[PATCH net v1 0/2] avoid compiler and IQ/OQ reordering

Vimlesh Kumar posted 2 patches 1 month, 2 weeks ago
.../ethernet/marvell/octeon_ep/octep_main.c   | 40 +++++++++++++------
.../net/ethernet/marvell/octeon_ep/octep_rx.c | 27 +++++++++----
.../marvell/octeon_ep_vf/octep_vf_main.c      | 38 +++++++++++++-----
.../marvell/octeon_ep_vf/octep_vf_rx.c        | 28 +++++++++----
4 files changed, 95 insertions(+), 38 deletions(-)
[PATCH net v1 0/2] avoid compiler and IQ/OQ reordering
Posted by Vimlesh Kumar 1 month, 2 weeks ago
Utilize READ_ONCE and WRITE_ONCE APIs to prevent compiler
optimization and reordering. Ensure IO queue OUT/IN_CNT
registers are flushed. Relocate IQ/OQ IN/OUT_CNTS updates
to occur before NAPI completion, and replace napi_complete
with napi_complete_done.

Vimlesh Kumar (2):
  octeon_ep: avoid compiler and IQ/OQ reordering
  octeon_ep_vf: avoid compiler and IQ/OQ reordering

 .../ethernet/marvell/octeon_ep/octep_main.c   | 40 +++++++++++++------
 .../net/ethernet/marvell/octeon_ep/octep_rx.c | 27 +++++++++----
 .../marvell/octeon_ep_vf/octep_vf_main.c      | 38 +++++++++++++-----
 .../marvell/octeon_ep_vf/octep_vf_rx.c        | 28 +++++++++----
 4 files changed, 95 insertions(+), 38 deletions(-)

-- 
2.47.0