| Message ID | cover.1562162469.git.pabeni@redhat.com |
|---|---|
| Headers | show |
| Series | net: use ICW for sk_proto->{send,recv}msg | expand |
On Wed, Jul 3, 2019 at 10:07 AM Paolo Abeni <pabeni@redhat.com> wrote: > > This series extends ICW usage to one of the few remaining spots in fast-path > still hitting per packet retpoline overhead, namely the sk_proto->{send,recv}msg > calls. > > The first 3 patches in this series refactor the existing code so that applying > the ICW macros is straight-forward: we demux inet_{recv,send}msg in ipv4 and > ipv6 variants so that each of them can easily select the appropriate TCP or UDP > direct call. While at it, a new helper is created to avoid excessive code > duplication, and the current ICWs for inet_{recv,send}msg are adjusted > accordingly. > > The last 2 patches really introduce the new ICW use-case, respectively for the > ipv6 and the ipv4 code path. > > This gives up to 5% performance improvement under UDP flood, and smaller but > measurable gains for TCP RR workloads. > > v1 -> v2: > - drop inet6_{recv,send}msg declaration from header file, > prefer ICW macro instead > - avoid unneeded reclaration for udp_sendmsg, as suggested by Willem > > Paolo Abeni (5): > inet: factor out inet_send_prepare() > ipv6: provide and use ipv6 specific version for {recv,send}msg > net: adjust socket level ICW to cope with ipv6 variant of > {recv,send}msg > ipv6: use indirect call wrappers for {tcp,udpv6}_{recv,send}msg() > ipv4: use indirect call wrappers for {tcp,udp}_{recv,send}msg() Acked-by: Willem de Bruijn <willemb@google.com>
From: Willem de Bruijn <willemdebruijn.kernel@gmail.com> Date: Wed, 3 Jul 2019 10:45:13 -0400 > On Wed, Jul 3, 2019 at 10:07 AM Paolo Abeni <pabeni@redhat.com> wrote: >> >> This series extends ICW usage to one of the few remaining spots in fast-path >> still hitting per packet retpoline overhead, namely the sk_proto->{send,recv}msg >> calls. >> >> The first 3 patches in this series refactor the existing code so that applying >> the ICW macros is straight-forward: we demux inet_{recv,send}msg in ipv4 and >> ipv6 variants so that each of them can easily select the appropriate TCP or UDP >> direct call. While at it, a new helper is created to avoid excessive code >> duplication, and the current ICWs for inet_{recv,send}msg are adjusted >> accordingly. >> >> The last 2 patches really introduce the new ICW use-case, respectively for the >> ipv6 and the ipv4 code path. >> >> This gives up to 5% performance improvement under UDP flood, and smaller but >> measurable gains for TCP RR workloads. >> >> v1 -> v2: >> - drop inet6_{recv,send}msg declaration from header file, >> prefer ICW macro instead >> - avoid unneeded reclaration for udp_sendmsg, as suggested by Willem >> >> Paolo Abeni (5): >> inet: factor out inet_send_prepare() >> ipv6: provide and use ipv6 specific version for {recv,send}msg >> net: adjust socket level ICW to cope with ipv6 variant of >> {recv,send}msg >> ipv6: use indirect call wrappers for {tcp,udpv6}_{recv,send}msg() >> ipv4: use indirect call wrappers for {tcp,udp}_{recv,send}msg() > > Acked-by: Willem de Bruijn <willemb@google.com> Series applied, thanks.
This series extends ICW usage to one of the few remaining spots in fast-path still hitting per packet retpoline overhead, namely the sk_proto->{send,recv}msg calls. The first 3 patches in this series refactor the existing code so that applying the ICW macros is straight-forward: we demux inet_{recv,send}msg in ipv4 and ipv6 variants so that each of them can easily select the appropriate TCP or UDP direct call. While at it, a new helper is created to avoid excessive code duplication, and the current ICWs for inet_{recv,send}msg are adjusted accordingly. The last 2 patches really introduce the new ICW use-case, respectively for the ipv6 and the ipv4 code path. This gives up to 5% performance improvement under UDP flood, and smaller but measurable gains for TCP RR workloads. v1 -> v2: - drop inet6_{recv,send}msg declaration from header file, prefer ICW macro instead - avoid unneeded reclaration for udp_sendmsg, as suggested by Willem Paolo Abeni (5): inet: factor out inet_send_prepare() ipv6: provide and use ipv6 specific version for {recv,send}msg net: adjust socket level ICW to cope with ipv6 variant of {recv,send}msg ipv6: use indirect call wrappers for {tcp,udpv6}_{recv,send}msg() ipv4: use indirect call wrappers for {tcp,udp}_{recv,send}msg() include/net/inet_common.h | 1 + net/ipv4/af_inet.c | 31 ++++++++++++++++++----------- net/ipv6/af_inet6.c | 41 +++++++++++++++++++++++++++++++++++---- net/socket.c | 23 +++++++++++----------- 4 files changed, 69 insertions(+), 27 deletions(-)