Michael S. Tsirkin
2014-Dec-08 15:16 UTC
[PATCH v2 08/10] virtio_pci: split out legacy device support
Move everything dealing with legacy devices out to virtio_pci_legacy.c.
Expose common code APIs in virtio_pci.h
Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
---
drivers/virtio/virtio_pci.h | 133 ++++++++++++
drivers/virtio/virtio_pci.c | 420 ++-----------------------------------
drivers/virtio/virtio_pci_legacy.c | 323 ++++++++++++++++++++++++++++
3 files changed, 468 insertions(+), 408 deletions(-)
create mode 100644 drivers/virtio/virtio_pci.h
create mode 100644 drivers/virtio/virtio_pci_legacy.c
diff --git a/drivers/virtio/virtio_pci.h b/drivers/virtio/virtio_pci.h
new file mode 100644
index 0000000..a3b1259
--- /dev/null
+++ b/drivers/virtio/virtio_pci.h
@@ -0,0 +1,133 @@
+#ifndef _DRIVERS_VIRTIO_VIRTIO_PCI_H
+#define _DRIVERS_VIRTIO_VIRTIO_PCI_H
+/*
+ * Virtio PCI driver
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors:
+ * Anthony Liguori <aliguori at us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/virtio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+#define VIRTIO_PCI_NO_LEGACY
+#include <linux/virtio_pci.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+
+struct virtio_pci_vq_info {
+ /* the actual virtqueue */
+ struct virtqueue *vq;
+
+ /* the number of entries in the queue */
+ int num;
+
+ /* the virtual address of the ring queue */
+ void *queue;
+
+ /* the list node for the virtqueues list */
+ struct list_head node;
+
+ /* MSI-X vector (or none) */
+ unsigned msix_vector;
+};
+
+/* Our device structure */
+struct virtio_pci_device {
+ struct virtio_device vdev;
+ struct pci_dev *pci_dev;
+
+ /* the IO mapping for the PCI config space */
+ void __iomem *ioaddr;
+
+ /* the IO mapping for ISR operation */
+ void __iomem *isr;
+
+ /* a list of queues so we can dispatch IRQs */
+ spinlock_t lock;
+ struct list_head virtqueues;
+
+ /* array of all queues for house-keeping */
+ struct virtio_pci_vq_info **vqs;
+
+ /* MSI-X support */
+ int msix_enabled;
+ int intx_enabled;
+ struct msix_entry *msix_entries;
+ cpumask_var_t *msix_affinity_masks;
+ /* Name strings for interrupts. This size should be enough,
+ * and I'm too lazy to allocate each name separately. */
+ char (*msix_names)[256];
+ /* Number of available vectors */
+ unsigned msix_vectors;
+ /* Vectors allocated, excluding per-vq vectors if any */
+ unsigned msix_used_vectors;
+
+ /* Whether we have vector per vq */
+ bool per_vq_vectors;
+
+ struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
+ unsigned idx,
+ void (*callback)(struct virtqueue *vq),
+ const char *name,
+ u16 msix_vec);
+ void (*del_vq)(struct virtio_pci_vq_info *info);
+
+ u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
+};
+
+/* Constants for MSI-X */
+/* Use first vector for configuration changes, second and the rest for
+ * virtqueues Thus, we need at least 2 vectors for MSI. */
+enum {
+ VP_MSIX_CONFIG_VECTOR = 0,
+ VP_MSIX_VQ_VECTOR = 1,
+};
+
+/* Convert a generic virtio device to our structure */
+static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
+{
+ return container_of(vdev, struct virtio_pci_device, vdev);
+}
+
+/* wait for pending irq handlers */
+void vp_synchronize_vectors(struct virtio_device *vdev);
+/* the notify function used when creating a virt queue */
+bool vp_notify(struct virtqueue *vq);
+/* the config->del_vqs() implementation */
+void vp_del_vqs(struct virtio_device *vdev);
+/* the config->find_vqs() implementation */
+int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char *names[]);
+const char *vp_bus_name(struct virtio_device *vdev);
+
+/* Setup the affinity for a virtqueue:
+ * - force the affinity for per vq vector
+ * - OR over all affinities for shared MSI
+ * - ignore the affinity request if we're using INTX
+ */
+int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
+void virtio_pci_release_dev(struct device *);
+
+#ifdef CONFIG_PM_SLEEP
+extern const struct dev_pm_ops virtio_pci_pm_ops;
+#endif
+
+#endif
diff --git a/drivers/virtio/virtio_pci.c b/drivers/virtio/virtio_pci.c
index c8ca3f7..d73ceec 100644
--- a/drivers/virtio/virtio_pci.c
+++ b/drivers/virtio/virtio_pci.c
@@ -14,179 +14,10 @@
*
*/
-#include <linux/module.h>
-#include <linux/list.h>
-#include <linux/pci.h>
-#include <linux/slab.h>
-#include <linux/interrupt.h>
-#include <linux/virtio.h>
-#include <linux/virtio_config.h>
-#include <linux/virtio_ring.h>
-#include <linux/virtio_pci.h>
-#include <linux/highmem.h>
-#include <linux/spinlock.h>
-
-MODULE_AUTHOR("Anthony Liguori <aliguori at us.ibm.com>");
-MODULE_DESCRIPTION("virtio-pci");
-MODULE_LICENSE("GPL");
-MODULE_VERSION("1");
-
-struct virtio_pci_vq_info {
- /* the actual virtqueue */
- struct virtqueue *vq;
-
- /* the number of entries in the queue */
- int num;
-
- /* the virtual address of the ring queue */
- void *queue;
-
- /* the list node for the virtqueues list */
- struct list_head node;
-
- /* MSI-X vector (or none) */
- unsigned msix_vector;
-};
-
-/* Our device structure */
-struct virtio_pci_device {
- struct virtio_device vdev;
- struct pci_dev *pci_dev;
-
- /* the IO mapping for the PCI config space */
- void __iomem *ioaddr;
-
- /* the IO mapping for ISR operation */
- void __iomem *isr;
-
- /* a list of queues so we can dispatch IRQs */
- spinlock_t lock;
- struct list_head virtqueues;
-
- /* array of all queues for house-keeping */
- struct virtio_pci_vq_info **vqs;
-
- /* MSI-X support */
- int msix_enabled;
- int intx_enabled;
- struct msix_entry *msix_entries;
- cpumask_var_t *msix_affinity_masks;
- /* Name strings for interrupts. This size should be enough,
- * and I'm too lazy to allocate each name separately. */
- char (*msix_names)[256];
- /* Number of available vectors */
- unsigned msix_vectors;
- /* Vectors allocated, excluding per-vq vectors if any */
- unsigned msix_used_vectors;
-
- /* Whether we have vector per vq */
- bool per_vq_vectors;
-
- struct virtqueue *(*setup_vq)(struct virtio_pci_device *vp_dev,
- struct virtio_pci_vq_info *info,
- unsigned idx,
- void (*callback)(struct virtqueue *vq),
- const char *name,
- u16 msix_vec);
- void (*del_vq)(struct virtio_pci_vq_info *info);
- u16 (*config_vector)(struct virtio_pci_device *vp_dev, u16 vector);
-};
-
-/* Constants for MSI-X */
-/* Use first vector for configuration changes, second and the rest for
- * virtqueues Thus, we need at least 2 vectors for MSI. */
-enum {
- VP_MSIX_CONFIG_VECTOR = 0,
- VP_MSIX_VQ_VECTOR = 1,
-};
-
-/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
-static const struct pci_device_id virtio_pci_id_table[] = {
- { PCI_DEVICE(0x1af4, PCI_ANY_ID) },
- { 0 }
-};
-
-MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
-
-/* Convert a generic virtio device to our structure */
-static struct virtio_pci_device *to_vp_device(struct virtio_device *vdev)
-{
- return container_of(vdev, struct virtio_pci_device, vdev);
-}
-
-/* virtio config->get_features() implementation */
-static u64 vp_get_features(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
- /* When someone needs more than 32 feature bits, we'll need to
- * steal a bit to indicate that the rest are somewhere else. */
- return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
-}
-
-/* virtio config->finalize_features() implementation */
-static int vp_finalize_features(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
- /* Give virtio_ring a chance to accept features. */
- vring_transport_features(vdev);
-
- /* Make sure we don't have any features > 32 bits! */
- BUG_ON((u32)vdev->features != vdev->features);
-
- /* We only support 32 feature bits. */
- iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
-
- return 0;
-}
-
-/* virtio config->get() implementation */
-static void vp_get(struct virtio_device *vdev, unsigned offset,
- void *buf, unsigned len)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- void __iomem *ioaddr = vp_dev->ioaddr +
- VIRTIO_PCI_CONFIG(vp_dev) + offset;
- u8 *ptr = buf;
- int i;
-
- for (i = 0; i < len; i++)
- ptr[i] = ioread8(ioaddr + i);
-}
-
-/* the config->set() implementation. it's symmetric to the
config->get()
- * implementation */
-static void vp_set(struct virtio_device *vdev, unsigned offset,
- const void *buf, unsigned len)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- void __iomem *ioaddr = vp_dev->ioaddr +
- VIRTIO_PCI_CONFIG(vp_dev) + offset;
- const u8 *ptr = buf;
- int i;
-
- for (i = 0; i < len; i++)
- iowrite8(ptr[i], ioaddr + i);
-}
-
-/* config->{get,set}_status() implementations */
-static u8 vp_get_status(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
-}
-
-static void vp_set_status(struct virtio_device *vdev, u8 status)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- /* We should never be setting status to 0. */
- BUG_ON(status == 0);
- iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
-}
+#include "virtio_pci_legacy.c"
/* wait for pending irq handlers */
-static void vp_synchronize_vectors(struct virtio_device *vdev)
+void vp_synchronize_vectors(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
int i;
@@ -198,20 +29,8 @@ static void vp_synchronize_vectors(struct virtio_device
*vdev)
synchronize_irq(vp_dev->msix_entries[i].vector);
}
-static void vp_reset(struct virtio_device *vdev)
-{
- struct virtio_pci_device *vp_dev = to_vp_device(vdev);
- /* 0 status means a reset. */
- iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
- /* Flush out the status write, and flush in device writes,
- * including MSi-X interrupts, if any. */
- ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
- /* Flush pending VQ/configuration callbacks. */
- vp_synchronize_vectors(vdev);
-}
-
/* the notify function used when creating a virt queue */
-static bool vp_notify(struct virtqueue *vq)
+bool vp_notify(struct virtqueue *vq)
{
/* we write the queue's selector into the notification register to
* signal the other end */
@@ -272,15 +91,6 @@ static irqreturn_t vp_interrupt(int irq, void *opaque)
return vp_vring_interrupt(irq, opaque);
}
-u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
-{
- /* Setup the vector used for configuration events */
- iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
- /* Verify we had enough resources to assign the vector */
- /* Will also flush the write out to device */
- return ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
-}
-
static void vp_free_vectors(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -401,68 +211,6 @@ static int vp_request_intx(struct virtio_device *vdev)
return err;
}
-static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
- struct virtio_pci_vq_info *info,
- unsigned index,
- void (*callback)(struct virtqueue *vq),
- const char *name,
- u16 msix_vec)
-{
- struct virtqueue *vq;
- unsigned long size;
- u16 num;
- int err;
-
- /* Select the queue we're interested in */
- iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
-
- /* Check if queue is either not available or already active. */
- num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
- if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
- return ERR_PTR(-ENOENT);
-
- info->num = num;
- info->msix_vector = msix_vec;
-
- size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
- info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
- if (info->queue == NULL)
- return ERR_PTR(-ENOMEM);
-
- /* activate the queue */
- iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
- vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
-
- /* create the vring */
- vq = vring_new_virtqueue(index, info->num,
- VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
- true, info->queue, vp_notify, callback, name);
- if (!vq) {
- err = -ENOMEM;
- goto out_activate_queue;
- }
-
- vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
-
- if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
- iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
- msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
- if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
- err = -EBUSY;
- goto out_assign;
- }
- }
-
- return vq;
-
-out_assign:
- vring_del_virtqueue(vq);
-out_activate_queue:
- iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
- free_pages_exact(info->queue, size);
- return ERR_PTR(err);
-}
-
static struct virtqueue *vp_setup_vq(struct virtio_device *vdev, unsigned
index,
void (*callback)(struct virtqueue *vq),
const char *name,
@@ -498,30 +246,6 @@ out_info:
return vq;
}
-static void del_vq(struct virtio_pci_vq_info *info)
-{
- struct virtqueue *vq = info->vq;
- struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
- unsigned long size;
-
- iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
-
- if (vp_dev->msix_enabled) {
- iowrite16(VIRTIO_MSI_NO_VECTOR,
- vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
- /* Flush the write out to device */
- ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
- }
-
- vring_del_virtqueue(vq);
-
- /* Select and deactivate the queue */
- iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
-
- size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
- free_pages_exact(info->queue, size);
-}
-
static void vp_del_vq(struct virtqueue *vq)
{
struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
@@ -537,7 +261,7 @@ static void vp_del_vq(struct virtqueue *vq)
}
/* the config->del_vqs() implementation */
-static void vp_del_vqs(struct virtio_device *vdev)
+void vp_del_vqs(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
struct virtqueue *vq, *n;
@@ -637,10 +361,10 @@ error_find:
}
/* the config->find_vqs() implementation */
-static int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
- struct virtqueue *vqs[],
- vq_callback_t *callbacks[],
- const char *names[])
+int vp_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+ struct virtqueue *vqs[],
+ vq_callback_t *callbacks[],
+ const char *names[])
{
int err;
@@ -658,7 +382,7 @@ static int vp_find_vqs(struct virtio_device *vdev, unsigned
nvqs,
false, false);
}
-static const char *vp_bus_name(struct virtio_device *vdev)
+const char *vp_bus_name(struct virtio_device *vdev)
{
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -670,7 +394,7 @@ static const char *vp_bus_name(struct virtio_device *vdev)
* - OR over all affinities for shared MSI
* - ignore the affinity request if we're using INTX
*/
-static int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
{
struct virtio_device *vdev = vq->vdev;
struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -694,21 +418,7 @@ static int vp_set_vq_affinity(struct virtqueue *vq, int
cpu)
return 0;
}
-static const struct virtio_config_ops virtio_pci_config_ops = {
- .get = vp_get,
- .set = vp_set,
- .get_status = vp_get_status,
- .set_status = vp_set_status,
- .reset = vp_reset,
- .find_vqs = vp_find_vqs,
- .del_vqs = vp_del_vqs,
- .get_features = vp_get_features,
- .finalize_features = vp_finalize_features,
- .bus_name = vp_bus_name,
- .set_vq_affinity = vp_set_vq_affinity,
-};
-
-static void virtio_pci_release_dev(struct device *_d)
+void virtio_pci_release_dev(struct device *_d)
{
/*
* No need for a release method as we allocate/free
@@ -717,100 +427,6 @@ static void virtio_pci_release_dev(struct device *_d)
*/
}
-/* the PCI probing function */
-static int virtio_pci_probe(struct pci_dev *pci_dev,
- const struct pci_device_id *id)
-{
- struct virtio_pci_device *vp_dev;
- int err;
-
- /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
- if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
- return -ENODEV;
-
- if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
- printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
- VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
- return -ENODEV;
- }
-
- /* allocate our structure and fill it out */
- vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
- if (vp_dev == NULL)
- return -ENOMEM;
-
- vp_dev->vdev.dev.parent = &pci_dev->dev;
- vp_dev->vdev.dev.release = virtio_pci_release_dev;
- vp_dev->vdev.config = &virtio_pci_config_ops;
- vp_dev->pci_dev = pci_dev;
- INIT_LIST_HEAD(&vp_dev->virtqueues);
- spin_lock_init(&vp_dev->lock);
-
- /* Disable MSI/MSIX to bring device to a known good state. */
- pci_msi_off(pci_dev);
-
- /* enable the device */
- err = pci_enable_device(pci_dev);
- if (err)
- goto out;
-
- err = pci_request_regions(pci_dev, "virtio-pci");
- if (err)
- goto out_enable_device;
-
- vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
- if (vp_dev->ioaddr == NULL) {
- err = -ENOMEM;
- goto out_req_regions;
- }
-
- vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
-
- pci_set_drvdata(pci_dev, vp_dev);
- pci_set_master(pci_dev);
-
- /* we use the subsystem vendor/device id as the virtio vendor/device
- * id. this allows us to use the same PCI vendor/device id for all
- * virtio devices and to identify the particular virtio driver by
- * the subsystem ids */
- vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
- vp_dev->vdev.id.device = pci_dev->subsystem_device;
-
- vp_dev->config_vector = vp_config_vector;
- vp_dev->setup_vq = setup_vq;
- vp_dev->del_vq = del_vq;
-
- /* finally register the virtio device */
- err = register_virtio_device(&vp_dev->vdev);
- if (err)
- goto out_set_drvdata;
-
- return 0;
-
-out_set_drvdata:
- pci_iounmap(pci_dev, vp_dev->ioaddr);
-out_req_regions:
- pci_release_regions(pci_dev);
-out_enable_device:
- pci_disable_device(pci_dev);
-out:
- kfree(vp_dev);
- return err;
-}
-
-static void virtio_pci_remove(struct pci_dev *pci_dev)
-{
- struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-
- unregister_virtio_device(&vp_dev->vdev);
-
- vp_del_vqs(&vp_dev->vdev);
- pci_iounmap(pci_dev, vp_dev->ioaddr);
- pci_release_regions(pci_dev);
- pci_disable_device(pci_dev);
- kfree(vp_dev);
-}
-
#ifdef CONFIG_PM_SLEEP
static int virtio_pci_freeze(struct device *dev)
{
@@ -839,19 +455,7 @@ static int virtio_pci_restore(struct device *dev)
return virtio_device_restore(&vp_dev->vdev);
}
-static const struct dev_pm_ops virtio_pci_pm_ops = {
+const struct dev_pm_ops virtio_pci_pm_ops = {
SET_SYSTEM_SLEEP_PM_OPS(virtio_pci_freeze, virtio_pci_restore)
};
#endif
-
-static struct pci_driver virtio_pci_driver = {
- .name = "virtio-pci",
- .id_table = virtio_pci_id_table,
- .probe = virtio_pci_probe,
- .remove = virtio_pci_remove,
-#ifdef CONFIG_PM_SLEEP
- .driver.pm = &virtio_pci_pm_ops,
-#endif
-};
-
-module_pci_driver(virtio_pci_driver);
diff --git a/drivers/virtio/virtio_pci_legacy.c
b/drivers/virtio/virtio_pci_legacy.c
new file mode 100644
index 0000000..9fdec9a
--- /dev/null
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -0,0 +1,323 @@
+/*
+ * Virtio PCI driver
+ *
+ * This module allows virtio devices to be used over a virtual PCI device.
+ * This can be used with QEMU based VMMs like KVM or Xen.
+ *
+ * Copyright IBM Corp. 2007
+ *
+ * Authors:
+ * Anthony Liguori <aliguori at us.ibm.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "virtio_pci.h"
+
+/* Qumranet donated their vendor ID for devices 0x1000 thru 0x10FF. */
+static const struct pci_device_id virtio_pci_id_table[] = {
+ { PCI_DEVICE(0x1af4, PCI_ANY_ID) },
+ { 0 }
+};
+
+MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
+
+/* virtio config->get_features() implementation */
+static u64 vp_get_features(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ /* When someone needs more than 32 feature bits, we'll need to
+ * steal a bit to indicate that the rest are somewhere else. */
+ return ioread32(vp_dev->ioaddr + VIRTIO_PCI_HOST_FEATURES);
+}
+
+/* virtio config->finalize_features() implementation */
+static int vp_finalize_features(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+ /* Give virtio_ring a chance to accept features. */
+ vring_transport_features(vdev);
+
+ /* Make sure we don't have any features > 32 bits! */
+ BUG_ON((u32)vdev->features != vdev->features);
+
+ /* We only support 32 feature bits. */
+ iowrite32(vdev->features, vp_dev->ioaddr + VIRTIO_PCI_GUEST_FEATURES);
+
+ return 0;
+}
+
+/* virtio config->get() implementation */
+static void vp_get(struct virtio_device *vdev, unsigned offset,
+ void *buf, unsigned len)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ void __iomem *ioaddr = vp_dev->ioaddr +
+ VIRTIO_PCI_CONFIG(vp_dev) + offset;
+ u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ ptr[i] = ioread8(ioaddr + i);
+}
+
+/* the config->set() implementation. it's symmetric to the
config->get()
+ * implementation */
+static void vp_set(struct virtio_device *vdev, unsigned offset,
+ const void *buf, unsigned len)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ void __iomem *ioaddr = vp_dev->ioaddr +
+ VIRTIO_PCI_CONFIG(vp_dev) + offset;
+ const u8 *ptr = buf;
+ int i;
+
+ for (i = 0; i < len; i++)
+ iowrite8(ptr[i], ioaddr + i);
+}
+
+/* config->{get,set}_status() implementations */
+static u8 vp_get_status(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ return ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_set_status(struct virtio_device *vdev, u8 status)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ /* We should never be setting status to 0. */
+ BUG_ON(status == 0);
+ iowrite8(status, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+}
+
+static void vp_reset(struct virtio_device *vdev)
+{
+ struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+ /* 0 status means a reset. */
+ iowrite8(0, vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+ /* Flush out the status write, and flush in device writes,
+ * including MSi-X interrupts, if any. */
+ ioread8(vp_dev->ioaddr + VIRTIO_PCI_STATUS);
+ /* Flush pending VQ/configuration callbacks. */
+ vp_synchronize_vectors(vdev);
+}
+
+u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+{
+ /* Setup the vector used for configuration events */
+ iowrite16(vector, vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+ /* Verify we had enough resources to assign the vector */
+ /* Will also flush the write out to device */
+ return ioread16(vp_dev->ioaddr + VIRTIO_MSI_CONFIG_VECTOR);
+}
+
+static struct virtqueue *setup_vq(struct virtio_pci_device *vp_dev,
+ struct virtio_pci_vq_info *info,
+ unsigned index,
+ void (*callback)(struct virtqueue *vq),
+ const char *name,
+ u16 msix_vec)
+{
+ struct virtqueue *vq;
+ unsigned long size;
+ u16 num;
+ int err;
+
+ /* Select the queue we're interested in */
+ iowrite16(index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+ /* Check if queue is either not available or already active. */
+ num = ioread16(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NUM);
+ if (!num || ioread32(vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN))
+ return ERR_PTR(-ENOENT);
+
+ info->num = num;
+ info->msix_vector = msix_vec;
+
+ size = PAGE_ALIGN(vring_size(num, VIRTIO_PCI_VRING_ALIGN));
+ info->queue = alloc_pages_exact(size, GFP_KERNEL|__GFP_ZERO);
+ if (info->queue == NULL)
+ return ERR_PTR(-ENOMEM);
+
+ /* activate the queue */
+ iowrite32(virt_to_phys(info->queue) >> VIRTIO_PCI_QUEUE_ADDR_SHIFT,
+ vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+ /* create the vring */
+ vq = vring_new_virtqueue(index, info->num,
+ VIRTIO_PCI_VRING_ALIGN, &vp_dev->vdev,
+ true, info->queue, vp_notify, callback, name);
+ if (!vq) {
+ err = -ENOMEM;
+ goto out_activate_queue;
+ }
+
+ vq->priv = (void __force *)vp_dev->ioaddr + VIRTIO_PCI_QUEUE_NOTIFY;
+
+ if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+ iowrite16(msix_vec, vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+ msix_vec = ioread16(vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+ if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+ err = -EBUSY;
+ goto out_assign;
+ }
+ }
+
+ return vq;
+
+out_assign:
+ vring_del_virtqueue(vq);
+out_activate_queue:
+ iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+ free_pages_exact(info->queue, size);
+ return ERR_PTR(err);
+}
+
+static void del_vq(struct virtio_pci_vq_info *info)
+{
+ struct virtqueue *vq = info->vq;
+ struct virtio_pci_device *vp_dev = to_vp_device(vq->vdev);
+ unsigned long size;
+
+ iowrite16(vq->index, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_SEL);
+
+ if (vp_dev->msix_enabled) {
+ iowrite16(VIRTIO_MSI_NO_VECTOR,
+ vp_dev->ioaddr + VIRTIO_MSI_QUEUE_VECTOR);
+ /* Flush the write out to device */
+ ioread8(vp_dev->ioaddr + VIRTIO_PCI_ISR);
+ }
+
+ vring_del_virtqueue(vq);
+
+ /* Select and deactivate the queue */
+ iowrite32(0, vp_dev->ioaddr + VIRTIO_PCI_QUEUE_PFN);
+
+ size = PAGE_ALIGN(vring_size(info->num, VIRTIO_PCI_VRING_ALIGN));
+ free_pages_exact(info->queue, size);
+}
+
+static const struct virtio_config_ops virtio_pci_config_ops = {
+ .get = vp_get,
+ .set = vp_set,
+ .get_status = vp_get_status,
+ .set_status = vp_set_status,
+ .reset = vp_reset,
+ .find_vqs = vp_find_vqs,
+ .del_vqs = vp_del_vqs,
+ .get_features = vp_get_features,
+ .finalize_features = vp_finalize_features,
+ .bus_name = vp_bus_name,
+ .set_vq_affinity = vp_set_vq_affinity,
+};
+
+/* the PCI probing function */
+static int virtio_pci_probe(struct pci_dev *pci_dev,
+ const struct pci_device_id *id)
+{
+ struct virtio_pci_device *vp_dev;
+ int err;
+
+ /* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
+ if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
+ return -ENODEV;
+
+ if (pci_dev->revision != VIRTIO_PCI_ABI_VERSION) {
+ printk(KERN_ERR "virtio_pci: expected ABI version %d, got %d\n",
+ VIRTIO_PCI_ABI_VERSION, pci_dev->revision);
+ return -ENODEV;
+ }
+
+ /* allocate our structure and fill it out */
+ vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+ if (vp_dev == NULL)
+ return -ENOMEM;
+
+ vp_dev->vdev.dev.parent = &pci_dev->dev;
+ vp_dev->vdev.dev.release = virtio_pci_release_dev;
+ vp_dev->vdev.config = &virtio_pci_config_ops;
+ vp_dev->pci_dev = pci_dev;
+ INIT_LIST_HEAD(&vp_dev->virtqueues);
+ spin_lock_init(&vp_dev->lock);
+
+ /* Disable MSI/MSIX to bring device to a known good state. */
+ pci_msi_off(pci_dev);
+
+ /* enable the device */
+ err = pci_enable_device(pci_dev);
+ if (err)
+ goto out;
+
+ err = pci_request_regions(pci_dev, "virtio-pci");
+ if (err)
+ goto out_enable_device;
+
+ vp_dev->ioaddr = pci_iomap(pci_dev, 0, 0);
+ if (vp_dev->ioaddr == NULL) {
+ err = -ENOMEM;
+ goto out_req_regions;
+ }
+
+ vp_dev->isr = vp_dev->ioaddr + VIRTIO_PCI_ISR;
+
+ pci_set_drvdata(pci_dev, vp_dev);
+ pci_set_master(pci_dev);
+
+ /* we use the subsystem vendor/device id as the virtio vendor/device
+ * id. this allows us to use the same PCI vendor/device id for all
+ * virtio devices and to identify the particular virtio driver by
+ * the subsystem ids */
+ vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+ vp_dev->vdev.id.device = pci_dev->subsystem_device;
+
+ vp_dev->config_vector = vp_config_vector;
+ vp_dev->setup_vq = setup_vq;
+ vp_dev->del_vq = del_vq;
+
+ /* finally register the virtio device */
+ err = register_virtio_device(&vp_dev->vdev);
+ if (err)
+ goto out_set_drvdata;
+
+ return 0;
+
+out_set_drvdata:
+ pci_iounmap(pci_dev, vp_dev->ioaddr);
+out_req_regions:
+ pci_release_regions(pci_dev);
+out_enable_device:
+ pci_disable_device(pci_dev);
+out:
+ kfree(vp_dev);
+ return err;
+}
+
+static void virtio_pci_remove(struct pci_dev *pci_dev)
+{
+ struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+ unregister_virtio_device(&vp_dev->vdev);
+
+ vp_del_vqs(&vp_dev->vdev);
+ pci_iounmap(pci_dev, vp_dev->ioaddr);
+ pci_release_regions(pci_dev);
+ pci_disable_device(pci_dev);
+ kfree(vp_dev);
+}
+
+static struct pci_driver virtio_pci_driver = {
+ .name = "virtio-pci",
+ .id_table = virtio_pci_id_table,
+ .probe = virtio_pci_probe,
+ .remove = virtio_pci_remove,
+#ifdef CONFIG_PM_SLEEP
+ .driver.pm = &virtio_pci_pm_ops,
+#endif
+};
+
+module_pci_driver(virtio_pci_driver);
--
MST
Possibly Parallel Threads
- [PATCH v2 08/10] virtio_pci: split out legacy device support
- [PATCH 8/9] virtio_pci: split out legacy device support
- [PATCH 8/9] virtio_pci: split out legacy device support
- [kvm-devel] [Virtio-for-kvm] [PATCH 05/13] [Mostly resend] virtio additions
- [kvm-devel] [Virtio-for-kvm] [PATCH 05/13] [Mostly resend] virtio additions
Wisdom of the Ancients
