}
EXPORT_SYMBOL(tcp_set_rcvlowat);
+static void tcp_update_recv_tstamps(struct sk_buff *skb,
+ struct scm_timestamping_internal *tss)
+{
+ if (skb->tstamp)
+ tss->ts[0] = ktime_to_timespec64(skb->tstamp);
+ else
+ tss->ts[0] = (struct timespec64) {0};
+
+ if (skb_hwtstamps(skb)->hwtstamp)
+ tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp);
+ else
+ tss->ts[2] = (struct timespec64) {0};
+}
+
#ifdef CONFIG_MMU
static const struct vm_operations_struct tcp_vm_ops = {
};
struct scm_timestamping_internal *tss,
int *cmsg_flags);
static int receive_fallback_to_copy(struct sock *sk,
- struct tcp_zerocopy_receive *zc, int inq)
+ struct tcp_zerocopy_receive *zc, int inq,
+ struct scm_timestamping_internal *tss)
{
unsigned long copy_address = (unsigned long)zc->copybuf_address;
- struct scm_timestamping_internal tss_unused;
- int err, cmsg_flags_unused;
struct msghdr msg = {};
struct iovec iov;
+ int err;
zc->length = 0;
zc->recv_skip_hint = 0;
return err;
err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0,
- &tss_unused, &cmsg_flags_unused);
+ tss, &zc->msg_flags);
if (err < 0)
return err;
return (__s32)copylen;
}
-static int tcp_zerocopy_handle_leftover_data(struct tcp_zerocopy_receive *zc,
- struct sock *sk,
- struct sk_buff *skb,
- u32 *seq,
- s32 copybuf_len)
+static int tcp_zc_handle_leftover(struct tcp_zerocopy_receive *zc,
+ struct sock *sk,
+ struct sk_buff *skb,
+ u32 *seq,
+ s32 copybuf_len,
+ struct scm_timestamping_internal *tss)
{
u32 offset, copylen = min_t(u32, copybuf_len, zc->recv_skip_hint);
if (!copylen)
return 0;
/* skb is null if inq < PAGE_SIZE. */
- if (skb)
+ if (skb) {
offset = *seq - TCP_SKB_CB(skb)->seq;
- else
+ } else {
skb = tcp_recv_skb(sk, *seq, &offset);
+ if (TCP_SKB_CB(skb)->has_rxtstamp) {
+ tcp_update_recv_tstamps(skb, tss);
+ zc->msg_flags |= TCP_CMSG_TS;
+ }
+ }
zc->copybuf_len = tcp_copy_straggler_data(zc, skb, copylen, &offset,
seq);
err);
}
+static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+ struct scm_timestamping_internal *tss);
+static void tcp_zc_finalize_rx_tstamp(struct sock *sk,
+ struct tcp_zerocopy_receive *zc,
+ struct scm_timestamping_internal *tss)
+{
+ unsigned long msg_control_addr;
+ struct msghdr cmsg_dummy;
+
+ msg_control_addr = (unsigned long)zc->msg_control;
+ cmsg_dummy.msg_control = (void *)msg_control_addr;
+ cmsg_dummy.msg_controllen =
+ (__kernel_size_t)zc->msg_controllen;
+ cmsg_dummy.msg_flags = in_compat_syscall()
+ ? MSG_CMSG_COMPAT : 0;
+ zc->msg_flags = 0;
+ if (zc->msg_control == msg_control_addr &&
+ zc->msg_controllen == cmsg_dummy.msg_controllen) {
+ tcp_recv_timestamp(&cmsg_dummy, sk, tss);
+ zc->msg_control = (__u64)
+ ((uintptr_t)cmsg_dummy.msg_control);
+ zc->msg_controllen =
+ (__u64)cmsg_dummy.msg_controllen;
+ zc->msg_flags = (__u32)cmsg_dummy.msg_flags;
+ }
+}
+
#define TCP_ZEROCOPY_PAGE_BATCH_SIZE 32
static int tcp_zerocopy_receive(struct sock *sk,
- struct tcp_zerocopy_receive *zc)
+ struct tcp_zerocopy_receive *zc,
+ struct scm_timestamping_internal *tss)
{
u32 length = 0, offset, vma_len, avail_len, copylen = 0;
unsigned long address = (unsigned long)zc->address;
int ret;
zc->copybuf_len = 0;
+ zc->msg_flags = 0;
if (address & (PAGE_SIZE - 1) || address != zc->address)
return -EINVAL;
sock_rps_record_flow(sk);
if (inq && inq <= copybuf_len)
- return receive_fallback_to_copy(sk, zc, inq);
+ return receive_fallback_to_copy(sk, zc, inq, tss);
if (inq < PAGE_SIZE) {
zc->length = 0;
} else {
skb = tcp_recv_skb(sk, seq, &offset);
}
+
+ if (TCP_SKB_CB(skb)->has_rxtstamp) {
+ tcp_update_recv_tstamps(skb, tss);
+ zc->msg_flags |= TCP_CMSG_TS;
+ }
zc->recv_skip_hint = skb->len - offset;
frags = skb_advance_to_frag(skb, offset, &offset_frag);
if (!frags || offset_frag)
mmap_read_unlock(current->mm);
/* Try to copy straggler data. */
if (!ret)
- copylen = tcp_zerocopy_handle_leftover_data(zc, sk, skb, &seq,
- copybuf_len);
+ copylen = tcp_zc_handle_leftover(zc, sk, skb, &seq, copybuf_len, tss);
if (length + copylen) {
WRITE_ONCE(tp->copied_seq, seq);
}
#endif
-static void tcp_update_recv_tstamps(struct sk_buff *skb,
- struct scm_timestamping_internal *tss)
-{
- if (skb->tstamp)
- tss->ts[0] = ktime_to_timespec64(skb->tstamp);
- else
- tss->ts[0] = (struct timespec64) {0};
-
- if (skb_hwtstamps(skb)->hwtstamp)
- tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp);
- else
- tss->ts[2] = (struct timespec64) {0};
-}
-
/* Similar to __sock_recv_timestamp, but does not require an skb */
static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
struct scm_timestamping_internal *tss)
}
#ifdef CONFIG_MMU
case TCP_ZEROCOPY_RECEIVE: {
+ struct scm_timestamping_internal tss;
struct tcp_zerocopy_receive zc = {};
int err;
if (copy_from_user(&zc, optval, len))
return -EFAULT;
lock_sock(sk);
- err = tcp_zerocopy_receive(sk, &zc);
+ err = tcp_zerocopy_receive(sk, &zc, &tss);
release_sock(sk);
- if (len >= offsetofend(struct tcp_zerocopy_receive, err))
- goto zerocopy_rcv_sk_err;
+ if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags))
+ goto zerocopy_rcv_cmsg;
switch (len) {
+ case offsetofend(struct tcp_zerocopy_receive, msg_flags):
+ goto zerocopy_rcv_cmsg;
+ case offsetofend(struct tcp_zerocopy_receive, msg_controllen):
+ case offsetofend(struct tcp_zerocopy_receive, msg_control):
+ case offsetofend(struct tcp_zerocopy_receive, flags):
+ case offsetofend(struct tcp_zerocopy_receive, copybuf_len):
+ case offsetofend(struct tcp_zerocopy_receive, copybuf_address):
case offsetofend(struct tcp_zerocopy_receive, err):
goto zerocopy_rcv_sk_err;
case offsetofend(struct tcp_zerocopy_receive, inq):
default:
goto zerocopy_rcv_out;
}
+zerocopy_rcv_cmsg:
+ if (zc.msg_flags & TCP_CMSG_TS)
+ tcp_zc_finalize_rx_tstamp(sk, &zc, &tss);
+ else
+ zc.msg_flags = 0;
zerocopy_rcv_sk_err:
if (!err)
zc.err = sock_error(sk);