net: tcp: fix rx timestamp behavior for tcp_recvmsg
authorKelly Littlepage <kelly@onechronos.com>
Fri, 8 May 2020 19:58:46 +0000 (19:58 +0000)
committerJakub Kicinski <kuba@kernel.org>
Fri, 8 May 2020 23:09:22 +0000 (16:09 -0700)
commitcc4de047b33be247f9c8150d3e496743a49642b8
tree9186f31adaac25603b71240bec756b5cda7cb999
parentdd912306ff008891c82cd9f63e8181e47a9cb2fb
net: tcp: fix rx timestamp behavior for tcp_recvmsg

The stated intent of the original commit is to is to "return the timestamp
corresponding to the highest sequence number data returned." The current
implementation returns the timestamp for the last byte of the last fully
read skb, which is not necessarily the last byte in the recv buffer. This
patch converts behavior to the original definition, and to the behavior of
the previous draft versions of commit 98aaa913b4ed ("tcp: Extend
SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg") which also match this
behavior.

Fixes: 98aaa913b4ed ("tcp: Extend SOF_TIMESTAMPING_RX_SOFTWARE to TCP recvmsg")
Co-developed-by: Iris Liu <iris@onechronos.com>
Signed-off-by: Iris Liu <iris@onechronos.com>
Signed-off-by: Kelly Littlepage <kelly@onechronos.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
net/ipv4/tcp.c