netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bobby Eshleman <bobbyeshleman@gmail.com>
To: "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>,
	 Kuniyuki Iwashima <kuniyu@google.com>,
	 Willem de Bruijn <willemb@google.com>,
	Neal Cardwell <ncardwell@google.com>,
	 David Ahern <dsahern@kernel.org>, Arnd Bergmann <arnd@arndb.de>,
	 Jonathan Corbet <corbet@lwn.net>,
	Andrew Lunn <andrew+netdev@lunn.ch>,
	 Shuah Khan <shuah@kernel.org>,
	Mina Almasry <almasrymina@google.com>
Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
	 linux-arch@vger.kernel.org, linux-doc@vger.kernel.org,
	 linux-kselftest@vger.kernel.org,
	Stanislav Fomichev <sdf@fomichev.me>,
	 Bobby Eshleman <bobbyeshleman@meta.com>
Subject: [PATCH net-next v6 4/6] net: devmem: add SO_DEVMEM_AUTORELEASE for autorelease control
Date: Tue, 04 Nov 2025 17:23:23 -0800	[thread overview]
Message-ID: <20251104-scratch-bobbyeshleman-devmem-tcp-token-upstream-v6-4-ea98cf4d40b3@meta.com> (raw)
In-Reply-To: <20251104-scratch-bobbyeshleman-devmem-tcp-token-upstream-v6-0-ea98cf4d40b3@meta.com>

From: Bobby Eshleman <bobbyeshleman@meta.com>

Add SO_DEVMEM_AUTORELEASE socket option to allow applications to
control token release behavior on a per-socket basis.

The socket option accepts boolean values (0 or 1):
- 1 (true): outstanding tokens are automatically released when the
  socket closes
- 0 (false): outstanding tokens are released when the dmabuf is unbound

The option can only be changed when the socket has no outstanding
tokens, enforced by checking:
1. The frags xarray is empty (no tokens in autorelease mode)
2. The outstanding_urefs counter is zero (no tokens in manual mode)

This restriction prevents inconsistent token tracking state between
acquisition and release calls. If either condition fails, setsockopt
returns -EBUSY.

The default state is autorelease off.

Signed-off-by: Bobby Eshleman <bobbyeshleman@meta.com>
---
 include/uapi/asm-generic/socket.h       |  2 ++
 net/core/sock.c                         | 51 +++++++++++++++++++++++++++++++++
 net/ipv4/tcp.c                          |  2 +-
 tools/include/uapi/asm-generic/socket.h |  2 ++
 4 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 53b5a8c002b1..59302318bb34 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -150,6 +150,8 @@
 #define SO_INQ			84
 #define SCM_INQ			SO_INQ
 
+#define SO_DEVMEM_AUTORELEASE	85
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))
diff --git a/net/core/sock.c b/net/core/sock.c
index 465645c1d74f..27af476f3cd3 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1160,6 +1160,46 @@ sock_devmem_dontneed_autorelease(struct sock *sk, struct dmabuf_token *tokens,
 	return ret;
 }
 
+static noinline_for_stack int
+sock_devmem_set_autorelease(struct sock *sk, sockptr_t optval, unsigned int optlen)
+{
+	int val;
+
+	if (!sk_is_tcp(sk))
+		return -EBADF;
+
+	if (optlen < sizeof(int))
+		return -EINVAL;
+
+	if (copy_from_sockptr(&val, optval, sizeof(val)))
+		return -EFAULT;
+
+	/* Validate that val is 0 or 1 */
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	sockopt_lock_sock(sk);
+
+	/* Can only change autorelease if:
+	 * 1. No tokens in the frags xarray (autorelease mode)
+	 * 2. No outstanding urefs (manual release mode)
+	 */
+	if (!xa_empty(&sk->sk_devmem_info.frags)) {
+		sockopt_release_sock(sk);
+		return -EBUSY;
+	}
+
+	if (atomic_read(&sk->sk_devmem_info.outstanding_urefs) > 0) {
+		sockopt_release_sock(sk);
+		return -EBUSY;
+	}
+
+	sk->sk_devmem_info.autorelease = !!val;
+
+	sockopt_release_sock(sk);
+	return 0;
+}
+
 static noinline_for_stack int
 sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
 {
@@ -1351,6 +1391,9 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 #ifdef CONFIG_PAGE_POOL
 	case SO_DEVMEM_DONTNEED:
 		return sock_devmem_dontneed(sk, optval, optlen);
+
+	case SO_DEVMEM_AUTORELEASE:
+		return sock_devmem_set_autorelease(sk, optval, optlen);
 #endif
 	case SO_SNDTIMEO_OLD:
 	case SO_SNDTIMEO_NEW:
@@ -2208,6 +2251,14 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		v.val = READ_ONCE(sk->sk_txrehash);
 		break;
 
+#ifdef CONFIG_PAGE_POOL
+	case SO_DEVMEM_AUTORELEASE:
+		if (!sk_is_tcp(sk))
+			return -EBADF;
+		v.val = sk->sk_devmem_info.autorelease;
+		break;
+#endif
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 052875c1b547..8226ba892b36 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -496,7 +496,7 @@ void tcp_init_sock(struct sock *sk)
 	xa_init_flags(&sk->sk_devmem_info.frags, XA_FLAGS_ALLOC1);
 	sk->sk_devmem_info.binding = NULL;
 	atomic_set(&sk->sk_devmem_info.outstanding_urefs, 0);
-	sk->sk_devmem_info.autorelease = true;
+	sk->sk_devmem_info.autorelease = false;
 }
 EXPORT_IPV6_MOD(tcp_init_sock);
 
diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index f333a0ac4ee4..9710a3d7cc4d 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -147,6 +147,8 @@
 
 #define SO_PASSRIGHTS		83
 
+#define SO_DEVMEM_AUTORELEASE	85
+
 #if !defined(__KERNEL__)
 
 #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__))

-- 
2.47.3


  parent reply	other threads:[~2025-11-05  1:23 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-05  1:23 [PATCH net-next v6 0/6] net: devmem: improve cpu cost of RX token management Bobby Eshleman
2025-11-05  1:23 ` [PATCH net-next v6 1/6] net: devmem: rename tx_vec to vec in dmabuf binding Bobby Eshleman
2025-11-05  1:23 ` [PATCH net-next v6 2/6] net: devmem: refactor sock_devmem_dontneed for autorelease split Bobby Eshleman
2025-11-05  1:23 ` [PATCH net-next v6 3/6] net: devmem: prepare for autorelease rx token management Bobby Eshleman
2025-11-05 16:02   ` kernel test robot
2025-11-05 20:55   ` kernel test robot
2025-11-06 15:11   ` Dan Carpenter
2025-11-06 15:14   ` Dan Carpenter
2025-11-05  1:23 ` Bobby Eshleman [this message]
2025-11-05 17:16   ` [PATCH net-next v6 4/6] net: devmem: add SO_DEVMEM_AUTORELEASE for autorelease control kernel test robot
2025-11-05  1:23 ` [PATCH net-next v6 5/6] net: devmem: document SO_DEVMEM_AUTORELEASE socket option Bobby Eshleman
2025-11-05 17:34   ` Stanislav Fomichev
2025-11-05 17:44     ` Mina Almasry
2025-11-05 19:31       ` Stanislav Fomichev
2025-11-05 23:17         ` Stanislav Fomichev
2025-11-07  2:22           ` Bobby Eshleman
2025-11-05 17:59     ` Bobby Eshleman
2025-11-05  1:23 ` [PATCH net-next v6 6/6] net: devmem: add tests for " Bobby Eshleman

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=20251104-scratch-bobbyeshleman-devmem-tcp-token-upstream-v6-4-ea98cf4d40b3@meta.com \
    --to=bobbyeshleman@gmail.com \
    --cc=almasrymina@google.com \
    --cc=andrew+netdev@lunn.ch \
    --cc=arnd@arndb.de \
    --cc=bobbyeshleman@meta.com \
    --cc=corbet@lwn.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=edumazet@google.com \
    --cc=horms@kernel.org \
    --cc=kuba@kernel.org \
    --cc=kuniyu@google.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=sdf@fomichev.me \
    --cc=shuah@kernel.org \
    --cc=willemb@google.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).