diff options
Diffstat (limited to 'net/xdp/xdp_umem.c')
-rw-r--r-- | net/xdp/xdp_umem.c | 242 |
1 files changed, 35 insertions, 207 deletions
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index e97db37354e4..56d052bc65cb 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -23,162 +23,6 @@ static DEFINE_IDA(umem_ida); -void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_add_rcu(&xs->list, &umem->xsk_tx_list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - -void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) -{ - unsigned long flags; - - if (!xs->tx) - return; - - spin_lock_irqsave(&umem->xsk_tx_list_lock, flags); - list_del_rcu(&xs->list); - spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags); -} - -/* The umem is stored both in the _rx struct and the _tx struct as we do - * not know if the device has more tx queues than rx, or the opposite. - * This might also change during run time. - */ -static int xdp_reg_umem_at_qid(struct net_device *dev, struct xdp_umem *umem, - u16 queue_id) -{ - if (queue_id >= max_t(unsigned int, - dev->real_num_rx_queues, - dev->real_num_tx_queues)) - return -EINVAL; - - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = umem; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = umem; - - return 0; -} - -struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, - u16 queue_id) -{ - if (queue_id < dev->real_num_rx_queues) - return dev->_rx[queue_id].umem; - if (queue_id < dev->real_num_tx_queues) - return dev->_tx[queue_id].umem; - - return NULL; -} -EXPORT_SYMBOL(xdp_get_umem_from_qid); - -static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id) -{ - if (queue_id < dev->real_num_rx_queues) - dev->_rx[queue_id].umem = NULL; - if (queue_id < dev->real_num_tx_queues) - dev->_tx[queue_id].umem = NULL; -} - -int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, - u16 queue_id, u16 flags) -{ - bool force_zc, force_copy; - struct netdev_bpf bpf; - int err = 0; - - ASSERT_RTNL(); - - force_zc = flags & XDP_ZEROCOPY; - force_copy = flags & XDP_COPY; - - if (force_zc && force_copy) - return -EINVAL; - - if (xdp_get_umem_from_qid(dev, queue_id)) - return -EBUSY; - - err = xdp_reg_umem_at_qid(dev, umem, queue_id); - if (err) - return err; - - umem->dev = dev; - umem->queue_id = queue_id; - - if (flags & XDP_USE_NEED_WAKEUP) { - umem->flags |= XDP_UMEM_USES_NEED_WAKEUP; - /* Tx needs to be explicitly woken up the first time. - * Also for supporting drivers that do not implement this - * feature. They will always have to call sendto(). - */ - xsk_set_tx_need_wakeup(umem); - } - - dev_hold(dev); - - if (force_copy) - /* For copy-mode, we are done. */ - return 0; - - if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_wakeup) { - err = -EOPNOTSUPP; - goto err_unreg_umem; - } - - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = umem; - bpf.xsk.queue_id = queue_id; - - err = dev->netdev_ops->ndo_bpf(dev, &bpf); - if (err) - goto err_unreg_umem; - - umem->zc = true; - return 0; - -err_unreg_umem: - if (!force_zc) - err = 0; /* fallback to copy mode */ - if (err) - xdp_clear_umem_at_qid(dev, queue_id); - return err; -} - -void xdp_umem_clear_dev(struct xdp_umem *umem) -{ - struct netdev_bpf bpf; - int err; - - ASSERT_RTNL(); - - if (!umem->dev) - return; - - if (umem->zc) { - bpf.command = XDP_SETUP_XSK_UMEM; - bpf.xsk.umem = NULL; - bpf.xsk.queue_id = umem->queue_id; - - err = umem->dev->netdev_ops->ndo_bpf(umem->dev, &bpf); - - if (err) - WARN(1, "failed to disable umem!\n"); - } - - xdp_clear_umem_at_qid(umem->dev, umem->queue_id); - - dev_put(umem->dev); - umem->dev = NULL; - umem->zc = false; -} - static void xdp_umem_unpin_pages(struct xdp_umem *umem) { unpin_user_pages_dirty_lock(umem->pgs, umem->npgs, true); @@ -195,38 +39,33 @@ static void xdp_umem_unaccount_pages(struct xdp_umem *umem) } } -static void xdp_umem_release(struct xdp_umem *umem) +static void xdp_umem_addr_unmap(struct xdp_umem *umem) { - rtnl_lock(); - xdp_umem_clear_dev(umem); - rtnl_unlock(); - - ida_simple_remove(&umem_ida, umem->id); + vunmap(umem->addrs); + umem->addrs = NULL; +} - if (umem->fq) { - xskq_destroy(umem->fq); - umem->fq = NULL; - } +static int xdp_umem_addr_map(struct xdp_umem *umem, struct page **pages, + u32 nr_pages) +{ + umem->addrs = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL); + if (!umem->addrs) + return -ENOMEM; + return 0; +} - if (umem->cq) { - xskq_destroy(umem->cq); - umem->cq = NULL; - } +static void xdp_umem_release(struct xdp_umem *umem) +{ + umem->zc = false; + ida_simple_remove(&umem_ida, umem->id); - xp_destroy(umem->pool); + xdp_umem_addr_unmap(umem); xdp_umem_unpin_pages(umem); xdp_umem_unaccount_pages(umem); kfree(umem); } -static void xdp_umem_release_deferred(struct work_struct *work) -{ - struct xdp_umem *umem = container_of(work, struct xdp_umem, work); - - xdp_umem_release(umem); -} - void xdp_get_umem(struct xdp_umem *umem) { refcount_inc(&umem->users); @@ -237,10 +76,8 @@ void xdp_put_umem(struct xdp_umem *umem) if (!umem) return; - if (refcount_dec_and_test(&umem->users)) { - INIT_WORK(&umem->work, xdp_umem_release_deferred); - schedule_work(&umem->work); - } + if (refcount_dec_and_test(&umem->users)) + xdp_umem_release(umem); } static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address) @@ -303,10 +140,10 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { + u32 npgs_rem, chunk_size = mr->chunk_size, headroom = mr->headroom; bool unaligned_chunks = mr->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG; - u32 chunk_size = mr->chunk_size, headroom = mr->headroom; u64 npgs, addr = mr->addr, size = mr->len; - unsigned int chunks, chunks_per_page; + unsigned int chunks, chunks_rem; int err; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { @@ -319,8 +156,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) return -EINVAL; } - if (mr->flags & ~(XDP_UMEM_UNALIGNED_CHUNK_FLAG | - XDP_UMEM_USES_NEED_WAKEUP)) + if (mr->flags & ~XDP_UMEM_UNALIGNED_CHUNK_FLAG) return -EINVAL; if (!unaligned_chunks && !is_power_of_2(chunk_size)) @@ -336,19 +172,18 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if ((addr + size) < addr) return -EINVAL; - npgs = size >> PAGE_SHIFT; + npgs = div_u64_rem(size, PAGE_SIZE, &npgs_rem); + if (npgs_rem) + npgs++; if (npgs > U32_MAX) return -EINVAL; - chunks = (unsigned int)div_u64(size, chunk_size); + chunks = (unsigned int)div_u64_rem(size, chunk_size, &chunks_rem); if (chunks == 0) return -EINVAL; - if (!unaligned_chunks) { - chunks_per_page = PAGE_SIZE / chunk_size; - if (chunks < chunks_per_page || chunks % chunks_per_page) - return -EINVAL; - } + if (!unaligned_chunks && chunks_rem) + return -EINVAL; if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; @@ -356,13 +191,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->size = size; umem->headroom = headroom; umem->chunk_size = chunk_size; + umem->chunks = chunks; umem->npgs = (u32)npgs; umem->pgs = NULL; umem->user = NULL; umem->flags = mr->flags; - INIT_LIST_HEAD(&umem->xsk_tx_list); - spin_lock_init(&umem->xsk_tx_list_lock); + INIT_LIST_HEAD(&umem->xsk_dma_list); refcount_set(&umem->users, 1); err = xdp_umem_account_pages(umem); @@ -373,15 +208,13 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if (err) goto out_account; - umem->pool = xp_create(umem->pgs, umem->npgs, chunks, chunk_size, - headroom, size, unaligned_chunks); - if (!umem->pool) { - err = -ENOMEM; - goto out_pin; - } + err = xdp_umem_addr_map(umem, umem->pgs, umem->npgs); + if (err) + goto out_unpin; + return 0; -out_pin: +out_unpin: xdp_umem_unpin_pages(umem); out_account: xdp_umem_unaccount_pages(umem); @@ -413,8 +246,3 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) return umem; } - -bool xdp_umem_validate_queues(struct xdp_umem *umem) -{ - return umem->fq && umem->cq; -} |