summaryrefslogtreecommitdiff
path: root/include/net
diff options
context:
space:
mode:
authorDavid S. Miller <davem@davemloft.net>2019-09-07 16:24:50 +0300
committerDavid S. Miller <davem@davemloft.net>2019-09-07 16:24:50 +0300
commit6938843dd8bba53147c12b625a567e2ea7e4e263 (patch)
tree0897384fe9baf3959a008536d44e358d9e9cc2c8 /include/net
parent742ca7812bcc96db59c9bf01ed64ff3f0f293189 (diff)
parent5c875c1af8dc69e64e0e457956b4271eac792733 (diff)
downloadlinux-6938843dd8bba53147c12b625a567e2ea7e4e263.tar.xz
Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queue
Jeff Kirsher says: ==================== 100GbE Intel Wired LAN Driver Updates 2019-09-05 This series contains updates to ice driver. Brett fixes the setting of num_q_vectors by using the maximum number between the allocated transmit and receive queues. Anirudh simplifies the code to use a helper function to return the main VSI, which is the first element in the pf->vsi array. Adds a pointer check to prevent a NULL pointer dereference. Adds a check to ensure we do not initialize DCB on devices that are not DCB capable. Does some housekeeping on the code to remove unnecessary indirection and reduce the PF structure by removing elements that are not needed since the values they were storing can be readily gotten from ice_get_avail_*_count()'s. Updates the printed strings to make it easier to search the logs for driver capabilities. Jesse cleans up unnecessary function arguments. Updated the code to use prefetch() to add some efficiency to the driver to avoid a cache miss. Did some housekeeping on the code to remove the configurable transmit work limit via ethtool which ended up creating performance overhead. Made additional performance enhancements by updating the driver to start out with a reasonable number of descriptors by changing the default to 2048. Mitch fixes the reset logic for VFs by clearing VF_MBX_ARQLEN register when the source of the reset is not PFR. Lukasz updates the driver to include a similar fix for the i40e driver by reporting link down for VF's when the PF queues are not enabled. Akeem updates the driver to report the VF link status once we get VF resources so that we can reflect the link status similarly to how the PF reports link speed. Ashish updates the transmit context structure based on recent changes to the hardware specification. Dave updates the DCB logic to allow a delayed registration for MIB change events so that the driver is not accepting events before it is ready for them. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/net')
0 files changed, 0 insertions, 0 deletions