Add a single "Updated NXP DPAA drivers" entry for the changes made by
this series, with one sub-bullet each:
- FMCLESS mode now defaults to the maximum Rx queues per port instead
of the number of lcores
- the fmlib create_device() and get_device_id() helpers are renamed
with an fm_ prefix
- DMA devargs to control the existing scatter-gather batching, data
validation and ERR050757 programming at runtime
(dpaa_dma_sg_disable, dpaa_dma_data_validation,
dpaa_dma_pci_read_disable)
Signed-off-by: Hemant Agrawal <[email protected]>
---
doc/guides/rel_notes/release_26_11.rst | 17 +++++++++++++++++
1 file changed, 17 insertions(+)
diff --git a/doc/guides/rel_notes/release_26_11.rst
b/doc/guides/rel_notes/release_26_11.rst
index e027c7a27f..b8d3e41fcb 100644
--- a/doc/guides/rel_notes/release_26_11.rst
+++ b/doc/guides/rel_notes/release_26_11.rst
@@ -120,6 +120,23 @@ New Features
* Added Tx pause support for the ENETC4 VF via Rx congestion mode.
* Added WRR Tx scheduler devarg (``enetc4_txq_wrr``) for ENETC4 VF ring
weights.
+* **Updated NXP DPAA drivers.**
+
+ * Changed the default number of Rx queues in FMCLESS mode to the maximum
+ supported per port instead of the number of lcores, because several
+ queues may be processed on the same core.
+ * Renamed the fmlib ``create_device()`` and ``get_device_id()`` helpers to
+ ``fm_create_device()`` and ``fm_get_device_id()`` so that every global
+ symbol of the driver carries a prefix.
+ * Added device arguments to the DPAA QDMA driver to control existing
+ driver behaviour at runtime: ``dpaa_dma_sg_disable`` submits each
+ descriptor as an individual single-entry transfer instead of the
+ default scatter-gather batching, ``dpaa_dma_data_validation`` enables
+ the post-transfer data validation helper for debugging, and, when the
+ driver is built with ``RTE_DMA_DPAA_ERRATA_ERR050757``,
+ ``dpaa_dma_pci_read_disable`` skips the ERR050757 source
+ read-transaction programming.
+
* **Updated Solarflare network driver.**
* Added VF support on AMD Solarflare X45xx adapters.
--
2.25.1
