sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz_full

index 6c9f19a33865a..ce3c58286062c 100644
@@ -18,15 +18,16 @@
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern void task_cputime(struct task_struct *t,
+extern bool task_cputime(struct task_struct *t,
 			 u64 *utime, u64 *stime);
 extern u64 task_gtime(struct task_struct *t);
 #else
-static inline void task_cputime(struct task_struct *t,
+static inline bool task_cputime(struct task_struct *t,
 				u64 *utime, u64 *stime)
 {
 	*utime = t->utime;
 	*stime = t->stime;
+	return false;
 }
 
 static inline u64 task_gtime(struct task_struct *t)

index 872e481d5098c..9392aea1804e5 100644
@@ -615,7 +615,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 		.sum_exec_runtime = p->se.sum_exec_runtime,
 	};
 
-	task_cputime(p, &cputime.utime, &cputime.stime);
+	if (task_cputime(p, &cputime.utime, &cputime.stime))
+		cputime.sum_exec_runtime = task_sched_runtime(p);
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);

@@ -828,19 +829,21 @@ u64 task_gtime(struct task_struct *t)
  * add up the pending nohz execution time since the last
  * cputime snapshot.
  */
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
 	struct vtime *vtime = &t->vtime;
 	unsigned int seq;
 	u64 delta;
+	int ret;
 
 	if (!vtime_accounting_enabled()) {
 		*utime = t->utime;
 		*stime = t->stime;
-		return;
+		return false;
 	}
 
 	do {
+		ret = false;
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		*utime = t->utime;

@@ -850,6 +853,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		if (vtime->state < VTIME_SYS)
 			continue;
 
+		ret = true;
 		delta = vtime_delta(vtime);
 
 		/*

@@ -861,6 +865,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		else
 			*utime += vtime->utime + delta;
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return ret;
 }
 
 static int vtime_state_fetch(struct vtime *vtime, int cpu)

index 322b65d456767..41f470929e991 100644
@@ -595,7 +595,8 @@ void irq_enter_rcu(void)
 {
 	__irq_enter_raw();
 
-	if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))
+	if (tick_nohz_full_cpu(smp_processor_id()) ||
+	    (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET)))
 		tick_irq_enter();
 
 	account_hardirq_enter(current);

index 6bffe5af8cb11..17a283ce2b20f 100644
@@ -1375,6 +1375,13 @@ static inline void tick_nohz_irq_enter(void)
 	now = ktime_get();
 	if (ts->idle_active)
 		tick_nohz_stop_idle(ts, now);
+	/*
+	 * If all CPUs are idle. We may need to update a stale jiffies value.
+	 * Note nohz_full is a special case: a timekeeper is guaranteed to stay
+	 * alive but it might be busy looping with interrupts disabled in some
+	 * rare case (typically stop machine). So we must make sure we have a
+	 * last resort.
+	 */
 	if (ts->tick_stopped)
 		tick_nohz_update_jiffies(now);
 }

index dacdf2395f01a..4e212f04268bb 100644
@@ -7776,10 +7776,10 @@ static __init int hardware_setup(void)
 		ple_window_shrink = 0;
 	}
 
-	if (!cpu_has_vmx_apicv()) {
+	if (!cpu_has_vmx_apicv())
 		enable_apicv = 0;
+	if (!enable_apicv)
 		vmx_x86_ops.sync_pir_to_irr = NULL;
-	}
 
 	if (cpu_has_vmx_tsc_scaling()) {
 		kvm_has_tsc_control = true;

index 134c4ea5e6ad8..ae8092f0d401e 100644
@@ -1842,8 +1842,6 @@ void sev_vm_destroy(struct kvm *kvm)
 		return;
 	}
 
-	mutex_lock(&kvm->lock);
-
 	/*
 	 * Ensure that all guest tagged cache entries are flushed before
 	 * releasing the pages back to the system for use. CLFLUSH will

@@ -1863,8 +1861,6 @@ void sev_vm_destroy(struct kvm *kvm)
 		}
 	}
 
-	mutex_unlock(&kvm->lock);
-
 	sev_unbind_asid(kvm, sev->handle);
 	sev_asid_free(sev);
 }

index 0299cd81b8ba2..aa3795cd7bd3d 100644
@@ -12,6 +12,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <sys/resource.h>
 
 #include "test_util.h"
 

@@ -40,10 +41,39 @@ int main(int argc, char *argv[])
 {
 	int kvm_max_vcpu_id = kvm_check_cap(KVM_CAP_MAX_VCPU_ID);
 	int kvm_max_vcpus = kvm_check_cap(KVM_CAP_MAX_VCPUS);
+	/*
+	 * Number of file descriptors reqired, KVM_CAP_MAX_VCPUS for vCPU fds +
+	 * an arbitrary number for everything else.
+	 */
+	int nr_fds_wanted = kvm_max_vcpus + 100;
+	struct rlimit rl;
 
 	pr_info("KVM_CAP_MAX_VCPU_ID: %d\n", kvm_max_vcpu_id);
 	pr_info("KVM_CAP_MAX_VCPUS: %d\n", kvm_max_vcpus);
 
+	/*
+	 * Check that we're allowed to open nr_fds_wanted file descriptors and
+	 * try raising the limits if needed.
+	 */
+	TEST_ASSERT(!getrlimit(RLIMIT_NOFILE, &rl), "getrlimit() failed!");
+
+	if (rl.rlim_cur < nr_fds_wanted) {
+		rl.rlim_cur = nr_fds_wanted;
+		if (rl.rlim_max < nr_fds_wanted) {
+			int old_rlim_max = rl.rlim_max;
+			rl.rlim_max = nr_fds_wanted;
+
+			int r = setrlimit(RLIMIT_NOFILE, &rl);
+			if (r < 0) {
+				printf("RLIMIT_NOFILE hard limit is too low (%d, wanted %d)\n",
+				       old_rlim_max, nr_fds_wanted);
+				exit(KSFT_SKIP);
+			}
+		} else {
+			TEST_ASSERT(!setrlimit(RLIMIT_NOFILE, &rl), "setrlimit() failed!");
+		}
+	}
+
 	/*
 	 * Upstream KVM prior to 4.8 does not support KVM_CAP_MAX_VCPU_ID.
 	 * Userspace is supposed to use KVM_CAP_MAX_VCPUS as the maximum ID

index 0a88cb4f731f4..31392e492ce5e 100644
@@ -5022,6 +5022,14 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/*
 	 * Invalidate all MMU roles to force them to reinitialize as CPUID
 	 * information is factored into reserved bit calculations.
+	 *
+	 * Correctly handling multiple vCPU models with respect to paging and
+	 * physical address properties) in a single VM would require tracking
+	 * all relevant CPUID information in kvm_mmu_page_role. That is very
+	 * undesirable as it would increase the memory requirements for
+	 * gfn_track (see struct kvm_mmu_page_role comments).  For now that
+	 * problem is swept under the rug; KVM's CPUID API is horrific and
+	 * it's all but impossible to solve it without introducing a new API.
 	 */
 	vcpu->arch.root_mmu.mmu_role.ext.valid = 0;
 	vcpu->arch.guest_mmu.mmu_role.ext.valid = 0;

@@ -5029,24 +5037,10 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	kvm_mmu_reset_context(vcpu);
 
 	/*
-	 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
-	 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
-	 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
-	 * faults due to reusing SPs/SPTEs.  Alert userspace, but otherwise
-	 * sweep the problem under the rug.
-	 *
-	 * KVM's horrific CPUID ABI makes the problem all but impossible to
-	 * solve, as correctly handling multiple vCPU models (with respect to
-	 * paging and physical address properties) in a single VM would require
-	 * tracking all relevant CPUID information in kvm_mmu_page_role.  That
-	 * is very undesirable as it would double the memory requirements for
-	 * gfn_track (see struct kvm_mmu_page_role comments), and in practice
-	 * no sane VMM mucks with the core vCPU model on the fly.
+	 * Changing guest CPUID after KVM_RUN is forbidden, see the comment in
+	 * kvm_arch_vcpu_ioctl().
 	 */
-	if (vcpu->arch.last_vmentry_cpu != -1) {
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} after KVM_RUN may cause guest instability\n");
-		pr_warn_ratelimited("KVM: KVM_SET_CPUID{,2} will fail after KVM_RUN starting with Linux 5.16\n");
-	}
+	KVM_BUG_ON(vcpu->arch.last_vmentry_cpu != -1, vcpu->kvm);
 }
 
 void kvm_mmu_reset_context(struct kvm_vcpu *vcpu)

index b7aa845f7beee..2a584070833f9 100644
@@ -5088,6 +5088,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid __user *cpuid_arg = argp;
 		struct kvm_cpuid cpuid;
 
+		/*
+		 * KVM does not correctly handle changing guest CPUID after KVM_RUN, as
+		 * MAXPHYADDR, GBPAGES support, AMD reserved bit behavior, etc.. aren't
+		 * tracked in kvm_mmu_page_role.  As a result, KVM may miss guest page
+		 * faults due to reusing SPs/SPTEs.  In practice no sane VMM mucks with
+		 * the core vCPU model on the fly, so fail.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;

@@ -5098,6 +5109,14 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		struct kvm_cpuid2 __user *cpuid_arg = argp;
 		struct kvm_cpuid2 cpuid;
 
+		/*
+		 * KVM_SET_CPUID{,2} after KVM_RUN is forbidded, see the comment in
+		 * KVM_SET_CPUID case above.
+		 */
+		r = -EINVAL;
+		if (vcpu->arch.last_vmentry_cpu != -1)
+			goto out;
+
 		r = -EFAULT;
 		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
 			goto out;

index 91d88aaa98992..672915ce73d8f 100644
@@ -165,10 +165,10 @@ static void hv_set_cpuid(struct kvm_vm *vm, struct kvm_cpuid2 *cpuid,
 	vcpu_set_cpuid(vm, VCPU_ID, cpuid);
 }
 
-static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
-				   struct kvm_cpuid2 *best)
+static void guest_test_msrs_access(void)
 {
 	struct kvm_run *run;
+	struct kvm_vm *vm;
 	struct ucall uc;
 	int stage = 0, r;
 	struct kvm_cpuid_entry2 feat = {

@@ -180,11 +180,34 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 	struct kvm_cpuid_entry2 dbg = {
 		.function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 	};
-	struct kvm_enable_cap cap = {0};
-
-	run = vcpu_state(vm, VCPU_ID);
+	struct kvm_cpuid2 *best;
+	vm_vaddr_t msr_gva;
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
+		.args = {1}
+	};
+	struct msr_data *msr;
 
 	while (true) {
+		vm = vm_create_default(VCPU_ID, 0, guest_msr);
+
+		msr_gva = vm_vaddr_alloc_page(vm);
+		memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize());
+		msr = addr_gva2hva(vm, msr_gva);
+
+		vcpu_args_set(vm, VCPU_ID, 1, msr_gva);
+		vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+		vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+		best = kvm_get_supported_hv_cpuid();
+
+		vm_init_descriptor_tables(vm);
+		vcpu_init_descriptor_tables(vm, VCPU_ID);
+		vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
+
+		run = vcpu_state(vm, VCPU_ID);
+
 		switch (stage) {
 		case 0:
 			/*

@@ -315,6 +338,7 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 			 * capability enabled and guest visible CPUID bit unset.
 			 */
 			cap.cap = KVM_CAP_HYPERV_SYNIC2;
+			cap.args[0] = 0;
 			vcpu_enable_cap(vm, VCPU_ID, &cap);
 			break;
 		case 22:

@@ -461,9 +485,9 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_SYNC:
-			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
-				    uc.args[1], stage);
+			TEST_ASSERT(uc.args[1] == 0,
+				    "Unexpected stage: %ld (0 expected)\n",
+				    uc.args[1]);
 			break;
 		case UCALL_ABORT:
 			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],

@@ -474,13 +498,14 @@ static void guest_test_msrs_access(struct kvm_vm *vm, struct msr_data *msr,
 		}
 
 		stage++;
+		kvm_vm_free(vm);
 	}
 }
 
-static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall,
-				     void *input, void *output, struct kvm_cpuid2 *best)
+static void guest_test_hcalls_access(void)
 {
 	struct kvm_run *run;
+	struct kvm_vm *vm;
 	struct ucall uc;
 	int stage = 0, r;
 	struct kvm_cpuid_entry2 feat = {

@@ -493,10 +518,38 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 	struct kvm_cpuid_entry2 dbg = {
 		.function = HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 	};
-
-	run = vcpu_state(vm, VCPU_ID);
+	struct kvm_enable_cap cap = {
+		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
+		.args = {1}
+	};
+	vm_vaddr_t hcall_page, hcall_params;
+	struct hcall_data *hcall;
+	struct kvm_cpuid2 *best;
 
 	while (true) {
+		vm = vm_create_default(VCPU_ID, 0, guest_hcall);
+
+		vm_init_descriptor_tables(vm);
+		vcpu_init_descriptor_tables(vm, VCPU_ID);
+		vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
+
+		/* Hypercall input/output */
+		hcall_page = vm_vaddr_alloc_pages(vm, 2);
+		hcall = addr_gva2hva(vm, hcall_page);
+		memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
+
+		hcall_params = vm_vaddr_alloc_page(vm);
+		memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize());
+
+		vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params);
+		vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+		vcpu_set_hv_cpuid(vm, VCPU_ID);
+
+		best = kvm_get_supported_hv_cpuid();
+
+		run = vcpu_state(vm, VCPU_ID);
+
 		switch (stage) {
 		case 0:
 			hcall->control = 0xdeadbeef;

@@ -606,9 +659,9 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 
 		switch (get_ucall(vm, VCPU_ID, &uc)) {
 		case UCALL_SYNC:
-			TEST_ASSERT(uc.args[1] == stage,
-				    "Unexpected stage: %ld (%d expected)\n",
-				    uc.args[1], stage);
+			TEST_ASSERT(uc.args[1] == 0,
+				    "Unexpected stage: %ld (0 expected)\n",
+				    uc.args[1]);
 			break;
 		case UCALL_ABORT:
 			TEST_FAIL("%s at %s:%ld", (const char *)uc.args[0],

@@ -619,66 +672,15 @@ static void guest_test_hcalls_access(struct kvm_vm *vm, struct hcall_data *hcall
 		}
 
 		stage++;
+		kvm_vm_free(vm);
 	}
 }
 
 int main(void)
 {
-	struct kvm_cpuid2 *best;
-	struct kvm_vm *vm;
-	vm_vaddr_t msr_gva, hcall_page, hcall_params;
-	struct kvm_enable_cap cap = {
-		.cap = KVM_CAP_HYPERV_ENFORCE_CPUID,
-		.args = {1}
-	};
-
-	/* Test MSRs */
-	vm = vm_create_default(VCPU_ID, 0, guest_msr);
-
-	msr_gva = vm_vaddr_alloc_page(vm);
-	memset(addr_gva2hva(vm, msr_gva), 0x0, getpagesize());
-	vcpu_args_set(vm, VCPU_ID, 1, msr_gva);
-	vcpu_enable_cap(vm, VCPU_ID, &cap);
-
-	vcpu_set_hv_cpuid(vm, VCPU_ID);
-
-	best = kvm_get_supported_hv_cpuid();
-
-	vm_init_descriptor_tables(vm);
-	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_install_exception_handler(vm, GP_VECTOR, guest_gp_handler);
-
 	pr_info("Testing access to Hyper-V specific MSRs\n");
-	guest_test_msrs_access(vm, addr_gva2hva(vm, msr_gva),
-			       best);
-	kvm_vm_free(vm);
-
-	/* Test hypercalls */
-	vm = vm_create_default(VCPU_ID, 0, guest_hcall);
-
-	vm_init_descriptor_tables(vm);
-	vcpu_init_descriptor_tables(vm, VCPU_ID);
-	vm_install_exception_handler(vm, UD_VECTOR, guest_ud_handler);
-
-	/* Hypercall input/output */
-	hcall_page = vm_vaddr_alloc_pages(vm, 2);
-	memset(addr_gva2hva(vm, hcall_page), 0x0, 2 * getpagesize());
-
-	hcall_params = vm_vaddr_alloc_page(vm);
-	memset(addr_gva2hva(vm, hcall_params), 0x0, getpagesize());
-
-	vcpu_args_set(vm, VCPU_ID, 2, addr_gva2gpa(vm, hcall_page), hcall_params);
-	vcpu_enable_cap(vm, VCPU_ID, &cap);
-
-	vcpu_set_hv_cpuid(vm, VCPU_ID);
-
-	best = kvm_get_supported_hv_cpuid();
+	guest_test_msrs_access();
 
 	pr_info("Testing access to Hyper-V hypercalls\n");
-	guest_test_hcalls_access(vm, addr_gva2hva(vm, hcall_params),
-				 addr_gva2hva(vm, hcall_page),
-				 addr_gva2hva(vm, hcall_page) + getpagesize(),
-				 best);
-
-	kvm_vm_free(vm);
+	guest_test_hcalls_access();
 }

index ce1847bc898b2..c6bfd4e15d28a 100644
@@ -3001,7 +3001,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	int r;
 	gpa_t gpa = ghc->gpa + offset;
 
-	BUG_ON(len + offset > ghc->len);
+	if (WARN_ON_ONCE(len + offset > ghc->len))
+		return -EINVAL;
 
 	if (slots->generation != ghc->generation) {
 		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))

@@ -3038,7 +3039,8 @@ int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 	int r;
 	gpa_t gpa = ghc->gpa + offset;
 
-	BUG_ON(len + offset > ghc->len);
+	if (WARN_ON_ONCE(len + offset > ghc->len))
+		return -EINVAL;
 
 	if (slots->generation != ghc->generation) {
 		if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))

index 27e61ff3ac3e8..f1b2b2a6ff4db 100644
@@ -81,7 +81,6 @@ struct kvm_ioapic {
 	unsigned long irq_states[IOAPIC_NUM_PINS];
 	struct kvm_io_device dev;
 	struct kvm *kvm;
-	void (*ack_notifier)(void *opaque, int irq);
 	spinlock_t lock;
 	struct rtc_status rtc_status;
 	struct delayed_work eoi_inject;

index 650642b18d151..c2d7cfe82d004 100644
@@ -56,7 +56,6 @@ struct kvm_pic {
 	struct kvm_io_device dev_master;
 	struct kvm_io_device dev_slave;
 	struct kvm_io_device dev_elcr;
-	void (*ack_notifier)(void *opaque, int irq);
 	unsigned long irq_states[PIC_NUM_PINS];
 };