public inbox for [email protected]
 help / color / mirror / Atom feed
From: David Wei <[email protected]>
To: [email protected], [email protected]
Cc: Jens Axboe <[email protected]>,
	Pavel Begunkov <[email protected]>,
	Jakub Kicinski <[email protected]>, Paolo Abeni <[email protected]>,
	"David S. Miller" <[email protected]>,
	Eric Dumazet <[email protected]>,
	Jesper Dangaard Brouer <[email protected]>,
	David Ahern <[email protected]>,
	Mina Almasry <[email protected]>,
	Stanislav Fomichev <[email protected]>,
	Joe Damato <[email protected]>,
	Pedro Tammela <[email protected]>
Subject: [PATCH v7 13/15] io_uring/zcrx: set pp memory provider for an rx queue
Date: Tue, 29 Oct 2024 16:05:16 -0700	[thread overview]
Message-ID: <[email protected]> (raw)
In-Reply-To: <[email protected]>

From: David Wei <[email protected]>

Set the page pool memory provider for the rx queue configured for zero
copy to io_uring. Then the rx queue is reset using
netdev_rx_queue_restart() and netdev core + page pool will take care of
filling the rx queue from the io_uring zero copy memory provider.

For now, there is only one ifq so its destruction happens implicitly
during io_uring cleanup.

Signed-off-by: David Wei <[email protected]>
---
 io_uring/zcrx.c | 86 +++++++++++++++++++++++++++++++++++++++++++++++--
 io_uring/zcrx.h |  2 ++
 2 files changed, 86 insertions(+), 2 deletions(-)

diff --git a/io_uring/zcrx.c b/io_uring/zcrx.c
index 477b0d1b7b91..3f4625730dbd 100644
--- a/io_uring/zcrx.c
+++ b/io_uring/zcrx.c
@@ -8,6 +8,7 @@
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/memory_provider.h>
 #include <trace/events/page_pool.h>
+#include <net/netdev_rx_queue.h>
 #include <net/tcp.h>
 #include <net/rps.h>
 
@@ -36,6 +37,65 @@ static inline struct io_zcrx_area *io_zcrx_iov_to_area(const struct net_iov *nio
 	return container_of(owner, struct io_zcrx_area, nia);
 }
 
+static int io_open_zc_rxq(struct io_zcrx_ifq *ifq, unsigned ifq_idx)
+{
+	struct netdev_rx_queue *rxq;
+	struct net_device *dev = ifq->dev;
+	int ret;
+
+	ASSERT_RTNL();
+
+	if (ifq_idx >= dev->num_rx_queues)
+		return -EINVAL;
+	ifq_idx = array_index_nospec(ifq_idx, dev->num_rx_queues);
+
+	rxq = __netif_get_rx_queue(ifq->dev, ifq_idx);
+	if (rxq->mp_params.mp_priv)
+		return -EEXIST;
+
+	ifq->if_rxq = ifq_idx;
+	rxq->mp_params.mp_ops = &io_uring_pp_zc_ops;
+	rxq->mp_params.mp_priv = ifq;
+	ret = netdev_rx_queue_restart(ifq->dev, ifq->if_rxq);
+	if (ret)
+		goto fail;
+	return 0;
+fail:
+	rxq->mp_params.mp_ops = NULL;
+	rxq->mp_params.mp_priv = NULL;
+	ifq->if_rxq = -1;
+	return ret;
+}
+
+static void io_close_zc_rxq(struct io_zcrx_ifq *ifq)
+{
+	struct netdev_rx_queue *rxq;
+	int err;
+
+	if (ifq->if_rxq == -1)
+		return;
+
+	rtnl_lock();
+	if (WARN_ON_ONCE(ifq->if_rxq >= ifq->dev->num_rx_queues)) {
+		rtnl_unlock();
+		return;
+	}
+
+	rxq = __netif_get_rx_queue(ifq->dev, ifq->if_rxq);
+
+	WARN_ON_ONCE(rxq->mp_params.mp_priv != ifq);
+
+	rxq->mp_params.mp_ops = NULL;
+	rxq->mp_params.mp_priv = NULL;
+
+	err = netdev_rx_queue_restart(ifq->dev, ifq->if_rxq);
+	if (err)
+		pr_devel("io_uring: can't restart a queue on zcrx close\n");
+
+	rtnl_unlock();
+	ifq->if_rxq = -1;
+}
+
 static int io_allocate_rbuf_ring(struct io_zcrx_ifq *ifq,
 				 struct io_uring_zcrx_ifq_reg *reg)
 {
@@ -156,9 +216,12 @@ static struct io_zcrx_ifq *io_zcrx_ifq_alloc(struct io_ring_ctx *ctx)
 
 static void io_zcrx_ifq_free(struct io_zcrx_ifq *ifq)
 {
+	io_close_zc_rxq(ifq);
+
 	if (ifq->area)
 		io_zcrx_free_area(ifq->area);
-
+	if (ifq->dev)
+		netdev_put(ifq->dev, &ifq->netdev_tracker);
 	io_free_rbuf_ring(ifq);
 	kfree(ifq);
 }
@@ -214,7 +277,18 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 		goto err;
 
 	ifq->rq_entries = reg.rq_entries;
-	ifq->if_rxq = reg.if_rxq;
+
+	ret = -ENODEV;
+	rtnl_lock();
+	ifq->dev = netdev_get_by_index(current->nsproxy->net_ns, reg.if_idx,
+				       &ifq->netdev_tracker, GFP_KERNEL);
+	if (!ifq->dev)
+		goto err_rtnl_unlock;
+
+	ret = io_open_zc_rxq(ifq, reg.if_rxq);
+	if (ret)
+		goto err_rtnl_unlock;
+	rtnl_unlock();
 
 	ring_sz = sizeof(struct io_uring);
 	rqes_sz = sizeof(struct io_uring_zcrx_rqe) * ifq->rq_entries;
@@ -224,15 +298,20 @@ int io_register_zcrx_ifq(struct io_ring_ctx *ctx,
 	reg.offsets.tail = offsetof(struct io_uring, tail);
 
 	if (copy_to_user(arg, &reg, sizeof(reg))) {
+		io_close_zc_rxq(ifq);
 		ret = -EFAULT;
 		goto err;
 	}
 	if (copy_to_user(u64_to_user_ptr(reg.area_ptr), &area, sizeof(area))) {
+		io_close_zc_rxq(ifq);
 		ret = -EFAULT;
 		goto err;
 	}
 	ctx->ifq = ifq;
 	return 0;
+
+err_rtnl_unlock:
+	rtnl_unlock();
 err:
 	io_zcrx_ifq_free(ifq);
 	return ret;
@@ -254,6 +333,9 @@ void io_unregister_zcrx_ifqs(struct io_ring_ctx *ctx)
 void io_shutdown_zcrx_ifqs(struct io_ring_ctx *ctx)
 {
 	lockdep_assert_held(&ctx->uring_lock);
+
+	if (ctx->ifq)
+		io_close_zc_rxq(ctx->ifq);
 }
 
 static void io_zcrx_get_buf_uref(struct net_iov *niov)
diff --git a/io_uring/zcrx.h b/io_uring/zcrx.h
index 1f039ad45a63..d3f6b6cdd647 100644
--- a/io_uring/zcrx.h
+++ b/io_uring/zcrx.h
@@ -5,6 +5,7 @@
 #include <linux/io_uring_types.h>
 #include <linux/socket.h>
 #include <net/page_pool/types.h>
+#include <net/net_trackers.h>
 
 #define IO_ZC_RX_UREF			0x10000
 #define IO_ZC_RX_KREF_MASK		(IO_ZC_RX_UREF - 1)
@@ -37,6 +38,7 @@ struct io_zcrx_ifq {
 	struct page			**rqe_pages;
 
 	u32				if_rxq;
+	netdevice_tracker		netdev_tracker;
 };
 
 #if defined(CONFIG_IO_URING_ZCRX)
-- 
2.43.5


  parent reply	other threads:[~2024-10-29 23:06 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-29 23:05 [PATCH v7 00/15] io_uring zero copy rx David Wei
2024-10-29 23:05 ` [PATCH v7 01/15] net: prefix devmem specific helpers David Wei
2024-10-29 23:05 ` [PATCH v7 02/15] net: generalise net_iov chunk owners David Wei
2024-10-29 23:05 ` [PATCH v7 03/15] net: page_pool: create hooks for custom page providers David Wei
2024-10-29 23:05 ` [PATCH v7 04/15] net: prepare for non devmem TCP memory providers David Wei
2024-10-29 23:05 ` [PATCH v7 05/15] net: page_pool: add ->scrub mem provider callback David Wei
2024-10-29 23:05 ` [PATCH v7 06/15] net: page pool: add helper creating area from pages David Wei
2024-10-29 23:05 ` [PATCH v7 07/15] net: page_pool: introduce page_pool_mp_return_in_cache David Wei
2024-10-29 23:05 ` [PATCH v7 08/15] net: add helper executing custom callback from napi David Wei
2024-10-29 23:05 ` [PATCH v7 09/15] io_uring/zcrx: add interface queue and refill queue David Wei
2024-10-29 23:05 ` [PATCH v7 10/15] io_uring/zcrx: add io_zcrx_area David Wei
2024-10-29 23:05 ` [PATCH v7 11/15] io_uring/zcrx: implement zerocopy receive pp memory provider David Wei
2024-10-29 23:05 ` [PATCH v7 12/15] io_uring/zcrx: add io_recvzc request David Wei
2024-10-29 23:05 ` David Wei [this message]
2024-10-29 23:05 ` [PATCH v7 14/15] io_uring/zcrx: add copy fallback David Wei
2024-10-29 23:05 ` [PATCH v7 15/15] io_uring/zcrx: throttle receive requests David Wei

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    [email protected] \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox