[RFC PATCH 06/10] net: add SO_DEVMEM_DONTNEED setsockopt to release RX pages

[Mina Almasry]

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: Mina Almasry <almasrymina@xxxxxxxxxx>
---
 include/uapi/asm-generic/socket.h |  1 +
 include/uapi/linux/uio.h          |  4 +++
 net/core/sock.c                   | 41 +++++++++++++++++++++++++++++++
 3 files changed, 46 insertions(+)

diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 88f9234f78cb..2a5a7f5da358 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -132,6 +132,7 @@
 
 #define SO_RCVMARK		75
 
+#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 8b0be0f50838..faaa765fd5a4 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 24f2761bdb1d..f9b9d9ec7322 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1531,7 +1531,48 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		/* Paired with READ_ONCE() in tcp_rtx_synack() */
 		WRITE_ONCE(sk->sk_txrehash, (u8)val);
 		break;
+	case SO_DEVMEM_DONTNEED: {
+		struct devmemtoken tokens[128];
+		unsigned int num_tokens, i, j;
 
+		if (sk->sk_type != SOCK_STREAM ||
+		    sk->sk_protocol != IPPROTO_TCP) {
+			ret = -EBADF;
+			break;
+		}
+
+		if (optlen % sizeof(struct devmemtoken) ||
+		    optlen > sizeof(tokens)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		num_tokens = optlen / sizeof(struct devmemtoken);
+		if (copy_from_sockptr(tokens, optval, optlen)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		ret = 0;
+
+		for (i = 0; i < num_tokens; i++) {
+			for (j = 0; j < tokens[i].token_count; j++) {
+				struct page *pg = xa_erase(&sk->sk_pagepool,
+							   tokens[i].token_start + j);
+
+				if (pg)
+					put_page(pg);
+				else
+					/* -EINTR here notifies the userspace
+					 * that not all tokens passed to it have
+					 * been freed.
+					 */
+					ret = -EINTR;
+			}
+		}
+
+		break;
+	}
 	default:
 		ret = -ENOPROTOOPT;
 		break;
-- 
2.41.0.390.g38632f3daf-goog