@@ -1711,9 +1711,12 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size,
void msg_zerocopy_put_abort(struct ubuf_info *uarg, bool have_uref);
+struct net_devmem_dmabuf_binding;
+
int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, struct iov_iter *from,
- size_t length);
+ size_t length,
+ struct net_devmem_dmabuf_binding *binding);
int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
struct iov_iter *from, size_t length);
@@ -1721,12 +1724,14 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
static inline int skb_zerocopy_iter_dgram(struct sk_buff *skb,
struct msghdr *msg, int len)
{
- return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len);
+ return __zerocopy_sg_from_iter(msg, skb->sk, skb, &msg->msg_iter, len,
+ NULL);
}
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
- struct ubuf_info *uarg);
+ struct ubuf_info *uarg,
+ struct net_devmem_dmabuf_binding *binding);
/* Internal */
#define skb_shinfo(SKB) ((struct skb_shared_info *)(skb_end_pointer(SKB)))
@@ -3697,6 +3702,10 @@ static inline dma_addr_t __skb_frag_dma_map(struct device *dev,
size_t offset, size_t size,
enum dma_data_direction dir)
{
+ if (skb_frag_is_net_iov(frag)) {
+ return netmem_to_net_iov(frag->netmem)->dma_addr + offset +
+ frag->offset;
+ }
return dma_map_page(dev, skb_frag_page(frag),
skb_frag_off(frag) + offset, size, dir);
}
@@ -1822,6 +1822,7 @@ struct sockcm_cookie {
u32 tsflags;
u32 ts_opt_id;
u32 priority;
+ u32 dmabuf_id;
};
static inline void sockcm_init(struct sockcm_cookie *sockc,
@@ -38,10 +38,14 @@ struct dmabuf_token {
__u32 token_count;
};
+struct dmabuf_tx_cmsg {
+ __u32 dmabuf_id;
+};
+
/*
* UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
*/
-
+
#define UIO_FASTIOV 8
#define UIO_MAXIOV 1024
@@ -63,6 +63,8 @@
#include <net/busy_poll.h>
#include <crypto/hash.h>
+#include "devmem.h"
+
/*
* Is a socket 'connection oriented' ?
*/
@@ -692,9 +694,42 @@ int zerocopy_fill_skb_from_iter(struct sk_buff *skb,
return 0;
}
+static int
+zerocopy_fill_skb_from_devmem(struct sk_buff *skb, struct iov_iter *from,
+ int length,
+ struct net_devmem_dmabuf_binding *binding)
+{
+ int i = skb_shinfo(skb)->nr_frags;
+ size_t virt_addr, size, off;
+ struct net_iov *niov;
+
+ while (length && iov_iter_count(from)) {
+ if (i == MAX_SKB_FRAGS)
+ return -EMSGSIZE;
+
+ virt_addr = (size_t)iter_iov_addr(from);
+ niov = net_devmem_get_niov_at(binding, virt_addr, &off, &size);
+ if (!niov)
+ return -EFAULT;
+
+ size = min_t(size_t, size, length);
+ size = min_t(size_t, size, iter_iov_len(from));
+
+ get_netmem(net_iov_to_netmem(niov));
+ skb_add_rx_frag_netmem(skb, i, net_iov_to_netmem(niov), off,
+ size, PAGE_SIZE);
+ iov_iter_advance(from, size);
+ length -= size;
+ i++;
+ }
+
+ return 0;
+}
+
int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
struct sk_buff *skb, struct iov_iter *from,
- size_t length)
+ size_t length,
+ struct net_devmem_dmabuf_binding *binding)
{
unsigned long orig_size = skb->truesize;
unsigned long truesize;
@@ -702,6 +737,8 @@ int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk,
if (msg && msg->msg_ubuf && msg->sg_from_iter)
ret = msg->sg_from_iter(skb, from, length);
+ else if (unlikely(binding))
+ ret = zerocopy_fill_skb_from_devmem(skb, from, length, binding);
else
ret = zerocopy_fill_skb_from_iter(skb, from, length);
@@ -735,7 +772,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from)
if (skb_copy_datagram_from_iter(skb, 0, from, copy))
return -EFAULT;
- return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U);
+ return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U, NULL);
}
EXPORT_SYMBOL(zerocopy_sg_from_iter);
@@ -16,6 +16,7 @@
#include <net/netdev_queues.h>
#include <net/netdev_rx_queue.h>
#include <net/page_pool/helpers.h>
+#include <net/sock.h>
#include <trace/events/page_pool.h>
#include "devmem.h"
@@ -64,8 +65,10 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
dma_buf_detach(binding->dmabuf, binding->attachment);
dma_buf_put(binding->dmabuf);
xa_destroy(&binding->bound_rxqs);
+ kfree(binding->tx_vec);
kfree(binding);
}
+EXPORT_SYMBOL(__net_devmem_dmabuf_binding_free);
struct net_iov *
net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
@@ -110,6 +113,13 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
unsigned long xa_idx;
unsigned int rxq_idx;
+ xa_erase(&net_devmem_dmabuf_bindings, binding->id);
+
+ /* Ensure no tx net_devmem_lookup_dmabuf() are in flight after the
+ * erase.
+ */
+ synchronize_net();
+
if (binding->list.next)
list_del(&binding->list);
@@ -123,8 +133,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx));
}
- xa_erase(&net_devmem_dmabuf_bindings, binding->id);
-
net_devmem_dmabuf_binding_put(binding);
}
@@ -185,8 +193,9 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
}
struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
- struct netlink_ext_ack *extack)
+net_devmem_bind_dmabuf(struct net_device *dev,
+ enum dma_data_direction direction,
+ unsigned int dmabuf_fd, struct netlink_ext_ack *extack)
{
struct net_devmem_dmabuf_binding *binding;
static u32 id_alloc_next;
@@ -229,7 +238,7 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
}
binding->sgt = dma_buf_map_attachment_unlocked(binding->attachment,
- DMA_FROM_DEVICE);
+ direction);
if (IS_ERR(binding->sgt)) {
err = PTR_ERR(binding->sgt);
NL_SET_ERR_MSG(extack, "Failed to map dmabuf attachment");
@@ -240,13 +249,22 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
* binding can be much more flexible than that. We may be able to
* allocate MTU sized chunks here. Leave that for future work...
*/
- binding->chunk_pool =
- gen_pool_create(PAGE_SHIFT, dev_to_node(&dev->dev));
+ binding->chunk_pool = gen_pool_create(PAGE_SHIFT,
+ dev_to_node(&dev->dev));
if (!binding->chunk_pool) {
err = -ENOMEM;
goto err_unmap;
}
+ if (direction == DMA_TO_DEVICE) {
+ binding->tx_vec = kcalloc(dmabuf->size / PAGE_SIZE,
+ sizeof(struct net_iov *), GFP_KERNEL);
+ if (!binding->tx_vec) {
+ err = -ENOMEM;
+ goto err_free_chunks;
+ }
+ }
+
virtual = 0;
for_each_sgtable_dma_sg(binding->sgt, sg, sg_idx) {
dma_addr_t dma_addr = sg_dma_address(sg);
@@ -288,6 +306,8 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
niov->owner = owner;
page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
net_devmem_get_dma_addr(niov));
+ if (direction == DMA_TO_DEVICE)
+ binding->tx_vec[owner->base_virtual / PAGE_SIZE + i] = niov;
}
virtual += len;
@@ -313,6 +333,21 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
return ERR_PTR(err);
}
+struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id)
+{
+ struct net_devmem_dmabuf_binding *binding;
+
+ rcu_read_lock();
+ binding = xa_load(&net_devmem_dmabuf_bindings, id);
+ if (binding) {
+ if (!net_devmem_dmabuf_binding_get(binding))
+ binding = NULL;
+ }
+ rcu_read_unlock();
+
+ return binding;
+}
+
void dev_dmabuf_uninstall(struct net_device *dev)
{
struct net_devmem_dmabuf_binding *binding;
@@ -343,6 +378,53 @@ void net_devmem_put_net_iov(struct net_iov *niov)
net_devmem_dmabuf_binding_put(niov->owner->binding);
}
+struct net_devmem_dmabuf_binding *net_devmem_get_binding(struct sock *sk,
+ unsigned int dmabuf_id)
+{
+ struct net_devmem_dmabuf_binding *binding;
+ struct dst_entry *dst = __sk_dst_get(sk);
+ int err = 0;
+
+ binding = net_devmem_lookup_dmabuf(dmabuf_id);
+ if (!binding || !binding->tx_vec) {
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ /* The dma-addrs in this binding are only reachable to the corresponding
+ * net_device.
+ */
+ if (!dst || !dst->dev || dst->dev->ifindex != binding->dev->ifindex) {
+ err = -ENODEV;
+ goto out_err;
+ }
+
+ return binding;
+
+out_err:
+ if (binding)
+ net_devmem_dmabuf_binding_put(binding);
+
+ return ERR_PTR(err);
+}
+
+struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding,
+ size_t virt_addr, size_t *off, size_t *size)
+{
+ size_t idx;
+
+ if (virt_addr >= binding->dmabuf->size)
+ return NULL;
+
+ idx = virt_addr / PAGE_SIZE;
+
+ *off = virt_addr % PAGE_SIZE;
+ *size = PAGE_SIZE - *off;
+
+ return binding->tx_vec[idx];
+}
+
/*** "Dmabuf devmem memory provider" ***/
int mp_dmabuf_devmem_init(struct page_pool *pool)
@@ -46,6 +46,12 @@ struct net_devmem_dmabuf_binding {
* active.
*/
u32 id;
+
+ /* Array of net_iov pointers for this binding, sorted by virtual
+ * address. This array is convenient to map the virtual addresses to
+ * net_iovs in the TX path.
+ */
+ struct net_iov **tx_vec;
};
#if defined(CONFIG_NET_DEVMEM)
@@ -70,12 +76,15 @@ struct dmabuf_genpool_chunk_owner {
void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
struct net_devmem_dmabuf_binding *
-net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
- struct netlink_ext_ack *extack);
+net_devmem_bind_dmabuf(struct net_device *dev,
+ enum dma_data_direction direction,
+ unsigned int dmabuf_fd, struct netlink_ext_ack *extack);
+struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id);
void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
struct net_devmem_dmabuf_binding *binding,
struct netlink_ext_ack *extack);
+void net_devmem_bind_tx_release(struct sock *sk);
void dev_dmabuf_uninstall(struct net_device *dev);
static inline struct dmabuf_genpool_chunk_owner *
@@ -108,10 +117,10 @@ static inline u32 net_iov_binding_id(const struct net_iov *niov)
return net_iov_owner(niov)->binding->id;
}
-static inline void
+static inline bool
net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
{
- refcount_inc(&binding->ref);
+ return refcount_inc_not_zero(&binding->ref);
}
static inline void
@@ -130,6 +139,12 @@ struct net_iov *
net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
void net_devmem_free_dmabuf(struct net_iov *ppiov);
+struct net_devmem_dmabuf_binding *
+net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id);
+struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr,
+ size_t *off, size_t *size);
+
#else
struct net_devmem_dmabuf_binding;
@@ -153,11 +168,17 @@ __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
static inline struct net_devmem_dmabuf_binding *
net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
+ enum dma_data_direction direction,
struct netlink_ext_ack *extack)
{
return ERR_PTR(-EOPNOTSUPP);
}
+static inline struct net_devmem_dmabuf_binding *net_devmem_lookup_dmabuf(u32 id)
+{
+ return NULL;
+}
+
static inline void
net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
{
@@ -195,6 +216,19 @@ static inline u32 net_iov_binding_id(const struct net_iov *niov)
{
return 0;
}
+
+static inline struct net_devmem_dmabuf_binding *
+net_devmem_get_binding(struct sock *sk, unsigned int dmabuf_id)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline struct net_iov *
+net_devmem_get_niov_at(struct net_devmem_dmabuf_binding *binding, size_t addr,
+ size_t *off, size_t *size)
+{
+ return NULL;
+}
#endif
#endif /* _NET_DEVMEM_H */
@@ -854,7 +854,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
goto err_unlock;
}
- binding = net_devmem_bind_dmabuf(netdev, dmabuf_fd, info->extack);
+ binding = net_devmem_bind_dmabuf(netdev, DMA_FROM_DEVICE, dmabuf_fd,
+ info->extack);
if (IS_ERR(binding)) {
err = PTR_ERR(binding);
goto err_unlock;
@@ -911,10 +912,68 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
return err;
}
-/* stub */
int netdev_nl_bind_tx_doit(struct sk_buff *skb, struct genl_info *info)
{
- return 0;
+ struct net_devmem_dmabuf_binding *binding;
+ struct list_head *sock_binding_list;
+ struct net_device *netdev;
+ u32 ifindex, dmabuf_fd;
+ struct sk_buff *rsp;
+ int err = 0;
+ void *hdr;
+
+ if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX) ||
+ GENL_REQ_ATTR_CHECK(info, NETDEV_A_DMABUF_FD))
+ return -EINVAL;
+
+ ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
+ dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]);
+
+ sock_binding_list =
+ genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk);
+ if (IS_ERR(sock_binding_list))
+ return PTR_ERR(sock_binding_list);
+
+ rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+ if (!rsp)
+ return -ENOMEM;
+
+ hdr = genlmsg_iput(rsp, info);
+ if (!hdr) {
+ err = -EMSGSIZE;
+ goto err_genlmsg_free;
+ }
+
+ rtnl_lock();
+
+ netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+ if (!netdev || !netif_device_present(netdev)) {
+ err = -ENODEV;
+ goto err_unlock;
+ }
+
+ binding = net_devmem_bind_dmabuf(netdev, DMA_TO_DEVICE, dmabuf_fd,
+ info->extack);
+ if (IS_ERR(binding)) {
+ err = PTR_ERR(binding);
+ goto err_unlock;
+ }
+
+ list_add(&binding->list, sock_binding_list);
+
+ nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
+ genlmsg_end(rsp, hdr);
+
+ rtnl_unlock();
+
+ return genlmsg_reply(rsp, info);
+
+ net_devmem_unbind_dmabuf(binding);
+err_unlock:
+ rtnl_unlock();
+err_genlmsg_free:
+ nlmsg_free(rsp);
+ return err;
}
void netdev_nl_sock_priv_init(struct list_head *priv)
@@ -1882,7 +1882,8 @@ EXPORT_SYMBOL_GPL(msg_zerocopy_ubuf_ops);
int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
struct msghdr *msg, int len,
- struct ubuf_info *uarg)
+ struct ubuf_info *uarg,
+ struct net_devmem_dmabuf_binding *binding)
{
int err, orig_len = skb->len;
@@ -1901,7 +1902,8 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb,
return -EEXIST;
}
- err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len);
+ err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len,
+ binding);
if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) {
struct sock *save_sk = skb->sk;
@@ -2911,6 +2911,7 @@ EXPORT_SYMBOL(sock_alloc_send_pskb);
int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
struct sockcm_cookie *sockc)
{
+ struct dmabuf_tx_cmsg dmabuf_tx;
u32 tsflags;
BUILD_BUG_ON(SOF_TIMESTAMPING_LAST == (1 << 31));
@@ -2964,6 +2965,13 @@ int __sock_cmsg_send(struct sock *sk, struct cmsghdr *cmsg,
if (!sk_set_prio_allowed(sk, *(u32 *)CMSG_DATA(cmsg)))
return -EPERM;
sockc->priority = *(u32 *)CMSG_DATA(cmsg);
+ break;
+ case SCM_DEVMEM_DMABUF:
+ if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct dmabuf_tx_cmsg)))
+ return -EINVAL;
+ dmabuf_tx = *(struct dmabuf_tx_cmsg *)CMSG_DATA(cmsg);
+ sockc->dmabuf_id = dmabuf_tx.dmabuf_id;
+
break;
default:
return -EINVAL;
@@ -1051,6 +1051,7 @@ int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
{
+ struct net_devmem_dmabuf_binding *binding = NULL;
struct tcp_sock *tp = tcp_sk(sk);
struct ubuf_info *uarg = NULL;
struct sk_buff *skb;
@@ -1063,6 +1064,15 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
flags = msg->msg_flags;
+ sockcm_init(&sockc, sk);
+ if (msg->msg_controllen) {
+ err = sock_cmsg_send(sk, msg, &sockc);
+ if (unlikely(err)) {
+ err = -EINVAL;
+ goto out_err;
+ }
+ }
+
if ((flags & MSG_ZEROCOPY) && size) {
if (msg->msg_ubuf) {
uarg = msg->msg_ubuf;
@@ -1080,6 +1090,15 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
else
uarg_to_msgzc(uarg)->zerocopy = 0;
}
+
+ if (sockc.dmabuf_id != 0) {
+ binding = net_devmem_get_binding(sk, sockc.dmabuf_id);
+ if (IS_ERR(binding)) {
+ err = PTR_ERR(binding);
+ binding = NULL;
+ goto out_err;
+ }
+ }
} else if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES) && size) {
if (sk->sk_route_caps & NETIF_F_SG)
zc = MSG_SPLICE_PAGES;
@@ -1123,15 +1142,6 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
/* 'common' sending to sendq */
}
- sockcm_init(&sockc, sk);
- if (msg->msg_controllen) {
- err = sock_cmsg_send(sk, msg, &sockc);
- if (unlikely(err)) {
- err = -EINVAL;
- goto out_err;
- }
- }
-
/* This should be in poll */
sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
@@ -1248,7 +1258,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
goto wait_for_space;
}
- err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg);
+ err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg,
+ binding);
if (err == -EMSGSIZE || err == -EEXIST) {
tcp_mark_push(tp, skb);
goto new_segment;
@@ -1329,6 +1340,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
/* msg->msg_ubuf is pinned by the caller so we don't take extra refs */
if (uarg && !msg->msg_ubuf)
net_zcopy_put(uarg);
+ if (binding)
+ net_devmem_dmabuf_binding_put(binding);
return copied + copied_syn;
do_error:
@@ -1346,6 +1359,9 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
sk->sk_write_space(sk);
tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED);
}
+ if (binding)
+ net_devmem_dmabuf_binding_put(binding);
+
return err;
}
EXPORT_SYMBOL_GPL(tcp_sendmsg_locked);
@@ -107,8 +107,7 @@ static int virtio_transport_fill_skb(struct sk_buff *skb,
{
if (zcopy)
return __zerocopy_sg_from_iter(info->msg, NULL, skb,
- &info->msg->msg_iter,
- len);
+ &info->msg->msg_iter, len, NULL);
return memcpy_from_msg(skb_put(skb, len), info->msg, len);
}