Merge tag 'kvm-riscv-fixes-6.16-2' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv fixes for 6.16, take #2

- Disable vstimecmp before exiting to user-space
- Move HGEI[E|P] CSR access to IMSIC virtualization

Author: bonzini

arch/riscv/include/asm/kvm_aia.h

@@ -87,6 +87,9 @@ DECLARE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
 
 extern struct kvm_device_ops kvm_riscv_aia_device_ops;
 
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu);
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu);
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu);
 void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu);
 int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu);
 
@@ -161,7 +164,6 @@ void kvm_riscv_aia_destroy_vm(struct kvm *kvm);
 int kvm_riscv_aia_alloc_hgei(int cpu, struct kvm_vcpu *owner,
 			     void __iomem **hgei_va, phys_addr_t *hgei_pa);
 void kvm_riscv_aia_free_hgei(int cpu, int hgei);
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable);
 
 void kvm_riscv_aia_enable(void);
 void kvm_riscv_aia_disable(void);

arch/riscv/include/asm/kvm_host.h

@@ -306,6 +306,9 @@ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu)
 	return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu;
 }
 
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+
 #define KVM_RISCV_GSTAGE_TLB_MIN_ORDER		12
 
 void kvm_riscv_local_hfence_gvma_vmid_gpa(unsigned long vmid,

arch/riscv/kvm/aia.c

@@ -30,28 +30,6 @@ unsigned int kvm_riscv_aia_nr_hgei;
 unsigned int kvm_riscv_aia_max_ids;
 DEFINE_STATIC_KEY_FALSE(kvm_riscv_aia_available);
 
-static int aia_find_hgei(struct kvm_vcpu *owner)
-{
-	int i, hgei;
-	unsigned long flags;
-	struct aia_hgei_control *hgctrl = get_cpu_ptr(&aia_hgei);
-
-	raw_spin_lock_irqsave(&hgctrl->lock, flags);
-
-	hgei = -1;
-	for (i = 1; i <= kvm_riscv_aia_nr_hgei; i++) {
-		if (hgctrl->owners[i] == owner) {
-			hgei = i;
-			break;
-		}
-	}
-
-	raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
-
-	put_cpu_ptr(&aia_hgei);
-	return hgei;
-}
-
 static inline unsigned long aia_hvictl_value(bool ext_irq_pending)
 {
 	unsigned long hvictl;
@@ -95,7 +73,6 @@ void kvm_riscv_vcpu_aia_sync_interrupts(struct kvm_vcpu *vcpu)
 
 bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 {
-	int hgei;
 	unsigned long seip;
 
 	if (!kvm_riscv_aia_available())
@@ -114,11 +91,7 @@ bool kvm_riscv_vcpu_aia_has_interrupts(struct kvm_vcpu *vcpu, u64 mask)
 	if (!kvm_riscv_aia_initialized(vcpu->kvm) || !seip)
 		return false;
 
-	hgei = aia_find_hgei(vcpu);
-	if (hgei > 0)
-		return !!(ncsr_read(CSR_HGEIP) & BIT(hgei));
-
-	return false;
+	return kvm_riscv_vcpu_aia_imsic_has_interrupt(vcpu);
 }
 
 void kvm_riscv_vcpu_aia_update_hvip(struct kvm_vcpu *vcpu)
@@ -164,6 +137,9 @@ void kvm_riscv_vcpu_aia_load(struct kvm_vcpu *vcpu, int cpu)
 		csr_write(CSR_HVIPRIO2H, csr->hviprio2h);
 #endif
 	}
+
+	if (kvm_riscv_aia_initialized(vcpu->kvm))
+		kvm_riscv_vcpu_aia_imsic_load(vcpu, cpu);
 }
 
 void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
@@ -174,6 +150,9 @@ void kvm_riscv_vcpu_aia_put(struct kvm_vcpu *vcpu)
 	if (!kvm_riscv_aia_available())
 		return;
 
+	if (kvm_riscv_aia_initialized(vcpu->kvm))
+		kvm_riscv_vcpu_aia_imsic_put(vcpu);
+
 	if (kvm_riscv_nacl_available()) {
 		nsh = nacl_shmem();
 		csr->vsiselect = nacl_csr_read(nsh, CSR_VSISELECT);
@@ -472,22 +451,6 @@ void kvm_riscv_aia_free_hgei(int cpu, int hgei)
 	raw_spin_unlock_irqrestore(&hgctrl->lock, flags);
 }
 
-void kvm_riscv_aia_wakeon_hgei(struct kvm_vcpu *owner, bool enable)
-{
-	int hgei;
-
-	if (!kvm_riscv_aia_available())
-		return;
-
-	hgei = aia_find_hgei(owner);
-	if (hgei > 0) {
-		if (enable)
-			csr_set(CSR_HGEIE, BIT(hgei));
-		else
-			csr_clear(CSR_HGEIE, BIT(hgei));
-	}
-}
-
 static irqreturn_t hgei_interrupt(int irq, void *dev_id)
 {
 	int i;

arch/riscv/kvm/aia_imsic.c

@@ -676,6 +676,48 @@ static void imsic_swfile_update(struct kvm_vcpu *vcpu,
 	imsic_swfile_extirq_update(vcpu);
 }
 
+bool kvm_riscv_vcpu_aia_imsic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+	unsigned long flags;
+	bool ret = false;
+
+	/*
+	 * The IMSIC SW-file directly injects interrupt via hvip so
+	 * only check for interrupt when IMSIC VS-file is being used.
+	 */
+
+	read_lock_irqsave(&imsic->vsfile_lock, flags);
+	if (imsic->vsfile_cpu > -1)
+		ret = !!(csr_read(CSR_HGEIP) & BIT(imsic->vsfile_hgei));
+	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+
+	return ret;
+}
+
+void kvm_riscv_vcpu_aia_imsic_load(struct kvm_vcpu *vcpu, int cpu)
+{
+	/*
+	 * No need to explicitly clear HGEIE CSR bits because the
+	 * hgei interrupt handler (aka hgei_interrupt()) will always
+	 * clear it for us.
+	 */
+}
+
+void kvm_riscv_vcpu_aia_imsic_put(struct kvm_vcpu *vcpu)
+{
+	struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+	unsigned long flags;
+
+	if (!kvm_vcpu_is_blocking(vcpu))
+		return;
+
+	read_lock_irqsave(&imsic->vsfile_lock, flags);
+	if (imsic->vsfile_cpu > -1)
+		csr_set(CSR_HGEIE, BIT(imsic->vsfile_hgei));
+	read_unlock_irqrestore(&imsic->vsfile_lock, flags);
+}
+
 void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu)
 {
 	unsigned long flags;
@@ -781,6 +823,9 @@ int kvm_riscv_vcpu_aia_imsic_update(struct kvm_vcpu *vcpu)
 	 * producers to the new IMSIC VS-file.
 	 */
 
+	/* Ensure HGEIE CSR bit is zero before using the new IMSIC VS-file */
+	csr_clear(CSR_HGEIE, BIT(new_vsfile_hgei));
+
 	/* Zero-out new IMSIC VS-file */
 	imsic_vsfile_local_clear(new_vsfile_hgei, imsic->nr_hw_eix);
 

arch/riscv/kvm/vcpu.c

@@ -207,16 +207,6 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 	return kvm_riscv_vcpu_timer_pending(vcpu);
 }
 
-void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
-{
-	kvm_riscv_aia_wakeon_hgei(vcpu, true);
-}
-
-void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
-{
-	kvm_riscv_aia_wakeon_hgei(vcpu, false);
-}
-
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
 {
 	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&

arch/riscv/kvm/vcpu_timer.c

@@ -345,8 +345,24 @@ void kvm_riscv_vcpu_timer_save(struct kvm_vcpu *vcpu)
 	/*
 	 * The vstimecmp CSRs are saved by kvm_riscv_vcpu_timer_sync()
 	 * upon every VM exit so no need to save here.
+	 *
+	 * If VS-timer expires when no VCPU running on a host CPU then
+	 * WFI executed by such host CPU will be effective NOP resulting
+	 * in no power savings. This is because as-per RISC-V Privileged
+	 * specificaiton: "WFI is also required to resume execution for
+	 * locally enabled interrupts pending at any privilege level,
+	 * regardless of the global interrupt enable at each privilege
+	 * level."
+	 *
+	 * To address the above issue, vstimecmp CSR must be set to -1UL
+	 * over here when VCPU is scheduled-out or exits to user space.
 	 */
 
+	csr_write(CSR_VSTIMECMP, -1UL);
+#if defined(CONFIG_32BIT)
+	csr_write(CSR_VSTIMECMPH, -1UL);
+#endif
+
 	/* timer should be enabled for the remaining operations */
 	if (unlikely(!t->init_done))
 		return;