All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jakub Sitnicki <jakub@cloudflare.com>
To: Lorenzo Bianconi <lorenzo@kernel.org>
Cc: netdev@vger.kernel.org, davem@davemloft.net, ast@kernel.org,
	brouer@redhat.com, daniel@iogearbox.net, toke@redhat.com,
	lorenzo.bianconi@redhat.com, dsahern@kernel.org,
	andrii.nakryiko@gmail.com, bpf@vger.kernel.org
Subject: Re: [PATCH v7 bpf-next 0/9] introduce support for XDP programs in CPUMAP
Date: Fri, 17 Jul 2020 12:00:13 +0200	[thread overview]
Message-ID: <20200717120013.0926a74e@toad> (raw)
In-Reply-To: <cover.1594734381.git.lorenzo@kernel.org>

On Tue, 14 Jul 2020 15:56:33 +0200
Lorenzo Bianconi <lorenzo@kernel.org> wrote:

> Similar to what David Ahern proposed in [1] for DEVMAPs, introduce the
> capability to attach and run a XDP program to CPUMAP entries.
> The idea behind this feature is to add the possibility to define on which CPU
> run the eBPF program if the underlying hw does not support RSS.
> I respin patch 1/6 from a previous series sent by David [2].
> The functionality has been tested on Marvell Espressobin, i40e and mlx5.
> Detailed tests results can be found here:
> https://github.com/xdp-project/xdp-project/blob/master/areas/cpumap/cpumap04-map-xdp-prog.org
> 
> Changes since v6:
> - rebase on top of bpf-next
> - move bpf_cpumap_val and bpf_prog in the first bpf_cpu_map_entry cache-line
> 
> Changes since v5:
> - move bpf_prog_put() in put_cpu_map_entry()
> - remove READ_ONCE(rcpu->prog) in cpu_map_bpf_prog_run_xdp
> - rely on bpf_prog_get_type() instead of bpf_prog_get_type_dev() in
>   __cpu_map_load_bpf_program()
> 
> Changes since v4:
> - move xdp_clear_return_frame_no_direct inside rcu section
> - update David Ahern's email address
> 
> Changes since v3:
> - fix typo in commit message
> - fix access to ctx->ingress_ifindex in cpumap bpf selftest
> 
> Changes since v2:
> - improved comments
> - fix return value in xdp_convert_buff_to_frame
> - added patch 1/9: "cpumap: use non-locked version __ptr_ring_consume_batched"
> - do not run kmem_cache_alloc_bulk if all frames have been consumed by the XDP
>   program attached to the CPUMAP entry
> - removed bpf_trace_printk in kselftest
> 
> Changes since v1:
> - added performance test results
> - added kselftest support
> - fixed memory accounting with page_pool
> - extended xdp_redirect_cpu_user.c to load an external program to perform
>   redirect
> - reported ifindex to attached eBPF program
> - moved bpf_cpumap_val definition to include/uapi/linux/bpf.h
> 
> [1] https://patchwork.ozlabs.org/project/netdev/cover/20200529220716.75383-1-dsahern@kernel.org/
> [2] https://patchwork.ozlabs.org/project/netdev/patch/20200513014607.40418-2-dsahern@kernel.org/
> 
> David Ahern (1):
>   net: refactor xdp_convert_buff_to_frame
> 
> Jesper Dangaard Brouer (1):
>   cpumap: use non-locked version __ptr_ring_consume_batched
> 
> Lorenzo Bianconi (7):
>   samples/bpf: xdp_redirect_cpu_user: do not update bpf maps in option
>     loop
>   cpumap: formalize map value as a named struct
>   bpf: cpumap: add the possibility to attach an eBPF program to cpumap
>   bpf: cpumap: implement XDP_REDIRECT for eBPF programs attached to map
>     entries
>   libbpf: add SEC name for xdp programs attached to CPUMAP
>   samples/bpf: xdp_redirect_cpu: load a eBPF program on cpumap
>   selftest: add tests for XDP programs in CPUMAP entries
> 
>  include/linux/bpf.h                           |   6 +
>  include/net/xdp.h                             |  41 ++--
>  include/trace/events/xdp.h                    |  16 +-
>  include/uapi/linux/bpf.h                      |  14 ++
>  kernel/bpf/cpumap.c                           | 162 +++++++++++---
>  net/core/dev.c                                |   9 +
>  samples/bpf/xdp_redirect_cpu_kern.c           |  25 ++-
>  samples/bpf/xdp_redirect_cpu_user.c           | 209 ++++++++++++++++--
>  tools/include/uapi/linux/bpf.h                |  14 ++
>  tools/lib/bpf/libbpf.c                        |   2 +
>  .../bpf/prog_tests/xdp_cpumap_attach.c        |  70 ++++++
>  .../bpf/progs/test_xdp_with_cpumap_helpers.c  |  36 +++
>  12 files changed, 531 insertions(+), 73 deletions(-)
>  create mode 100644 tools/testing/selftests/bpf/prog_tests/xdp_cpumap_attach.c
>  create mode 100644 tools/testing/selftests/bpf/progs/test_xdp_with_cpumap_helpers.c
> 

This started showing up with when running ./test_progs from recent
bpf-next (bfdfa51702de). Any chance it is related?

[ 2950.440613] =============================================

[ 3073.281578] INFO: task cpumap/0/map:26:536 blocked for more than 860 seconds.
[ 3073.285492]       Tainted: G        W         5.8.0-rc4-01471-g15d51f3a516b #814
[ 3073.289177] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[ 3073.293021] cpumap/0/map:26 D    0   536      2 0x00004000
[ 3073.295755] Call Trace:
[ 3073.297143]  __schedule+0x5ad/0xf10
[ 3073.299032]  ? pci_mmcfg_check_reserved+0xd0/0xd0
[ 3073.301416]  ? static_obj+0x31/0x80
[ 3073.303277]  ? mark_held_locks+0x24/0x90
[ 3073.305313]  ? cpu_map_update_elem+0x6d0/0x6d0
[ 3073.307544]  schedule+0x6f/0x160
[ 3073.309282]  schedule_preempt_disabled+0x14/0x20
[ 3073.311593]  kthread+0x175/0x240
[ 3073.313299]  ? kthread_create_on_node+0xd0/0xd0
[ 3073.315106]  ret_from_fork+0x1f/0x30
[ 3073.316365]
               Showing all locks held in the system:
[ 3073.318423] 1 lock held by khungtaskd/33:
[ 3073.319642]  #0: ffffffff82d246a0 (rcu_read_lock){....}-{1:2}, at: debug_show_all_locks+0x28/0x1c3

[ 3073.322249] =============================================

  parent reply	other threads:[~2020-07-17 10:00 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-14 13:56 [PATCH v7 bpf-next 0/9] introduce support for XDP programs in CPUMAP Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 1/9] cpumap: use non-locked version __ptr_ring_consume_batched Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 2/9] net: refactor xdp_convert_buff_to_frame Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 3/9] samples/bpf: xdp_redirect_cpu_user: do not update bpf maps in option loop Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 4/9] cpumap: formalize map value as a named struct Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 5/9] bpf: cpumap: add the possibility to attach an eBPF program to cpumap Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 6/9] bpf: cpumap: implement XDP_REDIRECT for eBPF programs attached to map entries Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 7/9] libbpf: add SEC name for xdp programs attached to CPUMAP Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 8/9] samples/bpf: xdp_redirect_cpu: load a eBPF program on cpumap Lorenzo Bianconi
2020-07-14 13:56 ` [PATCH v7 bpf-next 9/9] selftest: add tests for XDP programs in CPUMAP entries Lorenzo Bianconi
2020-07-14 15:19 ` [PATCH v7 bpf-next 0/9] introduce support for XDP programs in CPUMAP Alexei Starovoitov
2020-07-14 15:35   ` Lorenzo Bianconi
2020-07-16 16:27     ` Daniel Borkmann
2020-07-17 10:00 ` Jakub Sitnicki [this message]
2020-07-17 10:08   ` Jakub Sitnicki
2020-07-17 11:06     ` Lorenzo Bianconi
2020-07-17 11:01   ` Lorenzo Bianconi
2020-07-17 15:13     ` Jakub Sitnicki
2020-07-17 16:31       ` Lorenzo Bianconi
2020-07-17 19:12       ` Lorenzo Bianconi
2020-07-17 23:13         ` Alexei Starovoitov

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=20200717120013.0926a74e@toad \
    --to=jakub@cloudflare.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=brouer@redhat.com \
    --cc=daniel@iogearbox.net \
    --cc=davem@davemloft.net \
    --cc=dsahern@kernel.org \
    --cc=lorenzo.bianconi@redhat.com \
    --cc=lorenzo@kernel.org \
    --cc=netdev@vger.kernel.org \
    --cc=toke@redhat.com \
    /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.