linux-kernel - [RFC PATCH 3/6] RISC-V: KVM: Add a xarray to record host irq msg

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20250811061104.10326-4-fangyu.yu@linux.alibaba.com>
Date: Mon, 11 Aug 2025 14:11:01 +0800
From: fangyu.yu@...ux.alibaba.com
To: anup@...infault.org,
	paul.walmsley@...ive.com,
	palmer@...belt.com,
	aou@...s.berkeley.edu,
	alex@...ti.fr,
	atishp@...shpatra.org,
	tjeznach@...osinc.com,
	joro@...tes.org,
	will@...nel.org,
	robin.murphy@....com,
	sunilvl@...tanamicro.com,
	rafael.j.wysocki@...el.com,
	tglx@...utronix.de,
	ajones@...tanamicro.com
Cc: guoren@...ux.alibaba.com,
	guoren@...nel.org,
	kvm@...r.kernel.org,
	kvm-riscv@...ts.infradead.org,
	linux-riscv@...ts.infradead.org,
	linux-kernel@...r.kernel.org,
	iommu@...ts.linux.dev,
	Fangyu Yu <fangyu.yu@...ux.alibaba.com>
Subject: [RFC PATCH 3/6] RISC-V: KVM: Add a xarray to record host irq msg

From: Fangyu Yu <fangyu.yu@...ux.alibaba.com>

In the irq bypass scenario,the host interrupt comes from VFIO, and
it is an enabled MSI/MSI-X interrupt.  Due to the  reconfiguration
of the PCI-e BAR space during the irq bypass process,this host irq
will not be triggered in the host system.

We can use this host irq as a notice MSI in IOMMU MRIF mode.

Signed-off-by: Fangyu Yu <fangyu.yu@...ux.alibaba.com>
---
 arch/riscv/kvm/aia_imsic.c | 69 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 68 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index e91164742fd0..58807e68a3dd 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -60,6 +60,9 @@ struct imsic {
 	struct imsic_mrif *swfile;
 	phys_addr_t swfile_pa;
 	raw_spinlock_t swfile_extirq_lock;
+
+	bool mrif_support;
+	struct xarray hostirq_array;	/* Attached host irq array */
 };
 
 #define imsic_vs_csr_read(__c)			\
@@ -740,6 +743,57 @@ void kvm_riscv_vcpu_aia_imsic_release(struct kvm_vcpu *vcpu)
 	kvm_riscv_aia_free_hgei(old_vsfile_cpu, old_vsfile_hgei);
 }
 
+static int kvm_arch_update_irqfd_unset(struct kvm *kvm, unsigned int host_irq)
+{
+	struct kvm_vcpu *vcpu;
+	unsigned long tmp;
+
+	kvm_for_each_vcpu(tmp, vcpu, kvm) {
+		struct imsic *imsic = vcpu->arch.aia_context.imsic_state;
+		struct msi_msg *curr = xa_load(&imsic->hostirq_array, host_irq);
+
+		if (!curr)
+			continue;
+
+		xa_erase(&imsic->hostirq_array, host_irq);
+		kfree(curr);
+		break;
+	}
+
+	return irq_set_vcpu_affinity(host_irq, NULL);
+}
+
+static struct msi_msg *kvm_arch_update_irqfd_hostirq(struct imsic *imsic,
+						     unsigned int host_irq, int *ret,
+						     struct kvm_kernel_irq_routing_entry *e)
+{
+	struct msi_msg *priv_msg = xa_load(&imsic->hostirq_array, host_irq);
+
+	if (!priv_msg) {
+		priv_msg = kzalloc(sizeof(*priv_msg), GFP_KERNEL);
+		if (!priv_msg) {
+			*ret = -ENOMEM;
+			goto out;
+		}
+
+		struct msi_msg host_msg, *curr;
+
+		get_cached_msi_msg(host_irq, &host_msg);
+		priv_msg[0] = host_msg;
+		curr = xa_cmpxchg(&imsic->hostirq_array, host_irq,
+				NULL, priv_msg, GFP_ATOMIC);
+		if (WARN_ON_ONCE(curr)) {
+			*ret = xa_err(curr) ? : -EBUSY;
+			kfree(priv_msg);
+			goto out;
+		}
+	}
+	*ret = 0;
+
+out:
+	return priv_msg;
+}
+
 int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 				  uint32_t guest_irq, bool set)
 {
@@ -750,7 +804,7 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 	int idx, ret = -ENXIO;
 
 	if (!set)
-		return irq_set_vcpu_affinity(host_irq, NULL);
+		return kvm_arch_update_irqfd_unset(kvm, host_irq);
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
@@ -795,6 +849,11 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 
 			vcpu_info.msi_addr_pattern = tppn & ~vcpu_info.msi_addr_mask;
 			vcpu_info.gpa = target;
+			vcpu_info.host_irq = host_irq;
+			vcpu_info.host_msg =
+				    kvm_arch_update_irqfd_hostirq(imsic, host_irq, &ret, e);
+			if (ret)
+				goto out;
 
 			read_lock_irqsave(&imsic->vsfile_lock, flags);
 
@@ -848,6 +907,10 @@ static int kvm_riscv_vcpu_irq_update(struct kvm_vcpu *vcpu)
 		if (!irqfd->producer)
 			continue;
 		host_irq = irqfd->producer->irq;
+		vcpu_info.host_irq = host_irq;
+		vcpu_info.host_msg = xa_load(&imsic->hostirq_array, host_irq);
+		if (!vcpu_info.host_msg)
+			continue;
 
 		if (imsic->vsfile_cpu < 0) {
 			vcpu_info.hpa = imsic->swfile_pa;
@@ -855,6 +918,7 @@ static int kvm_riscv_vcpu_irq_update(struct kvm_vcpu *vcpu)
 		} else {
 			vcpu_info.mrif = false;
 		}
+
 		ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
 		if (ret) {
 			spin_unlock_irq(&kvm->irqfds.lock);
@@ -1195,6 +1259,9 @@ int kvm_riscv_vcpu_aia_imsic_init(struct kvm_vcpu *vcpu)
 	imsic->swfile_pa = page_to_phys(swfile_page);
 	raw_spin_lock_init(&imsic->swfile_extirq_lock);
 
+	xa_init(&imsic->hostirq_array);
+	imsic->mrif_support = false;
+
 	/* Setup IO device */
 	kvm_iodevice_init(&imsic->iodev, &imsic_iodoev_ops);
 	mutex_lock(&kvm->slots_lock);
-- 
2.49.0