@@ -179,6 +179,11 @@ static void tap_put_queue(struct tap_queue *q)
sock_put(&q->sk);
}
+static const struct virtio_net_hash *tap_find_hash(const struct sk_buff *skb)
+{
+ return NULL;
+}
+
/*
* Select a queue based on the rxq of the device on which this packet
* arrived. If the incoming device is not mq, calculate a flow hash
@@ -711,11 +716,12 @@ static ssize_t tap_put_user(struct tap_queue *q,
int total;
if (q->flags & IFF_VNET_HDR) {
- struct virtio_net_hdr vnet_hdr;
+ struct virtio_net_hdr_v1_hash vnet_hdr;
vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
- ret = tun_vnet_hdr_from_skb(q->flags, NULL, skb, &vnet_hdr);
+ ret = tun_vnet_hdr_from_skb(vnet_hdr_len, q->flags, NULL, skb,
+ tap_find_hash, &vnet_hdr);
if (ret)
return ret;
@@ -451,6 +451,11 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
e->rps_rxhash = hash;
}
+static const struct virtio_net_hash *tun_find_hash(const struct sk_buff *skb)
+{
+ return NULL;
+}
+
/* We try to identify a flow through its rxhash. The reason that
* we do not check rxq no. is because some cards(e.g 82599), chooses
* the rxq based on the txq where the last packet of the flow comes. As
@@ -1993,7 +1998,7 @@ static ssize_t tun_put_user_xdp(struct tun_struct *tun,
ssize_t ret;
if (tun->flags & IFF_VNET_HDR) {
- struct virtio_net_hdr gso = { 0 };
+ struct virtio_net_hdr_v1_hash gso = { 0 };
vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
@@ -2046,9 +2051,10 @@ static ssize_t tun_put_user(struct tun_struct *tun,
}
if (vnet_hdr_sz) {
- struct virtio_net_hdr gso;
+ struct virtio_net_hdr_v1_hash gso;
- ret = tun_vnet_hdr_from_skb(tun->flags, tun->dev, skb, &gso);
+ ret = tun_vnet_hdr_from_skb(vnet_hdr_sz, tun->flags, tun->dev,
+ skb, tun_find_hash, &gso);
if (ret)
return ret;
@@ -6,6 +6,16 @@
#define TUN_VNET_LE 0x80000000
#define TUN_VNET_BE 0x40000000
+typedef struct virtio_net_hash *(*tun_vnet_hash_add)(struct sk_buff *);
+typedef const struct virtio_net_hash *(*tun_vnet_hash_find)(const struct sk_buff *);
+
+struct tun_vnet_hash_container {
+ struct tun_vnet_hash common;
+ struct tun_vnet_hash_rss rss;
+ u32 rss_key[VIRTIO_NET_RSS_MAX_KEY_SIZE];
+ u16 rss_indirection_table[];
+};
+
static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags)
{
bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) &&
@@ -107,6 +117,119 @@ static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags,
}
}
+static inline long tun_vnet_ioctl_gethashcap(void __user *argp)
+{
+ static const struct tun_vnet_hash cap = {
+ .flags = TUN_VNET_HASH_REPORT | TUN_VNET_HASH_RSS,
+ .types = VIRTIO_NET_SUPPORTED_HASH_TYPES
+ };
+
+ return copy_to_user(argp, &cap, sizeof(cap)) ? -EFAULT : 0;
+}
+
+static inline long tun_vnet_ioctl_sethash(struct tun_vnet_hash_container __rcu **hashp,
+ void __user *argp)
+{
+ struct tun_vnet_hash hash_buf;
+ struct tun_vnet_hash_container *hash;
+
+ if (copy_from_user(&hash_buf, argp, sizeof(hash_buf)))
+ return -EFAULT;
+ argp = (struct tun_vnet_hash __user *)argp + 1;
+
+ if (hash_buf.flags & TUN_VNET_HASH_RSS) {
+ struct tun_vnet_hash_rss rss;
+ size_t indirection_table_size;
+ size_t key_size;
+ size_t size;
+
+ if (copy_from_user(&rss, argp, sizeof(rss)))
+ return -EFAULT;
+ argp = (struct tun_vnet_hash_rss __user *)argp + 1;
+
+ indirection_table_size = ((size_t)rss.indirection_table_mask + 1) * 2;
+ key_size = virtio_net_hash_key_length(hash_buf.types);
+ size = struct_size(hash, rss_indirection_table,
+ (size_t)rss.indirection_table_mask + 1);
+
+ hash = kmalloc(size, GFP_KERNEL);
+ if (!hash)
+ return -ENOMEM;
+
+ if (copy_from_user(hash->rss_indirection_table,
+ argp, indirection_table_size)) {
+ kfree(hash);
+ return -EFAULT;
+ }
+ argp = (u16 __user *)argp + rss.indirection_table_mask + 1;
+
+ if (copy_from_user(hash->rss_key, argp, key_size)) {
+ kfree(hash);
+ return -EFAULT;
+ }
+
+ virtio_net_toeplitz_convert_key(hash->rss_key, key_size);
+ hash->rss = rss;
+ } else {
+ hash = kmalloc(sizeof(hash->common), GFP_KERNEL);
+ if (!hash)
+ return -ENOMEM;
+ }
+
+ hash->common = hash_buf;
+ kfree_rcu_mightsleep(rcu_replace_pointer_rtnl(*hashp, hash));
+ return 0;
+}
+
+static inline void tun_vnet_hash_report(const struct tun_vnet_hash_container *hash,
+ struct sk_buff *skb,
+ const struct flow_keys_basic *keys,
+ u32 value,
+ tun_vnet_hash_add vnet_hash_add)
+{
+ struct virtio_net_hash *report;
+
+ if (!hash || !(hash->common.flags & TUN_VNET_HASH_REPORT))
+ return;
+
+ report = vnet_hash_add(skb);
+ if (!report)
+ return;
+
+ *report = (struct virtio_net_hash) {
+ .report = virtio_net_hash_report(hash->common.types, keys),
+ .value = value
+ };
+}
+
+static inline u16 tun_vnet_rss_select_queue(u32 numqueues,
+ const struct tun_vnet_hash_container *hash,
+ struct sk_buff *skb,
+ tun_vnet_hash_add vnet_hash_add)
+{
+ struct virtio_net_hash *report;
+ struct virtio_net_hash ret;
+ u16 index;
+
+ if (!numqueues)
+ return 0;
+
+ virtio_net_hash_rss(skb, hash->common.types, hash->rss_key, &ret);
+
+ if (!ret.report)
+ return hash->rss.unclassified_queue % numqueues;
+
+ if (hash->common.flags & TUN_VNET_HASH_REPORT) {
+ report = vnet_hash_add(skb);
+ if (report)
+ *report = ret;
+ }
+
+ index = ret.value & hash->rss.indirection_table_mask;
+
+ return hash->rss_indirection_table[index] % numqueues;
+}
+
static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
struct iov_iter *from,
struct virtio_net_hdr *hdr)
@@ -135,15 +258,17 @@ static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
}
static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
- const struct virtio_net_hdr *hdr)
+ const struct virtio_net_hdr_v1_hash *hdr)
{
+ int content_sz = MIN(sizeof(*hdr), sz);
+
if (unlikely(iov_iter_count(iter) < sz))
return -EINVAL;
- if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
+ if (unlikely(copy_to_iter(hdr, content_sz, iter) != content_sz))
return -EFAULT;
- if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr))
+ if (iov_iter_zero(sz - content_sz, iter) != sz - content_sz)
return -EFAULT;
return 0;
@@ -155,26 +280,38 @@ static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb,
return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags));
}
-static inline int tun_vnet_hdr_from_skb(unsigned int flags,
+static inline int tun_vnet_hdr_from_skb(int sz, unsigned int flags,
const struct net_device *dev,
const struct sk_buff *skb,
- struct virtio_net_hdr *hdr)
+ tun_vnet_hash_find vnet_hash_find,
+ struct virtio_net_hdr_v1_hash *hdr)
{
int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
+ const struct virtio_net_hash *report = sz < sizeof(struct virtio_net_hdr_v1_hash) ?
+ NULL : vnet_hash_find(skb);
+
+ *hdr = (struct virtio_net_hdr_v1_hash) {
+ .hash_report = VIRTIO_NET_HASH_REPORT_NONE
+ };
+
+ if (report) {
+ hdr->hash_value = cpu_to_le32(report->value);
+ hdr->hash_report = cpu_to_le16(report->report);
+ }
- if (virtio_net_hdr_from_skb(skb, hdr,
+ if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)hdr,
tun_vnet_is_little_endian(flags), true,
vlan_hlen)) {
struct skb_shared_info *sinfo = skb_shinfo(skb);
if (net_ratelimit()) {
netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
- sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size),
- tun_vnet16_to_cpu(flags, hdr->hdr_len));
+ sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->hdr.gso_size),
+ tun_vnet16_to_cpu(flags, hdr->hdr.hdr_len));
print_hex_dump(KERN_ERR, "tun: ",
DUMP_PREFIX_NONE,
16, 1, skb->head,
- min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true);
+ min(tun_vnet16_to_cpu(flags, hdr->hdr.hdr_len), 64), true);
}
WARN_ON_ONCE(1);
return -EINVAL;
@@ -62,6 +62,42 @@
#define TUNSETCARRIER _IOW('T', 226, int)
#define TUNGETDEVNETNS _IO('T', 227)
+/**
+ * define TUNGETVNETHASHCAP - ioctl to get virtio_net hashing capability
+ *
+ * The argument is a pointer to &struct tun_vnet_hash which will store the
+ * maximal virtio_net hashing configuration.
+ */
+#define TUNGETVNETHASHCAP _IOR('T', 228, struct tun_vnet_hash)
+
+/**
+ * define TUNSETVNETHASH - ioctl to configure virtio_net hashing
+ *
+ * The argument is a pointer to &struct tun_vnet_hash.
+ *
+ * The argument is a pointer to the compound of the following in order if
+ * %TUN_VNET_HASH_RSS is set:
+ *
+ * 1. &struct tun_vnet_hash
+ * 2. &struct tun_vnet_hash_rss
+ * 3. Indirection table
+ * 4. Key
+ *
+ * The %TUN_VNET_HASH_REPORT flag set with this ioctl will be effective only
+ * after calling the %TUNSETVNETHDRSZ ioctl with a number greater than or equal
+ * to the size of &struct virtio_net_hdr_v1_hash.
+ *
+ * The members added to the legacy header by %TUN_VNET_HASH_REPORT flag will
+ * always be little-endian.
+ *
+ * This ioctl results in %EBADFD if the underlying device is deleted. It affects
+ * all queues attached to the same device.
+ *
+ * This ioctl currently has no effect on XDP packets and packets with
+ * queue_mapping set by TC.
+ */
+#define TUNSETVNETHASH _IOW('T', 229, struct tun_vnet_hash)
+
/* TUNSETIFF ifr flags */
#define IFF_TUN 0x0001
#define IFF_TAP 0x0002
@@ -124,4 +160,41 @@ struct tun_filter {
*/
#define TUN_STEERINGEBPF_FALLBACK -1
+/**
+ * define TUN_VNET_HASH_REPORT - Request virtio_net hash reporting for vhost
+ */
+#define TUN_VNET_HASH_REPORT 0x0001
+
+/**
+ * define TUN_VNET_HASH_RSS - Request virtio_net RSS
+ */
+#define TUN_VNET_HASH_RSS 0x0002
+
+/**
+ * struct tun_vnet_hash - virtio_net hashing configuration
+ * @flags:
+ * Bitmask consists of %TUN_VNET_HASH_REPORT and %TUN_VNET_HASH_RSS
+ * @pad:
+ * Should be filled with zero before passing to %TUNSETVNETHASH
+ * @types:
+ * Bitmask of allowed hash types
+ */
+struct tun_vnet_hash {
+ __u16 flags;
+ __u8 pad[2];
+ __u32 types;
+};
+
+/**
+ * struct tun_vnet_hash_rss - virtio_net RSS configuration
+ * @indirection_table_mask:
+ * Bitmask to be applied to the indirection table index
+ * @unclassified_queue:
+ * The index of the queue to place unclassified packets in
+ */
+struct tun_vnet_hash_rss {
+ __u16 indirection_table_mask;
+ __u16 unclassified_queue;
+};
+
#endif /* _UAPI__IF_TUN_H */