[PATCH v5-light 0/6] KVM: Improve IRQ assignment for device passthrough

[PATCH v5-light 0/6] KVM: Improve IRQ assignment for device passthrough

[Jan Kiszka]

This is the rebased light version of the previous series, i.e. without
PCI-2.3-based IRQ masking or any SRCU conversion. PCI-2.3 support is
under rework to explore options for automatic mode switches.

Jan Kiszka (6):
  KVM: Clear assigned guest IRQ on release
  KVM: Switch assigned device IRQ forwarding to threaded handler
  KVM: Refactor IRQ names of assigned devices
  KVM: Save/restore state of assigned PCI device
  KVM: Clean up kvm_vm_ioctl_assigned_device
  KVM: Document device assigment API

 Documentation/kvm/api.txt |  178 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/kvm_host.h  |   13 +---
 virt/kvm/assigned-dev.c   |  125 ++++++++++++--------------------
 3 files changed, 227 insertions(+), 89 deletions(-)

[PATCH v5-light 1/6] KVM: Clear assigned guest IRQ on release

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

When we deassign a guest IRQ, clear the potentially asserted guest line.
There might be no chance for the guest to do this, specifically if we
switch from INTx to MSI mode.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 virt/kvm/assigned-dev.c |    3 +++
 1 files changed, 3 insertions(+), 0 deletions(-)

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 7c98928..ecc4419 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -141,6 +141,9 @@ static void deassign_guest_irq(struct kvm *kvm,
 	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
 	assigned_dev->ack_notifier.gsi = -1;
 
+	kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
+		    assigned_dev->guest_irq, 0);
+
 	if (assigned_dev->irq_source_id != -1)
 		kvm_free_irq_source_id(kvm, assigned_dev->irq_source_id);
 	assigned_dev->irq_source_id = -1;
-- 
1.7.1

[PATCH v5-light 2/6] KVM: Switch assigned device IRQ forwarding to threaded handler

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

This improves the IRQ forwarding for assigned devices: By using the
kernel's threaded IRQ scheme, we can get rid of the latency-prone work
queue and simplify the code in the same run.

Moreover, we no longer have to hold assigned_dev_lock while raising the
guest IRQ, which can be a lenghty operation as we may have to iterate
over all VCPUs. The lock is now only used for synchronizing masking vs.
unmasking of INTx-type IRQs, thus is renames to intx_lock.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 include/linux/kvm_host.h |   12 +----
 virt/kvm/assigned-dev.c  |  107 +++++++++++++++-------------------------------
 2 files changed, 36 insertions(+), 83 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 2d63f2c..9fe7fef 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -470,16 +470,8 @@ struct kvm_irq_ack_notifier {
 	void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
 };
 
-#define KVM_ASSIGNED_MSIX_PENDING		0x1
-struct kvm_guest_msix_entry {
-	u32 vector;
-	u16 entry;
-	u16 flags;
-};
-
 struct kvm_assigned_dev_kernel {
 	struct kvm_irq_ack_notifier ack_notifier;
-	struct work_struct interrupt_work;
 	struct list_head list;
 	int assigned_dev_id;
 	int host_segnr;
@@ -490,13 +482,13 @@ struct kvm_assigned_dev_kernel {
 	bool host_irq_disabled;
 	struct msix_entry *host_msix_entries;
 	int guest_irq;
-	struct kvm_guest_msix_entry *guest_msix_entries;
+	struct msix_entry *guest_msix_entries;
 	unsigned long irq_requested_type;
 	int irq_source_id;
 	int flags;
 	struct pci_dev *dev;
 	struct kvm *kvm;
-	spinlock_t assigned_dev_lock;
+	spinlock_t intx_lock;
 };
 
 struct kvm_irq_mask_notifier {
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index ecc4419..1d77ce1 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -55,58 +55,31 @@ static int find_index_from_host_irq(struct kvm_assigned_dev_kernel
 	return index;
 }
 
-static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
+static irqreturn_t kvm_assigned_dev_thread(int irq, void *dev_id)
 {
-	struct kvm_assigned_dev_kernel *assigned_dev;
-	int i;
+	struct kvm_assigned_dev_kernel *assigned_dev = dev_id;
+	u32 vector;
+	int index;
 
-	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
-				    interrupt_work);
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_INTX) {
+		spin_lock(&assigned_dev->intx_lock);
+		disable_irq_nosync(irq);
+		assigned_dev->host_irq_disabled = true;
+		spin_unlock(&assigned_dev->intx_lock);
+	}
 
-	spin_lock_irq(&assigned_dev->assigned_dev_lock);
 	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		struct kvm_guest_msix_entry *guest_entries =
-			assigned_dev->guest_msix_entries;
-		for (i = 0; i < assigned_dev->entries_nr; i++) {
-			if (!(guest_entries[i].flags &
-					KVM_ASSIGNED_MSIX_PENDING))
-				continue;
-			guest_entries[i].flags &= ~KVM_ASSIGNED_MSIX_PENDING;
+		index = find_index_from_host_irq(assigned_dev, irq);
+		if (index >= 0) {
+			vector = assigned_dev->
+					guest_msix_entries[index].vector;
 			kvm_set_irq(assigned_dev->kvm,
-				    assigned_dev->irq_source_id,
-				    guest_entries[i].vector, 1);
+				    assigned_dev->irq_source_id, vector, 1);
 		}
 	} else
 		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
 			    assigned_dev->guest_irq, 1);
 
-	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
-}
-
-static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
-{
-	unsigned long flags;
-	struct kvm_assigned_dev_kernel *assigned_dev =
-		(struct kvm_assigned_dev_kernel *) dev_id;
-
-	spin_lock_irqsave(&assigned_dev->assigned_dev_lock, flags);
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
-		int index = find_index_from_host_irq(assigned_dev, irq);
-		if (index < 0)
-			goto out;
-		assigned_dev->guest_msix_entries[index].flags |=
-			KVM_ASSIGNED_MSIX_PENDING;
-	}
-
-	schedule_work(&assigned_dev->interrupt_work);
-
-	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
-		disable_irq_nosync(irq);
-		assigned_dev->host_irq_disabled = true;
-	}
-
-out:
-	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);
 	return IRQ_HANDLED;
 }
 
@@ -114,7 +87,6 @@ out:
 static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 {
 	struct kvm_assigned_dev_kernel *dev;
-	unsigned long flags;
 
 	if (kian->gsi == -1)
 		return;
@@ -127,12 +99,12 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 	/* The guest irq may be shared so this ack may be
 	 * from another device.
 	 */
-	spin_lock_irqsave(&dev->assigned_dev_lock, flags);
+	spin_lock(&dev->intx_lock);
 	if (dev->host_irq_disabled) {
 		enable_irq(dev->host_irq);
 		dev->host_irq_disabled = false;
 	}
-	spin_unlock_irqrestore(&dev->assigned_dev_lock, flags);
+	spin_unlock(&dev->intx_lock);
 }
 
 static void deassign_guest_irq(struct kvm *kvm,
@@ -155,28 +127,19 @@ static void deassign_host_irq(struct kvm *kvm,
 			      struct kvm_assigned_dev_kernel *assigned_dev)
 {
 	/*
-	 * In kvm_free_device_irq, cancel_work_sync return true if:
-	 * 1. work is scheduled, and then cancelled.
-	 * 2. work callback is executed.
-	 *
-	 * The first one ensured that the irq is disabled and no more events
-	 * would happen. But for the second one, the irq may be enabled (e.g.
-	 * for MSI). So we disable irq here to prevent further events.
+	 * We disable irq here to prevent further events.
 	 *
 	 * Notice this maybe result in nested disable if the interrupt type is
 	 * INTx, but it's OK for we are going to free it.
 	 *
 	 * If this function is a part of VM destroy, please ensure that till
 	 * now, the kvm state is still legal for probably we also have to wait
-	 * interrupt_work done.
+	 * on a currently running IRQ handler.
 	 */
 	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
 		int i;
 		for (i = 0; i < assigned_dev->entries_nr; i++)
-			disable_irq_nosync(assigned_dev->
-					   host_msix_entries[i].vector);
-
-		cancel_work_sync(&assigned_dev->interrupt_work);
+			disable_irq(assigned_dev->host_msix_entries[i].vector);
 
 		for (i = 0; i < assigned_dev->entries_nr; i++)
 			free_irq(assigned_dev->host_msix_entries[i].vector,
@@ -188,8 +151,7 @@ static void deassign_host_irq(struct kvm *kvm,
 		pci_disable_msix(assigned_dev->dev);
 	} else {
 		/* Deal with MSI and INTx */
-		disable_irq_nosync(assigned_dev->host_irq);
-		cancel_work_sync(&assigned_dev->interrupt_work);
+		disable_irq(assigned_dev->host_irq);
 
 		free_irq(assigned_dev->host_irq, (void *)assigned_dev);
 
@@ -268,8 +230,9 @@ static int assigned_device_enable_host_intx(struct kvm *kvm,
 	 * on the same interrupt line is not a happy situation: there
 	 * are going to be long delays in accepting, acking, etc.
 	 */
-	if (request_irq(dev->host_irq, kvm_assigned_dev_intr,
-			0, "kvm_assigned_intx_device", (void *)dev))
+	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
+				 IRQF_ONESHOT, "kvm_assigned_intx_device",
+				 (void *)dev))
 		return -EIO;
 	return 0;
 }
@@ -287,8 +250,8 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 	}
 
 	dev->host_irq = dev->dev->irq;
-	if (request_irq(dev->host_irq, kvm_assigned_dev_intr, 0,
-			"kvm_assigned_msi_device", (void *)dev)) {
+	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
+				 0, "kvm_assigned_msi_device", (void *)dev)) {
 		pci_disable_msi(dev->dev);
 		return -EIO;
 	}
@@ -313,10 +276,10 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 		return r;
 
 	for (i = 0; i < dev->entries_nr; i++) {
-		r = request_irq(dev->host_msix_entries[i].vector,
-				kvm_assigned_dev_intr, 0,
-				"kvm_assigned_msix_device",
-				(void *)dev);
+		r = request_threaded_irq(dev->host_msix_entries[i].vector,
+					 NULL, kvm_assigned_dev_thread,
+					 0, "kvm_assigned_msix_device",
+					 (void *)dev);
 		if (r)
 			goto err;
 	}
@@ -557,12 +520,10 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	match->host_devfn = assigned_dev->devfn;
 	match->flags = assigned_dev->flags;
 	match->dev = dev;
-	spin_lock_init(&match->assigned_dev_lock);
+	spin_lock_init(&match->intx_lock);
 	match->irq_source_id = -1;
 	match->kvm = kvm;
 	match->ack_notifier.irq_acked = kvm_assigned_dev_ack_irq;
-	INIT_WORK(&match->interrupt_work,
-		  kvm_assigned_dev_interrupt_work_handler);
 
 	list_add(&match->list, &kvm->arch.assigned_dev_head);
 
@@ -654,9 +615,9 @@ static int kvm_vm_ioctl_set_msix_nr(struct kvm *kvm,
 			r = -ENOMEM;
 			goto msix_nr_out;
 		}
-		adev->guest_msix_entries = kzalloc(
-				sizeof(struct kvm_guest_msix_entry) *
-				entry_nr->entry_nr, GFP_KERNEL);
+		adev->guest_msix_entries =
+			kzalloc(sizeof(struct msix_entry) * entry_nr->entry_nr,
+				GFP_KERNEL);
 		if (!adev->guest_msix_entries) {
 			kfree(adev->host_msix_entries);
 			r = -ENOMEM;
-- 
1.7.1

[PATCH v5-light 3/6] KVM: Refactor IRQ names of assigned devices

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Cosmetic change, but it helps to correlate IRQs with PCI devices.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 include/linux/kvm_host.h |    1 +
 virt/kvm/assigned-dev.c  |   11 ++++++-----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9fe7fef..4bd663d 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -489,6 +489,7 @@ struct kvm_assigned_dev_kernel {
 	struct pci_dev *dev;
 	struct kvm *kvm;
 	spinlock_t intx_lock;
+	char irq_name[32];
 };
 
 struct kvm_irq_mask_notifier {
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 1d77ce1..7623408 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -231,8 +231,7 @@ static int assigned_device_enable_host_intx(struct kvm *kvm,
 	 * are going to be long delays in accepting, acking, etc.
 	 */
 	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-				 IRQF_ONESHOT, "kvm_assigned_intx_device",
-				 (void *)dev))
+				 IRQF_ONESHOT, dev->irq_name, (void *)dev))
 		return -EIO;
 	return 0;
 }
@@ -251,7 +250,7 @@ static int assigned_device_enable_host_msi(struct kvm *kvm,
 
 	dev->host_irq = dev->dev->irq;
 	if (request_threaded_irq(dev->host_irq, NULL, kvm_assigned_dev_thread,
-				 0, "kvm_assigned_msi_device", (void *)dev)) {
+				 0, dev->irq_name, (void *)dev)) {
 		pci_disable_msi(dev->dev);
 		return -EIO;
 	}
@@ -278,8 +277,7 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 	for (i = 0; i < dev->entries_nr; i++) {
 		r = request_threaded_irq(dev->host_msix_entries[i].vector,
 					 NULL, kvm_assigned_dev_thread,
-					 0, "kvm_assigned_msix_device",
-					 (void *)dev);
+					 0, dev->irq_name, (void *)dev);
 		if (r)
 			goto err;
 	}
@@ -336,6 +334,9 @@ static int assign_host_irq(struct kvm *kvm,
 	if (dev->irq_requested_type & KVM_DEV_IRQ_HOST_MASK)
 		return r;
 
+	snprintf(dev->irq_name, sizeof(dev->irq_name), "kvm:%s",
+		 pci_name(dev->dev));
+
 	switch (host_irq_type) {
 	case KVM_DEV_IRQ_HOST_INTX:
 		r = assigned_device_enable_host_intx(kvm, dev);
-- 
1.7.1

[PATCH v5-light 4/6] KVM: Save/restore state of assigned PCI device

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

The guest may change states that pci_reset_function does not touch. So
we better save/restore the assigned device across guest usage.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 virt/kvm/assigned-dev.c |    5 ++++-
 1 files changed, 4 insertions(+), 1 deletions(-)

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 7623408..d389207 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -197,7 +197,8 @@ static void kvm_free_assigned_device(struct kvm *kvm,
 {
 	kvm_free_assigned_irq(kvm, assigned_dev);
 
-	pci_reset_function(assigned_dev->dev);
+	__pci_reset_function(assigned_dev->dev);
+	pci_restore_state(assigned_dev->dev);
 
 	pci_release_regions(assigned_dev->dev);
 	pci_disable_device(assigned_dev->dev);
@@ -514,6 +515,7 @@ static int kvm_vm_ioctl_assign_device(struct kvm *kvm,
 	}
 
 	pci_reset_function(dev);
+	pci_save_state(dev);
 
 	match->assigned_dev_id = assigned_dev->assigned_dev_id;
 	match->host_segnr = assigned_dev->segnr;
@@ -544,6 +546,7 @@ out:
 	mutex_unlock(&kvm->lock);
 	return r;
 out_list_del:
+	pci_restore_state(dev);
 	list_del(&match->list);
 	pci_release_regions(dev);
 out_disable:
-- 
1.7.1

[PATCH v5-light 5/6] KVM: Clean up kvm_vm_ioctl_assigned_device

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Any arch not supporting device assigment will also not build
assigned-dev.c. So testing for KVM_CAP_DEVICE_DEASSIGNMENT is pointless.
KVM_CAP_ASSIGN_DEV_IRQ is unconditinally set. Moreover, add a default
case for dispatching the ioctl.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 virt/kvm/assigned-dev.c |    9 ++++-----
 1 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index d389207..ae72ae6 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -674,7 +674,7 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 				  unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
-	int r = -ENOTTY;
+	int r;
 
 	switch (ioctl) {
 	case KVM_ASSIGN_PCI_DEVICE: {
@@ -692,7 +692,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 		r = -EOPNOTSUPP;
 		break;
 	}
-#ifdef KVM_CAP_ASSIGN_DEV_IRQ
 	case KVM_ASSIGN_DEV_IRQ: {
 		struct kvm_assigned_irq assigned_irq;
 
@@ -715,8 +714,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
-#endif
-#ifdef KVM_CAP_DEVICE_DEASSIGNMENT
 	case KVM_DEASSIGN_PCI_DEVICE: {
 		struct kvm_assigned_pci_dev assigned_dev;
 
@@ -728,7 +725,6 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 			goto out;
 		break;
 	}
-#endif
 #ifdef KVM_CAP_IRQ_ROUTING
 	case KVM_SET_GSI_ROUTING: {
 		struct kvm_irq_routing routing;
@@ -781,6 +777,9 @@ long kvm_vm_ioctl_assigned_device(struct kvm *kvm, unsigned ioctl,
 		break;
 	}
 #endif
+	default:
+		r = -ENOTTY;
+		break;
 	}
 out:
 	return r;
-- 
1.7.1

[PATCH v5-light 6/6] KVM: Document device assigment API

[Jan Kiszka]

From: Jan Kiszka <jan.kiszka@siemens.com>

Adds API documentation for KVM_[DE]ASSIGN_PCI_DEVICE,
KVM_[DE]ASSIGN_DEV_IRQ, KVM_SET_GSI_ROUTING, KVM_ASSIGN_SET_MSIX_NR, and
KVM_ASSIGN_SET_MSIX_ENTRY.

Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
---
 Documentation/kvm/api.txt |  178 +++++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 178 insertions(+), 0 deletions(-)

diff --git a/Documentation/kvm/api.txt b/Documentation/kvm/api.txt
index b336266..e1a9297 100644
--- a/Documentation/kvm/api.txt
+++ b/Documentation/kvm/api.txt
@@ -1085,6 +1085,184 @@ of 4 instructions that make up a hypercall.
 If any additional field gets added to this structure later on, a bit for that
 additional piece of information will be set in the flags bitmap.
 
+4.47 KVM_ASSIGN_PCI_DEVICE
+
+Capability: KVM_CAP_DEVICE_ASSIGNMENT
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_pci_dev (in)
+Returns: 0 on success, -1 on error
+
+Assigns a host PCI device to the VM.
+
+struct kvm_assigned_pci_dev {
+	__u32 assigned_dev_id;
+	__u32 busnr;
+	__u32 devfn;
+	__u32 flags;
+	__u32 segnr;
+	union {
+		__u32 reserved[11];
+	};
+};
+
+The PCI device is specified by the triple segnr, busnr, and devfn.
+Identification in succeeding service requests is done via assigned_dev_id. The
+following flags are specified:
+
+/* Depends on KVM_CAP_IOMMU */
+#define KVM_DEV_ASSIGN_ENABLE_IOMMU	(1 << 0)
+
+4.48 KVM_DEASSIGN_PCI_DEVICE
+
+Capability: KVM_CAP_DEVICE_DEASSIGNMENT
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_pci_dev (in)
+Returns: 0 on success, -1 on error
+
+Ends PCI device assignment, releasing all associated resources.
+
+See KVM_CAP_DEVICE_ASSIGNMENT for the data structure. Only assigned_dev_id is
+used in kvm_assigned_pci_dev to identify the device.
+
+4.49 KVM_ASSIGN_DEV_IRQ
+
+Capability: KVM_CAP_ASSIGN_DEV_IRQ
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_irq (in)
+Returns: 0 on success, -1 on error
+
+Assigns an IRQ to a passed-through device.
+
+struct kvm_assigned_irq {
+	__u32 assigned_dev_id;
+	__u32 host_irq;
+	__u32 guest_irq;
+	__u32 flags;
+	union {
+		struct {
+			__u32 addr_lo;
+			__u32 addr_hi;
+			__u32 data;
+		} guest_msi;
+		__u32 reserved[12];
+	};
+};
+
+The following flags are defined:
+
+#define KVM_DEV_IRQ_HOST_INTX    (1 << 0)
+#define KVM_DEV_IRQ_HOST_MSI     (1 << 1)
+#define KVM_DEV_IRQ_HOST_MSIX    (1 << 2)
+
+#define KVM_DEV_IRQ_GUEST_INTX   (1 << 8)
+#define KVM_DEV_IRQ_GUEST_MSI    (1 << 9)
+#define KVM_DEV_IRQ_GUEST_MSIX   (1 << 10)
+
+It is not valid to specify multiple types per host or guest IRQ. However, the
+IRQ type of host and guest can differ or can even be null.
+
+4.50 KVM_DEASSIGN_DEV_IRQ
+
+Capability: KVM_CAP_ASSIGN_DEV_IRQ
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_irq (in)
+Returns: 0 on success, -1 on error
+
+Ends an IRQ assignment to a passed-through device.
+
+See KVM_ASSIGN_DEV_IRQ for the data structure. The target device is specified
+by assigned_dev_id, flags must correspond to the IRQ type specified on
+KVM_ASSIGN_DEV_IRQ. Partial deassignment of host or guest IRQ is allowed.
+
+4.51 KVM_SET_GSI_ROUTING
+
+Capability: KVM_CAP_IRQ_ROUTING
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_irq_routing (in)
+Returns: 0 on success, -1 on error
+
+Sets the GSI routing table entries, overwriting any previously set entries.
+
+struct kvm_irq_routing {
+	__u32 nr;
+	__u32 flags;
+	struct kvm_irq_routing_entry entries[0];
+};
+
+No flags are specified so far, the corresponding field must be set to zero.
+
+struct kvm_irq_routing_entry {
+	__u32 gsi;
+	__u32 type;
+	__u32 flags;
+	__u32 pad;
+	union {
+		struct kvm_irq_routing_irqchip irqchip;
+		struct kvm_irq_routing_msi msi;
+		__u32 pad[8];
+	} u;
+};
+
+/* gsi routing entry types */
+#define KVM_IRQ_ROUTING_IRQCHIP 1
+#define KVM_IRQ_ROUTING_MSI 2
+
+No flags are specified so far, the corresponding field must be set to zero.
+
+struct kvm_irq_routing_irqchip {
+	__u32 irqchip;
+	__u32 pin;
+};
+
+struct kvm_irq_routing_msi {
+	__u32 address_lo;
+	__u32 address_hi;
+	__u32 data;
+	__u32 pad;
+};
+
+4.52 KVM_ASSIGN_SET_MSIX_NR
+
+Capability: KVM_CAP_DEVICE_MSIX
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_msix_nr (in)
+Returns: 0 on success, -1 on error
+
+Set the number of MSI-X interrupts for an assigned device. This service can
+only be called once in the lifetime of an assigned device.
+
+struct kvm_assigned_msix_nr {
+	__u32 assigned_dev_id;
+	__u16 entry_nr;
+	__u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV		256
+
+4.53 KVM_ASSIGN_SET_MSIX_ENTRY
+
+Capability: KVM_CAP_DEVICE_MSIX
+Architectures: x86 ia64
+Type: vm ioctl
+Parameters: struct kvm_assigned_msix_entry (in)
+Returns: 0 on success, -1 on error
+
+Specifies the routing of an MSI-X assigned device interrupt to a GSI. Setting
+the GSI vector to zero means disabling the interrupt.
+
+struct kvm_assigned_msix_entry {
+	__u32 assigned_dev_id;
+	__u32 gsi;
+	__u16 entry; /* The index of entry in the MSI-X table */
+	__u16 padding[3];
+};
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by
-- 
1.7.1

Re: [PATCH v5-light 0/6] KVM: Improve IRQ assignment for device passthrough

[Alex Williamson]

On Tue, 2010-11-16 at 22:30 +0100, Jan Kiszka wrote:
> This is the rebased light version of the previous series, i.e. without
> PCI-2.3-based IRQ masking or any SRCU conversion. PCI-2.3 support is
> under rework to explore options for automatic mode switches.
> 
> Jan Kiszka (6):
>   KVM: Clear assigned guest IRQ on release
>   KVM: Switch assigned device IRQ forwarding to threaded handler
>   KVM: Refactor IRQ names of assigned devices
>   KVM: Save/restore state of assigned PCI device
>   KVM: Clean up kvm_vm_ioctl_assigned_device
>   KVM: Document device assigment API
> 
>  Documentation/kvm/api.txt |  178 +++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/kvm_host.h  |   13 +---
>  virt/kvm/assigned-dev.c   |  125 ++++++++++++--------------------
>  3 files changed, 227 insertions(+), 89 deletions(-)
> 

Series looks good to me.

Acked-by: Alex Williamson <alex.williamson@redhat.com>

Re: [PATCH v5-light 0/6] KVM: Improve IRQ assignment for device passthrough

[Avi Kivity]

On 11/16/2010 11:30 PM, Jan Kiszka wrote:
> This is the rebased light version of the previous series, i.e. without
> PCI-2.3-based IRQ masking or any SRCU conversion. PCI-2.3 support is
> under rework to explore options for automatic mode switches.
>

Looks good, especially the threaded irq - a real winner.

-- 
error compiling committee.c: too many arguments to function

Re: [PATCH v5-light 0/6] KVM: Improve IRQ assignment for device passthrough

[Michael S. Tsirkin]

On Tue, Nov 16, 2010 at 10:30:01PM +0100, Jan Kiszka wrote:
> This is the rebased light version of the previous series, i.e. without
> PCI-2.3-based IRQ masking or any SRCU conversion. PCI-2.3 support is
> under rework to explore options for automatic mode switches.
> 
> Jan Kiszka (6):
>   KVM: Clear assigned guest IRQ on release
>   KVM: Switch assigned device IRQ forwarding to threaded handler
>   KVM: Refactor IRQ names of assigned devices
>   KVM: Save/restore state of assigned PCI device
>   KVM: Clean up kvm_vm_ioctl_assigned_device
>   KVM: Document device assigment API
> 
>  Documentation/kvm/api.txt |  178 +++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/kvm_host.h  |   13 +---
>  virt/kvm/assigned-dev.c   |  125 ++++++++++++--------------------
>  3 files changed, 227 insertions(+), 89 deletions(-)

Acked-by: Michael S. Tsirkin <mst@redhat.com>

Re: [PATCH v5-light 0/6] KVM: Improve IRQ assignment for device passthrough

[Marcelo Tosatti]

On Tue, Nov 16, 2010 at 10:30:01PM +0100, Jan Kiszka wrote:
> This is the rebased light version of the previous series, i.e. without
> PCI-2.3-based IRQ masking or any SRCU conversion. PCI-2.3 support is
> under rework to explore options for automatic mode switches.
> 
> Jan Kiszka (6):
>   KVM: Clear assigned guest IRQ on release
>   KVM: Switch assigned device IRQ forwarding to threaded handler
>   KVM: Refactor IRQ names of assigned devices
>   KVM: Save/restore state of assigned PCI device
>   KVM: Clean up kvm_vm_ioctl_assigned_device
>   KVM: Document device assigment API
> 
>  Documentation/kvm/api.txt |  178 +++++++++++++++++++++++++++++++++++++++++++++
>  include/linux/kvm_host.h  |   13 +---
>  virt/kvm/assigned-dev.c   |  125 ++++++++++++--------------------
>  3 files changed, 227 insertions(+), 89 deletions(-)

Applied, thanks.