Received-SPF: pass (google.com: domain of linux-kernel+bounces-120114-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Date: Tue, 26 Mar 2024 15:50:43 -0700
In-Reply-To: <20240326225048.785801-1-almasrymina@google.com>
Precedence: bulk
Mime-Version: 1.0
References: <20240326225048.785801-1-almasrymina@google.com>
Message-ID: <20240326225048.785801-13-almasrymina@google.com>
Subject: [RFC PATCH net-next v7 12/14] net: add SO_DEVMEM_DONTNEED setsockopt
 to release RX frags
From: Mina Almasry <almasrymina@google.com>
To: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, 
	linux-doc@vger.kernel.org, linux-alpha@vger.kernel.org, 
	linux-mips@vger.kernel.org, linux-parisc@vger.kernel.org, 
	sparclinux@vger.kernel.org, linux-trace-kernel@vger.kernel.org, 
	linux-arch@vger.kernel.org, bpf@vger.kernel.org, 
	linux-kselftest@vger.kernel.org, linux-media@vger.kernel.org, 
	dri-devel@lists.freedesktop.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>, 
	Jonathan Corbet <corbet@lwn.net>, Richard Henderson <richard.henderson@linaro.org>, 
	Ivan Kokshaysky <ink@jurassic.park.msu.ru>, Matt Turner <mattst88@gmail.com>, 
	Thomas Bogendoerfer <tsbogend@alpha.franken.de>, 
	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>, Helge Deller <deller@gmx.de>, 
	Andreas Larsson <andreas@gaisler.com>, Jesper Dangaard Brouer <hawk@kernel.org>, 
	Ilias Apalodimas <ilias.apalodimas@linaro.org>, Steven Rostedt <rostedt@goodmis.org>, 
	Masami Hiramatsu <mhiramat@kernel.org>, Mathieu Desnoyers <mathieu.desnoyers@efficios.com>, 
	Arnd Bergmann <arnd@arndb.de>, Alexei Starovoitov <ast@kernel.org>, Daniel Borkmann <daniel@iogearbox.net>, 
	Andrii Nakryiko <andrii@kernel.org>, Martin KaFai Lau <martin.lau@linux.dev>, 
	Eduard Zingerman <eddyz87@gmail.com>, Song Liu <song@kernel.org>, 
	Yonghong Song <yonghong.song@linux.dev>, John Fastabend <john.fastabend@gmail.com>, 
	KP Singh <kpsingh@kernel.org>, Stanislav Fomichev <sdf@google.com>, Hao Luo <haoluo@google.com>, 
	Jiri Olsa <jolsa@kernel.org>, Steffen Klassert <steffen.klassert@secunet.com>, 
	Herbert Xu <herbert@gondor.apana.org.au>, David Ahern <dsahern@kernel.org>, 
	Willem de Bruijn <willemdebruijn.kernel@gmail.com>, Shuah Khan <shuah@kernel.org>, 
	Sumit Semwal <sumit.semwal@linaro.org>, 
	"=?UTF-8?q?Christian=20K=C3=B6nig?=" <christian.koenig@amd.com>, Pavel Begunkov <asml.silence@gmail.com>, 
	David Wei <dw@davidwei.uk>, Jason Gunthorpe <jgg@ziepe.ca>, Yunsheng Lin <linyunsheng@huawei.com>, 
	Shailend Chand <shailend@google.com>, Harshitha Ramamurthy <hramamurthy@google.com>, 
	Shakeel Butt <shakeel.butt@linux.dev>, Jeroen de Borst <jeroendb@google.com>, 
	Praveen Kaligineedi <pkaligineedi@google.com>, Willem de Bruijn <willemb@google.com>, 
	Kaiyuan Zhang <kaiyuanz@google.com>
Content-Type: text/plain; charset="UTF-8"

Add an interface for the user to notify the kernel that it is done
reading the devmem dmabuf frags returned as cmsg. The kernel will
drop the reference on the frags to make them available for reuse.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>

---

v7:
- Updated SO_DEVMEM_* uapi to use the next available entry (Arnd).

v6:
- Squash in locking optimizations from edumazet@google.com. With his
  changes we lock the xarray once per sock_devmem_dontneed operation
  rather than once per frag.

Changes in v1:
- devmemtoken -> dmabuf_token (David).
- Use napi_pp_put_page() for refcounting (Yunsheng).
- Fix build error with missing socket options on other asms.

---
 arch/alpha/include/uapi/asm/socket.h  |  1 +
 arch/mips/include/uapi/asm/socket.h   |  1 +
 arch/parisc/include/uapi/asm/socket.h |  1 +
 arch/sparc/include/uapi/asm/socket.h  |  1 +
 include/uapi/asm-generic/socket.h     |  1 +
 include/uapi/linux/uio.h              |  4 ++
 net/core/sock.c                       | 61 +++++++++++++++++++++++++++
 7 files changed, 70 insertions(+)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index ef4656a41058..251b73c5481e 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -144,6 +144,7 @@
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 414807d55e33..8ab7582291ab 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -155,6 +155,7 @@
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 2b817efd4544..38fc0b188e08 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -136,6 +136,7 @@
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	79
 #define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
 
 #if !defined(__KERNEL__)
 
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 00248fc68977..57084ed2f3c4 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -137,6 +137,7 @@
 #define SCM_DEVMEM_LINEAR        SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF         0x0058
 #define SCM_DEVMEM_DMABUF        SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED       0x0059
 
 #if !defined(__KERNEL__)
 
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 25a2f5255f52..1acb77780f10 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -135,6 +135,7 @@
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
+#define SO_DEVMEM_DONTNEED	97
 #define SO_DEVMEM_LINEAR	98
 #define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
 #define SO_DEVMEM_DMABUF	99
diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
index 3a22ddae376a..d17f8fcd93ec 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -33,6 +33,10 @@ struct dmabuf_cmsg {
 				 */
 };
 
+struct dmabuf_token {
+	__u32 token_start;
+	__u32 token_count;
+};
 /*
  *	UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
diff --git a/net/core/sock.c b/net/core/sock.c
index 43bf3818c19e..b589610cbe4a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1049,6 +1049,63 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+#ifdef CONFIG_PAGE_POOL
+static noinline_for_stack int
+sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
+{
+	unsigned int num_tokens, i, j, k, netmem_num = 0;
+	struct dmabuf_token *tokens;
+	netmem_ref netmems[16];
+	int ret;
+
+	if (sk->sk_type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP)
+		return -EBADF;
+
+	if (optlen % sizeof(struct dmabuf_token) ||
+	    optlen > sizeof(*tokens) * 128)
+		return -EINVAL;
+
+	tokens = kvmalloc_array(128, sizeof(*tokens), GFP_KERNEL);
+	if (!tokens)
+		return -ENOMEM;
+
+	num_tokens = optlen / sizeof(struct dmabuf_token);
+	if (copy_from_sockptr(tokens, optval, optlen))
+		return -EFAULT;
+
+	ret = 0;
+
+	xa_lock_bh(&sk->sk_user_frags);
+	for (i = 0; i < num_tokens; i++) {
+		for (j = 0; j < tokens[i].token_count; j++) {
+			netmem_ref netmem = (__force netmem_ref)__xa_erase(
+				&sk->sk_user_frags, tokens[i].token_start + j);
+
+			if (netmem &&
+			    !WARN_ON_ONCE(!netmem_is_net_iov(netmem))) {
+				netmems[netmem_num++] = netmem;
+				if (netmem_num == ARRAY_SIZE(netmems)) {
+					xa_unlock_bh(&sk->sk_user_frags);
+					for (k = 0; k < netmem_num; k++)
+						WARN_ON_ONCE(!napi_pp_put_page(netmems[k],
+									       false));
+					netmem_num = 0;
+					xa_lock_bh(&sk->sk_user_frags);
+				}
+				ret++;
+			}
+		}
+	}
+
+	xa_unlock_bh(&sk->sk_user_frags);
+	for (k = 0; k < netmem_num; k++)
+		WARN_ON_ONCE(!napi_pp_put_page(netmems[k], false));
+
+	kvfree(tokens);
+	return ret;
+}
+#endif
+
 void sockopt_lock_sock(struct sock *sk)
 {
 	/* When current->bpf_ctx is set, the setsockopt is called from
@@ -1200,6 +1257,10 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 			ret = -EOPNOTSUPP;
 		return ret;
 		}
+#ifdef CONFIG_PAGE_POOL
+	case SO_DEVMEM_DONTNEED:
+		return sock_devmem_dontneed(sk, optval, optlen);
+#endif
 	}
 
 	sockopt_lock_sock(sk);
-- 
2.44.0.396.g6e790dbe36-goog