From: Byungchul Park <byungchul@sk.com>
To: willy@infradead.org, netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
kernel_team@skhynix.com, almasrymina@google.com,
ilias.apalodimas@linaro.org, harry.yoo@oracle.com,
akpm@linux-foundation.org, andrew+netdev@lunn.ch,
asml.silence@gmail.com, toke@redhat.com, david@redhat.com,
Liam.Howlett@oracle.com, vbabka@suse.cz, rppt@kernel.org,
surenb@google.com, mhocko@suse.com, linux-rdma@vger.kernel.org,
bpf@vger.kernel.org, vishal.moola@gmail.com, hannes@cmpxchg.org,
ziy@nvidia.com, jackmanb@google.com, wei.fang@nxp.com,
shenwei.wang@nxp.com, xiaoning.wang@nxp.com, davem@davemloft.net,
edumazet@google.com, kuba@kernel.org, pabeni@redhat.com,
anthony.l.nguyen@intel.com, przemyslaw.kitszel@intel.com,
sgoutham@marvell.com, gakula@marvell.com, sbhatta@marvell.com,
hkelam@marvell.com, bbhushan2@marvell.com, tariqt@nvidia.com,
ast@kernel.org, daniel@iogearbox.net, hawk@kernel.org,
john.fastabend@gmail.com, sdf@fomichev.me, saeedm@nvidia.com,
leon@kernel.org, mbloch@nvidia.com, danishanwar@ti.com,
rogerq@kernel.org, nbd@nbd.name, lorenzo@kernel.org,
ryder.lee@mediatek.com, shayne.chen@mediatek.com,
sean.wang@mediatek.com, matthias.bgg@gmail.com,
angelogioacchino.delregno@collabora.com,
aleksander.lobakin@intel.com, horms@kernel.org, m-malladi@ti.com,
krzysztof.kozlowski@linaro.org,
matthias.schiffer@ew.tq-group.com, robh@kernel.org,
imx@lists.linux.dev, intel-wired-lan@lists.osuosl.org,
linux-arm-kernel@lists.infradead.org,
linux-wireless@vger.kernel.org,
linux-mediatek@lists.infradead.org
Subject: [PATCH net-next v11 01/12] netmem: introduce struct netmem_desc mirroring struct page
Date: Thu, 17 Jul 2025 16:00:41 +0900 [thread overview]
Message-ID: <20250717070052.6358-2-byungchul@sk.com> (raw)
In-Reply-To: <20250717070052.6358-1-byungchul@sk.com>
To simplify struct page, the page pool members of struct page should be
moved to other, allowing these members to be removed from struct page.
Introduce a network memory descriptor to store the members, struct
netmem_desc, and make it union'ed with the existing fields in struct
net_iov, allowing to organize the fields of struct net_iov.
Signed-off-by: Byungchul Park <byungchul@sk.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
---
include/net/netmem.h | 116 +++++++++++++++++++++++++++++++++++--------
1 file changed, 95 insertions(+), 21 deletions(-)
diff --git a/include/net/netmem.h b/include/net/netmem.h
index de1d95f04076..535cf17b9134 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -12,6 +12,50 @@
#include <linux/mm.h>
#include <net/net_debug.h>
+/* These fields in struct page are used by the page_pool and net stack:
+ *
+ * struct {
+ * unsigned long pp_magic;
+ * struct page_pool *pp;
+ * unsigned long _pp_mapping_pad;
+ * unsigned long dma_addr;
+ * atomic_long_t pp_ref_count;
+ * };
+ *
+ * We mirror the page_pool fields here so the page_pool can access these
+ * fields without worrying whether the underlying fields belong to a
+ * page or netmem_desc.
+ *
+ * CAUTION: Do not update the fields in netmem_desc without also
+ * updating the anonymous aliasing union in struct net_iov.
+ */
+struct netmem_desc {
+ unsigned long _flags;
+ unsigned long pp_magic;
+ struct page_pool *pp;
+ unsigned long _pp_mapping_pad;
+ unsigned long dma_addr;
+ atomic_long_t pp_ref_count;
+};
+
+#define NETMEM_DESC_ASSERT_OFFSET(pg, desc) \
+ static_assert(offsetof(struct page, pg) == \
+ offsetof(struct netmem_desc, desc))
+NETMEM_DESC_ASSERT_OFFSET(flags, _flags);
+NETMEM_DESC_ASSERT_OFFSET(pp_magic, pp_magic);
+NETMEM_DESC_ASSERT_OFFSET(pp, pp);
+NETMEM_DESC_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad);
+NETMEM_DESC_ASSERT_OFFSET(dma_addr, dma_addr);
+NETMEM_DESC_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
+#undef NETMEM_DESC_ASSERT_OFFSET
+
+/*
+ * Since struct netmem_desc uses the space in struct page, the size
+ * should be checked, until struct netmem_desc has its own instance from
+ * slab, to avoid conflicting with other members within struct page.
+ */
+static_assert(sizeof(struct netmem_desc) <= offsetof(struct page, _refcount));
+
/* net_iov */
DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
@@ -30,13 +74,48 @@ enum net_iov_type {
NET_IOV_MAX = ULONG_MAX
};
+/* A memory descriptor representing abstract networking I/O vectors,
+ * generally for non-pages memory that doesn't have its corresponding
+ * struct page and needs to be explicitly allocated through slab.
+ *
+ * net_iovs are allocated and used by networking code, and the size of
+ * the chunk is PAGE_SIZE.
+ *
+ * This memory can be any form of non-struct paged memory. Examples
+ * include imported dmabuf memory and imported io_uring memory. See
+ * net_iov_type for all the supported types.
+ *
+ * @pp_magic: pp field, similar to the one in struct page/struct
+ * netmem_desc.
+ * @pp: the pp this net_iov belongs to, if any.
+ * @dma_addr: the dma addrs of the net_iov. Needed for the network
+ * card to send/receive this net_iov.
+ * @pp_ref_count: the pp ref count of this net_iov, exactly the same
+ * usage as struct page/struct netmem_desc.
+ * @owner: the net_iov_area this net_iov belongs to, if any.
+ * @type: the type of the memory. Different types of net_iovs are
+ * supported.
+ */
struct net_iov {
- enum net_iov_type type;
- unsigned long pp_magic;
- struct page_pool *pp;
+ union {
+ struct netmem_desc desc;
+
+ /* XXX: The following part should be removed once all
+ * the references to them are converted so as to be
+ * accessed via netmem_desc e.g. niov->desc.pp instead
+ * of niov->pp.
+ */
+ struct {
+ unsigned long _flags;
+ unsigned long pp_magic;
+ struct page_pool *pp;
+ unsigned long _pp_mapping_pad;
+ unsigned long dma_addr;
+ atomic_long_t pp_ref_count;
+ };
+ };
struct net_iov_area *owner;
- unsigned long dma_addr;
- atomic_long_t pp_ref_count;
+ enum net_iov_type type;
};
struct net_iov_area {
@@ -48,27 +127,22 @@ struct net_iov_area {
unsigned long base_virtual;
};
-/* These fields in struct page are used by the page_pool and net stack:
+/* net_iov is union'ed with struct netmem_desc mirroring struct page, so
+ * the page_pool can access these fields without worrying whether the
+ * underlying fields are accessed via netmem_desc or directly via
+ * net_iov, until all the references to them are converted so as to be
+ * accessed via netmem_desc e.g. niov->desc.pp instead of niov->pp.
*
- * struct {
- * unsigned long pp_magic;
- * struct page_pool *pp;
- * unsigned long _pp_mapping_pad;
- * unsigned long dma_addr;
- * atomic_long_t pp_ref_count;
- * };
- *
- * We mirror the page_pool fields here so the page_pool can access these fields
- * without worrying whether the underlying fields belong to a page or net_iov.
- *
- * The non-net stack fields of struct page are private to the mm stack and must
- * never be mirrored to net_iov.
+ * The non-net stack fields of struct page are private to the mm stack
+ * and must never be mirrored to net_iov.
*/
-#define NET_IOV_ASSERT_OFFSET(pg, iov) \
- static_assert(offsetof(struct page, pg) == \
+#define NET_IOV_ASSERT_OFFSET(desc, iov) \
+ static_assert(offsetof(struct netmem_desc, desc) == \
offsetof(struct net_iov, iov))
+NET_IOV_ASSERT_OFFSET(_flags, _flags);
NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic);
NET_IOV_ASSERT_OFFSET(pp, pp);
+NET_IOV_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad);
NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
#undef NET_IOV_ASSERT_OFFSET
--
2.17.1
next prev parent reply other threads:[~2025-07-17 7:01 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-17 7:00 [PATCH net-next v11 00/12] Split netmem from struct page Byungchul Park
2025-07-17 7:00 ` Byungchul Park [this message]
2025-07-17 7:00 ` [PATCH net-next v11 02/12] netmem: use netmem_desc instead of page to access ->pp in __netmem_get_pp() Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 03/12] netmem, mlx4: access ->pp_ref_count through netmem_desc instead of page Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 04/12] netdevsim: access ->pp " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 05/12] mt76: " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 06/12] net: fec: " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 07/12] octeontx2-pf: " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 08/12] iavf: " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 09/12] idpf: " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 10/12] mlx5: " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 11/12] net: ti: icssg-prueth: " Byungchul Park
2025-07-17 7:00 ` [PATCH net-next v11 12/12] libeth: xdp: " Byungchul Park
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=20250717070052.6358-2-byungchul@sk.com \
--to=byungchul@sk.com \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=aleksander.lobakin@intel.com \
--cc=almasrymina@google.com \
--cc=andrew+netdev@lunn.ch \
--cc=angelogioacchino.delregno@collabora.com \
--cc=anthony.l.nguyen@intel.com \
--cc=asml.silence@gmail.com \
--cc=ast@kernel.org \
--cc=bbhushan2@marvell.com \
--cc=bpf@vger.kernel.org \
--cc=daniel@iogearbox.net \
--cc=danishanwar@ti.com \
--cc=davem@davemloft.net \
--cc=david@redhat.com \
--cc=edumazet@google.com \
--cc=gakula@marvell.com \
--cc=hannes@cmpxchg.org \
--cc=harry.yoo@oracle.com \
--cc=hawk@kernel.org \
--cc=hkelam@marvell.com \
--cc=horms@kernel.org \
--cc=ilias.apalodimas@linaro.org \
--cc=imx@lists.linux.dev \
--cc=intel-wired-lan@lists.osuosl.org \
--cc=jackmanb@google.com \
--cc=john.fastabend@gmail.com \
--cc=kernel_team@skhynix.com \
--cc=krzysztof.kozlowski@linaro.org \
--cc=kuba@kernel.org \
--cc=leon@kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mediatek@lists.infradead.org \
--cc=linux-mm@kvack.org \
--cc=linux-rdma@vger.kernel.org \
--cc=linux-wireless@vger.kernel.org \
--cc=lorenzo@kernel.org \
--cc=m-malladi@ti.com \
--cc=matthias.bgg@gmail.com \
--cc=matthias.schiffer@ew.tq-group.com \
--cc=mbloch@nvidia.com \
--cc=mhocko@suse.com \
--cc=nbd@nbd.name \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=przemyslaw.kitszel@intel.com \
--cc=robh@kernel.org \
--cc=rogerq@kernel.org \
--cc=rppt@kernel.org \
--cc=ryder.lee@mediatek.com \
--cc=saeedm@nvidia.com \
--cc=sbhatta@marvell.com \
--cc=sdf@fomichev.me \
--cc=sean.wang@mediatek.com \
--cc=sgoutham@marvell.com \
--cc=shayne.chen@mediatek.com \
--cc=shenwei.wang@nxp.com \
--cc=surenb@google.com \
--cc=tariqt@nvidia.com \
--cc=toke@redhat.com \
--cc=vbabka@suse.cz \
--cc=vishal.moola@gmail.com \
--cc=wei.fang@nxp.com \
--cc=willy@infradead.org \
--cc=xiaoning.wang@nxp.com \
--cc=ziy@nvidia.com \
/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;
as well as URLs for NNTP newsgroup(s).