@@ -108,10 +108,45 @@ static inline bool xsk_buff_can_alloc(struct xsk_buff_pool *pool, u32 count)
static inline void xsk_buff_free(struct xdp_buff *xdp)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+ struct list_head *xskb_list = &xskb->pool->xskb_list;
+ struct xdp_buff_xsk *pos, *tmp;
+ if (likely(!xdp_buff_has_frags(xdp)))
+ goto out;
+
+ list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
+ list_del(&pos->xskb_list_node);
+ xp_free(pos);
+ }
+
+ xdp_get_shared_info_from_buff(xdp)->nr_frags = 0;
+out:
xp_free(xskb);
}
+static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+{
+ struct xdp_buff_xsk *frag = container_of(xdp, struct xdp_buff_xsk, xdp);
+
+ list_add_tail(&frag->xskb_list_node, &frag->pool->xskb_list);
+}
+
+static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+{
+ struct xdp_buff_xsk *xskb = container_of(first, struct xdp_buff_xsk, xdp);
+ struct xdp_buff *ret = NULL;
+ struct xdp_buff_xsk *frag;
+
+ frag = list_first_entry_or_null(&xskb->pool->xskb_list,
+ struct xdp_buff_xsk, xskb_list_node);
+ if (frag) {
+ list_del(&frag->xskb_list_node);
+ ret = &frag->xdp;
+ }
+
+ return ret;
+}
+
static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
{
xdp->data = xdp->data_hard_start + XDP_PACKET_HEADROOM;
@@ -265,6 +300,15 @@ static inline void xsk_buff_free(struct xdp_buff *xdp)
{
}
+static inline void xsk_buff_add_frag(struct xdp_buff *xdp)
+{
+}
+
+static inline struct xdp_buff *xsk_buff_get_frag(struct xdp_buff *first)
+{
+ return NULL;
+}
+
static inline void xsk_buff_set_size(struct xdp_buff *xdp, u32 size)
{
}
@@ -29,6 +29,7 @@ struct xdp_buff_xsk {
struct xsk_buff_pool *pool;
u64 orig_addr;
struct list_head free_list_node;
+ struct list_head xskb_list_node;
};
#define XSK_CHECK_PRIV_TYPE(t) BUILD_BUG_ON(sizeof(t) > offsetofend(struct xdp_buff_xsk, cb))
@@ -54,6 +55,7 @@ struct xsk_buff_pool {
struct xdp_umem *umem;
struct work_struct work;
struct list_head free_list;
+ struct list_head xskb_list;
u32 heads_cnt;
u16 queue_id;
@@ -155,8 +155,32 @@ static int __xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff_xsk *xskb, u32 len,
static int xsk_rcv_zc(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len)
{
struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
+ u32 frags = xdp_buff_has_frags(xdp);
+ struct xdp_buff_xsk *pos, *tmp;
+ struct list_head *xskb_list;
+ u32 contd = 0;
+ int err;
+
+ if (frags)
+ contd = XDP_PKT_CONTD;
- return __xsk_rcv_zc(xs, xskb, len, 0);
+ err = __xsk_rcv_zc(xs, xskb, len, contd);
+ if (err || likely(!frags))
+ goto out;
+
+ xskb_list = &xskb->pool->xskb_list;
+ list_for_each_entry_safe(pos, tmp, xskb_list, xskb_list_node) {
+ if (list_is_singular(xskb_list))
+ contd = 0;
+ len = pos->xdp.data_end - pos->xdp.data;
+ err = __xsk_rcv_zc(xs, pos, len, contd);
+ if (err)
+ return err;
+ list_del(&pos->xskb_list_node);
+ }
+
+out:
+ return err;
}
static void *xsk_copy_xdp_start(struct xdp_buff *from)
@@ -86,6 +86,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
pool->umem = umem;
pool->addrs = umem->addrs;
INIT_LIST_HEAD(&pool->free_list);
+ INIT_LIST_HEAD(&pool->xskb_list);
INIT_LIST_HEAD(&pool->xsk_tx_list);
spin_lock_init(&pool->xsk_tx_list_lock);
spin_lock_init(&pool->cq_lock);
@@ -99,6 +100,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
xskb->pool = pool;
xskb->xdp.frame_sz = umem->chunk_size - umem->headroom;
INIT_LIST_HEAD(&xskb->free_list_node);
+ INIT_LIST_HEAD(&xskb->xskb_list_node);
if (pool->unaligned)
pool->free_heads[i] = xskb;
else
@@ -187,6 +189,11 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
goto err_unreg_pool;
}
+ if (netdev->xdp_zc_max_segs == 1 && (flags & XDP_USE_SG)) {
+ err = -EOPNOTSUPP;
+ goto err_unreg_pool;
+ }
+
bpf.command = XDP_SETUP_XSK_POOL;
bpf.xsk.pool = pool;
bpf.xsk.queue_id = queue_id;
Given that skb_shared_info relies on skb_frag_t, in order to support xskb chaining, introduce xdp_buff_xsk::xskb_list_node and xsk_buff_pool::xskb_list. This is needed so ZC drivers can add frags as xskb nodes which will make it possible to handle it both when producing AF_XDP Rx descriptors as well as freeing/recycling all the frags that a single frame carries. Speaking of latter, update xsk_buff_free() to take care of list nodes. For the former (adding as frags), introduce xsk_buff_add_frag() for ZC drivers usage that is going to be used to add a frag to xskb list from pool. xsk_buff_get_frag() will be utilized by XDP_TX and, on contrary, will return xdp_buff. One of the previous patches added a wrapper for ZC Rx so implement xskb list walk and production of Rx descriptors there. On bind() path, bail out if socket wants to use ZC multi-buffer but underlying netdev does not support it. Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com> --- include/net/xdp_sock_drv.h | 44 +++++++++++++++++++++++++++++++++++++ include/net/xsk_buff_pool.h | 2 ++ net/xdp/xsk.c | 26 +++++++++++++++++++++- net/xdp/xsk_buff_pool.c | 7 ++++++ 4 files changed, 78 insertions(+), 1 deletion(-)