[PATCH v3] virt: IRQ bypass manager

[Alex Williamson]

When a physical I/O device is assigned to a virtual machine through
facilities like VFIO and KVM, the interrupt for the device generally
bounces through the host system before being injected into the VM.
However, hardware technologies exist that often allow the host to be
bypassed for some of these scenarios.  Intel Posted Interrupts allow
the specified physical edge interrupts to be directly injected into a
guest when delivered to a physical processor while the vCPU is
running.  ARM IRQ Forwarding allows forwarded physical interrupts to
be directly deactivated by the guest.

The IRQ bypass manager here is meant to provide the shim to connect
interrupt producers, generally the host physical device driver, with
interrupt consumers, generally the hypervisor, in order to configure
these bypass mechanism.  To do this, we base the connection on a
shared, opaque token.  For KVM-VFIO this is expected to be an
eventfd_ctx since this is the connection we already use to connect an
eventfd to an irqfd on the in-kernel path.  When a producer and
consumer with matching tokens is found, callbacks via both registered
participants allow the bypass facilities to be automatically enabled.

Signed-off-by: Alex Williamson <alex.williamson@xxxxxxxxxx>
---

v3: Fix list_for_each_entry issue noted by Eric

Do we want to revisit whether add and del are required callbacks?
Maybe they should only be required for the consumer?  If Feng already
doesn't require them for Intel PI, let's not impose stub callback
requirements.

 MAINTAINERS               |    7 +
 include/linux/irqbypass.h |   90 ++++++++++++++++
 virt/lib/Kconfig          |    2 
 virt/lib/Makefile         |    1 
 virt/lib/irqbypass.c      |  256 +++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 356 insertions(+)
 create mode 100644 include/linux/irqbypass.h
 create mode 100644 virt/lib/Kconfig
 create mode 100644 virt/lib/Makefile
 create mode 100644 virt/lib/irqbypass.c

diff --git a/MAINTAINERS b/MAINTAINERS
index a9ae6c1..10c8b2f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10963,6 +10963,13 @@ L:	netdev@xxxxxxxxxxxxxxx
 S:	Maintained
 F:	drivers/net/ethernet/via/via-velocity.*
 
+VIRT LIB
+M:	Alex Williamson <alex.williamson@xxxxxxxxxx>
+M:	Paolo Bonzini <pbonzini@xxxxxxxxxx>
+L:	kvm@xxxxxxxxxxxxxxx
+S:	Supported
+F:	virt/lib/
+
 VIVID VIRTUAL VIDEO DRIVER
 M:	Hans Verkuil <hverkuil@xxxxxxxxx>
 L:	linux-media@xxxxxxxxxxxxxxx
diff --git a/include/linux/irqbypass.h b/include/linux/irqbypass.h
new file mode 100644
index 0000000..fde7b64
--- /dev/null
+++ b/include/linux/irqbypass.h
@@ -0,0 +1,90 @@
+/*
+ * IRQ offload/bypass manager
+ *
+ * Copyright (C) 2015 Red Hat, Inc.
+ * Copyright (c) 2015 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef IRQBYPASS_H
+#define IRQBYPASS_H
+
+#include <linux/list.h>
+
+struct irq_bypass_consumer;
+
+/*
+ * Theory of operation
+ *
+ * The IRQ bypass manager is a simple set of lists and callbacks that allows
+ * IRQ producers (ex. physical interrupt sources) to be matched to IRQ
+ * consumers (ex. virtualization hardware that allows IRQ bypass or offload)
+ * via a shared token (ex. eventfd_ctx).  Producers and consumers register
+ * independently.  When a token match is found, the optional @stop callback
+ * will be called for each participant.  The pair will then be connected via
+ * the @add_* callbacks, and finally the optional @start callback will allow
+ * any final coordination.  When either participant is unregistered, the
+ * process is repeated using the @del_* callbacks in place of the @add_*
+ * callbacks.  Match tokens must be unique per producer/consumer, 1:N pairings
+ * are not supported.
+ */
+
+/**
+ * struct irq_bypass_producer - IRQ bypass producer definition
+ * @node: IRQ bypass manager private list management
+ * @token: opaque token to match between producer and consumer
+ * @irq: Linux IRQ number for the producer device
+ * @add_consumer: Connect the IRQ producer to an IRQ consumer
+ * @del_consumer: Disconnect the IRQ producer from an IRQ consumer
+ * @stop: Perform any quiesce operations necessary prior to add/del (optional)
+ * @start: Perform any startup operations necessary after add/del (optional)
+ *
+ * The IRQ bypass producer structure represents an interrupt source for
+ * participation in possible host bypass, for instance an interrupt vector
+ * for a physical device assigned to a VM.
+ */
+struct irq_bypass_producer {
+	struct list_head node;
+	void *token;
+	int irq;
+	int (*add_consumer)(struct irq_bypass_producer *,
+			    struct irq_bypass_consumer *);
+	void (*del_consumer)(struct irq_bypass_producer *,
+			     struct irq_bypass_consumer *);
+	void (*stop)(struct irq_bypass_producer *);
+	void (*start)(struct irq_bypass_producer *);
+};
+
+/**
+ * struct irq_bypass_consumer - IRQ bypass consumer definition
+ * @node: IRQ bypass manager private list management
+ * @token: opaque token to match between producer and consumer
+ * @add_producer: Connect the IRQ consumer to an IRQ producer
+ * @del_producer: Disconnect the IRQ consumer from an IRQ producer
+ * @stop: Perform any quiesce operations necessary prior to add/del (optional)
+ * @start: Perform any startup operations necessary after add/del (optional)
+ *
+ * The IRQ bypass consumer structure represents an interrupt sink for
+ * participation in possible host bypass, for instance a hypervisor may
+ * support offloads to allow bypassing the host entirely or offload
+ * portions of the interrupt handling to the VM.
+ */
+struct irq_bypass_consumer {
+	struct list_head node;
+	void *token;
+	int (*add_producer)(struct irq_bypass_consumer *,
+			    struct irq_bypass_producer *);
+	void (*del_producer)(struct irq_bypass_consumer *,
+			     struct irq_bypass_producer *);
+	void (*stop)(struct irq_bypass_consumer *);
+	void (*start)(struct irq_bypass_consumer *);
+};
+
+int irq_bypass_register_producer(struct irq_bypass_producer *);
+void irq_bypass_unregister_producer(struct irq_bypass_producer *);
+int irq_bypass_register_consumer(struct irq_bypass_consumer *);
+void irq_bypass_unregister_consumer(struct irq_bypass_consumer *);
+
+#endif /* IRQBYPASS_H */
diff --git a/virt/lib/Kconfig b/virt/lib/Kconfig
new file mode 100644
index 0000000..89a414f
--- /dev/null
+++ b/virt/lib/Kconfig
@@ -0,0 +1,2 @@
+config IRQ_BYPASS_MANAGER
+	tristate
diff --git a/virt/lib/Makefile b/virt/lib/Makefile
new file mode 100644
index 0000000..901228d
--- /dev/null
+++ b/virt/lib/Makefile
@@ -0,0 +1 @@
+obj-$(CONFIG_IRQ_BYPASS_MANAGER) += irqbypass.o
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
new file mode 100644
index 0000000..98a4141
--- /dev/null
+++ b/virt/lib/irqbypass.c
@@ -0,0 +1,256 @@
+/*
+ * IRQ offload/bypass manager
+ *
+ * Copyright (C) 2015 Red Hat, Inc.
+ * Copyright (c) 2015 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Various virtualization hardware acceleration techniques allow bypassing or
+ * offloading interrupts received from devices around the host kernel.  Posted
+ * Interrupts on Intel VT-d systems can allow interrupts to be received
+ * directly by a virtual machine.  ARM IRQ Forwarding allows forwarded physical
+ * interrupts to be directly deactivated by the guest.  This manager allows
+ * interrupt producers and consumers to find each other to enable this sort of
+ * bypass.
+ */
+
+#include <linux/irqbypass.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("IRQ bypass manager utility module");
+
+static LIST_HEAD(producers);
+static LIST_HEAD(consumers);
+static DEFINE_MUTEX(lock);
+
+/* @lock must be held when calling connect */
+static int __connect(struct irq_bypass_producer *prod,
+		     struct irq_bypass_consumer *cons)
+{
+	int ret;
+
+	if (prod->stop)
+		prod->stop(prod);
+	if (cons->stop)
+		cons->stop(cons);
+
+	ret = prod->add_consumer(prod, cons);
+	if (!ret) {
+		ret = cons->add_producer(cons, prod);
+		if (ret)
+			prod->del_consumer(prod, cons);
+	}
+
+	if (cons->start)
+		cons->start(cons);
+	if (prod->start)
+		prod->start(prod);
+
+	return ret;
+}
+
+/* @lock must be held when calling disconnect */
+static void __disconnect(struct irq_bypass_producer *prod,
+			 struct irq_bypass_consumer *cons)
+{
+	if (prod->stop)
+		prod->stop(prod);
+	if (cons->stop)
+		cons->stop(cons);
+
+	cons->del_producer(cons, prod);
+	prod->del_consumer(prod, cons);
+
+	if (cons->start)
+		cons->start(cons);
+	if (prod->start)
+		prod->start(prod);
+}
+
+/**
+ * irq_bypass_register_producer - register IRQ bypass producer
+ * @producer: pointer to producer structure
+ *
+ * Add the provided IRQ producer to the list of producers and connect
+ * with any matching token found on the IRQ consumers list.
+ */
+int irq_bypass_register_producer(struct irq_bypass_producer *producer)
+{
+	struct irq_bypass_producer *tmp;
+	struct irq_bypass_consumer *consumer;
+
+	if (!producer->add_consumer || !producer->del_consumer)
+		return -EINVAL;
+
+	might_sleep();
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	mutex_lock(&lock);
+
+	list_for_each_entry(tmp, &producers, node) {
+		if (tmp->token == producer->token) {
+			mutex_unlock(&lock);
+			module_put(THIS_MODULE);
+			return -EBUSY;
+		}
+	}
+
+	list_for_each_entry(consumer, &consumers, node) {
+		if (consumer->token == producer->token) {
+			int ret = __connect(producer, consumer);
+			if (ret) {
+				mutex_unlock(&lock);
+				module_put(THIS_MODULE);
+				return ret;
+			}
+			break;
+		}
+	}
+
+	list_add(&producer->node, &producers);
+
+	mutex_unlock(&lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_bypass_register_producer);
+
+/**
+ * irq_bypass_unregister_producer - unregister IRQ bypass producer
+ * @producer: pointer to producer structure
+ *
+ * Remove a previously registered IRQ producer from the list of producers
+ * and disconnect it from any connected IRQ consumer.
+ */
+void irq_bypass_unregister_producer(struct irq_bypass_producer *producer)
+{
+	struct irq_bypass_producer *tmp;
+	struct irq_bypass_consumer *consumer;
+
+	might_sleep();
+
+	if (!try_module_get(THIS_MODULE))
+		return; /* nothing in the list anyway */
+
+	mutex_lock(&lock);
+
+	list_for_each_entry(tmp, &producers, node) {
+		if (tmp->token != producer->token)
+			continue;
+
+		list_for_each_entry(consumer, &consumers, node) {
+			if (consumer->token == producer->token) {
+				__disconnect(producer, consumer);
+				break;
+			}
+		}
+
+		list_del(&producer->node);
+		module_put(THIS_MODULE);
+		break;
+	}
+
+	mutex_unlock(&lock);
+
+	module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer);
+
+/**
+ * irq_bypass_register_consumer - register IRQ bypass consumer
+ * @consumer: pointer to consumer structure
+ *
+ * Add the provided IRQ consumer to the list of consumers and connect
+ * with any matching token found on the IRQ producer list.
+ */
+int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
+{
+	struct irq_bypass_consumer *tmp;
+	struct irq_bypass_producer *producer;
+
+	if (!consumer->add_producer || !consumer->del_producer)
+		return -EINVAL;
+
+	might_sleep();
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	mutex_lock(&lock);
+
+	list_for_each_entry(tmp, &consumers, node) {
+		if (tmp->token == consumer->token) {
+			mutex_unlock(&lock);
+			module_put(THIS_MODULE);
+			return -EBUSY;
+		}
+	}
+
+	list_for_each_entry(producer, &producers, node) {
+		if (producer->token == consumer->token) {
+			int ret = __connect(producer, consumer);
+			if (ret) {
+				mutex_unlock(&lock);
+				module_put(THIS_MODULE);
+				return ret;
+			}
+			break;
+		}
+	}
+
+	list_add(&consumer->node, &consumers);
+
+	mutex_unlock(&lock);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(irq_bypass_register_consumer);
+
+/**
+ * irq_bypass_unregister_consumer - unregister IRQ bypass consumer
+ * @consumer: pointer to consumer structure
+ *
+ * Remove a previously registered IRQ consumer from the list of consumers
+ * and disconnect it from any connected IRQ producer.
+ */
+void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
+{
+	struct irq_bypass_consumer *tmp;
+	struct irq_bypass_producer *producer;
+
+	might_sleep();
+
+	if (!try_module_get(THIS_MODULE))
+		return; /* nothing in the list anyway */
+
+	mutex_lock(&lock);
+
+	list_for_each_entry(tmp, &consumers, node) {
+		if (tmp->token != consumer->token)
+			continue;
+
+		list_for_each_entry(producer, &producers, node) {
+			if (producer->token == consumer->token) {
+				__disconnect(producer, consumer);
+				break;
+			}
+		}
+
+		list_del(&consumer->node);
+		module_put(THIS_MODULE);
+		break;
+	}
+
+	mutex_unlock(&lock);
+
+	module_put(THIS_MODULE);
+}
+EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer);

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/