From: Jakub Kicinski <jakub.kicinski@netronome.com>
To: davem@davemloft.net
Cc: netdev@vger.kernel.org, davejwatson@fb.com, borisp@mellanox.com,
aviadye@mellanox.com, john.fastabend@gmail.com,
daniel@iogearbox.net,
Jakub Kicinski <jakub.kicinski@netronome.com>
Subject: [PATCH net-next 0/6] net/tls: add ctrl path tracing and statistics
Date: Fri, 4 Oct 2019 16:19:21 -0700 [thread overview]
Message-ID: <20191004231927.21134-1-jakub.kicinski@netronome.com> (raw)
Hi!
This set adds trace events related to TLS offload and basic MIB stats
for TLS.
First patch contains the TLS offload related trace points. Those are
helpful in troubleshooting offload issues, especially around the
resync paths.
Second patch adds a tracepoint to the fastpath of device offload,
it's separated out in case there will be objections to adding
fast path tracepoints. Again, it's quite useful for debugging
offload issues.
Next four patches add MIB statistics. The statistics are implemented
as per-cpu per-netns counters. Since there are currently no fast path
statistics we could move to atomic variables. Per-CPU seem more common.
Most basic statistics are number of created and live sessions, broken
out to offloaded and non-offloaded. Users seem to like those a lot.
Next there is a statistic for decryption errors. These are primarily
useful for device offload debug, in normal deployments decryption
errors should not be common.
Last but not least a counter for device RX resync.
Jakub Kicinski (6):
net/tls: add tracing for device/offload events
net/tls: add device decrypted trace point
net/tls: add skeleton of MIB statistics
net/tls: add statistics for installed sessions
net/tls: add TlsDecryptError stat
net/tls: add TlsDeviceRxResync statistic
Documentation/networking/tls.rst | 30 +++
.../ethernet/netronome/nfp/nfp_net_common.c | 3 +-
include/net/netns/mib.h | 3 +
include/net/snmp.h | 6 +
include/net/tls.h | 21 +-
include/uapi/linux/snmp.h | 17 ++
net/tls/Makefile | 4 +-
net/tls/tls_device.c | 36 +++-
net/tls/tls_main.c | 60 +++++-
net/tls/tls_proc.c | 47 ++++
net/tls/tls_sw.c | 5 +
net/tls/trace.c | 10 +
net/tls/trace.h | 202 ++++++++++++++++++
13 files changed, 429 insertions(+), 15 deletions(-)
create mode 100644 net/tls/tls_proc.c
create mode 100644 net/tls/trace.c
create mode 100644 net/tls/trace.h
--
2.21.0
next reply other threads:[~2019-10-04 23:19 UTC|newest]
Thread overview: 9+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-10-04 23:19 Jakub Kicinski [this message]
2019-10-04 23:19 ` [PATCH net-next 1/6] net/tls: add tracing for device/offload events Jakub Kicinski
2019-10-04 23:19 ` [PATCH net-next 2/6] net/tls: add device decrypted trace point Jakub Kicinski
2019-10-04 23:19 ` [PATCH net-next 3/6] net/tls: add skeleton of MIB statistics Jakub Kicinski
2019-10-04 23:19 ` [PATCH net-next 4/6] net/tls: add statistics for installed sessions Jakub Kicinski
2019-10-04 23:19 ` [PATCH net-next 5/6] net/tls: add TlsDecryptError stat Jakub Kicinski
2019-10-04 23:19 ` [PATCH net-next 6/6] net/tls: add TlsDeviceRxResync statistic Jakub Kicinski
2019-10-05 12:09 ` [PATCH net-next 0/6] net/tls: add ctrl path tracing and statistics Simon Horman
2019-10-05 23:29 ` David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191004231927.21134-1-jakub.kicinski@netronome.com \
--to=jakub.kicinski@netronome.com \
--cc=aviadye@mellanox.com \
--cc=borisp@mellanox.com \
--cc=daniel@iogearbox.net \
--cc=davejwatson@fb.com \
--cc=davem@davemloft.net \
--cc=john.fastabend@gmail.com \
--cc=netdev@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.