net: add SO_DEVMEM_DONTNEED setsockopt to release RX frags

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>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240910171458.219195-11-almasrymina@google.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

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__)
 

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__)
 

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__)
 

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__)
 

include/uapi/asm-generic/socket.h

@@ -139,6 +139,7 @@
 #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__)
 

include/uapi/linux/uio.h

@@ -33,6 +33,11 @@ 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)
  */

net/core/sock.c

@@ -124,6 +124,7 @@
 #include <linux/netdevice.h>
 #include <net/protocol.h>
 #include <linux/skbuff.h>
+#include <linux/skbuff_ref.h>
 #include <net/net_namespace.h>
 #include <net/request_sock.h>
 #include <net/sock.h>
@@ -1049,6 +1050,69 @@ static int sock_reserve_memory(struct sock *sk, int bytes)
 	return 0;
 }
 
+#ifdef CONFIG_PAGE_POOL
+
+/* This is the number of tokens that the user can SO_DEVMEM_DONTNEED in
+ * 1 syscall. The limit exists to limit the amount of memory the kernel
+ * allocates to copy these tokens.
+ */
+#define MAX_DONTNEED_TOKENS 128
+
+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 = 0;
+
+	if (!sk_is_tcp(sk))
+		return -EBADF;
+
+	if (optlen % sizeof(struct dmabuf_token) ||
+	    optlen > sizeof(*tokens) * MAX_DONTNEED_TOKENS)
+		return -EINVAL;
+
+	tokens = kvmalloc_array(optlen, sizeof(*tokens), GFP_KERNEL);
+	if (!tokens)
+		return -ENOMEM;
+
+	num_tokens = optlen / sizeof(struct dmabuf_token);
+	if (copy_from_sockptr(tokens, optval, optlen)) {
+		kvfree(tokens);
+		return -EFAULT;
+	}
+
+	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]));
+					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]));
+
+	kvfree(tokens);
+	return ret;
+}
+#endif
+
 void sockopt_lock_sock(struct sock *sk)
 {
 	/* When current->bpf_ctx is set, the setsockopt is called from
@@ -1211,6 +1275,10 @@ 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);