Re: [net-next PATCH 2/3] octeontx2-af: Add devlink health reporters for NPA

[Willem de Bruijn <willemdebruijn.kernel@gmail.com>]

On Mon, Nov 2, 2020 at 12:07 AM George Cherian
<george.cherian@marvell.com> wrote:
>
> Add health reporters for RVU NPA block.
> Only reporter dump is supported
>
> Output:
>  # devlink health
>  pci/0002:01:00.0:
>    reporter npa
>      state healthy error 0 recover 0
>  # devlink  health dump show pci/0002:01:00.0 reporter npa
>  NPA_AF_GENERAL:
>         Unmap PF Error: 0
>         Free Disabled for NIX0 RX: 0
>         Free Disabled for NIX0 TX: 0
>         Free Disabled for NIX1 RX: 0
>         Free Disabled for NIX1 TX: 0
>         Free Disabled for SSO: 0
>         Free Disabled for TIM: 0
>         Free Disabled for DPI: 0
>         Free Disabled for AURA: 0
>         Alloc Disabled for Resvd: 0
>   NPA_AF_ERR:
>         Memory Fault on NPA_AQ_INST_S read: 0
>         Memory Fault on NPA_AQ_RES_S write: 0
>         AQ Doorbell Error: 0
>         Poisoned data on NPA_AQ_INST_S read: 0
>         Poisoned data on NPA_AQ_RES_S write: 0
>         Poisoned data on HW context read: 0
>   NPA_AF_RVU:
>         Unmap Slot Error: 0
>
> Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
> Signed-off-by: Jerin Jacob <jerinj@marvell.com>
> Signed-off-by: George Cherian <george.cherian@marvell.com>


> +static bool rvu_npa_af_request_irq(struct rvu *rvu, int blkaddr, int offset,
> +                                  const char *name, irq_handler_t fn)
> +{
> +       struct rvu_devlink *rvu_dl = rvu->rvu_dl;
> +       int rc;
> +
> +       WARN_ON(rvu->irq_allocated[offset]);

Please use WARN_ON sparingly for important unrecoverable events. This
seems like a basic precondition. If it can happen at all, can probably
catch in a normal branch with a netdev_err. The stacktrace in the oops
is not likely to point at the source of the non-zero value, anyway.

> +       rvu->irq_allocated[offset] = false;

Why initialize this here? Are these fields not zeroed on alloc? Is
this here only to safely call rvu_npa_unregister_interrupts on partial
alloc? Then it might be simpler to just have jump labels in this
function to free the successfully requested irqs.

> +       sprintf(&rvu->irq_name[offset * NAME_SIZE], name);
> +       rc = request_irq(pci_irq_vector(rvu->pdev, offset), fn, 0,
> +                        &rvu->irq_name[offset * NAME_SIZE], rvu_dl);
> +       if (rc)
> +               dev_warn(rvu->dev, "Failed to register %s irq\n", name);
> +       else
> +               rvu->irq_allocated[offset] = true;
> +
> +       return rvu->irq_allocated[offset];
> +}

> +static int rvu_npa_health_reporters_create(struct rvu_devlink *rvu_dl)
> +{
> +       struct devlink_health_reporter *rvu_npa_health_reporter;
> +       struct rvu_npa_event_cnt *npa_event_count;
> +       struct rvu *rvu = rvu_dl->rvu;
> +
> +       npa_event_count = kzalloc(sizeof(*npa_event_count), GFP_KERNEL);
> +       if (!npa_event_count)
> +               return -ENOMEM;
> +
> +       rvu_dl->npa_event_cnt = npa_event_count;
> +       rvu_npa_health_reporter = devlink_health_reporter_create(rvu_dl->dl,
> +                                                                &rvu_npa_hw_fault_reporter_ops,
> +                                                                0, rvu);
> +       if (IS_ERR(rvu_npa_health_reporter)) {
> +               dev_warn(rvu->dev, "Failed to create npa reporter, err =%ld\n",
> +                        PTR_ERR(rvu_npa_health_reporter));
> +               return PTR_ERR(rvu_npa_health_reporter);
> +       }
> +
> +       rvu_dl->rvu_npa_health_reporter = rvu_npa_health_reporter;
> +       return 0;
> +}
> +
> +static void rvu_npa_health_reporters_destroy(struct rvu_devlink *rvu_dl)
> +{
> +       if (!rvu_dl->rvu_npa_health_reporter)
> +               return;
> +
> +       devlink_health_reporter_destroy(rvu_dl->rvu_npa_health_reporter);
> +}
> +
> +static int rvu_health_reporters_create(struct rvu *rvu)
> +{
> +       struct rvu_devlink *rvu_dl;
> +
> +       if (!rvu->rvu_dl)
> +               return -EINVAL;
> +
> +       rvu_dl = rvu->rvu_dl;
> +       return rvu_npa_health_reporters_create(rvu_dl);

No need for local var rvu_dl. Here and below.

Without that, the entire helper is probably not needed.

> +}
> +
> +static void rvu_health_reporters_destroy(struct rvu *rvu)
> +{
> +       struct rvu_devlink *rvu_dl;
> +
> +       if (!rvu->rvu_dl)
> +               return;
> +
> +       rvu_dl = rvu->rvu_dl;
> +       rvu_npa_health_reporters_destroy(rvu_dl);
> +}
> +
>  static int rvu_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
>                                 struct netlink_ext_ack *extack)
>  {
> @@ -53,7 +483,8 @@ int rvu_register_dl(struct rvu *rvu)
>         rvu_dl->dl = dl;
>         rvu_dl->rvu = rvu;
>         rvu->rvu_dl = rvu_dl;
> -       return 0;
> +
> +       return rvu_health_reporters_create(rvu);

when would this be called with rvu->rvu_dl == NULL?