diff --git a/crypto/algif_hash.c b/crypto/algif_hash.c index 35c93ff11f35..83cd2cc49c9f 100644 --- a/crypto/algif_hash.c +++ b/crypto/algif_hash.c @@ -42,7 +42,7 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock, struct alg_sock *ask = alg_sk(sk); struct hash_ctx *ctx = ask->private; unsigned long iovlen; - struct iovec *iov; + const struct iovec *iov; long copied = 0; int err; @@ -58,7 +58,7 @@ static int hash_sendmsg(struct kiocb *unused, struct socket *sock, ctx->more = 0; - for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0; + for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0; iovlen--, iov++) { unsigned long seglen = iov->iov_len; char __user *from = iov->iov_base; diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index c3b482bee208..4f45dab24648 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -429,13 +429,13 @@ static int skcipher_recvmsg(struct kiocb *unused, struct socket *sock, struct skcipher_sg_list *sgl; struct scatterlist *sg; unsigned long iovlen; - struct iovec *iov; + const struct iovec *iov; int err = -EAGAIN; int used; long copied = 0; lock_sock(sk); - for (iov = msg->msg_iov, iovlen = msg->msg_iovlen; iovlen > 0; + for (iov = msg->msg_iter.iov, iovlen = msg->msg_iter.nr_segs; iovlen > 0; iovlen--, iov++) { unsigned long seglen = iov->iov_len; char __user *from = iov->iov_base; diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index 1b7b303085d2..7aaaf51e1596 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -27,6 +27,7 @@ #include #include #include +#include #include "vmci_handle_array.h" #include "vmci_queue_pair.h" @@ -429,11 +430,11 @@ static int __qp_memcpy_from_queue(void *dest, to_copy = size - bytes_copied; if (is_iovec) { - struct iovec *iov = (struct iovec *)dest; + struct msghdr *msg = dest; int err; /* The iovec will track bytes_copied internally. */ - err = memcpy_toiovec(iov, (u8 *)va + page_offset, + err = memcpy_to_msg(msg, (u8 *)va + page_offset, to_copy); if (err != 0) { if (kernel_if->host) @@ -3264,13 +3265,13 @@ EXPORT_SYMBOL_GPL(vmci_qpair_enquev); * of bytes dequeued or < 0 on error. */ ssize_t vmci_qpair_dequev(struct vmci_qp *qpair, - void *iov, + struct msghdr *msg, size_t iov_size, int buf_type) { ssize_t result; - if (!qpair || !iov) + if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); @@ -3279,7 +3280,7 @@ ssize_t vmci_qpair_dequev(struct vmci_qp *qpair, result = qp_dequeue_locked(qpair->produce_q, qpair->consume_q, qpair->consume_q_size, - iov, iov_size, + msg, iov_size, qp_memcpy_from_queue_iov, true); @@ -3308,13 +3309,13 @@ EXPORT_SYMBOL_GPL(vmci_qpair_dequev); * of bytes peeked or < 0 on error. */ ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, - void *iov, + struct msghdr *msg, size_t iov_size, int buf_type) { ssize_t result; - if (!qpair || !iov) + if (!qpair) return VMCI_ERROR_INVALID_ARGS; qp_lock(qpair); @@ -3323,7 +3324,7 @@ ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, result = qp_dequeue_locked(qpair->produce_q, qpair->consume_q, qpair->consume_q_size, - iov, iov_size, + msg, iov_size, qp_memcpy_from_queue_iov, false); diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index ba1e5db2152e..2c157cced81f 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -1095,9 +1095,7 @@ static int macvtap_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len) { struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock); - struct iov_iter from; - iov_iter_init(&from, WRITE, m->msg_iov, m->msg_iovlen, total_len); - return macvtap_get_user(q, m, &from, m->msg_flags & MSG_DONTWAIT); + return macvtap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT); } static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock, @@ -1105,12 +1103,10 @@ static int macvtap_recvmsg(struct kiocb *iocb, struct socket *sock, int flags) { struct macvtap_queue *q = container_of(sock, struct macvtap_queue, sock); - struct iov_iter to; int ret; if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) return -EINVAL; - iov_iter_init(&to, READ, m->msg_iov, m->msg_iovlen, total_len); - ret = macvtap_do_read(q, &to, flags & MSG_DONTWAIT); + ret = macvtap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT); if (ret > total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c index 794a47329368..af034dba9bd6 100644 --- a/drivers/net/ppp/ppp_generic.c +++ b/drivers/net/ppp/ppp_generic.c @@ -417,6 +417,7 @@ static ssize_t ppp_read(struct file *file, char __user *buf, ssize_t ret; struct sk_buff *skb = NULL; struct iovec iov; + struct iov_iter to; ret = count; @@ -462,7 +463,8 @@ static ssize_t ppp_read(struct file *file, char __user *buf, ret = -EFAULT; iov.iov_base = buf; iov.iov_len = count; - if (skb_copy_datagram_iovec(skb, 0, &iov, skb->len)) + iov_iter_init(&to, READ, &iov, 1, count); + if (skb_copy_datagram_iter(skb, 0, &to, skb->len)) goto outf; ret = skb->len; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 9c58286b8a42..f3e992ed87ac 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1449,13 +1449,11 @@ static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, int ret; struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = __tun_get(tfile); - struct iov_iter from; if (!tun) return -EBADFD; - iov_iter_init(&from, WRITE, m->msg_iov, m->msg_iovlen, total_len); - ret = tun_get_user(tun, tfile, m->msg_control, &from, + ret = tun_get_user(tun, tfile, m->msg_control, &m->msg_iter, m->msg_flags & MSG_DONTWAIT); tun_put(tun); return ret; @@ -1467,7 +1465,6 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock, { struct tun_file *tfile = container_of(sock, struct tun_file, socket); struct tun_struct *tun = __tun_get(tfile); - struct iov_iter to; int ret; if (!tun) @@ -1482,8 +1479,7 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock, SOL_PACKET, TUN_TX_TIMESTAMP); goto out; } - iov_iter_init(&to, READ, m->msg_iov, m->msg_iovlen, total_len); - ret = tun_do_read(tun, tfile, &to, flags & MSG_DONTWAIT); + ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT); if (ret > total_len) { m->msg_flags |= MSG_TRUNC; ret = flags & MSG_TRUNC ? ret : total_len; diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index ce87ce9bdb9c..7c6a95bcb35e 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1326,21 +1326,19 @@ static int iscsit_do_rx_data( struct iscsi_conn *conn, struct iscsi_data_count *count) { - int data = count->data_length, rx_loop = 0, total_rx = 0, iov_len; - struct kvec *iov_p; + int data = count->data_length, rx_loop = 0, total_rx = 0; struct msghdr msg; if (!conn || !conn->sock || !conn->conn_ops) return -1; memset(&msg, 0, sizeof(struct msghdr)); - - iov_p = count->iov; - iov_len = count->iov_count; + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, + count->iov, count->iov_count, data); while (total_rx < data) { - rx_loop = kernel_recvmsg(conn->sock, &msg, iov_p, iov_len, - (data - total_rx), MSG_WAITALL); + rx_loop = sock_recvmsg(conn->sock, &msg, + (data - total_rx), MSG_WAITALL); if (rx_loop <= 0) { pr_debug("rx_loop: %d total_rx: %d\n", rx_loop, total_rx); diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 8dae2f724a35..9f06e70a2631 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -342,7 +342,6 @@ static void handle_tx(struct vhost_net *net) .msg_namelen = 0, .msg_control = NULL, .msg_controllen = 0, - .msg_iov = vq->iov, .msg_flags = MSG_DONTWAIT, }; size_t len, total_len = 0; @@ -396,8 +395,8 @@ static void handle_tx(struct vhost_net *net) } /* Skip header. TODO: support TSO. */ s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out); - msg.msg_iovlen = out; len = iov_length(vq->iov, out); + iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len); /* Sanity check */ if (!len) { vq_err(vq, "Unexpected header len for TX: " @@ -562,7 +561,6 @@ static void handle_rx(struct vhost_net *net) .msg_namelen = 0, .msg_control = NULL, /* FIXME: get and handle RX aux data. */ .msg_controllen = 0, - .msg_iov = vq->iov, .msg_flags = MSG_DONTWAIT, }; struct virtio_net_hdr_mrg_rxbuf hdr = { @@ -600,7 +598,7 @@ static void handle_rx(struct vhost_net *net) break; /* On overrun, truncate and discard */ if (unlikely(headcount > UIO_MAXIOV)) { - msg.msg_iovlen = 1; + iov_iter_init(&msg.msg_iter, READ, vq->iov, 1, 1); err = sock->ops->recvmsg(NULL, sock, &msg, 1, MSG_DONTWAIT | MSG_TRUNC); pr_debug("Discarded rx packet: len %zd\n", sock_len); @@ -626,7 +624,7 @@ static void handle_rx(struct vhost_net *net) /* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF: * needed because recvmsg can modify msg_iov. */ copy_iovec_hdr(vq->iov, nvq->hdr, sock_hlen, in); - msg.msg_iovlen = in; + iov_iter_init(&msg.msg_iter, READ, vq->iov, in, sock_len); err = sock->ops->recvmsg(NULL, sock, &msg, sock_len, MSG_DONTWAIT | MSG_TRUNC); /* Userspace might have consumed the packet meanwhile: diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 03a3beb17004..06e14bfb3496 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -306,8 +306,8 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg, _debug("- range %u-%u%s", offset, to, msg->msg_flags ? " [more]" : ""); - msg->msg_iov = (struct iovec *) iov; - msg->msg_iovlen = 1; + iov_iter_init(&msg->msg_iter, WRITE, + (struct iovec *) iov, 1, to - offset); /* have to change the state *before* sending the last * packet as RxRPC might give us the reply before it @@ -384,8 +384,8 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp, msg.msg_name = NULL; msg.msg_namelen = 0; - msg.msg_iov = (struct iovec *) iov; - msg.msg_iovlen = 1; + iov_iter_init(&msg.msg_iter, WRITE, (struct iovec *)iov, 1, + call->request_size); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = (call->send_pages ? MSG_MORE : 0); @@ -778,8 +778,7 @@ void afs_send_empty_reply(struct afs_call *call) iov[0].iov_len = 0; msg.msg_name = NULL; msg.msg_namelen = 0; - msg.msg_iov = iov; - msg.msg_iovlen = 0; + iov_iter_init(&msg.msg_iter, WRITE, iov, 0, 0); /* WTF? */ msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -815,8 +814,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) iov[0].iov_len = len; msg.msg_name = NULL; msg.msg_namelen = 0; - msg.msg_iov = iov; - msg.msg_iovlen = 1; + iov_iter_init(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index ef64cec42804..ab0bc43c82a4 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2644,24 +2644,17 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); unsigned int datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); -int skb_copy_datagram_iovec(const struct sk_buff *from, int offset, - struct iovec *to, int size); +int skb_copy_datagram_iter(const struct sk_buff *from, int offset, + struct iov_iter *to, int size); static inline int skb_copy_datagram_msg(const struct sk_buff *from, int offset, struct msghdr *msg, int size) { - return skb_copy_datagram_iovec(from, offset, msg->msg_iov, size); -} -int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, int hlen, - struct iovec *iov); -static inline int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, - struct msghdr *msg) -{ - return skb_copy_and_csum_datagram_iovec(skb, hlen, msg->msg_iov); + return skb_copy_datagram_iter(from, offset, &msg->msg_iter, size); } +int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, int hlen, + struct msghdr *msg); int skb_copy_datagram_from_iter(struct sk_buff *skb, int offset, struct iov_iter *from, int len); -int skb_copy_datagram_iter(const struct sk_buff *from, int offset, - struct iov_iter *to, int size); int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *frm); void skb_free_datagram(struct sock *sk, struct sk_buff *skb); void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb); @@ -2689,12 +2682,13 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); static inline int memcpy_from_msg(void *data, struct msghdr *msg, int len) { - return memcpy_fromiovec(data, msg->msg_iov, len); + /* XXX: stripping const */ + return memcpy_fromiovec(data, (struct iovec *)msg->msg_iter.iov, len); } static inline int memcpy_to_msg(struct msghdr *msg, void *data, int len) { - return memcpy_toiovec(msg->msg_iov, data, len); + return copy_to_iter(data, len, &msg->msg_iter) == len ? 0 : -EFAULT; } struct skb_checksum_ops { diff --git a/include/linux/socket.h b/include/linux/socket.h index de5222832be4..048d6d6eed6d 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -47,8 +47,7 @@ struct linger { struct msghdr { void *msg_name; /* ptr to socket address structure */ int msg_namelen; /* size of socket address structure */ - struct iovec *msg_iov; /* scatter/gather array */ - __kernel_size_t msg_iovlen; /* # elements in msg_iov */ + struct iov_iter msg_iter; /* data */ void *msg_control; /* ancillary data */ __kernel_size_t msg_controllen; /* ancillary data buffer length */ unsigned int msg_flags; /* flags on received message */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3fa0a9669a3a..67309ece0772 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -162,7 +162,7 @@ struct tcp_sock { struct { struct sk_buff_head prequeue; struct task_struct *task; - struct iovec *iov; + struct msghdr *msg; int memory; int len; } ucopy; diff --git a/include/linux/uio.h b/include/linux/uio.h index 9b1581414cd4..a41e252396c0 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -31,6 +31,7 @@ struct iov_iter { size_t count; union { const struct iovec *iov; + const struct kvec *kvec; const struct bio_vec *bvec; }; unsigned long nr_segs; @@ -82,10 +83,13 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i); size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i); size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i); +size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i); size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); +void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *iov, + unsigned long nr_segs, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, @@ -123,9 +127,10 @@ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { i->count = count; } +size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); +size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i); int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len); -int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len); int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, int offset, int len); int memcpy_toiovecend(const struct iovec *v, unsigned char *kdata, diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h index 023430e265fe..5691f752ce8f 100644 --- a/include/linux/vmw_vmci_api.h +++ b/include/linux/vmw_vmci_api.h @@ -24,6 +24,7 @@ #define VMCI_KERNEL_API_VERSION_2 2 #define VMCI_KERNEL_API_VERSION VMCI_KERNEL_API_VERSION_2 +struct msghdr; typedef void (vmci_device_shutdown_fn) (void *device_registration, void *user_data); @@ -75,8 +76,8 @@ ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size, ssize_t vmci_qpair_enquev(struct vmci_qp *qpair, void *iov, size_t iov_size, int mode); ssize_t vmci_qpair_dequev(struct vmci_qp *qpair, - void *iov, size_t iov_size, int mode); -ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, void *iov, size_t iov_size, + struct msghdr *msg, size_t iov_size, int mode); +ssize_t vmci_qpair_peekv(struct vmci_qp *qpair, struct msghdr *msg, size_t iov_size, int mode); #endif /* !__VMW_VMCI_API_H__ */ diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index eee3ef530e79..d1bb342d083f 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -608,10 +608,6 @@ struct l2cap_ops { struct sk_buff *(*alloc_skb) (struct l2cap_chan *chan, unsigned long hdr_len, unsigned long len, int nb); - int (*memcpy_fromiovec) (struct l2cap_chan *chan, - unsigned char *kdata, - struct iovec *iov, - int len); }; struct l2cap_conn { @@ -905,31 +901,6 @@ static inline long l2cap_chan_no_get_sndtimeo(struct l2cap_chan *chan) return 0; } -static inline int l2cap_chan_no_memcpy_fromiovec(struct l2cap_chan *chan, - unsigned char *kdata, - struct iovec *iov, - int len) -{ - /* Following is safe since for compiler definitions of kvec and - * iovec are identical, yielding the same in-core layout and alignment - */ - struct kvec *vec = (struct kvec *)iov; - - while (len > 0) { - if (vec->iov_len) { - int copy = min_t(unsigned int, len, vec->iov_len); - memcpy(kdata, vec->iov_base, copy); - len -= copy; - kdata += copy; - vec->iov_base += copy; - vec->iov_len -= copy; - } - vec++; - } - - return 0; -} - extern bool disable_ertm; int l2cap_init_sockets(void); diff --git a/include/net/udplite.h b/include/net/udplite.h index 9a28a5179400..ae7c8d1fbcad 100644 --- a/include/net/udplite.h +++ b/include/net/udplite.h @@ -19,7 +19,9 @@ extern struct udp_table udplite_table; static __inline__ int udplite_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { - return memcpy_fromiovecend(to, (struct iovec *) from, offset, len); + struct msghdr *msg = from; + /* XXX: stripping const */ + return memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len); } /* Designate sk as UDP-Lite socket */ diff --git a/lib/iovec.c b/lib/iovec.c index df3abd1eaa4a..2d99cb4a5006 100644 --- a/lib/iovec.c +++ b/lib/iovec.c @@ -27,31 +27,6 @@ int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) } EXPORT_SYMBOL(memcpy_fromiovec); -/* - * Copy kernel to iovec. Returns -EFAULT on error. - * - * Note: this modifies the original iovec. - */ - -int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) -{ - while (len > 0) { - if (iov->iov_len) { - int copy = min_t(unsigned int, iov->iov_len, len); - if (copy_to_user(iov->iov_base, kdata, copy)) - return -EFAULT; - kdata += copy; - len -= copy; - iov->iov_len -= copy; - iov->iov_base += copy; - } - iov++; - } - - return 0; -} -EXPORT_SYMBOL(memcpy_toiovec); - /* * Copy kernel to iovec. Returns -EFAULT on error. */ diff --git a/mm/iov_iter.c b/mm/iov_iter.c index e34a3cb6aad6..a1599ca4ab0e 100644 --- a/mm/iov_iter.c +++ b/mm/iov_iter.c @@ -3,95 +3,136 @@ #include #include #include +#include -static size_t copy_to_iter_iovec(void *from, size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - left = __copy_to_user(buf, from, copy); - copy -= left; - skip += copy; - from += copy; - bytes -= copy; - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_to_user(buf, from, copy); - copy -= left; - skip = copy; - from += copy; - bytes -= copy; - } - - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; +#define iterate_iovec(i, n, __v, __p, skip, STEP) { \ + size_t left; \ + size_t wanted = n; \ + __p = i->iov; \ + __v.iov_len = min(n, __p->iov_len - skip); \ + if (likely(__v.iov_len)) { \ + __v.iov_base = __p->iov_base + skip; \ + left = (STEP); \ + __v.iov_len -= left; \ + skip += __v.iov_len; \ + n -= __v.iov_len; \ + } else { \ + left = 0; \ + } \ + while (unlikely(!left && n)) { \ + __p++; \ + __v.iov_len = min(n, __p->iov_len); \ + if (unlikely(!__v.iov_len)) \ + continue; \ + __v.iov_base = __p->iov_base; \ + left = (STEP); \ + __v.iov_len -= left; \ + skip = __v.iov_len; \ + n -= __v.iov_len; \ + } \ + n = wanted - n; \ } -static size_t copy_from_iter_iovec(void *to, size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; +#define iterate_kvec(i, n, __v, __p, skip, STEP) { \ + size_t wanted = n; \ + __p = i->kvec; \ + __v.iov_len = min(n, __p->iov_len - skip); \ + if (likely(__v.iov_len)) { \ + __v.iov_base = __p->iov_base + skip; \ + (void)(STEP); \ + skip += __v.iov_len; \ + n -= __v.iov_len; \ + } \ + while (unlikely(n)) { \ + __p++; \ + __v.iov_len = min(n, __p->iov_len); \ + if (unlikely(!__v.iov_len)) \ + continue; \ + __v.iov_base = __p->iov_base; \ + (void)(STEP); \ + skip = __v.iov_len; \ + n -= __v.iov_len; \ + } \ + n = wanted; \ +} - if (unlikely(bytes > i->count)) - bytes = i->count; +#define iterate_bvec(i, n, __v, __p, skip, STEP) { \ + size_t wanted = n; \ + __p = i->bvec; \ + __v.bv_len = min_t(size_t, n, __p->bv_len - skip); \ + if (likely(__v.bv_len)) { \ + __v.bv_page = __p->bv_page; \ + __v.bv_offset = __p->bv_offset + skip; \ + (void)(STEP); \ + skip += __v.bv_len; \ + n -= __v.bv_len; \ + } \ + while (unlikely(n)) { \ + __p++; \ + __v.bv_len = min_t(size_t, n, __p->bv_len); \ + if (unlikely(!__v.bv_len)) \ + continue; \ + __v.bv_page = __p->bv_page; \ + __v.bv_offset = __p->bv_offset; \ + (void)(STEP); \ + skip = __v.bv_len; \ + n -= __v.bv_len; \ + } \ + n = wanted; \ +} - if (unlikely(!bytes)) - return 0; +#define iterate_all_kinds(i, n, v, I, B, K) { \ + size_t skip = i->iov_offset; \ + if (unlikely(i->type & ITER_BVEC)) { \ + const struct bio_vec *bvec; \ + struct bio_vec v; \ + iterate_bvec(i, n, v, bvec, skip, (B)) \ + } else if (unlikely(i->type & ITER_KVEC)) { \ + const struct kvec *kvec; \ + struct kvec v; \ + iterate_kvec(i, n, v, kvec, skip, (K)) \ + } else { \ + const struct iovec *iov; \ + struct iovec v; \ + iterate_iovec(i, n, v, iov, skip, (I)) \ + } \ +} - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - left = __copy_from_user(to, buf, copy); - copy -= left; - skip += copy; - to += copy; - bytes -= copy; - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __copy_from_user(to, buf, copy); - copy -= left; - skip = copy; - to += copy; - bytes -= copy; - } - - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; +#define iterate_and_advance(i, n, v, I, B, K) { \ + size_t skip = i->iov_offset; \ + if (unlikely(i->type & ITER_BVEC)) { \ + const struct bio_vec *bvec; \ + struct bio_vec v; \ + iterate_bvec(i, n, v, bvec, skip, (B)) \ + if (skip == bvec->bv_len) { \ + bvec++; \ + skip = 0; \ + } \ + i->nr_segs -= bvec - i->bvec; \ + i->bvec = bvec; \ + } else if (unlikely(i->type & ITER_KVEC)) { \ + const struct kvec *kvec; \ + struct kvec v; \ + iterate_kvec(i, n, v, kvec, skip, (K)) \ + if (skip == kvec->iov_len) { \ + kvec++; \ + skip = 0; \ + } \ + i->nr_segs -= kvec - i->kvec; \ + i->kvec = kvec; \ + } else { \ + const struct iovec *iov; \ + struct iovec v; \ + iterate_iovec(i, n, v, iov, skip, (I)) \ + if (skip == iov->iov_len) { \ + iov++; \ + skip = 0; \ + } \ + i->nr_segs -= iov - i->iov; \ + i->iov = iov; \ + } \ + i->count -= n; \ + i->iov_offset = skip; \ } static size_t copy_page_to_iter_iovec(struct page *page, size_t offset, size_t bytes, @@ -256,134 +297,6 @@ done: return wanted - bytes; } -static size_t zero_iovec(size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, left, wanted; - const struct iovec *iov; - char __user *buf; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - iov = i->iov; - skip = i->iov_offset; - buf = iov->iov_base + skip; - copy = min(bytes, iov->iov_len - skip); - - left = __clear_user(buf, copy); - copy -= left; - skip += copy; - bytes -= copy; - - while (unlikely(!left && bytes)) { - iov++; - buf = iov->iov_base; - copy = min(bytes, iov->iov_len); - left = __clear_user(buf, copy); - copy -= left; - skip = copy; - bytes -= copy; - } - - if (skip == iov->iov_len) { - iov++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= iov - i->iov; - i->iov = iov; - i->iov_offset = skip; - return wanted - bytes; -} - -static size_t __iovec_copy_from_user_inatomic(char *vaddr, - const struct iovec *iov, size_t base, size_t bytes) -{ - size_t copied = 0, left = 0; - - while (bytes) { - char __user *buf = iov->iov_base + base; - int copy = min(bytes, iov->iov_len - base); - - base = 0; - left = __copy_from_user_inatomic(vaddr, buf, copy); - copied += copy; - bytes -= copy; - vaddr += copy; - iov++; - - if (unlikely(left)) - break; - } - return copied - left; -} - -/* - * Copy as much as we can into the page and return the number of bytes which - * were successfully copied. If a fault is encountered then return the number of - * bytes which were copied. - */ -static size_t copy_from_user_atomic_iovec(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t copied; - - kaddr = kmap_atomic(page); - if (likely(i->nr_segs == 1)) { - int left; - char __user *buf = i->iov->iov_base + i->iov_offset; - left = __copy_from_user_inatomic(kaddr + offset, buf, bytes); - copied = bytes - left; - } else { - copied = __iovec_copy_from_user_inatomic(kaddr + offset, - i->iov, i->iov_offset, bytes); - } - kunmap_atomic(kaddr); - - return copied; -} - -static void advance_iovec(struct iov_iter *i, size_t bytes) -{ - BUG_ON(i->count < bytes); - - if (likely(i->nr_segs == 1)) { - i->iov_offset += bytes; - i->count -= bytes; - } else { - const struct iovec *iov = i->iov; - size_t base = i->iov_offset; - unsigned long nr_segs = i->nr_segs; - - /* - * The !iov->iov_len check ensures we skip over unlikely - * zero-length segments (without overruning the iovec). - */ - while (bytes || unlikely(i->count && !iov->iov_len)) { - int copy; - - copy = min(bytes, iov->iov_len - base); - BUG_ON(!i->count || i->count < copy); - i->count -= copy; - bytes -= copy; - base += copy; - if (iov->iov_len == base) { - iov++; - nr_segs--; - base = 0; - } - } - i->iov = iov; - i->iov_offset = base; - i->nr_segs = nr_segs; - } -} - /* * Fault in the first iovec of the given iov_iter, to a maximum length * of bytes. Returns 0 on success, or non-zero if the memory could not be @@ -395,7 +308,7 @@ static void advance_iovec(struct iov_iter *i, size_t bytes) */ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) { - if (!(i->type & ITER_BVEC)) { + if (!(i->type & (ITER_BVEC|ITER_KVEC))) { char __user *buf = i->iov->iov_base + i->iov_offset; bytes = min(bytes, i->iov->iov_len - i->iov_offset); return fault_in_pages_readable(buf, bytes); @@ -404,136 +317,25 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) } EXPORT_SYMBOL(iov_iter_fault_in_readable); -static unsigned long alignment_iovec(const struct iov_iter *i) -{ - const struct iovec *iov = i->iov; - unsigned long res; - size_t size = i->count; - size_t n; - - if (!size) - return 0; - - res = (unsigned long)iov->iov_base + i->iov_offset; - n = iov->iov_len - i->iov_offset; - if (n >= size) - return res | size; - size -= n; - res |= n; - while (size > (++iov)->iov_len) { - res |= (unsigned long)iov->iov_base | iov->iov_len; - size -= iov->iov_len; - } - res |= (unsigned long)iov->iov_base | size; - return res; -} - void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { /* It will get better. Eventually... */ - if (segment_eq(get_fs(), KERNEL_DS)) + if (segment_eq(get_fs(), KERNEL_DS)) { direction |= ITER_KVEC; - i->type = direction; - i->iov = iov; + i->type = direction; + i->kvec = (struct kvec *)iov; + } else { + i->type = direction; + i->iov = iov; + } i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_init); -static ssize_t get_pages_iovec(struct iov_iter *i, - struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start) -{ - size_t offset = i->iov_offset; - const struct iovec *iov = i->iov; - size_t len; - unsigned long addr; - int n; - int res; - - len = iov->iov_len - offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - addr = (unsigned long)iov->iov_base + offset; - len += *start = addr & (PAGE_SIZE - 1); - if (len > maxpages * PAGE_SIZE) - len = maxpages * PAGE_SIZE; - addr &= ~(PAGE_SIZE - 1); - n = (len + PAGE_SIZE - 1) / PAGE_SIZE; - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); - if (unlikely(res < 0)) - return res; - return (res == n ? len : res * PAGE_SIZE) - *start; -} - -static ssize_t get_pages_alloc_iovec(struct iov_iter *i, - struct page ***pages, size_t maxsize, - size_t *start) -{ - size_t offset = i->iov_offset; - const struct iovec *iov = i->iov; - size_t len; - unsigned long addr; - void *p; - int n; - int res; - - len = iov->iov_len - offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - addr = (unsigned long)iov->iov_base + offset; - len += *start = addr & (PAGE_SIZE - 1); - addr &= ~(PAGE_SIZE - 1); - n = (len + PAGE_SIZE - 1) / PAGE_SIZE; - - p = kmalloc(n * sizeof(struct page *), GFP_KERNEL); - if (!p) - p = vmalloc(n * sizeof(struct page *)); - if (!p) - return -ENOMEM; - - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); - if (unlikely(res < 0)) { - kvfree(p); - return res; - } - *pages = p; - return (res == n ? len : res * PAGE_SIZE) - *start; -} - -static int iov_iter_npages_iovec(const struct iov_iter *i, int maxpages) -{ - size_t offset = i->iov_offset; - size_t size = i->count; - const struct iovec *iov = i->iov; - int npages = 0; - int n; - - for (n = 0; size && n < i->nr_segs; n++, iov++) { - unsigned long addr = (unsigned long)iov->iov_base + offset; - size_t len = iov->iov_len - offset; - offset = 0; - if (unlikely(!len)) /* empty segment */ - continue; - if (len > size) - len = size; - npages += (addr + len + PAGE_SIZE - 1) / PAGE_SIZE - - addr / PAGE_SIZE; - if (npages >= maxpages) /* don't bother going further */ - return maxpages; - size -= len; - offset = 0; - } - return min(npages, maxpages); -} - static void memcpy_from_page(char *to, struct page *page, size_t offset, size_t len) { char *from = kmap_atomic(page); @@ -555,293 +357,78 @@ static void memzero_page(struct page *page, size_t offset, size_t len) kunmap_atomic(addr); } -static size_t copy_to_iter_bvec(void *from, size_t bytes, struct iov_iter *i) +size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i) { - size_t skip, copy, wanted; - const struct bio_vec *bvec; - + char *from = addr; if (unlikely(bytes > i->count)) bytes = i->count; if (unlikely(!bytes)) return 0; - wanted = bytes; - bvec = i->bvec; - skip = i->iov_offset; - copy = min_t(size_t, bytes, bvec->bv_len - skip); + iterate_and_advance(i, bytes, v, + __copy_to_user(v.iov_base, (from += v.iov_len) - v.iov_len, + v.iov_len), + memcpy_to_page(v.bv_page, v.bv_offset, + (from += v.bv_len) - v.bv_len, v.bv_len), + memcpy(v.iov_base, (from += v.iov_len) - v.iov_len, v.iov_len) + ) - memcpy_to_page(bvec->bv_page, skip + bvec->bv_offset, from, copy); - skip += copy; - from += copy; - bytes -= copy; - while (bytes) { - bvec++; - copy = min(bytes, (size_t)bvec->bv_len); - memcpy_to_page(bvec->bv_page, bvec->bv_offset, from, copy); - skip = copy; - from += copy; - bytes -= copy; - } - if (skip == bvec->bv_len) { - bvec++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= bvec - i->bvec; - i->bvec = bvec; - i->iov_offset = skip; - return wanted - bytes; -} - -static size_t copy_from_iter_bvec(void *to, size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, wanted; - const struct bio_vec *bvec; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - bvec = i->bvec; - skip = i->iov_offset; - - copy = min(bytes, bvec->bv_len - skip); - - memcpy_from_page(to, bvec->bv_page, bvec->bv_offset + skip, copy); - - to += copy; - skip += copy; - bytes -= copy; - - while (bytes) { - bvec++; - copy = min(bytes, (size_t)bvec->bv_len); - memcpy_from_page(to, bvec->bv_page, bvec->bv_offset, copy); - skip = copy; - to += copy; - bytes -= copy; - } - if (skip == bvec->bv_len) { - bvec++; - skip = 0; - } - i->count -= wanted; - i->nr_segs -= bvec - i->bvec; - i->bvec = bvec; - i->iov_offset = skip; - return wanted; -} - -static size_t copy_page_to_iter_bvec(struct page *page, size_t offset, - size_t bytes, struct iov_iter *i) -{ - void *kaddr = kmap_atomic(page); - size_t wanted = copy_to_iter_bvec(kaddr + offset, bytes, i); - kunmap_atomic(kaddr); - return wanted; -} - -static size_t copy_page_from_iter_bvec(struct page *page, size_t offset, - size_t bytes, struct iov_iter *i) -{ - void *kaddr = kmap_atomic(page); - size_t wanted = copy_from_iter_bvec(kaddr + offset, bytes, i); - kunmap_atomic(kaddr); - return wanted; -} - -static size_t zero_bvec(size_t bytes, struct iov_iter *i) -{ - size_t skip, copy, wanted; - const struct bio_vec *bvec; - - if (unlikely(bytes > i->count)) - bytes = i->count; - - if (unlikely(!bytes)) - return 0; - - wanted = bytes; - bvec = i->bvec; - skip = i->iov_offset; - copy = min_t(size_t, bytes, bvec->bv_len - skip); - - memzero_page(bvec->bv_page, skip + bvec->bv_offset, copy); - skip += copy; - bytes -= copy; - while (bytes) { - bvec++; - copy = min(bytes, (size_t)bvec->bv_len); - memzero_page(bvec->bv_page, bvec->bv_offset, copy); - skip = copy; - bytes -= copy; - } - if (skip == bvec->bv_len) { - bvec++; - skip = 0; - } - i->count -= wanted - bytes; - i->nr_segs -= bvec - i->bvec; - i->bvec = bvec; - i->iov_offset = skip; - return wanted - bytes; -} - -static size_t copy_from_user_bvec(struct page *page, - struct iov_iter *i, unsigned long offset, size_t bytes) -{ - char *kaddr; - size_t left; - const struct bio_vec *bvec; - size_t base = i->iov_offset; - - kaddr = kmap_atomic(page); - for (left = bytes, bvec = i->bvec; left; bvec++, base = 0) { - size_t copy = min(left, bvec->bv_len - base); - if (!bvec->bv_len) - continue; - memcpy_from_page(kaddr + offset, bvec->bv_page, - bvec->bv_offset + base, copy); - offset += copy; - left -= copy; - } - kunmap_atomic(kaddr); return bytes; } +EXPORT_SYMBOL(copy_to_iter); -static void advance_bvec(struct iov_iter *i, size_t bytes) +size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { - BUG_ON(i->count < bytes); + char *to = addr; + if (unlikely(bytes > i->count)) + bytes = i->count; - if (likely(i->nr_segs == 1)) { - i->iov_offset += bytes; - i->count -= bytes; - } else { - const struct bio_vec *bvec = i->bvec; - size_t base = i->iov_offset; - unsigned long nr_segs = i->nr_segs; - - /* - * The !iov->iov_len check ensures we skip over unlikely - * zero-length segments (without overruning the iovec). - */ - while (bytes || unlikely(i->count && !bvec->bv_len)) { - int copy; - - copy = min(bytes, bvec->bv_len - base); - BUG_ON(!i->count || i->count < copy); - i->count -= copy; - bytes -= copy; - base += copy; - if (bvec->bv_len == base) { - bvec++; - nr_segs--; - base = 0; - } - } - i->bvec = bvec; - i->iov_offset = base; - i->nr_segs = nr_segs; - } -} - -static unsigned long alignment_bvec(const struct iov_iter *i) -{ - const struct bio_vec *bvec = i->bvec; - unsigned long res; - size_t size = i->count; - size_t n; - - if (!size) + if (unlikely(!bytes)) return 0; - res = bvec->bv_offset + i->iov_offset; - n = bvec->bv_len - i->iov_offset; - if (n >= size) - return res | size; - size -= n; - res |= n; - while (size > (++bvec)->bv_len) { - res |= bvec->bv_offset | bvec->bv_len; - size -= bvec->bv_len; - } - res |= bvec->bv_offset | size; - return res; -} + iterate_and_advance(i, bytes, v, + __copy_from_user((to += v.iov_len) - v.iov_len, v.iov_base, + v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len), + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + ) -static ssize_t get_pages_bvec(struct iov_iter *i, - struct page **pages, size_t maxsize, unsigned maxpages, - size_t *start) + return bytes; +} +EXPORT_SYMBOL(copy_from_iter); + +size_t copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { - const struct bio_vec *bvec = i->bvec; - size_t len = bvec->bv_len - i->iov_offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - /* can't be more than PAGE_SIZE */ - *start = bvec->bv_offset + i->iov_offset; + char *to = addr; + if (unlikely(bytes > i->count)) + bytes = i->count; - get_page(*pages = bvec->bv_page); + if (unlikely(!bytes)) + return 0; - return len; -} - -static ssize_t get_pages_alloc_bvec(struct iov_iter *i, - struct page ***pages, size_t maxsize, - size_t *start) -{ - const struct bio_vec *bvec = i->bvec; - size_t len = bvec->bv_len - i->iov_offset; - if (len > i->count) - len = i->count; - if (len > maxsize) - len = maxsize; - *start = bvec->bv_offset + i->iov_offset; - - *pages = kmalloc(sizeof(struct page *), GFP_KERNEL); - if (!*pages) - return -ENOMEM; - - get_page(**pages = bvec->bv_page); - - return len; -} - -static int iov_iter_npages_bvec(const struct iov_iter *i, int maxpages) -{ - size_t offset = i->iov_offset; - size_t size = i->count; - const struct bio_vec *bvec = i->bvec; - int npages = 0; - int n; - - for (n = 0; size && n < i->nr_segs; n++, bvec++) { - size_t len = bvec->bv_len - offset; - offset = 0; - if (unlikely(!len)) /* empty segment */ - continue; - if (len > size) - len = size; - npages++; - if (npages >= maxpages) /* don't bother going further */ - return maxpages; - size -= len; - offset = 0; - } - return min(npages, maxpages); + iterate_and_advance(i, bytes, v, + __copy_from_user_nocache((to += v.iov_len) - v.iov_len, + v.iov_base, v.iov_len), + memcpy_from_page((to += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len), + memcpy((to += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + ) + + return bytes; } +EXPORT_SYMBOL(copy_from_iter_nocache); size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { - if (i->type & ITER_BVEC) - return copy_page_to_iter_bvec(page, offset, bytes, i); - else + if (i->type & (ITER_BVEC|ITER_KVEC)) { + void *kaddr = kmap_atomic(page); + size_t wanted = copy_to_iter(kaddr + offset, bytes, i); + kunmap_atomic(kaddr); + return wanted; + } else return copy_page_to_iter_iovec(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_to_iter); @@ -849,57 +436,53 @@ EXPORT_SYMBOL(copy_page_to_iter); size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, struct iov_iter *i) { - if (i->type & ITER_BVEC) - return copy_page_from_iter_bvec(page, offset, bytes, i); - else + if (i->type & (ITER_BVEC|ITER_KVEC)) { + void *kaddr = kmap_atomic(page); + size_t wanted = copy_from_iter(kaddr + offset, bytes, i); + kunmap_atomic(kaddr); + return wanted; + } else return copy_page_from_iter_iovec(page, offset, bytes, i); } EXPORT_SYMBOL(copy_page_from_iter); -size_t copy_to_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - if (i->type & ITER_BVEC) - return copy_to_iter_bvec(addr, bytes, i); - else - return copy_to_iter_iovec(addr, bytes, i); -} -EXPORT_SYMBOL(copy_to_iter); - -size_t copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) -{ - if (i->type & ITER_BVEC) - return copy_from_iter_bvec(addr, bytes, i); - else - return copy_from_iter_iovec(addr, bytes, i); -} -EXPORT_SYMBOL(copy_from_iter); - size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { - if (i->type & ITER_BVEC) { - return zero_bvec(bytes, i); - } else { - return zero_iovec(bytes, i); - } + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + iterate_and_advance(i, bytes, v, + __clear_user(v.iov_base, v.iov_len), + memzero_page(v.bv_page, v.bv_offset, v.bv_len), + memset(v.iov_base, 0, v.iov_len) + ) + + return bytes; } EXPORT_SYMBOL(iov_iter_zero); size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes) { - if (i->type & ITER_BVEC) - return copy_from_user_bvec(page, i, offset, bytes); - else - return copy_from_user_atomic_iovec(page, i, offset, bytes); + char *kaddr = kmap_atomic(page), *p = kaddr + offset; + iterate_all_kinds(i, bytes, v, + __copy_from_user_inatomic((p += v.iov_len) - v.iov_len, + v.iov_base, v.iov_len), + memcpy_from_page((p += v.bv_len) - v.bv_len, v.bv_page, + v.bv_offset, v.bv_len), + memcpy((p += v.iov_len) - v.iov_len, v.iov_base, v.iov_len) + ) + kunmap_atomic(kaddr); + return bytes; } EXPORT_SYMBOL(iov_iter_copy_from_user_atomic); void iov_iter_advance(struct iov_iter *i, size_t size) { - if (i->type & ITER_BVEC) - advance_bvec(i, size); - else - advance_iovec(i, size); + iterate_and_advance(i, size, v, 0, 0, 0) } EXPORT_SYMBOL(iov_iter_advance); @@ -917,12 +500,33 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_single_seg_count); +void iov_iter_kvec(struct iov_iter *i, int direction, + const struct kvec *iov, unsigned long nr_segs, + size_t count) +{ + BUG_ON(!(direction & ITER_KVEC)); + i->type = direction; + i->kvec = (struct kvec *)iov; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count; +} +EXPORT_SYMBOL(iov_iter_kvec); + unsigned long iov_iter_alignment(const struct iov_iter *i) { - if (i->type & ITER_BVEC) - return alignment_bvec(i); - else - return alignment_iovec(i); + unsigned long res = 0; + size_t size = i->count; + + if (!size) + return 0; + + iterate_all_kinds(i, size, v, + (res |= (unsigned long)v.iov_base | v.iov_len, 0), + res |= v.bv_offset | v.bv_len, + res |= (unsigned long)v.iov_base | v.iov_len + ) + return res; } EXPORT_SYMBOL(iov_iter_alignment); @@ -930,29 +534,207 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start) { - if (i->type & ITER_BVEC) - return get_pages_bvec(i, pages, maxsize, maxpages, start); - else - return get_pages_iovec(i, pages, maxsize, maxpages, start); + if (maxsize > i->count) + maxsize = i->count; + + if (!maxsize) + return 0; + + iterate_all_kinds(i, maxsize, v, ({ + unsigned long addr = (unsigned long)v.iov_base; + size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); + int n; + int res; + + if (len > maxpages * PAGE_SIZE) + len = maxpages * PAGE_SIZE; + addr &= ~(PAGE_SIZE - 1); + n = DIV_ROUND_UP(len, PAGE_SIZE); + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); + if (unlikely(res < 0)) + return res; + return (res == n ? len : res * PAGE_SIZE) - *start; + 0;}),({ + /* can't be more than PAGE_SIZE */ + *start = v.bv_offset; + get_page(*pages = v.bv_page); + return v.bv_len; + }),({ + return -EFAULT; + }) + ) + return 0; } EXPORT_SYMBOL(iov_iter_get_pages); +static struct page **get_pages_array(size_t n) +{ + struct page **p = kmalloc(n * sizeof(struct page *), GFP_KERNEL); + if (!p) + p = vmalloc(n * sizeof(struct page *)); + return p; +} + ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start) { - if (i->type & ITER_BVEC) - return get_pages_alloc_bvec(i, pages, maxsize, start); - else - return get_pages_alloc_iovec(i, pages, maxsize, start); + struct page **p; + + if (maxsize > i->count) + maxsize = i->count; + + if (!maxsize) + return 0; + + iterate_all_kinds(i, maxsize, v, ({ + unsigned long addr = (unsigned long)v.iov_base; + size_t len = v.iov_len + (*start = addr & (PAGE_SIZE - 1)); + int n; + int res; + + addr &= ~(PAGE_SIZE - 1); + n = DIV_ROUND_UP(len, PAGE_SIZE); + p = get_pages_array(n); + if (!p) + return -ENOMEM; + res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); + if (unlikely(res < 0)) { + kvfree(p); + return res; + } + *pages = p; + return (res == n ? len : res * PAGE_SIZE) - *start; + 0;}),({ + /* can't be more than PAGE_SIZE */ + *start = v.bv_offset; + *pages = p = get_pages_array(1); + if (!p) + return -ENOMEM; + get_page(*p = v.bv_page); + return v.bv_len; + }),({ + return -EFAULT; + }) + ) + return 0; } EXPORT_SYMBOL(iov_iter_get_pages_alloc); +size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, + struct iov_iter *i) +{ + char *to = addr; + __wsum sum, next; + size_t off = 0; + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + sum = *csum; + iterate_and_advance(i, bytes, v, ({ + int err = 0; + next = csum_and_copy_from_user(v.iov_base, + (to += v.iov_len) - v.iov_len, + v.iov_len, 0, &err); + if (!err) { + sum = csum_block_add(sum, next, off); + off += v.iov_len; + } + err ? v.iov_len : 0; + }), ({ + char *p = kmap_atomic(v.bv_page); + next = csum_partial_copy_nocheck(p + v.bv_offset, + (to += v.bv_len) - v.bv_len, + v.bv_len, 0); + kunmap_atomic(p); + sum = csum_block_add(sum, next, off); + off += v.bv_len; + }),({ + next = csum_partial_copy_nocheck(v.iov_base, + (to += v.iov_len) - v.iov_len, + v.iov_len, 0); + sum = csum_block_add(sum, next, off); + off += v.iov_len; + }) + ) + *csum = sum; + return bytes; +} +EXPORT_SYMBOL(csum_and_copy_from_iter); + +size_t csum_and_copy_to_iter(void *addr, size_t bytes, __wsum *csum, + struct iov_iter *i) +{ + char *from = addr; + __wsum sum, next; + size_t off = 0; + if (unlikely(bytes > i->count)) + bytes = i->count; + + if (unlikely(!bytes)) + return 0; + + sum = *csum; + iterate_and_advance(i, bytes, v, ({ + int err = 0; + next = csum_and_copy_to_user((from += v.iov_len) - v.iov_len, + v.iov_base, + v.iov_len, 0, &err); + if (!err) { + sum = csum_block_add(sum, next, off); + off += v.iov_len; + } + err ? v.iov_len : 0; + }), ({ + char *p = kmap_atomic(v.bv_page); + next = csum_partial_copy_nocheck((from += v.bv_len) - v.bv_len, + p + v.bv_offset, + v.bv_len, 0); + kunmap_atomic(p); + sum = csum_block_add(sum, next, off); + off += v.bv_len; + }),({ + next = csum_partial_copy_nocheck((from += v.iov_len) - v.iov_len, + v.iov_base, + v.iov_len, 0); + sum = csum_block_add(sum, next, off); + off += v.iov_len; + }) + ) + *csum = sum; + return bytes; +} +EXPORT_SYMBOL(csum_and_copy_to_iter); + int iov_iter_npages(const struct iov_iter *i, int maxpages) { - if (i->type & ITER_BVEC) - return iov_iter_npages_bvec(i, maxpages); - else - return iov_iter_npages_iovec(i, maxpages); + size_t size = i->count; + int npages = 0; + + if (!size) + return 0; + + iterate_all_kinds(i, size, v, ({ + unsigned long p = (unsigned long)v.iov_base; + npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) + - p / PAGE_SIZE; + if (npages >= maxpages) + return maxpages; + 0;}),({ + npages++; + if (npages >= maxpages) + return maxpages; + }),({ + unsigned long p = (unsigned long)v.iov_base; + npages += DIV_ROUND_UP(p + v.iov_len, PAGE_SIZE) + - p / PAGE_SIZE; + if (npages >= maxpages) + return maxpages; + }) + ) + return npages; } EXPORT_SYMBOL(iov_iter_npages); diff --git a/net/atm/common.c b/net/atm/common.c index f59112944c91..b84057e41bd6 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -577,9 +577,6 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, struct atm_vcc *vcc; struct sk_buff *skb; int eff, error; - struct iov_iter from; - - iov_iter_init(&from, WRITE, m->msg_iov, m->msg_iovlen, size); lock_sock(sk); if (sock->state != SS_CONNECTED) { @@ -634,7 +631,7 @@ int vcc_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, goto out; skb->dev = NULL; /* for paths shared with net_device interfaces */ ATM_SKB(skb)->atm_options = vcc->atm_options; - if (copy_from_iter(skb_put(skb, size), size, &from) != size) { + if (copy_from_iter(skb_put(skb, size), size, &m->msg_iter) != size) { kfree_skb(skb); error = -EFAULT; goto out; diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index bdcaefd2db12..76617be1e797 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -537,12 +537,12 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb, */ chan->data = skb; - memset(&msg, 0, sizeof(msg)); - msg.msg_iov = (struct iovec *) &iv; - msg.msg_iovlen = 1; iv.iov_base = skb->data; iv.iov_len = skb->len; + memset(&msg, 0, sizeof(msg)); + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len); + err = l2cap_chan_send(chan, &msg, skb->len); if (err > 0) { netdev->stats.tx_bytes += err; @@ -1050,7 +1050,6 @@ static const struct l2cap_ops bt_6lowpan_chan_ops = { .suspend = chan_suspend_cb, .get_sndtimeo = chan_get_sndtimeo_cb, .alloc_skb = chan_alloc_skb_cb, - .memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec, .teardown = l2cap_chan_no_teardown, .defer = l2cap_chan_no_defer, diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 5dcade511fdb..cedfbda15dad 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -60,8 +60,7 @@ void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *data) memset(&msg, 0, sizeof(msg)); - msg.msg_iov = (struct iovec *) &iv; - msg.msg_iovlen = 1; + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len); l2cap_chan_send(chan, &msg, total_len); @@ -720,7 +719,6 @@ static const struct l2cap_ops a2mp_chan_ops = { .resume = l2cap_chan_no_resume, .set_shutdown = l2cap_chan_no_set_shutdown, .get_sndtimeo = l2cap_chan_no_get_sndtimeo, - .memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec, }; static struct l2cap_chan *a2mp_chan_open(struct l2cap_conn *conn, bool locked) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index a8da7ea9c2c0..a2b6dfa38a0c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -2103,8 +2103,7 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan, struct sk_buff **frag; int sent = 0; - if (chan->ops->memcpy_fromiovec(chan, skb_put(skb, count), - msg->msg_iov, count)) + if (copy_from_iter(skb_put(skb, count), count, &msg->msg_iter) != count) return -EFAULT; sent += count; @@ -2124,8 +2123,8 @@ static inline int l2cap_skbuff_fromiovec(struct l2cap_chan *chan, *frag = tmp; - if (chan->ops->memcpy_fromiovec(chan, skb_put(*frag, count), - msg->msg_iov, count)) + if (copy_from_iter(skb_put(*frag, count), count, + &msg->msg_iter) != count) return -EFAULT; sent += count; diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index b0efb7202957..f65caf41953f 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1336,13 +1336,6 @@ static struct sk_buff *l2cap_sock_alloc_skb_cb(struct l2cap_chan *chan, return skb; } -static int l2cap_sock_memcpy_fromiovec_cb(struct l2cap_chan *chan, - unsigned char *kdata, - struct iovec *iov, int len) -{ - return memcpy_fromiovec(kdata, iov, len); -} - static void l2cap_sock_ready_cb(struct l2cap_chan *chan) { struct sock *sk = chan->data; @@ -1427,7 +1420,6 @@ static const struct l2cap_ops l2cap_chan_ops = { .set_shutdown = l2cap_sock_set_shutdown_cb, .get_sndtimeo = l2cap_sock_get_sndtimeo_cb, .alloc_skb = l2cap_sock_alloc_skb_cb, - .memcpy_fromiovec = l2cap_sock_memcpy_fromiovec_cb, }; static void l2cap_sock_destruct(struct sock *sk) diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index 96bf16dcd9e9..6a46252fe66f 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -539,8 +539,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data) memset(&msg, 0, sizeof(msg)); - msg.msg_iov = (struct iovec *) &iv; - msg.msg_iovlen = 2; + iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len); l2cap_chan_send(chan, &msg, 1 + len); @@ -2865,7 +2864,6 @@ static const struct l2cap_ops smp_chan_ops = { .suspend = l2cap_chan_no_suspend, .set_shutdown = l2cap_chan_no_set_shutdown, .get_sndtimeo = l2cap_chan_no_get_sndtimeo, - .memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec, }; static inline struct l2cap_chan *smp_new_conn_cb(struct l2cap_chan *pchan) @@ -2914,7 +2912,6 @@ static const struct l2cap_ops smp_root_chan_ops = { .resume = l2cap_chan_no_resume, .set_shutdown = l2cap_chan_no_set_shutdown, .get_sndtimeo = l2cap_chan_no_get_sndtimeo, - .memcpy_fromiovec = l2cap_chan_no_memcpy_fromiovec, }; static struct l2cap_chan *smp_add_cid(struct hci_dev *hdev, u16 cid) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index ac618b0b8a4f..769b185fefbd 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -535,7 +535,7 @@ static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock, goto err; ret = -EINVAL; - if (unlikely(msg->msg_iov->iov_base == NULL)) + if (unlikely(msg->msg_iter.iov->iov_base == NULL)) goto err; noblock = msg->msg_flags & MSG_DONTWAIT; diff --git a/net/compat.c b/net/compat.c index 062f157d2a6b..3236b4167a32 100644 --- a/net/compat.c +++ b/net/compat.c @@ -37,13 +37,14 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg, struct iovec **iov) { compat_uptr_t uaddr, uiov, tmp3; + compat_size_t nr_segs; ssize_t err; if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || __get_user(uaddr, &umsg->msg_name) || __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || __get_user(uiov, &umsg->msg_iov) || - __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) || + __get_user(nr_segs, &umsg->msg_iovlen) || __get_user(tmp3, &umsg->msg_control) || __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) @@ -68,14 +69,15 @@ ssize_t get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (kmsg->msg_iovlen > UIO_MAXIOV) + if (nr_segs > UIO_MAXIOV) return -EMSGSIZE; err = compat_rw_copy_check_uvector(save_addr ? READ : WRITE, - compat_ptr(uiov), kmsg->msg_iovlen, + compat_ptr(uiov), nr_segs, UIO_FASTIOV, *iov, iov); if (err >= 0) - kmsg->msg_iov = *iov; + iov_iter_init(&kmsg->msg_iter, save_addr ? READ : WRITE, + *iov, nr_segs, err); return err; } diff --git a/net/core/datagram.c b/net/core/datagram.c index b6e303b0f01f..df493d68330c 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -309,90 +309,6 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) } EXPORT_SYMBOL(skb_kill_datagram); -/** - * skb_copy_datagram_iovec - Copy a datagram to an iovec. - * @skb: buffer to copy - * @offset: offset in the buffer to start copying from - * @to: io vector to copy to - * @len: amount of data to copy from buffer to iovec - * - * Note: the iovec is modified during the copy. - */ -int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, - struct iovec *to, int len) -{ - int start = skb_headlen(skb); - int i, copy = start - offset; - struct sk_buff *frag_iter; - - trace_skb_copy_datagram_iovec(skb, len); - - /* Copy header. */ - if (copy > 0) { - if (copy > len) - copy = len; - if (memcpy_toiovec(to, skb->data + offset, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - - /* Copy paged appendix. Hmm... why does this look so complicated? */ - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - int end; - const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - - WARN_ON(start > offset + len); - - end = start + skb_frag_size(frag); - if ((copy = end - offset) > 0) { - int err; - u8 *vaddr; - struct page *page = skb_frag_page(frag); - - if (copy > len) - copy = len; - vaddr = kmap(page); - err = memcpy_toiovec(to, vaddr + frag->page_offset + - offset - start, copy); - kunmap(page); - if (err) - goto fault; - if (!(len -= copy)) - return 0; - offset += copy; - } - start = end; - } - - skb_walk_frags(skb, frag_iter) { - int end; - - WARN_ON(start > offset + len); - - end = start + frag_iter->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_datagram_iovec(frag_iter, - offset - start, - to, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - start = end; - } - if (!len) - return 0; - -fault: - return -EFAULT; -} -EXPORT_SYMBOL(skb_copy_datagram_iovec); - /** * skb_copy_datagram_iter - Copy a datagram to an iovec iterator. * @skb: buffer to copy @@ -615,27 +531,25 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) EXPORT_SYMBOL(zerocopy_sg_from_iter); static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, - u8 __user *to, int len, + struct iov_iter *to, int len, __wsum *csump) { int start = skb_headlen(skb); int i, copy = start - offset; struct sk_buff *frag_iter; int pos = 0; + int n; /* Copy header. */ if (copy > 0) { - int err = 0; if (copy > len) copy = len; - *csump = csum_and_copy_to_user(skb->data + offset, to, copy, - *csump, &err); - if (err) + n = csum_and_copy_to_iter(skb->data + offset, copy, csump, to); + if (n != copy) goto fault; if ((len -= copy) == 0) return 0; offset += copy; - to += copy; pos = copy; } @@ -647,26 +561,22 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, end = start + skb_frag_size(frag); if ((copy = end - offset) > 0) { - __wsum csum2; - int err = 0; - u8 *vaddr; + __wsum csum2 = 0; struct page *page = skb_frag_page(frag); + u8 *vaddr = kmap(page); if (copy > len) copy = len; - vaddr = kmap(page); - csum2 = csum_and_copy_to_user(vaddr + - frag->page_offset + - offset - start, - to, copy, 0, &err); + n = csum_and_copy_to_iter(vaddr + frag->page_offset + + offset - start, copy, + &csum2, to); kunmap(page); - if (err) + if (n != copy) goto fault; *csump = csum_block_add(*csump, csum2, pos); if (!(len -= copy)) return 0; offset += copy; - to += copy; pos += copy; } start = end; @@ -691,7 +601,6 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, if ((len -= copy) == 0) return 0; offset += copy; - to += copy; pos += copy; } start = end; @@ -744,20 +653,19 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb) EXPORT_SYMBOL(__skb_checksum_complete); /** - * skb_copy_and_csum_datagram_iovec - Copy and checksum skb to user iovec. + * skb_copy_and_csum_datagram_msg - Copy and checksum skb to user iovec. * @skb: skbuff * @hlen: hardware length - * @iov: io vector + * @msg: destination * * Caller _must_ check that skb will fit to this iovec. * * Returns: 0 - success. * -EINVAL - checksum failure. - * -EFAULT - fault during copy. Beware, in this case iovec - * can be modified! + * -EFAULT - fault during copy. */ -int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, - int hlen, struct iovec *iov) +int skb_copy_and_csum_datagram_msg(struct sk_buff *skb, + int hlen, struct msghdr *msg) { __wsum csum; int chunk = skb->len - hlen; @@ -765,28 +673,20 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, if (!chunk) return 0; - /* Skip filled elements. - * Pretty silly, look at memcpy_toiovec, though 8) - */ - while (!iov->iov_len) - iov++; - - if (iov->iov_len < chunk) { + if (iov_iter_count(&msg->msg_iter) < chunk) { if (__skb_checksum_complete(skb)) goto csum_error; - if (skb_copy_datagram_iovec(skb, hlen, iov, chunk)) + if (skb_copy_datagram_msg(skb, hlen, msg, chunk)) goto fault; } else { csum = csum_partial(skb->data, hlen, skb->csum); - if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base, + if (skb_copy_and_csum_datagram(skb, hlen, &msg->msg_iter, chunk, &csum)) goto fault; if (csum_fold(csum)) goto csum_error; if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); - iov->iov_len -= chunk; - iov->iov_base += chunk; } return 0; csum_error: @@ -794,7 +694,7 @@ csum_error: fault: return -EFAULT; } -EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); +EXPORT_SYMBOL(skb_copy_and_csum_datagram_msg); /** * datagram_poll - generic datagram poll diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 4a929adf2ab7..b50861b22b6b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -752,14 +752,16 @@ EXPORT_SYMBOL(ip_fragment); int ip_generic_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { - struct iovec *iov = from; + struct msghdr *msg = from; if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (memcpy_fromiovecend(to, iov, offset, len) < 0) + /* XXX: stripping const */ + if (memcpy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len) < 0) return -EFAULT; } else { __wsum csum = 0; - if (csum_partial_copy_fromiovecend(to, iov, offset, len, &csum) < 0) + /* XXX: stripping const */ + if (csum_partial_copy_fromiovecend(to, (struct iovec *)msg->msg_iter.iov, offset, len, &csum) < 0) return -EFAULT; skb->csum = csum_block_add(skb->csum, csum, odd); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 8dd4ae0424fc..c0d82f78d364 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -811,7 +811,8 @@ back_from_confirm: pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence; - pfh.iov = msg->msg_iov; + /* XXX: stripping const */ + pfh.iov = (struct iovec *)msg->msg_iter.iov; pfh.wcheck = 0; pfh.family = AF_INET; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 43385a9fa441..0bb68df5055d 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -82,7 +82,7 @@ #include struct raw_frag_vec { - struct iovec *iov; + struct msghdr *msg; union { struct icmphdr icmph; char c[1]; @@ -440,7 +440,7 @@ static int raw_probe_proto_opt(struct raw_frag_vec *rfv, struct flowi4 *fl4) /* We only need the first two bytes. */ rfv->hlen = 2; - err = memcpy_fromiovec(rfv->hdr.c, rfv->iov, rfv->hlen); + err = memcpy_from_msg(rfv->hdr.c, rfv->msg, rfv->hlen); if (err) return err; @@ -478,7 +478,7 @@ static int raw_getfrag(void *from, char *to, int offset, int len, int odd, offset -= rfv->hlen; - return ip_generic_getfrag(rfv->iov, to, offset, len, odd, skb); + return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, @@ -600,7 +600,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, daddr, saddr, 0, 0); if (!inet->hdrincl) { - rfv.iov = msg->msg_iov; + rfv.msg = msg; rfv.hlen = 0; err = raw_probe_proto_opt(&rfv, &fl4); @@ -625,7 +625,8 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, back_from_confirm: if (inet->hdrincl) - err = raw_send_hdrinc(sk, &fl4, msg->msg_iov, len, + /* XXX: stripping const */ + err = raw_send_hdrinc(sk, &fl4, (struct iovec *)msg->msg_iter.iov, len, &rt, msg->msg_flags); else { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 427aee33ffc0..3075723c729b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1067,7 +1067,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size) { - struct iovec *iov; + const struct iovec *iov; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; int iovlen, flags, err, copied = 0; @@ -1118,8 +1118,8 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, mss_now = tcp_send_mss(sk, &size_goal, flags); /* Ok commence sending. */ - iovlen = msg->msg_iovlen; - iov = msg->msg_iov; + iovlen = msg->msg_iter.nr_segs; + iov = msg->msg_iter.iov; copied = 0; err = -EPIPE; @@ -1711,7 +1711,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) { user_recv = current; tp->ucopy.task = user_recv; - tp->ucopy.iov = msg->msg_iov; + tp->ucopy.msg = msg; } tp->ucopy.len = len; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 69de1a1c05c9..075ab4d5af5e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4421,7 +4421,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) __set_current_state(TASK_RUNNING); local_bh_enable(); - if (!skb_copy_datagram_iovec(skb, 0, tp->ucopy.iov, chunk)) { + if (!skb_copy_datagram_msg(skb, 0, tp->ucopy.msg, chunk)) { tp->ucopy.len -= chunk; tp->copied_seq += chunk; eaten = (chunk == skb->len); @@ -4941,10 +4941,9 @@ static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) local_bh_enable(); if (skb_csum_unnecessary(skb)) - err = skb_copy_datagram_iovec(skb, hlen, tp->ucopy.iov, chunk); + err = skb_copy_datagram_msg(skb, hlen, tp->ucopy.msg, chunk); else - err = skb_copy_and_csum_datagram_iovec(skb, hlen, - tp->ucopy.iov); + err = skb_copy_and_csum_datagram_msg(skb, hlen, tp->ucopy.msg); if (!err) { tp->ucopy.len -= chunk; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index f37ecf53ee8a..7f18262e2326 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3073,7 +3073,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) syn_data->ip_summed = CHECKSUM_PARTIAL; memcpy(syn_data->cb, syn->cb, sizeof(syn->cb)); if (unlikely(memcpy_fromiovecend(skb_put(syn_data, space), - fo->data->msg_iov, 0, space))) { + fo->data->msg_iter.iov, 0, space))) { kfree_skb(syn_data); goto fallback; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index dd8e00634563..13b4dcf86ef6 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1049,7 +1049,7 @@ back_from_confirm: /* Lockless fast path for the non-corking case. */ if (!corkreq) { - skb = ip_make_skb(sk, fl4, getfrag, msg->msg_iov, ulen, + skb = ip_make_skb(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, msg->msg_flags); err = PTR_ERR(skb); @@ -1080,7 +1080,7 @@ back_from_confirm: do_append_data: up->len += ulen; - err = ip_append_data(sk, fl4, getfrag, msg->msg_iov, ulen, + err = ip_append_data(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index 5b7a1ed2aba9..2d3148378a1f 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -163,7 +163,8 @@ int ping_v6_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, pfh.icmph.checksum = 0; pfh.icmph.un.echo.id = inet->inet_sport; pfh.icmph.un.echo.sequence = user_icmph.icmp6_sequence; - pfh.iov = msg->msg_iov; + /* XXX: stripping const */ + pfh.iov = (struct iovec *)msg->msg_iter.iov; pfh.wcheck = 0; pfh.family = AF_INET6; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 8baa53e17a30..ee25631f8c29 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -672,65 +672,62 @@ error: return err; } -static int rawv6_probe_proto_opt(struct flowi6 *fl6, struct msghdr *msg) +struct raw6_frag_vec { + struct msghdr *msg; + int hlen; + char c[4]; +}; + +static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { - struct iovec *iov; - u8 __user *type = NULL; - u8 __user *code = NULL; - u8 len = 0; - int probed = 0; - int i; - - if (!msg->msg_iov) - return 0; - - for (i = 0; i < msg->msg_iovlen; i++) { - iov = &msg->msg_iov[i]; - if (!iov) - continue; - - switch (fl6->flowi6_proto) { - case IPPROTO_ICMPV6: - /* check if one-byte field is readable or not. */ - if (iov->iov_base && iov->iov_len < 1) - break; - - if (!type) { - type = iov->iov_base; - /* check if code field is readable or not. */ - if (iov->iov_len > 1) - code = type + 1; - } else if (!code) - code = iov->iov_base; - - if (type && code) { - if (get_user(fl6->fl6_icmp_type, type) || - get_user(fl6->fl6_icmp_code, code)) - return -EFAULT; - probed = 1; - } - break; - case IPPROTO_MH: - if (iov->iov_base && iov->iov_len < 1) - break; - /* check if type field is readable or not. */ - if (iov->iov_len > 2 - len) { - u8 __user *p = iov->iov_base; - if (get_user(fl6->fl6_mh_type, &p[2 - len])) - return -EFAULT; - probed = 1; - } else - len += iov->iov_len; - - break; - default: - probed = 1; - break; + int err = 0; + switch (fl6->flowi6_proto) { + case IPPROTO_ICMPV6: + rfv->hlen = 2; + err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); + if (!err) { + fl6->fl6_icmp_type = rfv->c[0]; + fl6->fl6_icmp_code = rfv->c[1]; } - if (probed) - break; + break; + case IPPROTO_MH: + rfv->hlen = 4; + err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); + if (!err) + fl6->fl6_mh_type = rfv->c[2]; } - return 0; + return err; +} + +static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, + struct sk_buff *skb) +{ + struct raw6_frag_vec *rfv = from; + + if (offset < rfv->hlen) { + int copy = min(rfv->hlen - offset, len); + + if (skb->ip_summed == CHECKSUM_PARTIAL) + memcpy(to, rfv->c + offset, copy); + else + skb->csum = csum_block_add( + skb->csum, + csum_partial_copy_nocheck(rfv->c + offset, + to, copy, 0), + odd); + + odd = 0; + offset += copy; + to += copy; + len -= copy; + + if (!len) + return 0; + } + + offset -= rfv->hlen; + + return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, @@ -745,6 +742,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; + struct raw6_frag_vec rfv; struct flowi6 fl6; int addr_len = msg->msg_namelen; int hlimit = -1; @@ -848,7 +846,9 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; - err = rawv6_probe_proto_opt(&fl6, msg); + rfv.msg = msg; + rfv.hlen = 0; + err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; @@ -886,10 +886,11 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, back_from_confirm: if (inet->hdrincl) - err = rawv6_send_hdrinc(sk, msg->msg_iov, len, &fl6, &dst, msg->msg_flags); + /* XXX: stripping const */ + err = rawv6_send_hdrinc(sk, (struct iovec *)msg->msg_iter.iov, len, &fl6, &dst, msg->msg_flags); else { lock_sock(sk); - err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, + err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, msg->msg_flags, dontfrag); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 7f96432292ce..189dc4ae3eca 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1312,7 +1312,7 @@ do_append_data: dontfrag = np->dontfrag; up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - err = ip6_append_data(sk, getfrag, msg->msg_iov, ulen, + err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr), hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, dontfrag); diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 2177b960da87..8611f1b63141 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -619,7 +619,7 @@ static int l2tp_ip6_sendmsg(struct kiocb *iocb, struct sock *sk, back_from_confirm: lock_sock(sk); - err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, + err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, hlimit, tclass, opt, &fl6, (struct rt6_info *)dst, msg->msg_flags, dontfrag); diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 63aa5c8acf12..cc9bcf008b03 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2305,7 +2305,7 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock, } if (netlink_tx_is_mmaped(sk) && - msg->msg_iov->iov_base == NULL) { + msg->msg_iter.iov->iov_base == NULL) { err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, siocb); goto out; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index efa844501136..ed2e620b61df 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -2408,11 +2408,8 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) unsigned short gso_type = 0; int hlen, tlen; int extra_len = 0; - struct iov_iter from; ssize_t n; - iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len); - /* * Get and verify the address. */ @@ -2451,7 +2448,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) len -= vnet_hdr_len; err = -EFAULT; - n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &from); + n = copy_from_iter(&vnet_hdr, vnet_hdr_len, &msg->msg_iter); if (n != vnet_hdr_len) goto out_unlock; @@ -2522,7 +2519,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) } /* Returns -EFAULT on error */ - err = skb_copy_datagram_from_iter(skb, offset, &from, len); + err = skb_copy_datagram_from_iter(skb, offset, &msg->msg_iter, len); if (err) goto out_free; diff --git a/net/rds/recv.c b/net/rds/recv.c index 47d7b1029b33..f9ec1acd801c 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -404,7 +404,6 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, int ret = 0, nonblock = msg_flags & MSG_DONTWAIT; DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct rds_incoming *inc = NULL; - struct iov_iter to; /* udp_recvmsg()->sock_recvtimeo() gets away without locking too.. */ timeo = sock_rcvtimeo(sk, nonblock); @@ -415,6 +414,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, goto out; while (1) { + struct iov_iter save; /* If there are pending notifications, do those - and nothing else */ if (!list_empty(&rs->rs_notify_queue)) { ret = rds_notify_queue_get(rs, msg); @@ -450,8 +450,8 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rdsdebug("copying inc %p from %pI4:%u to user\n", inc, &inc->i_conn->c_faddr, ntohs(inc->i_hdr.h_sport)); - iov_iter_init(&to, READ, msg->msg_iov, msg->msg_iovlen, size); - ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &to); + save = msg->msg_iter; + ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter); if (ret < 0) break; @@ -464,6 +464,7 @@ int rds_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, rds_inc_put(inc); inc = NULL; rds_stats_inc(s_recv_deliver_raced); + msg->msg_iter = save; continue; } diff --git a/net/rds/send.c b/net/rds/send.c index 4de62ead1c71..40a5629a0a13 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -934,9 +934,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, int queued = 0, allocated_mr = 0; int nonblock = msg->msg_flags & MSG_DONTWAIT; long timeo = sock_sndtimeo(sk, nonblock); - struct iov_iter from; - iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, payload_len); /* Mirror Linux UDP mirror of BSD error message compatibility */ /* XXX: Perhaps MSG_MORE someday */ if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_CMSG_COMPAT)) { @@ -984,7 +982,7 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, ret = -ENOMEM; goto out; } - ret = rds_message_copy_from_user(rm, &from); + ret = rds_message_copy_from_user(rm, &msg->msg_iter); if (ret) goto out; } diff --git a/net/rxrpc/ar-output.c b/net/rxrpc/ar-output.c index 0b4b9a79f5ab..86e0f10aa2c0 100644 --- a/net/rxrpc/ar-output.c +++ b/net/rxrpc/ar-output.c @@ -531,14 +531,12 @@ static int rxrpc_send_data(struct kiocb *iocb, struct rxrpc_skb_priv *sp; unsigned char __user *from; struct sk_buff *skb; - struct iovec *iov; + const struct iovec *iov; struct sock *sk = &rx->sk; long timeo; bool more; int ret, ioc, segment, copied; - _enter(",,,{%zu},%zu", msg->msg_iovlen, len); - timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); /* this should be in poll */ @@ -547,8 +545,8 @@ static int rxrpc_send_data(struct kiocb *iocb, if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) return -EPIPE; - iov = msg->msg_iov; - ioc = msg->msg_iovlen - 1; + iov = msg->msg_iter.iov; + ioc = msg->msg_iter.nr_segs - 1; from = iov->iov_base; segment = iov->iov_len; iov++; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 0397ac9fd98c..c92f96cda699 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -1609,9 +1609,6 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, __u16 sinfo_flags = 0; long timeo; int err; - struct iov_iter from; - - iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, msg_len); err = 0; sp = sctp_sk(sk); @@ -1950,7 +1947,7 @@ static int sctp_sendmsg(struct kiocb *iocb, struct sock *sk, } /* Break the message into multiple chunks of maximum size. */ - datamsg = sctp_datamsg_from_user(asoc, sinfo, &from); + datamsg = sctp_datamsg_from_user(asoc, sinfo, &msg->msg_iter); if (IS_ERR(datamsg)) { err = PTR_ERR(datamsg); goto out_free; diff --git a/net/socket.c b/net/socket.c index f676ac4a3701..8809afccf7fa 100644 --- a/net/socket.c +++ b/net/socket.c @@ -689,8 +689,7 @@ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, * the following is safe, since for compiler definitions of kvec and * iovec are identical, yielding the same in-core layout and alignment */ - msg->msg_iov = (struct iovec *)vec; - msg->msg_iovlen = num; + iov_iter_init(&msg->msg_iter, WRITE, (struct iovec *)vec, num, size); result = sock_sendmsg(sock, msg, size); set_fs(oldfs); return result; @@ -853,7 +852,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, * the following is safe, since for compiler definitions of kvec and * iovec are identical, yielding the same in-core layout and alignment */ - msg->msg_iov = (struct iovec *)vec, msg->msg_iovlen = num; + iov_iter_init(&msg->msg_iter, READ, (struct iovec *)vec, num, size); result = sock_recvmsg(sock, msg, size, flags); set_fs(oldfs); return result; @@ -913,8 +912,7 @@ static ssize_t do_sock_read(struct msghdr *msg, struct kiocb *iocb, msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; - msg->msg_iov = (struct iovec *)iov; - msg->msg_iovlen = nr_segs; + iov_iter_init(&msg->msg_iter, READ, iov, nr_segs, size); msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; return __sock_recvmsg(iocb, sock, msg, size, msg->msg_flags); @@ -953,8 +951,7 @@ static ssize_t do_sock_write(struct msghdr *msg, struct kiocb *iocb, msg->msg_namelen = 0; msg->msg_control = NULL; msg->msg_controllen = 0; - msg->msg_iov = (struct iovec *)iov; - msg->msg_iovlen = nr_segs; + iov_iter_init(&msg->msg_iter, WRITE, iov, nr_segs, size); msg->msg_flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; if (sock->type == SOCK_SEQPACKET) msg->msg_flags |= MSG_EOR; @@ -1798,8 +1795,7 @@ SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, iov.iov_base = buff; iov.iov_len = len; msg.msg_name = NULL; - msg.msg_iov = &iov; - msg.msg_iovlen = 1; + iov_iter_init(&msg.msg_iter, WRITE, &iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; @@ -1856,10 +1852,9 @@ SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, msg.msg_control = NULL; msg.msg_controllen = 0; - msg.msg_iovlen = 1; - msg.msg_iov = &iov; iov.iov_len = size; iov.iov_base = ubuf; + iov_iter_init(&msg.msg_iter, READ, &iov, 1, size); /* Save some cycles and don't copy the address if not needed */ msg.msg_name = addr ? (struct sockaddr *)&address : NULL; /* We assume all kernel code knows the size of sockaddr_storage */ @@ -1993,13 +1988,14 @@ static ssize_t copy_msghdr_from_user(struct msghdr *kmsg, { struct sockaddr __user *uaddr; struct iovec __user *uiov; + size_t nr_segs; ssize_t err; if (!access_ok(VERIFY_READ, umsg, sizeof(*umsg)) || __get_user(uaddr, &umsg->msg_name) || __get_user(kmsg->msg_namelen, &umsg->msg_namelen) || __get_user(uiov, &umsg->msg_iov) || - __get_user(kmsg->msg_iovlen, &umsg->msg_iovlen) || + __get_user(nr_segs, &umsg->msg_iovlen) || __get_user(kmsg->msg_control, &umsg->msg_control) || __get_user(kmsg->msg_controllen, &umsg->msg_controllen) || __get_user(kmsg->msg_flags, &umsg->msg_flags)) @@ -2029,14 +2025,15 @@ static ssize_t copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (kmsg->msg_iovlen > UIO_MAXIOV) + if (nr_segs > UIO_MAXIOV) return -EMSGSIZE; err = rw_copy_check_uvector(save_addr ? READ : WRITE, - uiov, kmsg->msg_iovlen, + uiov, nr_segs, UIO_FASTIOV, *iov, iov); if (err >= 0) - kmsg->msg_iov = *iov; + iov_iter_init(&kmsg->msg_iter, save_addr ? READ : WRITE, + *iov, nr_segs, err); return err; } diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 5b0659791c07..a687b30a699c 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -194,7 +194,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, __skb_queue_tail(list, skb); skb_copy_to_linear_data(skb, mhdr, mhsz); pktpos = skb->data + mhsz; - if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iov, offset, + if (!dsz || !memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, dsz)) return dsz; rc = -EFAULT; @@ -224,7 +224,7 @@ int tipc_msg_build(struct tipc_msg *mhdr, struct msghdr *m, int offset, if (drem < pktrem) pktrem = drem; - if (memcpy_fromiovecend(pktpos, m->msg_iov, offset, pktrem)) { + if (memcpy_fromiovecend(pktpos, m->msg_iter.iov, offset, pktrem)) { rc = -EFAULT; goto error; } diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4450d6226602..8e1b10274b02 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1459,9 +1459,6 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, struct scm_cookie tmp_scm; int max_level; int data_len = 0; - struct iov_iter from; - - iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len); if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1519,7 +1516,7 @@ static int unix_dgram_sendmsg(struct kiocb *kiocb, struct socket *sock, skb_put(skb, len - data_len); skb->data_len = data_len; skb->len = len; - err = skb_copy_datagram_from_iter(skb, 0, &from, len); + err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, len); if (err) goto out_free; @@ -1641,9 +1638,6 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, bool fds_sent = false; int max_level; int data_len; - struct iov_iter from; - - iov_iter_init(&from, WRITE, msg->msg_iov, msg->msg_iovlen, len); if (NULL == siocb->scm) siocb->scm = &tmp_scm; @@ -1700,7 +1694,7 @@ static int unix_stream_sendmsg(struct kiocb *kiocb, struct socket *sock, skb_put(skb, size - data_len); skb->data_len = data_len; skb->len = size; - err = skb_copy_datagram_from_iter(skb, 0, &from, size); + err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size); if (err) { kfree_skb(skb); goto out_err; diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index c1c038952973..02d2e5229240 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -1840,9 +1840,9 @@ static ssize_t vmci_transport_stream_dequeue( int flags) { if (flags & MSG_PEEK) - return vmci_qpair_peekv(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0); + return vmci_qpair_peekv(vmci_trans(vsk)->qpair, msg, len, 0); else - return vmci_qpair_dequev(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0); + return vmci_qpair_dequev(vmci_trans(vsk)->qpair, msg, len, 0); } static ssize_t vmci_transport_stream_enqueue( @@ -1850,7 +1850,8 @@ static ssize_t vmci_transport_stream_enqueue( struct msghdr *msg, size_t len) { - return vmci_qpair_enquev(vmci_trans(vsk)->qpair, msg->msg_iov, len, 0); + /* XXX: stripping const */ + return vmci_qpair_enquev(vmci_trans(vsk)->qpair, (struct iovec *)msg->msg_iter.iov, len, 0); } static s64 vmci_transport_stream_has_data(struct vsock_sock *vsk)