[PATCH v2 04/20] virtio: Implement get_shm_region for PCI transport

[Vivek Goyal <vgoyal@redhat.com>]

From: Sebastien Boeuf <sebastien.boeuf@intel.com>

On PCI the shm regions are found using capability entries;
find a region by searching for the capability.

Signed-off-by: Sebastien Boeuf <sebastien.boeuf@intel.com>
Signed-off-by: Dr. David Alan Gilbert <dgilbert@redhat.com>
Signed-off-by: kbuild test robot <lkp@intel.com>
Cc: kvm@vger.kernel.org
Cc: "Michael S. Tsirkin" <mst@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c | 96 ++++++++++++++++++++++++++++++
 include/uapi/linux/virtio_pci.h    | 11 +++-
 2 files changed, 106 insertions(+), 1 deletion(-)

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index db93cedd262f..3fc0cd848fe9 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -444,6 +444,100 @@ static void del_vq(struct virtio_pci_vq_info *info)
 	vring_del_virtqueue(vq);
 }
 
+static int virtio_pci_find_shm_cap(struct pci_dev *dev, u8 required_id,
+				   u8 *bar, u64 *offset, u64 *len)
+{
+	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, cap_len, id;
+		u32 tmp32;
+		u64 res_offset, res_length;
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 cfg_type), &type);
+		if (type != VIRTIO_PCI_CAP_SHARED_MEMORY_CFG)
+			continue;
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 cap_len), &cap_len);
+		if (cap_len != sizeof(struct virtio_pci_cap64)) {
+			printk(KERN_ERR "%s: shm cap with bad size offset: %d"
+			       "size: %d\n", __func__, pos, cap_len);
+			continue;
+		}
+
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+                                                         id), &id);
+		if (id != required_id)
+			continue;
+
+		/* Type, and ID match, looks good */
+		pci_read_config_byte(dev, pos + offsetof(struct virtio_pci_cap,
+							 bar), bar);
+
+		/* Read the lower 32bit of length and offset */
+		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
+							  offset), &tmp32);
+		res_offset = tmp32;
+		pci_read_config_dword(dev, pos + offsetof(struct virtio_pci_cap,
+							  length), &tmp32);
+		res_length = tmp32;
+
+		/* and now the top half */
+		pci_read_config_dword(dev,
+				      pos + offsetof(struct virtio_pci_cap64,
+                                                     offset_hi), &tmp32);
+		res_offset |= ((u64)tmp32) << 32;
+		pci_read_config_dword(dev,
+				      pos + offsetof(struct virtio_pci_cap64,
+                                                     length_hi), &tmp32);
+		res_length |= ((u64)tmp32) << 32;
+
+		*offset = res_offset;
+		*len = res_length;
+
+		return pos;
+	}
+	return 0;
+}
+
+static bool vp_get_shm_region(struct virtio_device *vdev,
+			      struct virtio_shm_region *region, u8 id)
+{
+	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
+	struct pci_dev *pci_dev = vp_dev->pci_dev;
+	u8 bar;
+	u64 offset, len;
+	phys_addr_t phys_addr;
+	size_t bar_len;
+
+	if (!virtio_pci_find_shm_cap(pci_dev, id, &bar, &offset, &len)) {
+		return false;
+	}
+
+	phys_addr = pci_resource_start(pci_dev, bar);
+	bar_len = pci_resource_len(pci_dev, bar);
+
+	if ((offset + len) < offset) {
+		dev_err(&pci_dev->dev, "%s: cap offset+len overflow detected\n",
+			__func__);
+		return false;
+	}
+
+	if (offset + len > bar_len) {
+		dev_err(&pci_dev->dev, "%s: bar shorter than cap offset+len\n",
+			__func__);
+		return false;
+	}
+
+	region->len = len;
+	region->addr = (u64) phys_addr + offset;
+
+	return true;
+}
+
 static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.get		= NULL,
 	.set		= NULL,
@@ -458,6 +552,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
+	.get_shm_region  = vp_get_shm_region,
 };
 
 static const struct virtio_config_ops virtio_pci_config_ops = {
@@ -474,6 +569,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
 	.get_vq_affinity = vp_get_vq_affinity,
+	.get_shm_region  = vp_get_shm_region,
 };
 
 /**
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 90007a1abcab..fe9f43680a1d 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -113,6 +113,8 @@
 #define VIRTIO_PCI_CAP_DEVICE_CFG	4
 /* PCI configuration access */
 #define VIRTIO_PCI_CAP_PCI_CFG		5
+/* Additional shared memory capability */
+#define VIRTIO_PCI_CAP_SHARED_MEMORY_CFG 8
 
 /* This is the PCI capability header: */
 struct virtio_pci_cap {
@@ -121,11 +123,18 @@ struct virtio_pci_cap {
 	__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. */
+	__u8 id;		/* Multiple capabilities of the same type */
+	__u8 padding[2];	/* Pad to full dword. */
 	__le32 offset;		/* Offset within bar. */
 	__le32 length;		/* Length of the structure, in bytes. */
 };
 
+struct virtio_pci_cap64 {
+       struct virtio_pci_cap cap;
+       __le32 offset_hi;             /* Most sig 32 bits of offset */
+       __le32 length_hi;             /* Most sig 32 bits of length */
+};
+
 struct virtio_pci_notify_cap {
 	struct virtio_pci_cap cap;
 	__le32 notify_off_multiplier;	/* Multiplier for queue_notify_off. */
-- 
2.25.4