mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Björn Töpel" <bjorn@kernel.org>
To: Magnus Karlsson <magnus.karlsson@intel.com>,
	Maciej Fijalkowski <maciej.fijalkowski@intel.com>,
	Stanislav Fomichev <sdf@fomichev.me>,
	"David S. Miller" <davem@davemloft.net>,
	Eric Dumazet <edumazet@kernel.org>,
	Jakub Kicinski <kuba@kernel.org>, Paolo Abeni <pabeni@redhat.com>,
	Simon Horman <horms@kernel.org>, Jonathan Corbet <corbet@lwn.net>,
	Shuah Khan <skhan@linuxfoundation.org>,
	Randy Dunlap <rdunlap@infradead.org>,
	Alexander Duyck <alexanderduyck@fb.com>,
	kernel-team@meta.com, Andrew Lunn <andrew+netdev@lunn.ch>,
	Jesper Dangaard Brouer <hawk@kernel.org>,
	Ilias Apalodimas <ilias.apalodimas@linaro.org>,
	Alexei Starovoitov <ast@kernel.org>,
	Daniel Borkmann <daniel@iogearbox.net>,
	John Fastabend <john.fastabend@gmail.com>,
	Pavel Begunkov <asml.silence@gmail.com>,
	Jens Axboe <axboe@kernel.dk>, Andrii Nakryiko <andrii@kernel.org>,
	Eduard Zingerman <eddyz87@gmail.com>,
	Kumar Kartikeya Dwivedi <memxor@gmail.com>,
	Martin KaFai Lau <martin.lau@linux.dev>,
	Song Liu <song@kernel.org>,
	Yonghong Song <yonghong.song@linux.dev>,
	Jiri Olsa <jolsa@kernel.org>,
	Emil Tsalapatis <emil@etsalapatis.com>,
	Ihor Solodrai <ihor.solodrai@linux.dev>,
	netdev@vger.kernel.org, bpf@vger.kernel.org,
	io-uring@vger.kernel.org
Cc: "Björn Töpel" <bjorn@kernel.org>,
	"Mike Marciniszyn (Meta)" <mike.marciniszyn@gmail.com>,
	"Weiming Shi" <bestswngs@gmail.com>,
	"Nikolay Aleksandrov" <razor@blackwall.org>,
	"David Wei" <dw@davidwei.uk>,
	"Alexander Lobakin" <aleksander.lobakin@intel.com>,
	linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
	"Mina Almasry" <almasrymina@google.com>
Subject: [RFC net-next 03/15] net: Add memory provider capabilities
Date: Fri,  2 Oct 2026 21:00:04 +0200	[thread overview]
Message-ID: <20261002190018.696925-4-bjorn@kernel.org> (raw)
In-Reply-To: <20261002190018.696925-1-bjorn@kernel.org>

The current memory providers, devmem and io_uring zero-copy RX, give
memory that the CPU cannot read. The core allows them only on queues
with header-data split on, a zero header-split threshold, and no XDP
program. AF_XDP needs a provider that the CPU can read and that
works with XDP.

Add a capability field to the provider operations, with
MP_CAP_READABLE as the first flag. Apply the header-split and XDP
rules only to providers without it. A queue with an AF_XDP buffer
pool still rejects other providers, but it accepts the provider made
from that same pool.

Provider memory can become free while a queue is restarted, and no
device event reports it. After a restart, and after a failed restart
is rolled back, schedule the queue's NAPI if the queue has a
provider, so the driver tries to refill.

Signed-off-by: Björn Töpel <bjorn@kernel.org>
---
 Documentation/networking/netmem.rst     |  7 ++-
 include/net/page_pool/memory_provider.h | 11 +++++
 include/net/page_pool/types.h           |  7 +--
 net/core/dev.c                          |  4 +-
 net/core/netdev_rx_queue.c              | 57 ++++++++++++++++++++-----
 net/ethtool/rings.c                     | 18 +++-----
 net/xdp/xsk_buff_pool.c                 |  3 +-
 7 files changed, 78 insertions(+), 29 deletions(-)

diff --git a/Documentation/networking/netmem.rst b/Documentation/networking/netmem.rst
index 217869d1108d..aacd185843ac 100644
--- a/Documentation/networking/netmem.rst
+++ b/Documentation/networking/netmem.rst
@@ -48,8 +48,11 @@ Driver RX Requirements
    - PP_FLAG_DMA_SYNC_DEV: netmem dma addr is not necessarily dma-syncable
      by the driver. The driver must delegate the dma syncing to the page_pool,
      which knows when dma-syncing is (or is not) appropriate.
-   - PP_FLAG_ALLOW_UNREADABLE_NETMEM. The driver must specify this flag iff
-     tcp-data-split is enabled.
+   - PP_FLAG_ALLOW_UNREADABLE_NETMEM. This opts the page pool into the memory
+     provider configured on its RX queue. For a provider without
+     MP_CAP_READABLE, the driver must specify it only for a payload pool
+     with tcp-data-split enabled. A readable provider may also back a
+     regular or header pool.
 
 5. The driver must not assume the netmem is readable and/or backed by pages.
    The netmem returned by the page_pool may be unreadable, in which case
diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
index 255ce4cfd975..d18ec079ffe2 100644
--- a/include/net/page_pool/memory_provider.h
+++ b/include/net/page_pool/memory_provider.h
@@ -9,6 +9,15 @@ struct netdev_rx_queue;
 struct netlink_ext_ack;
 struct sk_buff;
 
+/**
+ * enum mp_caps - memory provider capabilities
+ * @MP_CAP_READABLE: The CPU can access provider buffers. They may back
+ *	header and regular page pools, and XDP programs may run on them.
+ */
+enum mp_caps {
+	MP_CAP_READABLE		= BIT(0),
+};
+
 struct memory_provider_ops {
 	netmem_ref (*alloc_netmems)(struct page_pool *pool, gfp_t gfp);
 	bool (*release_netmem)(struct page_pool *pool, netmem_ref netmem);
@@ -17,11 +26,13 @@ struct memory_provider_ops {
 	int (*nl_fill)(void *mp_priv, struct sk_buff *rsp,
 		       struct netdev_rx_queue *rxq);
 	void (*uninstall)(void *mp_priv, struct netdev_rx_queue *rxq);
+	u32 caps;
 };
 
 bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr);
 void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov);
 void net_mp_niov_clear_page_pool(struct net_iov *niov);
+bool netif_mp_lacks_cap(struct net_device *dev, u32 cap);
 
 int netif_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 		      const struct pp_memory_provider_params *p,
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 03da138722f5..a96376613dda 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -22,9 +22,10 @@
 					*/
 #define PP_FLAG_SYSTEM_POOL	BIT(2) /* Global system page_pool */
 
-/* Allow unreadable (net_iov backed) netmem in this page_pool. Drivers setting
- * this must be able to support unreadable netmem, where netmem_address() would
- * return NULL. This flag should not be set for header page_pools.
+/* Allow memory-provider (net_iov backed) netmem in this page_pool. Drivers
+ * setting this must honor the provider's capabilities. Unless the provider has
+ * MP_CAP_READABLE, netmem_address() returns NULL, and the flag must not be set
+ * for a header page_pool.
  *
  * If the driver sets PP_FLAG_ALLOW_UNREADABLE_NETMEM, it should also set
  * page_pool_params.slow.queue_idx.
diff --git a/net/core/dev.c b/net/core/dev.c
index 5ac08da8b9d7..12b532c09a9c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10423,7 +10423,7 @@ int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 		return -EBUSY;
 	}
 
-	if (dev_get_min_mp_channel_count(dev)) {
+	if (netif_mp_lacks_cap(dev, MP_CAP_READABLE)) {
 		NL_SET_ERR_MSG(bpf->extack, "unable to propagate XDP to device using memory provider");
 		return -EBUSY;
 	}
@@ -10499,7 +10499,7 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
 		return -EBUSY;
 	}
 
-	if (dev_get_min_mp_channel_count(dev)) {
+	if (netif_mp_lacks_cap(dev, MP_CAP_READABLE)) {
 		NL_SET_ERR_MSG(extack, "unable to install XDP to device using memory provider");
 		return -EBUSY;
 	}
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index 00a7011eb4d5..610e31d1a717 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -82,8 +82,12 @@ __netif_get_rx_queue_lease(struct net_device **dev, unsigned int *rxq_idx,
 /* See also page_pool_is_unreadable() */
 bool netif_rxq_has_unreadable_mp(struct net_device *dev, unsigned int rxq_idx)
 {
-	if (rxq_idx < dev->real_num_rx_queues)
-		return __netif_get_rx_queue(dev, rxq_idx)->mp_params.mp_ops;
+	const struct memory_provider_ops *ops;
+
+	if (rxq_idx < dev->real_num_rx_queues) {
+		ops = __netif_get_rx_queue(dev, rxq_idx)->mp_params.mp_ops;
+		return ops && !(ops->caps & MP_CAP_READABLE);
+	}
 	return false;
 }
 EXPORT_SYMBOL(netif_rxq_has_unreadable_mp);
@@ -95,6 +99,32 @@ bool netif_rxq_has_mp(struct net_device *dev, unsigned int rxq_idx)
 	return false;
 }
 
+/* Return true if an installed memory provider lacks @cap. */
+bool netif_mp_lacks_cap(struct net_device *dev, u32 cap)
+{
+	const struct memory_provider_ops *ops;
+	int i;
+
+	netdev_assert_locked_ops_compat(dev);
+
+	for (i = dev->real_num_rx_queues - 1; i >= 0; i--) {
+		ops = dev->_rx[i].mp_params.mp_ops;
+		if (ops && (ops->caps & cap) != cap)
+			return true;
+	}
+
+	return false;
+}
+
+/* Provider memory may become available while the queue is replaced,
+ * without a device event to report it.
+ */
+static void netdev_rx_queue_kick(struct netdev_rx_queue *rxq)
+{
+	if (rxq->mp_params.mp_ops && rxq->napi)
+		napi_schedule(rxq->napi);
+}
+
 static int netdev_rx_queue_reconfig(struct net_device *dev,
 				    unsigned int rxq_idx,
 				    struct netdev_queue_config *qcfg_old,
@@ -142,6 +172,8 @@ static int netdev_rx_queue_reconfig(struct net_device *dev,
 	}
 
 	qops->ndo_queue_mem_free(dev, old_mem);
+	if (netif_running(dev))
+		netdev_rx_queue_kick(rxq);
 
 	kvfree(old_mem);
 	kvfree(new_mem);
@@ -165,6 +197,11 @@ static int netdev_rx_queue_reconfig(struct net_device *dev,
 
 err_free_new_queue_mem:
 	qops->ndo_queue_mem_free(dev, new_mem);
+	/* Freeing the replacement can hand provider memory back to the old
+	 * queue, which still runs unless the rollback failed.
+	 */
+	if (err != -ENETDOWN && netif_running(dev))
+		netdev_rx_queue_kick(rxq);
 
 err_free_old_mem:
 	kvfree(old_mem);
@@ -189,6 +226,7 @@ static int __netif_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 			       struct netlink_ext_ack *extack)
 {
 	const struct netdev_queue_mgmt_ops *qops = dev->queue_mgmt_ops;
+	u32 caps = p->mp_ops->caps;
 	struct netdev_queue_config qcfg[2];
 	struct netdev_rx_queue *rxq;
 	int ret;
@@ -196,15 +234,13 @@ static int __netif_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 	if (!qops)
 		return -EOPNOTSUPP;
 
-	if (dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED) {
-		NL_SET_ERR_MSG(extack, "tcp-data-split is disabled");
+	if ((dev->cfg->hds_config != ETHTOOL_TCP_DATA_SPLIT_ENABLED ||
+	     dev->cfg->hds_thresh) && !(caps & MP_CAP_READABLE)) {
+		NL_SET_ERR_MSG(extack,
+			       "memory provider does not support current tcp-data-split configuration");
 		return -EINVAL;
 	}
-	if (dev->cfg->hds_thresh) {
-		NL_SET_ERR_MSG(extack, "hds-thresh is not zero");
-		return -EINVAL;
-	}
-	if (dev_xdp_prog_count(dev)) {
+	if (dev_xdp_prog_count(dev) && !(caps & MP_CAP_READABLE)) {
 		NL_SET_ERR_MSG(extack, "unable to custom memory provider to device with XDP program attached");
 		return -EEXIST;
 	}
@@ -219,7 +255,8 @@ static int __netif_mp_open_rxq(struct net_device *dev, unsigned int rxq_idx,
 		return -EEXIST;
 	}
 #ifdef CONFIG_XDP_SOCKETS
-	if (rxq->pool) {
+	/* An AF_XDP pool owns the queue unless it is this provider. */
+	if (rxq->pool && rxq->pool != p->mp_priv) {
 		NL_SET_ERR_MSG(extack, "designated queue already in use by AF_XDP");
 		return -EBUSY;
 	}
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index e3810c0320e3..789d0e328b77 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
 #include <net/netdev_queues.h>
+#include <net/page_pool/memory_provider.h>
 
 #include "common.h"
 #include "netlink.h"
@@ -258,17 +259,12 @@ ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	if (dev_get_min_mp_channel_count(dev)) {
-		if (kernel_ringparam.tcp_data_split !=
-		    ETHTOOL_TCP_DATA_SPLIT_ENABLED) {
-			NL_SET_ERR_MSG(info->extack,
-				       "can't disable tcp-data-split while device has memory provider enabled");
-			return -EINVAL;
-		} else if (kernel_ringparam.hds_thresh) {
-			NL_SET_ERR_MSG(info->extack,
-				       "can't set non-zero hds_thresh while device is memory provider enabled");
-			return -EINVAL;
-		}
+	if ((kernel_ringparam.tcp_data_split !=
+	     ETHTOOL_TCP_DATA_SPLIT_ENABLED || kernel_ringparam.hds_thresh) &&
+	    netif_mp_lacks_cap(dev, MP_CAP_READABLE)) {
+		NL_SET_ERR_MSG(info->extack,
+			       "memory provider does not support requested tcp-data-split configuration");
+		return -EINVAL;
 	}
 
 	/* ensure new ring parameters are within limits */
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 9d2d94f1fb75..f01e1de7360e 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -2,6 +2,7 @@
 
 #include <linux/netdevice.h>
 #include <net/netdev_lock.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/xsk_buff_pool.h>
 #include <net/xdp_sock.h>
 #include <net/xdp_sock_drv.h>
@@ -235,7 +236,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
 		goto err_unreg_pool;
 	}
 
-	if (dev_get_min_mp_channel_count(netdev)) {
+	if (netif_mp_lacks_cap(netdev, MP_CAP_READABLE)) {
 		err = -EBUSY;
 		goto err_unreg_pool;
 	}
-- 
2.55.0


  parent reply	other threads:[~2026-10-02 19:00 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-10-02 19:00 [RFC net-next 00/15] xsk: Zero copy through page-pool memory providers Björn Töpel
2026-10-02 19:00 ` [RFC net-next 01/15] xdp: Size zero-copy skb heads by their contents Björn Töpel
2026-10-02 19:00 ` [RFC net-next 02/15] eth: fbnic: Report the logical XDP RX queue Björn Töpel
2026-10-02 19:00 ` Björn Töpel [this message]
2026-10-02 19:00 ` [RFC net-next 04/15] net: Let memory providers set RX buffer headroom Björn Töpel
2026-10-02 19:00 ` [RFC net-next 05/15] page_pool: Extend memory provider operations Björn Töpel
2026-10-02 19:00 ` [RFC net-next 06/15] xdp: Track non-page netmem in receive buffers Björn Töpel
2026-10-02 19:00 ` [RFC net-next 07/15] xsk: Keep the DMA mapping in the buffer pool Björn Töpel
2026-10-02 19:00 ` [RFC net-next 08/15] xsk: Handle a detached FILL ring in RX wakeup Björn Töpel
2026-10-02 19:00 ` [RFC net-next 09/15] xsk: Add a page-pool memory provider for UMEM Björn Töpel
2026-10-02 19:00 ` [RFC net-next 10/15] xsk: Add RX helpers for page-pool drivers Björn Töpel
2026-10-02 19:00 ` [RFC net-next 11/15] xdp: Copy provider buffers on pass and redirect Björn Töpel
2026-10-02 19:00 ` [RFC net-next 12/15] xsk: Receive provider UMEM without copying Björn Töpel
2026-10-02 19:00 ` [RFC net-next 13/15] eth: fbnic: Support AF_XDP zero-copy receive Björn Töpel
2026-10-02 19:00 ` [RFC net-next 14/15] eth: fbnic: Support AF_XDP zero-copy transmit Björn Töpel
2026-10-02 19:00 ` [RFC net-next 15/15] Documentation: xsk: Document page-pool zero copy Björn Töpel

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 \
    --in-reply-to=20261002190018.696925-4-bjorn@kernel.org \
    --to=bjorn@kernel.org \
    --cc=aleksander.lobakin@intel.com \
    --cc=alexanderduyck@fb.com \
    --cc=almasrymina@google.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=andrii@kernel.org \
    --cc=asml.silence@gmail.com \
    --cc=ast@kernel.org \
    --cc=axboe@kernel.dk \
    --cc=bestswngs@gmail.com \
    --cc=bpf@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dw@davidwei.uk \
    --cc=eddyz87@gmail.com \
    --cc=edumazet@kernel.org \
    --cc=emil@etsalapatis.com \
    --cc=hawk@kernel.org \
    --cc=horms@kernel.org \
    --cc=ihor.solodrai@linux.dev \
    --cc=ilias.apalodimas@linaro.org \
    --cc=io-uring@vger.kernel.org \
    --cc=john.fastabend@gmail.com \
    --cc=jolsa@kernel.org \
    --cc=kernel-team@meta.com \
    --cc=kuba@kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maciej.fijalkowski@intel.com \
    --cc=magnus.karlsson@intel.com \
    --cc=martin.lau@linux.dev \
    --cc=memxor@gmail.com \
    --cc=mike.marciniszyn@gmail.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=razor@blackwall.org \
    --cc=rdunlap@infradead.org \
    --cc=sdf@fomichev.me \
    --cc=skhan@linuxfoundation.org \
    --cc=song@kernel.org \
    --cc=yonghong.song@linux.dev \
    /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

all inboxes | Powered by JetHome®