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

Pull kvm updates from Paolo Bonzini:
 "Quite a large pull request due to a selftest API overhaul and some
  patches that had come in too late for 5.19.

  ARM:

   - Unwinder implementations for both nVHE modes (classic and
     protected), complete with an overflow stack

   - Rework of the sysreg access from userspace, with a complete rewrite
     of the vgic-v3 view to allign with the rest of the infrastructure

   - Disagregation of the vcpu flags in separate sets to better track
     their use model.

   - A fix for the GICv2-on-v3 selftest

   - A small set of cosmetic fixes

  RISC-V:

   - Track ISA extensions used by Guest using bitmap

   - Added system instruction emulation framework

   - Added CSR emulation framework

   - Added gfp_custom flag in struct kvm_mmu_memory_cache

   - Added G-stage ioremap() and iounmap() functions

   - Added support for Svpbmt inside Guest

  s390:

   - add an interface to provide a hypervisor dump for secure guests

   - improve selftests to use TAP interface

   - enable interpretive execution of zPCI instructions (for PCI
     passthrough)

   - First part of deferred teardown

   - CPU Topology

   - PV attestation

   - Minor fixes

  x86:

   - Permit guests to ignore single-bit ECC errors

   - Intel IPI virtualization

   - Allow getting/setting pending triple fault with
     KVM_GET/SET_VCPU_EVENTS

   - PEBS virtualization

   - Simplify PMU emulation by just using PERF_TYPE_RAW events

   - More accurate event reinjection on SVM (avoid retrying
     instructions)

   - Allow getting/setting the state of the speaker port data bit

   - Refuse starting the kvm-intel module if VM-Entry/VM-Exit controls
     are inconsistent

   - "Notify" VM exit (detect microarchitectural hangs) for Intel

   - Use try_cmpxchg64 instead of cmpxchg64

   - Ignore benign host accesses to PMU MSRs when PMU is disabled

   - Allow disabling KVM's "MONITOR/MWAIT are NOPs!" behavior

   - Allow NX huge page mitigation to be disabled on a per-vm basis

   - Port eager page splitting to shadow MMU as well

   - Enable CMCI capability by default and handle injected UCNA errors

   - Expose pid of vcpu threads in debugfs

   - x2AVIC support for AMD

   - cleanup PIO emulation

   - Fixes for LLDT/LTR emulation

   - Don't require refcounted "struct page" to create huge SPTEs

   - Miscellaneous cleanups:
      - MCE MSR emulation
      - Use separate namespaces for guest PTEs and shadow PTEs bitmasks
      - PIO emulation
      - Reorganize rmap API, mostly around rmap destruction
      - Do not workaround very old KVM bugs for L0 that runs with nesting enabled
      - new selftests API for CPUID

  Generic:

   - Fix races in gfn->pfn cache refresh; do not pin pages tracked by
     the cache

   - new selftests API using struct kvm_vcpu instead of a (vm, id)
     tuple"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (606 commits)
  selftests: kvm: set rax before vmcall
  selftests: KVM: Add exponent check for boolean stats
  selftests: KVM: Provide descriptive assertions in kvm_binary_stats_test
  selftests: KVM: Check stat name before other fields
  KVM: x86/mmu: remove unused variable
  RISC-V: KVM: Add support for Svpbmt inside Guest/VM
  RISC-V: KVM: Use PAGE_KERNEL_IO in kvm_riscv_gstage_ioremap()
  RISC-V: KVM: Add G-stage ioremap() and iounmap() functions
  KVM: Add gfp_custom flag in struct kvm_mmu_memory_cache
  RISC-V: KVM: Add extensible CSR emulation framework
  RISC-V: KVM: Add extensible system instruction emulation framework
  RISC-V: KVM: Factor-out instruction emulation into separate sources
  RISC-V: KVM: move preempt_disable() call in kvm_arch_vcpu_ioctl_run
  RISC-V: KVM: Make kvm_riscv_guest_timer_init a void function
  RISC-V: KVM: Fix variable spelling mistake
  RISC-V: KVM: Improve ISA extension by using a bitmap
  KVM, x86/mmu: Fix the comment around kvm_tdp_mmu_zap_leafs()
  KVM: SVM: Dump Virtual Machine Save Area (VMSA) to klog
  KVM: x86/mmu: Treat NX as a valid SPTE bit for NPT
  KVM: x86: Do not block APIC write for non ICR registers
  ...

1 files changed, 42 insertions, 53 deletions

diff --git a/tools/testing/selftests/kvm/dirty_log_test.c b/tools/testing/selftests/kvm/dirty_log_test.c
index 3fcd89e195c7..9c883c94d478 100644
--- a/tools/testing/selftests/kvm/dirty_log_test.c
+++ b/tools/testing/selftests/kvm/dirty_log_test.c
@@ -23,8 +23,6 @@
 #include "guest_modes.h"
 #include "processor.h"
 
-#define VCPU_ID				1
-
 /* The memory slot index to track dirty pages */
 #define TEST_MEM_SLOT_INDEX		1
 
@@ -212,34 +210,31 @@ static void sem_wait_until(sem_t *sem)
 
 static bool clear_log_supported(void)
 {
-	return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+	return kvm_has_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
 }
 
 static void clear_log_create_vm_done(struct kvm_vm *vm)
 {
-	struct kvm_enable_cap cap = {};
 	u64 manual_caps;
 
 	manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
 	TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!");
 	manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
 			KVM_DIRTY_LOG_INITIALLY_SET);
-	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
-	cap.args[0] = manual_caps;
-	vm_enable_cap(vm, &cap);
+	vm_enable_cap(vm, KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2, manual_caps);
 }
 
-static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+static void dirty_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot,
 					  void *bitmap, uint32_t num_pages)
 {
-	kvm_vm_get_dirty_log(vm, slot, bitmap);
+	kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap);
 }
 
-static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+static void clear_log_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot,
 					  void *bitmap, uint32_t num_pages)
 {
-	kvm_vm_get_dirty_log(vm, slot, bitmap);
-	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
+	kvm_vm_get_dirty_log(vcpu->vm, slot, bitmap);
+	kvm_vm_clear_dirty_log(vcpu->vm, slot, bitmap, 0, num_pages);
 }
 
 /* Should only be called after a GUEST_SYNC */
@@ -253,14 +248,14 @@ static void vcpu_handle_sync_stop(void)
 	}
 }
 
-static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
+static void default_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 {
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct kvm_run *run = vcpu->run;
 
 	TEST_ASSERT(ret == 0 || (ret == -1 && err == EINTR),
 		    "vcpu run failed: errno=%d", err);
 
-	TEST_ASSERT(get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC,
+	TEST_ASSERT(get_ucall(vcpu, NULL) == UCALL_SYNC,
 		    "Invalid guest sync status: exit_reason=%s\n",
 		    exit_reason_str(run->exit_reason));
 
@@ -269,7 +264,7 @@ static void default_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
 
 static bool dirty_ring_supported(void)
 {
-	return kvm_check_cap(KVM_CAP_DIRTY_LOG_RING);
+	return kvm_has_cap(KVM_CAP_DIRTY_LOG_RING);
 }
 
 static void dirty_ring_create_vm_done(struct kvm_vm *vm)
@@ -331,7 +326,7 @@ static void dirty_ring_continue_vcpu(void)
 	sem_post(&sem_vcpu_cont);
 }
 
-static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
+static void dirty_ring_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot,
 					   void *bitmap, uint32_t num_pages)
 {
 	/* We only have one vcpu */
@@ -351,10 +346,10 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	}
 
 	/* Only have one vcpu */
-	count = dirty_ring_collect_one(vcpu_map_dirty_ring(vm, VCPU_ID),
+	count = dirty_ring_collect_one(vcpu_map_dirty_ring(vcpu),
 				       slot, bitmap, num_pages, &fetch_index);
 
-	cleared = kvm_vm_reset_dirty_ring(vm);
+	cleared = kvm_vm_reset_dirty_ring(vcpu->vm);
 
 	/* Cleared pages should be the same as collected */
 	TEST_ASSERT(cleared == count, "Reset dirty pages (%u) mismatch "
@@ -369,12 +364,12 @@ static void dirty_ring_collect_dirty_pages(struct kvm_vm *vm, int slot,
 	pr_info("Iteration %ld collected %u pages\n", iteration, count);
 }
 
-static void dirty_ring_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
+static void dirty_ring_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 {
-	struct kvm_run *run = vcpu_state(vm, VCPU_ID);
+	struct kvm_run *run = vcpu->run;
 
 	/* A ucall-sync or ring-full event is allowed */
-	if (get_ucall(vm, VCPU_ID, NULL) == UCALL_SYNC) {
+	if (get_ucall(vcpu, NULL) == UCALL_SYNC) {
 		/* We should allow this to continue */
 		;
 	} else if (run->exit_reason == KVM_EXIT_DIRTY_RING_FULL ||
@@ -408,10 +403,10 @@ struct log_mode {
 	/* Hook when the vm creation is done (before vcpu creation) */
 	void (*create_vm_done)(struct kvm_vm *vm);
 	/* Hook to collect the dirty pages into the bitmap provided */
-	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
+	void (*collect_dirty_pages) (struct kvm_vcpu *vcpu, int slot,
 				     void *bitmap, uint32_t num_pages);
 	/* Hook to call when after each vcpu run */
-	void (*after_vcpu_run)(struct kvm_vm *vm, int ret, int err);
+	void (*after_vcpu_run)(struct kvm_vcpu *vcpu, int ret, int err);
 	void (*before_vcpu_join) (void);
 } log_modes[LOG_MODE_NUM] = {
 	{
@@ -473,22 +468,22 @@ static void log_mode_create_vm_done(struct kvm_vm *vm)
 		mode->create_vm_done(vm);
 }
 
-static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
+static void log_mode_collect_dirty_pages(struct kvm_vcpu *vcpu, int slot,
 					 void *bitmap, uint32_t num_pages)
 {
 	struct log_mode *mode = &log_modes[host_log_mode];
 
 	TEST_ASSERT(mode->collect_dirty_pages != NULL,
 		    "collect_dirty_pages() is required for any log mode!");
-	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
+	mode->collect_dirty_pages(vcpu, slot, bitmap, num_pages);
 }
 
-static void log_mode_after_vcpu_run(struct kvm_vm *vm, int ret, int err)
+static void log_mode_after_vcpu_run(struct kvm_vcpu *vcpu, int ret, int err)
 {
 	struct log_mode *mode = &log_modes[host_log_mode];
 
 	if (mode->after_vcpu_run)
-		mode->after_vcpu_run(vm, ret, err);
+		mode->after_vcpu_run(vcpu, ret, err);
 }
 
 static void log_mode_before_vcpu_join(void)
@@ -509,16 +504,15 @@ static void generate_random_array(uint64_t *guest_array, uint64_t size)
 
 static void *vcpu_worker(void *data)
 {
-	int ret, vcpu_fd;
-	struct kvm_vm *vm = data;
+	int ret;
+	struct kvm_vcpu *vcpu = data;
+	struct kvm_vm *vm = vcpu->vm;
 	uint64_t *guest_array;
 	uint64_t pages_count = 0;
 	struct kvm_signal_mask *sigmask = alloca(offsetof(struct kvm_signal_mask, sigset)
 						 + sizeof(sigset_t));
 	sigset_t *sigset = (sigset_t *) &sigmask->sigset;
 
-	vcpu_fd = vcpu_get_fd(vm, VCPU_ID);
-
 	/*
 	 * SIG_IPI is unblocked atomically while in KVM_RUN.  It causes the
 	 * ioctl to return with -EINTR, but it is still pending and we need
@@ -527,7 +521,7 @@ static void *vcpu_worker(void *data)
 	sigmask->len = 8;
 	pthread_sigmask(0, NULL, sigset);
 	sigdelset(sigset, SIG_IPI);
-	vcpu_ioctl(vm, VCPU_ID, KVM_SET_SIGNAL_MASK, sigmask);
+	vcpu_ioctl(vcpu, KVM_SET_SIGNAL_MASK, sigmask);
 
 	sigemptyset(sigset);
 	sigaddset(sigset, SIG_IPI);
@@ -539,13 +533,13 @@ static void *vcpu_worker(void *data)
 		generate_random_array(guest_array, TEST_PAGES_PER_LOOP);
 		pages_count += TEST_PAGES_PER_LOOP;
 		/* Let the guest dirty the random pages */
-		ret = ioctl(vcpu_fd, KVM_RUN, NULL);
+		ret = __vcpu_run(vcpu);
 		if (ret == -1 && errno == EINTR) {
 			int sig = -1;
 			sigwait(sigset, &sig);
 			assert(sig == SIG_IPI);
 		}
-		log_mode_after_vcpu_run(vm, ret, errno);
+		log_mode_after_vcpu_run(vcpu, ret, errno);
 	}
 
 	pr_info("Dirtied %"PRIu64" pages\n", pages_count);
@@ -671,21 +665,17 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 	}
 }
 
-static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, struct kvm_vcpu **vcpu,
 				uint64_t extra_mem_pages, void *guest_code)
 {
 	struct kvm_vm *vm;
-	uint64_t extra_pg_pages = extra_mem_pages / 512 * 2;
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
-	kvm_vm_elf_load(vm, program_invocation_name);
-#ifdef __x86_64__
-	vm_create_irqchip(vm);
-#endif
+	vm = __vm_create(mode, 1, extra_mem_pages);
+
 	log_mode_create_vm_done(vm);
-	vm_vcpu_add_default(vm, vcpuid, guest_code);
+	*vcpu = vm_vcpu_add(vm, 0, guest_code);
 	return vm;
 }
 
@@ -701,6 +691,7 @@ struct test_params {
 static void run_test(enum vm_guest_mode mode, void *arg)
 {
 	struct test_params *p = arg;
+	struct kvm_vcpu *vcpu;
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 
@@ -718,25 +709,23 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	 * (e.g., 64K page size guest will need even less memory for
 	 * page tables).
 	 */
-	vm = create_vm(mode, VCPU_ID,
-		       2ul << (DIRTY_MEM_BITS - PAGE_SHIFT_4K),
-		       guest_code);
+	vm = create_vm(mode, &vcpu,
+		       2ul << (DIRTY_MEM_BITS - PAGE_SHIFT_4K), guest_code);
 
-	guest_page_size = vm_get_page_size(vm);
+	guest_page_size = vm->page_size;
 	/*
 	 * A little more than 1G of guest page sized pages.  Cover the
 	 * case where the size is not aligned to 64 pages.
 	 */
-	guest_num_pages = (1ul << (DIRTY_MEM_BITS -
-				   vm_get_page_shift(vm))) + 3;
+	guest_num_pages = (1ul << (DIRTY_MEM_BITS - vm->page_shift)) + 3;
 	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
 
 	host_page_size = getpagesize();
 	host_num_pages = vm_num_host_pages(mode, guest_num_pages);
 
 	if (!p->phys_offset) {
-		guest_test_phys_mem = (vm_get_max_gfn(vm) -
-				       guest_num_pages) * guest_page_size;
+		guest_test_phys_mem = (vm->max_gfn - guest_num_pages) *
+				      guest_page_size;
 		guest_test_phys_mem = align_down(guest_test_phys_mem, host_page_size);
 	} else {
 		guest_test_phys_mem = p->phys_offset;
@@ -781,12 +770,12 @@ static void run_test(enum vm_guest_mode mode, void *arg)
 	host_clear_count = 0;
 	host_track_next_count = 0;
 
-	pthread_create(&vcpu_thread, NULL, vcpu_worker, vm);
+	pthread_create(&vcpu_thread, NULL, vcpu_worker, vcpu);
 
 	while (iteration < p->iterations) {
 		/* Give the vcpu thread some time to dirty some pages */
 		usleep(p->interval * 1000);
-		log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
+		log_mode_collect_dirty_pages(vcpu, TEST_MEM_SLOT_INDEX,
 					     bmap, host_num_pages);
 
 		/*