netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Yonghong Song <yhs@fb.com>
To: Martin KaFai Lau <kafai@fb.com>
Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com>,
	Andrii Nakryiko <andriin@fb.com>, bpf <bpf@vger.kernel.org>,
	Networking <netdev@vger.kernel.org>,
	Alexei Starovoitov <ast@fb.com>,
	Daniel Borkmann <daniel@iogearbox.net>,
	Kernel Team <kernel-team@fb.com>
Subject: Re: [PATCH bpf-next v1 07/19] bpf: create anonymous bpf iterator
Date: Wed, 29 Apr 2020 13:54:25 -0700	[thread overview]
Message-ID: <3f9de8b8-45dc-a1f2-13d5-2f6345976814@fb.com> (raw)
In-Reply-To: <20200429205051.fjf7uxowggqoxozh@kafai-mbp>



On 4/29/20 1:50 PM, Martin KaFai Lau wrote:
> On Wed, Apr 29, 2020 at 12:20:05PM -0700, Yonghong Song wrote:
>>
>>
>> On 4/29/20 11:46 AM, Martin KaFai Lau wrote:
>>> On Wed, Apr 29, 2020 at 11:16:35AM -0700, Andrii Nakryiko wrote:
>>>> On Wed, Apr 29, 2020 at 12:07 AM Yonghong Song <yhs@fb.com> wrote:
>>>>>
>>>>>
>>>>>
>>>>> On 4/28/20 11:56 PM, Andrii Nakryiko wrote:
>>>>>> On Mon, Apr 27, 2020 at 1:19 PM Yonghong Song <yhs@fb.com> wrote:
>>>>>>>
>>>>>>> A new bpf command BPF_ITER_CREATE is added.
>>>>>>>
>>>>>>> The anonymous bpf iterator is seq_file based.
>>>>>>> The seq_file private data are referenced by targets.
>>>>>>> The bpf_iter infrastructure allocated additional space
>>>>>>> at seq_file->private after the space used by targets
>>>>>>> to store some meta data, e.g.,
>>>>>>>      prog:       prog to run
>>>>>>>      session_id: an unique id for each opened seq_file
>>>>>>>      seq_num:    how many times bpf programs are queried in this session
>>>>>>>      has_last:   indicate whether or not bpf_prog has been called after
>>>>>>>                  all valid objects have been processed
>>>>>>>
>>>>>>> A map between file and prog/link is established to help
>>>>>>> fops->release(). When fops->release() is called, just based on
>>>>>>> inode and file, bpf program cannot be located since target
>>>>>>> seq_priv_size not available. This map helps retrieve the prog
>>>>>>> whose reference count needs to be decremented.
>>>>>>>
>>>>>>> Signed-off-by: Yonghong Song <yhs@fb.com>
>>>>>>> ---
>>>>>>>     include/linux/bpf.h            |   3 +
>>>>>>>     include/uapi/linux/bpf.h       |   6 ++
>>>>>>>     kernel/bpf/bpf_iter.c          | 162 ++++++++++++++++++++++++++++++++-
>>>>>>>     kernel/bpf/syscall.c           |  27 ++++++
>>>>>>>     tools/include/uapi/linux/bpf.h |   6 ++
>>>>>>>     5 files changed, 203 insertions(+), 1 deletion(-)
>>>>>>>
>>>>>>> diff --git a/include/linux/bpf.h b/include/linux/bpf.h
>>>>>>> index 4fc39d9b5cd0..0f0cafc65a04 100644
>>>>>>> --- a/include/linux/bpf.h
>>>>>>> +++ b/include/linux/bpf.h
>>>>>>> @@ -1112,6 +1112,8 @@ struct bpf_link *bpf_link_get_from_fd(u32 ufd);
>>>>>>>     int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
>>>>>>>     int bpf_obj_get_user(const char __user *pathname, int flags);
>>>>>>>
>>>>>>> +#define BPF_DUMP_SEQ_NET_PRIVATE       BIT(0)
>>>>>>> +
>>>>>>>     struct bpf_iter_reg {
>>>>>>>            const char *target;
>>>>>>>            const char *target_func_name;
>>>>>>> @@ -1133,6 +1135,7 @@ int bpf_iter_run_prog(struct bpf_prog *prog, void *ctx);
>>>>>>>     int bpf_iter_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
>>>>>>>     int bpf_iter_link_replace(struct bpf_link *link, struct bpf_prog *old_prog,
>>>>>>>                              struct bpf_prog *new_prog);
>>>>>>> +int bpf_iter_new_fd(struct bpf_link *link);
>>>>>>>
>>>>>>>     int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
>>>>>>>     int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
>>>>>>> diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
>>>>>>> index f39b9fec37ab..576651110d16 100644
>>>>>>> --- a/include/uapi/linux/bpf.h
>>>>>>> +++ b/include/uapi/linux/bpf.h
>>>>>>> @@ -113,6 +113,7 @@ enum bpf_cmd {
>>>>>>>            BPF_MAP_DELETE_BATCH,
>>>>>>>            BPF_LINK_CREATE,
>>>>>>>            BPF_LINK_UPDATE,
>>>>>>> +       BPF_ITER_CREATE,
>>>>>>>     };
>>>>>>>
>>>>>>>     enum bpf_map_type {
>>>>>>> @@ -590,6 +591,11 @@ union bpf_attr {
>>>>>>>                    __u32           old_prog_fd;
>>>>>>>            } link_update;
>>>>>>>
>>>>>>> +       struct { /* struct used by BPF_ITER_CREATE command */
>>>>>>> +               __u32           link_fd;
>>>>>>> +               __u32           flags;
>>>>>>> +       } iter_create;
>>>>>>> +
>>>>>>>     } __attribute__((aligned(8)));
>>>>>>>
>>>>>>>     /* The description below is an attempt at providing documentation to eBPF
>>>>>>> diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
>>>>>>> index fc1ce5ee5c3f..1f4e778d1814 100644
>>>>>>> --- a/kernel/bpf/bpf_iter.c
>>>>>>> +++ b/kernel/bpf/bpf_iter.c
>>>>>>> @@ -2,6 +2,7 @@
>>>>>>>     /* Copyright (c) 2020 Facebook */
>>>>>>>
>>>>>>>     #include <linux/fs.h>
>>>>>>> +#include <linux/anon_inodes.h>
>>>>>>>     #include <linux/filter.h>
>>>>>>>     #include <linux/bpf.h>
>>>>>>>
>>>>>>> @@ -19,6 +20,19 @@ struct bpf_iter_link {
>>>>>>>            struct bpf_iter_target_info *tinfo;
>>>>>>>     };
>>>>>>>
>>>>>>> +struct extra_priv_data {
>>>>>>> +       struct bpf_prog *prog;
>>>>>>> +       u64 session_id;
>>>>>>> +       u64 seq_num;
>>>>>>> +       bool has_last;
>>>>>>> +};
>>>>>>> +
>>>>>>> +struct anon_file_prog_assoc {
>>>>>>> +       struct list_head list;
>>>>>>> +       struct file *file;
>>>>>>> +       struct bpf_prog *prog;
>>>>>>> +};
>>>>>>> +
>>>>>>>     static struct list_head targets;
>>>>>>>     static struct mutex targets_mutex;
>>>>>>>     static bool bpf_iter_inited = false;
>>>>>>> @@ -26,6 +40,50 @@ static bool bpf_iter_inited = false;
>>>>>>>     /* protect bpf_iter_link.link->prog upddate */
>>>>>>>     static struct mutex bpf_iter_mutex;
>>>>>>>
>>>>>>> +/* Since at anon seq_file release function, the prog cannot
>>>>>>> + * be retrieved since target seq_priv_size is not available.
>>>>>>> + * Keep a list of <anon_file, prog> mapping, so that
>>>>>>> + * at file release stage, the prog can be released properly.
>>>>>>> + */
>>>>>>> +static struct list_head anon_iter_info;
>>>>>>> +static struct mutex anon_iter_info_mutex;
>>>>>>> +
>>>>>>> +/* incremented on every opened seq_file */
>>>>>>> +static atomic64_t session_id;
>>>>>>> +
>>>>>>> +static u32 get_total_priv_dsize(u32 old_size)
>>>>>>> +{
>>>>>>> +       return roundup(old_size, 8) + sizeof(struct extra_priv_data);
>>>>>>> +}
>>>>>>> +
>>>>>>> +static void *get_extra_priv_dptr(void *old_ptr, u32 old_size)
>>>>>>> +{
>>>>>>> +       return old_ptr + roundup(old_size, 8);
>>>>>>> +}
>>>>>>> +
>>>>>>> +static int anon_iter_release(struct inode *inode, struct file *file)
>>>>>>> +{
>>>>>>> +       struct anon_file_prog_assoc *finfo;
>>>>>>> +
>>>>>>> +       mutex_lock(&anon_iter_info_mutex);
>>>>>>> +       list_for_each_entry(finfo, &anon_iter_info, list) {
>>>>>>> +               if (finfo->file == file) {
>>>>>>
>>>>>> I'll look at this and other patches more thoroughly tomorrow with
>>>>>> clear head, but this iteration to find anon_file_prog_assoc is really
>>>>>> unfortunate.
>>>>>>
>>>>>> I think the problem is that you are allowing seq_file infrastructure
>>>>>> to call directly into target implementation of seq_operations without
>>>>>> intercepting them. If you change that and put whatever extra info is
>>>>>> necessary into seq_file->private in front of target's private state,
>>>>>> then you shouldn't need this, right?
>>>>>
>>>>> Yes. This is true. The idea is to minimize the target change.
>>>>> But maybe this is not a good goal by itself.
>>>>>
>>>>> You are right, if I intercept all seq_ops(), I do not need the
>>>>> above change, I can tailor seq_file private_data right before
>>>>> calling target one and restore after the target call.
>>>>>
>>>>> Originally I only have one interception, show(), now I have
>>>>> stop() too to call bpf at the end of iteration. Maybe I can
>>>>> interpret all four, I think. This way, I can also get ride
>>>>> of target feature.
>>>>
>>>> If the main goal is to minimize target changes and make them exactly
>>>> seq_operations implementation, then one easier way to get easy access
>>>> to our own metadata in seq_file->private is to set it to point
>>>> **after** our metadata, but before target's metadata. Roughly in
>>>> pseudo code:
>>>>
>>>> struct bpf_iter_seq_file_meta {} __attribute((aligned(8)));
>>>>
>>>> void *meta = kmalloc(sizeof(struct bpf_iter_seq_file_meta) +
>>>> target_private_size);
>>>> seq_file->private = meta + sizeof(struct bpf_iter_seq_file_meta);
>>> I have suggested the same thing earlier.  Good to know that we think alike ;)
>>>
>>> May be put them in a struct such that container_of...etc can be used:
>>> struct bpf_iter_private {
>>>           struct extra_priv_data iter_private;
>>> 	u8 target_private[] __aligned(8);
>>> };
>>
>> This should work, but need to intercept all seq_ops() operations
>> because target expects private data is `target_private` only.
>> Let me experiment what is the best way to do this.
> As long as "seq_file->private = bpf_iter_private->target_private;" as
> Andrii also suggested, the existing seq_ops() should not have to be
> changed or needed to be intercepted because they are only
> accessing it through seq_file->private.
> 
> The bpf_iter logic should be the only one needed to access the
> bpf_iter_private->iter_private and it can be obtained by, e.g.
> "container_of(seq_file->private, struct bpf_iter_private, target_private)"

Thanks for explanation! I never thought of using container_of
magic here. It indeed work very nicely.

> 
>>
>>>
>>>>
>>>>
>>>> Then to recover bpf_iter_Seq_file_meta:
>>>>
>>>> struct bpf_iter_seq_file_meta *meta = seq_file->private - sizeof(*meta);
>>>>
>>>> /* voila! */
>>>>
>>>> This doesn't have a benefit of making targets simpler, but will
>>>> require no changes to them at all. Plus less indirect calls, so less
>>>> performance penalty.
>>>>

  reply	other threads:[~2020-04-29 20:54 UTC|newest]

Thread overview: 81+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-27 20:12 [PATCH bpf-next v1 00/19] bpf: implement bpf iterator for kernel data Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 01/19] net: refactor net assignment for seq_net_private structure Yonghong Song
2020-04-29  5:38   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 02/19] bpf: implement an interface to register bpf_iter targets Yonghong Song
2020-04-28 16:20   ` Martin KaFai Lau
2020-04-28 16:50     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 03/19] bpf: add bpf_map iterator Yonghong Song
2020-04-29  0:37   ` Martin KaFai Lau
2020-04-29  0:48     ` Alexei Starovoitov
2020-04-29  1:15       ` Yonghong Song
2020-04-29  2:44         ` Alexei Starovoitov
2020-04-29  5:09           ` Yonghong Song
2020-04-29  6:08             ` Andrii Nakryiko
2020-04-29  6:20               ` Yonghong Song
2020-04-29  6:30                 ` Alexei Starovoitov
2020-04-29  6:40                   ` Andrii Nakryiko
2020-04-29  6:44                     ` Yonghong Song
2020-04-29 15:34                       ` Alexei Starovoitov
2020-04-29 18:14                         ` Yonghong Song
2020-04-29 19:19                         ` Andrii Nakryiko
2020-04-29 20:15                           ` Yonghong Song
2020-04-30  3:06                             ` Alexei Starovoitov
2020-04-30  4:01                               ` Yonghong Song
2020-04-29  6:34                 ` Martin KaFai Lau
2020-04-29  6:51                   ` Yonghong Song
2020-04-29 19:25                     ` Andrii Nakryiko
2020-04-29  1:02     ` Yonghong Song
2020-04-29  6:04   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 04/19] bpf: allow loading of a bpf_iter program Yonghong Song
2020-04-29  0:54   ` Martin KaFai Lau
2020-04-29  1:27     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 05/19] bpf: support bpf tracing/iter programs for BPF_LINK_CREATE Yonghong Song
2020-04-29  1:17   ` [Potential Spoof] " Martin KaFai Lau
2020-04-29  6:25   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 06/19] bpf: support bpf tracing/iter programs for BPF_LINK_UPDATE Yonghong Song
2020-04-29  1:32   ` Martin KaFai Lau
2020-04-29  5:04     ` Yonghong Song
2020-04-29  5:58       ` Martin KaFai Lau
2020-04-29  6:32         ` Andrii Nakryiko
2020-04-29  6:41           ` Martin KaFai Lau
2020-04-27 20:12 ` [PATCH bpf-next v1 07/19] bpf: create anonymous bpf iterator Yonghong Song
2020-04-29  5:39   ` Martin KaFai Lau
2020-04-29  6:56   ` Andrii Nakryiko
2020-04-29  7:06     ` Yonghong Song
2020-04-29 18:16       ` Andrii Nakryiko
2020-04-29 18:46         ` Martin KaFai Lau
2020-04-29 19:20           ` Yonghong Song
2020-04-29 20:50             ` Martin KaFai Lau
2020-04-29 20:54               ` Yonghong Song [this message]
2020-04-29 19:39   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 08/19] bpf: create file " Yonghong Song
2020-04-29 20:40   ` Andrii Nakryiko
2020-04-30 18:02     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 09/19] bpf: add PTR_TO_BTF_ID_OR_NULL support Yonghong Song
2020-04-29 20:46   ` Andrii Nakryiko
2020-04-29 20:51     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 10/19] bpf: add netlink and ipv6_route targets Yonghong Song
2020-04-28 19:49   ` kbuild test robot
2020-04-28 19:50   ` [RFC PATCH] bpf: __bpf_iter__netlink() can be static kbuild test robot
2020-04-27 20:12 ` [PATCH bpf-next v1 11/19] bpf: add task and task/file targets Yonghong Song
2020-04-30  2:08   ` Andrii Nakryiko
2020-05-01 17:23     ` Yonghong Song
2020-05-01 19:01       ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 12/19] bpf: add bpf_seq_printf and bpf_seq_write helpers Yonghong Song
2020-04-28  6:02   ` kbuild test robot
2020-04-28 16:35     ` Yonghong Song
2020-04-30 20:06       ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 13/19] bpf: handle spilled PTR_TO_BTF_ID properly when checking stack_boundary Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 14/19] bpf: support variable length array in tracing programs Yonghong Song
2020-04-30 20:04   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 15/19] tools/libbpf: add bpf_iter support Yonghong Song
2020-04-30  1:41   ` Andrii Nakryiko
2020-05-02  7:17     ` Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 16/19] tools/bpftool: add bpf_iter support for bptool Yonghong Song
2020-04-28  9:27   ` Quentin Monnet
2020-04-28 17:35     ` Yonghong Song
2020-04-29  8:37       ` Quentin Monnet
2020-04-27 20:12 ` [PATCH bpf-next v1 17/19] tools/bpf: selftests: add iterator programs for ipv6_route and netlink Yonghong Song
2020-04-30  2:12   ` Andrii Nakryiko
2020-04-27 20:12 ` [PATCH bpf-next v1 18/19] tools/bpf: selftests: add iter progs for bpf_map/task/task_file Yonghong Song
2020-04-27 20:12 ` [PATCH bpf-next v1 19/19] tools/bpf: selftests: add bpf_iter selftests Yonghong Song

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=3f9de8b8-45dc-a1f2-13d5-2f6345976814@fb.com \
    --to=yhs@fb.com \
    --cc=andrii.nakryiko@gmail.com \
    --cc=andriin@fb.com \
    --cc=ast@fb.com \
    --cc=bpf@vger.kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=kafai@fb.com \
    --cc=kernel-team@fb.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).