| Message ID | 5d9c5b2d3bbc444ff32bddeece7a239d046bd79c.1380703263.git.agordeev@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Delegated to: | Bjorn Helgaas |
| Headers | show |
On Wed, Oct 02, 2013 at 12:49:10PM +0200, Alexander Gordeev wrote: > Signed-off-by: Alexander Gordeev <agordeev@redhat.com> > --- > drivers/ntb/ntb_hw.c | 2 +- > 1 files changed, 1 insertions(+), 1 deletions(-) > > diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c > index de2062c..eccd5e5 100644 > --- a/drivers/ntb/ntb_hw.c > +++ b/drivers/ntb/ntb_hw.c > @@ -1066,7 +1066,7 @@ static int ntb_setup_msix(struct ntb_device *ndev) > /* On SNB, the link interrupt is always tied to 4th vector. If > * we can't get all 4, then we can't use MSI-X. > */ > - if (ndev->hw_type != BWD_HW) { > + if ((rc < SNB_MSIX_CNT) && (ndev->hw_type != BWD_HW)) { Nack, this check is unnecessary. Also, no comment in the commit on why it could be necessary. > rc = -EIO; > goto err1; > } > -- > 1.7.7.6 > -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wed, Oct 02, 2013 at 05:48:05PM -0700, Jon Mason wrote: > On Wed, Oct 02, 2013 at 12:49:10PM +0200, Alexander Gordeev wrote: > > Signed-off-by: Alexander Gordeev <agordeev@redhat.com> > > --- > > drivers/ntb/ntb_hw.c | 2 +- > > 1 files changed, 1 insertions(+), 1 deletions(-) > > > > diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c > > index de2062c..eccd5e5 100644 > > --- a/drivers/ntb/ntb_hw.c > > +++ b/drivers/ntb/ntb_hw.c > > @@ -1066,7 +1066,7 @@ static int ntb_setup_msix(struct ntb_device *ndev) > > /* On SNB, the link interrupt is always tied to 4th vector. If > > * we can't get all 4, then we can't use MSI-X. > > */ > > - if (ndev->hw_type != BWD_HW) { > > + if ((rc < SNB_MSIX_CNT) && (ndev->hw_type != BWD_HW)) { > > Nack, this check is unnecessary. If SNB can do more than SNB_MSIX_CNT MSI-Xs then this check is needed to enable less than maximum MSI-Xs in case the maximum was not allocated. Otherwise SNB will fallback to single MSI instead of multiple MSI-Xs.
On Sat, Oct 05, 2013 at 11:43:04PM +0200, Alexander Gordeev wrote: > On Wed, Oct 02, 2013 at 05:48:05PM -0700, Jon Mason wrote: > > On Wed, Oct 02, 2013 at 12:49:10PM +0200, Alexander Gordeev wrote: > > > Signed-off-by: Alexander Gordeev <agordeev@redhat.com> > > > --- > > > drivers/ntb/ntb_hw.c | 2 +- > > > 1 files changed, 1 insertions(+), 1 deletions(-) > > > > > > diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c > > > index de2062c..eccd5e5 100644 > > > --- a/drivers/ntb/ntb_hw.c > > > +++ b/drivers/ntb/ntb_hw.c > > > @@ -1066,7 +1066,7 @@ static int ntb_setup_msix(struct ntb_device *ndev) > > > /* On SNB, the link interrupt is always tied to 4th vector. If > > > * we can't get all 4, then we can't use MSI-X. > > > */ > > > - if (ndev->hw_type != BWD_HW) { > > > + if ((rc < SNB_MSIX_CNT) && (ndev->hw_type != BWD_HW)) { > > > > Nack, this check is unnecessary. > > If SNB can do more than SNB_MSIX_CNT MSI-Xs then this check is needed > to enable less than maximum MSI-Xs in case the maximum was not allocated. > Otherwise SNB will fallback to single MSI instead of multiple MSI-Xs. Per the comment in the code snippet above, "If we can't get all 4, then we can't use MSI-X". There is already a check to see if more than 4 were acquired. So it's not possible to hit this. Even if it was, don't use SNB_MSIX_CNT here (limits.msix_cnt is the preferred variable). Also, the "()" are unnecessary. Thanks, Jon > -- > Regards, > Alexander Gordeev > agordeev@redhat.com -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Oct 07, 2013 at 09:50:57AM -0700, Jon Mason wrote: > On Sat, Oct 05, 2013 at 11:43:04PM +0200, Alexander Gordeev wrote: > > On Wed, Oct 02, 2013 at 05:48:05PM -0700, Jon Mason wrote: > > > On Wed, Oct 02, 2013 at 12:49:10PM +0200, Alexander Gordeev wrote: > > > > Signed-off-by: Alexander Gordeev <agordeev@redhat.com> > > > > --- > > > > drivers/ntb/ntb_hw.c | 2 +- > > > > 1 files changed, 1 insertions(+), 1 deletions(-) > > > > > > > > diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c > > > > index de2062c..eccd5e5 100644 > > > > --- a/drivers/ntb/ntb_hw.c > > > > +++ b/drivers/ntb/ntb_hw.c > > > > @@ -1066,7 +1066,7 @@ static int ntb_setup_msix(struct ntb_device *ndev) > > > > /* On SNB, the link interrupt is always tied to 4th vector. If > > > > * we can't get all 4, then we can't use MSI-X. > > > > */ > > > > - if (ndev->hw_type != BWD_HW) { > > > > + if ((rc < SNB_MSIX_CNT) && (ndev->hw_type != BWD_HW)) { > > > > > > Nack, this check is unnecessary. > > > > If SNB can do more than SNB_MSIX_CNT MSI-Xs then this check is needed > > to enable less than maximum MSI-Xs in case the maximum was not allocated. > > Otherwise SNB will fallback to single MSI instead of multiple MSI-Xs. > > Per the comment in the code snippet above, "If we can't get all 4, > then we can't use MSI-X". There is already a check to see if more > than 4 were acquired. So it's not possible to hit this. Even if it > was, don't use SNB_MSIX_CNT here (limits.msix_cnt is the preferred > variable). Also, the "()" are unnecessary. The changelog is definitely bogus. I meant here an improvement to the existing scheme, not a conversion to the new one: msix_entries = msix_table_size(val); Getting i.e. 16 vectors here. if (msix_entries > ndev->limits.msix_cnt) { rc = -EINVAL; goto err; } Upper limit check i.e. succeeds. [...] rc = pci_enable_msix(pdev, ndev->msix_entries, msix_entries); pci_enable_msix() does not success and returns i.e. 8 here, should retry. if (rc < 0) goto err1; if (rc > 0) { /* On SNB, the link interrupt is always tied to 4th vector. If * we can't get all 4, then we can't use MSI-X. */ if (ndev->hw_type != BWD_HW) { On SNB bail out here, although could have continue with 8 vectors. Can only use SNB_MSIX_CNT here, since limits.msix_cnt is the upper limit. rc = -EIO; goto err1; } [...] }
On Mon, Oct 07, 2013 at 08:38:45PM +0200, Alexander Gordeev wrote: > On Mon, Oct 07, 2013 at 09:50:57AM -0700, Jon Mason wrote: > > On Sat, Oct 05, 2013 at 11:43:04PM +0200, Alexander Gordeev wrote: > > > On Wed, Oct 02, 2013 at 05:48:05PM -0700, Jon Mason wrote: > > > > On Wed, Oct 02, 2013 at 12:49:10PM +0200, Alexander Gordeev wrote: > > > > > Signed-off-by: Alexander Gordeev <agordeev@redhat.com> > > > > > --- > > > > > drivers/ntb/ntb_hw.c | 2 +- > > > > > 1 files changed, 1 insertions(+), 1 deletions(-) > > > > > > > > > > diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c > > > > > index de2062c..eccd5e5 100644 > > > > > --- a/drivers/ntb/ntb_hw.c > > > > > +++ b/drivers/ntb/ntb_hw.c > > > > > @@ -1066,7 +1066,7 @@ static int ntb_setup_msix(struct ntb_device *ndev) > > > > > /* On SNB, the link interrupt is always tied to 4th vector. If > > > > > * we can't get all 4, then we can't use MSI-X. > > > > > */ > > > > > - if (ndev->hw_type != BWD_HW) { > > > > > + if ((rc < SNB_MSIX_CNT) && (ndev->hw_type != BWD_HW)) { > > > > > > > > Nack, this check is unnecessary. > > > > > > If SNB can do more than SNB_MSIX_CNT MSI-Xs then this check is needed > > > to enable less than maximum MSI-Xs in case the maximum was not allocated. > > > Otherwise SNB will fallback to single MSI instead of multiple MSI-Xs. > > > > Per the comment in the code snippet above, "If we can't get all 4, > > then we can't use MSI-X". There is already a check to see if more > > than 4 were acquired. So it's not possible to hit this. Even if it > > was, don't use SNB_MSIX_CNT here (limits.msix_cnt is the preferred > > variable). Also, the "()" are unnecessary. > > The changelog is definitely bogus. I meant here an improvement to the > existing scheme, not a conversion to the new one: > > msix_entries = msix_table_size(val); > > Getting i.e. 16 vectors here. > > if (msix_entries > ndev->limits.msix_cnt) { On SNB HW, limits.msix_cnt is set to SNB_MSIX_CNT (4) http://lxr.free-electrons.com/source/drivers/ntb/ntb_hw.c#L558 > rc = -EINVAL; > goto err; > } > > Upper limit check i.e. succeeds. > > [...] > > rc = pci_enable_msix(pdev, ndev->msix_entries, msix_entries); > > pci_enable_msix() does not success and returns i.e. 8 here, should retry. Per the above, since our upper bound is 4. We will either have this return 0 for all 4 or a number between 1 and 3 (or an error, but that's not relevant to this discussion). > if (rc < 0) > goto err1; > if (rc > 0) { > /* On SNB, the link interrupt is always tied to 4th vector. If > * we can't get all 4, then we can't use MSI-X. > */ > if (ndev->hw_type != BWD_HW) { > > On SNB bail out here, although could have continue with 8 vectors. > Can only use SNB_MSIX_CNT here, since limits.msix_cnt is the upper limit. Since we can guarantee that rc is between 1 and 3 at this point (on SNB HW), we should error out. Thanks, Jon > > rc = -EIO; > goto err1; > } > > [...] > } > > -- > Regards, > Alexander Gordeev > agordeev@redhat.com -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/drivers/ntb/ntb_hw.c b/drivers/ntb/ntb_hw.c index de2062c..eccd5e5 100644 --- a/drivers/ntb/ntb_hw.c +++ b/drivers/ntb/ntb_hw.c @@ -1066,7 +1066,7 @@ static int ntb_setup_msix(struct ntb_device *ndev) /* On SNB, the link interrupt is always tied to 4th vector. If * we can't get all 4, then we can't use MSI-X. */ - if (ndev->hw_type != BWD_HW) { + if ((rc < SNB_MSIX_CNT) && (ndev->hw_type != BWD_HW)) { rc = -EIO; goto err1; }
Signed-off-by: Alexander Gordeev <agordeev@redhat.com> --- drivers/ntb/ntb_hw.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-)