aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
Diffstat
-rw-r--r--Documentation/networking/kcm.txt285
-rw-r--r--include/linux/net.h1
-rw-r--r--include/linux/rculist.h21
-rw-r--r--include/linux/socket.h7
-rw-r--r--include/net/kcm.h226
-rw-r--r--include/net/tcp.h24
-rw-r--r--include/uapi/linux/kcm.h40
-rw-r--r--net/Kconfig1
-rw-r--r--net/Makefile1
-rw-r--r--net/core/skbuff.c39
-rw-r--r--net/ipv4/tcp.c15
-rw-r--r--net/kcm/Kconfig10
-rw-r--r--net/kcm/Makefile3
-rw-r--r--net/kcm/kcmproc.c426
-rw-r--r--net/kcm/kcmsock.c2409
-rw-r--r--net/socket.c18
16 files changed, 3483 insertions, 43 deletions
diff --git a/Documentation/networking/kcm.txt b/Documentation/networking/kcm.txt
new file mode 100644
index 000000000000..3476ede5bc2c
--- /dev/null
+++ b/Documentation/networking/kcm.txt
@@ -0,0 +1,285 @@
+Kernel Connection Mulitplexor
+-----------------------------
+
+Kernel Connection Multiplexor (KCM) is a mechanism that provides a message based
+interface over TCP for generic application protocols. With KCM an application
+can efficiently send and receive application protocol messages over TCP using
+datagram sockets.
+
+KCM implements an NxM multiplexor in the kernel as diagrammed below:
+
++------------+ +------------+ +------------+ +------------+
+| KCM socket | | KCM socket | | KCM socket | | KCM socket |
++------------+ +------------+ +------------+ +------------+
+ | | | |
+ +-----------+ | | +----------+
+ | | | |
+ +----------------------------------+
+ | Multiplexor |
+ +----------------------------------+
+ | | | | |
+ +---------+ | | | ------------+
+ | | | | |
++----------+ +----------+ +----------+ +----------+ +----------+
+| Psock | | Psock | | Psock | | Psock | | Psock |
++----------+ +----------+ +----------+ +----------+ +----------+
+ | | | | |
++----------+ +----------+ +----------+ +----------+ +----------+
+| TCP sock | | TCP sock | | TCP sock | | TCP sock | | TCP sock |
++----------+ +----------+ +----------+ +----------+ +----------+
+
+KCM sockets
+-----------
+
+The KCM sockets provide the user interface to the muliplexor. All the KCM sockets
+bound to a multiplexor are considered to have equivalent function, and I/O
+operations in different sockets may be done in parallel without the need for
+synchronization between threads in userspace.
+
+Multiplexor
+-----------
+
+The multiplexor provides the message steering. In the transmit path, messages
+written on a KCM socket are sent atomically on an appropriate TCP socket.
+Similarly, in the receive path, messages are constructed on each TCP socket
+(Psock) and complete messages are steered to a KCM socket.
+
+TCP sockets & Psocks
+--------------------
+
+TCP sockets may be bound to a KCM multiplexor. A Psock structure is allocated
+for each bound TCP socket, this structure holds the state for constructing
+messages on receive as well as other connection specific information for KCM.
+
+Connected mode semantics
+------------------------
+
+Each multiplexor assumes that all attached TCP connections are to the same
+destination and can use the different connections for load balancing when
+transmitting. The normal send and recv calls (include sendmmsg and recvmmsg)
+can be used to send and receive messages from the KCM socket.
+
+Socket types
+------------
+
+KCM supports SOCK_DGRAM and SOCK_SEQPACKET socket types.
+
+Message delineation
+-------------------
+
+Messages are sent over a TCP stream with some application protocol message
+format that typically includes a header which frames the messages. The length
+of a received message can be deduced from the application protocol header
+(often just a simple length field).
+
+A TCP stream must be parsed to determine message boundaries. Berkeley Packet
+Filter (BPF) is used for this. When attaching a TCP socket to a multiplexor a
+BPF program must be specified. The program is called at the start of receiving
+a new message and is given an skbuff that contains the bytes received so far.
+It parses the message header and returns the length of the message. Given this
+information, KCM will construct the message of the stated length and deliver it
+to a KCM socket.
+
+TCP socket management
+---------------------
+
+When a TCP socket is attached to a KCM multiplexor data ready (POLLIN) and
+write space available (POLLOUT) events are handled by the multiplexor. If there
+is a state change (disconnection) or other error on a TCP socket, an error is
+posted on the TCP socket so that a POLLERR event happens and KCM discontinues
+using the socket. When the application gets the error notification for a
+TCP socket, it should unattach the socket from KCM and then handle the error
+condition (the typical response is to close the socket and create a new
+connection if necessary).
+
+KCM limits the maximum receive message size to be the size of the receive
+socket buffer on the attached TCP socket (the socket buffer size can be set by
+SO_RCVBUF). If the length of a new message reported by the BPF program is
+greater than this limit a corresponding error (EMSGSIZE) is posted on the TCP
+socket. The BPF program may also enforce a maximum messages size and report an
+error when it is exceeded.
+
+A timeout may be set for assembling messages on a receive socket. The timeout
+value is taken from the receive timeout of the attached TCP socket (this is set
+by SO_RCVTIMEO). If the timer expires before assembly is complete an error
+(ETIMEDOUT) is posted on the socket.
+
+User interface
+==============
+
+Creating a multiplexor
+----------------------
+
+A new multiplexor and initial KCM socket is created by a socket call:
+
+ socket(AF_KCM, type, protocol)
+
+ - type is either SOCK_DGRAM or SOCK_SEQPACKET
+ - protocol is KCMPROTO_CONNECTED
+
+Cloning KCM sockets
+-------------------
+
+After the first KCM socket is created using the socket call as described
+above, additional sockets for the multiplexor can be created by cloning
+a KCM socket. This is accomplished by an ioctl on a KCM socket:
+
+ /* From linux/kcm.h */
+ struct kcm_clone {
+ int fd;
+ };
+
+ struct kcm_clone info;
+
+ memset(&info, 0, sizeof(info));
+
+ err = ioctl(kcmfd, SIOCKCMCLONE, &info);
+
+ if (!err)
+ newkcmfd = info.fd;
+
+Attach transport sockets
+------------------------
+
+Attaching of transport sockets to a multiplexor is performed by calling an
+ioctl on a KCM socket for the multiplexor. e.g.:
+
+ /* From linux/kcm.h */
+ struct kcm_attach {
+ int fd;
+ int bpf_fd;
+ };
+
+ struct kcm_attach info;
+
+ memset(&info, 0, sizeof(info));
+
+ info.fd = tcpfd;
+ info.bpf_fd = bpf_prog_fd;
+
+ ioctl(kcmfd, SIOCKCMATTACH, &info);
+
+The kcm_attach structure contains:
+ fd: file descriptor for TCP socket being attached
+ bpf_prog_fd: file descriptor for compiled BPF program downloaded
+
+Unattach transport sockets
+--------------------------
+
+Unattaching a transport socket from a multiplexor is straightforward. An
+"unattach" ioctl is done with the kcm_unattach structure as the argument:
+
+ /* From linux/kcm.h */
+ struct kcm_unattach {
+ int fd;
+ };
+
+ struct kcm_unattach info;
+
+ memset(&info, 0, sizeof(info));
+
+ info.fd = cfd;
+
+ ioctl(fd, SIOCKCMUNATTACH, &info);
+
+Disabling receive on KCM socket
+-------------------------------
+
+A setsockopt is used to disable or enable receiving on a KCM socket.
+When receive is disabled, any pending messages in the socket's
+receive buffer are moved to other sockets. This feature is useful
+if an application thread knows that it will be doing a lot of
+work on a request and won't be able to service new messages for a
+while. Example use:
+
+ int val = 1;
+
+ setsockopt(kcmfd, SOL_KCM, KCM_RECV_DISABLE, &val, sizeof(val))
+
+BFP programs for message delineation
+------------------------------------
+
+BPF programs can be compiled using the BPF LLVM backend. For exmple,
+the BPF program for parsing Thrift is:
+
+ #include "bpf.h" /* for __sk_buff */
+ #include "bpf_helpers.h" /* for load_word intrinsic */
+
+ SEC("socket_kcm")
+ int bpf_prog1(struct __sk_buff *skb)
+ {
+ return load_word(skb, 0) + 4;
+ }
+
+ char _license[] SEC("license") = "GPL";
+
+Use in applications
+===================
+
+KCM accelerates application layer protocols. Specifically, it allows
+applications to use a message based interface for sending and receiving
+messages. The kernel provides necessary assurances that messages are sent
+and received atomically. This relieves much of the burden applications have
+in mapping a message based protocol onto the TCP stream. KCM also make
+application layer messages a unit of work in the kernel for the purposes of
+steerng and scheduling, which in turn allows a simpler networking model in
+multithreaded applications.
+
+Configurations
+--------------
+
+In an Nx1 configuration, KCM logically provides multiple socket handles
+to the same TCP connection. This allows parallelism between in I/O
+operations on the TCP socket (for instance copyin and copyout of data is
+parallelized). In an application, a KCM socket can be opened for each
+processing thread and inserted into the epoll (similar to how SO_REUSEPORT
+is used to allow multiple listener sockets on the same port).
+
+In a MxN configuration, multiple connections are established to the
+same destination. These are used for simple load balancing.
+
+Message batching
+----------------
+
+The primary purpose of KCM is load balancing between KCM sockets and hence
+threads in a nominal use case. Perfect load balancing, that is steering
+each received message to a different KCM socket or steering each sent
+message to a different TCP socket, can negatively impact performance
+since this doesn't allow for affinities to be established. Balancing
+based on groups, or batches of messages, can be beneficial for performance.
+
+On transmit, there are three ways an application can batch (pipeline)
+messages on a KCM socket.
+ 1) Send multiple messages in a single sendmmsg.
+ 2) Send a group of messages each with a sendmsg call, where all messages
+ except the last have MSG_BATCH in the flags of sendmsg call.
+ 3) Create "super message" composed of multiple messages and send this
+ with a single sendmsg.
+
+On receive, the KCM module attempts to queue messages received on the
+same KCM socket during each TCP ready callback. The targeted KCM socket
+changes at each receive ready callback on the KCM socket. The application
+does not need to configure this.
+
+Error handling
+--------------
+
+An application should include a thread to monitor errors raised on
+the TCP connection. Normally, this will be done by placing each
+TCP socket attached to a KCM multiplexor in epoll set for POLLERR
+event. If an error occurs on an attached TCP socket, KCM sets an EPIPE
+on the socket thus waking up the application thread. When the application
+sees the error (which may just be a disconnect) it should unattach the
+socket from KCM and then close it. It is assumed that once an error is
+posted on the TCP socket the data stream is unrecoverable (i.e. an error
+may have occurred in in the middle of receiving a messssge).
+
+TCP connection monitoring
+-------------------------
+
+In KCM there is no means to correlate a message to the TCP socket that
+was used to send or receive the message (except in the case there is
+only one attached TCP socket). However, the application does retain
+an open file descriptor to the socket so it will be able to get statistics
+from the socket which can be used in detecting issues (such as high
+retransmissions on the socket).
diff --git a/include/linux/net.h b/include/linux/net.h
index 0b4ac7da583a..49175e4ced11 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -215,6 +215,7 @@ int __sock_create(struct net *net, int family, int type, int proto,
int sock_create(int family, int type, int proto, struct socket **res);
int sock_create_kern(struct net *net, int family, int type, int proto, struct socket **res);
int sock_create_lite(int family, int type, int proto, struct socket **res);
+struct socket *sock_alloc(void);
void sock_release(struct socket *sock);
int sock_sendmsg(struct socket *sock, struct msghdr *msg);
int sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 14ec1652daf4..17d4f849c65e 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -319,6 +319,27 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
})
/**
+ * list_next_or_null_rcu - get the first element from a list
+ * @head: the head for the list.
+ * @ptr: the list head to take the next element from.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the list_head within the struct.
+ *
+ * Note that if the ptr is at the end of the list, NULL is returned.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_next_or_null_rcu(head, ptr, type, member) \
+({ \
+ struct list_head *__head = (head); \
+ struct list_head *__ptr = (ptr); \
+ struct list_head *__next = READ_ONCE(__ptr->next); \
+ likely(__next != __head) ? list_entry_rcu(__next, type, \
+ member) : NULL; \
+})
+
+/**
* list_for_each_entry_rcu - iterate over rcu list of given type
* @pos: the type * to use as a loop cursor.
* @head: the head for your list.
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 5bf59c8493b7..73bf6c6a833b 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -200,7 +200,9 @@ struct ucred {
#define AF_ALG 38 /* Algorithm sockets */
#define AF_NFC 39 /* NFC sockets */
#define AF_VSOCK 40 /* vSockets */
-#define AF_MAX 41 /* For now.. */
+#define AF_KCM 41 /* Kernel Connection Multiplexor*/
+
+#define AF_MAX 42 /* For now.. */
/* Protocol families, same as address families. */
#define PF_UNSPEC AF_UNSPEC
@@ -246,6 +248,7 @@ struct ucred {
#define PF_ALG AF_ALG
#define PF_NFC AF_NFC
#define PF_VSOCK AF_VSOCK
+#define PF_KCM AF_KCM
#define PF_MAX AF_MAX
/* Maximum queue length specifiable by listen. */
@@ -274,6 +277,7 @@ struct ucred {
#define MSG_MORE 0x8000 /* Sender will send more */
#define MSG_WAITFORONE 0x10000 /* recvmmsg(): block until 1+ packets avail */
#define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
+#define MSG_BATCH 0x40000 /* sendmmsg(): more messages coming */
#define MSG_EOF MSG_FIN
#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */
@@ -322,6 +326,7 @@ struct ucred {
#define SOL_CAIF 278
#define SOL_ALG 279
#define SOL_NFC 280
+#define SOL_KCM 281
/* IPX options */
#define IPX_TYPE 1
diff --git a/include/net/kcm.h b/include/net/kcm.h
new file mode 100644
index 000000000000..95c425ca97b6
--- /dev/null
+++ b/include/net/kcm.h
@@ -0,0 +1,226 @@
+/*
+ * Kernel Connection Multiplexor
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __NET_KCM_H_
+#define __NET_KCM_H_
+
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <uapi/linux/kcm.h>
+
+extern unsigned int kcm_net_id;
+
+#define KCM_STATS_ADD(stat, count) ((stat) += (count))
+#define KCM_STATS_INCR(stat) ((stat)++)
+
+struct kcm_psock_stats {
+ unsigned long long rx_msgs;
+ unsigned long long rx_bytes;
+ unsigned long long tx_msgs;
+ unsigned long long tx_bytes;
+ unsigned int rx_aborts;
+ unsigned int rx_mem_fail;
+ unsigned int rx_need_more_hdr;
+ unsigned int rx_msg_too_big;
+ unsigned int rx_msg_timeouts;
+ unsigned int rx_bad_hdr_len;
+ unsigned long long reserved;
+ unsigned long long unreserved;
+ unsigned int tx_aborts;
+};
+
+struct kcm_mux_stats {
+ unsigned long long rx_msgs;
+ unsigned long long rx_bytes;
+ unsigned long long tx_msgs;
+ unsigned long long tx_bytes;
+ unsigned int rx_ready_drops;
+ unsigned int tx_retries;
+ unsigned int psock_attach;
+ unsigned int psock_unattach_rsvd;
+ unsigned int psock_unattach;
+};
+
+struct kcm_stats {
+ unsigned long long rx_msgs;
+ unsigned long long rx_bytes;
+ unsigned long long tx_msgs;
+ unsigned long long tx_bytes;
+};
+
+struct kcm_tx_msg {
+ unsigned int sent;
+ unsigned int fragidx;
+ unsigned int frag_offset;
+ unsigned int msg_flags;
+ struct sk_buff *frag_skb;
+ struct sk_buff *last_skb;
+};
+
+struct kcm_rx_msg {
+ int full_len;
+ int accum_len;
+ int offset;
+ int early_eaten;
+};
+
+/* Socket structure for KCM client sockets */
+struct kcm_sock {
+ struct sock sk;
+ struct kcm_mux *mux;
+ struct list_head kcm_sock_list;
+ int index;
+ u32 done : 1;
+ struct work_struct done_work;
+
+ struct kcm_stats stats;
+
+ /* Transmit */
+ struct kcm_psock *tx_psock;
+ struct work_struct tx_work;
+ struct list_head wait_psock_list;
+ struct sk_buff *seq_skb;
+
+ /* Don't use bit fields here, these are set under different locks */
+ bool tx_wait;
+ bool tx_wait_more;
+
+ /* Receive */
+ struct kcm_psock *rx_psock;
+ struct list_head wait_rx_list; /* KCMs waiting for receiving */
+ bool rx_wait;
+ u32 rx_disabled : 1;
+};
+
+struct bpf_prog;
+
+/* Structure for an attached lower socket */
+struct kcm_psock {
+ struct sock *sk;
+ struct kcm_mux *mux;
+ int index;
+
+ u32 tx_stopped : 1;
+ u32 rx_stopped : 1;
+ u32 done : 1;
+ u32 unattaching : 1;
+
+ void (*save_state_change)(struct sock *sk);
+ void (*save_data_ready)(struct sock *sk);
+ void (*save_write_space)(struct sock *sk);
+
+ struct list_head psock_list;
+
+ struct kcm_psock_stats stats;
+
+ /* Receive */
+ struct sk_buff *rx_skb_head;
+ struct sk_buff **rx_skb_nextp;
+ struct sk_buff *ready_rx_msg;
+ struct list_head psock_ready_list;
+ struct work_struct rx_work;
+ struct delayed_work rx_delayed_work;
+ struct bpf_prog *bpf_prog;
+ struct kcm_sock *rx_kcm;
+ unsigned long long saved_rx_bytes;
+ unsigned long long saved_rx_msgs;
+ struct timer_list rx_msg_timer;
+ unsigned int rx_need_bytes;
+
+ /* Transmit */
+ struct kcm_sock *tx_kcm;
+ struct list_head psock_avail_list;
+ unsigned long long saved_tx_bytes;
+ unsigned long long saved_tx_msgs;
+};
+
+/* Per net MUX list */
+struct kcm_net {
+ struct mutex mutex;
+ struct kcm_psock_stats aggregate_psock_stats;
+ struct kcm_mux_stats aggregate_mux_stats;
+ struct list_head mux_list;
+ int count;
+};
+
+/* Structure for a MUX */
+struct kcm_mux {
+ struct list_head kcm_mux_list;
+ struct rcu_head rcu;
+ struct kcm_net *knet;
+
+ struct list_head kcm_socks; /* All KCM sockets on MUX */
+ int kcm_socks_cnt; /* Total KCM socket count for MUX */
+ struct list_head psocks; /* List of all psocks on MUX */
+ int psocks_cnt; /* Total attached sockets */
+
+ struct kcm_mux_stats stats;
+ struct kcm_psock_stats aggregate_psock_stats;
+
+ /* Receive */
+ spinlock_t rx_lock ____cacheline_aligned_in_smp;
+ struct list_head kcm_rx_waiters; /* KCMs waiting for receiving */
+ struct list_head psocks_ready; /* List of psocks with a msg ready */
+ struct sk_buff_head rx_hold_queue;
+
+ /* Transmit */
+ spinlock_t lock ____cacheline_aligned_in_smp; /* TX and mux locking */
+ struct list_head psocks_avail; /* List of available psocks */
+ struct list_head kcm_tx_waiters; /* KCMs waiting for a TX psock */
+};
+
+#ifdef CONFIG_PROC_FS
+int kcm_proc_init(void);
+void kcm_proc_exit(void);
+#else
+static int kcm_proc_init(void) { return 0; }
+static void kcm_proc_exit(void) { }
+#endif
+
+static inline void aggregate_psock_stats(struct kcm_psock_stats *stats,
+ struct kcm_psock_stats *agg_stats)
+{
+ /* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat)
+ SAVE_PSOCK_STATS(rx_msgs);
+ SAVE_PSOCK_STATS(rx_bytes);
+ SAVE_PSOCK_STATS(rx_aborts);
+ SAVE_PSOCK_STATS(rx_mem_fail);
+ SAVE_PSOCK_STATS(rx_need_more_hdr);
+ SAVE_PSOCK_STATS(rx_msg_too_big);
+ SAVE_PSOCK_STATS(rx_msg_timeouts);
+ SAVE_PSOCK_STATS(rx_bad_hdr_len);
+ SAVE_PSOCK_STATS(tx_msgs);
+ SAVE_PSOCK_STATS(tx_bytes);
+ SAVE_PSOCK_STATS(reserved);
+ SAVE_PSOCK_STATS(unreserved);
+ SAVE_PSOCK_STATS(tx_aborts);
+#undef SAVE_PSOCK_STATS
+}
+
+static inline void aggregate_mux_stats(struct kcm_mux_stats *stats,
+ struct kcm_mux_stats *agg_stats)
+{
+ /* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_MUX_STATS(_stat) (agg_stats->_stat += stats->_stat)
+ SAVE_MUX_STATS(rx_msgs);
+ SAVE_MUX_STATS(rx_bytes);
+ SAVE_MUX_STATS(tx_msgs);
+ SAVE_MUX_STATS(tx_bytes);
+ SAVE_MUX_STATS(rx_ready_drops);
+ SAVE_MUX_STATS(psock_attach);
+ SAVE_MUX_STATS(psock_unattach_rsvd);
+ SAVE_MUX_STATS(psock_unattach);
+#undef SAVE_MUX_STATS
+}
+
+#endif /* __NET_KCM_H_ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e90db8546806..0302636af98c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1816,4 +1816,28 @@ static inline void skb_set_tcp_pure_ack(struct sk_buff *skb)
skb->truesize = 2;
}
+static inline int tcp_inq(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int answ;
+
+ if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
+ answ = 0;
+ } else if (sock_flag(sk, SOCK_URGINLINE) ||
+ !tp->urg_data ||
+ before(tp->urg_seq, tp->copied_seq) ||
+ !before(tp->urg_seq, tp->rcv_nxt)) {
+
+ answ = tp->rcv_nxt - tp->copied_seq;
+
+ /* Subtract 1, if FIN was received */
+ if (answ && sock_flag(sk, SOCK_DONE))
+ answ--;
+ } else {
+ answ = tp->urg_seq - tp->copied_seq;
+ }
+
+ return answ;
+}
+
#endif /* _TCP_H */
diff --git a/include/uapi/linux/kcm.h b/include/uapi/linux/kcm.h
new file mode 100644
index 000000000000..a5a530940b99
--- /dev/null
+++ b/include/uapi/linux/kcm.h
@@ -0,0 +1,40 @@
+/*
+ * Kernel Connection Multiplexor
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * User API to clone KCM sockets and attach transport socket to a KCM
+ * multiplexor.
+ */
+
+#ifndef KCM_KERNEL_H
+#define KCM_KERNEL_H
+
+struct kcm_attach {
+ int fd;
+ int bpf_fd;
+};
+
+struct kcm_unattach {
+ int fd;
+};
+
+struct kcm_clone {
+ int fd;
+};
+
+#define SIOCKCMATTACH (SIOCPROTOPRIVATE + 0)
+#define SIOCKCMUNATTACH (SIOCPROTOPRIVATE + 1)
+#define SIOCKCMCLONE (SIOCPROTOPRIVATE + 2)
+
+#define KCMPROTO_CONNECTED 0
+
+/* Socket options */
+#define KCM_RECV_DISABLE 1
+
+#endif
+
diff --git a/net/Kconfig b/net/Kconfig
index 2760825e53fa..10640d5f8bee 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -360,6 +360,7 @@ source "net/can/Kconfig"
source "net/irda/Kconfig"
source "net/bluetooth/Kconfig"
source "net/rxrpc/Kconfig"
+source "net/kcm/Kconfig"
config FIB_RULES
bool
diff --git a/net/Makefile b/net/Makefile
index a5d04098dfce..81d14119eab5 100644
--- a/net/Makefile
+++ b/net/Makefile
@@ -34,6 +34,7 @@ obj-$(CONFIG_IRDA) += irda/
obj-$(CONFIG_BT) += bluetooth/
obj-$(CONFIG_SUNRPC) += sunrpc/
obj-$(CONFIG_AF_RXRPC) += rxrpc/
+obj-$(CONFIG_AF_KCM) += kcm/
obj-$(CONFIG_ATM) += atm/
obj-$(CONFIG_L2TP) += l2tp/
obj-$(CONFIG_DECNET) += decnet/
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 9d7be61e5e6b..51d768e7bc90 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1918,6 +1918,7 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
struct splice_pipe_desc *spd, struct sock *sk)
{
int seg;
+ struct sk_buff *iter;
/* map the linear part :
* If skb->head_frag is set, this 'linear' part is backed by a
@@ -1944,6 +1945,19 @@ static bool __skb_splice_bits(struct sk_buff *skb, struct pipe_inode_info *pipe,
return true;
}
+ skb_walk_frags(skb, iter) {
+ if (*offset >= iter->len) {
+ *offset -= iter->len;
+ continue;
+ }
+ /* __skb_splice_bits() only fails if the output has no room
+ * left, so no point in going over the frag_list for the error
+ * case.
+ */
+ if (__skb_splice_bits(iter, pipe, offset, len, spd, sk))
+ return true;
+ }
+
return false;
}
@@ -1970,9 +1984,7 @@ ssize_t skb_socket_splice(struct sock *sk,
/*
* Map data from the skb to a pipe. Should handle both the linear part,
- * the fragments, and the frag list. It does NOT handle frag lists within
- * the frag list, if such a thing exists. We'd probably need to recurse to
- * handle that cleanly.
+ * the fragments, and the frag list.
*/
int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
struct pipe_inode_info *pipe, unsigned int tlen,
@@ -1991,29 +2003,10 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
.ops = &nosteal_pipe_buf_ops,
.spd_release = sock_spd_release,
};
- struct sk_buff *frag_iter;
int ret = 0;
- /*
- * __skb_splice_bits() only fails if the output has no room left,
- * so no point in going over the frag_list for the error case.
- */
- if (__skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk))
- goto done;
- else if (!tlen)
- goto done;
+ __skb_splice_bits(skb, pipe, &offset, &tlen, &spd, sk);
- /*
- * now see if we have a frag_list to map
- */
- skb_walk_frags(skb, frag_iter) {
- if (!tlen)
- break;
- if (__skb_splice_bits(frag_iter, pipe, &offset, &tlen, &spd, sk))
- break;
- }
-
-done:
if (spd.nr_pages)
ret = splice_cb(sk, pipe, &spd);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f9faadb42485..a265f00b9df9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -556,20 +556,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg)
return -EINVAL;
slow = lock_sock_fast(sk);
- if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))
- answ = 0;
- else if (sock_flag(sk, SOCK_URGINLINE) ||
- !tp->urg_data ||
- before(tp->urg_seq, tp->copied_seq) ||
- !before(tp->urg_seq, tp->rcv_nxt)) {
-
- answ = tp->rcv_nxt - tp->copied_seq;
-
- /* Subtract 1, if FIN was received */
- if (answ && sock_flag(sk, SOCK_DONE))
- answ--;
- } else
- answ = tp->urg_seq - tp->copied_seq;
+ answ = tcp_inq(sk);
unlock_sock_fast(sk, slow);
break;
case SIOCATMARK:
diff --git a/net/kcm/Kconfig b/net/kcm/Kconfig
new file mode 100644
index 000000000000..5db94d940ecc
--- /dev/null
+++ b/net/kcm/Kconfig
@@ -0,0 +1,10 @@
+
+config AF_KCM
+ tristate "KCM sockets"
+ depends on INET
+ select BPF_SYSCALL
+ ---help---
+ KCM (Kernel Connection Multiplexor) sockets provide a method
+ for multiplexing messages of a message based application
+ protocol over kernel connectons (e.g. TCP connections).
+
diff --git a/net/kcm/Makefile b/net/kcm/Makefile
new file mode 100644
index 000000000000..71256133e677
--- /dev/null
+++ b/net/kcm/Makefile
@@ -0,0 +1,3 @@
+obj-$(CONFIG_AF_KCM) += kcm.o
+
+kcm-y := kcmsock.o kcmproc.o
diff --git a/net/kcm/kcmproc.c b/net/kcm/kcmproc.c
new file mode 100644
index 000000000000..738008726cc6
--- /dev/null
+++ b/net/kcm/kcmproc.c
@@ -0,0 +1,426 @@
+#include <linux/in.h>
+#include <linux/inet.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/proc_fs.h>
+#include <linux/rculist.h>
+#include <linux/seq_file.h>
+#include <linux/socket.h>
+#include <net/inet_sock.h>
+#include <net/kcm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/tcp.h>
+
+#ifdef CONFIG_PROC_FS
+struct kcm_seq_muxinfo {
+ char *name;
+ const struct file_operations *seq_fops;
+ const struct seq_operations seq_ops;
+};
+
+static struct kcm_mux *kcm_get_first(struct seq_file *seq)
+{
+ struct net *net = seq_file_net(seq);
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ return list_first_or_null_rcu(&knet->mux_list,
+ struct kcm_mux, kcm_mux_list);
+}
+
+static struct kcm_mux *kcm_get_next(struct kcm_mux *mux)
+{
+ struct kcm_net *knet = mux->knet;
+
+ return list_next_or_null_rcu(&knet->mux_list, &mux->kcm_mux_list,
+ struct kcm_mux, kcm_mux_list);
+}
+
+static struct kcm_mux *kcm_get_idx(struct seq_file *seq, loff_t pos)
+{
+ struct net *net = seq_file_net(seq);
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+ struct kcm_mux *m;
+
+ list_for_each_entry_rcu(m, &knet->mux_list, kcm_mux_list) {
+ if (!pos)
+ return m;
+ --pos;
+ }
+ return NULL;
+}
+
+static void *kcm_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+ void *p;
+
+ if (v == SEQ_START_TOKEN)
+ p = kcm_get_first(seq);
+ else
+ p = kcm_get_next(v);
+ ++*pos;
+ return p;
+}
+
+static void *kcm_seq_start(struct seq_file *seq, loff_t *pos)
+ __acquires(rcu)
+{
+ rcu_read_lock();
+
+ if (!*pos)
+ return SEQ_START_TOKEN;
+ else
+ return kcm_get_idx(seq, *pos - 1);
+}
+
+static void kcm_seq_stop(struct seq_file *seq, void *v)
+ __releases(rcu)
+{
+ rcu_read_unlock();
+}
+
+struct kcm_proc_mux_state {
+ struct seq_net_private p;
+ int idx;
+};
+
+static int kcm_seq_open(struct inode *inode, struct file *file)
+{
+ struct kcm_seq_muxinfo *muxinfo = PDE_DATA(inode);
+ int err;
+
+ err = seq_open_net(inode, file, &muxinfo->seq_ops,
+ sizeof(struct kcm_proc_mux_state));
+ if (err < 0)
+ return err;
+ return err;
+}
+
+static void kcm_format_mux_header(struct seq_file *seq)
+{
+ struct net *net = seq_file_net(seq);
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ seq_printf(seq,
+ "*** KCM statistics (%d MUX) ****\n",
+ knet->count);
+
+ seq_printf(seq,
+ "%-14s %-10s %-16s %-10s %-16s %-8s %-8s %-8s %-8s %s",
+ "Object",
+ "RX-Msgs",
+ "RX-Bytes",
+ "TX-Msgs",
+ "TX-Bytes",
+ "Recv-Q",
+ "Rmem",
+ "Send-Q",
+ "Smem",
+ "Status");
+
+ /* XXX: pdsts header stuff here */
+ seq_puts(seq, "\n");
+}
+
+static void kcm_format_sock(struct kcm_sock *kcm, struct seq_file *seq,
+ int i, int *len)
+{
+ seq_printf(seq,
+ " kcm-%-7u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8s ",
+ kcm->index,
+ kcm->stats.rx_msgs,
+ kcm->stats.rx_bytes,
+ kcm->stats.tx_msgs,
+ kcm->stats.tx_bytes,
+ kcm->sk.sk_receive_queue.qlen,
+ sk_rmem_alloc_get(&kcm->sk),
+ kcm->sk.sk_write_queue.qlen,
+ "-");
+
+ if (kcm->tx_psock)
+ seq_printf(seq, "Psck-%u ", kcm->tx_psock->index);
+
+ if (kcm->tx_wait)
+ seq_puts(seq, "TxWait ");
+
+ if (kcm->tx_wait_more)
+ seq_puts(seq, "WMore ");
+
+ if (kcm->rx_wait)
+ seq_puts(seq, "RxWait ");
+
+ seq_puts(seq, "\n");
+}
+
+static void kcm_format_psock(struct kcm_psock *psock, struct seq_file *seq,
+ int i, int *len)
+{
+ seq_printf(seq,
+ " psock-%-5u %-10llu %-16llu %-10llu %-16llu %-8d %-8d %-8d %-8d ",
+ psock->index,
+ psock->stats.rx_msgs,
+ psock->stats.rx_bytes,
+ psock->stats.tx_msgs,
+ psock->stats.tx_bytes,
+ psock->sk->sk_receive_queue.qlen,
+ atomic_read(&psock->sk->sk_rmem_alloc),
+ psock->sk->sk_write_queue.qlen,
+ atomic_read(&psock->sk->sk_wmem_alloc));
+
+ if (psock->done)
+ seq_puts(seq, "Done ");
+
+ if (psock->tx_stopped)
+ seq_puts(seq, "TxStop ");
+
+ if (psock->rx_stopped)
+ seq_puts(seq, "RxStop ");
+
+ if (psock->tx_kcm)
+ seq_printf(seq, "Rsvd-%d ", psock->tx_kcm->index);
+
+ if (psock->ready_rx_msg)
+ seq_puts(seq, "RdyRx ");
+
+ seq_puts(seq, "\n");
+}
+
+static void
+kcm_format_mux(struct kcm_mux *mux, loff_t idx, struct seq_file *seq)
+{
+ int i, len;
+ struct kcm_sock *kcm;
+ struct kcm_psock *psock;
+
+ /* mux information */
+ seq_printf(seq,
+ "%-6s%-8s %-10llu %-16llu %-10llu %-16llu %-8s %-8s %-8s %-8s ",
+ "mux", "",
+ mux->stats.rx_msgs,
+ mux->stats.rx_bytes,
+ mux->stats.tx_msgs,
+ mux->stats.tx_bytes,
+ "-", "-", "-", "-");
+
+ seq_printf(seq, "KCMs: %d, Psocks %d\n",
+ mux->kcm_socks_cnt, mux->psocks_cnt);
+
+ /* kcm sock information */
+ i = 0;
+ spin_lock_bh(&mux->lock);
+ list_for_each_entry(kcm, &mux->kcm_socks, kcm_sock_list) {
+ kcm_format_sock(kcm, seq, i, &len);
+ i++;
+ }
+ i = 0;
+ list_for_each_entry(psock, &mux->psocks, psock_list) {
+ kcm_format_psock(psock, seq, i, &len);
+ i++;
+ }
+ spin_unlock_bh(&mux->lock);
+}
+
+static int kcm_seq_show(struct seq_file *seq, void *v)
+{
+ struct kcm_proc_mux_state *mux_state;
+
+ mux_state = seq->private;
+ if (v == SEQ_START_TOKEN) {
+ mux_state->idx = 0;
+ kcm_format_mux_header(seq);
+ } else {
+ kcm_format_mux(v, mux_state->idx, seq);
+ mux_state->idx++;
+ }
+ return 0;
+}
+
+static const struct file_operations kcm_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = kcm_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+};
+
+static struct kcm_seq_muxinfo kcm_seq_muxinfo = {
+ .name = "kcm",
+ .seq_fops = &kcm_seq_fops,
+ .seq_ops = {
+ .show = kcm_seq_show,
+ .start = kcm_seq_start,
+ .next = kcm_seq_next,
+ .stop = kcm_seq_stop,
+ }
+};
+
+static int kcm_proc_register(struct net *net, struct kcm_seq_muxinfo *muxinfo)
+{
+ struct proc_dir_entry *p;
+ int rc = 0;
+
+ p = proc_create_data(muxinfo->name, S_IRUGO, net->proc_net,
+ muxinfo->seq_fops, muxinfo);
+ if (!p)
+ rc = -ENOMEM;
+ return rc;
+}
+EXPORT_SYMBOL(kcm_proc_register);
+
+static void kcm_proc_unregister(struct net *net,
+ struct kcm_seq_muxinfo *muxinfo)
+{
+ remove_proc_entry(muxinfo->name, net->proc_net);
+}
+EXPORT_SYMBOL(kcm_proc_unregister);
+
+static int kcm_stats_seq_show(struct seq_file *seq, void *v)
+{
+ struct kcm_psock_stats psock_stats;
+ struct kcm_mux_stats mux_stats;
+ struct kcm_mux *mux;
+ struct kcm_psock *psock;
+ struct net *net = seq->private;
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ memset(&mux_stats, 0, sizeof(mux_stats));
+ memset(&psock_stats, 0, sizeof(psock_stats));
+
+ mutex_lock(&knet->mutex);
+
+ aggregate_mux_stats(&knet->aggregate_mux_stats, &mux_stats);
+ aggregate_psock_stats(&knet->aggregate_psock_stats,
+ &psock_stats);
+
+ list_for_each_entry_rcu(mux, &knet->mux_list, kcm_mux_list) {
+ spin_lock_bh(&mux->lock);
+ aggregate_mux_stats(&mux->stats, &mux_stats);
+ aggregate_psock_stats(&mux->aggregate_psock_stats,
+ &psock_stats);
+ list_for_each_entry(psock, &mux->psocks, psock_list)
+ aggregate_psock_stats(&psock->stats, &psock_stats);
+ spin_unlock_bh(&mux->lock);
+ }
+
+ mutex_unlock(&knet->mutex);
+
+ seq_printf(seq,
+ "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s\n",
+ "MUX",
+ "RX-Msgs",
+ "RX-Bytes",
+ "TX-Msgs",
+ "TX-Bytes",
+ "TX-Retries",
+ "Attach",
+ "Unattach",
+ "UnattchRsvd",
+ "RX-RdyDrops");
+
+ seq_printf(seq,
+ "%-8s %-10llu %-16llu %-10llu %-16llu %-10u %-10u %-10u %-10u %-10u\n",
+ "",
+ mux_stats.rx_msgs,
+ mux_stats.rx_bytes,
+ mux_stats.tx_msgs,
+ mux_stats.tx_bytes,
+ mux_stats.tx_retries,
+ mux_stats.psock_attach,
+ mux_stats.psock_unattach_rsvd,
+ mux_stats.psock_unattach,
+ mux_stats.rx_ready_drops);
+
+ seq_printf(seq,
+ "%-8s %-10s %-16s %-10s %-16s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s %-10s\n",
+ "Psock",
+ "RX-Msgs",
+ "RX-Bytes",
+ "TX-Msgs",
+ "TX-Bytes",
+ "Reserved",
+ "Unreserved",
+ "RX-Aborts",
+ "RX-MemFail",
+ "RX-NeedMor",
+ "RX-BadLen",
+ "RX-TooBig",
+ "RX-Timeout",
+ "TX-Aborts");
+
+ seq_printf(seq,
+ "%-8s %-10llu %-16llu %-10llu %-16llu %-10llu %-10llu %-10u %-10u %-10u %-10u %-10u %-10u %-10u\n",
+ "",
+ psock_stats.rx_msgs,
+ psock_stats.rx_bytes,
+ psock_stats.tx_msgs,
+ psock_stats.tx_bytes,
+ psock_stats.reserved,
+ psock_stats.unreserved,
+ psock_stats.rx_aborts,
+ psock_stats.rx_mem_fail,
+ psock_stats.rx_need_more_hdr,
+ psock_stats.rx_bad_hdr_len,
+ psock_stats.rx_msg_too_big,
+ psock_stats.rx_msg_timeouts,
+ psock_stats.tx_aborts);
+
+ return 0;
+}
+
+static int kcm_stats_seq_open(struct inode *inode, struct file *file)
+{
+ return single_open_net(inode, file, kcm_stats_seq_show);
+}
+
+static const struct file_operations kcm_stats_seq_fops = {
+ .owner = THIS_MODULE,
+ .open = kcm_stats_seq_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release_net,
+};
+
+static int kcm_proc_init_net(struct net *net)
+{
+ int err;
+
+ if (!proc_create("kcm_stats", S_IRUGO, net->proc_net,
+ &kcm_stats_seq_fops)) {
+ err = -ENOMEM;
+ goto out_kcm_stats;
+ }
+
+ err = kcm_proc_register(net, &kcm_seq_muxinfo);
+ if (err)
+ goto out_kcm;
+
+ return 0;
+
+out_kcm:
+ remove_proc_entry("kcm_stats", net->proc_net);
+out_kcm_stats:
+ return err;
+}
+
+static void kcm_proc_exit_net(struct net *net)
+{
+ kcm_proc_unregister(net, &kcm_seq_muxinfo);
+ remove_proc_entry("kcm_stats", net->proc_net);
+}
+
+static struct pernet_operations kcm_net_ops = {
+ .init = kcm_proc_init_net,
+ .exit = kcm_proc_exit_net,
+};
+
+int __init kcm_proc_init(void)
+{
+ return register_pernet_subsys(&kcm_net_ops);
+}
+
+void __exit kcm_proc_exit(void)
+{
+ unregister_pernet_subsys(&kcm_net_ops);
+}
+
+#endif /* CONFIG_PROC_FS */
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
new file mode 100644
index 000000000000..40662d73204f
--- /dev/null
+++ b/net/kcm/kcmsock.c
@@ -0,0 +1,2409 @@
+#include <linux/bpf.h>
+#include <linux/errno.h>
+#include <linux/errqueue.h>
+#include <linux/file.h>
+#include <linux/in.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/poll.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/uaccess.h>
+#include <linux/workqueue.h>
+#include <net/kcm.h>
+#include <net/netns/generic.h>
+#include <net/sock.h>
+#include <net/tcp.h>
+#include <uapi/linux/kcm.h>
+
+unsigned int kcm_net_id;
+
+static struct kmem_cache *kcm_psockp __read_mostly;
+static struct kmem_cache *kcm_muxp __read_mostly;
+static struct workqueue_struct *kcm_wq;
+
+static inline struct kcm_sock *kcm_sk(const struct sock *sk)
+{
+ return (struct kcm_sock *)sk;
+}
+
+static inline struct kcm_tx_msg *kcm_tx_msg(struct sk_buff *skb)
+{
+ return (struct kcm_tx_msg *)skb->cb;
+}
+
+static inline struct kcm_rx_msg *kcm_rx_msg(struct sk_buff *skb)
+{
+ return (struct kcm_rx_msg *)((void *)skb->cb +
+ offsetof(struct qdisc_skb_cb, data));
+}
+
+static void report_csk_error(struct sock *csk, int err)
+{
+ csk->sk_err = EPIPE;
+ csk->sk_error_report(csk);
+}
+
+/* Callback lock held */
+static void kcm_abort_rx_psock(struct kcm_psock *psock, int err,
+ struct sk_buff *skb)
+{
+ struct sock *csk = psock->sk;
+
+ /* Unrecoverable error in receive */
+
+ del_timer(&psock->rx_msg_timer);
+
+ if (psock->rx_stopped)
+ return;
+
+ psock->rx_stopped = 1;
+ KCM_STATS_INCR(psock->stats.rx_aborts);
+
+ /* Report an error on the lower socket */
+ report_csk_error(csk, err);
+}
+
+static void kcm_abort_tx_psock(struct kcm_psock *psock, int err,
+ bool wakeup_kcm)
+{
+ struct sock *csk = psock->sk;
+ struct kcm_mux *mux = psock->mux;
+
+ /* Unrecoverable error in transmit */
+
+ spin_lock_bh(&mux->lock);
+
+ if (psock->tx_stopped) {
+ spin_unlock_bh(&mux->lock);
+ return;
+ }
+
+ psock->tx_stopped = 1;
+ KCM_STATS_INCR(psock->stats.tx_aborts);
+
+ if (!psock->tx_kcm) {
+ /* Take off psocks_avail list */
+ list_del(&psock->psock_avail_list);
+ } else if (wakeup_kcm) {
+ /* In this case psock is being aborted while outside of
+ * write_msgs and psock is reserved. Schedule tx_work
+ * to handle the failure there. Need to commit tx_stopped
+ * before queuing work.
+ */
+ smp_mb();
+
+ queue_work(kcm_wq, &psock->tx_kcm->tx_work);
+ }
+
+ spin_unlock_bh(&mux->lock);
+
+ /* Report error on lower socket */
+ report_csk_error(csk, err);
+}
+
+/* RX mux lock held. */
+static void kcm_update_rx_mux_stats(struct kcm_mux *mux,
+ struct kcm_psock *psock)
+{
+ KCM_STATS_ADD(mux->stats.rx_bytes,
+ psock->stats.rx_bytes - psock->saved_rx_bytes);
+ mux->stats.rx_msgs +=
+ psock->stats.rx_msgs - psock->saved_rx_msgs;
+ psock->saved_rx_msgs = psock->stats.rx_msgs;
+ psock->saved_rx_bytes = psock->stats.rx_bytes;
+}
+
+static void kcm_update_tx_mux_stats(struct kcm_mux *mux,
+ struct kcm_psock *psock)
+{
+ KCM_STATS_ADD(mux->stats.tx_bytes,
+ psock->stats.tx_bytes - psock->saved_tx_bytes);
+ mux->stats.tx_msgs +=
+ psock->stats.tx_msgs - psock->saved_tx_msgs;
+ psock->saved_tx_msgs = psock->stats.tx_msgs;
+ psock->saved_tx_bytes = psock->stats.tx_bytes;
+}
+
+static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
+
+/* KCM is ready to receive messages on its queue-- either the KCM is new or
+ * has become unblocked after being blocked on full socket buffer. Queue any
+ * pending ready messages on a psock. RX mux lock held.
+ */
+static void kcm_rcv_ready(struct kcm_sock *kcm)
+{
+ struct kcm_mux *mux = kcm->mux;
+ struct kcm_psock *psock;
+ struct sk_buff *skb;
+
+ if (unlikely(kcm->rx_wait || kcm->rx_psock || kcm->rx_disabled))
+ return;
+
+ while (unlikely((skb = __skb_dequeue(&mux->rx_hold_queue)))) {
+ if (kcm_queue_rcv_skb(&kcm->sk, skb)) {
+ /* Assuming buffer limit has been reached */
+ skb_queue_head(&mux->rx_hold_queue, skb);
+ WARN_ON(!sk_rmem_alloc_get(&kcm->sk));
+ return;
+ }
+ }
+
+ while (!list_empty(&mux->psocks_ready)) {
+ psock = list_first_entry(&mux->psocks_ready, struct kcm_psock,
+ psock_ready_list);
+
+ if (kcm_queue_rcv_skb(&kcm->sk, psock->ready_rx_msg)) {
+ /* Assuming buffer limit has been reached */
+ WARN_ON(!sk_rmem_alloc_get(&kcm->sk));
+ return;
+ }
+
+ /* Consumed the ready message on the psock. Schedule rx_work to
+ * get more messages.
+ */
+ list_del(&psock->psock_ready_list);
+ psock->ready_rx_msg = NULL;
+
+ /* Commit clearing of ready_rx_msg for queuing work */
+ smp_mb();
+
+ queue_work(kcm_wq, &psock->rx_work);
+ }
+
+ /* Buffer limit is okay now, add to ready list */
+ list_add_tail(&kcm->wait_rx_list,
+ &kcm->mux->kcm_rx_waiters);
+ kcm->rx_wait = true;
+}
+
+static void kcm_rfree(struct sk_buff *skb)
+{
+ struct sock *sk = skb->sk;
+ struct kcm_sock *kcm = kcm_sk(sk);
+ struct kcm_mux *mux = kcm->mux;
+ unsigned int len = skb->truesize;
+
+ sk_mem_uncharge(sk, len);
+ atomic_sub(len, &sk->sk_rmem_alloc);
+
+ /* For reading rx_wait and rx_psock without holding lock */
+ smp_mb__after_atomic();
+
+ if (!kcm->rx_wait && !kcm->rx_psock &&
+ sk_rmem_alloc_get(sk) < sk->sk_rcvlowat) {
+ spin_lock_bh(&mux->rx_lock);
+ kcm_rcv_ready(kcm);
+ spin_unlock_bh(&mux->rx_lock);
+ }
+}
+
+static int kcm_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct sk_buff_head *list = &sk->sk_receive_queue;
+
+ if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+ return -ENOMEM;
+
+ if (!sk_rmem_schedule(sk, skb, skb->truesize))
+ return -ENOBUFS;
+
+ skb->dev = NULL;
+
+ skb_orphan(skb);
+ skb->sk = sk;
+ skb->destructor = kcm_rfree;
+ atomic_add(skb->truesize, &sk->sk_rmem_alloc);
+ sk_mem_charge(sk, skb->truesize);
+
+ skb_queue_tail(list, skb);
+
+ if (!sock_flag(sk, SOCK_DEAD))
+ sk->sk_data_ready(sk);
+
+ return 0;
+}
+
+/* Requeue received messages for a kcm socket to other kcm sockets. This is
+ * called with a kcm socket is receive disabled.
+ * RX mux lock held.
+ */
+static void requeue_rx_msgs(struct kcm_mux *mux, struct sk_buff_head *head)
+{
+ struct sk_buff *skb;
+ struct kcm_sock *kcm;
+
+ while ((skb = __skb_dequeue(head))) {
+ /* Reset destructor to avoid calling kcm_rcv_ready */
+ skb->destructor = sock_rfree;
+ skb_orphan(skb);
+try_again:
+ if (list_empty(&mux->kcm_rx_waiters)) {
+ skb_queue_tail(&mux->rx_hold_queue, skb);
+ continue;
+ }
+
+ kcm = list_first_entry(&mux->kcm_rx_waiters,
+ struct kcm_sock, wait_rx_list);
+
+ if (kcm_queue_rcv_skb(&kcm->sk, skb)) {
+ /* Should mean socket buffer full */
+ list_del(&kcm->wait_rx_list);
+ kcm->rx_wait = false;
+
+ /* Commit rx_wait to read in kcm_free */
+ smp_wmb();
+
+ goto try_again;
+ }
+ }
+}
+
+/* Lower sock lock held */
+static struct kcm_sock *reserve_rx_kcm(struct kcm_psock *psock,
+ struct sk_buff *head)
+{
+ struct kcm_mux *mux = psock->mux;
+ struct kcm_sock *kcm;
+
+ WARN_ON(psock->ready_rx_msg);
+
+ if (psock->rx_kcm)
+ return psock->rx_kcm;
+
+ spin_lock_bh(&mux->rx_lock);
+
+ if (psock->rx_kcm) {
+ spin_unlock_bh(&mux->rx_lock);
+ return psock->rx_kcm;
+ }
+
+ kcm_update_rx_mux_stats(mux, psock);
+
+ if (list_empty(&mux->kcm_rx_waiters)) {
+ psock->ready_rx_msg = head;
+ list_add_tail(&psock->psock_ready_list,
+ &mux->psocks_ready);
+ spin_unlock_bh(&mux->rx_lock);
+ return NULL;
+ }
+
+ kcm = list_first_entry(&mux->kcm_rx_waiters,
+ struct kcm_sock, wait_rx_list);
+ list_del(&kcm->wait_rx_list);
+ kcm->rx_wait = false;
+
+ psock->rx_kcm = kcm;
+ kcm->rx_psock = psock;
+
+ spin_unlock_bh(&mux->rx_lock);
+
+ return kcm;
+}
+
+static void kcm_done(struct kcm_sock *kcm);
+
+static void kcm_done_work(struct work_struct *w)
+{
+ kcm_done(container_of(w, struct kcm_sock, done_work));
+}
+
+/* Lower sock held */
+static void unreserve_rx_kcm(struct kcm_psock *psock,
+ bool rcv_ready)
+{
+ struct kcm_sock *kcm = psock->rx_kcm;
+ struct kcm_mux *mux = psock->mux;
+
+ if (!kcm)
+ return;
+
+ spin_lock_bh(&mux->rx_lock);
+
+ psock->rx_kcm = NULL;
+ kcm->rx_psock = NULL;
+
+ /* Commit kcm->rx_psock before sk_rmem_alloc_get to sync with
+ * kcm_rfree
+ */
+ smp_mb();
+
+ if (unlikely(kcm->done)) {
+ spin_unlock_bh(&mux->rx_lock);
+
+ /* Need to run kcm_done in a task since we need to qcquire
+ * callback locks which may already be held here.
+ */
+ INIT_WORK(&kcm->done_work, kcm_done_work);
+ schedule_work(&kcm->done_work);
+ return;
+ }
+
+ if (unlikely(kcm->rx_disabled)) {
+ requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue);
+ } else if (rcv_ready || unlikely(!sk_rmem_alloc_get(&kcm->sk))) {
+ /* Check for degenerative race with rx_wait that all
+ * data was dequeued (accounted for in kcm_rfree).
+ */
+ kcm_rcv_ready(kcm);
+ }
+ spin_unlock_bh(&mux->rx_lock);
+}
+
+static void kcm_start_rx_timer(struct kcm_psock *psock)
+{
+ if (psock->sk->sk_rcvtimeo)
+ mod_timer(&psock->rx_msg_timer, psock->sk->sk_rcvtimeo);
+}
+
+/* Macro to invoke filter function. */
+#define KCM_RUN_FILTER(prog, ctx) \
+ (*prog->bpf_func)(ctx, prog->insnsi)
+
+/* Lower socket lock held */
+static int kcm_tcp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
+ unsigned int orig_offset, size_t orig_len)
+{
+ struct kcm_psock *psock = (struct kcm_psock *)desc->arg.data;
+ struct kcm_rx_msg *rxm;
+ struct kcm_sock *kcm;
+ struct sk_buff *head, *skb;
+ size_t eaten = 0, cand_len;
+ ssize_t extra;
+ int err;
+ bool cloned_orig = false;
+
+ if (psock->ready_rx_msg)
+ return 0;
+
+ head = psock->rx_skb_head;
+ if (head) {
+ /* Message already in progress */
+
+ rxm = kcm_rx_msg(head);
+ if (unlikely(rxm->early_eaten)) {
+ /* Already some number of bytes on the receive sock
+ * data saved in rx_skb_head, just indicate they
+ * are consumed.
+ */
+ eaten = orig_len <= rxm->early_eaten ?
+ orig_len : rxm->early_eaten;
+ rxm->early_eaten -= eaten;
+
+ return eaten;
+ }
+
+ if (unlikely(orig_offset)) {
+ /* Getting data with a non-zero offset when a message is
+ * in progress is not expected. If it does happen, we
+ * need to clone and pull since we can't deal with
+ * offsets in the skbs for a message expect in the head.
+ */
+ orig_skb = skb_clone(orig_skb, GFP_ATOMIC);
+ if (!orig_skb) {
+ KCM_STATS_INCR(psock->stats.rx_mem_fail);
+ desc->error = -ENOMEM;
+ return 0;
+ }
+ if (!pskb_pull(orig_skb, orig_offset)) {
+ KCM_STATS_INCR(psock->stats.rx_mem_fail);
+ kfree_skb(orig_skb);
+ desc->error = -ENOMEM;
+ return 0;
+ }
+ cloned_orig = true;
+ orig_offset = 0;
+ }
+
+ if (!psock->rx_skb_nextp) {
+ /* We are going to append to the frags_list of head.
+ * Need to unshare the frag_list.
+ */
+ err = skb_unclone(head, GFP_ATOMIC);
+ if (err) {
+ KCM_STATS_INCR(psock->stats.rx_mem_fail);
+ desc->error = err;
+ return 0;
+ }
+
+ if (unlikely(skb_shinfo(head)->frag_list)) {
+ /* We can't append to an sk_buff that already
+ * has a frag_list. We create a new head, point
+ * the frag_list of that to the old head, and
+ * then are able to use the old head->next for
+ * appending to the message.
+ */
+ if (WARN_ON(head->next)) {
+ desc->error = -EINVAL;
+ return 0;
+ }
+
+ skb = alloc_skb(0, GFP_ATOMIC);
+ if (!skb) {
+ KCM_STATS_INCR(psock->stats.rx_mem_fail);
+ desc->error = -ENOMEM;
+ return 0;
+ }
+ skb->len = head->len;
+ skb->data_len = head->len;
+ skb->truesize = head->truesize;
+ *kcm_rx_msg(skb) = *kcm_rx_msg(head);
+ psock->rx_skb_nextp = &head->next;
+ skb_shinfo(skb)->frag_list = head;
+ psock->rx_skb_head = skb;
+ head = skb;
+ } else {
+ psock->rx_skb_nextp =
+ &skb_shinfo(head)->frag_list;
+ }
+ }
+ }
+
+ while (eaten < orig_len) {
+ /* Always clone since we will consume something */
+ skb = skb_clone(orig_skb, GFP_ATOMIC);
+ if (!skb) {
+ KCM_STATS_INCR(psock->stats.rx_mem_fail);
+ desc->error = -ENOMEM;
+ break;
+ }
+
+ cand_len = orig_len - eaten;
+
+ head = psock->rx_skb_head;
+ if (!head) {
+ head = skb;
+ psock->rx_skb_head = head;
+ /* Will set rx_skb_nextp on next packet if needed */
+ psock->rx_skb_nextp = NULL;
+ rxm = kcm_rx_msg(head);
+ memset(rxm, 0, sizeof(*rxm));
+ rxm->offset = orig_offset + eaten;
+ } else {
+ /* Unclone since we may be appending to an skb that we
+ * already share a frag_list with.
+ */
+ err = skb_unclone(skb, GFP_ATOMIC);
+ if (err) {
+ KCM_STATS_INCR(psock->stats.rx_mem_fail);
+ desc->error = err;
+ break;
+ }
+
+ rxm = kcm_rx_msg(head);
+ *psock->rx_skb_nextp = skb;
+ psock->rx_skb_nextp = &skb->next;
+ head->data_len += skb->len;
+ head->len += skb->len;
+ head->truesize += skb->truesize;
+ }
+
+ if (!rxm->full_len) {
+ ssize_t len;
+
+ len = KCM_RUN_FILTER(psock->bpf_prog, head);
+
+ if (!len) {
+ /* Need more header to determine length */
+ if (!rxm->accum_len) {
+ /* Start RX timer for new message */
+ kcm_start_rx_timer(psock);
+ }
+ rxm->accum_len += cand_len;
+ eaten += cand_len;
+ KCM_STATS_INCR(psock->stats.rx_need_more_hdr);
+ WARN_ON(eaten != orig_len);
+ break;
+ } else if (len > psock->sk->sk_rcvbuf) {
+ /* Message length exceeds maximum allowed */
+ KCM_STATS_INCR(psock->stats.rx_msg_too_big);
+ desc->error = -EMSGSIZE;
+ psock->rx_skb_head = NULL;
+ kcm_abort_rx_psock(psock, EMSGSIZE, head);
+ break;
+ } else if (len <= (ssize_t)head->len -
+ skb->len - rxm->offset) {
+ /* Length must be into new skb (and also
+ * greater than zero)
+ */
+ KCM_STATS_INCR(psock->stats.rx_bad_hdr_len);
+ desc->error = -EPROTO;
+ psock->rx_skb_head = NULL;
+ kcm_abort_rx_psock(psock, EPROTO, head);
+ break;
+ }
+
+ rxm->full_len = len;
+ }
+
+ extra = (ssize_t)(rxm->accum_len + cand_len) - rxm->full_len;
+
+ if (extra < 0) {
+ /* Message not complete yet. */
+ if (rxm->full_len - rxm->accum_len >
+ tcp_inq(psock->sk)) {
+ /* Don't have the whole messages in the socket
+ * buffer. Set psock->rx_need_bytes to wait for
+ * the rest of the message. Also, set "early
+ * eaten" since we've already buffered the skb
+ * but don't consume yet per tcp_read_sock.
+ */
+
+ if (!rxm->accum_len) {
+ /* Start RX timer for new message */
+ kcm_start_rx_timer(psock);
+ }
+
+ psock->rx_need_bytes = rxm->full_len -
+ rxm->accum_len;
+ rxm->accum_len += cand_len;
+ rxm->early_eaten = cand_len;
+ KCM_STATS_ADD(psock->stats.rx_bytes, cand_len);
+ desc->count = 0; /* Stop reading socket */
+ break;
+ }
+ rxm->accum_len += cand_len;
+ eaten += cand_len;
+ WARN_ON(eaten != orig_len);
+ break;
+ }
+
+ /* Positive extra indicates ore bytes than needed for the
+ * message
+ */
+
+ WARN_ON(extra > cand_len);
+
+ eaten += (cand_len - extra);
+
+ /* Hurray, we have a new message! */
+ del_timer(&psock->rx_msg_timer);
+ psock->rx_skb_head = NULL;
+ KCM_STATS_INCR(psock->stats.rx_msgs);
+
+try_queue:
+ kcm = reserve_rx_kcm(psock, head);
+ if (!kcm) {
+ /* Unable to reserve a KCM, message is held in psock. */
+ break;
+ }
+
+ if (kcm_queue_rcv_skb(&kcm->sk, head)) {
+ /* Should mean socket buffer full */
+ unreserve_rx_kcm(psock, false);
+ goto try_queue;
+ }
+ }
+
+ if (cloned_orig)
+ kfree_skb(orig_skb);
+
+ KCM_STATS_ADD(psock->stats.rx_bytes, eaten);
+
+ return eaten;
+}
+
+/* Called with lock held on lower socket */
+static int psock_tcp_read_sock(struct kcm_psock *psock)
+{
+ read_descriptor_t desc;
+
+ desc.arg.data = psock;
+ desc.error = 0;
+ desc.count = 1; /* give more than one skb per call */
+
+ /* sk should be locked here, so okay to do tcp_read_sock */
+ tcp_read_sock(psock->sk, &desc, kcm_tcp_recv);
+
+ unreserve_rx_kcm(psock, true);
+
+ return desc.error;
+}
+
+/* Lower sock lock held */
+static void psock_tcp_data_ready(struct sock *sk)
+{
+ struct kcm_psock *psock;
+
+ read_lock_bh(&sk->sk_callback_lock);
+
+ psock = (struct kcm_psock *)sk->sk_user_data;
+ if (unlikely(!psock || psock->rx_stopped))
+ goto out;
+
+ if (psock->ready_rx_msg)
+ goto out;
+
+ if (psock->rx_need_bytes) {
+ if (tcp_inq(sk) >= psock->rx_need_bytes)
+ psock->rx_need_bytes = 0;
+ else
+ goto out;
+ }
+
+ if (psock_tcp_read_sock(psock) == -ENOMEM)
+ queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0);
+
+out:
+ read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void do_psock_rx_work(struct kcm_psock *psock)
+{
+ read_descriptor_t rd_desc;
+ struct sock *csk = psock->sk;
+
+ /* We need the read lock to synchronize with psock_tcp_data_ready. We
+ * need the socket lock for calling tcp_read_sock.
+ */
+ lock_sock(csk);
+ read_lock_bh(&csk->sk_callback_lock);
+
+ if (unlikely(csk->sk_user_data != psock))
+ goto out;
+
+ if (unlikely(psock->rx_stopped))
+ goto out;
+
+ if (psock->ready_rx_msg)
+ goto out;
+
+ rd_desc.arg.data = psock;
+
+ if (psock_tcp_read_sock(psock) == -ENOMEM)
+ queue_delayed_work(kcm_wq, &psock->rx_delayed_work, 0);
+
+out:
+ read_unlock_bh(&csk->sk_callback_lock);
+ release_sock(csk);
+}
+
+static void psock_rx_work(struct work_struct *w)
+{
+ do_psock_rx_work(container_of(w, struct kcm_psock, rx_work));
+}
+
+static void psock_rx_delayed_work(struct work_struct *w)
+{
+ do_psock_rx_work(container_of(w, struct kcm_psock,
+ rx_delayed_work.work));
+}
+
+static void psock_tcp_state_change(struct sock *sk)
+{
+ /* TCP only does a POLLIN for a half close. Do a POLLHUP here
+ * since application will normally not poll with POLLIN
+ * on the TCP sockets.
+ */
+
+ report_csk_error(sk, EPIPE);
+}
+
+static void psock_tcp_write_space(struct sock *sk)
+{
+ struct kcm_psock *psock;
+ struct kcm_mux *mux;
+ struct kcm_sock *kcm;
+
+ read_lock_bh(&sk->sk_callback_lock);
+
+ psock = (struct kcm_psock *)sk->sk_user_data;
+ if (unlikely(!psock))
+ goto out;
+
+ mux = psock->mux;
+
+ spin_lock_bh(&mux->lock);
+
+ /* Check if the socket is reserved so someone is waiting for sending. */
+ kcm = psock->tx_kcm;
+ if (kcm)
+ queue_work(kcm_wq, &kcm->tx_work);
+
+ spin_unlock_bh(&mux->lock);
+out:
+ read_unlock_bh(&sk->sk_callback_lock);
+}
+
+static void unreserve_psock(struct kcm_sock *kcm);
+
+/* kcm sock is locked. */
+static struct kcm_psock *reserve_psock(struct kcm_sock *kcm)
+{
+ struct kcm_mux *mux = kcm->mux;
+ struct kcm_psock *psock;
+
+ psock = kcm->tx_psock;
+
+ smp_rmb(); /* Must read tx_psock before tx_wait */
+
+ if (psock) {
+ WARN_ON(kcm->tx_wait);
+ if (unlikely(psock->tx_stopped))
+ unreserve_psock(kcm);
+ else
+ return kcm->tx_psock;
+ }
+
+ spin_lock_bh(&mux->lock);
+
+ /* Check again under lock to see if psock was reserved for this
+ * psock via psock_unreserve.
+ */
+ psock = kcm->tx_psock;
+ if (unlikely(psock)) {
+ WARN_ON(kcm->tx_wait);
+ spin_unlock_bh(&mux->lock);
+ return kcm->tx_psock;
+ }
+
+ if (!list_empty(&mux->psocks_avail)) {
+ psock = list_first_entry(&mux->psocks_avail,
+ struct kcm_psock,
+ psock_avail_list);
+ list_del(&psock->psock_avail_list);
+ if (kcm->tx_wait) {
+ list_del(&kcm->wait_psock_list);
+ kcm->tx_wait = false;
+ }
+ kcm->tx_psock = psock;
+ psock->tx_kcm = kcm;
+ KCM_STATS_INCR(psock->stats.reserved);
+ } else if (!kcm->tx_wait) {
+ list_add_tail(&kcm->wait_psock_list,
+ &mux->kcm_tx_waiters);
+ kcm->tx_wait = true;
+ }
+
+ spin_unlock_bh(&mux->lock);
+
+ return psock;
+}
+
+/* mux lock held */
+static void psock_now_avail(struct kcm_psock *psock)
+{
+ struct kcm_mux *mux = psock->mux;
+ struct kcm_sock *kcm;
+
+ if (list_empty(&mux->kcm_tx_waiters)) {
+ list_add_tail(&psock->psock_avail_list,
+ &mux->psocks_avail);
+ } else {
+ kcm = list_first_entry(&mux->kcm_tx_waiters,
+ struct kcm_sock,
+ wait_psock_list);
+ list_del(&kcm->wait_psock_list);
+ kcm->tx_wait = false;
+ psock->tx_kcm = kcm;
+
+ /* Commit before changing tx_psock since that is read in
+ * reserve_psock before queuing work.
+ */
+ smp_mb();
+
+ kcm->tx_psock = psock;
+ KCM_STATS_INCR(psock->stats.reserved);
+ queue_work(kcm_wq, &kcm->tx_work);
+ }
+}
+
+/* kcm sock is locked. */
+static void unreserve_psock(struct kcm_sock *kcm)
+{
+ struct kcm_psock *psock;
+ struct kcm_mux *mux = kcm->mux;
+
+ spin_lock_bh(&mux->lock);
+
+ psock = kcm->tx_psock;
+
+ if (WARN_ON(!psock)) {
+ spin_unlock_bh(&mux->lock);
+ return;
+ }
+
+ smp_rmb(); /* Read tx_psock before tx_wait */
+
+ kcm_update_tx_mux_stats(mux, psock);
+
+ WARN_ON(kcm->tx_wait);
+
+ kcm->tx_psock = NULL;
+ psock->tx_kcm = NULL;
+ KCM_STATS_INCR(psock->stats.unreserved);
+
+ if (unlikely(psock->tx_stopped)) {
+ if (psock->done) {
+ /* Deferred free */
+ list_del(&psock->psock_list);
+ mux->psocks_cnt--;
+ sock_put(psock->sk);
+ fput(psock->sk->sk_socket->file);
+ kmem_cache_free(kcm_psockp, psock);
+ }
+
+ /* Don't put back on available list */
+
+ spin_unlock_bh(&mux->lock);
+
+ return;
+ }
+
+ psock_now_avail(psock);
+
+ spin_unlock_bh(&mux->lock);
+}
+
+static void kcm_report_tx_retry(struct kcm_sock *kcm)
+{
+ struct kcm_mux *mux = kcm->mux;
+
+ spin_lock_bh(&mux->lock);
+ KCM_STATS_INCR(mux->stats.tx_retries);
+ spin_unlock_bh(&mux->lock);
+}
+
+/* Write any messages ready on the kcm socket. Called with kcm sock lock
+ * held. Return bytes actually sent or error.
+ */
+static int kcm_write_msgs(struct kcm_sock *kcm)
+{
+ struct sock *sk = &kcm->sk;
+ struct kcm_psock *psock;
+ struct sk_buff *skb, *head;
+ struct kcm_tx_msg *txm;
+ unsigned short fragidx, frag_offset;
+ unsigned int sent, total_sent = 0;
+ int ret = 0;
+
+ kcm->tx_wait_more = false;
+ psock = kcm->tx_psock;
+ if (unlikely(psock && psock->tx_stopped)) {
+ /* A reserved psock was aborted asynchronously. Unreserve
+ * it and we'll retry the message.
+ */
+ unreserve_psock(kcm);
+ kcm_report_tx_retry(kcm);
+ if (skb_queue_empty(&sk->sk_write_queue))
+ return 0;
+
+ kcm_tx_msg(skb_peek(&sk->sk_write_queue))->sent = 0;
+
+ } else if (skb_queue_empty(&sk->sk_write_queue)) {
+ return 0;
+ }
+
+ head = skb_peek(&sk->sk_write_queue);
+ txm = kcm_tx_msg(head);
+
+ if (txm->sent) {
+ /* Send of first skbuff in queue already in progress */
+ if (WARN_ON(!psock)) {
+ ret = -EINVAL;
+ goto out;
+ }
+ sent = txm->sent;
+ frag_offset = txm->frag_offset;
+ fragidx = txm->fragidx;
+ skb = txm->frag_skb;
+
+ goto do_frag;
+ }
+
+try_again:
+ psock = reserve_psock(kcm);
+ if (!psock)
+ goto out;
+
+ do {
+ skb = head;
+ txm = kcm_tx_msg(head);
+ sent = 0;
+
+do_frag_list:
+ if (WARN_ON(!skb_shinfo(skb)->nr_frags)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ for (fragidx = 0; fragidx < skb_shinfo(skb)->nr_frags;
+ fragidx++) {
+ skb_frag_t *frag;
+
+ frag_offset = 0;
+do_frag:
+ frag = &skb_shinfo(skb)->frags[fragidx];
+ if (WARN_ON(!frag->size)) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = kernel_sendpage(psock->sk->sk_socket,
+ frag->page.p,
+ frag->page_offset + frag_offset,
+ frag->size - frag_offset,
+ MSG_DONTWAIT);
+ if (ret <= 0) {
+ if (ret == -EAGAIN) {
+ /* Save state to try again when there's
+ * write space on the socket
+ */
+ txm->sent = sent;
+ txm->frag_offset = frag_offset;
+ txm->fragidx = fragidx;
+ txm->frag_skb = skb;
+
+ ret = 0;
+ goto out;
+ }
+
+ /* Hard failure in sending message, abort this
+ * psock since it has lost framing
+ * synchonization and retry sending the
+ * message from the beginning.
+ */
+ kcm_abort_tx_psock(psock, ret ? -ret : EPIPE,
+ true);
+ unreserve_psock(kcm);
+
+ txm->sent = 0;
+ kcm_report_tx_retry(kcm);
+ ret = 0;
+
+ goto try_again;
+ }
+
+ sent += ret;
+ frag_offset += ret;
+ KCM_STATS_ADD(psock->stats.tx_bytes, ret);
+ if (frag_offset < frag->size) {
+ /* Not finished with this frag */
+ goto do_frag;
+ }
+ }
+
+ if (skb == head) {
+ if (skb_has_frag_list(skb)) {
+ skb = skb_shinfo(skb)->frag_list;
+ goto do_frag_list;
+ }
+ } else if (skb->next) {
+ skb = skb->next;
+ goto do_frag_list;
+ }
+
+ /* Successfully sent the whole packet, account for it. */
+ skb_dequeue(&sk->sk_write_queue);
+ kfree_skb(head);
+ sk->sk_wmem_queued -= sent;
+ total_sent += sent;
+ KCM_STATS_INCR(psock->stats.tx_msgs);
+ } while ((head = skb_peek(&sk->sk_write_queue)));
+out:
+ if (!head) {
+ /* Done with all queued messages. */
+ WARN_ON(!skb_queue_empty(&sk->sk_write_queue));
+ unreserve_psock(kcm);
+ }
+
+ /* Check if write space is available */
+ sk->sk_write_space(sk);
+
+ return total_sent ? : ret;
+}
+
+static void kcm_tx_work(struct work_struct *w)
+{
+ struct kcm_sock *kcm = container_of(w, struct kcm_sock, tx_work);
+ struct sock *sk = &kcm->sk;
+ int err;
+
+ lock_sock(sk);
+
+ /* Primarily for SOCK_DGRAM sockets, also handle asynchronous tx
+ * aborts
+ */
+ err = kcm_write_msgs(kcm);
+ if (err < 0) {
+ /* Hard failure in write, report error on KCM socket */
+ pr_warn("KCM: Hard failure on kcm_write_msgs %d\n", err);
+ report_csk_error(&kcm->sk, -err);
+ goto out;
+ }
+
+ /* Primarily for SOCK_SEQPACKET sockets */
+ if (likely(sk->sk_socket) &&
+ test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
+ clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ sk->sk_write_space(sk);
+ }
+
+out:
+ release_sock(sk);
+}
+
+static void kcm_push(struct kcm_sock *kcm)
+{
+ if (kcm->tx_wait_more)
+ kcm_write_msgs(kcm);
+}
+
+static ssize_t kcm_sendpage(struct socket *sock, struct page *page,
+ int offset, size_t size, int flags)
+
+{
+ struct sock *sk = sock->sk;
+ struct kcm_sock *kcm = kcm_sk(sk);
+ struct sk_buff *skb = NULL, *head = NULL;
+ long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
+ bool eor;
+ int err = 0;
+ int i;
+
+ if (flags & MSG_SENDPAGE_NOTLAST)
+ flags |= MSG_MORE;
+
+ /* No MSG_EOR from splice, only look at MSG_MORE */
+ eor = !(flags & MSG_MORE);
+
+ lock_sock(sk);
+
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+
+ err = -EPIPE;
+ if (sk->sk_err)
+ goto out_error;
+
+ if (kcm->seq_skb) {
+ /* Previously opened message */
+ head = kcm->seq_skb;
+ skb = kcm_tx_msg(head)->last_skb;
+ i = skb_shinfo(skb)->nr_frags;
+
+ if (skb_can_coalesce(skb, i, page, offset)) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size);
+ skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
+ goto coalesced;
+ }
+
+ if (i >= MAX_SKB_FRAGS) {
+ struct sk_buff *tskb;
+
+ tskb = alloc_skb(0, sk->sk_allocation);
+ while (!tskb) {
+ kcm_push(kcm);
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto out_error;
+ }
+
+ if (head == skb)
+ skb_shinfo(head)->frag_list = tskb;
+ else
+ skb->next = tskb;
+
+ skb = tskb;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ i = 0;
+ }
+ } else {
+ /* Call the sk_stream functions to manage the sndbuf mem. */
+ if (!sk_stream_memory_free(sk)) {
+ kcm_push(kcm);
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto out_error;
+ }
+
+ head = alloc_skb(0, sk->sk_allocation);
+ while (!head) {
+ kcm_push(kcm);
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto out_error;
+ }
+
+ skb = head;
+ i = 0;
+ }
+
+ get_page(page);
+ skb_fill_page_desc(skb, i, page, offset, size);
+ skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
+
+coalesced:
+ skb->len += size;
+ skb->data_len += size;
+ skb->truesize += size;
+ sk->sk_wmem_queued += size;
+ sk_mem_charge(sk, size);
+
+ if (head != skb) {
+ head->len += size;
+ head->data_len += size;
+ head->truesize += size;
+ }
+
+ if (eor) {
+ bool not_busy = skb_queue_empty(&sk->sk_write_queue);
+
+ /* Message complete, queue it on send buffer */
+ __skb_queue_tail(&sk->sk_write_queue, head);
+ kcm->seq_skb = NULL;
+ KCM_STATS_INCR(kcm->stats.tx_msgs);
+
+ if (flags & MSG_BATCH) {
+ kcm->tx_wait_more = true;
+ } else if (kcm->tx_wait_more || not_busy) {
+ err = kcm_write_msgs(kcm);
+ if (err < 0) {
+ /* We got a hard error in write_msgs but have
+ * already queued this message. Report an error
+ * in the socket, but don't affect return value
+ * from sendmsg
+ */
+ pr_warn("KCM: Hard failure on kcm_write_msgs\n");
+ report_csk_error(&kcm->sk, -err);
+ }
+ }
+ } else {
+ /* Message not complete, save state */
+ kcm->seq_skb = head;
+ kcm_tx_msg(head)->last_skb = skb;
+ }
+
+ KCM_STATS_ADD(kcm->stats.tx_bytes, size);
+
+ release_sock(sk);
+ return size;
+
+out_error:
+ kcm_push(kcm);
+
+ err = sk_stream_error(sk, flags, err);
+
+ /* make sure we wake any epoll edge trigger waiter */
+ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
+ sk->sk_write_space(sk);
+
+ release_sock(sk);
+ return err;
+}
+
+static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+{
+ struct sock *sk = sock->sk;
+ struct kcm_sock *kcm = kcm_sk(sk);
+ struct sk_buff *skb = NULL, *head = NULL;
+ size_t copy, copied = 0;
+ long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
+ int eor = (sock->type == SOCK_DGRAM) ?
+ !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR);
+ int err = -EPIPE;
+
+ lock_sock(sk);
+
+ /* Per tcp_sendmsg this should be in poll */
+ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk);
+
+ if (sk->sk_err)
+ goto out_error;
+
+ if (kcm->seq_skb) {
+ /* Previously opened message */
+ head = kcm->seq_skb;
+ skb = kcm_tx_msg(head)->last_skb;
+ goto start;
+ }
+
+ /* Call the sk_stream functions to manage the sndbuf mem. */
+ if (!sk_stream_memory_free(sk)) {
+ kcm_push(kcm);
+ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto out_error;
+ }
+
+ /* New message, alloc head skb */
+ head = alloc_skb(0, sk->sk_allocation);
+ while (!head) {
+ kcm_push(kcm);
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto out_error;
+
+ head = alloc_skb(0, sk->sk_allocation);
+ }
+
+ skb = head;
+
+ /* Set ip_summed to CHECKSUM_UNNECESSARY to avoid calling
+ * csum_and_copy_from_iter from skb_do_copy_data_nocache.
+ */
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+start:
+ while (msg_data_left(msg)) {
+ bool merge = true;
+ int i = skb_shinfo(skb)->nr_frags;
+ struct page_frag *pfrag = sk_page_frag(sk);
+
+ if (!sk_page_frag_refill(sk, pfrag))
+ goto wait_for_memory;
+
+ if (!skb_can_coalesce(skb, i, pfrag->page,
+ pfrag->offset)) {
+ if (i == MAX_SKB_FRAGS) {
+ struct sk_buff *tskb;
+
+ tskb = alloc_skb(0, sk->sk_allocation);
+ if (!tskb)
+ goto wait_for_memory;
+
+ if (head == skb)
+ skb_shinfo(head)->frag_list = tskb;
+ else
+ skb->next = tskb;
+
+ skb = tskb;
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+ continue;
+ }
+ merge = false;
+ }
+
+ copy = min_t(int, msg_data_left(msg),
+ pfrag->size - pfrag->offset);
+
+ if (!sk_wmem_schedule(sk, copy))
+ goto wait_for_memory;
+
+ err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb,
+ pfrag->page,
+ pfrag->offset,
+ copy);
+ if (err)
+ goto out_error;
+
+ /* Update the skb. */
+ if (merge) {
+ skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+ } else {
+ skb_fill_page_desc(skb, i, pfrag->page,
+ pfrag->offset, copy);
+ get_page(pfrag->page);
+ }
+
+ pfrag->offset += copy;
+ copied += copy;
+ if (head != skb) {
+ head->len += copy;
+ head->data_len += copy;
+ }
+
+ continue;
+
+wait_for_memory:
+ kcm_push(kcm);
+ err = sk_stream_wait_memory(sk, &timeo);
+ if (err)
+ goto out_error;
+ }
+
+ if (eor) {
+ bool not_busy = skb_queue_empty(&sk->sk_write_queue);
+
+ /* Message complete, queue it on send buffer */
+ __skb_queue_tail(&sk->sk_write_queue, head);
+ kcm->seq_skb = NULL;
+ KCM_STATS_INCR(kcm->stats.tx_msgs);
+
+ if (msg->msg_flags & MSG_BATCH) {
+ kcm->tx_wait_more = true;
+ } else if (kcm->tx_wait_more || not_busy) {
+ err = kcm_write_msgs(kcm);
+ if (err < 0) {
+ /* We got a hard error in write_msgs but have
+ * already queued this message. Report an error
+ * in the socket, but don't affect return value
+ * from sendmsg
+ */
+ pr_warn("KCM: Hard failure on kcm_write_msgs\n");
+ report_csk_error(&kcm->sk, -err);
+ }
+ }
+ } else {
+ /* Message not complete, save state */
+partial_message:
+ kcm->seq_skb = head;
+ kcm_tx_msg(head)->last_skb = skb;
+ }
+
+ KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
+
+ release_sock(sk);
+ return copied;
+
+out_error:
+ kcm_push(kcm);
+
+ if (copied && sock->type == SOCK_SEQPACKET) {
+ /* Wrote some bytes before encountering an
+ * error, return partial success.
+ */
+ goto partial_message;
+ }
+
+ if (head != kcm->seq_skb)
+ kfree_skb(head);
+
+ err = sk_stream_error(sk, msg->msg_flags, err);
+
+ /* make sure we wake any epoll edge trigger waiter */
+ if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && err == -EAGAIN))
+ sk->sk_write_space(sk);
+
+ release_sock(sk);
+ return err;
+}
+
+static struct sk_buff *kcm_wait_data(struct sock *sk, int flags,
+ long timeo, int *err)
+{
+ struct sk_buff *skb;
+
+ while (!(skb = skb_peek(&sk->sk_receive_queue))) {
+ if (sk->sk_err) {
+ *err = sock_error(sk);
+ return NULL;
+ }
+
+ if (sock_flag(sk, SOCK_DONE))
+ return NULL;
+
+ if ((flags & MSG_DONTWAIT) || !timeo) {
+ *err = -EAGAIN;
+ return NULL;
+ }
+
+ sk_wait_data(sk, &timeo, NULL);
+
+ /* Handle signals */
+ if (signal_pending(current)) {
+ *err = sock_intr_errno(timeo);
+ return NULL;
+ }
+ }
+
+ return skb;
+}
+
+static int kcm_recvmsg(struct socket *sock, struct msghdr *msg,
+ size_t len, int flags)
+{
+ struct sock *sk = sock->sk;
+ struct kcm_sock *kcm = kcm_sk(sk);
+ int err = 0;
+ long timeo;
+ struct kcm_rx_msg *rxm;
+ int copied = 0;
+ struct sk_buff *skb;
+
+ timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+
+ lock_sock(sk);
+
+ skb = kcm_wait_data(sk, flags, timeo, &err);
+ if (!skb)
+ goto out;
+
+ /* Okay, have a message on the receive queue */
+
+ rxm = kcm_rx_msg(skb);
+
+ if (len > rxm->full_len)
+ len = rxm->full_len;
+
+ err = skb_copy_datagram_msg(skb, rxm->offset, msg, len);
+ if (err < 0)
+ goto out;
+
+ copied = len;
+ if (likely(!(flags & MSG_PEEK))) {
+ KCM_STATS_ADD(kcm->stats.rx_bytes, copied);
+ if (copied < rxm->full_len) {
+ if (sock->type == SOCK_DGRAM) {
+ /* Truncated message */
+ msg->msg_flags |= MSG_TRUNC;
+ goto msg_finished;
+ }
+ rxm->offset += copied;
+ rxm->full_len -= copied;
+ } else {
+msg_finished:
+ /* Finished with message */
+ msg->msg_flags |= MSG_EOR;
+ KCM_STATS_INCR(kcm->stats.rx_msgs);
+ skb_unlink(skb, &sk->sk_receive_queue);
+ kfree_skb(skb);
+ }
+ }
+
+out:
+ release_sock(sk);
+
+ return copied ? : err;
+}
+
+static ssize_t kcm_sock_splice(struct sock *sk,
+ struct pipe_inode_info *pipe,
+ struct splice_pipe_desc *spd)
+{
+ int ret;
+
+ release_sock(sk);
+ ret = splice_to_pipe(pipe, spd);
+ lock_sock(sk);
+
+ return ret;
+}
+
+static ssize_t kcm_splice_read(struct socket *sock, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct sock *sk = sock->sk;
+ struct kcm_sock *kcm = kcm_sk(sk);
+ long timeo;
+ struct kcm_rx_msg *rxm;
+ int err = 0;
+ size_t copied;
+ struct sk_buff *skb;
+
+ /* Only support splice for SOCKSEQPACKET */
+
+ timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+
+ lock_sock(sk);
+
+ skb = kcm_wait_data(sk, flags, timeo, &err);
+ if (!skb)
+ goto err_out;
+
+ /* Okay, have a message on the receive queue */
+
+ rxm = kcm_rx_msg(skb);
+
+ if (len > rxm->full_len)
+ len = rxm->full_len;
+
+ copied = skb_splice_bits(skb, sk, rxm->offset, pipe, len, flags,
+ kcm_sock_splice);
+ if (copied < 0) {
+ err = copied;
+ goto err_out;
+ }
+
+ KCM_STATS_ADD(kcm->stats.rx_bytes, copied);
+
+ rxm->offset += copied;
+ rxm->full_len -= copied;
+
+ /* We have no way to return MSG_EOR. If all the bytes have been
+ * read we still leave the message in the receive socket buffer.
+ * A subsequent recvmsg needs to be done to return MSG_EOR and
+ * finish reading the message.
+ */
+
+ release_sock(sk);
+
+ return copied;
+
+err_out:
+ release_sock(sk);
+
+ return err;
+}
+
+/* kcm sock lock held */
+static void kcm_recv_disable(struct kcm_sock *kcm)
+{
+ struct kcm_mux *mux = kcm->mux;
+
+ if (kcm->rx_disabled)
+ return;
+
+ spin_lock_bh(&mux->rx_lock);
+
+ kcm->rx_disabled = 1;
+
+ /* If a psock is reserved we'll do cleanup in unreserve */
+ if (!kcm->rx_psock) {
+ if (kcm->rx_wait) {
+ list_del(&kcm->wait_rx_list);
+ kcm->rx_wait = false;
+ }
+
+ requeue_rx_msgs(mux, &kcm->sk.sk_receive_queue);
+ }
+
+ spin_unlock_bh(&mux->rx_lock);
+}
+
+/* kcm sock lock held */
+static void kcm_recv_enable(struct kcm_sock *kcm)
+{
+ struct kcm_mux *mux = kcm->mux;
+
+ if (!kcm->rx_disabled)
+ return;
+
+ spin_lock_bh(&mux->rx_lock);
+
+ kcm->rx_disabled = 0;
+ kcm_rcv_ready(kcm);
+
+ spin_unlock_bh(&mux->rx_lock);
+}
+
+static int kcm_setsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, unsigned int optlen)
+{
+ struct kcm_sock *kcm = kcm_sk(sock->sk);
+ int val, valbool;
+ int err = 0;
+
+ if (level != SOL_KCM)
+ return -ENOPROTOOPT;
+
+ if (optlen < sizeof(int))
+ return -EINVAL;
+
+ if (get_user(val, (int __user *)optval))
+ return -EINVAL;
+
+ valbool = val ? 1 : 0;
+
+ switch (optname) {
+ case KCM_RECV_DISABLE:
+ lock_sock(&kcm->sk);
+ if (valbool)
+ kcm_recv_disable(kcm);
+ else
+ kcm_recv_enable(kcm);
+ release_sock(&kcm->sk);
+ break;
+ default:
+ err = -ENOPROTOOPT;
+ }
+
+ return err;
+}
+
+static int kcm_getsockopt(struct socket *sock, int level, int optname,
+ char __user *optval, int __user *optlen)
+{
+ struct kcm_sock *kcm = kcm_sk(sock->sk);
+ int val, len;
+
+ if (level != SOL_KCM)
+ return -ENOPROTOOPT;
+
+ if (get_user(len, optlen))
+ return -EFAULT;
+
+ len = min_t(unsigned int, len, sizeof(int));
+ if (len < 0)
+ return -EINVAL;
+
+ switch (optname) {
+ case KCM_RECV_DISABLE:
+ val = kcm->rx_disabled;
+ break;
+ default:
+ return -ENOPROTOOPT;
+ }
+
+ if (put_user(len, optlen))
+ return -EFAULT;
+ if (copy_to_user(optval, &val, len))
+ return -EFAULT;
+ return 0;
+}
+
+static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
+{
+ struct kcm_sock *tkcm;
+ struct list_head *head;
+ int index = 0;
+
+ /* For SOCK_SEQPACKET sock type, datagram_poll checks the sk_state, so
+ * we set sk_state, otherwise epoll_wait always returns right away with
+ * POLLHUP
+ */
+ kcm->sk.sk_state = TCP_ESTABLISHED;
+
+ /* Add to mux's kcm sockets list */
+ kcm->mux = mux;
+ spin_lock_bh(&mux->lock);
+
+ head = &mux->kcm_socks;
+ list_for_each_entry(tkcm, &mux->kcm_socks, kcm_sock_list) {
+ if (tkcm->index != index)
+ break;
+ head = &tkcm->kcm_sock_list;
+ index++;
+ }
+
+ list_add(&kcm->kcm_sock_list, head);
+ kcm->index = index;
+
+ mux->kcm_socks_cnt++;
+ spin_unlock_bh(&mux->lock);
+
+ INIT_WORK(&kcm->tx_work, kcm_tx_work);
+
+ spin_lock_bh(&mux->rx_lock);
+ kcm_rcv_ready(kcm);
+ spin_unlock_bh(&mux->rx_lock);
+}
+
+static void kcm_rx_msg_timeout(unsigned long arg)
+{
+ struct kcm_psock *psock = (struct kcm_psock *)arg;
+
+ /* Message assembly timed out */
+ KCM_STATS_INCR(psock->stats.rx_msg_timeouts);
+ kcm_abort_rx_psock(psock, ETIMEDOUT, NULL);
+}
+
+static int kcm_attach(struct socket *sock, struct socket *csock,
+ struct bpf_prog *prog)
+{
+ struct kcm_sock *kcm = kcm_sk(sock->sk);
+ struct kcm_mux *mux = kcm->mux;
+ struct sock *csk;
+ struct kcm_psock *psock = NULL, *tpsock;
+ struct list_head *head;
+ int index = 0;
+
+ if (csock->ops->family != PF_INET &&
+ csock->ops->family != PF_INET6)
+ return -EINVAL;
+
+ csk = csock->sk;
+ if (!csk)
+ return -EINVAL;
+
+ /* Only support TCP for now */
+ if (csk->sk_protocol != IPPROTO_TCP)
+ return -EINVAL;
+
+ psock = kmem_cache_zalloc(kcm_psockp, GFP_KERNEL);
+ if (!psock)
+ return -ENOMEM;
+
+ psock->mux = mux;
+ psock->sk = csk;
+ psock->bpf_prog = prog;
+
+ setup_timer(&psock->rx_msg_timer, kcm_rx_msg_timeout,
+ (unsigned long)psock);
+
+ INIT_WORK(&psock->rx_work, psock_rx_work);
+ INIT_DELAYED_WORK(&psock->rx_delayed_work, psock_rx_delayed_work);
+
+ sock_hold(csk);
+
+ write_lock_bh(&csk->sk_callback_lock);
+ psock->save_data_ready = csk->sk_data_ready;
+ psock->save_write_space = csk->sk_write_space;
+ psock->save_state_change = csk->sk_state_change;
+ csk->sk_user_data = psock;
+ csk->sk_data_ready = psock_tcp_data_ready;
+ csk->sk_write_space = psock_tcp_write_space;
+ csk->sk_state_change = psock_tcp_state_change;
+ write_unlock_bh(&csk->sk_callback_lock);
+
+ /* Finished initialization, now add the psock to the MUX. */
+ spin_lock_bh(&mux->lock);
+ head = &mux->psocks;
+ list_for_each_entry(tpsock, &mux->psocks, psock_list) {
+ if (tpsock->index != index)
+ break;
+ head = &tpsock->psock_list;
+ index++;
+ }
+
+ list_add(&psock->psock_list, head);
+ psock->index = index;
+
+ KCM_STATS_INCR(mux->stats.psock_attach);
+ mux->psocks_cnt++;
+ psock_now_avail(psock);
+ spin_unlock_bh(&mux->lock);
+
+ /* Schedule RX work in case there are already bytes queued */
+ queue_work(kcm_wq, &psock->rx_work);
+
+ return 0;
+}
+
+static int kcm_attach_ioctl(struct socket *sock, struct kcm_attach *info)
+{
+ struct socket *csock;
+ struct bpf_prog *prog;
+ int err;
+
+ csock = sockfd_lookup(info->fd, &err);
+ if (!csock)
+ return -ENOENT;
+
+ prog = bpf_prog_get(info->bpf_fd);
+ if (IS_ERR(prog)) {
+ err = PTR_ERR(prog);
+ goto out;
+ }
+
+ if (prog->type != BPF_PROG_TYPE_SOCKET_FILTER) {
+ bpf_prog_put(prog);
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = kcm_attach(sock, csock, prog);
+ if (err) {
+ bpf_prog_put(prog);
+ goto out;
+ }
+
+ /* Keep reference on file also */
+
+ return 0;
+out:
+ fput(csock->file);
+ return err;
+}
+
+static void kcm_unattach(struct kcm_psock *psock)
+{
+ struct sock *csk = psock->sk;
+ struct kcm_mux *mux = psock->mux;
+
+ /* Stop getting callbacks from TCP socket. After this there should
+ * be no way to reserve a kcm for this psock.
+ */
+ write_lock_bh(&csk->sk_callback_lock);
+ csk->sk_user_data = NULL;
+ csk->sk_data_ready = psock->save_data_ready;
+ csk->sk_write_space = psock->save_write_space;
+ csk->sk_state_change = psock->save_state_change;
+ psock->rx_stopped = 1;
+
+ if (WARN_ON(psock->rx_kcm)) {
+ write_unlock_bh(&csk->sk_callback_lock);
+ return;
+ }
+
+ spin_lock_bh(&mux->rx_lock);
+
+ /* Stop receiver activities. After this point psock should not be
+ * able to get onto ready list either through callbacks or work.
+ */
+ if (psock->ready_rx_msg) {
+ list_del(&psock->psock_ready_list);
+ kfree_skb(psock->ready_rx_msg);
+ psock->ready_rx_msg = NULL;
+ KCM_STATS_INCR(mux->stats.rx_ready_drops);
+ }
+
+ spin_unlock_bh(&mux->rx_lock);
+
+ write_unlock_bh(&csk->sk_callback_lock);
+
+ del_timer_sync(&psock->rx_msg_timer);
+ cancel_work_sync(&psock->rx_work);
+ cancel_delayed_work_sync(&psock->rx_delayed_work);
+
+ bpf_prog_put(psock->bpf_prog);
+
+ kfree_skb(psock->rx_skb_head);
+ psock->rx_skb_head = NULL;
+
+ spin_lock_bh(&mux->lock);
+
+ aggregate_psock_stats(&psock->stats, &mux->aggregate_psock_stats);
+
+ KCM_STATS_INCR(mux->stats.psock_unattach);
+
+ if (psock->tx_kcm) {
+ /* psock was reserved. Just mark it finished and we will clean
+ * up in the kcm paths, we need kcm lock which can not be
+ * acquired here.
+ */
+ KCM_STATS_INCR(mux->stats.psock_unattach_rsvd);
+ spin_unlock_bh(&mux->lock);
+
+ /* We are unattaching a socket that is reserved. Abort the
+ * socket since we may be out of sync in sending on it. We need
+ * to do this without the mux lock.
+ */
+ kcm_abort_tx_psock(psock, EPIPE, false);
+
+ spin_lock_bh(&mux->lock);
+ if (!psock->tx_kcm) {
+ /* psock now unreserved in window mux was unlocked */
+ goto no_reserved;
+ }
+ psock->done = 1;
+
+ /* Commit done before queuing work to process it */
+ smp_mb();
+
+ /* Queue tx work to make sure psock->done is handled */
+ queue_work(kcm_wq, &psock->tx_kcm->tx_work);
+ spin_unlock_bh(&mux->lock);
+ } else {
+no_reserved:
+ if (!psock->tx_stopped)
+ list_del(&psock->psock_avail_list);
+ list_del(&psock->psock_list);
+ mux->psocks_cnt--;
+ spin_unlock_bh(&mux->lock);
+
+ sock_put(csk);
+ fput(csk->sk_socket->file);
+ kmem_cache_free(kcm_psockp, psock);
+ }
+}
+
+static int kcm_unattach_ioctl(struct socket *sock, struct kcm_unattach *info)
+{
+ struct kcm_sock *kcm = kcm_sk(sock->sk);
+ struct kcm_mux *mux = kcm->mux;
+ struct kcm_psock *psock;
+ struct socket *csock;
+ struct sock *csk;
+ int err;
+
+ csock = sockfd_lookup(info->fd, &err);
+ if (!csock)
+ return -ENOENT;
+
+ csk = csock->sk;
+ if (!csk) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = -ENOENT;
+
+ spin_lock_bh(&mux->lock);
+
+ list_for_each_entry(psock, &mux->psocks, psock_list) {
+ if (psock->sk != csk)
+ continue;
+
+ /* Found the matching psock */
+
+ if (psock->unattaching || WARN_ON(psock->done)) {
+ err = -EALREADY;
+ break;
+ }
+
+ psock->unattaching = 1;
+
+ spin_unlock_bh(&mux->lock);
+
+ kcm_unattach(psock);
+
+ err = 0;
+ goto out;
+ }
+
+ spin_unlock_bh(&mux->lock);
+
+out:
+ fput(csock->file);
+ return err;
+}
+
+static struct proto kcm_proto = {
+ .name = "KCM",
+ .owner = THIS_MODULE,
+ .obj_size = sizeof(struct kcm_sock),
+};
+
+/* Clone a kcm socket. */
+static int kcm_clone(struct socket *osock, struct kcm_clone *info,
+ struct socket **newsockp)
+{
+ struct socket *newsock;
+ struct sock *newsk;
+ struct file *newfile;
+ int err, newfd;
+
+ err = -ENFILE;
+ newsock = sock_alloc();
+ if (!newsock)
+ goto out;
+
+ newsock->type = osock->type;
+ newsock->ops = osock->ops;
+
+ __module_get(newsock->ops->owner);
+
+ newfd = get_unused_fd_flags(0);
+ if (unlikely(newfd < 0)) {
+ err = newfd;
+ goto out_fd_fail;
+ }
+
+ newfile = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name);
+ if (unlikely(IS_ERR(newfile))) {
+ err = PTR_ERR(newfile);
+ goto out_sock_alloc_fail;
+ }
+
+ newsk = sk_alloc(sock_net(osock->sk), PF_KCM, GFP_KERNEL,
+ &kcm_proto, true);
+ if (!newsk) {
+ err = -ENOMEM;
+ goto out_sk_alloc_fail;
+ }
+
+ sock_init_data(newsock, newsk);
+ init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux);
+
+ fd_install(newfd, newfile);
+ *newsockp = newsock;
+ info->fd = newfd;
+
+ return 0;
+
+out_sk_alloc_fail:
+ fput(newfile);
+out_sock_alloc_fail:
+ put_unused_fd(newfd);
+out_fd_fail:
+ sock_release(newsock);
+out:
+ return err;
+}
+
+static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
+{
+ int err;
+
+ switch (cmd) {
+ case SIOCKCMATTACH: {
+ struct kcm_attach info;
+
+ if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
+ err = -EFAULT;
+
+ err = kcm_attach_ioctl(sock, &info);
+
+ break;
+ }
+ case SIOCKCMUNATTACH: {
+ struct kcm_unattach info;
+
+ if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
+ err = -EFAULT;
+
+ err = kcm_unattach_ioctl(sock, &info);
+
+ break;
+ }
+ case SIOCKCMCLONE: {
+ struct kcm_clone info;
+ struct socket *newsock = NULL;
+
+ if (copy_from_user(&info, (void __user *)arg, sizeof(info)))
+ err = -EFAULT;
+
+ err = kcm_clone(sock, &info, &newsock);
+
+ if (!err) {
+ if (copy_to_user((void __user *)arg, &info,
+ sizeof(info))) {
+ err = -EFAULT;
+ sock_release(newsock);
+ }
+ }
+
+ break;
+ }
+ default:
+ err = -ENOIOCTLCMD;
+ break;
+ }
+
+ return err;
+}
+
+static void free_mux(struct rcu_head *rcu)
+{
+ struct kcm_mux *mux = container_of(rcu,
+ struct kcm_mux, rcu);
+
+ kmem_cache_free(kcm_muxp, mux);
+}
+
+static void release_mux(struct kcm_mux *mux)
+{
+ struct kcm_net *knet = mux->knet;
+ struct kcm_psock *psock, *tmp_psock;
+
+ /* Release psocks */
+ list_for_each_entry_safe(psock, tmp_psock,
+ &mux->psocks, psock_list) {
+ if (!WARN_ON(psock->unattaching))
+ kcm_unattach(psock);
+ }
+
+ if (WARN_ON(mux->psocks_cnt))
+ return;
+
+ __skb_queue_purge(&mux->rx_hold_queue);
+
+ mutex_lock(&knet->mutex);
+ aggregate_mux_stats(&mux->stats, &knet->aggregate_mux_stats);
+ aggregate_psock_stats(&mux->aggregate_psock_stats,
+ &knet->aggregate_psock_stats);
+ list_del_rcu(&mux->kcm_mux_list);
+ knet->count--;
+ mutex_unlock(&knet->mutex);
+
+ call_rcu(&mux->rcu, free_mux);
+}
+
+static void kcm_done(struct kcm_sock *kcm)
+{
+ struct kcm_mux *mux = kcm->mux;
+ struct sock *sk = &kcm->sk;
+ int socks_cnt;
+
+ spin_lock_bh(&mux->rx_lock);
+ if (kcm->rx_psock) {
+ /* Cleanup in unreserve_rx_kcm */
+ WARN_ON(kcm->done);
+ kcm->rx_disabled = 1;
+ kcm->done = 1;
+ spin_unlock_bh(&mux->rx_lock);
+ return;
+ }
+
+ if (kcm->rx_wait) {
+ list_del(&kcm->wait_rx_list);
+ kcm->rx_wait = false;
+ }
+ /* Move any pending receive messages to other kcm sockets */
+ requeue_rx_msgs(mux, &sk->sk_receive_queue);
+
+ spin_unlock_bh(&mux->rx_lock);
+
+ if (WARN_ON(sk_rmem_alloc_get(sk)))
+ return;
+
+ /* Detach from MUX */
+ spin_lock_bh(&mux->lock);
+
+ list_del(&kcm->kcm_sock_list);
+ mux->kcm_socks_cnt--;
+ socks_cnt = mux->kcm_socks_cnt;
+
+ spin_unlock_bh(&mux->lock);
+
+ if (!socks_cnt) {
+ /* We are done with the mux now. */
+ release_mux(mux);
+ }
+
+ WARN_ON(kcm->rx_wait);
+
+ sock_put(&kcm->sk);
+}
+
+/* Called by kcm_release to close a KCM socket.
+ * If this is the last KCM socket on the MUX, destroy the MUX.
+ */
+static int kcm_release(struct socket *sock)
+{
+ struct sock *sk = sock->sk;
+ struct kcm_sock *kcm;
+ struct kcm_mux *mux;
+ struct kcm_psock *psock;
+
+ if (!sk)
+ return 0;
+
+ kcm = kcm_sk(sk);
+ mux = kcm->mux;
+
+ sock_orphan(sk);
+ kfree_skb(kcm->seq_skb);
+
+ lock_sock(sk);
+ /* Purge queue under lock to avoid race condition with tx_work trying
+ * to act when queue is nonempty. If tx_work runs after this point
+ * it will just return.
+ */
+ __skb_queue_purge(&sk->sk_write_queue);
+ release_sock(sk);
+
+ spin_lock_bh(&mux->lock);
+ if (kcm->tx_wait) {
+ /* Take of tx_wait list, after this point there should be no way
+ * that a psock will be assigned to this kcm.
+ */
+ list_del(&kcm->wait_psock_list);
+ kcm->tx_wait = false;
+ }
+ spin_unlock_bh(&mux->lock);
+
+ /* Cancel work. After this point there should be no outside references
+ * to the kcm socket.
+ */
+ cancel_work_sync(&kcm->tx_work);
+
+ lock_sock(sk);
+ psock = kcm->tx_psock;
+ if (psock) {
+ /* A psock was reserved, so we need to kill it since it
+ * may already have some bytes queued from a message. We
+ * need to do this after removing kcm from tx_wait list.
+ */
+ kcm_abort_tx_psock(psock, EPIPE, false);
+ unreserve_psock(kcm);
+ }
+ release_sock(sk);
+
+ WARN_ON(kcm->tx_wait);
+ WARN_ON(kcm->tx_psock);
+
+ sock->sk = NULL;
+
+ kcm_done(kcm);
+
+ return 0;
+}
+
+static const struct proto_ops kcm_dgram_ops = {
+ .family = PF_KCM,
+ .owner = THIS_MODULE,
+ .release = kcm_release,
+ .bind = sock_no_bind,
+ .connect = sock_no_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = datagram_poll,
+ .ioctl = kcm_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = kcm_setsockopt,
+ .getsockopt = kcm_getsockopt,
+ .sendmsg = kcm_sendmsg,
+ .recvmsg = kcm_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = kcm_sendpage,
+};
+
+static const struct proto_ops kcm_seqpacket_ops = {
+ .family = PF_KCM,
+ .owner = THIS_MODULE,
+ .release = kcm_release,
+ .bind = sock_no_bind,
+ .connect = sock_no_connect,
+ .socketpair = sock_no_socketpair,
+ .accept = sock_no_accept,
+ .getname = sock_no_getname,
+ .poll = datagram_poll,
+ .ioctl = kcm_ioctl,
+ .listen = sock_no_listen,
+ .shutdown = sock_no_shutdown,
+ .setsockopt = kcm_setsockopt,
+ .getsockopt = kcm_getsockopt,
+ .sendmsg = kcm_sendmsg,
+ .recvmsg = kcm_recvmsg,
+ .mmap = sock_no_mmap,
+ .sendpage = kcm_sendpage,
+ .splice_read = kcm_splice_read,
+};
+
+/* Create proto operation for kcm sockets */
+static int kcm_create(struct net *net, struct socket *sock,
+ int protocol, int kern)
+{
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+ struct sock *sk;
+ struct kcm_mux *mux;
+
+ switch (sock->type) {
+ case SOCK_DGRAM:
+ sock->ops = &kcm_dgram_ops;
+ break;
+ case SOCK_SEQPACKET:
+ sock->ops = &kcm_seqpacket_ops;
+ break;
+ default:
+ return -ESOCKTNOSUPPORT;
+ }
+
+ if (protocol != KCMPROTO_CONNECTED)
+ return -EPROTONOSUPPORT;
+
+ sk = sk_alloc(net, PF_KCM, GFP_KERNEL, &kcm_proto, kern);
+ if (!sk)
+ return -ENOMEM;
+
+ /* Allocate a kcm mux, shared between KCM sockets */
+ mux = kmem_cache_zalloc(kcm_muxp, GFP_KERNEL);
+ if (!mux) {
+ sk_free(sk);
+ return -ENOMEM;
+ }
+
+ spin_lock_init(&mux->lock);
+ spin_lock_init(&mux->rx_lock);
+ INIT_LIST_HEAD(&mux->kcm_socks);
+ INIT_LIST_HEAD(&mux->kcm_rx_waiters);
+ INIT_LIST_HEAD(&mux->kcm_tx_waiters);
+
+ INIT_LIST_HEAD(&mux->psocks);
+ INIT_LIST_HEAD(&mux->psocks_ready);
+ INIT_LIST_HEAD(&mux->psocks_avail);
+
+ mux->knet = knet;
+
+ /* Add new MUX to list */
+ mutex_lock(&knet->mutex);
+ list_add_rcu(&mux->kcm_mux_list, &knet->mux_list);
+ knet->count++;
+ mutex_unlock(&knet->mutex);
+
+ skb_queue_head_init(&mux->rx_hold_queue);
+
+ /* Init KCM socket */
+ sock_init_data(sock, sk);
+ init_kcm_sock(kcm_sk(sk), mux);
+
+ return 0;
+}
+
+static struct net_proto_family kcm_family_ops = {
+ .family = PF_KCM,
+ .create = kcm_create,
+ .owner = THIS_MODULE,
+};
+
+static __net_init int kcm_init_net(struct net *net)
+{
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ INIT_LIST_HEAD_RCU(&knet->mux_list);
+ mutex_init(&knet->mutex);
+
+ return 0;
+}
+
+static __net_exit void kcm_exit_net(struct net *net)
+{
+ struct kcm_net *knet = net_generic(net, kcm_net_id);
+
+ /* All KCM sockets should be closed at this point, which should mean
+ * that all multiplexors and psocks have been destroyed.
+ */
+ WARN_ON(!list_empty(&knet->mux_list));
+}
+
+static struct pernet_operations kcm_net_ops = {
+ .init = kcm_init_net,
+ .exit = kcm_exit_net,
+ .id = &kcm_net_id,
+ .size = sizeof(struct kcm_net),
+};
+
+static int __init kcm_init(void)
+{
+ int err = -ENOMEM;
+
+ kcm_muxp = kmem_cache_create("kcm_mux_cache",
+ sizeof(struct kcm_mux), 0,
+ SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ if (!kcm_muxp)
+ goto fail;
+
+ kcm_psockp = kmem_cache_create("kcm_psock_cache",
+ sizeof(struct kcm_psock), 0,
+ SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ if (!kcm_psockp)
+ goto fail;
+
+ kcm_wq = create_singlethread_workqueue("kkcmd");
+ if (!kcm_wq)
+ goto fail;
+
+ err = proto_register(&kcm_proto, 1);
+ if (err)
+ goto fail;
+
+ err = sock_register(&kcm_family_ops);
+ if (err)
+ goto sock_register_fail;
+
+ err = register_pernet_device(&kcm_net_ops);
+ if (err)
+ goto net_ops_fail;
+
+ err = kcm_proc_init();
+ if (err)
+ goto proc_init_fail;
+
+ return 0;
+
+proc_init_fail:
+ unregister_pernet_device(&kcm_net_ops);
+
+net_ops_fail:
+ sock_unregister(PF_KCM);
+
+sock_register_fail:
+ proto_unregister(&kcm_proto);
+
+fail:
+ kmem_cache_destroy(kcm_muxp);
+ kmem_cache_destroy(kcm_psockp);
+
+ if (kcm_wq)
+ destroy_workqueue(kcm_wq);
+
+ return err;
+}
+
+static void __exit kcm_exit(void)
+{
+ kcm_proc_exit();
+ unregister_pernet_device(&kcm_net_ops);
+ sock_unregister(PF_KCM);
+ proto_unregister(&kcm_proto);
+ destroy_workqueue(kcm_wq);
+
+ kmem_cache_destroy(kcm_muxp);
+ kmem_cache_destroy(kcm_psockp);
+}
+
+module_init(kcm_init);
+module_exit(kcm_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(PF_KCM);
+
diff --git a/net/socket.c b/net/socket.c
index c044d1e8508c..886649c88d8f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -533,7 +533,7 @@ static const struct inode_operations sockfs_inode_ops = {
* NULL is returned.
*/
-static struct socket *sock_alloc(void)
+struct socket *sock_alloc(void)
{
struct inode *inode;
struct socket *sock;
@@ -554,6 +554,7 @@ static struct socket *sock_alloc(void)
this_cpu_add(sockets_in_use, 1);
return sock;
}
+EXPORT_SYMBOL(sock_alloc);
/**
* sock_release - close a socket
@@ -1874,7 +1875,8 @@ static int copy_msghdr_from_user(struct msghdr *kmsg,
static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
struct msghdr *msg_sys, unsigned int flags,
- struct used_address *used_address)
+ struct used_address *used_address,
+ unsigned int allowed_msghdr_flags)
{
struct compat_msghdr __user *msg_compat =
(struct compat_msghdr __user *)msg;
@@ -1900,6 +1902,7 @@ static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg,
if (msg_sys->msg_controllen > INT_MAX)
goto out_freeiov;
+ flags |= (msg_sys->msg_flags & allowed_msghdr_flags);
ctl_len = msg_sys->msg_controllen;
if ((MSG_CMSG_COMPAT & flags) && ctl_len) {
err =
@@ -1978,7 +1981,7 @@ long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags)
if (!sock)
goto out;
- err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL);
+ err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0);
fput_light(sock->file, fput_needed);
out:
@@ -2005,6 +2008,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
struct compat_mmsghdr __user *compat_entry;
struct msghdr msg_sys;
struct used_address used_address;
+ unsigned int oflags = flags;
if (vlen > UIO_MAXIOV)
vlen = UIO_MAXIOV;
@@ -2019,11 +2023,15 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
entry = mmsg;
compat_entry = (struct compat_mmsghdr __user *)mmsg;
err = 0;
+ flags |= MSG_BATCH;
while (datagrams < vlen) {
+ if (datagrams == vlen - 1)
+ flags = oflags;
+
if (MSG_CMSG_COMPAT & flags) {
err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry,
- &msg_sys, flags, &used_address);
+ &msg_sys, flags, &used_address, MSG_EOR);
if (err < 0)
break;
err = __put_user(err, &compat_entry->msg_len);
@@ -2031,7 +2039,7 @@ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen,
} else {
err = ___sys_sendmsg(sock,
(struct user_msghdr __user *)entry,
- &msg_sys, flags, &used_address);
+ &msg_sys, flags, &used_address, MSG_EOR);
if (err < 0)
break;
err = put_user(err, &entry->msg_len);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.