RE: [PATCH 0/2] genirq/affinity: try to make sure online CPU is assgined to irq vector

[Don Brace]

> -----Original Message-----
> From: Ming Lei [mailto:ming.lei@xxxxxxxxxx]
> Sent: Thursday, February 01, 2018 4:37 AM
> To: Don Brace <don.brace@xxxxxxxxxxxxx>
> Cc: Laurence Oberman <loberman@xxxxxxxxxx>; Thomas Gleixner
> <tglx@xxxxxxxxxxxxx>; Christoph Hellwig <hch@xxxxxxxxxxxxx>; Jens Axboe
> <axboe@xxxxxx>; linux-block@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx;
> Mike Snitzer <snitzer@xxxxxxxxxx>
> Subject: Re: [PATCH 0/2] genirq/affinity: try to make sure online CPU is assgined
> to irq vector
> 
> EXTERNAL EMAIL
> 
> 
> On Tue, Jan 16, 2018 at 03:22:18PM +0000, Don Brace wrote:
> > > -----Original Message-----
> > > From: Laurence Oberman [mailto:loberman@xxxxxxxxxx]
> > > Sent: Tuesday, January 16, 2018 7:29 AM
> > > To: Thomas Gleixner <tglx@xxxxxxxxxxxxx>; Ming Lei <ming.lei@xxxxxxxxxx>
> > > Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>; Jens Axboe <axboe@xxxxxx>;
> > > linux-block@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; Mike Snitzer
> > > <snitzer@xxxxxxxxxx>; Don Brace <don.brace@xxxxxxxxxxxxx>
> > > Subject: Re: [PATCH 0/2] genirq/affinity: try to make sure online CPU is
> assgined
> > > to irq vector
> > >
> > > > > It is because of irq_create_affinity_masks().
> > > >
> > > > That still does not answer the question. If the interrupt for a queue
> > > > is
> > > > assigned to an offline CPU, then the queue should not be used and
> > > > never
> > > > raise an interrupt. That's how managed interrupts have been designed.
> > > >
> > > > Thanks,
> > > >
> > > >       tglx
> > > >
> > > >
> > > >
> > > >
> > >
> > > I captured a full boot log for this issue for Microsemi, I will send it
> > > to Don Brace.
> > > I enabled all the HPSA debug and here is snippet
> > >
> > >
> > > ..
> > > ..
> > > ..
> > >   246.751135] INFO: task systemd-udevd:413 blocked for more than 120
> > > seconds.
> > > [  246.788008]       Tainted: G          I      4.15.0-rc4.noming+ #1
> > > [  246.822380] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs"
> > > disables this message.
> > > [  246.865594] systemd-udevd   D    0   413    411 0x80000004
> > > [  246.895519] Call Trace:
> > > [  246.909713]  ? __schedule+0x340/0xc20
> > > [  246.930236]  schedule+0x32/0x80
> > > [  246.947905]  schedule_timeout+0x23d/0x450
> > > [  246.970047]  ? find_held_lock+0x2d/0x90
> > > [  246.991774]  ? wait_for_completion_io+0x108/0x170
> > > [  247.018172]  io_schedule_timeout+0x19/0x40
> > > [  247.041208]  wait_for_completion_io+0x110/0x170
> > > [  247.067326]  ? wake_up_q+0x70/0x70
> > > [  247.086801]  hpsa_scsi_do_simple_cmd+0xc6/0x100 [hpsa]
> > > [  247.114315]  hpsa_scsi_do_simple_cmd_with_retry+0xb7/0x1c0 [hpsa]
> > > [  247.146629]  hpsa_scsi_do_inquiry+0x73/0xd0 [hpsa]
> > > [  247.174118]  hpsa_init_one+0x12cb/0x1a59 [hpsa]
> >
> > This trace comes from internally generated discovery commands. No SCSI
> devices have
> > been presented to the SML yet.
> >
> > At this point we should be running on only one CPU. These commands are
> meant to use
> > reply queue 0 which are tied to CPU 0. It's interesting that the patch helps.
> >
> > However, I was wondering if you could inspect the iLo IML logs and send the
> > AHS logs for inspection.
> 
> Hello Don,
> 
> Now the patch has been merged to linus tree as:
> 
> 84676c1f21e8ff54b ("genirq/affinity: assign vectors to all possible CPUs")
> 
> and it breaks Laurence's machine completely, :-(
> 
> I just take a look at HPSA's code, and found that reply queue is chosen
> in the following way in most of code path:
> 
>         if (likely(reply_queue == DEFAULT_REPLY_QUEUE))
>                 cp->ReplyQueue = smp_processor_id() % h->nreply_queues;
> 
> h->nreply_queues is the msix vector number which is returned from
> pci_alloc_irq_vectors(), and now some of vectors may be mapped to all
> offline CPUs, for example, one processor isn't plugged to socket.
> 
> If I understand correctly, 'cp->ReplyQueue' is aligned to one irq
> vector, and the command is expected by handled via that irq vector,
> is it right?
> 
> If yes, now I guess this way can't work any more if number of online
> CPUs is >= h->nreply_queues, and you may need to check the cpu affinity
> of one vector before choosing the reply queue, and block/blk-mq-pci.c
> may be helpful for you.
> 
> Thanks,
> Ming

Thanks Ming,
I start working up a patch.