Commit e2eed58 ("IB/qib: change QLogic to Intel") moved a firmware file
potentially breaking the ABI.
This patch reverts that aspect of the fix as well as reverting the
firmware name as used in qib.
Reported-by: David Woodhouse
Signed-off-by: Mike Marciniszyn
---
drivers/infinib
Commit e2eed58 ("IB/qib: change QLogic to Intel") moved a firmware file
potentially breaking the ABI.
This patch reverts that aspect of the fix as well as reverting the
firmware name as used in qib.
Reported-by: David Woodhouse
Signed-off-by: Mike Marciniszyn
---
drivers/infinib
Commit e2eed58 ("IB/qib: change QLogic to Intel") moved a firmware file
potentially breaking the ABI.
This patch reverts that aspect of the fix as well as reverting the
firmware name as used in qib.
Reported-by: David Woodhouse
Signed-off-by: Mike Marciniszyn
---
drivers/infinib
On 11/21/2020 4:51 AM, Christophe JAILLET wrote:
'pci_set_dma_mask()' + 'pci_set_consistent_dma_mask()' can be replaced by
an equivalent 'dma_set_mask_and_coherent()' which is much less verbose.
Signed-off-by: Christophe JAILLET
Thanks for the patch.
L
(-)
Looks ok!
Mike
Acked-by: Mike Marciniszyn
and tested with TID rdma to cover the interlock case.
Mike
Tested-by: Mike Marciniszyn
nt of the compare error no longer points
to the same physical address as was registered.
This patch totally resolves the issue!
Tested-by: Mike Marciniszyn
Tested-by: Josh Collier
;= 4.5-rc1 IB user memory registration thp bug
that results in memory corruption!
Reviewed-by: Dean Luick
Tested-by: Mike Marciniszyn
Tested-by: Josh Collier
e actually have this exact patch queued but have not yet sent it.
You saved us the trouble!
Mike
Acked-by: Mike Marciniszyn
9 matches
Mail list logo