On Wed, 3 Jul 2019 13:18:59 +0300
Ivan Khoronzhuk <ivan.khoronzhuk@xxxxxxxxxx> wrote:
> First of all, it is an absolute requirement that each RX-queue have
> their own page_pool object/allocator. And this change is intendant
> to handle special case, where a single RX-queue can receive packets
> from two different net_devices.
>
> In order to protect against using same allocator for 2 different rx
> queues, add queue_index to xdp_mem_allocator to catch the obvious
> mistake where queue_index mismatch, as proposed by Jesper Dangaard
> Brouer.
>
> Adding this on xdp allocator level allows drivers with such dependency
> change the allocators w/o modifications.
>
> Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@xxxxxxxxxx>
> ---
> include/net/xdp_priv.h | 2 ++
> net/core/xdp.c | 55 ++++++++++++++++++++++++++++++++++++++++++
> 2 files changed, 57 insertions(+)
>
> diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h
> index 6a8cba6ea79a..9858a4057842 100644
> --- a/include/net/xdp_priv.h
> +++ b/include/net/xdp_priv.h
> @@ -18,6 +18,8 @@ struct xdp_mem_allocator {
> struct rcu_head rcu;
> struct delayed_work defer_wq;
> unsigned long defer_warn;
> + unsigned long refcnt;
> + u32 queue_index;
> };
I don't like this approach, because I think we need to extend struct
xdp_mem_allocator with a net_device pointer, for doing dev_hold(), to
correctly handle lifetime issues. (As I tried to explain previously).
This will be much harder after this change, which is why I proposed the
other patch.
> #endif /* __LINUX_NET_XDP_PRIV_H__ */
> diff --git a/net/core/xdp.c b/net/core/xdp.c
> index 829377cc83db..4f0ddbb3717a 100644
> --- a/net/core/xdp.c
> +++ b/net/core/xdp.c
> @@ -98,6 +98,18 @@ static bool __mem_id_disconnect(int id, bool force)
> WARN(1, "Request remove non-existing id(%d), driver bug?", id);
> return true;
> }
> +
> + /* to avoid calling hash lookup twice, decrement refcnt here till it
> + * reaches zero, then it can be called from workqueue afterwards.
> + */
> + if (xa->refcnt)
> + xa->refcnt--;
> +
> + if (xa->refcnt) {
> + mutex_unlock(&mem_id_lock);
> + return true;
> + }
> +
> xa->disconnect_cnt++;
>
> /* Detects in-flight packet-pages for page_pool */
> @@ -312,6 +324,33 @@ static bool __is_supported_mem_type(enum xdp_mem_type type)
> return true;
> }
>
> +static struct xdp_mem_allocator *xdp_allocator_find(void *allocator)
> +{
> + struct xdp_mem_allocator *xae, *xa = NULL;
> + struct rhashtable_iter iter;
> +
> + if (!allocator)
> + return xa;
> +
> + rhashtable_walk_enter(mem_id_ht, &iter);
> + do {
> + rhashtable_walk_start(&iter);
> +
> + while ((xae = rhashtable_walk_next(&iter)) && !IS_ERR(xae)) {
> + if (xae->allocator == allocator) {
> + xa = xae;
> + break;
> + }
> + }
> +
> + rhashtable_walk_stop(&iter);
> +
> + } while (xae == ERR_PTR(-EAGAIN));
> + rhashtable_walk_exit(&iter);
> +
> + return xa;
> +}
> +
> int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
> enum xdp_mem_type type, void *allocator)
> {
> @@ -347,6 +386,20 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
> }
> }
>
> + mutex_lock(&mem_id_lock);
> + xdp_alloc = xdp_allocator_find(allocator);
> + if (xdp_alloc) {
> + /* One allocator per queue is supposed only */
> + if (xdp_alloc->queue_index != xdp_rxq->queue_index)
> + return -EINVAL;
> +
> + xdp_rxq->mem.id = xdp_alloc->mem.id;
> + xdp_alloc->refcnt++;
> + mutex_unlock(&mem_id_lock);
> + return 0;
> + }
> + mutex_unlock(&mem_id_lock);
> +
> xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp);
> if (!xdp_alloc)
> return -ENOMEM;
> @@ -360,6 +413,8 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
> xdp_rxq->mem.id = id;
> xdp_alloc->mem = xdp_rxq->mem;
> xdp_alloc->allocator = allocator;
> + xdp_alloc->refcnt = 1;
> + xdp_alloc->queue_index = xdp_rxq->queue_index;
>
> /* Insert allocator into ID lookup table */
> ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node);
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Principal Kernel Engineer at Red Hat
LinkedIn: http://www.linkedin.com/in/brouer
