netdev - Re: [PATCH AUTOSEL 5.10 03/45] SUNRPC: Handle TCP socket sends with kernel

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Mon, 8 Feb 2021 19:34:02 +0000
From:   Trond Myklebust <trondmy@...merspace.com>
To:     "sashal@...nel.org" <sashal@...nel.org>,
        "stable@...r.kernel.org" <stable@...r.kernel.org>,
        "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>
CC:     "linux-nfs@...r.kernel.org" <linux-nfs@...r.kernel.org>,
        "daire@...g.com" <daire@...g.com>,
        "netdev@...r.kernel.org" <netdev@...r.kernel.org>,
        "chuck.lever@...cle.com" <chuck.lever@...cle.com>
Subject: Re: [PATCH AUTOSEL 5.10 03/45] SUNRPC: Handle TCP socket sends with
 kernel_sendpage() again

On Tue, 2021-01-19 at 20:25 -0500, Sasha Levin wrote:
> From: Chuck Lever <chuck.lever@...cle.com>
> 
> [ Upstream commit 4a85a6a3320b4a622315d2e0ea91a1d2b013bce4 ]
> 
> Daire Byrne reports a ~50% aggregrate throughput regression on his
> Linux NFS server after commit da1661b93bf4 ("SUNRPC: Teach server to
> use xprt_sock_sendmsg for socket sends"), which replaced
> kernel_send_page() calls in NFSD's socket send path with calls to
> sock_sendmsg() using iov_iter.
> 
> Investigation showed that tcp_sendmsg() was not using zero-copy to
> send the xdr_buf's bvec pages, but instead was relying on memcpy.
> This means copying every byte of a large NFS READ payload.
> 
> It looks like TLS sockets do indeed support a ->sendpage method,
> so it's really not necessary to use xprt_sock_sendmsg() to support
> TLS fully on the server. A mechanical reversion of da1661b93bf4 is
> not possible at this point, but we can re-implement the server's
> TCP socket sendmsg path using kernel_sendpage().
> 
> Reported-by: Daire Byrne <daire@...g.com>
> BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=209439
> Signed-off-by: Chuck Lever <chuck.lever@...cle.com>
> Signed-off-by: Sasha Levin <sashal@...nel.org>
> ---
>  net/sunrpc/svcsock.c | 86
> +++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 85 insertions(+), 1 deletion(-)
> 
> diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
> index c2752e2b9ce34..4404c491eb388 100644
> --- a/net/sunrpc/svcsock.c
> +++ b/net/sunrpc/svcsock.c
> @@ -1062,6 +1062,90 @@ static int svc_tcp_recvfrom(struct svc_rqst
> *rqstp)
>         return 0;       /* record not complete */
>  }
>  
> +static int svc_tcp_send_kvec(struct socket *sock, const struct kvec
> *vec,
> +                             int flags)
> +{
> +       return kernel_sendpage(sock, virt_to_page(vec->iov_base),
> +                              offset_in_page(vec->iov_base),
> +                              vec->iov_len, flags);

I'm having trouble with this line. This looks like it is trying to push
a slab page into kernel_sendpage(). What guarantees that the nfsd
thread won't call kfree() before the socket layer is done transmitting
the page?



-- 
Trond Myklebust
Linux NFS client maintainer, Hammerspace
trond.myklebust@...merspace.com