Message-ID: <CAL+tcoD3Kj6h=RvkEJ_9vmJPWKGVcaLj4ws=JqRbE0TiyjDDWg@mail.gmail.com>
Date: Wed, 27 Aug 2025 00:00:15 +0800
From: Jason Xing <kerneljasonxing@...il.com>
To: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
Cc: bpf@...r.kernel.org, ast@...nel.org, daniel@...earbox.net, 
	andrii@...nel.org, netdev@...r.kernel.org, magnus.karlsson@...el.com, 
	stfomichev@...il.com, aleksander.lobakin@...el.com, 
	Eryk Kubanski <e.kubanski@...tner.samsung.com>
Subject: Re: [PATCH v6 bpf] xsk: fix immature cq descriptor production

On Wed, Aug 20, 2025 at 11:49 PM Maciej Fijalkowski
<maciej.fijalkowski@...el.com> wrote:
>
> Eryk reported an issue that I have put under Closes: tag, related to
> umem addrs being prematurely produced onto pool's completion queue.
> Let us make the skb's destructor responsible for producing all addrs
> that given skb used.
>
> Introduce struct xsk_addrs which will carry descriptor count with array
> of addresses taken from processed descriptors that will be carried via
> skb_shared_info::destructor_arg. This way we can refer to it within
> xsk_destruct_skb(). In order to mitigate the overhead that will be
> coming from memory allocations, let us introduce kmem_cache of
> xsk_addrs. There will be a single kmem_cache for xsk generic xmit on the
> system.
>
> Commit from fixes tag introduced the buggy behavior, it was not broken
> from day 1, but rather when xsk multi-buffer got introduced.
>
> Fixes: b7f72a30e9ac ("xsk: introduce wrappers and helpers for supporting multi-buffer in Tx path")
> Reported-by: Eryk Kubanski <e.kubanski@...tner.samsung.com>
> Closes: https://lore.kernel.org/netdev/20250530103456.53564-1-e.kubanski@partner.samsung.com/
> Acked-by: Magnus Karlsson <magnus.karlsson@...el.com>
> Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@...el.com>
> ---
>
> v1:
> https://lore.kernel.org/bpf/20250702101648.1942562-1-maciej.fijalkowski@intel.com/
> v2:
> https://lore.kernel.org/bpf/20250705135512.1963216-1-maciej.fijalkowski@intel.com/
> v3:
> https://lore.kernel.org/bpf/20250806154127.2161434-1-maciej.fijalkowski@intel.com/
> v4:
> https://lore.kernel.org/bpf/20250813171210.2205259-1-maciej.fijalkowski@intel.com/
> v5:
> https://lore.kernel.org/bpf/aKXBHGPxjpBDKOHq@boxer/T/
>
> v1->v2:
> * store addrs in array carried via destructor_arg instead having them
>   stored in skb headroom; cleaner and less hacky approach;
> v2->v3:
> * use kmem_cache for xsk_addrs allocation (Stan/Olek)
> * set err when xsk_addrs allocation fails (Dan)
> * change xsk_addrs layout to avoid holes
> * free xsk_addrs on error path
> * rebase
> v3->v4:
> * have kmem_cache as percpu vars
> * don't drop unnecessary braces (unrelated) (Stan)
> * use idx + i in xskq_prod_write_addr (Stan)
> * alloc kmem_cache on bind (Stan)
> * keep num_descs as first member in xsk_addrs (Magnus)
> * add ack from Magnus
> v4->v5:
> * have a single kmem_cache per xsk subsystem (Stan)
> v5->v6:
> * free skb in xsk_build_skb_zerocopy() when xsk_addrs allocation fails
>   (Stan)
> * unregister netdev notifier if creating kmem_cache fails (Stan)
>
> ---
>  net/xdp/xsk.c       | 95 +++++++++++++++++++++++++++++++++++++--------
>  net/xdp/xsk_queue.h | 12 ++++++
>  2 files changed, 91 insertions(+), 16 deletions(-)
>
> diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
> index 9c3acecc14b1..989d5ffb4273 100644
> --- a/net/xdp/xsk.c
> +++ b/net/xdp/xsk.c
> @@ -36,6 +36,13 @@
>  #define TX_BATCH_SIZE 32
>  #define MAX_PER_SOCKET_BUDGET 32
>
> +struct xsk_addrs {
> +       u32 num_descs;
> +       u64 addrs[MAX_SKB_FRAGS + 1];
> +};
> +
> +static struct kmem_cache *xsk_tx_generic_cache;

IMHO, adding a few heavy operations of allocating and freeing from
cache in the hot path is not a good choice. What I've been trying so
hard lately is to minimize the times of manipulating memory as much as
possible :( Memory hotspot can be easily captured by perf.

We might provide an new option in setsockopt() to let users
specifically support this use case since it does harm to normal cases?

> +
>  void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
>  {
>         if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
> @@ -532,25 +539,39 @@ static int xsk_wakeup(struct xdp_sock *xs, u8 flags)
>         return dev->netdev_ops->ndo_xsk_wakeup(dev, xs->queue_id, flags);
>  }
>
> -static int xsk_cq_reserve_addr_locked(struct xsk_buff_pool *pool, u64 addr)
> +static int xsk_cq_reserve_locked(struct xsk_buff_pool *pool)
>  {
>         unsigned long flags;
>         int ret;
>
>         spin_lock_irqsave(&pool->cq_lock, flags);
> -       ret = xskq_prod_reserve_addr(pool->cq, addr);
> +       ret = xskq_prod_reserve(pool->cq);
>         spin_unlock_irqrestore(&pool->cq_lock, flags);
>
>         return ret;
>  }
>
> -static void xsk_cq_submit_locked(struct xsk_buff_pool *pool, u32 n)
> +static void xsk_cq_submit_addr_locked(struct xdp_sock *xs,
> +                                     struct sk_buff *skb)
>  {
> +       struct xsk_buff_pool *pool = xs->pool;
> +       struct xsk_addrs *xsk_addrs;
>         unsigned long flags;
> +       u32 num_desc, i;
> +       u32 idx;
> +
> +       xsk_addrs = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg;
> +       num_desc = xsk_addrs->num_descs;
>
>         spin_lock_irqsave(&pool->cq_lock, flags);
> -       xskq_prod_submit_n(pool->cq, n);
> +       idx = xskq_get_prod(pool->cq);
> +
> +       for (i = 0; i < num_desc; i++)
> +               xskq_prod_write_addr(pool->cq, idx + i, xsk_addrs->addrs[i]);
> +       xskq_prod_submit_n(pool->cq, num_desc);
> +
>         spin_unlock_irqrestore(&pool->cq_lock, flags);
> +       kmem_cache_free(xsk_tx_generic_cache, xsk_addrs);
>  }
>
>  static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
> @@ -562,11 +583,6 @@ static void xsk_cq_cancel_locked(struct xsk_buff_pool *pool, u32 n)
>         spin_unlock_irqrestore(&pool->cq_lock, flags);
>  }
>
> -static u32 xsk_get_num_desc(struct sk_buff *skb)
> -{
> -       return skb ? (long)skb_shinfo(skb)->destructor_arg : 0;
> -}
> -
>  static void xsk_destruct_skb(struct sk_buff *skb)
>  {
>         struct xsk_tx_metadata_compl *compl = &skb_shinfo(skb)->xsk_meta;
> @@ -576,21 +592,37 @@ static void xsk_destruct_skb(struct sk_buff *skb)
>                 *compl->tx_timestamp = ktime_get_tai_fast_ns();
>         }
>
> -       xsk_cq_submit_locked(xdp_sk(skb->sk)->pool, xsk_get_num_desc(skb));
> +       xsk_cq_submit_addr_locked(xdp_sk(skb->sk), skb);
>         sock_wfree(skb);
>  }
>
> -static void xsk_set_destructor_arg(struct sk_buff *skb)
> +static u32 xsk_get_num_desc(struct sk_buff *skb)
>  {
> -       long num = xsk_get_num_desc(xdp_sk(skb->sk)->skb) + 1;
> +       struct xsk_addrs *addrs;
>
> -       skb_shinfo(skb)->destructor_arg = (void *)num;
> +       addrs = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg;
> +       return addrs->num_descs;
> +}
> +
> +static void xsk_set_destructor_arg(struct sk_buff *skb, struct xsk_addrs *addrs)
> +{
> +       skb_shinfo(skb)->destructor_arg = (void *)addrs;
> +}
> +
> +static void xsk_inc_skb_descs(struct sk_buff *skb)
> +{
> +       struct xsk_addrs *addrs;
> +
> +       addrs = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg;
> +       addrs->num_descs++;
>  }
>
>  static void xsk_consume_skb(struct sk_buff *skb)
>  {
>         struct xdp_sock *xs = xdp_sk(skb->sk);
>
> +       kmem_cache_free(xsk_tx_generic_cache,
> +                       (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg);

Replying to Daniel here: when EOVERFLOW occurs, it will finally go to
above function and clear the allocated memory and skb.

>         skb->destructor = sock_wfree;
>         xsk_cq_cancel_locked(xs->pool, xsk_get_num_desc(skb));
>         /* Free skb without triggering the perf drop trace */
> @@ -609,6 +641,7 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
>  {
>         struct xsk_buff_pool *pool = xs->pool;
>         u32 hr, len, ts, offset, copy, copied;
> +       struct xsk_addrs *addrs = NULL;

nit: no need to set to "NULL" at the begining.

>         struct sk_buff *skb = xs->skb;
>         struct page *page;
>         void *buffer;
> @@ -623,6 +656,14 @@ static struct sk_buff *xsk_build_skb_zerocopy(struct xdp_sock *xs,
>                         return ERR_PTR(err);
>
>                 skb_reserve(skb, hr);
> +
> +               addrs = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
> +               if (!addrs) {
> +                       kfree(skb);
> +                       return ERR_PTR(-ENOMEM);
> +               }
> +
> +               xsk_set_destructor_arg(skb, addrs);
>         }
>
>         addr = desc->addr;
> @@ -662,6 +703,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
>  {
>         struct xsk_tx_metadata *meta = NULL;
>         struct net_device *dev = xs->dev;
> +       struct xsk_addrs *addrs = NULL;
>         struct sk_buff *skb = xs->skb;
>         bool first_frag = false;
>         int err;
> @@ -694,6 +736,15 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
>                         err = skb_store_bits(skb, 0, buffer, len);
>                         if (unlikely(err))
>                                 goto free_err;
> +
> +                       addrs = kmem_cache_zalloc(xsk_tx_generic_cache, GFP_KERNEL);
> +                       if (!addrs) {
> +                               err = -ENOMEM;
> +                               goto free_err;
> +                       }
> +
> +                       xsk_set_destructor_arg(skb, addrs);
> +
>                 } else {
>                         int nr_frags = skb_shinfo(skb)->nr_frags;
>                         struct page *page;
> @@ -759,7 +810,9 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
>         skb->mark = READ_ONCE(xs->sk.sk_mark);
>         skb->destructor = xsk_destruct_skb;
>         xsk_tx_metadata_to_compl(meta, &skb_shinfo(skb)->xsk_meta);
> -       xsk_set_destructor_arg(skb);
> +
> +       addrs = (struct xsk_addrs *)skb_shinfo(skb)->destructor_arg;
> +       addrs->addrs[addrs->num_descs++] = desc->addr;
>
>         return skb;
>
> @@ -769,7 +822,7 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
>
>         if (err == -EOVERFLOW) {
>                 /* Drop the packet */
> -               xsk_set_destructor_arg(xs->skb);
> +               xsk_inc_skb_descs(xs->skb);
>                 xsk_drop_skb(xs->skb);
>                 xskq_cons_release(xs->tx);
>         } else {
> @@ -812,7 +865,7 @@ static int __xsk_generic_xmit(struct sock *sk)
>                  * if there is space in it. This avoids having to implement
>                  * any buffering in the Tx path.
>                  */
> -               err = xsk_cq_reserve_addr_locked(xs->pool, desc.addr);
> +               err = xsk_cq_reserve_locked(xs->pool);
>                 if (err) {
>                         err = -EAGAIN;
>                         goto out;
> @@ -1815,8 +1868,18 @@ static int __init xsk_init(void)
>         if (err)
>                 goto out_pernet;
>
> +       xsk_tx_generic_cache = kmem_cache_create("xsk_generic_xmit_cache",
> +                                                sizeof(struct xsk_addrs), 0,
> +                                                SLAB_HWCACHE_ALIGN, NULL);
> +       if (!xsk_tx_generic_cache) {
> +               err = -ENOMEM;
> +               goto out_unreg_notif;
> +       }
> +
>         return 0;
>
> +out_unreg_notif:
> +       unregister_netdevice_notifier(&xsk_netdev_notifier);
>  out_pernet:
>         unregister_pernet_subsys(&xsk_net_ops);
>  out_sk:
> diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
> index 46d87e961ad6..f16f390370dc 100644
> --- a/net/xdp/xsk_queue.h
> +++ b/net/xdp/xsk_queue.h
> @@ -344,6 +344,11 @@ static inline u32 xskq_cons_present_entries(struct xsk_queue *q)
>
>  /* Functions for producers */
>
> +static inline u32 xskq_get_prod(struct xsk_queue *q)
> +{
> +       return READ_ONCE(q->ring->producer);
> +}
> +
>  static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max)
>  {
>         u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons);
> @@ -390,6 +395,13 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr)
>         return 0;
>  }
>
> +static inline void xskq_prod_write_addr(struct xsk_queue *q, u32 idx, u64 addr)
> +{
> +       struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring;
> +
> +       ring->desc[idx & q->ring_mask] = addr;
> +}
> +
>  static inline void xskq_prod_write_addr_batch(struct xsk_queue *q, struct xdp_desc *descs,
>                                               u32 nb_entries)
>  {
> --
> 2.34.1
>
>

Powered by blists - more mailing lists