IB/hfi1: Add adaptive cacheless verbs copy

The kernel memcpy is faster than a cacheless copy.  However,
if too much of the L3 cache is overwritten by one-time copies
then overall bandwidth suffers.  Implement an adaptive scheme
where full page copies are tracked and if the number of unique
entries are larger than a threshold, verbs will use a cacheless
copy.  Tracked entries are gradually cleaned, allowing memcpy to
resume once the larger copies have stopped.

Reviewed-by: Dennis Dalessandro <[email protected]>
Reviewed-by: Mike Marciniszyn <[email protected]>
Signed-off-by: Dean Luick <[email protected]>
Signed-off-by: Jubin John <[email protected]>
Signed-off-by: Doug Ledford <[email protected]>

0 files changed, 0 insertions, 0 deletions