Re: [PATCH net-next RFC v5 01/15] devlink: Add reload action option to devlink reload command

[Moshe Shemesh]

On 9/23/2020 9:25 PM, Jakub Kicinski wrote:
> On Fri, 18 Sep 2020 19:06:37 +0300 Moshe Shemesh wrote:
> > Add devlink reload action to allow the user to request a specific reload
> > action. The action parameter is optional, if not specified then devlink
> > driver re-init action is used (backward compatible).
> > Note that when required to do firmware activation some drivers may need
> > to reload the driver. On the other hand some drivers may need to reset
> > the firmware to reinitialize the driver entities. Therefore, the devlink
> > reload command returns the actions which were actually performed.
> > Reload actions supported are:
> > driver_reinit: driver entities re-initialization, applying devlink-param
> >                 and devlink-resource values.
> > fw_activate: firmware activate.
> >
> > command examples:
> > $devlink dev reload pci/0000:82:00.0 action driver_reinit
> > reload_actions_performed:
> >    driver_reinit
> >
> > $devlink dev reload pci/0000:82:00.0 action fw_activate
> > reload_actions_performed:
> >    driver_reinit fw_activate
> >
> > Signed-off-by: Moshe Shemesh <moshe@xxxxxxxxxxxx>
> > @@ -3971,15 +3972,19 @@ static int mlx4_devlink_reload_up(struct devlink *devlink,
> >        int err;
> >
> >        err = mlx4_restart_one_up(persist->pdev, true, devlink);
> > -     if (err)
> > +     if (err) {
> >                mlx4_err(persist->dev, "mlx4_restart_one_up failed, ret=%d\n",
> >                         err);
> > +             return err;
> > +     }
> > +     *actions_performed = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
> FWIW I think drivers should be able to assign this even if they return
> an error. On error there is no certainty what actions were actually
> performed (e.g. when timeout happened but the device did the reset a
> little later) so this argument should not be interpreted in presence of
> errors, anyway.


Not sure I got it. Do you mean driver can assign it anyway and devlink 
should ignore in case of failure ?

As I implemented here devlink already ignores actions_performed in case 
driver returns with error.

> Also consider providing a second enum for the BIT(xyz)s.
OK.
> > -static bool devlink_reload_supported(const struct devlink *devlink)
> > +static bool devlink_reload_supported(const struct devlink_ops *ops)
> >   {
> > -     return devlink->ops->reload_down && devlink->ops->reload_up;
> > +     return ops->reload_down && ops->reload_up;
> >   }
> Please make the change to devlink_reload_supported() a separate patch.


Ack.

> > -
> > +
> What is this white space funk? 🤔


Missed that.

> >   static void devlink_reload_failed_set(struct devlink *devlink,
> >                                      bool reload_failed)
> >   {
> > @@ -2969,32 +2975,79 @@ bool devlink_is_reload_failed(const struct devlink *devlink)
> >   EXPORT_SYMBOL_GPL(devlink_is_reload_failed);
> >
> >   static int devlink_reload(struct devlink *devlink, struct net *dest_net,
> > -                       struct netlink_ext_ack *extack)
> > +                       enum devlink_reload_action action, struct netlink_ext_ack *extack,
> > +                       unsigned long *actions_performed)
> >   {
> >        int err;
> >
> >        if (!devlink->reload_enabled)
> >                return -EOPNOTSUPP;
> >
> > -     err = devlink->ops->reload_down(devlink, !!dest_net, extack);
> > +     err = devlink->ops->reload_down(devlink, !!dest_net, action, extack);
> >        if (err)
> >                return err;
> >
> >        if (dest_net && !net_eq(dest_net, devlink_net(devlink)))
> >                devlink_reload_netns_change(devlink, dest_net);
> >
> > -     err = devlink->ops->reload_up(devlink, extack);
> > +     err = devlink->ops->reload_up(devlink, action, extack, actions_performed);
> >        devlink_reload_failed_set(devlink, !!err);
> > -     return err;
> > +     if (err)
> > +             return err;
> > +
> > +     WARN_ON(!test_bit(action, actions_performed));
> > +     return 0;
> > +}
> > +
> > +static int
> > +devlink_nl_reload_actions_performed_fill(struct sk_buff *msg,
> > +                                      struct devlink *devlink,
> > +                                      unsigned long actions_performed,
> > +                                      enum devlink_command cmd, u32 portid,
> > +                                      u32 seq, int flags)
> > +{
> > +     struct nlattr *actions_performed_attr;
> > +     void *hdr;
> > +     int i;
> > +
> > +     hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
> > +     if (!hdr)
> > +             return -EMSGSIZE;
> > +
> > +     if (devlink_nl_put_handle(msg, devlink))
> > +             goto genlmsg_cancel;
> > +
> > +     actions_performed_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED);
> > +     if (!actions_performed_attr)
> > +             goto genlmsg_cancel;
> > +
> > +     for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) {
> > +             if (!test_bit(i, &actions_performed))
> > +                     continue;
> > +             if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, i))
> > +                     goto actions_performed_nest_cancel;
> Why not just return a mask? You need a special attribute for the nest,
> anyway..
>
> User space would probably actually prefer to have a single attr than an
> iteration over a nest...
OK.
> > +     }
> > +     nla_nest_end(msg, actions_performed_attr);
> > +     genlmsg_end(msg, hdr);
> > +     return 0;
> > +
> > +actions_performed_nest_cancel:
> > +     nla_nest_cancel(msg, actions_performed_attr);
> > +genlmsg_cancel:
> > +     genlmsg_cancel(msg, hdr);
> > +     return -EMSGSIZE;
> >   }
> >
> >   static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
> >   {
> >        struct devlink *devlink = info->user_ptr[0];
> > +     enum devlink_reload_action action;
> > +     unsigned long actions_performed;
> >        struct net *dest_net = NULL;
> > +     struct sk_buff *msg;
> >        int err;
> >
> > -     if (!devlink_reload_supported(devlink))
> > +     if (!devlink_reload_supported(devlink->ops))
> >                return -EOPNOTSUPP;
> >
> >        err = devlink_resources_validate(devlink, NULL, info);
> > @@ -3011,12 +3064,43 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
> >                        return PTR_ERR(dest_net);
> >        }
> >
> > -     err = devlink_reload(devlink, dest_net, info->extack);
> > +     if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
> > +             action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]);
> > +     else
> > +             action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT;
> > +
> > +     if (action == DEVLINK_RELOAD_ACTION_UNSPEC) {
> > +             NL_SET_ERR_MSG_MOD(info->extack, "Invalid reload action");
> > +             return -EINVAL;
> > +     } else if (!devlink_reload_action_is_supported(devlink, action)) {
> > +             NL_SET_ERR_MSG_MOD(info->extack, "Requested reload action is not supported by the driver");
> > +             return -EOPNOTSUPP;
> > +     }
> > +
> > +     err = devlink_reload(devlink, dest_net, action, info->extack, &actions_performed);
> Perhaps we can pass the requested action to the driver via
> actions_performed already, and then all the drivers which
> only do what they're asked to don't have to touch it?


Not sure about it. Note that in the next patch I add here limit_level 
and that has only input param, so I think it would be confusing.

> >        if (dest_net)
> >                put_net(dest_net);
> >
> > -     return err;
> > +     if (err)
> > +             return err;
> > +     /* For backward compatibility generate reply only if attributes used by user */
> > +     if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION])
> > +             return 0;
> > +
> > +     msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
> > +     if (!msg)
> > +             return -ENOMEM;
> > +
> > +     err = devlink_nl_reload_actions_performed_fill(msg, devlink, actions_performed,
> > +                                                    DEVLINK_CMD_RELOAD, info->snd_portid,
> > +                                                    info->snd_seq, 0);
> > +     if (err) {
> > +             nlmsg_free(msg);
> > +             return err;
> > +     }
> > +
> > +     return genlmsg_reply(msg, info);
> Are you using devlink_nl_reload_actions_performed_fill() somewhere else?
No
> I'd move the nlmsg_new() / genlmsg_reply() into the helper.


Can do it, but there are many _fill() functions in devlink.c code to 
fill the data, none of them include nlmsg_new() and genlmsg_reply() 
that's always in the calling function, even if the calling function adds 
only that. So I guess I will leave it for consistency.

> >   }
> >
> >   static int devlink_nl_flash_update_fill(struct sk_buff *msg,
> > @@ -7069,6 +7153,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
> >        [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 },
> >        [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 },
> >        [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED },
> > +     [DEVLINK_ATTR_RELOAD_ACTION] = { .type = NLA_U8 },
> Why not just range validation here?


All devlink attributes that pass here go through devlink_nl_poicy this 
way, including other enums.

I think changing that should be in a different patch for all, not in 
this patchset.

> >   };
> >
> >   static const struct genl_ops devlink_nl_ops[] = {
> > @@ -7402,6 +7487,20 @@ static struct genl_family devlink_nl_family __ro_after_init = {
> >        .n_mcgrps       = ARRAY_SIZE(devlink_nl_mcgrps),
> >   };
> >
> > +static bool devlink_reload_actions_valid(const struct devlink_ops *ops)
> > +{
> > +     if (!devlink_reload_supported(ops)) {
> > +             if (WARN_ON(ops->supported_reload_actions))
> > +                     return false;
> > +             return true;
> > +     }
> > +
> > +     if (WARN_ON(ops->supported_reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX) ||
> > +                 ops->supported_reload_actions <= BIT(DEVLINK_RELOAD_ACTION_UNSPEC)))
> This won't protect you from ACTION_UNSPEC being set..
>
> WARN_ON(ops->supported_reload_actions & ~GENMASK(...))


Right, I will fix.

> > +             return false;
> > +     return true;
> > +}