On Tue, Nov 5, 2019 at 6:15 PM Burakov, Anatoly
<anatoly.bura...@intel.com> wrote:
>
> On 05-Nov-19 3:15 PM, Anatoly Burakov wrote:
> > Currently, externally created heaps are supposed to be automatically
> > mapped for VFIO DMA by EAL, however they only do so if, at the time of
> > heap creation, VFIO is initialized and has at least one device
> > available. If no devices are available at the time of heap creation (or
> > if devices were available, but were since hot-unplugged, thus dropping
> > all VFIO container mappings), then VFIO mapping code would have skipped
> > over externally allocated heaps.
> >
> > The fix is two-fold. First, we allow externally allocated memory
> > segments to be marked as "heap" segments. This allows us to distinguish
> > between external memory segments that were created via heap API, from
> > those that were created via rte_extmem_register() API.
> >
> > Then, we fix the VFIO code to only skip non-heap external segments.
> > Also, since external heaps are not guaranteed to have valid IOVA
> > addresses, we will skip those which have invalid IOVA addresses as well.
> >
> > Fixes: 0f526d674f8e ("malloc: separate creating memseg list and malloc
> > heap")
> >
> > Signed-off-by: Anatoly Burakov <anatoly.bura...@intel.com>
> > ---
> >
> > Notes:
> > This cannot be backported to older releases as it breaks the
> > API and ABI. A separate fix is in the works for stable.
> >
>
> Alternative, non-breaking implementation available (which will be slower
> due to O(N) memseg list heaps lookups):
>
> http://patches.dpdk.org/patch/62486/
>
> I'm fine with either option being merged.
>
> The more perfect solution would've been to rename "msl->external" into
> "msl->flags" and have various flags for memseg lists, but it's too late
> to break the API now.
Either way is fine for me (between the 18.11 and the master patches you sent).
Breaking the ABI is acceptable, but I agree the API is another story.
If the code seems better to you with the additional heap flag, let's go for it.
I would still like to hear from Rajesh though, since he seems to be
the first to hit this issue.
--
David Marchand
