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:   Sun,  5 Nov 2023 18:44:10 -0800
In-Reply-To: <20231106024413.2801438-1-almasrymina@google.com>
Mime-Version: 1.0
References: <20231106024413.2801438-1-almasrymina@google.com>
Message-ID: <20231106024413.2801438-12-almasrymina@google.com>
Subject: [RFC PATCH v3 11/12] net: add SO_DEVMEM_DONTNEED setsockopt to
 release RX pages
From:   Mina Almasry <almasrymina@google.com>
To:     netdev@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-arch@vger.kernel.org, linux-kselftest@vger.kernel.org,
        linux-media@vger.kernel.org, dri-devel@lists.freedesktop.org,
        linaro-mm-sig@lists.linaro.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>,
        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>,
        Shakeel Butt <shakeelb@google.com>,
        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"
Precedence: bulk

Add an interface for the user to notify the kernel that it is done
reading the NET_RX dmabuf pages returned as cmsg. The kernel will
drop the reference on the NET_RX pages 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>

---
 include/uapi/asm-generic/socket.h |  1 +
 include/uapi/linux/uio.h          |  4 ++++
 net/core/sock.c                   | 36 +++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+)

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index aacb97f16b78..eb93b43394d4 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_HEADER	98
 #define SCM_DEVMEM_HEADER	SO_DEVMEM_HEADER
 #define SO_DEVMEM_OFFSET	99
diff --git a/include/uapi/linux/uio.h b/include/uapi/linux/uio.h
index ae94763b1963..71314bf41590 100644
--- a/include/uapi/linux/uio.h
+++ b/include/uapi/linux/uio.h
@@ -26,6 +26,10 @@ struct cmsg_devmem {
 	__u32 frag_token;
 };
 
+struct devmemtoken {
+	__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 1d28e3e87970..4ddc6b11d915 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1051,6 +1051,39 @@ 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 devmemtoken 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 devmemtoken) || optlen > sizeof(tokens))
+		return -EINVAL;
+
+	num_tokens = optlen / sizeof(struct devmemtoken);
+	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) {
+				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 +1571,9 @@ 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;
-- 
2.42.0.869.gea05f2083d-goog