 to page 0~(R-1)
+					 *                   full, vmexit
+					 *    collect 0~(R-1)
+					 *    kick vcpu
+					 *                   write 1 to (R-1)~(2R-2)
+					 *                   full, vmexit
+					 *    iter=2
+					 *    collect (R-1)~(2R-2)
+					 *    kick vcpu
+					 *                   write 1 to (2R-2)
+					 *                   (NOTE!!! "1" cached in cpu reg)
+					 *                   write 2 to (2R-1)~(3R-3)
+					 *                   full, vmexit
+					 *    iter=3
+					 *    collect (2R-2)~(3R-3)
+					 *    (here if we read value on page
+					 *     "2R-2" is 1, while iter=3!!!)
+					 */
+					matched = true;
+				} else {
+					/*
+					 * This is also special for dirty ring
+					 * when this page is exactly the last
+					 * page touched before vcpu ring full.
+					 * If it happens, we should expect the
+					 * value to change in the next round.
+					 */
+					set_bit_le(page, host_bmap_track);
+					continue;
+				}
+			}
+
+			TEST_ASSERT(matched,
 				    "Set page %"PRIu64" value %"PRIu64
 				    " incorrect (iteration=%"PRIu64")",
 				    page, *value_ptr, iteration);

@@ -488,6 +681,7 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 
 	/* Tell the vcpu thread to quit */
 	host_quit = true;
+	log_mode_before_vcpu_join();
 	pthread_join(vcpu_thread, NULL);
 
 	pr_info("Total bits checked: dirty (%"PRIu64"), clear (%"PRIu64"), "

@@ -548,6 +742,9 @@ int main(int argc, char *argv[])
 	unsigned int mode;
 	int opt, i, j;
 
+	sem_init(&dirty_ring_vcpu_stop, 0, 0);
+	sem_init(&dirty_ring_vcpu_cont, 0, 0);
+
 #ifdef __x86_64__
 	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
 #endif

index a99b875f50d2..554fdb294bef 100644
@@ -62,6 +62,7 @@ enum vm_mem_backing_src_type {
 
 int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
 
 struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
 struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);

@@ -71,6 +72,7 @@ void kvm_vm_release(struct kvm_vm *vmp);
 void kvm_vm_get_dirty_log(struct kvm_vm *vm, int slot, void *log);
 void kvm_vm_clear_dirty_log(struct kvm_vm *vm, int slot, void *log,
 			    uint64_t first_page, uint32_t num_pages);
+uint32_t kvm_vm_reset_dirty_ring(struct kvm_vm *vm);
 
 int kvm_memcmp_hva_gva(void *hva, struct kvm_vm *vm, const vm_vaddr_t gva,
 		       size_t len);

@@ -192,6 +194,7 @@ void vcpu_nested_state_get(struct kvm_vm *vm, uint32_t vcpuid,
 int vcpu_nested_state_set(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_nested_state *state, bool ignore_error);
 #endif
+void *vcpu_map_dirty_ring(struct kvm_vm *vm, uint32_t vcpuid);
 
 const char *exit_reason_str(unsigned int exit_reason);
 

89 lines not on this page · raw message

index ca56a0133127..22c84d9c8b03 100644
@@ -28,6 +28,9 @@ struct vcpu {
 	uint32_t id;
 	int fd;
 	struct kvm_run *state;
+	struct kvm_dirty_gfn *dirty_gfns;
+	uint32_t fetch_index;
+	uint32_t dirty_gfns_count;
 };
 
 struct kvm_vm {

@@ -50,6 +53,7 @@ struct kvm_vm {
 	vm_paddr_t pgd;
 	vm_vaddr_t gdt;
 	vm_vaddr_t tss;
+	uint32_t dirty_ring_size;
 };
 
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);

index 531431cff4fc..4b404dfdc2f9 100644
@@ -13,6 +13,9 @@
 #include <time.h>
 #include <pthread.h>
 #include <semaphore.h>
+#include <sys/types.h>
+#include <signal.h>
+#include <errno.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
 #include <asm/barrier.h>

@@ -59,7 +62,9 @@
 # define test_and_clear_bit_le	test_and_clear_bit
 #endif
 
-#define TEST_DIRTY_RING_COUNT		1024
+#define TEST_DIRTY_RING_COUNT		65536
+
+#define SIG_IPI SIGUSR1
 
 /*
  * Guest/Host shared variables. Ensure addr_gva2hva() and/or

@@ -135,6 +140,12 @@ static uint64_t host_track_next_count;
 /* Whether dirty ring reset is requested, or finished */
 static sem_t dirty_ring_vcpu_stop;
 static sem_t dirty_ring_vcpu_cont;
+/*
+ * This is updated by the vcpu thread to tell the host whether it's a
+ * ring-full event.  It should only be read until a sem_wait() of
+ * dirty_ring_vcpu_stop and before vcpu continues to run.
+ */
+static bool dirty_ring_vcpu_ring_full;
 
 enum log_mode_t {
 	/* Only use KVM_GET_DIRTY_LOG for logging */

@@ -156,6 +167,33 @@ enum log_mode_t {
 static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
 /* Logging mode for current run */
 static enum log_mode_t host_log_mode;
+static pthread_t vcpu_thread;
+
+/* Only way to pass this to the signal handler */
+static struct kvm_vm *current_vm;
+
+static void vcpu_sig_handler(int sig)
+{
+	TEST_ASSERT(sig == SIG_IPI, "unknown signal: %d", sig);
+}
+
+static void vcpu_kick(void)
+{
+	pthread_kill(vcpu_thread, SIG_IPI);
+}
+
+/*
+ * In our test we do signal tricks, let's use a better version of
+ * sem_wait to avoid signal interrupts
+ */
+static void sem_wait_until(sem_t *sem)
+{
+	int ret;
+
+	do
+		ret = sem_wait(sem);
+	while (ret == -1 && errno == EINTR);
+}
 
 static bool clear_log_supported(void)
 {

@@ -189,10 +227,13 @@ static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
 }
 
-static void default_after_vcpu_run(struct kvm_vm *vm)
+static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 {
 	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 
+	TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR),
+		    "vcpu run failed: errno=%d", err);
+
 	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
 		    "Invalid guest sync status: exit_reason=%s\n",
 		    exit_reason_str(run->exit_reason));

@@ -248,27 +289,37 @@ static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
 	return count;
 }
 
+static void dirty_ring_wait_vcpu(void)
+{
+	/* This makes sure that hardware PML cache flushed */
+	vcpu_kick();
+	sem_wait_until(&dirty_ring_vcpu_stop);
+}
+
+static void dirty_ring_continue_vcpu(void)
+{
+	pr_info("Notifying vcpu to continue\n");
+	sem_post(&dirty_ring_vcpu_cont);
+}
+
 static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
 					   void *bitmap, uint32_t num_pages)
 {
 	/* We only have one vcpu */
 	static uint32_t fetch_index = 0;
 	uint32_t count = 0, cleared;
+	bool continued_vcpu = false;
 
-	/*
-	 * Before fetching the dirty pages, we need a vmexit of the
-	 * worker vcpu to make sure the hardware dirty buffers were
-	 * flushed.  This is not needed for dirty-log/clear-log tests
-	 * because get dirty log will natually do so.
-	 *
-	 * For now we do it in the simple way - we simply wait until
-	 * the vcpu uses up the soft dirty ring, then it'll always
-	 * do a vmexit to make sure that PML buffers will be flushed.
-	 * In real hypervisors, we probably need a vcpu kick or to
-	 * stop the vcpus (before the final sync) to make sure we'll
-	 * get all the existing dirty PFNs even cached in hardware.
-	 */
-	sem_wait(&dirty_ring_vcpu_stop);
+	dirty_ring_wait_vcpu();
+
+	if (!dirty_ring_vcpu_ring_full) {
+		/*
+		 * This is not a ring-full event, it's safe to allow
+		 * vcpu to continue
+		 */
+		dirty_ring_continue_vcpu();
+		continued_vcpu = true;
+	}
 
 	/* Only have one vcpu */
 	count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID),

@@ -280,13 +331,16 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
 		    "with collected (%u)", cleared, count);
 
-	pr_info("Notifying vcpu to continue\n");
-	sem_post(&dirty_ring_vcpu_cont);
+	if (!continued_vcpu) {
+		TEST_ASSERT(dirty_ring_vcpu_ring_full,
+			    "Didn't continue vcpu even without ring full");
+		dirty_ring_continue_vcpu();
+	}
 
 	pr_info("Iteration %ld collected %u pages\n", iteration, count);
 }
 
-static void dirty_ring_after_vcpu_run(struct kvm_vm *vm)
+static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 {
 	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
 

@@ -294,10 +348,16 @@ static void dirty_ring_after_vcpu_run(struct kvm_vm *vm)
 	if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
 		/* We should allow this to continue */
 		;
-	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL) {
+	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL ||
+		   (ret == -1 && err == EINTR)) {
+		/* Update the flag first before pause */
+		WRITE_ONCE(dirty_ring_vcpu_ring_full,
+			   run->exit_reason == KVM_EXIT_DIRTY_RING_FULL);
 		sem_post(&dirty_ring_vcpu_stop);
-		pr_info("vcpu stops because dirty ring full...\n");
-		sem_wait(&dirty_ring_vcpu_cont);
+		pr_info("vcpu stops because %s...\n",
+			dirty_ring_vcpu_ring_full ?
+			"dirty ring is full" : "vcpu is kicked out");
+		sem_wait_until(&dirty_ring_vcpu_cont);
 		pr_info("vcpu continues now.\n");
 	} else {
 		TEST_ASSERT(false, "Invalid guest sync status: "

@@ -322,7 +382,7 @@ struct log_mode {
 	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
 				     void *bitmap, uint32_t num_pages);
 	/* Hook to call when after each vcpu run */
-	void (*after_vcpu_run)(struct kvm_vm *vm);
+	void (*after_vcpu_run)(struct kvm_vm *vm, int ret, int err);
 	void (*before_vcpu_join) (void);
 } log_modes[LOG_MODE_NUM] = {
 	{

@@ -394,12 +454,12 @@ static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
 }
 
-static void log_mode_after_vcpu_run(struct kvm_vm *vm)
+static void log_mode_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 {
 	struct log_mode *mode = &log_modes[host_log_mode];
 
 	if (mode->after_vcpu_run)
-		mode->after_vcpu_run(vm);
+		mode->after_vcpu_run(vm, ret, err);
 }
 
 static void log_mode_before_vcpu_join(void)

@@ -420,20 +480,27 @@ static void generate_random_array(uint64_t *guest_array, uint64_t size)
 
 static void *vcpu_worker(void *data)
 {
-	int ret;
+	int ret, vcpu_fd;
 	struct kvm_vm *vm = data;
 	uint64_t *guest_array;
 	uint64_t pages_count = 0;
+	struct sigaction sigact;
+
+	current_vm = vm;
+	vcpu_fd = vcpu_get_fd(vm, VCPU_ID);
+	memset(&sigact, 0, sizeof(sigact));
+	sigact.sa_handler = vcpu_sig_handler;
+	sigaction(SIG_IPI, &sigact, NULL);
 
 	guest_array = addr_gva2hva(vm, (vm_vaddr_t)random_array);
 
 	while (!READ_ONCE(host_quit)) {
+		/* Clear any existing kick signals */
 		generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 		pages_count += TEST_PAGES_PER_LOOP;
 		/* Let the guest dirty the random pages */
-		ret = _vcpu_run(vm, VCPU_ID);
-		TEST_ASSERT(ret == 0, "vcpu_run failed: %d\n", ret);
-		log_mode_after_vcpu_run(vm);
+		ret = ioctl(vcpu_fd, KVM_RUN, NULL);
+		log_mode_after_vcpu_run(vm, ret, errno);
 	}
 
 	pr_info("Dirtied %"PRIu64" pages\n", pages_count);

@@ -583,7 +650,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		     unsigned long interval, uint64_t phys_offset)
 {
-	pthread_t vcpu_thread;
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 

index 554fdb294bef..62254375ec50 100644
@@ -144,6 +144,7 @@ vm_paddr_t addr_gva2gpa(struct kvm_vm *vm, vm_vaddr_t gva);
 struct kvm_run *vcpu_state(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
 int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid);
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);

index e632d1f4a112..0e79bde7a2a8 100644
@@ -1207,6 +1207,15 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	return rc;
 }
 
+int vcpu_get_fd(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpuid);
+
+	TEST_ASSERT(vcpu != NULL, "vcpu not found, vcpuid: %u", vcpuid);
+
+	return vcpu->fd;
+}
+
 void vcpu_run_complete_io(struct kvm_vm *vm, uint32_t vcpuid)
 {
 	struct vcpu *vcpu = vcpu_find(vm, vcpuid);

index 4b404dfdc2f9..80c42c87265e 100644
@@ -168,6 +168,7 @@ static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
 /* Logging mode for current run */
 static enum log_mode_t host_log_mode;
 static pthread_t vcpu_thread;
+static uint32_t test_dirty_ring_count = TEST_DIRTY_RING_COUNT;
 
 /* Only way to pass this to the signal handler */
 static struct kvm_vm *current_vm;

@@ -250,7 +251,7 @@ static void dirty_ring_create_vm_done(struct kvm_vm *vm)
 	 * Switch to dirty ring mode after VM creation but before any
 	 * of the vcpu creation.
 	 */
-	vm_enable_dirty_ring(vm, TEST_DIRTY_RING_COUNT *
+	vm_enable_dirty_ring(vm, test_dirty_ring_count *
 			     sizeof(struct kvm_dirty_gfn));
 }
 

@@ -272,7 +273,7 @@ static uint32_t dirty_ring_collect_one(struct kvm_dirty_gfn *dirty_gfns,
 	uint32_t count = 0;
 
 	while (true) {
-		cur = &dirty_gfns[*fetch_index % TEST_DIRTY_RING_COUNT];
+		cur = &dirty_gfns[*fetch_index % test_dirty_ring_count];
 		if (!dirty_gfn_is_dirtied(cur))
 			break;
 		TEST_ASSERT(cur->slot == slot, "Slot number didn't match: "

@@ -778,6 +779,9 @@ static void help(char *name)
 	printf("usage: %s [-h] [-i iterations] [-I interval] "
 	       "[-p offset] [-m mode]\n", name);
 	puts("");
+	printf(" -c: specify dirty ring size, in number of entries\n");
+	printf("     (only useful for dirty-ring test; default: %"PRIu32")\n",
+	       TEST_DIRTY_RING_COUNT);
 	printf(" -i: specify iteration counts (default: %"PRIu64")\n",
 	       TEST_HOST_LOOP_N);
 	printf(" -I: specify interval in ms (default: %"PRIu64" ms)\n",

@@ -833,8 +837,11 @@ int main(int argc, char *argv[])
 	guest_mode_init(VM_MODE_P40V48_4K, true, true);
 #endif
 
-	while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
+	while ((opt = getopt(argc, argv, "c:hi:I:p:m:M:")) != -1) {
 		switch (opt) {
+		case 'c':
+			test_dirty_ring_count = strtol(optarg, NULL, 10);
+			break;
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
 			break;