netdev - [RFC 0/2] net/tls: don't block after strparser error

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-next>] [day] [month] [year] [list]

Message-Id: <20191007035323.4360-1-jakub.kicinski@netronome.com>
Date:   Sun,  6 Oct 2019 20:53:21 -0700
From:   Jakub Kicinski <jakub.kicinski@...ronome.com>
To:     netdev@...r.kernel.org, davem@...emloft.net, edumazet@...gle.com,
        willemb@...gle.com
Cc:     oss-drivers@...ronome.com, davejwatson@...com, borisp@...lanox.com,
        aviadye@...lanox.com, john.fastabend@...il.com,
        daniel@...earbox.net, Jakub Kicinski <jakub.kicinski@...ronome.com>
Subject: [RFC 0/2] net/tls: don't block after strparser error

Hi!

I was investigating the correct behaviour around small receive
window size and were slightly surprised to find that currently,
if the recv buffer is too small to fit the entire record, TLS will
report -EMSGSIZE once, and then block indefinitely on a subsequent
call.

Perhaps naively I'd think that the error should keep being
reported since the error condition is never cleared.

One way or the other I'd like to engrave the correct behaviour into
a selftest so I'd appreciate guidance on which one that is :)

This set makes the TLS socket keep reporting the strparser error
until it gets closed.

Jakub Kicinski (2):
  net/tls: don't clear socket error if strparser aborted
  selftests/tls: test the small receive buffer case

 net/tls/tls_sw.c                  |  7 +++++--
 tools/testing/selftests/net/tls.c | 28 ++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 2 deletions(-)

-- 
2.21.0