Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
Date:   Thu,  7 Dec 2023 16:52:45 -0800
In-Reply-To: <20231208005250.2910004-1-almasrymina@google.com>
Mime-Version: 1.0
References: <20231208005250.2910004-1-almasrymina@google.com>
Message-ID: <20231208005250.2910004-15-almasrymina@google.com>
Subject: [net-next v1 14/16] net: add SO_DEVMEM_DONTNEED setsockopt to release
 RX frags
From:   Mina Almasry <almasrymina@google.com>
To:     Shailend Chand <shailend@google.com>, netdev@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org,
        linux-arch@vger.kernel.org, linux-kselftest@vger.kernel.org,
        bpf@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>,
        Jeroen de Borst <jeroendb@google.com>,
        Praveen Kaligineedi <pkaligineedi@google.com>,
        Jesper Dangaard Brouer <hawk@kernel.org>,
        Ilias Apalodimas <ilias.apalodimas@linaro.org>,
        Arnd Bergmann <arnd@arndb.de>,
        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>,
        Yunsheng Lin <linyunsheng@huawei.com>,
        Harshitha Ramamurthy <hramamurthy@google.com>,
        Shakeel Butt <shakeelb@google.com>,
        Willem de Bruijn <willemb@google.com>,
        Kaiyuan Zhang <kaiyuanz@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

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 re-use.

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>

---

Changes in v1:
- devmemtoken -> dmabuf_token (David).
- Use napi_pp_put_page() for refcounting (Yunsheng).

---
 include/uapi/asm-generic/socket.h |  1 +
 include/uapi/linux/uio.h          |  4 ++++
 net/core/sock.c                   | 38 +++++++++++++++++++++++++++++++
 3 files changed, 43 insertions(+)

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 ad92e37699da..65f33178a601 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -30,6 +30,10 @@ struct dmabuf_cmsg {
 	__u32  dmabuf_id;	/* dmabuf id this frag belongs to. */
 };
 
+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 fef349dd72fa..521bdc4ff260 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1051,6 +1051,41 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+static noinline_for_stack int
+sock_devmem_dontneed(struct sock *sk, sockptr_t optval, unsigned int optlen)
+{
+	struct dmabuf_token tokens[128];
+	unsigned int num_tokens, i, j;
+	int ret;
+
+	if (sk->sk_type != SOCK_STREAM || sk->sk_protocol != IPPROTO_TCP)
+		return -EBADF;
+
+	if (optlen % sizeof(struct dmabuf_token) || optlen > sizeof(tokens))
+		return -EINVAL;
+
+	num_tokens = optlen / sizeof(struct dmabuf_token);
+	if (copy_from_sockptr(tokens, optval, optlen))
+		return -EFAULT;
+
+	ret = 0;
+	for (i = 0; i < num_tokens; i++) {
+		for (j = 0; j < tokens[i].token_count; j++) {
+			struct page *page = xa_erase(&sk->sk_user_pages,
+						     tokens[i].token_start + j);
+
+			if (page) {
+				if (WARN_ON_ONCE(!napi_pp_put_page(page,
+								   false)))
+					page_pool_page_put_many(page, 1);
+				ret++;
+			}
+		}
+	}
+
+	return ret;
+}
+
 void sockopt_lock_sock(struct sock *sk)
 {
 	/* When current->bpf_ctx is set, the setsockopt is called from
@@ -1538,6 +1573,9 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		break;
 	}
 
+	case SO_DEVMEM_DONTNEED:
+		ret = sock_devmem_dontneed(sk, optval, optlen);
+		break;
 	default:
 		ret = -ENOPROTOOPT;
 		break;
-- 
2.43.0.472.g3155946c3a-goog