RFC introduce new barrier class and use it for mlx5 PMD
Get series with b4
b4 am [email protected]Versions newest first
- v2 RFC Latest7 patches 4 repliesIn review
Patches in v2 No applies recorded yet
| # | Subject and files | Size | Replies | Applied |
|---|---|---|---|---|
| 1/7 | eal: introduce new class of barriers for DMA use caseslib/ lib/ lib/ +2 more | +55 | 0 replies | |
| 2/7 | net/mlx5: dmb for immediate doorbell ring on aarch64drivers/ | +1 | 0 replies | |
| 3/7 | net/mlx5: relax barrier to order UAR writes on aarch64drivers/ | +1 | 0 replies | |
| 4/7 | net/mlx5: relax barrier for aarch64drivers/ | +1 | 0 replies | |
| 5/7 | net/mlx5: add descriptive comment for a barrierdrivers/ | +5 | 0 replies | |
| 6/7 | net/mlx5: relax ordering for multi-packet RQ buffer refcntdrivers/ drivers/ drivers/ | +11 | 25 replies | |
| 7/7 | doc: clarify one configuration in mlx5 guidedoc/ | +4 | 0 replies |
Reviews trailers per patch
5 of 7 patches have a Reviewed-by or Acked-by of their own; the series has one for all of them.
| Patch | Steve Capper | Phil Yang | Gavin Hu | Ruifeng Wang | Jerin Jacob | David Christensen | Ajit Khaparde | Konstantin Ananyev | Alexander Kozyrev | Honnappa Nagarahalli | Viacheslav Ovsiienko |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Series | T-b T-b T-b T-b | A-b A-b A-b A-b A-b A-b A-b | R-b R-b | A-b A-b | A-b A-b | ||||||
| 1/7 | R-b | ||||||||||
| 2/7 | |||||||||||
| 3/7 | R-b | ||||||||||
| 4/7 | R-b | ||||||||||
| 5/7 | R-b | ||||||||||
| 6/7 | R-b | A-b A-b | R-b | A-b | |||||||
| 7/7 |
Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 11 reviewers.
Cover letter [dpdk-dev] [PATCH RFC v2 0/7] introduce new barrier class and use it for mlx5 PMD
To order writes to various memory types, 'sfence' is required for x86, and 'dmb oshst' is required for aarch64.
But within DPDK, there is no abstracted barriers covers this
combination: sfence(x86)/dmb(aarch64).
So introduce a new barrier class - rte_dma_*mb for this combination,
Doorbell rings are typical use cases of this new barrier class, which requires something ready in the memory before letting HW aware.
As a note, rte_io_wmb and rte_cio_wmb are compiler barriers for x86, while rte_wmb is 'dsb' for aarch64.
In the joint preliminary testing between Arm and Ampere, 8%~13% performance boost was measured.
As there is no functionality changes, it will not impact x86.
Gavin Hu (6):
eal: introduce new class of barriers for DMA use cases net/mlx5: dmb for immediate doorbell ring on aarch64 net/mlx5: relax barrier to order UAR writes on aarch64 net/mlx5: relax barrier for aarch64
net/mlx5: add descriptive comment for a barrier
doc: clarify one configuration in mlx5 guide
Phil Yang (1):
net/mlx5: relax ordering for multi-packet RQ buffer refcnt
doc/guides/nics/mlx5.rst | 6 ++-- drivers/net/mlx5/mlx5_rxq.c | 2 +- drivers/net/mlx5/mlx5_rxtx.c | 16 ++++++----- drivers/net/mlx5/mlx5_rxtx.h | 14 ++++++---- lib/librte_eal/arm/include/rte_atomic_32.h | 6 ++++ lib/librte_eal/arm/include/rte_atomic_64.h | 6 ++++ lib/librte_eal/include/generic/rte_atomic.h | 31 +++++++++++++++++++++ lib/librte_eal/ppc/include/rte_atomic.h | 6 ++++ lib/librte_eal/x86/include/rte_atomic.h | 6 ++++ 9 files changed, 78 insertions(+), 15 deletions(-)
Signature · 1 line
2.17.1