Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - 9k mtu perf improvements

 - vdpa feature provisioning

 - virtio blk SECURE ERASE support

 - fixes and cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio_pci: don't try to use intxif pin is zero
  vDPA: conditionally read MTU and MAC in dev cfg space
  vDPA: fix spars cast warning in vdpa_dev_net_mq_config_fill
  vDPA: check virtio device features to detect MQ
  vDPA: check VIRTIO_NET_F_RSS for max_virtqueue_paris's presence
  vDPA: only report driver features if FEATURES_OK is set
  vDPA: allow userspace to query features of a vDPA device
  virtio_blk: add SECURE ERASE command support
  vp_vdpa: support feature provisioning
  vdpa_sim_net: support feature provisioning
  vdpa: device feature provisioning
  virtio-net: use mtu size as buffer length for big packets
  virtio-net: introduce and use helper function for guest gso support checks
  virtio: drop vp_legacy_set_queue_size
  virtio_ring: make vring_alloc_queue_packed prettier
  virtio_ring: split: Operators use unified style
  vhost: add __init/__exit annotations to module init/exit funcs

6 files changed, 94 insertions, 23 deletions

diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c
index 7badf57775972..febdc99b51a7b 100644
--- a/drivers/vdpa/vdpa.c
+++ b/drivers/vdpa/vdpa.c
@@ -600,6 +600,11 @@ static int vdpa_nl_cmd_dev_add_set_doit(struct sk_buff *skb, struct genl_info *i
 		}
 		config.mask |= BIT_ULL(VDPA_ATTR_DEV_NET_CFG_MAX_VQP);
 	}
+	if (nl_attrs[VDPA_ATTR_DEV_FEATURES]) {
+		config.device_features =
+			nla_get_u64(nl_attrs[VDPA_ATTR_DEV_FEATURES]);
+		config.mask |= BIT_ULL(VDPA_ATTR_DEV_FEATURES);
+	}
 
 	/* Skip checking capability if user didn't prefer to configure any
 	 * device networking attributes. It is likely that user might have used
@@ -799,51 +804,76 @@ static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callba
 	return msg->len;
 }
 
-static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev,
-				       struct sk_buff *msg, u64 features,
+static int vdpa_dev_net_mq_config_fill(struct sk_buff *msg, u64 features,
 				       const struct virtio_net_config *config)
 {
 	u16 val_u16;
 
-	if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0)
+	if ((features & BIT_ULL(VIRTIO_NET_F_MQ)) == 0 &&
+	    (features & BIT_ULL(VIRTIO_NET_F_RSS)) == 0)
 		return 0;
 
-	val_u16 = le16_to_cpu(config->max_virtqueue_pairs);
+	val_u16 = __virtio16_to_cpu(true, config->max_virtqueue_pairs);
+
 	return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16);
 }
 
+static int vdpa_dev_net_mtu_config_fill(struct sk_buff *msg, u64 features,
+					const struct virtio_net_config *config)
+{
+	u16 val_u16;
+
+	if ((features & BIT_ULL(VIRTIO_NET_F_MTU)) == 0)
+		return 0;
+
+	val_u16 = __virtio16_to_cpu(true, config->mtu);
+
+	return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16);
+}
+
+static int vdpa_dev_net_mac_config_fill(struct sk_buff *msg, u64 features,
+					const struct virtio_net_config *config)
+{
+	if ((features & BIT_ULL(VIRTIO_NET_F_MAC)) == 0)
+		return 0;
+
+	return  nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR,
+			sizeof(config->mac), config->mac);
+}
+
 static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg)
 {
 	struct virtio_net_config config = {};
-	u64 features;
+	u64 features_device;
 	u16 val_u16;
 
-	vdpa_get_config_unlocked(vdev, 0, &config, sizeof(config));
-
-	if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac),
-		    config.mac))
-		return -EMSGSIZE;
+	vdev->config->get_config(vdev, 0, &config, sizeof(config));
 
 	val_u16 = __virtio16_to_cpu(true, config.status);
 	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16))
 		return -EMSGSIZE;
 
-	val_u16 = __virtio16_to_cpu(true, config.mtu);
-	if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16))
-		return -EMSGSIZE;
+	features_device = vdev->config->get_device_features(vdev);
 
-	features = vdev->config->get_driver_features(vdev);
-	if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features,
+	if (nla_put_u64_64bit(msg, VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES, features_device,
 			      VDPA_ATTR_PAD))
 		return -EMSGSIZE;
 
-	return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config);
+	if (vdpa_dev_net_mtu_config_fill(msg, features_device, &config))
+		return -EMSGSIZE;
+
+	if (vdpa_dev_net_mac_config_fill(msg, features_device, &config))
+		return -EMSGSIZE;
+
+	return vdpa_dev_net_mq_config_fill(msg, features_device, &config);
 }
 
 static int
 vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq,
 		     int flags, struct netlink_ext_ack *extack)
 {
+	u64 features_driver;
+	u8 status = 0;
 	u32 device_id;
 	void *hdr;
 	int err;
@@ -867,6 +897,17 @@ vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid,
 		goto msg_err;
 	}
 
+	/* only read driver features after the feature negotiation is done */
+	status = vdev->config->get_status(vdev);
+	if (status & VIRTIO_CONFIG_S_FEATURES_OK) {
+		features_driver = vdev->config->get_driver_features(vdev);
+		if (nla_put_u64_64bit(msg, VDPA_ATTR_DEV_NEGOTIATED_FEATURES, features_driver,
+				      VDPA_ATTR_PAD)) {
+			err = -EMSGSIZE;
+			goto msg_err;
+		}
+	}
+
 	switch (device_id) {
 	case VIRTIO_ID_NET:
 		err = vdpa_dev_net_config_fill(vdev, msg);
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index 225b7f5d8be35..b071f0d842fba 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -18,6 +18,7 @@
 #include <linux/vdpa.h>
 #include <linux/vhost_iotlb.h>
 #include <linux/iova.h>
+#include <uapi/linux/vdpa.h>
 
 #include "vdpa_sim.h"
 
@@ -245,13 +246,22 @@ static const struct dma_map_ops vdpasim_dma_ops = {
 static const struct vdpa_config_ops vdpasim_config_ops;
 static const struct vdpa_config_ops vdpasim_batch_config_ops;
 
-struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr,
+			       const struct vdpa_dev_set_config *config)
 {
 	const struct vdpa_config_ops *ops;
 	struct vdpasim *vdpasim;
 	struct device *dev;
 	int i, ret = -ENOMEM;
 
+	if (config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) {
+		if (config->device_features &
+		    ~dev_attr->supported_features)
+			return ERR_PTR(-EINVAL);
+		dev_attr->supported_features =
+			config->device_features;
+	}
+
 	if (batch_mapping)
 		ops = &vdpasim_batch_config_ops;
 	else
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.h b/drivers/vdpa/vdpa_sim/vdpa_sim.h
index 061986f30911a..0e78737dcc166 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.h
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.h
@@ -71,7 +71,8 @@ struct vdpasim {
 	spinlock_t iommu_lock;
 };
 
-struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr);
+struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *attr,
+			       const struct vdpa_dev_set_config *config);
 
 /* TODO: cross-endian support */
 static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
index c8bfea3b7db23..c6db1a1baf768 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_blk.c
@@ -383,7 +383,7 @@ static int vdpasim_blk_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	dev_attr.work_fn = vdpasim_blk_work;
 	dev_attr.buffer_size = VDPASIM_BLK_CAPACITY << SECTOR_SHIFT;
 
-	simdev = vdpasim_create(&dev_attr);
+	simdev = vdpasim_create(&dev_attr, config);
 	if (IS_ERR(simdev))
 		return PTR_ERR(simdev);
 
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
index 886449e885026..c3cb225ea4693 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim_net.c
@@ -254,7 +254,7 @@ static int vdpasim_net_dev_add(struct vdpa_mgmt_dev *mdev, const char *name,
 	dev_attr.work_fn = vdpasim_net_work;
 	dev_attr.buffer_size = PAGE_SIZE;
 
-	simdev = vdpasim_create(&dev_attr);
+	simdev = vdpasim_create(&dev_attr, config);
 	if (IS_ERR(simdev))
 		return PTR_ERR(simdev);
 
@@ -294,7 +294,8 @@ static struct vdpa_mgmt_dev mgmt_dev = {
 	.id_table = id_table,
 	.ops = &vdpasim_net_mgmtdev_ops,
 	.config_attr_mask = (1 << VDPA_ATTR_DEV_NET_CFG_MACADDR |
-			     1 << VDPA_ATTR_DEV_NET_CFG_MTU),
+			     1 << VDPA_ATTR_DEV_NET_CFG_MTU |
+		             1 << VDPA_ATTR_DEV_FEATURES),
 	.max_supported_vqs = VDPASIM_NET_VQ_NUM,
 	.supported_features = VDPASIM_NET_FEATURES,
 };
diff --git a/drivers/vdpa/virtio_pci/vp_vdpa.c b/drivers/vdpa/virtio_pci/vp_vdpa.c
index 04522077735b2..d448db0c4de3f 100644
--- a/drivers/vdpa/virtio_pci/vp_vdpa.c
+++ b/drivers/vdpa/virtio_pci/vp_vdpa.c
@@ -17,6 +17,7 @@
 #include <linux/virtio_ring.h>
 #include <linux/virtio_pci.h>
 #include <linux/virtio_pci_modern.h>
+#include <uapi/linux/vdpa.h>
 
 #define VP_VDPA_QUEUE_MAX 256
 #define VP_VDPA_DRIVER_NAME "vp_vdpa"
@@ -35,6 +36,7 @@ struct vp_vdpa {
 	struct virtio_pci_modern_device *mdev;
 	struct vp_vring *vring;
 	struct vdpa_callback config_cb;
+	u64 device_features;
 	char msix_name[VP_VDPA_NAME_SIZE];
 	int config_irq;
 	int queues;
@@ -66,9 +68,9 @@ static struct virtio_pci_modern_device *vp_vdpa_to_mdev(struct vp_vdpa *vp_vdpa)
 
 static u64 vp_vdpa_get_device_features(struct vdpa_device *vdpa)
 {
-	struct virtio_pci_modern_device *mdev = vdpa_to_mdev(vdpa);
+	struct vp_vdpa *vp_vdpa = vdpa_to_vp(vdpa);
 
-	return vp_modern_get_features(mdev);
+	return vp_vdpa->device_features;
 }
 
 static int vp_vdpa_set_driver_features(struct vdpa_device *vdpa, u64 features)
@@ -475,6 +477,7 @@ static int vp_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	struct pci_dev *pdev = mdev->pci_dev;
 	struct device *dev = &pdev->dev;
 	struct vp_vdpa *vp_vdpa = NULL;
+	u64 device_features;
 	int ret, i;
 
 	vp_vdpa = vdpa_alloc_device(struct vp_vdpa, vdpa,
@@ -491,6 +494,20 @@ static int vp_vdpa_dev_add(struct vdpa_mgmt_dev *v_mdev, const char *name,
 	vp_vdpa->queues = vp_modern_get_num_queues(mdev);
 	vp_vdpa->mdev = mdev;
 
+	device_features = vp_modern_get_features(mdev);
+	if (add_config->mask & BIT_ULL(VDPA_ATTR_DEV_FEATURES)) {
+		if (add_config->device_features & ~device_features) {
+			ret = -EINVAL;
+			dev_err(&pdev->dev, "Try to provision features "
+				"that are not supported by the device: "
+				"device_features 0x%llx provisioned 0x%llx\n",
+				device_features, add_config->device_features);
+			goto err;
+		}
+		device_features = add_config->device_features;
+	}
+	vp_vdpa->device_features = device_features;
+
 	ret = devm_add_action_or_reset(dev, vp_vdpa_free_irq_vectors, pdev);
 	if (ret) {
 		dev_err(&pdev->dev,
@@ -599,6 +616,7 @@ static int vp_vdpa_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mgtdev->id_table = mdev_id;
 	mgtdev->max_supported_vqs = vp_modern_get_num_queues(mdev);
 	mgtdev->supported_features = vp_modern_get_features(mdev);
+	mgtdev->config_attr_mask = (1 << VDPA_ATTR_DEV_FEATURES);
 	pci_set_master(pdev);
 	pci_set_drvdata(pdev, vp_vdpa_mgtdev);