Virtualization - Jan 2015 - [PATCH post-squash 0/9] virtio 1.0: virtio-pci fixup

This is just repost of all patches with fixups squashed in - convenient
if you just want to remove old ones from queue and apply new ones.
I also tweaked commit log for patch
	"virtio_pci: modern driver"
I also included Gerd's tag:
Tested-by: Gerd Hoffmann <kraxel at redhat.com>

You can find it all before the rebase -i --autosquash in my tree:
        git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git virtio-next
or after rebase -i --autosquash:
        git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git vhost-next

Hope it helps!

Michael S. Tsirkin (7):
  virtio_pci: move probe/remove code to common
  virtio_pci: modern driver
  virtio_pci_modern: reduce number of mappings
  virtio_pci_modern: support devices with no config
  virtio_pci: add an option to disable legacy driver
  virtio_pci: add module param to force legacy mode
  virtio_pci_modern: drop an unused function

Rusty Russell (2):
  virtio-pci: define layout for virtio 1.0
  virtio_pci: macros for PCI layout offsets

 drivers/virtio/virtio_pci_common.h |  43 ++-
 include/uapi/linux/virtio_pci.h    |  89 +++++
 drivers/virtio/virtio_pci_common.c |  94 ++++-
 drivers/virtio/virtio_pci_legacy.c |  75 +---
 drivers/virtio/virtio_pci_modern.c | 695 +++++++++++++++++++++++++++++++++++++
 drivers/virtio/Kconfig             |  19 +
 drivers/virtio/Makefile            |   3 +-
 7 files changed, 942 insertions(+), 76 deletions(-)
 create mode 100644 drivers/virtio/virtio_pci_modern.c

-- 
MST

Most of initialization is device-independent.
Let's move it to common.

Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 drivers/virtio/virtio_pci_common.h |  5 +--
 drivers/virtio/virtio_pci_common.c | 69 ++++++++++++++++++++++++++++++++++-
 drivers/virtio/virtio_pci_legacy.c | 75 ++++----------------------------------
 3 files changed, 77 insertions(+), 72 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.h
b/drivers/virtio/virtio_pci_common.h
index 5a49728..2b1e70d 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -127,8 +127,7 @@ const char *vp_bus_name(struct virtio_device *vdev);
  */
 int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
 
-int virtio_pci_legacy_probe(struct pci_dev *pci_dev,
-			    const struct pci_device_id *id);
-void virtio_pci_legacy_remove(struct pci_dev *pci_dev);
+int virtio_pci_legacy_probe(struct virtio_pci_device *);
+void virtio_pci_legacy_remove(struct virtio_pci_device *);
 
 #endif
diff --git a/drivers/virtio/virtio_pci_common.c
b/drivers/virtio/virtio_pci_common.c
index 9756f21..457cbe2 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -464,15 +464,80 @@ static const struct pci_device_id virtio_pci_id_table[] =
{
 
 MODULE_DEVICE_TABLE(pci, virtio_pci_id_table);
 
+static void virtio_pci_release_dev(struct device *_d)
+{
+	struct virtio_device *vdev = dev_to_virtio(_d);
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	/* As struct device is a kobject, it's not safe to
+	 * free the memory (including the reference counter itself)
+	 * until it's release callback. */
+	kfree(vp_dev);
+}
+
 static int virtio_pci_probe(struct pci_dev *pci_dev,
 			    const struct pci_device_id *id)
 {
-	return virtio_pci_legacy_probe(pci_dev, id);
+	struct virtio_pci_device *vp_dev;
+	int rc;
+
+	/* allocate our structure and fill it out */
+	vp_dev = kzalloc(sizeof(struct virtio_pci_device), GFP_KERNEL);
+	if (!vp_dev)
+		return -ENOMEM;
+
+	pci_set_drvdata(pci_dev, vp_dev);
+	vp_dev->vdev.dev.parent = &pci_dev->dev;
+	vp_dev->vdev.dev.release = virtio_pci_release_dev;
+	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 */
+	rc = pci_enable_device(pci_dev);
+	if (rc)
+		goto err_enable_device;
+
+	rc = pci_request_regions(pci_dev, "virtio-pci");
+	if (rc)
+		goto err_request_regions;
+
+	rc = virtio_pci_legacy_probe(vp_dev);
+	if (rc)
+		goto err_probe;
+
+	pci_set_master(pci_dev);
+
+	rc = register_virtio_device(&vp_dev->vdev);
+	if (rc)
+		goto err_register;
+
+	return 0;
+
+err_register:
+	virtio_pci_legacy_remove(vp_dev);
+err_probe:
+	pci_release_regions(pci_dev);
+err_request_regions:
+	pci_disable_device(pci_dev);
+err_enable_device:
+	kfree(vp_dev);
+	return rc;
 }
 
 static void virtio_pci_remove(struct pci_dev *pci_dev)
 {
-     virtio_pci_legacy_remove(pci_dev);
+	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
+
+	unregister_virtio_device(&vp_dev->vdev);
+
+	virtio_pci_legacy_remove(pci_dev);
+
+	pci_release_regions(pci_dev);
+	pci_disable_device(pci_dev);
 }
 
 static struct pci_driver virtio_pci_driver = {
diff --git a/drivers/virtio/virtio_pci_legacy.c
b/drivers/virtio/virtio_pci_legacy.c
index 19f9309..256a527 100644
--- a/drivers/virtio/virtio_pci_legacy.c
+++ b/drivers/virtio/virtio_pci_legacy.c
@@ -211,23 +211,10 @@ static const struct virtio_config_ops
virtio_pci_config_ops = {
 	.set_vq_affinity = vp_set_vq_affinity,
 };
 
-static void virtio_pci_release_dev(struct device *_d)
-{
-	struct virtio_device *vdev = dev_to_virtio(_d);
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
-	/* As struct device is a kobject, it's not safe to
-	 * free the memory (including the reference counter itself)
-	 * until it's release callback. */
-	kfree(vp_dev);
-}
-
 /* the PCI probing function */
-int virtio_pci_legacy_probe(struct pci_dev *pci_dev,
-			    const struct pci_device_id *id)
+int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
 {
-	struct virtio_pci_device *vp_dev;
-	int err;
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
 
 	/* We only own devices >= 0x1000 and <= 0x103f: leave the rest. */
 	if (pci_dev->device < 0x1000 || pci_dev->device > 0x103f)
@@ -239,41 +226,12 @@ int virtio_pci_legacy_probe(struct pci_dev *pci_dev,
 		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;
-	}
+	if (!vp_dev->ioaddr)
+		return -ENOMEM;
 
 	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
@@ -281,35 +239,18 @@ int virtio_pci_legacy_probe(struct pci_dev *pci_dev,
 	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
 	vp_dev->vdev.id.device = pci_dev->subsystem_device;
 
+	vp_dev->vdev.config = &virtio_pci_config_ops;
+
 	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;
 }
 
-void virtio_pci_legacy_remove(struct pci_dev *pci_dev)
+void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
 {
-	struct virtio_pci_device *vp_dev = pci_get_drvdata(pci_dev);
-
-	unregister_virtio_device(&vp_dev->vdev);
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
 
 	pci_iounmap(pci_dev, vp_dev->ioaddr);
-	pci_release_regions(pci_dev);
-	pci_disable_device(pci_dev);
 }
-- 
MST

From: Rusty Russell <rusty at rustcorp.com.au>

Based on patches by Michael S. Tsirkin <mst at redhat.com>, but I found it
hard to follow so changed to use structures which are more
self-documenting.

Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 include/uapi/linux/virtio_pci.h | 63 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 509d630..a2b2e13 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -99,4 +99,67 @@
 /* Vector value used to disable MSI for queue */
 #define VIRTIO_MSI_NO_VECTOR            0xffff
 
+#ifndef VIRTIO_PCI_NO_MODERN
+
+/* IDs for different capabilities.  Must all exist. */
+
+/* Common configuration */
+#define VIRTIO_PCI_CAP_COMMON_CFG	1
+/* Notifications */
+#define VIRTIO_PCI_CAP_NOTIFY_CFG	2
+/* ISR access */
+#define VIRTIO_PCI_CAP_ISR_CFG		3
+/* Device specific confiuration */
+#define VIRTIO_PCI_CAP_DEVICE_CFG	4
+
+/* This is the PCI capability header: */
+struct virtio_pci_cap {
+	__u8 cap_vndr;		/* Generic PCI field: PCI_CAP_ID_VNDR */
+	__u8 cap_next;		/* Generic PCI field: next ptr. */
+	__u8 cap_len;		/* Generic PCI field: capability length */
+	__u8 cfg_type;		/* Identifies the structure. */
+	__u8 bar;		/* Where to find it. */
+	__u8 padding[3];	/* Pad to full dword. */
+	__le32 offset;		/* Offset within bar. */
+	__le32 length;		/* Length of the structure, in bytes. */
+};
+
+#define VIRTIO_PCI_CAP_BAR_SHIFT	5
+#define VIRTIO_PCI_CAP_BAR_MASK		0x7
+#define VIRTIO_PCI_CAP_TYPE_SHIFT	0
+#define VIRTIO_PCI_CAP_TYPE_MASK	0x7
+
+struct virtio_pci_notify_cap {
+	struct virtio_pci_cap cap;
+	__le32 notify_off_multiplier;	/* Multiplier for queue_notify_off. */
+};
+
+/* Fields in VIRTIO_PCI_CAP_COMMON_CFG: */
+struct virtio_pci_common_cfg {
+	/* About the whole device. */
+	__le32 device_feature_select;	/* read-write */
+	__le32 device_feature;		/* read-only */
+	__le32 guest_feature_select;	/* read-write */
+	__le32 guest_feature;		/* read-write */
+	__le16 msix_config;		/* read-write */
+	__le16 num_queues;		/* read-only */
+	__u8 device_status;		/* read-write */
+	__u8 config_generation;		/* read-only */
+
+	/* About a specific virtqueue. */
+	__le16 queue_select;		/* read-write */
+	__le16 queue_size;		/* read-write, power of 2. */
+	__le16 queue_msix_vector;	/* read-write */
+	__le16 queue_enable;		/* read-write */
+	__le16 queue_notify_off;	/* read-only */
+	__le32 queue_desc_lo;		/* read-write */
+	__le32 queue_desc_hi;		/* read-write */
+	__le32 queue_avail_lo;		/* read-write */
+	__le32 queue_avail_hi;		/* read-write */
+	__le32 queue_used_lo;		/* read-write */
+	__le32 queue_used_hi;		/* read-write */
+};
+
+#endif /* VIRTIO_PCI_NO_MODERN */
+
 #endif
-- 
MST

Lightly tested against qemu.

One thing *not* implemented here is separate mappings
for descriptor/avail/used rings. That's nice to have,
will be done later after we have core support.

Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 drivers/virtio/virtio_pci_common.h |  25 +-
 drivers/virtio/virtio_pci_common.c |  14 +-
 drivers/virtio/virtio_pci_modern.c | 587 +++++++++++++++++++++++++++++++++++++
 drivers/virtio/Makefile            |   2 +-
 4 files changed, 621 insertions(+), 7 deletions(-)
 create mode 100644 drivers/virtio/virtio_pci_modern.c

diff --git a/drivers/virtio/virtio_pci_common.h
b/drivers/virtio/virtio_pci_common.h
index 2b1e70d..610c43f 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -53,12 +53,29 @@ struct virtio_pci_device {
 	struct virtio_device vdev;
 	struct pci_dev *pci_dev;
 
+	/* In legacy mode, these two point to within ->legacy. */
+	/* Where to read and clear interrupt */
+	u8 __iomem *isr;
+
+	/* Modern only fields */
+	/* The IO mapping for the PCI config space (non-legacy mode) */
+	struct virtio_pci_common_cfg __iomem *common;
+	/* Device-specific data (non-legacy mode)  */
+	void __iomem *device;
+
+	/* So we can sanity-check accesses. */
+	size_t device_len;
+
+	/* Capability for when we need to map notifications per-vq. */
+	int notify_map_cap;
+
+	/* Multiply queue_notify_off by this value. (non-legacy mode). */
+	u32 notify_offset_multiplier;
+
+	/* Legacy only field */
 	/* 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;
@@ -129,5 +146,7 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
 
 int virtio_pci_legacy_probe(struct virtio_pci_device *);
 void virtio_pci_legacy_remove(struct virtio_pci_device *);
+int virtio_pci_modern_probe(struct virtio_pci_device *);
+void virtio_pci_modern_remove(struct virtio_pci_device *);
 
 #endif
diff --git a/drivers/virtio/virtio_pci_common.c
b/drivers/virtio/virtio_pci_common.c
index 457cbe2..8ae34a3 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -505,7 +505,9 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	if (rc)
 		goto err_request_regions;
 
-	rc = virtio_pci_legacy_probe(vp_dev);
+	rc = virtio_pci_modern_probe(vp_dev);
+	if (rc == -ENODEV)
+		rc = virtio_pci_legacy_probe(vp_dev);
 	if (rc)
 		goto err_probe;
 
@@ -518,7 +520,10 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	return 0;
 
 err_register:
-	virtio_pci_legacy_remove(vp_dev);
+	if (vp_dev->ioaddr)
+	     virtio_pci_legacy_remove(vp_dev);
+	else
+	     virtio_pci_modern_remove(vp_dev);
 err_probe:
 	pci_release_regions(pci_dev);
 err_request_regions:
@@ -534,7 +539,10 @@ static void virtio_pci_remove(struct pci_dev *pci_dev)
 
 	unregister_virtio_device(&vp_dev->vdev);
 
-	virtio_pci_legacy_remove(pci_dev);
+	if (vp_dev->ioaddr)
+		virtio_pci_legacy_remove(vp_dev);
+	else
+		virtio_pci_modern_remove(vp_dev);
 
 	pci_release_regions(pci_dev);
 	pci_disable_device(pci_dev);
diff --git a/drivers/virtio/virtio_pci_modern.c
b/drivers/virtio/virtio_pci_modern.c
new file mode 100644
index 0000000..a3d8101
--- /dev/null
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -0,0 +1,587 @@
+/*
+ * Virtio PCI driver - modern (virtio 1.0) device support
+ *
+ * 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
+ * Copyright Red Hat, Inc. 2014
+ *
+ * Authors:
+ *  Anthony Liguori  <aliguori at us.ibm.com>
+ *  Rusty Russell <rusty at rustcorp.com.au>
+ *  Michael S. Tsirkin <mst at redhat.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.
+ *
+ */
+
+#define VIRTIO_PCI_NO_LEGACY
+#include "virtio_pci_common.h"
+
+static void __iomem *map_capability(struct pci_dev *dev, int off,
+				    size_t minlen,
+				    u32 align,
+				    u32 start, u32 size,
+				    size_t *len)
+{
+	u8 bar;
+	u32 offset, length;
+	void __iomem *p;
+
+	pci_read_config_byte(dev, off + offsetof(struct virtio_pci_cap,
+						 bar),
+			     &bar);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, offset),
+			     &offset);
+	pci_read_config_dword(dev, off + offsetof(struct virtio_pci_cap, length),
+			      &length);
+
+	if (length <= start) {
+		dev_err(&dev->dev,
+			"virtio_pci: bad capability len %u (>%u expected)\n",
+			length, start);
+		return NULL;
+	}
+
+	if (length - start < minlen) {
+		dev_err(&dev->dev,
+			"virtio_pci: bad capability len %u (>=%zu expected)\n",
+			length, minlen);
+		return NULL;
+	}
+
+	length -= start;
+
+	if (start + offset < offset) {
+		dev_err(&dev->dev,
+			"virtio_pci: map wrap-around %u+%u\n",
+			start, offset);
+		return NULL;
+	}
+
+	offset += start;
+
+	if (offset & (align - 1)) {
+		dev_err(&dev->dev,
+			"virtio_pci: offset %u not aligned to %u\n",
+			offset, align);
+		return NULL;
+	}
+
+	if (length > size)
+		length = size;
+
+	if (len)
+		*len = length;
+
+	if (minlen + offset < minlen ||
+	    minlen + offset > pci_resource_len(dev, bar)) {
+		dev_err(&dev->dev,
+			"virtio_pci: map virtio %zu@%u "
+			"out of range on bar %i length %lu\n",
+			minlen, offset,
+			bar, (unsigned long)pci_resource_len(dev, bar));
+		return NULL;
+	}
+
+	p = pci_iomap_range(dev, bar, offset, length);
+	if (!p)
+		dev_err(&dev->dev,
+			"virtio_pci: unable to map virtio %u@%u on bar %i\n",
+			length, offset, bar);
+	return p;
+}
+
+static void iowrite64_twopart(u64 val, __le32 __iomem *lo, __le32 __iomem *hi)
+{
+	iowrite32((u32)val, lo);
+	iowrite32(val >> 32, hi);
+}
+
+/* virtio config->get_features() implementation */
+static u64 vp_get_features(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	u64 features;
+
+	iowrite32(0, &vp_dev->common->device_feature_select);
+	features = ioread32(&vp_dev->common->device_feature);
+	iowrite32(1, &vp_dev->common->device_feature_select);
+	features |= ((u64)ioread32(&vp_dev->common->device_feature) <<
32);
+
+	return 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);
+
+	if (!__virtio_test_bit(vdev, VIRTIO_F_VERSION_1)) {
+		dev_err(&vdev->dev, "virtio: device uses modern interface "
+			"but does not have VIRTIO_F_VERSION_1\n");
+		return -EINVAL;
+	}
+
+	iowrite32(0, &vp_dev->common->guest_feature_select);
+	iowrite32((u32)vdev->features, &vp_dev->common->guest_feature);
+	iowrite32(1, &vp_dev->common->guest_feature_select);
+	iowrite32(vdev->features >> 32,
&vp_dev->common->guest_feature);
+
+	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);
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	BUG_ON(offset + len > vp_dev->device_len);
+
+	switch (len) {
+	case 1:
+		b = ioread8(vp_dev->device + offset);
+		memcpy(buf, &b, sizeof b);
+		break;
+	case 2:
+		w = cpu_to_le16(ioread16(vp_dev->device + offset));
+		memcpy(buf, &w, sizeof w);
+		break;
+	case 4:
+		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		memcpy(buf, &l, sizeof l);
+		break;
+	case 8:
+		l = cpu_to_le32(ioread32(vp_dev->device + offset));
+		memcpy(buf, &l, sizeof l);
+		l = cpu_to_le32(ioread32(vp_dev->device + offset + sizeof l));
+		memcpy(buf + sizeof l, &l, sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+/* 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);
+	u8 b;
+	__le16 w;
+	__le32 l;
+
+	BUG_ON(offset + len > vp_dev->device_len);
+
+	switch (len) {
+	case 1:
+		memcpy(&b, buf, sizeof b);
+		iowrite8(b, vp_dev->device + offset);
+		break;
+	case 2:
+		memcpy(&w, buf, sizeof w);
+		iowrite16(le16_to_cpu(w), vp_dev->device + offset);
+		break;
+	case 4:
+		memcpy(&l, buf, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		break;
+	case 8:
+		memcpy(&l, buf, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset);
+		memcpy(&l, buf + sizeof l, sizeof l);
+		iowrite32(le32_to_cpu(l), vp_dev->device + offset + sizeof l);
+		break;
+	default:
+		BUG();
+	}
+}
+
+static u32 vp_generation(struct virtio_device *vdev)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	return ioread8(&vp_dev->common->config_generation);
+}
+
+/* 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->common->device_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->common->device_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->common->device_status);
+	/* Flush out the status write, and flush in device writes,
+	 * including MSI-X interrupts, if any. */
+	ioread8(&vp_dev->common->device_status);
+	/* Flush pending VQ/configuration callbacks. */
+	vp_synchronize_vectors(vdev);
+}
+
+static u16 vp_config_vector(struct virtio_pci_device *vp_dev, u16 vector)
+{
+	/* Setup the vector used for configuration events */
+	iowrite16(vector, &vp_dev->common->msix_config);
+	/* Verify we had enough resources to assign the vector */
+	/* Will also flush the write out to device */
+	return ioread16(&vp_dev->common->msix_config);
+}
+
+static size_t vring_pci_size(u16 num)
+{
+	/* We only need a cacheline separation. */
+	return PAGE_ALIGN(vring_size(num, SMP_CACHE_BYTES));
+}
+
+static void *alloc_virtqueue_pages(int *num)
+{
+	void *pages;
+
+	/* TODO: allocate each queue chunk individually */
+	for (; *num && vring_pci_size(*num) > PAGE_SIZE; *num /= 2) {
+		pages = alloc_pages_exact(vring_pci_size(*num),
+					  GFP_KERNEL|__GFP_ZERO|__GFP_NOWARN);
+		if (pages)
+			return pages;
+	}
+
+	if (!*num)
+		return NULL;
+
+	/* Try to get a single page. You are my only hope! */
+	return alloc_pages_exact(vring_pci_size(*num), GFP_KERNEL|__GFP_ZERO);
+}
+
+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 virtio_pci_common_cfg __iomem *cfg = vp_dev->common;
+	struct virtqueue *vq;
+	u16 num, off;
+	int err;
+
+	if (index >= ioread16(&cfg->num_queues))
+		return ERR_PTR(-ENOENT);
+
+	/* Select the queue we're interested in */
+	iowrite16(index, &cfg->queue_select);
+
+	/* Check if queue is either not available or already active. */
+	num = ioread16(&cfg->queue_size);
+	if (!num || ioread8(&cfg->queue_enable))
+		return ERR_PTR(-ENOENT);
+
+	if (num & (num - 1)) {
+		dev_warn(&vp_dev->pci_dev->dev, "bad queue size %u",
num);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* get offset of notification word for this vq */
+	off = ioread16(&cfg->queue_notify_off);
+
+	info->num = num;
+	info->msix_vector = msix_vec;
+
+	info->queue = alloc_virtqueue_pages(&info->num);
+	if (info->queue == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	/* create the vring */
+	vq = vring_new_virtqueue(index, info->num,
+				 SMP_CACHE_BYTES, &vp_dev->vdev,
+				 true, info->queue, vp_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto err_new_queue;
+	}
+
+	/* activate the queue */
+	iowrite16(num, &cfg->queue_size);
+	iowrite64_twopart(virt_to_phys(info->queue),
+			  &cfg->queue_desc_lo, &cfg->queue_desc_hi);
+	iowrite64_twopart(virt_to_phys(virtqueue_get_avail(vq)),
+			  &cfg->queue_avail_lo, &cfg->queue_avail_hi);
+	iowrite64_twopart(virt_to_phys(virtqueue_get_used(vq)),
+			  &cfg->queue_used_lo, &cfg->queue_used_hi);
+
+	vq->priv = (void __force *)map_capability(vp_dev->pci_dev,
+				  vp_dev->notify_map_cap, 2, 2,
+				  off * vp_dev->notify_offset_multiplier, 2,
+				  NULL);
+
+	if (!vq->priv) {
+		err = -ENOMEM;
+		goto err_map_notify;
+	}
+
+	if (msix_vec != VIRTIO_MSI_NO_VECTOR) {
+		iowrite16(msix_vec, &cfg->queue_msix_vector);
+		msix_vec = ioread16(&cfg->queue_msix_vector);
+		if (msix_vec == VIRTIO_MSI_NO_VECTOR) {
+			err = -EBUSY;
+			goto err_assign_vector;
+		}
+	}
+
+	return vq;
+
+err_assign_vector:
+	pci_iounmap(vp_dev->pci_dev, (void __iomem __force *)vq->priv);
+err_map_notify:
+	vring_del_virtqueue(vq);
+err_new_queue:
+	free_pages_exact(info->queue, vring_pci_size(info->num));
+	return ERR_PTR(err);
+}
+
+static int vp_modern_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+			      struct virtqueue *vqs[],
+			      vq_callback_t *callbacks[],
+			      const char *names[])
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct virtqueue *vq;
+	int rc = vp_find_vqs(vdev, nvqs, vqs, callbacks, names);
+
+	if (rc)
+		return rc;
+
+	/* Select and activate all queues. Has to be done last: once we do
+	 * this, there's no way to go back except reset.
+	 */
+	list_for_each_entry(vq, &vdev->vqs, list) {
+		iowrite16(vq->index, &vp_dev->common->queue_select);
+		iowrite8(1, &vp_dev->common->queue_enable);
+	}
+
+	return 0;
+}
+
+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);
+
+	iowrite16(vq->index, &vp_dev->common->queue_select);
+
+	if (vp_dev->msix_enabled) {
+		iowrite16(VIRTIO_MSI_NO_VECTOR,
+			  &vp_dev->common->queue_msix_vector);
+		/* Flush the write out to device */
+		ioread16(&vp_dev->common->queue_msix_vector);
+	}
+
+	pci_iounmap(vp_dev->pci_dev, (void __force __iomem *)vq->priv);
+
+	vring_del_virtqueue(vq);
+
+	free_pages_exact(info->queue, vring_pci_size(info->num));
+}
+
+static const struct virtio_config_ops virtio_pci_config_ops = {
+	.get		= vp_get,
+	.set		= vp_set,
+	.generation	= vp_generation,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vqs	= vp_modern_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,
+};
+
+/**
+ * virtio_pci_find_capability - walk capabilities to find device info.
+ * @dev: the pci device
+ * @cfg_type: the VIRTIO_PCI_CAP_* value we seek
+ * @ioresource_types: IORESOURCE_MEM and/or IORESOURCE_IO.
+ *
+ * Returns offset of the capability, or 0.
+ */
+static inline int virtio_pci_find_capability(struct pci_dev *dev, u8 cfg_type,
+					     u32 ioresource_types)
+{
+	int pos;
+
+	for (pos = pci_find_capability(dev, PCI_CAP_ID_VNDR);
+	     pos > 0;
+	     pos = pci_find_next_capability(dev, pos, PCI_CAP_ID_VNDR)) {
+		u8 type, bar;
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 cfg_type),
+				     &type);
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 bar),
+				     &bar);
+
+		/* Ignore structures with reserved BAR values */
+		if (bar > 0x5)
+			continue;
+
+		if (type == cfg_type) {
+			if (pci_resource_len(dev, bar) &&
+			    pci_resource_flags(dev, bar) & ioresource_types)
+				return pos;
+		}
+	}
+	return 0;
+}
+
+static void virtio_pci_release_dev(struct device *_d)
+{
+	struct virtio_device *vdev = dev_to_virtio(_d);
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+
+	kfree(vp_dev);
+}
+
+/* TODO: validate the ABI statically. */
+static inline void check_offsets(void)
+{
+}
+
+/* the PCI probing function */
+int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev)
+{
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	int err, common, isr, notify, device;
+	u32 notify_length;
+
+	check_offsets();
+
+	/* We only own devices >= 0x1000 and <= 0x107f: leave the rest. */
+	if (pci_dev->device < 0x1000 || pci_dev->device > 0x107f)
+		return -ENODEV;
+
+	if (pci_dev->device < 0x1040) {
+		/* Transitional devices: use the PCI subsystem device id as
+		 * virtio device id, same as legacy driver always did.
+		 */
+		vp_dev->vdev.id.device = pci_dev->subsystem_device;
+	} else {
+		/* Modern devices: simply use PCI device id, but start from 0x1040. */
+		vp_dev->vdev.id.device = pci_dev->device - 0x1040;
+	}
+	vp_dev->vdev.id.vendor = pci_dev->subsystem_vendor;
+
+	if (virtio_device_is_legacy_only(vp_dev->vdev.id))
+		return -ENODEV;
+
+	/* check for a common config: if not, use legacy mode (bar 0). */
+	common = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_COMMON_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM);
+	if (!common) {
+		dev_info(&pci_dev->dev,
+			 "virtio_pci: leaving for legacy driver\n");
+		return -ENODEV;
+	}
+
+	/* If common is there, these should be too... */
+	isr = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_ISR_CFG,
+					 IORESOURCE_IO | IORESOURCE_MEM);
+	notify = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_NOTIFY_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM);
+	if (!isr || !notify) {
+		dev_err(&pci_dev->dev,
+			"virtio_pci: missing capabilities %i/%i/%i\n",
+			common, isr, notify);
+		return -EINVAL;
+	}
+
+	/* Device capability is only mandatory for devices that have
+	 * device-specific configuration.
+	 */
+	device = virtio_pci_find_capability(pci_dev, VIRTIO_PCI_CAP_DEVICE_CFG,
+					    IORESOURCE_IO | IORESOURCE_MEM);
+
+	err = -EINVAL;
+	vp_dev->common = map_capability(pci_dev, common,
+					sizeof(struct virtio_pci_common_cfg), 4,
+					0, sizeof(struct virtio_pci_common_cfg),
+					NULL);
+	if (!vp_dev->common)
+		goto err_map_common;
+	vp_dev->isr = map_capability(pci_dev, isr, sizeof(u8), 1,
+				     0, 1,
+				     NULL);
+	if (!vp_dev->isr)
+		goto err_map_isr;
+
+	/* Read notify_off_multiplier from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						notify_off_multiplier),
+			      &vp_dev->notify_offset_multiplier);
+	/* Read notify length from config space. */
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						cap.length),
+			      &notify_length);
+
+	vp_dev->notify_map_cap = notify;
+
+	/* Again, we don't know how much we should map, but PAGE_SIZE
+	 * is more than enough for all existing devices.
+	 */
+	if (device) {
+		vp_dev->device = map_capability(pci_dev, device, 0, 4,
+						0, PAGE_SIZE,
+						&vp_dev->device_len);
+		if (!vp_dev->device)
+			goto err_map_device;
+	}
+
+	vp_dev->vdev.config = &virtio_pci_config_ops;
+
+	vp_dev->config_vector = vp_config_vector;
+	vp_dev->setup_vq = setup_vq;
+	vp_dev->del_vq = del_vq;
+
+	return 0;
+
+err_map_device:
+	pci_iounmap(pci_dev, vp_dev->isr);
+err_map_isr:
+	pci_iounmap(pci_dev, vp_dev->common);
+err_map_common:
+	return err;
+}
+
+void virtio_pci_modern_remove(struct virtio_pci_device *vp_dev)
+{
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
+
+	if (vp_dev->device)
+		pci_iounmap(pci_dev, vp_dev->device);
+	pci_iounmap(pci_dev, vp_dev->isr);
+	pci_iounmap(pci_dev, vp_dev->common);
+}
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index bf5104b..bd230d1 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
 obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
-virtio_pci-y := virtio_pci_legacy.o virtio_pci_common.o
+virtio_pci-y := virtio_pci_modern.o virtio_pci_legacy.o virtio_pci_common.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
-- 
MST

From: Rusty Russell <rusty at rustcorp.com.au>

QEMU wants it, so why not?  Trust, but verify.

Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 include/uapi/linux/virtio_pci.h    | 36 +++++++++++++++++++----
 drivers/virtio/virtio_pci_modern.c | 60 +++++++++++++++++++++++++++++++++++++-
 2 files changed, 90 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index a2b2e13..3b7e4d2 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -124,11 +124,6 @@ struct virtio_pci_cap {
 	__le32 length;		/* Length of the structure, in bytes. */
 };
 
-#define VIRTIO_PCI_CAP_BAR_SHIFT	5
-#define VIRTIO_PCI_CAP_BAR_MASK		0x7
-#define VIRTIO_PCI_CAP_TYPE_SHIFT	0
-#define VIRTIO_PCI_CAP_TYPE_MASK	0x7
-
 struct virtio_pci_notify_cap {
 	struct virtio_pci_cap cap;
 	__le32 notify_off_multiplier;	/* Multiplier for queue_notify_off. */
@@ -160,6 +155,37 @@ struct virtio_pci_common_cfg {
 	__le32 queue_used_hi;		/* read-write */
 };
 
+/* Macro versions of offsets for the Old Timers! */
+#define VIRTIO_PCI_CAP_VNDR		0
+#define VIRTIO_PCI_CAP_NEXT		1
+#define VIRTIO_PCI_CAP_LEN		2
+#define VIRTIO_PCI_CAP_CFG_TYPE		3
+#define VIRTIO_PCI_CAP_BAR		4
+#define VIRTIO_PCI_CAP_OFFSET		8
+#define VIRTIO_PCI_CAP_LENGTH		12
+
+#define VIRTIO_PCI_NOTIFY_CAP_MULT	16
+
+#define VIRTIO_PCI_COMMON_DFSELECT	0
+#define VIRTIO_PCI_COMMON_DF		4
+#define VIRTIO_PCI_COMMON_GFSELECT	8
+#define VIRTIO_PCI_COMMON_GF		12
+#define VIRTIO_PCI_COMMON_MSIX		16
+#define VIRTIO_PCI_COMMON_NUMQ		18
+#define VIRTIO_PCI_COMMON_STATUS	20
+#define VIRTIO_PCI_COMMON_CFGGENERATION	21
+#define VIRTIO_PCI_COMMON_Q_SELECT	22
+#define VIRTIO_PCI_COMMON_Q_SIZE	24
+#define VIRTIO_PCI_COMMON_Q_MSIX	26
+#define VIRTIO_PCI_COMMON_Q_ENABLE	28
+#define VIRTIO_PCI_COMMON_Q_NOFF	30
+#define VIRTIO_PCI_COMMON_Q_DESCLO	32
+#define VIRTIO_PCI_COMMON_Q_DESCHI	36
+#define VIRTIO_PCI_COMMON_Q_AVAILLO	40
+#define VIRTIO_PCI_COMMON_Q_AVAILHI	44
+#define VIRTIO_PCI_COMMON_Q_USEDLO	48
+#define VIRTIO_PCI_COMMON_Q_USEDHI	52
+
 #endif /* VIRTIO_PCI_NO_MODERN */
 
 #endif
diff --git a/drivers/virtio/virtio_pci_modern.c
b/drivers/virtio/virtio_pci_modern.c
index a3d8101..b2e707ad 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -464,9 +464,67 @@ static void virtio_pci_release_dev(struct device *_d)
 	kfree(vp_dev);
 }
 
-/* TODO: validate the ABI statically. */
+/* This is part of the ABI.  Don't screw with it. */
 static inline void check_offsets(void)
 {
+	/* Note: disk space was harmed in compilation of this function. */
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_VNDR !+		     offsetof(struct virtio_pci_cap,
cap_vndr));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_NEXT !+		     offsetof(struct virtio_pci_cap,
cap_next));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LEN !+		     offsetof(struct virtio_pci_cap,
cap_len));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_CFG_TYPE !+		     offsetof(struct virtio_pci_cap,
cfg_type));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_BAR !+		     offsetof(struct virtio_pci_cap,
bar));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_OFFSET !+		     offsetof(struct virtio_pci_cap,
offset));
+	BUILD_BUG_ON(VIRTIO_PCI_CAP_LENGTH !+		     offsetof(struct virtio_pci_cap,
length));
+	BUILD_BUG_ON(VIRTIO_PCI_NOTIFY_CAP_MULT !+		     offsetof(struct
virtio_pci_notify_cap,
+			      notify_off_multiplier));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DFSELECT !+		     offsetof(struct
virtio_pci_common_cfg,
+			      device_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_DF !+		     offsetof(struct
virtio_pci_common_cfg, device_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GFSELECT !+		     offsetof(struct
virtio_pci_common_cfg,
+			      guest_feature_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_GF !+		     offsetof(struct
virtio_pci_common_cfg, guest_feature));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_MSIX !+		     offsetof(struct
virtio_pci_common_cfg, msix_config));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_NUMQ !+		     offsetof(struct
virtio_pci_common_cfg, num_queues));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_STATUS !+		     offsetof(struct
virtio_pci_common_cfg, device_status));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_CFGGENERATION !+		     offsetof(struct
virtio_pci_common_cfg, config_generation));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SELECT !+		     offsetof(struct
virtio_pci_common_cfg, queue_select));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_SIZE !+		     offsetof(struct
virtio_pci_common_cfg, queue_size));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_MSIX !+		     offsetof(struct
virtio_pci_common_cfg, queue_msix_vector));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_ENABLE !+		     offsetof(struct
virtio_pci_common_cfg, queue_enable));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_NOFF !+		     offsetof(struct
virtio_pci_common_cfg, queue_notify_off));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCLO !+		     offsetof(struct
virtio_pci_common_cfg, queue_desc_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_DESCHI !+		     offsetof(struct
virtio_pci_common_cfg, queue_desc_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILLO !+		     offsetof(struct
virtio_pci_common_cfg, queue_avail_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_AVAILHI !+		     offsetof(struct
virtio_pci_common_cfg, queue_avail_hi));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDLO !+		     offsetof(struct
virtio_pci_common_cfg, queue_used_lo));
+	BUILD_BUG_ON(VIRTIO_PCI_COMMON_Q_USEDHI !+		     offsetof(struct
virtio_pci_common_cfg, queue_used_hi));
 }
 
 /* the PCI probing function */
-- 
MST

We don't know the # of VQs that drivers are going to use so it's hard to
predict how much memory we'll need to map. However, the relevant
capability does give us an upper limit.
If that's below a page, we can reduce the number of required
mappings by mapping it all once ahead of the time.

Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 drivers/virtio/virtio_pci_common.h |  3 ++
 drivers/virtio/virtio_pci_modern.c | 57 ++++++++++++++++++++++++++++++++------
 2 files changed, 52 insertions(+), 8 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.h
b/drivers/virtio/virtio_pci_common.h
index 610c43f..d391805 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -62,8 +62,11 @@ struct virtio_pci_device {
 	struct virtio_pci_common_cfg __iomem *common;
 	/* Device-specific data (non-legacy mode)  */
 	void __iomem *device;
+	/* Base of vq notifications (non-legacy mode). */
+	void __iomem *notify_base;
 
 	/* So we can sanity-check accesses. */
+	size_t notify_len;
 	size_t device_len;
 
 	/* Capability for when we need to map notifications per-vq. */
diff --git a/drivers/virtio/virtio_pci_modern.c
b/drivers/virtio/virtio_pci_modern.c
index b2e707ad..0e54cc8 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -330,10 +330,26 @@ static struct virtqueue *setup_vq(struct virtio_pci_device
*vp_dev,
 	iowrite64_twopart(virt_to_phys(virtqueue_get_used(vq)),
 			  &cfg->queue_used_lo, &cfg->queue_used_hi);
 
-	vq->priv = (void __force *)map_capability(vp_dev->pci_dev,
-				  vp_dev->notify_map_cap, 2, 2,
-				  off * vp_dev->notify_offset_multiplier, 2,
-				  NULL);
+	if (vp_dev->notify_base) {
+		/* offset should not wrap */
+		if ((u64)off * vp_dev->notify_offset_multiplier + 2
+		    > vp_dev->notify_len) {
+			dev_warn(&vp_dev->pci_dev->dev,
+				 "bad notification offset %u (x %u) "
+				 "for queue %u > %zd",
+				 off, vp_dev->notify_offset_multiplier,
+				 index, vp_dev->notify_len);
+			err = -EINVAL;
+			goto err_map_notify;
+		}
+		vq->priv = (void __force *)vp_dev->notify_base +
+			off * vp_dev->notify_offset_multiplier;
+	} else {
+		vq->priv = (void __force *)map_capability(vp_dev->pci_dev,
+					  vp_dev->notify_map_cap, 2, 2,
+					  off * vp_dev->notify_offset_multiplier, 2,
+					  NULL);
+	}
 
 	if (!vq->priv) {
 		err = -ENOMEM;
@@ -352,7 +368,8 @@ static struct virtqueue *setup_vq(struct virtio_pci_device
*vp_dev,
 	return vq;
 
 err_assign_vector:
-	pci_iounmap(vp_dev->pci_dev, (void __iomem __force *)vq->priv);
+	if (!vp_dev->notify_base)
+		pci_iounmap(vp_dev->pci_dev, (void __iomem __force *)vq->priv);
 err_map_notify:
 	vring_del_virtqueue(vq);
 err_new_queue:
@@ -397,7 +414,8 @@ static void del_vq(struct virtio_pci_vq_info *info)
 		ioread16(&vp_dev->common->queue_msix_vector);
 	}
 
-	pci_iounmap(vp_dev->pci_dev, (void __force __iomem *)vq->priv);
+	if (!vp_dev->notify_base)
+		pci_iounmap(vp_dev->pci_dev, (void __force __iomem *)vq->priv);
 
 	vring_del_virtqueue(vq);
 
@@ -533,6 +551,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device
*vp_dev)
 	struct pci_dev *pci_dev = vp_dev->pci_dev;
 	int err, common, isr, notify, device;
 	u32 notify_length;
+	u32 notify_offset;
 
 	check_offsets();
 
@@ -599,13 +618,30 @@ int virtio_pci_modern_probe(struct virtio_pci_device
*vp_dev)
 			      notify + offsetof(struct virtio_pci_notify_cap,
 						notify_off_multiplier),
 			      &vp_dev->notify_offset_multiplier);
-	/* Read notify length from config space. */
+	/* Read notify length and offset from config space. */
 	pci_read_config_dword(pci_dev,
 			      notify + offsetof(struct virtio_pci_notify_cap,
 						cap.length),
 			      &notify_length);
 
-	vp_dev->notify_map_cap = notify;
+	pci_read_config_dword(pci_dev,
+			      notify + offsetof(struct virtio_pci_notify_cap,
+						cap.length),
+			      &notify_offset);
+
+	/* We don't know how many VQs we'll map, ahead of the time.
+	 * If notify length is small, map it all now.
+	 * Otherwise, map each VQ individually later.
+	 */
+	if ((u64)notify_length + (notify_offset % PAGE_SIZE) <= PAGE_SIZE) {
+		vp_dev->notify_base = map_capability(pci_dev, notify, 2, 2,
+						     0, notify_length,
+						     &vp_dev->notify_len);
+		if (!vp_dev->notify_base)
+			goto err_map_notify;
+	} else {
+		vp_dev->notify_map_cap = notify;
+	}
 
 	/* Again, we don't know how much we should map, but PAGE_SIZE
 	 * is more than enough for all existing devices.
@@ -627,6 +663,9 @@ int virtio_pci_modern_probe(struct virtio_pci_device
*vp_dev)
 	return 0;
 
 err_map_device:
+	if (vp_dev->notify_base)
+		pci_iounmap(pci_dev, vp_dev->notify_base);
+err_map_notify:
 	pci_iounmap(pci_dev, vp_dev->isr);
 err_map_isr:
 	pci_iounmap(pci_dev, vp_dev->common);
@@ -640,6 +679,8 @@ void virtio_pci_modern_remove(struct virtio_pci_device
*vp_dev)
 
 	if (vp_dev->device)
 		pci_iounmap(pci_dev, vp_dev->device);
+	if (vp_dev->notify_base)
+		pci_iounmap(pci_dev, vp_dev->notify_base);
 	pci_iounmap(pci_dev, vp_dev->isr);
 	pci_iounmap(pci_dev, vp_dev->common);
 }
-- 
MST

Virtio 1.0 spec lists device config as optional.
Set get/set callbacks to NULL. Drivers can check that
and fail gracefully.

Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c
b/drivers/virtio/virtio_pci_modern.c
index 0e54cc8..68ebc20 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -422,6 +422,21 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	free_pages_exact(info->queue, vring_pci_size(info->num));
 }
 
+static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
+	.get		= NULL,
+	.set		= NULL,
+	.generation	= vp_generation,
+	.get_status	= vp_get_status,
+	.set_status	= vp_set_status,
+	.reset		= vp_reset,
+	.find_vqs	= vp_modern_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 const struct virtio_config_ops virtio_pci_config_ops = {
 	.get		= vp_get,
 	.set		= vp_set,
@@ -652,9 +667,11 @@ int virtio_pci_modern_probe(struct virtio_pci_device
*vp_dev)
 						&vp_dev->device_len);
 		if (!vp_dev->device)
 			goto err_map_device;
-	}
 
-	vp_dev->vdev.config = &virtio_pci_config_ops;
+		vp_dev->vdev.config = &virtio_pci_config_ops;
+	} else {
+		vp_dev->vdev.config = &virtio_pci_config_nodev_ops;
+	}
 
 	vp_dev->config_vector = vp_config_vector;
 	vp_dev->setup_vq = setup_vq;
-- 
MST

Useful for testing device virtio 1 compatibility.
Based on patch by Rusty - couldn't resist putting
that flying car joke in there!

Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 drivers/virtio/virtio_pci_common.h | 10 ++++++++++
 drivers/virtio/Kconfig             | 19 +++++++++++++++++++
 drivers/virtio/Makefile            |  3 ++-
 3 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_pci_common.h
b/drivers/virtio/virtio_pci_common.h
index d391805..28ee4e5 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -147,8 +147,18 @@ const char *vp_bus_name(struct virtio_device *vdev);
  */
 int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
 
+#if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
 int virtio_pci_legacy_probe(struct virtio_pci_device *);
 void virtio_pci_legacy_remove(struct virtio_pci_device *);
+#else
+static inline int virtio_pci_legacy_probe(struct virtio_pci_device *vp_dev)
+{
+	return -ENODEV;
+}
+static inline void virtio_pci_legacy_remove(struct virtio_pci_device *vp_dev)
+{
+}
+#endif
 int virtio_pci_modern_probe(struct virtio_pci_device *);
 void virtio_pci_modern_remove(struct virtio_pci_device *);
 
diff --git a/drivers/virtio/Kconfig b/drivers/virtio/Kconfig
index 083fb45..b546da5 100644
--- a/drivers/virtio/Kconfig
+++ b/drivers/virtio/Kconfig
@@ -19,6 +19,25 @@ config VIRTIO_PCI
 
 	  If unsure, say M.
 
+config VIRTIO_PCI_LEGACY
+	bool "Support for legacy virtio draft 0.9.X and older devices"
+	default y
+	depends on VIRTIO_PCI
+	---help---
+          Virtio PCI Card 0.9.X Draft (circa 2014) and older device support.
+
+	  This option enables building a transitional driver, supporting
+	  both devices conforming to Virtio 1 specification, and legacy devices.
+	  If disabled, you get a slightly smaller, non-transitional driver,
+	  with no legacy compatibility.
+
+          So look out into your driveway.  Do you have a flying car?  If
+          so, you can happily disable this option and virtio will not
+          break.  Otherwise, leave it set.  Unless you're testing what
+          life will be like in The Future.
+
+	  If unsure, say Y.
+
 config VIRTIO_BALLOON
 	tristate "Virtio balloon driver"
 	depends on VIRTIO
diff --git a/drivers/virtio/Makefile b/drivers/virtio/Makefile
index bd230d1..d85565b 100644
--- a/drivers/virtio/Makefile
+++ b/drivers/virtio/Makefile
@@ -1,5 +1,6 @@
 obj-$(CONFIG_VIRTIO) += virtio.o virtio_ring.o
 obj-$(CONFIG_VIRTIO_MMIO) += virtio_mmio.o
 obj-$(CONFIG_VIRTIO_PCI) += virtio_pci.o
-virtio_pci-y := virtio_pci_modern.o virtio_pci_legacy.o virtio_pci_common.o
+virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
+virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
-- 
MST

If set, try legacy interface first, modern one if that fails.  Useful to
work around device/driver bugs, and for compatibility testing.

Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Signed-off-by: Rusty Russell <rusty at rustcorp.com.au>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 drivers/virtio/virtio_pci_common.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/virtio/virtio_pci_common.c
b/drivers/virtio/virtio_pci_common.c
index 8ae34a3..e894eb2 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -19,6 +19,14 @@
 
 #include "virtio_pci_common.h"
 
+static bool force_legacy = false;
+
+#if IS_ENABLED(CONFIG_VIRTIO_PCI_LEGACY)
+module_param(force_legacy, bool, 0444);
+MODULE_PARM_DESC(force_legacy,
+		 "Force legacy mode for transitional virtio 1 devices");
+#endif
+
 /* wait for pending irq handlers */
 void vp_synchronize_vectors(struct virtio_device *vdev)
 {
@@ -505,11 +513,20 @@ static int virtio_pci_probe(struct pci_dev *pci_dev,
 	if (rc)
 		goto err_request_regions;
 
-	rc = virtio_pci_modern_probe(vp_dev);
-	if (rc == -ENODEV)
+	if (force_legacy) {
 		rc = virtio_pci_legacy_probe(vp_dev);
-	if (rc)
-		goto err_probe;
+		/* Also try modern mode if we can't map BAR0 (no IO space). */
+		if (rc == -ENODEV || rc == -ENOMEM)
+			rc = virtio_pci_modern_probe(vp_dev);
+		if (rc)
+			goto err_probe;
+	} else {
+		rc = virtio_pci_modern_probe(vp_dev);
+		if (rc == -ENODEV)
+			rc = virtio_pci_legacy_probe(vp_dev);
+		if (rc)
+			goto err_probe;
+	}
 
 	pci_set_master(pci_dev);
 
-- 
MST

release function in modern driver is unused:
it's a left-over from when each driver had
to have its own release.

Signed-off-by: Michael S. Tsirkin <mst at redhat.com>
Tested-by: Gerd Hoffmann <kraxel at redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/virtio/virtio_pci_modern.c
b/drivers/virtio/virtio_pci_modern.c
index 68ebc20..f16e462 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -489,14 +489,6 @@ static inline int virtio_pci_find_capability(struct pci_dev
*dev, u8 cfg_type,
 	return 0;
 }
 
-static void virtio_pci_release_dev(struct device *_d)
-{
-	struct virtio_device *vdev = dev_to_virtio(_d);
-	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
-
-	kfree(vp_dev);
-}
-
 /* This is part of the ABI.  Don't screw with it. */
 static inline void check_offsets(void)
 {
-- 
MST