Andrew, David -
I remain a bit concerned regarding the merge process for this specific
patch (0003, the net/ipv4/tcp.c change) since I have other in-flight
changes for TCP receive zerocopy that I'd like to upstream for
net-next - and would like to avoid weird merge issues.
So perhaps the following could work:
1. Andrew, perhaps we could remove this particular patch (0003, the
net/ipv4/tcp.c change) from mm-next; that way we merge
vm_insert_pages() but not the call-site within TCP, for now.
2. net-next will eventually pick vm_insert_pages() up.
3. I can modify the zerocopy code to use it at that point?
Else I'm concerned a complicated merge situation may result.
What do you all think?
Thanks,
-Arjun
On Sun, Feb 16, 2020 at 6:49 PM Arjun Roy <arjunroy@xxxxxxxxxx> wrote:
>
> On Wed, Feb 12, 2020 at 6:56 PM Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> wrote:
> >
> > On Mon, 27 Jan 2020 18:59:58 -0800 Arjun Roy <arjunroy.kdev@xxxxxxxxx> wrote:
> >
> > > Use vm_insert_pages() for tcp receive zerocopy. Spin lock cycles
> > > (as reported by perf) drop from a couple of percentage points
> > > to a fraction of a percent. This results in a roughly 6% increase in
> > > efficiency, measured roughly as zerocopy receive count divided by CPU
> > > utilization.
> > >
> > > The intention of this patch-set is to reduce atomic ops for
> > > tcp zerocopy receives, which normally hits the same spinlock multiple
> > > times consecutively.
> >
> > For some reason the patch causes this:
> >
> > In file included from ./arch/x86/include/asm/atomic.h:5:0,
> > from ./include/linux/atomic.h:7,
> > from ./include/linux/crypto.h:15,
> > from ./include/crypto/hash.h:11,
> > from net/ipv4/tcp.c:246:
> > net/ipv4/tcp.c: In function ‘do_tcp_getsockopt.isra.29’:
> > ./include/linux/compiler.h:225:31: warning: ‘tp’ may be used uninitialized in this function [-Wmaybe-uninitialized]
> > case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
> > ~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~
> > net/ipv4/tcp.c:1779:19: note: ‘tp’ was declared here
> > struct tcp_sock *tp;
> > ^~
> >
> > It's a false positive. gcc-7.2.0
> >
> > : out:
> > : up_read(¤t->mm->mmap_sem);
> > : if (length) {
> > : WRITE_ONCE(tp->copied_seq, seq);
> >
> > but `length' is zero here.
> >
> > This suppresses it:
> >
> > --- a/net/ipv4/tcp.c~net-zerocopy-use-vm_insert_pages-for-tcp-rcv-zerocopy-fix
> > +++ a/net/ipv4/tcp.c
> > @@ -1788,6 +1788,8 @@ static int tcp_zerocopy_receive(struct s
> >
> > sock_rps_record_flow(sk);
> >
> > + tp = tcp_sk(sk);
> > +
> > down_read(¤t->mm->mmap_sem);
> >
> > ret = -EINVAL;
> > @@ -1796,7 +1798,6 @@ static int tcp_zerocopy_receive(struct s
> > goto out;
> > zc->length = min_t(unsigned long, zc->length, vma->vm_end - address);
> >
> > - tp = tcp_sk(sk);
> > seq = tp->copied_seq;
> > inq = tcp_inq(sk);
> > zc->length = min_t(u32, zc->length, inq);
> >
> > and I guess it's zero-cost.
> >
> >
> > Anyway, I'll sit on this lot for a while, hoping for a davem ack?
>
> Actually, speaking of the ack on the networking side:
>
> I guess this patch set is a bit weird since it requires some
> non-trivial coordination between mm and net-next? Not sure what the
> normal approach is in this case.
>
> -Arjun
