Re: [PATCH v3 5/9] perf/cxl: Accept an overflow interrupt on MSI message number 0

[Richard Cheng <icheng@nvidia.com>]

On Mon, Aug 03, 2026 at 07:30:00AM +0800, Dave Jiang wrote:
> 
> 
> On 8/2/26 10:57 PM, Richard Cheng wrote:
> > On Fri, Jul 31, 2026 at 04:28:23PM +0800, Dave Jiang wrote:
> >> cxl_pmu_probe() rejects the PMU when info->msi_vec <= 0, but that field
> >> holds the MSI/MSI-X message number the device signals overflow on. The
> >> field is 0-based, and -1 means no interrupt support. Message number 0 is
> >> valid and pci_irq_vector() takes a 0-based index, so a compliant device
> >> signalling on the first vector fails to probe.
> >>
> >> Reject only the no-interrupt case, matching how the CXL mailbox and event
> >> interrupts handle it.
> >>
> >> Fixes: 5d7107c72796 ("perf: CXL Performance Monitoring Unit driver")
> >> Reported-by: sashiko-bot@kernel.org
> >> Closes: https://sashiko.dev/#/patchset/20260715191454.459673-1-dave@stgolabs.net?part=1
> >> Assisted-by: Claude:claude-opus-4-8
> >> Reviewed-by: Jonathan Cameron <jonathan.cameron@oss.qualcomm.com>
> >> Reviewed-by: Davidlohr Bueso <dave@stgolabs.net>
> >> Signed-off-by: Dave Jiang <dave.jiang@intel.com>
> >> ---
> >> v3:
> >> - Rebase on the preceding patch, so this tests info->msi_vec rather than
> >>   info->irq. The fix is unchanged and the hunk is still one line.
> >> - Not guarding against pci_irq_vector()'s INTx fallback for vector 0, which
> >>   it returns when neither MSI nor MSI-X is enabled. A v3 draft added a
> >>   pci_dev_msi_enabled() check for that, but a modern CXL device wiring up
> >>   INTx is not a realistic prospect, and the consequence otherwise is a PMU
> >>   that counts nothing rather than anything unsafe. Left alone to keep this
> >>   a one-liner.
> >> ---
> >>  drivers/perf/cxl_pmu.c | 2 +-
> >>  1 file changed, 1 insertion(+), 1 deletion(-)
> >>
> >> diff --git a/drivers/perf/cxl_pmu.c b/drivers/perf/cxl_pmu.c
> >> index 56e6ae7bebf7..c9e30cb149df 100644
> >> --- a/drivers/perf/cxl_pmu.c
> >> +++ b/drivers/perf/cxl_pmu.c
> >> @@ -875,7 +875,7 @@ static int cxl_pmu_probe(struct device *dev)
> >>  		.capabilities = PERF_PMU_CAP_NO_EXCLUDE,
> >>  	};
> >>  
> >> -	if (info->msi_vec <= 0)
> >> +	if (info->msi_vec < 0)
> >>  		return -EINVAL;
> >>
> > 
> > Hi Dave,
> > 
> > I agree that 0 is a legal message number, but do we need to check whether
> > MSI is actually enabled ?
> 
> I actually dropped the check and added notes so sashiko doesn't freak out. I don't think it's necessary given there's not likely to have devices with INTX support.
>

I see, agree then.
 
> 
> > 
> > something like
> > """
> > if (info->msi_vec < 0 || (!pdev->msi_enabled && !pdev->msix_enabled))
> >     return -EINVAL;
> > """
> 
> I can add that if you still think it's needed. The one thing I can think of is someone pass in no_msi at the kernel commandline.  
> 

Ack on this, let's not add dead braches here.

Acked-by: Richard Cheng <icheng@nvidia.com>

Best regards,
Richard Cheng.

> > 
> > Best regards,
> > Richard Cheng
> > 
> > 
> > 
> > 
> >>  	rc = pci_irq_vector(pdev, info->msi_vec);
> >> -- 
> >> 2.55.0
> >>
> >>
>