From: Mina Almasry <almasrymina@google.com>
To: netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-doc@vger.kernel.org, virtualization@lists.linux.dev,
kvm@vger.kernel.org, linux-kselftest@vger.kernel.org
Cc: "Mina Almasry" <almasrymina@google.com>,
"David S. Miller" <davem@davemloft.net>,
"Eric Dumazet" <edumazet@google.com>,
"Jakub Kicinski" <kuba@kernel.org>,
"Paolo Abeni" <pabeni@redhat.com>,
"Simon Horman" <horms@kernel.org>,
"Donald Hunter" <donald.hunter@gmail.com>,
"Jonathan Corbet" <corbet@lwn.net>,
"Andrew Lunn" <andrew+netdev@lunn.ch>,
"David Ahern" <dsahern@kernel.org>,
"Michael S. Tsirkin" <mst@redhat.com>,
"Jason Wang" <jasowang@redhat.com>,
"Xuan Zhuo" <xuanzhuo@linux.alibaba.com>,
"Eugenio Pérez" <eperezma@redhat.com>,
"Stefan Hajnoczi" <stefanha@redhat.com>,
"Stefano Garzarella" <sgarzare@redhat.com>,
"Shuah Khan" <shuah@kernel.org>,
"Kaiyuan Zhang" <kaiyuanz@google.com>,
"Pavel Begunkov" <asml.silence@gmail.com>,
"Willem de Bruijn" <willemb@google.com>,
"Samiullah Khawaja" <skhawaja@google.com>,
"Stanislav Fomichev" <sdf@fomichev.me>,
"Joe Damato" <jdamato@fastly.com>,
dw@davidwei.uk
Subject: [PATCH RFC net-next v1 3/5] net: add get_netmem/put_netmem support
Date: Sat, 21 Dec 2024 00:42:34 +0000 [thread overview]
Message-ID: <20241221004236.2629280-4-almasrymina@google.com> (raw)
In-Reply-To: <20241221004236.2629280-1-almasrymina@google.com>
Currently net_iovs support only pp ref counts, and do not support a
page ref equivalent.
This is fine for the RX path as net_iovs are used exclusively with the
pp and only pp refcounting is needed there. The TX path however does not
use pp ref counts, thus, support for get_page/put_page equivalent is
needed for netmem.
Support get_netmem/put_netmem. Check the type of the netmem before
passing it to page or net_iov specific code to obtain a page ref
equivalent.
For dmabuf net_iovs, we obtain a ref on the underlying binding. This
ensures the entire binding doesn't disappear until all the net_iovs have
been put_netmem'ed. We do not need to track the refcount of individual
dmabuf net_iovs as we don't allocate/free them from a pool similar to
what the buddy allocator does for pages.
This code is written to be extensible by other net_iov implementers.
get_netmem/put_netmem will check the type of the netmem and route it to
the correct helper:
pages -> [get|put]_page()
dmabuf net_iovs -> net_devmem_[get|put]_net_iov()
new net_iovs -> new helpers
Signed-off-by: Mina Almasry <almasrymina@google.com>
---
include/linux/skbuff_ref.h | 4 ++--
include/net/netmem.h | 3 +++
net/core/devmem.c | 10 ++++++++++
net/core/devmem.h | 11 +++++++++++
net/core/skbuff.c | 30 ++++++++++++++++++++++++++++++
5 files changed, 56 insertions(+), 2 deletions(-)
diff --git a/include/linux/skbuff_ref.h b/include/linux/skbuff_ref.h
index 0f3c58007488..9e49372ef1a0 100644
--- a/include/linux/skbuff_ref.h
+++ b/include/linux/skbuff_ref.h
@@ -17,7 +17,7 @@
*/
static inline void __skb_frag_ref(skb_frag_t *frag)
{
- get_page(skb_frag_page(frag));
+ get_netmem(skb_frag_netmem(frag));
}
/**
@@ -40,7 +40,7 @@ static inline void skb_page_unref(netmem_ref netmem, bool recycle)
if (recycle && napi_pp_put_page(netmem))
return;
#endif
- put_page(netmem_to_page(netmem));
+ put_netmem(netmem);
}
/**
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 1b58faa4f20f..d30f31878a09 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -245,4 +245,7 @@ static inline unsigned long netmem_get_dma_addr(netmem_ref netmem)
return __netmem_clear_lsb(netmem)->dma_addr;
}
+void get_netmem(netmem_ref netmem);
+void put_netmem(netmem_ref netmem);
+
#endif /* _NET_NETMEM_H */
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 0b6ed7525b22..f7e06a8cba01 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -322,6 +322,16 @@ void dev_dmabuf_uninstall(struct net_device *dev)
}
}
+void net_devmem_get_net_iov(struct net_iov *niov)
+{
+ net_devmem_dmabuf_binding_get(niov->owner->binding);
+}
+
+void net_devmem_put_net_iov(struct net_iov *niov)
+{
+ net_devmem_dmabuf_binding_put(niov->owner->binding);
+}
+
/*** "Dmabuf devmem memory provider" ***/
int mp_dmabuf_devmem_init(struct page_pool *pool)
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 76099ef9c482..54e30fea80b3 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -119,6 +119,9 @@ net_devmem_dmabuf_binding_put(struct net_devmem_dmabuf_binding *binding)
__net_devmem_dmabuf_binding_free(binding);
}
+void net_devmem_get_net_iov(struct net_iov *niov);
+void net_devmem_put_net_iov(struct net_iov *niov);
+
struct net_iov *
net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
void net_devmem_free_dmabuf(struct net_iov *ppiov);
@@ -126,6 +129,14 @@ void net_devmem_free_dmabuf(struct net_iov *ppiov);
#else
struct net_devmem_dmabuf_binding;
+static inline void net_devmem_get_net_iov(struct net_iov *niov)
+{
+}
+
+static inline void net_devmem_put_net_iov(struct net_iov *niov)
+{
+}
+
static inline void
__net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
{
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a441613a1e6c..815245d5c36b 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -88,6 +88,7 @@
#include <linux/textsearch.h>
#include "dev.h"
+#include "devmem.h"
#include "netmem_priv.h"
#include "sock_destructor.h"
@@ -7290,3 +7291,32 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes,
return false;
}
EXPORT_SYMBOL(csum_and_copy_from_iter_full);
+
+void get_netmem(netmem_ref netmem)
+{
+ if (netmem_is_net_iov(netmem)) {
+ /* Assume any net_iov is devmem and route it to
+ * net_devmem_get_net_iov. As new net_iov types are added they
+ * need to be checked here.
+ */
+ net_devmem_get_net_iov(netmem_to_net_iov(netmem));
+ return;
+ }
+ get_page(netmem_to_page(netmem));
+}
+EXPORT_SYMBOL(get_netmem);
+
+void put_netmem(netmem_ref netmem)
+{
+ if (netmem_is_net_iov(netmem)) {
+ /* Assume any net_iov is devmem and route it to
+ * net_devmem_put_net_iov. As new net_iov types are added they
+ * need to be checked here.
+ */
+ net_devmem_put_net_iov(netmem_to_net_iov(netmem));
+ return;
+ }
+
+ put_page(netmem_to_page(netmem));
+}
+EXPORT_SYMBOL(put_netmem);
--
2.47.1.613.gc27f4b7a9f-goog
next prev parent reply other threads:[~2024-12-21 0:51 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-12-21 0:42 [PATCH RFC net-next v1 0/5] Device memory TCP TX Mina Almasry
2024-12-21 0:42 ` [PATCH RFC net-next v1 1/5] net: add devmem TCP TX documentation Mina Almasry
2024-12-21 4:56 ` Stanislav Fomichev
2025-01-27 22:45 ` Mina Almasry
2025-01-28 3:51 ` Stanislav Fomichev
2024-12-21 0:42 ` [PATCH RFC net-next v1 2/5] selftests: ncdevmem: Implement devmem TCP TX Mina Almasry
2024-12-21 4:57 ` Stanislav Fomichev
2024-12-26 21:24 ` Willem de Bruijn
2024-12-21 0:42 ` Mina Almasry [this message]
2024-12-26 19:07 ` [PATCH RFC net-next v1 3/5] net: add get_netmem/put_netmem support Stanislav Fomichev
2025-01-27 22:47 ` Mina Almasry
2024-12-21 0:42 ` [PATCH RFC net-next v1 4/5] net: devmem TCP tx netlink api Mina Almasry
2024-12-21 0:42 ` [PATCH RFC net-next v1 5/5] net: devmem: Implement TX path Mina Almasry
2024-12-21 5:09 ` Stanislav Fomichev
2024-12-26 19:10 ` Stanislav Fomichev
2025-01-27 22:52 ` Mina Almasry
2024-12-26 21:52 ` Willem de Bruijn
2025-01-28 0:06 ` Mina Almasry
2025-01-28 14:49 ` Willem de Bruijn
2025-02-05 12:41 ` Pavel Begunkov
2025-02-05 20:22 ` Mina Almasry
2025-02-05 22:16 ` Pavel Begunkov
2025-02-05 22:22 ` Pavel Begunkov
2025-02-10 21:14 ` Mina Almasry
2024-12-28 19:28 ` David Ahern
2024-12-21 4:53 ` [PATCH RFC net-next v1 0/5] Device memory TCP TX Stanislav Fomichev
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=20241221004236.2629280-4-almasrymina@google.com \
--to=almasrymina@google.com \
--cc=andrew+netdev@lunn.ch \
--cc=asml.silence@gmail.com \
--cc=corbet@lwn.net \
--cc=davem@davemloft.net \
--cc=donald.hunter@gmail.com \
--cc=dsahern@kernel.org \
--cc=dw@davidwei.uk \
--cc=edumazet@google.com \
--cc=eperezma@redhat.com \
--cc=horms@kernel.org \
--cc=jasowang@redhat.com \
--cc=jdamato@fastly.com \
--cc=kaiyuanz@google.com \
--cc=kuba@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=sdf@fomichev.me \
--cc=sgarzare@redhat.com \
--cc=shuah@kernel.org \
--cc=skhawaja@google.com \
--cc=stefanha@redhat.com \
--cc=virtualization@lists.linux.dev \
--cc=willemb@google.com \
--cc=xuanzhuo@linux.alibaba.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